阅读说明：本技术 信息校准检索方法、装置、计算机设备及可读存储介质 (Information calibration retrieval method and device, computer equipment and readable storage medium ) 是由 马明信 卢孟余 于 2020-12-25 设计创作，主要内容包括：本发明涉及人工智能,公开了一种信息校准检索方法、装置、计算机设备及可读存储介质,包括：获取输入信息；对所述输入信息进行拆分得到输入词条；提取所述输入词条中的文字词条,对所述文字词条进行校准得到待检索词条；调用搜索引擎根据所述待检索词条进行检索得到反馈信息。本发明还涉及区块链技术,信息可存储于区块链节点中。本发明保证了检索的文字词条的规范性,进而保证搜索引擎能够准确的检索到相应的反馈信息,以及避免了多个词条组合在一起导致检索匹配度下降的问题发生,提高了反馈信息检索的速度、准确度和匹配度。(The invention relates to artificial intelligence, and discloses an information calibration retrieval method, an information calibration retrieval device, computer equipment and a readable storage medium, wherein the information calibration retrieval method comprises the following steps: acquiring input information; splitting the input information to obtain an input entry; extracting the character entries in the input entries, and calibrating the character entries to obtain the entries to be retrieved; and calling a search engine to retrieve according to the entry to be retrieved to obtain feedback information. The invention also relates to a blockchain technique, where information can be stored in blockchain nodes. The invention ensures the normalization of the retrieved word entries, further ensures that the search engine can accurately retrieve the corresponding feedback information, avoids the problem of the reduction of retrieval matching degree caused by the combination of a plurality of word entries, and improves the speed, accuracy and matching degree of the feedback information retrieval.)

1. An information calibration retrieval method, comprising:

acquiring input information;

splitting the input information to obtain an input entry;

extracting the character entries in the input entries, and calibrating the character entries to obtain the entries to be retrieved;

and calling a search engine to retrieve according to the entry to be retrieved to obtain feedback information.

2. The method of information calibration retrieval according to claim 1, wherein before the obtaining the input information, the method further comprises:

sending an input template to the client;

the step of acquiring the input information includes:

acquiring input information input by the client in the input template;

the step of obtaining the input information further comprises:

and identifying the target text selected by the client, and setting the target text as input information.

3. The method for calibrating and retrieving information as claimed in claim 1, wherein the step of splitting the input information to obtain the input entries comprises:

splitting the input information by adopting a maximum matching method or a minimum segmentation method to obtain a character entry;

dividing the input information to obtain a first mixed entry by taking the character entries as separators, and segmenting the first mixed entry by adopting an English segmentation rule to obtain letter entries;

dividing the input information by taking the character entries and the letter entries as separators to obtain second mixed entries, and judging whether the second mixed entries reach a preset identification length or not;

if yes, judging that the mixed entry is a VIN code entry;

if not, judging that the mixed entry is an English number entry;

and summarizing the character entries, the letter entries, the VIN code entries and the English number entries to obtain input entries.

4. The method of claim 1, wherein after the splitting the input information to obtain the input entries, the method further comprises:

extracting VIN code entries in the input entries, and judging whether the digital information conforms to a preset VIN code rule; if yes, setting the digital information as a vocabulary entry to be retrieved; if not, sending digital error reporting information to the client;

and setting the letter entries and the English-number entries in the input entries as entries to be retrieved.

5. The method of claim 4, wherein the step of determining whether the digital information complies with a preset VIN code rule comprises:

acquiring a head code of the VIN code entry through a head regular expression;

identifying a VIN code rule corresponding to the VIN code vocabulary entry from a preset rule base according to the head code;

and judging whether the VIN code vocabulary entry accords with the VIN code rule.

6. The information calibration retrieval method of claim 1, wherein the step of calibrating the text entry to obtain the entry to be retrieved comprises:

calling a preset industry dictionary, and judging whether the word entries are the standard names recorded in the industry dictionary;

if yes, setting the character entries as entries to be retrieved;

if not, setting the standard name corresponding to the word entry in the industry dictionary as the entry to be retrieved.

