阅读说明：本技术 一种数据处理的方法、装置和存储介质 (Data processing method, device and storage medium ) 是由 郑章海 于 2020-05-29 设计创作，主要内容包括：本申请公开了一种数据处理的方法、装置和存储介质,具体为首先接收前端的会话请求,其中,会话请求携带第一会话标识,其次,读取已创建的问题单的第二会话标识,进一步地,遍历问题单,并在问题单对应的第二会话标识中检索是否存在与第一会话标识相同的第二会话标识,最后,当检索不到与第一会话标识相同的第二会话标识时,为当前的会话请求创建对应的问题单。本申请实施例通过检测前端会话请求是否存在缺失问题单,并自动进行创建,为实现客户问题单的自动创建,避免漏单,提升了客户服务体验。(The application discloses a data processing method, a data processing device and a storage medium, and particularly relates to a method for receiving a session request at a front end, wherein the session request carries a first session identifier, reading a second session identifier of a created question list, traversing the question list, searching whether a second session identifier same as the first session identifier exists in the second session identifier corresponding to the question list, and finally creating a corresponding question list for the current session request when the second session identifier same as the first session identifier does not exist. According to the embodiment of the application, whether the missing question list exists in the front-end session request or not is detected, and the missing question list is automatically created, so that the automatic creation of the customer question list is realized, the missing question list is avoided, and the customer service experience is improved.)

1. A method of data processing, comprising:

receiving a session request of a front end, wherein the session request carries a first session identifier;

reading a second session identifier of the created question sheet;

traversing the question list, and searching whether the second session identifier which is the same as the first session identifier exists in the second session identifier corresponding to the question list;

and when the second session identification which is the same as the first session identification is not retrieved, creating the corresponding question list for the current session request.

2. The method of claim 1, wherein between the step of receiving a session request of a front end and the step of reading a second session identifier of the created question ticket, the method further comprises:

recording a timestamp of when each of the session requests was received;

and when the first session identifications of at least two session requests are the same, retaining the session request corresponding to the timestamp closest to the current time and the first session identification.

3. The method of claim 1, wherein the step of creating the corresponding question ticket for the current session request comprises:

inputting the conversation request into a pre-trained question list prediction model, and generating the question list corresponding to the conversation request, wherein the question list comprises a question list type and a question list description.

4. The method of claim 3, wherein after the step of creating the corresponding question ticket for the current session request, the method further comprises:

judging whether the question list carries a question list follow-up mark or not, putting the question list into a client follow-up list queue when the question list carries the question list follow-up mark, and performing a closing operation on the question list which does not carry the question list follow-up mark when preset time is met.

5. An apparatus for data processing, the apparatus comprising:

the receiving module is used for receiving a session request of a front end, wherein the session request carries a first session identifier;

the comparison module is used for reading a second session identifier of the created question list;

the retrieval module is used for traversing the question list and retrieving whether the second session identifier which is the same as the first session identifier exists in the second session identifier corresponding to the question list;

and the creating module is used for creating the corresponding question list for the current session request when the second session identifier which is the same as the first session identifier is not retrieved.

6. The apparatus of claim 5, further comprising:

the recording module is used for recording the time stamp when each session request is received;

and the reservation module is used for reserving the session request and the first session identification corresponding to the timestamp closest to the current time when the first session identifications of at least two session requests are the same.

7. The apparatus of claim 5, wherein the creation module is configured to:

inputting the conversation request into a pre-trained question list prediction model, and generating the question list corresponding to the conversation request, wherein the question list comprises a question list type and a question list description.

8. The apparatus of claim 5, further comprising:

and the judging module is used for judging whether the question list carries a question list follow-up mark or not, putting the question list into a client follow-up list queue when the question list carries the question list follow-up mark, and performing order closing operation on the question list which does not carry the question list follow-up mark when preset time is met.

9. A non-transitory computer readable storage medium storing instructions that, when executed by a processor, cause the processor to perform the steps of a method of data processing according to any one of claims 1 to 4.

