Data processing method and device, storage medium and electronic equipment

文档序号：1816635 发布日期：2021-11-09 浏览：26次中文

阅读说明：本技术 数据处理方法及装置、存储介质、电子设备 (Data processing method and device, storage medium and electronic equipment ) 是由王炜姚澜孙翠荣解忠乾罗川江于 2021-08-09 设计创作，主要内容包括：本公开的实施方式涉及计算机技术领域,更具体地,本公开的实施方式涉及数据处理方法及装置,存储介质和电子设备。所述方法包括：获取搜索文本；基于所述搜索文本确定对应的第一意图评分结果；其中,所述第一意图评分结果以离线方式获取；以及根据所述搜索文本对应的语法向量的编码特征和词向量的编码特征进行聚合处理,以根据聚合处理结果确定第二意图评分结果；结合所述第一意图评分结果和所述第二意图评分结果确定所述搜索文本的泛搜意图识别结果。本公开的方案在保证意图识别结果准确性的前提下,可以进一步的保证意图识别的效率,提升针对搜索文本的意图识别的速度。(Embodiments of the present disclosure relate to the field of computer technologies, and in particular, to a data processing method and apparatus, a storage medium, and an electronic device. The method comprises the following steps: acquiring a search text; determining a corresponding first intent scoring result based on the search text; wherein the first intention scoring result is obtained in an offline manner; performing aggregation processing according to the coding features of the grammar vectors and the coding features of the word vectors corresponding to the search texts to determine a second intention scoring result according to the aggregation processing result; determining a pan search intent recognition result for the search text in conjunction with the first intent scoring result and the second intent scoring result. According to the scheme, on the premise of ensuring the accuracy of the intention recognition result, the intention recognition efficiency can be further ensured, and the intention recognition speed for the search text is increased.)

1. A data processing method, comprising:

acquiring a search text;

determining a corresponding first intent scoring result based on the search text; wherein the first intention scoring result is obtained in an offline manner; and

performing aggregation processing according to the coding features of the grammar vectors and the coding features of the word vectors corresponding to the search texts to determine a second intention scoring result according to the aggregation processing result;

determining a pan search intent recognition result for the search text in conjunction with the first intent scoring result and the second intent scoring result.

2. The data processing method of claim 1, wherein the method further comprises:

determining heat information and intention information corresponding to the search text based on a pre-constructed entity dictionary, and determining a third intention recognition result according to the heat information and the intention information; for determining a pan search intent recognition result for the search text in conjunction with the first intent scoring result, the second intent scoring result, and the third intent recognition result.

3. The data processing method of claim 1, wherein the method further comprises:

performing first preprocessing on historical data of a search text to obtain a text to be processed in a target format;

extracting a text representation vector corresponding to the text to be processed by using a BERT model;

performing full-connection processing based on the text characterization vector to obtain an output two-dimensional vector;

and determining a first intention scoring result corresponding to the historical search text data according to the two-dimensional vector.

4. The data processing method of claim 3, wherein determining a corresponding first intent scoring result based on the search text comprises:

and querying historical search text data based on the search text to obtain matched historical search texts, and configuring first intention scoring results corresponding to the historical search texts as first intention scoring results corresponding to the current search text.

5. The data processing method of claim 1, wherein the performing an aggregation process based on the grammar vector corresponding to the search text and the coding features corresponding to the word vectors to determine a second intention scoring result according to the aggregation process result comprises:

performing second preprocessing on the search text;

performing word segmentation on the second preprocessing result, configuring corresponding identifications for each word segmentation result by using a preset single word dictionary, and constructing the word vector by using mapping values corresponding to each word segmentation result; and

splitting the second preprocessing result according to a preset granularity, configuring an identifier corresponding to each splitting result by using a preset grammar dictionary, and constructing the grammar vector by using the corresponding mapping value of the splitting result;

and sequentially performing convolution processing, pooling processing, normalization processing, aggregation processing and full-connection processing on the basis of the coding features corresponding to the grammar vectors and the coding features corresponding to the word vectors to obtain the second intention scoring result.

6. The data processing method according to claim 2, wherein the determining of the popularity information and the intention information corresponding to the search text based on a pre-constructed entity dictionary and the determining of a third intention recognition result according to the popularity information and the intention information comprises:

inquiring the entity dictionary according to the search text to obtain a corresponding matching result;

and calculating a third intention recognition result corresponding to the search text according to a preset heat value and a preset intention value corresponding to the matching result.

7. The data processing method according to claim 2 or 6, wherein the determining a pan search intention recognition result of the search text comprises:

when the intention information in the third intention recognition result is recognized to accord with a preset rule, and the heat information in the third intention recognition result is judged to be larger than or equal to a preset heat threshold value, determining that the search text is a non-extensive search intention; or

When the intention information in the third intention recognition result is recognized to accord with a preset rule, and the heat information in the third intention recognition result is judged to be smaller than a preset heat threshold value, calculating a probability value of the extensive search intention recognition result according to the first intention recognition result and the second intention recognition result; when the probability value reaches a preset threshold value, determining the search text as a general search intention; or

When the intention information in the third intention identification result is identified to be not in accordance with a preset rule, calculating a probability value of the extensive search intention identification result according to the first intention identification result and the second intention identification result; and when the probability value reaches a preset threshold value, determining the search text as a general search intention.

8. A data processing apparatus, comprising:

the request response module is used for acquiring a search text;

a first intention scoring result determination module for determining a corresponding first intention scoring result based on the search text; wherein the first intention scoring result is obtained in an offline manner; and

the second intention scoring result determining module is used for carrying out aggregation processing according to the coding features of the grammar vectors and the coding features of the word vectors corresponding to the search texts so as to determine a second intention scoring result according to the aggregation processing result;

and the recognition result output module is used for combining the first intention scoring result and the second intention scoring result to determine a pan search intention recognition result of the search text.

9. A storage medium having stored thereon a computer program, characterized in that the computer program, when executed by a processor, implements the data processing method of any one of claims 1 to 7.

10. An electronic device, comprising:

a processor; and

a memory for storing executable instructions of the processor;

wherein the processor is configured to perform the data processing method of any of claims 1-7 via execution of the executable instructions.