7. The information calibration retrieval method of claim 1, wherein the step of calling the search engine to retrieve the entry to be retrieved to obtain the feedback information comprises:

judging whether the search engine is a conventional search engine or an intelligent search engine;

if the search engine is a conventional search engine, calling the search engine and retrieving by taking the entry to be retrieved as a keyword to obtain feedback information;

if the search engine is an intelligent search engine, acquiring a history record of the client from a database, enabling the search engine to take the entry to be retrieved as a keyword, and retrieving according to the history record to obtain feedback information;

after the search engine is called to retrieve according to the entry to be retrieved to obtain feedback information, the method further comprises the following steps:

and uploading the feedback information to a block chain.

8. An information calibration retrieval apparatus, comprising:

the input module is used for acquiring input information;

the splitting module is used for splitting the input information to obtain an input entry;

the calibration module is used for extracting the character entries in the input entries and calibrating the character entries to obtain the entries to be retrieved;

and the feedback module is used for calling a search engine to retrieve according to the entry to be retrieved to obtain feedback information.

9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the information calibration retrieval method according to any one of claims 1 to 7 are implemented by the processor of the computer device when executing the computer program.

10. A computer-readable storage medium, on which a computer program is stored, wherein the computer program stored in the computer-readable storage medium, when being executed by a processor, implements the steps of the information calibration retrieval method according to any one of claims 1 to 7.

Technical Field

The invention relates to the technical field of artificial intelligence voice semantics, in particular to an information calibration retrieval method, an information calibration retrieval device, computer equipment and a readable storage medium.

Background

The search engine is a one-door search technology which searches out formulated information from the internet by using a specific strategy and feeds the formulated information back to a user according to user requirements and a certain algorithm, and can search by acquiring some Chinese/English numbers input in an input box by a client and clicking for search.

The current search engine generally searches by using information input by a client as a keyword, however, the inventor finds that once the information has an irregular name or a search method using a plurality of words as a keyword, the searched information is often not in accordance with the search expectation of the user, and further the problem of low search accuracy occurs.

Disclosure of Invention

The invention aims to provide an information calibration retrieval method, an information calibration retrieval device, a computer device and a readable storage medium, which are used for solving the problem that in the prior art, when information has an irregular name or a retrieval method using a plurality of vocabularies as a keyword, the retrieved information is not in accordance with retrieval expectation of a user, and further retrieval accuracy is low.

In order to achieve the above object, the present invention provides an information calibration retrieval method, including:

acquiring input information;

splitting the input information to obtain an input entry;

extracting the character entries in the input entries, and calibrating the character entries to obtain the entries to be retrieved;

and calling a search engine to retrieve according to the entry to be retrieved to obtain feedback information.

In the above scheme, before the obtaining of the input information, the method further includes:

sending an input template to the client;

the step of acquiring the input information includes:

acquiring input information input by the client in the input template;

the step of obtaining the input information further comprises:

and identifying the target text selected by the client, and setting the target text as input information.

In the foregoing solution, the step of splitting the input information to obtain an input entry includes:

splitting the input information by adopting a maximum matching method or a minimum segmentation method to obtain a character entry;

dividing the input information to obtain a first mixed entry by taking the character entries as separators, and segmenting the first mixed entry by adopting an English segmentation rule to obtain letter entries;

dividing the input information by taking the character entries and the letter entries as separators to obtain second mixed entries, and judging whether the second mixed entries reach a preset identification length or not;

if yes, judging that the mixed entry is a VIN code entry;

if not, judging that the mixed entry is an English number entry;

and summarizing the character entries, the letter entries, the VIN code entries and the English number entries to obtain input entries.

In the above scheme, after the splitting of the input information to obtain the input entry, the method further includes:

extracting VIN code entries in the input entries, and judging whether the digital information conforms to a preset VIN code rule; if yes, setting the digital information as a vocabulary entry to be retrieved; if not, sending digital error reporting information to the client;

and setting the letter entries and the English-number entries in the input entries as entries to be retrieved.

In the foregoing solution, the step of determining whether the digital information conforms to a preset VIN code rule includes:

acquiring a head code of the VIN code entry through a head regular expression;

identifying a VIN code rule corresponding to the VIN code vocabulary entry from a preset rule base according to the head code;

and judging whether the VIN code vocabulary entry accords with the VIN code rule.

In the foregoing scheme, the step of calibrating the text entry to obtain the entry to be retrieved includes:

calling a preset industry dictionary, and judging whether the word entries are the standard names recorded in the industry dictionary;

if yes, setting the character entries as entries to be retrieved;

if not, setting the standard name corresponding to the word entry in the industry dictionary as the entry to be retrieved.