10. A terminal device, comprising a processor configured to perform the steps of a method of data processing according to any one of claims 1 to 4.

Technical Field

The present application relates to the field of electronic commerce technologies, and in particular, to a method, an apparatus, and a storage medium for data processing.

Background

Post-customer service has a critical position in e-commerce services. The after-market quality of service is closely related to the user's stickiness. Whether the customer service can solve the customer problem in time or not is a core element of after-sales service. The customer service will typically manually create and follow up customer questions on a session basis. In the case of a large amount of customer consultation, there may be a problem of missing customer problem tickets, causing a decrease in service quality.

Fig. 1 is a schematic diagram of an existing problem ticket creating architecture according to an embodiment of the present application. In which, a client 1 consults a customer service 1 through an instant messaging system (hereinafter referred to as IM system), and a session 1 is generated in the IM system. The customer service 1 creates a question list and follows to solve the customer problem based on the session of the IM system to the question list system. When the customer 2 consults the customer service 2, the customer is too late to create the question list, which may result in the customer problem not being followed continuously and may cause customer complaints.

Disclosure of Invention

The embodiment of the application provides a data processing method, and the problems that list omission can be caused due to the fact that list cannot be automatically created and customer service experience is reduced are solved.

The method comprises the following steps:

receiving a session request of a front end, wherein the session request carries a first session identifier;

reading a second session identifier of the created question sheet;

traversing the question list, and searching whether the second session identifier which is the same as the first session identifier exists in the second session identifier corresponding to the question list;

and when the second session identification which is the same as the first session identification is not retrieved, creating the corresponding question list for the current session request.

Optionally, recording a timestamp of when each of the session requests was received;

and when the first session identifications of at least two session requests are the same, retaining the session request corresponding to the timestamp closest to the current time and the first session identification.

Optionally, the session request is input into a pre-trained question list prediction model, and the question list corresponding to the session request is generated, wherein the question list includes a question list type and a question list description.

Optionally, whether the question list carries a question list follow-up identifier is judged, when the question list carries the question list follow-up identifier, the question list is placed in a client follow-up list queue, and when preset time is met, the question list which does not carry the question list follow-up identifier is subjected to a closing order operation.

In another embodiment of the present invention, there is provided an apparatus for data processing, the apparatus including:

the receiving module is used for receiving a session request of a front end, wherein the session request carries a first session identifier;

the comparison module is used for reading a second session identifier of the created question list;

a searching module, configured to traverse the question list, and search whether the second session identifier that is the same as the first session identifier exists in the second session identifier corresponding to the question list

And the creating module is used for creating the corresponding question list for the current session request when the second session identifier which is the same as the first session identifier is not retrieved.

Optionally, the apparatus further comprises:

the recording module is used for recording the time stamp when each session request is received;

and the reservation module is used for reserving the session request and the first session identification corresponding to the timestamp closest to the current time when the first session identifications of at least two session requests are the same.

Optionally, the creating module is configured to:

inputting the conversation request into a pre-trained question list prediction model, and generating the question list corresponding to the conversation request, wherein the question list comprises a question list type and a question list description.

Optionally, the apparatus further comprises:

and the judging module is used for judging whether the question list carries a question list follow-up mark or not, putting the question list into a client follow-up list queue when the question list carries the question list follow-up mark, and performing order closing operation on the question list which does not carry the question list follow-up mark when preset time is met.

In another embodiment of the invention, a non-transitory computer readable storage medium is provided, storing instructions that, when executed by a processor, cause the processor to perform the steps of one of the above-described methods of data processing.

In another embodiment of the present invention, a terminal device is provided, which includes a processor configured to execute the steps of a data processing method as described above.