Technical Field

Embodiments of the present disclosure relate to the field of computer technologies, and in particular, to a data processing method and apparatus, a storage medium, and an electronic device.

Background

This section is intended to provide a background or context to the embodiments of the disclosure recited in the claims and the description herein is not admitted to be prior art by inclusion in this section.

In current technology, a user may obtain desired data content by entering a search request in a search engine. In a music search scenario, a user may enter a search request, such as text content, in a search box; the music search engine can search according to the characters input by the user and provide corresponding search results. When the music search engine or the background server searches data according to the content input by the user, whether the characters input by the user belong to the broad search intention can be judged according to intention identification.

Disclosure of Invention

However, in some technologies, the intention recognition usually can only give a recognition result of an accurate search request intention for a search request input by a user. For ambiguous search requests, the search engine recalls and sorts the results according to intention recognition, and accurate search results cannot be provided for such a broad intention search.

For this reason, an improved data processing method and apparatus, a storage medium, and an electronic device are highly needed to provide a solution capable of accurately identifying whether a search request of a user is a general search intention.

In this context, embodiments of the present invention are intended to provide a data processing method and apparatus, a storage medium, and an electronic device.

According to an aspect of the present disclosure, there is provided a data processing method including: acquiring a search text;

determining a corresponding first intent scoring result based on the search text; wherein the first intention scoring result is obtained in an offline manner; and

determining a pan search intent recognition result for the search text in conjunction with the first intent scoring result and the second intent scoring result.

In an exemplary embodiment of the present disclosure, the method further comprises:

In an exemplary embodiment of the present disclosure, determining a corresponding first intent scoring result based on the search text includes:

In an exemplary embodiment of the present disclosure, the performing an aggregation process based on the grammar vector corresponding to the search text and the coding features corresponding to the word vectors to determine a second intention scoring result according to an aggregation process result includes:

performing second preprocessing on the search text;

In one exemplary embodiment of the present disclosure,

in an exemplary embodiment of the present disclosure, the determining heat information and intention information corresponding to the search text based on a pre-constructed entity dictionary and determining a third intention recognition result according to the heat information and the intention information includes:

inquiring the entity dictionary according to the search text to obtain a corresponding matching result;

and calculating a third intention recognition result corresponding to the search text according to a preset heat value and a preset intention value corresponding to the matching result.

In an exemplary embodiment of the present disclosure, the determining the pan search intention recognition result of the search text includes:

In an exemplary embodiment of the present disclosure, the method further comprises:

acquiring updating data and updating a basic database based on the updating data;

screening the resource data in the basic database according to a preset heat threshold value to delete the resource data with the heat value smaller than the preset heat threshold value;

extracting a target field from each resource data in the basic database, and carrying out normalization processing on the target field to obtain an entity field; establishing an incidence relation between the entity field and the corresponding resource data;

and configuring the heat information and the intention information of the entity field based on the heat information and the intention information corresponding to the resource data with the incidence relation with the entity field, and constructing the entity dictionary according to the entity field.

In an exemplary embodiment of the present disclosure, in determining that the search text is the broad search intention, the method further includes:

and performing label association on the word segmentation result of the search text, and configuring a data label corresponding to the search text according to the label association result corresponding to the word segmentation result of the search text.

In an exemplary embodiment of the present disclosure, the performing, by the root, tag association on the word segmentation result of the search text, so as to configure a data tag corresponding to the search text according to the tag association result corresponding to the word segmentation result of the search text, includes:

performing word segmentation processing on the search text, and configuring corresponding tags for word segmentation results by using a preset service tag set so as to obtain a tag list corresponding to the word segmentation results of the search text;

performing text matching on a corresponding text coding result corresponding to the search text and a preset candidate resource to obtain a similar label result with the similarity degree larger than a preset threshold value;

and comparing the label list with the similar label result, and when the label list is matched with the matching result, configuring the label comparison result as a label result corresponding to the search text for performing data search based on the label result corresponding to the search text.

According to an aspect of the present disclosure, there is provided a data processing apparatus including:

the request response module is used for acquiring a search text;

In an exemplary embodiment of the present disclosure, the apparatus further includes:

the third intention recognition result determining module is used for determining heat information and intention information corresponding to the search text based on a pre-constructed entity dictionary and determining a third intention recognition result according to the heat information and the intention information; for determining a pan search intent recognition result for the search text in conjunction with the first intent scoring result, the second intent scoring result, and the third intent recognition result.

In an exemplary embodiment of the present disclosure, the apparatus further includes:

the first data processing module is used for carrying out first preprocessing on historical data of the searched text to obtain a text to be processed in a target format; extracting a text representation vector corresponding to the text to be processed by using a BERT model; performing full-connection processing based on the text characterization vector to obtain an output two-dimensional vector; and determining a first intention scoring result corresponding to the historical search text data according to the two-dimensional vector.

In an exemplary embodiment of the disclosure, the first intention scoring result determining module is configured to query the search text history data based on the search text to obtain a matching historical search text, and configure a first intention scoring result corresponding to the historical search text as a current first intention scoring result corresponding to the search text.

In an exemplary embodiment of the present disclosure, the second intention scoring result determining module includes: performing second preprocessing on the search text; performing word segmentation on the second preprocessing result, configuring corresponding identifications for each word segmentation result by using a preset single word dictionary, and constructing the word vector by using mapping values corresponding to each word segmentation result; splitting the second preprocessing result according to a preset granularity, configuring an identifier corresponding to each splitting result by using a preset grammar dictionary, and constructing the grammar vector by using the corresponding mapping value of the splitting result; and sequentially performing convolution processing, pooling processing, normalization processing, aggregation processing and full-connection processing on the basis of the coding features corresponding to the grammar vectors and the coding features corresponding to the word vectors to obtain the second intention scoring result.

In an exemplary embodiment of the present disclosure, the third intention recognition result determining module includes: inquiring the entity dictionary according to the search text to obtain a corresponding matching result; and calculating a third intention recognition result corresponding to the search text according to a preset heat value and a preset intention value corresponding to the matching result.