In the above scheme, the step of calling the search engine to retrieve the entry to be retrieved to obtain the feedback information includes:

judging whether the search engine is a conventional search engine or an intelligent search engine;

if the search engine is a conventional search engine, calling the search engine and retrieving by taking the entry to be retrieved as a keyword to obtain feedback information;

if the search engine is an intelligent search engine, acquiring a history record of the client from a database, enabling the search engine to take the entry to be retrieved as a keyword, and retrieving according to the history record to obtain feedback information;

after the search engine is called to retrieve according to the entry to be retrieved to obtain feedback information, the method further comprises the following steps:

and uploading the feedback information to a block chain.

In order to achieve the above object, the present invention further provides an information calibration retrieving apparatus, including:

the input module is used for acquiring input information;

the splitting module is used for splitting the input information to obtain an input entry;

the calibration module is used for extracting the character entries in the input entries and calibrating the character entries to obtain the entries to be retrieved;

and the feedback module is used for calling a search engine to retrieve according to the entry to be retrieved to obtain feedback information.

To achieve the above object, the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor of the computer device implements the steps of the above information calibration retrieval method when executing the computer program.

In order to achieve the above object, the present invention further provides a computer readable storage medium, which stores a computer program, and the computer program stored in the computer readable storage medium realizes the steps of the above information calibration retrieval method when executed by a processor.

According to the information calibration retrieval method, the information calibration retrieval device, the computer equipment and the readable storage medium, the input information is split to obtain the input entries capable of reflecting the meaning of the input information, and the technical effect of identifying the meaning expressed by the input information is achieved; the method comprises the steps of extracting word entries in the input entries, calibrating the word entries through an industry dictionary to obtain standard names corresponding to the word entries and setting the standard names as entries to be retrieved, so that the normalization of the obtained entries to be retrieved is guaranteed, the retrieval accuracy is further guaranteed, the normalization of the retrieved word entries is further guaranteed, and a search engine can be guaranteed to accurately retrieve corresponding feedback information. Therefore, the input information is split and the word entries in the input information are calibrated, so that the normalization of the entry to be retrieved is ensured, the problem that the retrieval matching degree is reduced due to the combination of a plurality of entries is solved, and the speed, the accuracy and the matching degree of feedback information retrieval are improved.

Drawings

FIG. 1 is a flowchart of a first embodiment of a method for calibrating and retrieving information according to the present invention;

FIG. 2 is a schematic diagram of an environmental application of the information calibration retrieving method according to a second embodiment of the information calibration retrieving method of the present invention;

FIG. 3 is a flowchart of a detailed method of an information calibration retrieving method according to a second embodiment of the information calibration retrieving method of the present invention;

FIG. 4 is a schematic diagram of program modules of a third embodiment of an information calibration and retrieval apparatus according to the present invention;

fig. 5 is a schematic diagram of a hardware structure of a computer device according to a fourth embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

The invention provides an information calibration retrieval method, an information calibration retrieval device, computer equipment and a readable storage medium, which are suitable for the technical field of artificial intelligent voice semantics and provide an information calibration retrieval method based on an input module, a splitting module, a calibration module, a feedback module, a template module, a verification module and an alphanumeric module. The method comprises the steps of splitting input information to obtain an input entry, extracting the character entries in the input entry, calibrating the character entries to obtain an entry to be retrieved, and calling a search engine to retrieve according to the entry to be retrieved to obtain feedback information.

The first embodiment is as follows:

referring to fig. 1, an information calibration retrieving method of the present embodiment includes:

s102: acquiring input information;

s103: splitting the input information to obtain an input entry;

s106: extracting the character entries in the input entries, and calibrating the character entries to obtain the entries to be retrieved;

s107: and calling a search engine to retrieve according to the entry to be retrieved to obtain feedback information.