Based on the above embodiment, first a session request of a front end is received, where the session request carries a first session identifier, then a second session identifier of a created question list is read, further, the question list is traversed, and whether a second session identifier identical to the first session identifier exists in the second session identifier corresponding to the question list is retrieved, and finally, when the second session identifier identical to the first session identifier is not retrieved, a corresponding question list is created for the current session request. According to the embodiment of the application, whether the missing question list exists in the front-end session request or not is detected, and the missing question list is automatically created, so that the automatic creation of the customer question list is realized, the missing question list is avoided, and the customer service experience is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.

FIG. 1 is a schematic diagram of an existing problem ticket creation architecture provided for embodiments of the present application;

FIG. 2 is a schematic diagram of an architecture for automatically creating a question sheet according to an embodiment of the present application;

fig. 3 is a schematic flow chart illustrating a method for data processing according to embodiment 100 of the present application;

fig. 4 is a schematic diagram illustrating a specific flow of a method for data processing according to an embodiment 200 of the present application;

FIG. 5 is a block diagram of an automatic creation system provided by an embodiment of the present application;

fig. 6 is a schematic diagram illustrating an apparatus for data processing according to an embodiment 600 of the present application;

fig. 7 shows a schematic diagram of a terminal device provided in embodiment 700 of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. 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 application.

The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprising" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements explicitly listed, but may include other steps or elements not explicitly listed or inherent to such process, method, article, or apparatus.

Based on the problems in the prior art, the embodiment of the application provides a data processing method, which is mainly applicable to the technical field of electronic commerce. Fig. 2 is a schematic diagram of an architecture for automatically creating a question list according to an embodiment of the present application. The method comprises the steps of monitoring conversation between a client and a customer service, detecting whether a user question is recorded or not, and automatically creating a question list through an automatic creation system when a missing question list is detected. The technical solution of the present invention is described in detail below with specific embodiments to implement a data processing method. Several of the following embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Fig. 3 is a schematic flowchart of a data processing method according to embodiment 100 of the present application. The detailed steps are as follows:

s11, receiving a session request of the front end, wherein the session request carries a first session identifier.

In this step, the user communicates with the customer service at the front end to trigger the generation of the session request. Specifically, when a user makes a conversation with a customer service in an instant messaging tool such as a customer service conversation page of an application program or a customer service conversation page of an e-commerce website, or through a telephone system, a conversation request is generated for each complete session, and a corresponding first session identifier is generated for the conversation request. Each session request carries a unique first session identification.

And S12, reading the second session identification of the created question list.

In this step, after receiving the session request sent by the front end, the processing system reads the second session identifier of the established question list in the question list system. Wherein the second session identifier is a unique identifier generated when a question sheet is generated for the session request.

And S13, traversing the question list, and searching whether a second session identifier identical to the first session identifier exists in a second session identifier corresponding to the question list.

Here, when a session request is received, traversing the read second session identifier of the question sheet corresponding to the session request, and comparing the second session identifier with the first session request identifier carried by the session request.

And S14, when the second conversation mark same as the first conversation mark is not searched, creating a corresponding question list for the current conversation request.

In this step, when traversing the question sheet is finished, a second session identifier that is the same as the first session identifier is not detected in the second session identifier, a corresponding question sheet and a second session identifier are created for the current session request corresponding to the first session identifier that is not detected currently, and the question sheet and the second session identifier are stored.

As described above, based on the above embodiment, first a session request of a front end is received, where the session request carries a first session identifier, then a second session identifier of a created question sheet is read, further, the question sheet is traversed, and whether a second session identifier identical to the first session identifier exists in the second session identifier corresponding to the question sheet is retrieved, and finally, when the second session identifier identical to the first session identifier is not retrieved, a corresponding question sheet is created for the current session request. According to the embodiment of the application, whether the missing question list exists in the front-end session request or not is detected, and the missing question list is automatically created, so that the automatic creation of the customer question list is realized, the missing question list is avoided, and the customer service experience is improved.

Fig. 4 is a schematic diagram illustrating a specific flow of a data processing method according to embodiment 200 of the present application. Wherein, the detailed process of the specific flow is as follows:

s201, receiving a session request of a front end.

