CN111382252B

CN111382252B - Method, device, equipment and medium for determining problem category based on user request

Info

Publication number: CN111382252B
Application number: CN202010116522.3A
Authority: CN
Inventors: 林施扬; 邱岳亮; 王杰
Original assignee: Alipay Hangzhou Information Technology Co Ltd
Current assignee: Alipay Hangzhou Information Technology Co Ltd
Priority date: 2020-02-25
Filing date: 2020-02-25
Publication date: 2023-09-26
Anticipated expiration: 2040-02-25
Also published as: CN111382252A

Abstract

The embodiment of the specification discloses a problem category determining method based on a user request, which comprises the steps of obtaining the user request of a target user; if the history request record of the target user exists, carrying out intention recognition on the user request to obtain the target request intention of the user request; determining a target scene corresponding to the target request intention according to the history request record of the target user and the target request intention; determining a target customer service robot corresponding to the target scene according to the corresponding relation between the scene and the customer service robot, and sending the user request to the target customer service robot; and if the history request record of the target user does not exist, determining a target customer service robot corresponding to the user request from the M customer service robots according to at least one data of the target request intention and the embedded point information of the last service page, and sending the user request to the target customer service robot.

Description

Method, device, equipment and medium for determining problem category based on user request

Technical Field

The embodiment of the specification relates to the technical field of customer service data processing, in particular to a method, a device, equipment and a medium for determining a problem category based on a user request.

Background

With the rapid development of the electronic information industry, more and more services are applied to electronic devices, and the more services, the more services exist, the related services have relevance, so as to reduce the number of applications in the electronic devices, the integrated service platform is used for providing customer service for the related services.

The services provided by the existing integrated service platform are generally directly provided by relevant government departments or industry institutions in various places, the business logic and service conditions are different, and the integrated service platform needs to make enough business knowledge reserve and time cost to build an intelligent customer service system covering all incoming services, and the customer who will complain or consult usually manually guides the self customer service channel of the institution or industry service provider.

Disclosure of Invention

The embodiment of the specification provides a problem category determining method, device, equipment and medium based on a user request, which can improve the matching degree of a target customer service robot and the user request, and further improve the accuracy of responding to the user request.

A first aspect of embodiments of the present disclosure provides a method for determining a problem category based on a user request, including:

acquiring a user request of a target user;

if the history request record of the target user exists, carrying out intention recognition on the user request to obtain the target request intention of the user request; determining a target scene corresponding to the target request intention according to the history request record of the target user and the target request intention; according to the corresponding relation between the scene and the customer service robots, determining a target customer service robot corresponding to the target scene from M preset customer service robots, and sending the user request to the target customer service robot, wherein M is an integer greater than 1.

And if the history request record of the target user does not exist, determining a target customer service robot corresponding to the user request from the M customer service robots according to at least one data of the target request intention and the embedded point information of the last service page, and sending the user request to the target customer service robot, wherein the embedded point information of the last service page is carried in the user request.

A second aspect of embodiments of the present disclosure provides a method for determining a problem category based on a user request, which is applied to an integrated service platform, where the integrated service platform includes a platform customer service robot, and is capable of calling a three-party customer service robot that hosts a service provider of the integrated service platform, and a knowledge base content on which the three-party customer service robot depends is maintained by the service provider corresponding to the three-party customer service robot, where the method includes:

acquiring a user request of a target user;

performing intention recognition on the user request to obtain an intention recognition result;

if the history request record of the target user exists, determining a target scene corresponding to the user request according to the intention recognition result and the history request record of the target user;

if the history request record of the target user does not exist and the intention recognition result is that the target request intention is recognized, acquiring a target scene corresponding to the user request according to the corresponding relation between the preset request intention and the scene; if the intention recognition result is that the intention of the target request is not recognized and the user request carries embedded point information of the last service page, determining a target scene corresponding to the user request according to the embedded point information;

According to the corresponding relation between a preset scene and the customer service robot, selecting the platform customer service robot or a certain three-party customer service robot as a target customer service robot; and sending the user request to the target customer service robot.

A third aspect of embodiments of the present disclosure provides a method for determining a problem category based on a user request, including:

acquiring a user request of a target user;

if the history request record of the target user exists, determining a target scene corresponding to the user request according to the history request record of the target user and the target request intention;

according to the corresponding relation between a preset scene and the customer service robots, determining a target customer service robot corresponding to the target scene from M preset customer service robots, and sending the user request to the target customer service robot, wherein M is an integer greater than 1.