In an exemplary embodiment of the present disclosure, the recognition result output module includes:

the first identification module is used for determining that the search text is a non-extensive search intention when the intention information in the third intention identification result is identified to accord with a preset rule and the heat information in the third intention identification result is judged to be greater than or equal to a preset heat threshold;

a second identification module, configured to, when it is identified that the intention information in the third intention identification result conforms to a preset rule and it is determined that the heat information in the third intention identification result is smaller than a preset heat threshold, calculate a probability value of the general search intention identification result according to the first intention identification result and the second intention identification result; when the probability value reaches a preset threshold value, determining the search text as a general search intention;

a third identification module, configured to calculate a probability value of the extensive search intention identification result according to the first intention identification result and the second intention identification result when it is identified that the intention information in the third intention identification result does not conform to a preset rule; and when the probability value reaches a preset threshold value, determining the search text as a general search intention.

In an exemplary embodiment of the present disclosure, the apparatus further includes:

the entity dictionary building module is used for acquiring updating data and updating a basic database based on the updating data; screening the resource data in the basic database according to a preset heat threshold value to delete the resource data with the heat value smaller than the preset heat threshold value; extracting a target field from each resource data in the basic database, and carrying out normalization processing on the target field to obtain an entity field; establishing an incidence relation between the entity field and the corresponding resource data; and configuring the heat information and the intention information of the entity field based on the heat information and the intention information corresponding to the resource data with the incidence relation with the entity field, and constructing the entity dictionary according to the entity field.

In an exemplary embodiment of the present disclosure, the apparatus further includes:

and the tag matching module is used for performing tag association on the word segmentation result of the search text when the search text is determined to be the general search intention so as to configure the data tag corresponding to the search text according to the tag association result corresponding to the word segmentation result of the search text.

In an exemplary embodiment of the present disclosure, the tag matching module includes: performing word segmentation processing on the search text, and configuring corresponding tags for word segmentation results by using a preset service tag set so as to obtain a tag list corresponding to the word segmentation results of the search text; performing text matching on a corresponding text coding result corresponding to the search text and a preset candidate resource to obtain a similar label result with the similarity degree larger than a preset threshold value; and comparing the label list with the similar label result, and when the label list is matched with the matching result, configuring the label comparison result as a label result corresponding to the search text for performing data search based on the label result corresponding to the search text.

According to an aspect of the present disclosure, there is provided a storage medium having stored thereon a computer program which, when executed by a processor, performs the above-described data processing method.

According to an aspect of the present disclosure, there is provided an electronic device including:

a processor; and

a memory for storing executable instructions of the processor;

wherein the processor is configured to perform any one of the data processing methods described above via execution of the executable instructions.

According to the data processing method of the embodiment of the disclosure, after the search text of the user is acquired, the first intention scoring result aiming at the search text is acquired in an off-line mode, the corresponding second intention scoring result is calculated by utilizing the aggregation result of a plurality of coding features corresponding to the search text, and whether the current search text belongs to the pan search intention or not can be accurately judged by combining the intention scoring results acquired by utilizing two different calculation modes. In addition, the first intention scoring result with higher accuracy is obtained in an off-line mode, so that the intention identification efficiency can be further ensured on the premise of ensuring the accuracy of the intention identification result, and the intention identification speed for the search text is increased.

Drawings

The above and other objects, features and advantages of exemplary embodiments of the present disclosure will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. Several embodiments of the present disclosure are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which:

FIG. 1 schematically shows a flow diagram of a data processing method according to an embodiment of the invention;

FIG. 2 schematically shows a system architecture diagram of a data processing method according to an embodiment of the present invention;

FIG. 3 schematically shows a flow chart of a method of building a data dictionary in accordance with an embodiment of the present disclosure;

fig. 4 schematically shows a schematic structural diagram of a fully connected network according to an embodiment of the present disclosure;

FIG. 5 schematically illustrates a structural schematic of a neural network according to an embodiment of the present disclosure;

FIG. 6 is a system architecture diagram schematically illustrating a data processing method according to an embodiment of the present invention;

FIG. 7 schematically illustrates a diagram of a method of determining a flooding intent, according to an embodiment of the present disclosure;

FIG. 8 schematically illustrates a diagram of a method of tag association for search text of a broad search intent, according to an embodiment of the present disclosure;

FIG. 9 schematically shows a block diagram of a data processing apparatus according to an embodiment of the present disclosure;

FIG. 10 schematically illustrates a diagram of a search results interaction interface presentation in accordance with a method of an embodiment of the present disclosure;

FIG. 11 shows a schematic diagram of a storage medium according to an embodiment of the present disclosure; and

FIG. 12 schematically illustrates a block diagram of an electronic device in accordance with the disclosed embodiments.

In the drawings, the same or corresponding reference numerals indicate the same or corresponding parts.

Detailed Description

The principles and spirit of the present invention will be described with reference to a number of exemplary embodiments. It is understood that these embodiments are given solely for the purpose of enabling those skilled in the art to better understand and to practice the invention, and are not intended to limit the scope of the invention in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

As will be appreciated by one skilled in the art, embodiments of the present disclosure may be embodied as a system, apparatus, device, method, or computer program product. Accordingly, the present disclosure may be embodied in the form of: entirely hardware, entirely software (including firmware, resident software, micro-code, etc.), or a combination of hardware and software.

According to an embodiment of the present disclosure, a data processing method, a data processing apparatus, a storage medium, and an electronic device are provided.

In this document, any number of elements in the drawings is by way of example and not by way of limitation, and any nomenclature is used solely for differentiation and not by way of limitation.

The principles and spirit of the present disclosure are explained in detail below with reference to several representative embodiments of the present disclosure.