Here, a corresponding session is generated based on the chat records of the client and the customer service in the time-keeping communication system or the telephone system, and a session request for the session is generated. Wherein the session request carries a unique first session identifier. The first session identification is generated based on session content corresponding to the session request, and when the session content is similar, the same first session identification is generated.

S202, invalid session requests in the session requests are filtered.

Here, the timestamp of each received session request is recorded, and when the first session identifier of at least two session requests is the same, the session request corresponding to the timestamp closest to the current time and the first session identifier are retained. In addition, a service blacklist can be set based on service needs, and text comparison and session filtering requests can be performed based on the service blacklist.

And S203, reading a second session identifier of the question sheet corresponding to the session request.

Here, for the session request for which the question list is already established, a second session identifier corresponding to the question list is generated at the same time when the question list is established, and is stored together with the question list. And when a session request of the front end is received, reading the question list and a second session identifier in the question list system.

S204, comparing the first session identification with the second session identification.

Here, it is compared whether the first session identification and the second session identification are identical.

And S205, when the second session identifier which is the same as the first session identifier cannot be searched in the second session identifier, creating a corresponding question list for the current session request.

Here, the session request is input into a pre-trained question list prediction model, and a question list corresponding to the session request is generated, wherein the question list comprises a question list type and a question list description. The method comprises the steps of obtaining information such as question bill classification and question bill description from a question bill prediction model according to a first session identifier of a session request, calling an interface of a question bill creating system to generate a question bill, and adding the question bill classification and the question bill description to the question bill. In addition, the question sheet prediction model can also output the question sheet order following identification of whether the conversation request needs to follow up. If the current question list is a commodity performance problem (such as specific performance configuration of a mobile phone), follow-up of manual customer service is not needed, namely, a question list follow-up mark is not generated; if the current question list is a commodity after-sale problem, manual customer service follow-up is generally required to be carried out, and a micro-order list following identifier is generated. Further, when the second session identification identical to the first session identification is not retrieved from the second session identification, the current session request is ended.

And S206, judging whether the question list carries the question list follow-up identification.

And S207, when the question sheet carries the question sheet follow-up identification, putting the question sheet into a client follow-up queue.

In this step, when the question list carries the question list follow-up identifier, it is determined that the question list needs to be followed up by the manual customer. Therefore, the question sheet is placed in the customer order queue.

And S208, performing order closing operation on the question list which does not carry the question list follow-up identification.

Here, when the preset time is satisfied, the order closing operation is performed on the question sheet which does not carry the question sheet follow-up mark.

The application realizes the data processing method based on the steps. A conversation is generated through the chat records of the client and the customer service in the instant messaging system or the telephone system, and a conversation request is generated. After receiving the session request, the automatic creation system performs timing detection to determine whether the session request is bound with the question sheet. And if the session request is not bound with the question list, performing an automatic creation process. And acquiring information such as a question bill follow-up identification, question bill classification, question bill description and the like in a question bill prediction model according to the session request, calling an interface of a question bill system to generate a question bill, and adding question classification and description on the question bill. Further, whether the question list needs to be followed is judged based on the question list follow-up identification. If the follow-up is needed, the question sheet is put into a customer service follow-up queue, and finally follow-up is carried out by manual customer service; if the follow-up is not needed, the question list is put into a timing order queue, and the system automatically orders the question list. According to the method, the omitted problem list is automatically created, the customer service labor cost is reduced, and the satisfaction degree of customer problems is improved. In addition, when the question list is created, the accurate classification and the problem description of the customer question list are calculated through the conversation interest and the problem prediction model, so that the understanding of customer service on the customer problems is improved, the effect of rapidly solving the customer problems is achieved, and the working efficiency of the customer service is improved.