A fourth aspect of the embodiments of the present specification provides a problem category determining apparatus based on a user request, including:

a user request acquisition unit for acquiring a user request of a target user;

the target customer service robot determining unit is used for carrying out intention recognition on the user request if a history request record of the target user exists, so as to obtain a target request intention of the user request; determining a target scene corresponding to the target request intention according to the history request record of the target user and the target request intention; determining a target customer service robot corresponding to the target scene from M preset customer service robots according to the corresponding relation between the scene and the customer service robots, wherein M is an integer greater than 1; if the history request record of the target user does not exist, determining a target customer service robot corresponding to the user request from the M customer service robots according to at least one data of the target request intention and the embedded point information of the last service page, wherein the embedded point information of the last service page is carried in the user request

And the user request sending unit is used for sending the user request to the target customer service robot.

A fifth aspect of embodiments of the present disclosure provides a problem category determining device based on a user request, which is applied to an integrated service platform, where the integrated service platform includes a platform customer service robot, and is capable of invoking a three-party customer service robot that hosts a service provider of the integrated service platform, and content of a knowledge base relied on by the three-party customer service robot is maintained by the corresponding service provider, and includes:

a request acquisition unit for acquiring a user request of a target user;

the intention recognition unit is used for carrying out intention recognition on the user request and obtaining an intention recognition result;

a target scene determining unit, configured to determine, if there is a history request record of the target user, a target scene corresponding to the user request according to the intention recognition result and the history request record of the target user; if the history request record of the target user does not exist and the intention recognition result is that the target request intention is recognized, acquiring a target scene corresponding to the user request according to the corresponding relation between the preset request intention and the scene; if the intention recognition result is that the intention of the target request is not recognized and the user request carries embedded point information of the last service page, determining a target scene corresponding to the user request according to the embedded point information;

The target robot determining unit is used for selecting the platform customer service robot or a certain three-party customer service robot as a target customer service robot according to the corresponding relation between a preset scene and the customer service robot;

and the request sending unit is used for sending the user request to the target customer service robot.

A sixth aspect of embodiments of the present specification provides a problem category determining apparatus based on a user request, including:

the data acquisition unit is used for acquiring a user request of a target user;

the intention determining unit is used for carrying out intention recognition on the user request and obtaining an intention recognition result;

a scene determining unit, configured to determine, if there is a history request record of the target user, a target scene corresponding to the user request according to the history request record of the target user and the target request intention; if the history request record of the target user does not exist and the intention recognition result is that the target request intention is recognized, acquiring a target scene corresponding to the user request according to the corresponding relation between the preset request intention and the scene; if the intention recognition result is that the intention of the target request is not recognized and the user request carries embedded point information of the last service page, determining a target scene corresponding to the user request according to the embedded point information;

The robot determining unit is used for determining target customer service robots corresponding to the target scene from the preset M customer service robots according to the corresponding relation between the preset scene and the customer service robots, wherein M is an integer greater than 1;

and the sending unit is used for sending the user request to the target customer service robot.

The seventh aspect of the embodiments of the present disclosure further provides a problem category determining system based on a user request, including a client, a comprehensive service platform, and M customer service robots, where M is an integer greater than 1, including:

the client is used for acquiring input data of a target user, generating a user request and sending the user request to the comprehensive service platform;

the comprehensive service platform is used for receiving the user request sent by the client, and if a history request record corresponding to the target user exists, carrying out intention recognition on the user request to obtain a target request intention of the user request; determining a target scene corresponding to the target request intention according to the history request record of the target user and the target request intention; the method comprises the steps of carrying out a first treatment on the surface of the Determining a target customer service robot corresponding to the target scene from the M customer service robots according to the corresponding relation between the scene and the customer service robots, and sending the user request to the target customer service machine; if the buried point information carried by the user request is acquired; determining target customer service robots corresponding to the user requests from the M customer service robots according to the buried point information;

The target customer service robot is used for receiving the user request sent by the comprehensive service platform; responding to the user request to obtain a response result; and returning the response result to the client through the comprehensive service platform.

An eighth aspect of the embodiments of the present specification also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the above-described problem category determination method based on a user request when executing the program.