Summary of The Invention

The inventor finds that in application scenes of music search, news search, information search and the like, after a user inputs a text of information to be searched in a search box of an application program, a background can provide a corresponding search result to the user according to the input text content. In the recall stage, i.e., the process of screening out appropriate search results to the user according to certain conditions, intention recognition plays a crucial role. For the text content input by the user, firstly, judging whether the input text of the user belongs to a universal search intention according to intention identification, namely searching data meeting certain requirements; and if the search result belongs to the broad search intention, recalling and sequencing the resources corresponding to the text association with the broad search label, and displaying the final data search result. Taking a music application as an example, in some music search systems, for a search request (Query) input by a user, intention identification usually only gives an accurate identification result of the Query intention; and, the search system has weak support for such results of the broad intent search when recalling the ranking according to the intent recognition results. In some technologies, a text of a search request input by a user is treated in a unified manner with a text of a precise search, and when the search request currently input by the user is recalled and ordered according to a precise search intention, a search result can partially meet requirements only when the similarity between a general search intention text input by the user and a field corresponding to the search result is high. However, when the text of the current search request of the user is not clear search intention, for example, the search request is an intention of "good listening cantonese song" and the like which is not specifically directed to a certain song, the user actually wants to search for a song such as cantonese, rather than a certain song; at this time, if the user recalls in a precise intention manner, the user points to a certain song, and the obtained result is a song which literally contains characters such as cantonese and the like, which obviously does not meet the requirement of the user for broad search intention. In some technologies, when a call is made based on the title of a song using a DSSM (Deep Structured Semantic model) algorithm, characteristics such as the style and the type of the song cannot be effectively considered; recalling from the title or name of a song directly with a Query entered by the user does not meet the user's broad search intent requirements.

In view of the above, the basic idea of the present invention is: according to the data processing method and the data processing device, the search request of the user can be analyzed from multiple dimensions, whether the current search request is a general search intention or not is judged, and a corresponding intention scoring result is obtained; and combining the intention scoring results of multiple dimensions, thereby accurately judging whether the current search request of the user is a general search intention.

Having described the general principles of the invention, various non-limiting embodiments of the invention are described in detail below.

Exemplary method

A data processing method according to an exemplary embodiment of the present disclosure is described below with reference to fig. 1.

Referring to fig. 1, the data processing method may include the steps of:

s11, acquiring a search text;

s12, determining a corresponding first intention scoring result based on the search text; wherein the first intention scoring result is obtained in an offline manner; and

s13, performing aggregation processing according to the coding features of the grammar vectors and the coding features of the word vectors corresponding to the search texts, and determining a second intention scoring result according to the aggregation processing result;

s14, determining a pan search intention recognition result of the search text by combining the first intention scoring result and the second intention scoring result.

In the data processing method of the embodiment of the disclosure, after the search text of the user is obtained, on one hand, a first intention scoring result aiming at the search text is obtained in an off-line mode; on the other hand, the aggregation results of a plurality of coding features corresponding to the search text can be simultaneously utilized to calculate a corresponding second intention scoring result; therefore, whether the current search text belongs to the extensive search intention or not can be accurately judged by means of the intention scoring results obtained by two different calculation modes and novel combination. In addition, the first intention scoring result with higher accuracy is acquired in an off-line mode, so that the intention identification efficiency can be further ensured on the premise of ensuring the accuracy of the intention identification result, and the intention identification speed for the search text is increased.

Fig. 2 schematically shows a schematic diagram of an exemplary system architecture to which the technical solutions of the embodiments of the present disclosure may be applied. As shown in fig. 2, the system architecture may include a configuration terminal device 201 and a server 203. The terminal device can be an intelligent terminal device such as a mobile phone, a computer and a tablet computer. Data transmission is performed between the terminal device 201 and the server 203 via the network 202. The network may include various connection types, such as wired communication links, wireless communication links, and so forth. Wherein the number of terminal devices and servers in fig. 2 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation. For example, the server 203 may be a server cluster composed of a plurality of servers. The data processing method can be executed in a terminal device at a server side or a user side. Alternatively, the method can be executed by the server and the user terminal cooperatively.

In step S11, a search text is acquired.

In an exemplary embodiment of the present disclosure, taking an application of a music type as an example, the data processing method described above may be executed by a terminal device and a server in cooperation.

In a graphical user interface on a user-side terminal device, a search box may be provided in a music application. The user may enter text to be searched within the search box. When a user clicks a "search" or "ok" button in the graphical user interface, a search request may be created for the search text currently entered by the user. The search request may include a search text output by a user, and information such as a user identifier, a terminal device identifier, and time. For the search text, it may be first determined whether it is a general search intention. For example, the search text may be for a certain type of music, or for a certain language of music, etc. For example, the search text content input by the user may be "good-listening korean song".

Of course, in other exemplary embodiments of the present disclosure, the search text may also be search content for video, news, or other types of information.

In step S12, determining a corresponding first intention scoring result based on the search text; wherein the first intention scoring result is obtained in an offline manner.

In an exemplary embodiment of the present disclosure, for a search text input by a user, a corresponding first intention recognition result may be first acquired in an offline manner. Specifically, the text history data may be searched based on the search text query to obtain a matching history search text, and the first intention scoring result corresponding to the history search text may be configured as the first intention scoring result corresponding to the current search text.

In an exemplary embodiment of the present disclosure, a data dictionary based on history search data may be constructed in advance. Specifically, referring to fig. 3, the method may further include:

step S301, performing first preprocessing on historical data of a search text to acquire a text to be processed in a target format;

step S302, extracting a text representation vector corresponding to the text to be processed by using a BERT model;

step S303, performing full-connection processing based on the text representation vector to obtain an output two-dimensional vector;

step S304, determining a first intention scoring result corresponding to the search text historical data according to the two-dimensional vector.

For example, the search text history data described above may be search text history data of the entire users, not just the search history of the current user.

For each history search text entered by the user in the search history, a first pre-processing may be performed first. That is, a flag is added to the search text Query, and the processing obtains the expression form of [ CLS ] + Query + [ SEP ]. And then, loading the trained BERT model, taking the preprocessed search text as the input of the model, and extracting the text features of the text to be processed by using the BERT model. Then, acquiring 0 th-order characteristics of the acquired text characteristics, namely text representation of a CLS label part, and representing semantic vectors of the text; i.e. the text characterization vector described above. And inputting the semantic vector into a full-connection network, performing two-layer classification on the semantic vector through two full-connection layers, and performing normalization through a softmax layer to obtain two-dimensional vector output, so as to obtain a first intention identification result of whether the search text historical data is a universal search intention. Referring to fig. 4, the fully-connected network may include a first and a second fully-connected layers arranged in sequence; wherein, the fully-connected layer may include a sense layer and an overfitting (Dropout) layer; the sense layer in the first fully-connected layer may be configured with a size of 16; the sense layer in the second fully-connected layer may be configured with a size of 2; wherein the loss function may use a cross-entropy loss function.