Further, as shown in fig. 5, an embodiment of the present application also shows a module diagram of an automatic creation system. The method comprises the steps that a request module receives a conversation request generated by a timing communication system or a telephone system, and detects whether the conversation request is bound with a question list system; the filtering module is mainly used for filtering the session requests with invalid and blacklist configuration; the document creation module is mainly used for generating a question list in a question list system according to information provided by the message leaving module and the question list prediction model; the question list prediction model predicts question list classification and question list description according to the conversation content corresponding to the conversation request; the message leaving module supplements the question list description of the question list; the task module and the configuration module are mainly used for scheduling tasks and automatically creating configuration of the system respectively.

Based on the same inventive concept, embodiment 600 of the present application further provides an apparatus for data processing, where as shown in fig. 6, the apparatus includes:

a receiving module 61, configured to receive a session request from a front end, where the session request carries a first session identifier;

a comparison module 62, configured to read a second session identifier of the created question ticket;

the retrieval module 63 is configured to traverse the question list, and retrieve whether a second session identifier that is the same as the first session identifier exists in a second session identifier corresponding to the question list;

and a creating module 64, configured to create a corresponding question sheet for the current session request when a second session identifier identical to the first session identifier is not retrieved from the second session identifiers.

In this embodiment, specific functions and interaction manners of the receiving module 61, the comparing module 62, the retrieving module 63, and the creating module 64 can be referred to the record of the embodiment corresponding to fig. 1, and are not described herein again.

Optionally, the apparatus further comprises:

a recording module 65 for recording a timestamp when each session request is received;

a retaining module 66, configured to retain the session request and the first session identifier corresponding to the timestamp closest to the current time when the first session identifiers of at least two session requests are the same.

Optionally, the creating module 64 is configured to:

inputting the session request into a pre-trained question list prediction model, and generating a question list corresponding to the session request, wherein the question list comprises a question list type and a question list description.

Optionally, the apparatus further comprises:

the judging module 67 is used for judging whether the question list carries the question list follow-up identification, putting the question list into a client follow-up list queue when the question list carries the question list follow-up identification, and performing order closing operation on the question list which does not carry the question list follow-up identification when the preset time is met.

As shown in fig. 7, another embodiment 700 of the present application further provides a terminal device, which includes a processor 701, where the processor 701 is configured to execute the steps of the data processing method described above. As can also be seen from fig. 7, the terminal device provided by the above embodiment further includes a non-transitory computer readable storage medium 702, the non-transitory computer readable storage medium 702 having stored thereon a computer program, which when executed by the processor 701 performs the steps of the above-described method for data processing. In practice, the terminal device may be one or more computers, as long as the computer-readable medium and the processor are included.

In particular, the storage medium can be a general-purpose storage medium, such as a removable disk, a hard disk, a FLASH, and the like, and when the computer program on the storage medium is executed, the computer program can execute the steps of the data processing method. In practical applications, the computer readable medium may be included in the apparatus/device/system described in the above embodiments, or may exist alone without being assembled into the apparatus/device/system. The computer-readable storage medium carries one or more programs which, when executed, enable performance of the steps of a method of data processing as described above.

According to embodiments disclosed herein, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example and without limitation: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing, without limiting the scope of the present disclosure. In the embodiments disclosed herein, a computer 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 flowchart and block diagrams in the figures of the present application illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments disclosed herein. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Those skilled in the art will appreciate that various combinations and/or combinations of features recited in the various embodiments and/or claims of the present disclosure can be made, even if such combinations or combinations are not explicitly recited in the present application. In particular, the features recited in the various embodiments and/or claims of the present application may be combined and/or coupled in various ways, all of which fall within the scope of the present disclosure, without departing from the spirit and teachings of the present application.

Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present application, and are used for illustrating the technical solutions of the present application, but not limiting the same, and the scope of the present application is not limited thereto, and although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can still change or easily conceive of the technical solutions described in the foregoing embodiments or equivalent replacement of some technical features thereof within the technical scope disclosed in the present application; such changes, variations and substitutions do not depart from the spirit and scope of the exemplary embodiments of the present application and are intended to be covered by the appended claims. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.