In an exemplary embodiment, the input information is split to obtain an input entry capable of reflecting the meaning of the input information, so that the technical effect of identifying the meaning expressed by the input information is realized; the method comprises the steps of extracting word entries in the input entries, calibrating the word entries through an industry dictionary to obtain standard names corresponding to the word entries and setting the standard names as entries to be retrieved, so that the normalization of the obtained entries to be retrieved is guaranteed, the retrieval accuracy is further guaranteed, the normalization of the retrieved word entries is further guaranteed, and a search engine can be guaranteed to accurately retrieve corresponding feedback information. The search engine can be a conventional search engine created based on technologies such as keywords, crawlers and the like, and can also be an intelligent search engine created based on a machine learning algorithm; therefore, the input information is split and the word entries in the input information are calibrated, so that the normalization of the entry to be retrieved is ensured, the problem that the retrieval matching degree is reduced due to the combination of a plurality of entries is solved, and the speed, the accuracy and the matching degree of feedback information retrieval are improved.

Example two:

the embodiment is a specific application scenario of the first embodiment, and the method provided by the present invention can be more clearly and specifically explained through the embodiment.

The method provided in this embodiment is specifically described below by taking an example in which, in a server running an information calibration retrieval method, input information is split and calibrated to obtain a to-be-retrieved entry, and then retrieval is performed according to the to-be-retrieved entry to obtain feedback information. It should be noted that the present embodiment is only exemplary, and does not limit the protection scope of the embodiments of the present invention.

Fig. 2 schematically shows an environment application diagram of the information calibration retrieval method according to the second embodiment of the present application.

In an exemplary embodiment, the servers 2 where the information calibration retrieval method is located are respectively connected with the clients 4 through the network 3; the server 2 may provide services through one or more networks 3, which networks 3 may include various network devices, such as routers, switches, multiplexers, hubs, modems, bridges, repeaters, firewalls, proxy devices, and/or the like. The network 3 may include physical links, such as coaxial cable links, twisted pair cable links, fiber optic links, combinations thereof, and/or the like. The network 3 may include wireless links, such as cellular links, satellite links, Wi-Fi links, and/or the like; the client 4 may be a computer device such as a smart phone, a tablet computer, a notebook computer, and a desktop computer.

Fig. 3 is a flowchart illustrating an embodiment of a method for calibrating and retrieving information, the method includes steps S201 to S207.

The method specifically comprises the following steps:

s201: and sending the input template to the client.

In the step, the input template is sent to the client to ensure that the client can input information in a standardized way.

Optionally, an XML format file is used as the input template.

S202: input information is acquired.

In this embodiment, the step of acquiring the input information includes:

s21: and acquiring the input information input by the client in the input template.

In this embodiment, the step of obtaining the input information further includes:

s22: and identifying the target text selected by the client, and setting the target text as input information.

In this step, a target text selected or delineated by the client in the displayed text is identified, and the target text is set as input information to be retrieved.

S203: and splitting the input information to obtain an input entry.

In order to identify the meaning expressed by the input information, the step divides the input information to obtain an input entry capable of reflecting the meaning of the input information.

In a preferred embodiment, the step of splitting the input information to obtain the input entry includes:

s31: and splitting the input information by adopting a maximum matching method or a minimum segmentation method to obtain a character entry.

In this step, the maximum matching method is to use a dictionary as a basis, take the longest word in the dictionary as the scanning string of the first word taking number, and scan in the dictionary, for example: the longest word in the dictionary is 7 Chinese characters in total, and the maximum matching initial word number is 7 Chinese characters. Then decreasing the number word by word and searching in the corresponding dictionary.

In this embodiment, in order to improve the scanning efficiency, a plurality of dictionaries may be further designed according to the number of words, and then scanning is performed from different dictionaries according to the number of words, for example: a two-word dictionary containing two words, a three-word dictionary containing three words, and so on.

The maximum matching method comprises a forward maximum matching rule, a reverse maximum matching rule and a bidirectional maximum matching rule;

1. forward maximum matching rule:

the word is taken from front to back in the forward direction, from 7- >1, and one word is subtracted each time until the dictionary hits or 1 word remains.

1, time: "We are in wildlife", scan 7-word dictionary, none

And 2, time: "We are moving in the wild", scan 6-word dictionary, none

。。。。

The 6 th time: "We" scan a 2-word dictionary, having

Scanning is stopped, the 1 st word is output as 'us', and the 2 nd round scanning is started after the 1 st word is removed, namely:

and 2, scanning:

1, time: "play in the wild animal park", scan 7-word dictionary, have

And 2, time: in the wild zoo, 6-word dictionary is scanned, none

。。。。

The 6 th time: in the field, scan 2-word dictionary, have

Scanning is stopped, the 2 nd word is output as 'in the field', the 3 rd round scanning is started after the 2 nd word is removed, and the like.