After the corresponding pan search intention recognition result is calculated and determined for the historical search data in a period of time, a local and offline data dictionary of historical search data can be constructed according to the historical data. In some embodiments, the above-mentioned process of time-sufficient data dictionary may be completed by the server side, and the constructed data dictionary is issued to the terminal device, so that the terminal device can perform the calculation of the first intention scoring result in an off-line manner. Or, each terminal device may respectively construct a corresponding sub-data dictionary according to the history search record of the user in the terminal device, and then upload the sub-data dictionary to the server, and the server integrates the data and then issues the data to each terminal device. And the server side can update the data dictionary according to a certain period, so that the validity of the data dictionary is ensured, and the search text input by the user can obtain a corresponding and accurate first intention scoring result.

After receiving the current search text of the user, the terminal equipment can perform text matching on the text content of the user and each text in the data dictionary, so that the historical search text with the highest matching degree is screened out; and taking the first intention scoring result corresponding to the historical search text as the first intention scoring result corresponding to the current search text. Alternatively, if the matching historical search text cannot be searched in the data dictionary, the first intention scoring result may be set to null.

In step S13, an aggregation process is performed according to the encoding features of the grammar vector and the encoding features of the word vector corresponding to the search text, so as to determine a second intention scoring result according to the aggregation process result.

In an exemplary embodiment of the present disclosure, a second intention scoring result corresponding to the search text may be calculated in an online manner. Specifically, the step S13 may include:

step S131, carrying out second preprocessing on the search text;

step S132, performing word segmentation on the second preprocessing result, configuring corresponding identifications for each word segmentation result by using a preset single word dictionary, and constructing the word vector by using the mapping values corresponding to each word segmentation result; and

step S133, splitting the second preprocessing result according to a preset granularity, configuring the identifier corresponding to each split result by using a preset grammar dictionary, and constructing the grammar vector for the corresponding mapping value by using the split result;

step S134, performing convolution processing, pooling processing, normalization processing, aggregation processing and full-connection processing in sequence based on the coding features corresponding to the grammar vectors and the coding features corresponding to the word vectors to obtain the second intention scoring result.

Specifically, after the search text of the user is obtained, second preprocessing may be performed on the search text. For example, the second preprocessing may be special symbol processing, capital and lower case conversion of english, full angle and half angle conversion, and simplified and traditional character unification on the search text. For example, a special symbol or a special character in the search text may be deleted, or replaced with a specified text content; english in the text content can be capitalized; converting the character into a full-angle character; and converting complex font into corresponding simplified font.

After the second preprocessing is completed on the search text, a corresponding word vector (char embedding) and grammar vector (bigram embedding) may be calculated. Generally, in the deep learning method, a traditional text is converted into an id sequence through a mapping relation from a single word or a word to an id in a word list, and a representation vector is formed, namely, Embedding. The expression of Embedding is particularly important in deep learning training, and can digitize texts which cannot be directly transferred and learned by a machine, so that mathematical transformation of different network structures can be calculated in a deep learning network. In essence, the deep learning method is that a high-order function y ═ F (x) performs high-order parameter fitting on an input vector to obtain a mapping relation from an input value x to an output value y, the mapping relation from a text to an input value vector Embedding is determined by a constructed word list, and the Embedding expression is used as the basis of the deep learning method and can express non-numerical characteristics and input into numerical characteristics, so that a model can perform a series of numerical transformation.

Specifically, the word segmentation process may be performed on the second preprocessing result. For example, the search text of the user is "good-hearing korean song". Splitting based on single characters, and corresponding to 6 splitting results: "good", "listen", "of", "korean", "voice", "song". And then, a pre-constructed single word dictionary is utilized to inquire the mapping ID (identity) corresponding to each word segmentation result, namely the single word identification. For example, the single-word dictionary may be configured by a Corpus set Corpus ═ { q } configured based on a large number of querys₁，q₂，q_i，……q_nPerforming word segmentation on the Corpus set to obtain corresponding Corpus_Char＝{c₁，c₂，c_i，……c_m}; wherein m is the dimension of the defined single word dictionary. Giving each word a self-increment id identification through a single word dictionary to obtain Dict ═ c₁:1,c₂:2,c_i:i,c_mM, UNK 0 }; where UNK represents the default identification key of all words not in the dictionary.

Based on the pre-constructed single word dictionary, performing single word segmentation on the 'good-hearing Korean song' search text of the example, and inquiring the single word dictionary for the single word segmentation result to obtain identification data corresponding to each single word segmentation result; and then constructing a word vector corresponding to the search text according to each identification data. Wherein the dimension of the word vector can be configured to be 30. If the constructed word vector is less than 30 dimensions, it may be populated with the default representation "0".

In addition, after the second preprocessing is completed, after the word vector corresponding to the search text is constructed, or while the word vector is constructed, the grammar vector corresponding to the search text can also be constructed. For example, for the above-mentioned search text "good-listening korean song", word segmentation may be performed at a preset granularity. For example, if the length of the preset granularity is 2, the search text is split according to the granularity of two characters, and 5 two-character word segmentation results of "good hearing", "korean", and "song" are obtained as the corresponding split results. For each word segmentation result, a pre-constructed bigram (bigram) unit dictionary, namely the grammar dictionary can be utilized; and searching the dictionary and obtaining the identifier corresponding to each word segmentation result, and then constructing a grammar vector corresponding to the search text based on the identifiers of the word segmentation results. Wherein, the bigram unit dictionary, namely the grammar dictionary, can be constructed by utilizing large-scale corpora in advance; the construction process refers to the construction process of the word dictionary. For the above-mentioned syntax vector, the dimension of the vector can be configured to be 30. If the constructed word vector is less than 30 dimensions, it may be populated with the default representation "0".