The ninth aspect of the embodiments of the present specification also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the above-described problem category determination method based on a user request.

The beneficial effects of the embodiment of the specification are as follows:

based on the technical scheme, after the user request of the target user is acquired, firstly, judging a history request record, and when the history request record exists, determining the target customer service robot according to the history request record and the target request intention identified by the intention, wherein the two constraint conditions enable the accuracy of the determined target customer service robot to be higher; even if the matching degree of the target customer service robot and the user request is higher, the accuracy of responding to the user request can be improved on the basis that the matching degree of the target customer service robot and the user request is higher.

In addition, in the absence of a history request record, according to at least one data in the embedded point information of the target request intention and the last service page, determining a target customer service robot, wherein the last service page is the last service page requested by the user, so that the relevance between the last service page and the user request is stronger, and on the basis of the stronger relevance, a service scene corresponding to the last service page is taken as the target scene, so that the relevance between the target scene and the user request is also enhanced; and on the basis of stronger relevance between the target scene and the user request, the relevance between the determined target customer service robot and the user request is also enhanced, so that the accuracy of the determined target customer service robot is further improved, namely, the matching degree of the target customer service robot and the user request is higher, and on the basis of higher matching degree of the target customer service robot and the user request, the accuracy of responding to the user request is also improved.

Drawings

FIG. 1 is a method flow diagram of a method for determining a problem category based on a user request in an embodiment of the present disclosure;

FIG. 2 is a flow chart of a method for determining when there is a history of target users in an embodiment of the present disclosure;

FIG. 3 is a flowchart of a first method for determining a method when there is no history request record of a target user in the embodiment of the present disclosure;

FIG. 4 is a second method flow of determining a method when there is no history request record of a target user in the embodiment of the present disclosure;

FIG. 5 is a schematic diagram of a problem category determination system based on user requests according to an embodiment of the present disclosure;

fig. 6 is a schematic diagram of a connection structure between a comprehensive service platform and M customer service robots in an embodiment of the present disclosure;

FIG. 7 is a schematic diagram illustrating a data processing structure of an integrated service platform according to an embodiment of the present disclosure;

fig. 8 is a schematic structural diagram of a problem category determining apparatus based on a user request in the embodiment of the present specification;

fig. 9 is a schematic structural diagram of an electronic device in an embodiment of the present disclosure.

Detailed Description

In order to better understand the technical solutions described above, the technical solutions of the embodiments of the present specification are described in detail below through the accompanying drawings and the specific embodiments, and it should be understood that the specific features of the embodiments of the present specification and the specific features of the embodiments of the present specification are detailed descriptions of the technical solutions of the embodiments of the present specification, and not limit the technical solutions of the present specification, and the technical features of the embodiments of the present specification may be combined without conflict.

In a first aspect, as shown in fig. 1, an embodiment of the present disclosure provides a method for determining a problem category based on a user request, including:

s102, acquiring a user request of a target user;

s104, if the history request record of the target user exists, acquiring the history request record of the target user; performing intention recognition on the user request to obtain a target request intention of the user request; determining a target scene corresponding to the target request intention according to the historical route data and scene configuration; according to the corresponding relation between the scene and the customer service robots, determining a target customer service robot corresponding to the target scene from M preset customer service robots, and sending the user request to the target customer service robot, wherein M is an integer greater than 1.

And S106, if the history request record of the target user does not exist, determining target customer service robots corresponding to the user request from the M customer service robots according to at least one of the target request intention and the embedded point information of the last service page, wherein the embedded point information of the last service page is carried in the user request.

The problem category determining method based on the user request, provided by the embodiment of the specification, is applied to a comprehensive service platform, and each customer service robot corresponds to at least one service, namely one customer service robot can process one or more services; further, the M customer service robots comprise platform customer service robots of the comprehensive service platform and third party customer service robots provided by third party service parties.

In the embodiment of the present disclosure, the integrated service platform may be a tablet computer, a notebook computer, a desktop computer, an integrated machine, a smart phone, or other devices; further, the client may be a tablet computer, a notebook computer, a desktop computer, an integrated machine, a smart phone, and other devices.

Specifically, when the third party service party includes an accumulation fund service party, a social security service party and a gas service party, the M customer service robots include an accumulation fund customer service robot provided by the accumulation fund service party, a social security customer service robot provided by the social security service party, a gas customer service robot provided by the gas service party and the platform customer service robot.