2. Reverse maximum matching rule:

reverse, i.e. words are taken from back to front, and the other logic is the same as forward. Namely:

1, scanning: 'playing in wild animal park'

1, time: "play in the wild animal park", scan 7-word dictionary, have

And 2, time: play in wild zoo, scan 6-word dictionary, have

。。。。

And 7, time: "Play" and scan 1-word dictionary, have

Scanning is stopped, play is output, 1 is added to the word of the single word dictionary, and the 2 nd round of scanning is started

And 2, scanning: people in wild animal park "

1, time: "they are in the wild zoo", scan 7-word dictionary, do not

And 2, time: in the wild zoo, 6-word dictionary is scanned, none

And (3) time: "wild zoo", scan 5-word dictionary, have

Scanning is stopped, a 'wild zoo' is output, the 3 rd round scanning is started, and the like.

3. Bidirectional maximum matching rule:

the forward maximum matching method and the reverse maximum matching method both have limitations, the example is the limitation of the forward maximum matching method, the reverse direction also exists (for example, Changchun pharmacy, and reverse segmentation is 'Long/spring pharmacy'), so that the two-way maximum matching rules, namely, the two maximum matching rules are cut once, and then one word segmentation result is selected and output according to the principle that more words with large granularity are better, and the less words with non-dictionary words and single words are better.

Based on the above example: "we play in the wild zoo", using the positive maximum matching rule, the final segmentation result is: "we/in the field/live/thing/garden/play", wherein, two words are 3, the single dictionary word is 2, and the non-dictionary word is 1. And (3) adopting a reverse maximum matching rule, wherein the final segmentation result is as follows: "we/in/wilderness/play", where the five words are 1, the two words are 1, the single dictionary word is 2, and the non-dictionary word is 0. Non-dictionary words: forward (1) > reverse (0) (fewer is better), single word dictionary word: forward (2) is reverse (2) (the smaller the number, the better), and the total number of words: forward (6) > reverse (4) (fewer are better) so the final output is a reverse result.

S32: and taking the character entries as separators, segmenting the input information to obtain first mixed entries, and segmenting the first mixed entries by adopting an English segmentation rule to obtain letter entries.

The English word segmentation rule comprises the following steps: a space/symbol segmentation sub-rule which identifies spaces and symbols in the first mixed entry through a regular expression to segment the first mixed entry to obtain letter entries,

for example: segmenting the first mixed entry using the following code

And eliminating a stop word (stop word) sub-rule, wherein high-frequency words like a/an/and/are/then are used as stop words, and the first mixed entry is segmented by taking the stop words as separators to obtain letter entries.

The stem extraction (Stemming) sub-rule, say that an english word has a plurality of singular and plural variants, -ing and-ed, but should be treated as the same word when calculating the correlation. For example, if the applet and the applets are the same word, the applet is the stem, the going and the done are the same word, the do is the stem, and the stem in the first mixed entry is extracted as the letter entry, so as to avoid repeated retrieval of the same meaning from the vocabulary.

Any one of three algorithms including Porter Stemming, Lovins stemmer and Lancaster Stemming can be adopted to execute the stem extraction sub-rule.

S33: and dividing the input information by taking the character entries and the letter entries as separators to obtain second mixed entries, and judging whether the second mixed entries reach a preset identification length.

S34: if yes, the mixed entry is judged to be a VIN code entry

S35: if not, judging that the mixed entry is an English number entry;

s36: and summarizing the character entries, the letter entries, the VIN code entries and the English number entries to obtain input entries.

S204: extracting VIN code entries in the input entries, and judging whether the digital information conforms to a preset VIN code rule; if yes, setting the digital information as a vocabulary entry to be retrieved; and if not, sending digital error reporting information to the client.

In order to ensure that VIN code entries in the input entries accord with VIN code rules and accurate feedback information can be retrieved according to the VIN code entries, the accuracy of the VIN code entries is ensured by extracting the VIN code entries in the input entries and judging whether the digital information accords with the preset VIN code rules.

In a preferred embodiment, the step of determining whether the digital information conforms to a preset VIN code rule includes:

s41: and acquiring the head codes of the VIN code entries through the head regular expression.