After the word vector and the grammar vector corresponding to the search text are obtained, the word vector and the grammar vector can be used as input parameters, the online neural network model is input, and a corresponding second intention scoring result is output. Referring to fig. 5, the encoding features of word vectors and grammar vectors may be used as inputs, two inputs with different dimensions are normalized to a uniform dimension by a pooling layer (MaxPooling layer) of a neural network model, the outputs of the two MaxPooling layers are aggregated by a merging layer (conse), the aggregated result is further processed by a two-layer fully-connected network, and a two-classification result is obtained by a normalization layer (Softmax layer). Wherein the loss function may use a cross-entropy loss function. A Cross Entropy Loss function (Cross Entropy Loss) can be used to measure the difference between the predicted result distribution and the true annotated distribution; assume that M in the sample is the number of classes, y_icFor indicating variables, i.e. true label, i.e. 1 when the prediction class and the sample class are the same, otherwise 0, p_icIn order to observe the prediction probability that a sample belongs to a certain category, the corresponding Cross entry Loss function is as follows:

alternatively, in some other embodiments, the vector representation corresponding to the search text may also be calculated using the RNN model.

In step S14, a pan search intention recognition result of the search text is determined in combination with the first intention scoring result and the second intention scoring result.

In an exemplary embodiment of the disclosure, after the first intention scoring result and the second intention scoring result corresponding to the search text are obtained through calculation, the probability of whether the search text is the general search intention can be calculated according to the two results. Specifically, different weights may be configured for the two intention scoring results, respectively, and the pan-search intention recognition result may be calculated. For example, the formula may include:

Output＝Score_online*0.4+Score_offline*0.6

wherein, Score _ online is a second intention scoring result obtained in an online manner; score _ offline is a first intention scoring result obtained in an off-line manner. In addition, in other exemplary embodiments, other weighting ratios may be configured, such as 0.3 to 0.7, 0.25 to 0.75, etc.; the user-defined configuration can be specifically performed according to the application scene and the search correspondence.

Furthermore, in some exemplary embodiments of the present disclosure, the data processing method described above may further include: determining heat information and intention information corresponding to the search text based on a pre-constructed entity dictionary, and determining a third intention recognition result according to the heat information and the intention information; for determining a pan search intent recognition result for the search text in conjunction with the first intent scoring result, the second intent scoring result, and the third intent recognition result.

Specifically, referring to fig. 6, a data processing method provided may include:

step S61, acquiring a search text;

step S62, determining a corresponding first intention scoring result based on the search text; wherein the first intention scoring result is obtained in an offline manner; and

step S63, carrying out aggregation processing according to the coding features of the grammar vectors and the coding features of the word vectors corresponding to the search texts, so as to determine a second intention scoring result according to the aggregation processing result;

step S64, determining heat information and intention information corresponding to the search text based on a pre-constructed entity dictionary, and determining a third intention recognition result according to the heat information and the intention information;

step S65, determining a pan search intention recognition result of the search text in combination with the first intention scoring result, the second intention scoring result and the third intention recognition result.

In some exemplary embodiments of the present disclosure, the step S64 may include:

step S641 of inquiring the entity dictionary according to the search text to obtain a corresponding matching result;

step S642, calculating a third intention recognition result corresponding to the search text according to a preset heat value and a preset intention value corresponding to the matching result.

Specifically, an entity dictionary may be constructed in advance. Entities can be contained in the entity dictionary, and the heat value and intention value scores corresponding to the entities are contained; in addition, the entity name, the entity type, and the resource ID corresponding to each entity may also be included. For the search text of the user, one or more characteristic fields can be identified, the identified and output characteristic fields are used for searching the entity dictionary, and the associated heat information and intention information are obtained as an accurate third intention identification result.

In some exemplary embodiments, after the search text input by the user is acquired, the first intention scoring result and the second intention scoring result may be simultaneously calculated while the third intention recognition result is simultaneously calculated. Alternatively, in some exemplary embodiments, the third intention recognition result may also be calculated after the first intention scoring result and the second intention scoring result are obtained. For example, when the first intention recognition result is calculated to be null, the third intention recognition result may be calculated, so that the pan search intention recognition result of the search text may be calculated in combination with the second intention scoring result and the third intention scoring result. Alternatively, after the first intention scoring result and the second intention scoring result are obtained, whether to calculate the third intention recognition result may be determined according to other indexes.

In some exemplary embodiments of the present disclosure, the method of constructing an entity dictionary described above may include:

step S601, acquiring updating data and updating a basic database based on the updating data;

step S602, screening the resource data in the basic database according to a preset heat threshold value to delete the resource data with the heat value smaller than the preset heat threshold value;

step S603, extracting a target field from each resource data in the basic database, and performing normalization processing on the target field to obtain an entity field; establishing an incidence relation between the entity field and the corresponding resource data;

step S604, configuring the hot degree information and the intention information of the entity field based on the hot degree information and the intention information corresponding to the resource data with the incidence relation with the entity field, and constructing the entity dictionary according to the entity field.

Specifically, at the server side, the basic song database after the song library is updated can be regularly pulled every day according to the day-level updating data of the song library, and timely updating of the song entity information is guaranteed. Each piece of data in the basic database of the song may include ID and resource name of the resource, resource type, and related information such as popularity score and song library intention score. For example, as shown in table 1, the related information corresponding to the single song "staggered spatio-temporal" and the singer "playing" may include the following.

TABLE 1

For the basic database after the update point, the cold song resources such as single songs/singers/albums and the like can be filtered according to the heat information of the song library. For example, the entire resource in the music library may contain a singer 10 years ago, but this singer has never been searched by the user in the music application, and the popularity score is 0 or a small value, which is useless for searching information and requires filtering processing.

In addition, for the basic database after data filtering, a song resource name normalization process may be performed, and the resource ID and associated information are given in the song database, as shown in table 1. And the entity dictionary of songs requires entity-associated information as shown in table 2.

TABLE 2

In the song library data filtered according to the popularity, resource names such as single song names, song names and album names are respectively extracted from the resource name fields of the song library, the extracted resource names are subjected to text preprocessing operations such as case conversion and special Chinese character removal, entity names with text normalization are obtained, and then the resource types and resource ID information related to the entities are associated. For example, the singer resource name "SHE" is changed into "SHE" after text preprocessing; after the song "She" is subjected to text preprocessing, the song "She" is also changed into "She"; the normalized entity word "SHE" associates the entity types of the singer "SHE" and the song "SHE" in the song library, and the corresponding information of the intention score, the popularity value, the resource ID, and the like.