In this step, the head regular expression is used to obtain a first character code, a second character code and a third character code in the VIN code entry;

wherein the first letter is an alphanumeric character designating a geographic region, such as africa, asia, europe, oceania, north america, and south america.

The second code is a letter or number that identifies a country within a particular region. In the United states, the Society of Automotive Engineers (SAE) is responsible for assigning country codes.

The third code is a letter or number designating a particular manufacturing plant and is assigned by authorities in various countries.

S42: and identifying a VIN code rule corresponding to the VIN code vocabulary entry from a preset rule base according to the head code.

Since the VIN code rules of different geographical areas, countries and manufacturers are different, the step of obtaining the geographical area, the country and the manufacturer of the VIN code according to the header code by storing the VIN code rules of different geographical areas, countries and manufacturers in the rule base, and identifying the VIN code rule matched with the VIN code from the rule base according to the geographical area, the country and the manufacturer so as to ensure the accuracy of VIN code verification.

S43: and judging whether the VIN code vocabulary entry accords with the VIN code rule.

In this step, the VIN code rule has a verification rule, where the verification rule is a weighted calculation formula obtained based on a world vehicle identification code (VIN) data manual, and the weighted calculation formula is used to calculate the words in the VIN code to obtain a weighted value, and determine whether the weighted value is consistent with the check digit in the VIN code, so as to achieve the technical effect of determining whether the VIN code vocabulary entry conforms to the VIN code rule.

In fig. 3, the S204 is shown by the following notation:

s204-1: extracting VIN code entries in the input entries, and judging whether the digital information conforms to a preset VIN code rule;

s204-2: if yes, setting the digital information as a vocabulary entry to be retrieved;

s204-3: and if not, sending digital error reporting information to the client.

S205: and setting the letter entries and the English-number entries in the input entries as entries to be retrieved.

Because the letter entries reflect English meanings with a certain specific meaning, the letter entries are directly set as entries to be retrieved; the English terms with numbers, single letters and the mixture of the numbers and the single letters have specific meanings for retrieval operation, and in order to ensure the retrieval efficiency of feedback information, the English terms are directly taken as the terms to be retrieved.

S206: and extracting the character entries in the input entries, and calibrating the character entries to obtain the entries to be retrieved.

In order to ensure the normalization of the retrieved word entries and ensure that a search engine can accurately retrieve corresponding feedback information, the step extracts the word entries in the input entry, calibrates the word entries through an industrial dictionary to obtain the normalized names corresponding to the word entries and sets the normalized names as the entries to be retrieved, so as to ensure the normalization of the obtained entries to be retrieved and further ensure the accuracy of retrieval.

In a preferred embodiment, the step of calibrating the text entry to obtain the entry to be retrieved includes:

s61: calling a preset industry dictionary, and judging whether the word entries are the standard names recorded in the industry dictionary;

s62: if yes, setting the character entries as entries to be retrieved;

s63: if not, setting the standard name corresponding to the word entry in the industry dictionary as the entry to be retrieved.

The industry dictionary is a computer dictionary created based on natural language processing technology, and comprises a standard name and colloquial, near-meaning words and ellipses consistent with the meaning of the standard name.

S207: and calling a search engine to retrieve according to the entry to be retrieved to obtain feedback information.

In this step, the search engine may be a conventional search engine created based on technologies such as keywords and crawlers, or may be an intelligent search engine created based on a machine learning algorithm.

In a preferred embodiment, the step of calling the search engine to retrieve the entry to be retrieved to obtain the feedback information includes:

s71: judging whether the search engine is a conventional search engine or an intelligent search engine;

s72: and if the search engine is a conventional search engine, calling the search engine and retrieving by taking the entry to be retrieved as a keyword to obtain feedback information.

S73: and if the search engine is an intelligent search engine, acquiring the history record of the client from a database, enabling the search engine to take the entry to be retrieved as a keyword, and retrieving according to the history record to obtain feedback information.