According to the information of the song library resources related to the entity,giving the entity a normalized score for the intent of a single song/singer/album, etc. For example, the entity "she" corresponds to a plurality of single song (song) resource IDs, including { ID }₁，id₂，id₃,}. And summing the original intention scores corresponding to the single song resource IDs to obtain a single song (song) intention score in the entity dictionary. The calculation formula may include:

in some exemplary embodiments of the present disclosure, after three intention recognition results are obtained through three different ways, the determination may be made in combination with the three intention recognition results. Specifically, referring to fig. 7, the step S65 may include:

In an exemplary embodiment of the present disclosure, after determining that the search text of the user is the general search intention, the method may further include: and performing label association on the word segmentation result of the search text, and configuring a data label corresponding to the search text according to the label association result corresponding to the word segmentation result of the search text.

Specifically, referring to fig. 8, the foregoing steps may specifically include:

step S81, performing word segmentation processing on the search text, and configuring corresponding tags for word segmentation results by using a preset service tag set to obtain a tag list corresponding to the word segmentation results of the search text;

step S82, performing text matching on the corresponding text coding result corresponding to the search text and a preset candidate resource to obtain a similar label result with the similarity degree larger than a preset threshold value;

step S83, comparing the label list with the similar label result, and when the label list is matched with the matching result, configuring the label comparison result as a label result corresponding to the search text, so as to perform data search based on the label result corresponding to the search text.

Specifically, for a search text with a general search intention, word segmentation processing may be performed first to obtain a tag word segmentation sequence of the search text, and the tag word segmentation sequence is mapped through a preset tag list to obtain a preliminary tag list. For the input search text, the corresponding text representation Query can be obtained by using BERT coding_encode. Obtaining label characterization Topic by BERT coding for all labels in candidate resource library_encode. And (4) recalling the most similar Topic by a similarity threshold control according to the text representation corresponding to the obtained search text through a faiss tool, and outputting if the most similar Topic is output, otherwise, outputting to be 0. For example, the search text is "good-hearing korean song", word segmentation is performed to obtain "good-hearing", "good", "korean" and "song", and a preliminary tag in the word segmentation result is "korean" through a preset service tag set. Then, calculating the text representation corresponding to the search text as Query_encode. The most similar Topic is obtained by the faiss tool_encodeObtaining the most similar label in Korean through a preset similarity threshold value of 0.8, and mapping the result with the first-step participleAnd if the labels are overlapped, determining that the final label is 'Korean', so that data search can be performed according to the label 'Korean', and displaying the search result to the user. For example, referring to the interactive interface shown in fig. 10, the search text input by the user is "good-hearing yue langue", after the search text is identified and determined as the intention identification by the above method, the tag corresponding to the search text is determined as "chinese-yue langue" by the above method, so that data search is performed by the tag, and the song search result is displayed in the interactive interface. For example, search result 1 recommended according to the label "chinese-cantonese" may be "favorite-wisdom min"; search result 2 may be "don't care-miss-shake full version"; search result 3 may be "kiss-forest-singing everywhere: yanqian "; and so on.

In summary, in the method provided by the present disclosure, after the search text is obtained, the corresponding first intention recognition result is obtained in an offline manner, and the corresponding second intention recognition result and the third intention recognition result are determined in an online manner. The evaluation result of whether the search text belongs to the general search intention or not is obtained in different dimensions through different calculation modes, and whether the search text belongs to the general search intention or not can be accurately identified. After the search text is determined to belong to the broad search intention, through carrying out tag association, tags more suitable for recall sequencing can be extracted to change semantic deviation texts possibly brought by directly recalling the original search text, so that the final search result meets the real broad search intention requirement of the user. The technical scheme of the application can be applied to music and video search in music application programs; the method can also be applied to the general search scenes in news information and financial application programs and the general search scenes of the videos in the video application programs.

Exemplary devices

Having introduced the data processing method of the exemplary embodiment of the present disclosure, next, a data processing apparatus of the exemplary embodiment of the present disclosure is described with reference to fig. 9.

Referring to fig. 9, a data processing apparatus 90 according to an exemplary embodiment of the present disclosure may include: a request response module 901, a first intention scoring result determining module 902, a second intention scoring result determining module 903 and a recognition result output module 904. Wherein the content of the first and second substances,

the request response module 901 may be configured to obtain a search text.

The first intent score result determination module 902 may be for determining a corresponding first intent score result based on the search text; wherein the first intention scoring result is obtained in an offline manner.

The second intention scoring result determining module 903 may be configured to perform aggregation processing according to the encoding features of the grammar vector and the encoding features of the word vector corresponding to the search text, so as to determine a second intention scoring result according to an aggregation processing result.

The recognition result output module 904 can be configured to determine a pan search intent recognition result for the search text in conjunction with the first intent scoring result and the second intent scoring result.

According to an exemplary embodiment of the present disclosure, the apparatus 90 may further include: a third intent recognition result determination module.

The third intention recognition result determining module may be configured to determine popularity information and intention information corresponding to the search text based on a pre-constructed entity dictionary, and determine a third intention recognition result according to the popularity information and the intention information; for determining a pan search intent recognition result for the search text in conjunction with the first intent scoring result, the second intent scoring result, and the third intent recognition result.

According to an exemplary embodiment of the present disclosure, the apparatus 90 may further include: a first data processing module.

The first data processing module can be used for performing first preprocessing on historical data of a search text to acquire a text to be processed in a target format; extracting a text representation vector corresponding to the text to be processed by using a BERT model; performing full-connection processing based on the text characterization vector to obtain an output two-dimensional vector; and determining a first intention scoring result corresponding to the historical search text data according to the two-dimensional vector.

According to an exemplary embodiment of the disclosure, the first intention scoring result determining module is configured to query the search text history data based on the search text to obtain a matched historical search text, and configure a first intention scoring result corresponding to the historical search text as a current first intention scoring result corresponding to the search text.

According to an exemplary embodiment of the present disclosure, the second intention scoring result determining module may include: performing second preprocessing on the search text; performing word segmentation on the second preprocessing result, configuring corresponding identifications for each word segmentation result by using a preset single word dictionary, and constructing the word vector by using mapping values corresponding to each word segmentation result; splitting the second preprocessing result according to a preset granularity, configuring an identifier corresponding to each splitting result by using a preset grammar dictionary, and constructing the grammar vector by using the corresponding mapping value of the splitting result; and sequentially performing convolution processing, pooling processing, normalization processing, aggregation processing and full-connection processing on the basis of the coding features corresponding to the grammar vectors and the coding features corresponding to the word vectors to obtain the second intention scoring result.