In the step, a historical retrieval record of the client is called, a key word in the historical retrieval record is obtained through a word frequency calculation algorithm, the key word is used as the entry to be retrieved to analyze the hot input and potential input objects of the client, so that the search engine retrieves the entry to be retrieved as a keyword to obtain feedback information, and further the matching degree and the relevance between the feedback information and the input information are improved

In this embodiment, a TF-IDF (term frequency-inverse document frequency) algorithm may be adopted as the term frequency calculation algorithm, and the TF-IDF algorithm includes two parts: TF (TF frequency) algorithm and IDF algorithm, wherein TF (term frequency) algorithm is used for counting the frequency of a word appearing in a Document, IDF (inverse Document frequency) algorithm is used for counting the number of documents of a Document set in which a word appears, and important words reflecting historical retrieval emphasis of a client are obtained through TF algorithm and IDF algorithm.

After the search engine is called to retrieve according to the entry to be retrieved to obtain feedback information, the method further comprises the following steps:

and uploading the feedback information to a block chain.

It should be noted that the corresponding digest information is obtained based on the feedback information, and specifically, the digest information is obtained by hashing the feedback information, for example, by using the sha256s algorithm. Uploading summary information to the blockchain can ensure the safety and the fair transparency of the user. The user equipment may download the summary information from the blockchain to verify whether the feedback information is tampered. The blockchain referred to in this example is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm, and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

Example three:

referring to fig. 4, an information calibration retrieving apparatus 1 of the present embodiment includes:

an input module 12 for acquiring input information;

the splitting module 13 is configured to split the input information to obtain an input entry;

the calibration module 16 is configured to extract a text entry in the input entry, and calibrate the text entry to obtain an entry to be retrieved;

and the feedback module 17 is used for calling a search engine to retrieve according to the entry to be retrieved to obtain feedback information.

Optionally, the information calibration and retrieval apparatus 1 further includes:

and the template module 11 is used for sending the input template to the client.

Optionally, the information calibration and retrieval apparatus 1 further includes:

the checking module 14 is configured to extract a VIN code entry in the input entry, and determine whether the digital information conforms to a preset VIN code rule; if yes, setting the digital information as a vocabulary entry to be retrieved; and if not, sending digital error reporting information to the client.

Optionally, the information calibration and retrieval apparatus 1 further includes:

and the letter-English module 15 is used for setting the letter entries and the English-number entries in the input entries as the entries to be retrieved.

The technical scheme is applied to the field of artificial intelligence voice semantics, input information is split through a natural language processing algorithm to obtain an input entry so as to realize semantic analysis, the character entries in the input entry are extracted, the character entries are calibrated to obtain entries to be retrieved, and a search engine is called to retrieve according to the entries to be retrieved to obtain feedback information.

Example four:

in order to achieve the above object, the present invention further provides a computer device 5, components of the information calibration and retrieval apparatus according to the third embodiment may be distributed in different computer devices, and the computer device 5 may be a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack server, a blade server, a tower server, or a rack server (including an independent server or a server cluster composed of a plurality of application servers) for executing programs. The computer device of the embodiment at least includes but is not limited to: a memory 51, a processor 52, which may be communicatively coupled to each other via a system bus, as shown in FIG. 5. It should be noted that fig. 5 only shows a computer device with components, but it should be understood that not all of the shown components are required to be implemented, and more or fewer components may be implemented instead.

In this embodiment, the memory 51 (i.e., a readable storage medium) includes a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the memory 51 may be an internal storage unit of the computer device, such as a hard disk or a memory of the computer device. In other embodiments, the memory 51 may be an external storage device of a computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like, provided on the computer device. Of course, the memory 51 may also include both internal and external storage devices of the computer device. In this embodiment, the memory 51 is generally used for storing an operating system and various application software installed on the computer device, such as the program code of the information calibration and retrieval apparatus in the third embodiment. Further, the memory 51 may also be used to temporarily store various types of data that have been output or are to be output.

Processor 52 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 52 is typically used to control the overall operation of the computer device. In this embodiment, the processor 52 is configured to run the program codes stored in the memory 51 or process data, for example, run the information calibration retrieving device, so as to implement the information calibration retrieving method of the first embodiment and the second embodiment.

Example five:

to achieve the above objects, the present invention also provides a computer readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application store, etc., on which a computer program is stored, which when executed by a processor 52, implements corresponding functions. The computer readable storage medium of the present embodiment is used for storing an information calibration retrieving apparatus, and when executed by the processor 52, the information calibration retrieving method of the first embodiment and the second embodiment is implemented.

The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.

Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner.

The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.