According to an exemplary embodiment of the present disclosure, the third intention recognition result determining module may include: inquiring the entity dictionary according to the search text to obtain a corresponding matching result; and calculating a third intention recognition result corresponding to the search text according to a preset heat value and a preset intention value corresponding to the matching result.

According to an exemplary embodiment of the present disclosure, the recognition result output module 904 may further include: the device comprises a first identification module, a second identification module and a third identification module. Wherein the content of the first and second substances,

the first identification module may be configured to determine that the search text is a non-extensive search intention when it is determined that the intention information in the third intention identification result conforms to a preset rule and it is determined that the popularity information in the third intention identification result is greater than or equal to a preset popularity threshold.

The second identification module may be configured to, when the intention information in the third intention identification result is identified to meet a preset rule and the heat information in the third intention identification result is determined to be less than a preset heat threshold, calculate a probability value of the general search intention identification result according to the first intention identification result and the second intention identification result; and when the probability value reaches a preset threshold value, determining the search text as a general search intention.

The third identification module may be configured to, when it is identified that the intention information in the third intention identification result does not comply with a preset rule, calculate a probability value of the general search intention identification result according to the first intention identification result and the second intention identification result; and when the probability value reaches a preset threshold value, determining the search text as a general search intention.

According to an exemplary embodiment of the present disclosure, the apparatus 90 may further include: and an entity dictionary construction module.

The entity dictionary construction module can be used for acquiring updating data and updating a basic database based on the updating data; screening the resource data in the basic database according to a preset heat threshold value to delete the resource data with the heat value smaller than the preset heat threshold value; extracting a target field from each resource data in the basic database, and carrying out normalization processing on the target field to obtain an entity field; establishing an incidence relation between the entity field and the corresponding resource data; and configuring the heat information and the intention information of the entity field based on the heat information and the intention information corresponding to the resource data with the incidence relation with the entity field, and constructing the entity dictionary according to the entity field.

According to an exemplary embodiment of the present disclosure, the apparatus 90 may further include: and a tag matching module.

The tag matching module may be configured to, when it is determined that the search text is the general search intention, perform tag association on a word segmentation result of the search text, so as to configure a data tag corresponding to the search text according to a tag association result corresponding to the word segmentation result of the search text.

According to an exemplary embodiment of the present disclosure, the tag matching module may include: performing word segmentation processing on the search text, and configuring corresponding tags for word segmentation results by using a preset service tag set so as to obtain a tag list corresponding to the word segmentation results of the search text; performing text matching on a corresponding text coding result corresponding to the search text and a preset candidate resource to obtain a similar label result with the similarity degree larger than a preset threshold value; and comparing the label list with the similar label result, and when the label list is matched with the matching result, configuring the label comparison result as a label result corresponding to the search text for performing data search based on the label result corresponding to the search text.

Since each functional module of the data processing apparatus according to the embodiment of the present disclosure is the same as that in the embodiment of the data processing method, it is not described herein again.

Exemplary storage Medium

Having described the data processing method and apparatus of the exemplary embodiments of the present disclosure, a storage medium of the exemplary embodiments of the present disclosure is explained next with reference to fig. 11.

Referring to fig. 11, a program product 1100 for implementing the above-described data processing method according to an embodiment of the present disclosure is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

A computer readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

Exemplary electronic device

Having described the storage medium of the exemplary embodiment of the present disclosure, next, an electronic device of the exemplary embodiment of the present disclosure is explained with reference to fig. 12.

The electronic device 800 shown in fig. 12 is only an example and should not bring any limitations to the function and scope of use of the embodiments of the present disclosure.

As shown in fig. 12, the electronic device 800 is embodied in the form of a general purpose computing device. The components of the electronic device 800 may include, but are not limited to: the at least one processing unit 810, the at least one memory unit 820, a bus 830 connecting different system components (including the memory unit 820 and the processing unit 810), and a display unit 840.

Wherein the storage unit stores program code that is executable by the processing unit 810 to cause the processing unit 810 to perform steps according to various exemplary embodiments of the present invention as described in the above section "exemplary methods" of the present specification. For example, the processing unit 810 may perform the steps as shown in fig. 1.

The memory unit 820 may include volatile memory units such as a random access memory unit (RAM)8201 and/or a cache memory unit 8202, and may further include a read only memory unit (ROM) 8203.

The storage unit 820 may also include a program/utility 8204 having a set (at least one) of program modules 8205, such program modules 8205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.

Bus 830 may include a data bus, an address bus, and a control bus.

The electronic device 800 may also communicate with one or more external devices 900 (e.g., keyboard, pointing device, bluetooth device, etc.), which may be through an input/output (I/O) interface 850. The electronic device 800 further comprises a display unit 840 connected to the input/output (I/O) interface 850 for displaying. Also, the electronic device 800 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the internet) via the network adapter 860. As shown, the network adapter 860 communicates with the other modules of the electronic device 800 via the bus 830. It should be appreciated that although not shown, other hardware and/or software modules may be used in conjunction with the electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

It should be noted that although in the above detailed description several modules or sub-modules of the audio playback device and the audio sharing device are mentioned, such division is merely exemplary and not mandatory. Indeed, the features and functionality of two or more of the units/modules described above may be embodied in one unit/module, in accordance with embodiments of the present disclosure. Conversely, the features and functions of one unit/module described above may be further divided into embodiments by a plurality of units/modules.

Further, while the operations of the disclosed methods are depicted in the drawings in a particular order, this does not require or imply that these operations must be performed in this particular order, or that all of the illustrated operations must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions.

While the spirit and principles of the invention have been described with reference to several particular embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, nor is the division of aspects, which is for convenience only as the features in such aspects may not be combined to benefit. The invention is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

27页详细技术资料下载

上一篇：一种医用注射器针头装配设备

下一篇：一种基于文本风格迁移技术的文字美化方法

Data processing method and device, storage medium and electronic equipment

相关技术

网友询问留言