In the embodiment of the specification, the comprehensive service platform provides a unified customer service interface for unified intelligent customer service; enabling a user to enter the unified customer service interface through a third-party specific service page and a platform page of the comprehensive service platform, receiving input data of the user on the unified customer service interface by a client, and generating the user request according to the input data; and the client sends the generated user request to the comprehensive service platform, so that the comprehensive service platform obtains the user request.

In the embodiment of the present disclosure, the history request record of the target user and the user request of the target user may be a request generated in one session, where the target user sends multiple requests including the user request and the history request in one session; of course, the history of the target user request and the user request of the target user may be requests generated by the target user in multiple sessions.

The primary session in the embodiment of the present disclosure is specifically that a session is taken as a primary session when a user enters a unified customer service interface provided by the integrated service platform until the user exits the unified customer service interface, for example, the user enters the unified customer service interface at a first time and continues to exit at a second time, and at this time, interaction between the user and the unified customer service interface from the first time to the second time is taken as a primary session; and the user enters the unified customer service interface again at a third moment after the second moment and continuously exits at a fourth moment, and at the moment, the user interacts with the unified customer service interface from the third moment to the fourth moment to serve as another session. It is known that each user request is generated by the user and the integrated service platform in the session process.

Thus, in step S102, the user request sent by the client may be received first; the user request not only includes the input data, but also includes a target user identifier of the target user, where the user identifier may be a user I D, and the user request may correspond to any one of the N services.

In this embodiment of the present disclosure, after the connection between the client and the unified customer service interface is established, a session channel is established between the client and the integrated service platform, and the integrated service platform receives the user request sent by the client through the session channel.

Specifically, the user request further carries embedded point information of a previous service page, wherein the previous service page is a previous service page of the target user for accessing the unified customer service interface, the embedded point information comprises service subject information of the previous server page, and the service subject information comprises a subject of the previous server page. For example, the social security inquiry provided in the payment treasured city service edition is provided by various social security offices, and when the user has a question about the content of the inquiry, the object to be consulted is the local social security office providing the social security inquiry, and the social security office is the service subject.

In the embodiment of the specification, the comprehensive service platform buries the scene of the user before entering the unified customer service interface, namely buries the previous service page of each user before accessing the unified customer service interface, is used for collecting the buries information of the previous service page, and writes the buries information into the user request of the user; thus, the previous service page accessed before the target user accesses the unified customer service interface is the last service page, and point embedding is performed in the process of accessing the last service page by the target user; according to the embedded point in the process of accessing the last service page by the target user, the embedded point information of the target user for accessing the last service page can be obtained; in this way, in the process of generating the user request according to the input data, the user request can be generated according to the input data and the embedded point information; the embedded point information of the previous service page may also be directly written into the user request after the user request is generated, which is not particularly limited in this specification.

For example, a b city public deposit service page displayed on a client side by a target user a enters the unified customer service interface, input data of a in the unified customer service interface is "the public deposit account password is forgotten", and a user request of a is generated according to the "the public deposit account password is forgotten", wherein the user request of a carries data of "the public deposit account password is forgotten", and carries a user I D of a is 10258, for example, and carries embedded point information of a for accessing the b city public deposit service page; and then the client sends the user request of a to the comprehensive service platform, so that the comprehensive service platform obtains the user request of a.

After executing step S102, it may also be detected whether a history request record of the target user exists in a platform database of the integrated service platform, and if the history request record of the target user exists in the platform database, step S104 is executed; if the history request record of the target user does not exist in the platform database, step S106 is executed.

In this embodiment of the present disclosure, the platform database may be electronic devices such as a desktop computer, a notebook computer, a smart phone, and an all-in-one machine, where a history request record of a history user is stored in the platform database, where the history user is a user before the target user accesses the integrated service platform, and the history request record records user request data, a subsequent processing result, and response content of the customer service robot; at this time, the history request record of each history user can be associated with the user identification of the history user, so that the multiplexing of the user requests of the subsequent rounds is facilitated.

Specifically, after the user request is obtained in step S102, according to the target user identifier carried in the user request, the target user identifier is used as search content, and whether a history request record corresponding to the target user identifier exists in the platform database is searched; at this time, whether a history request record corresponding to the target user identifier exists or not may be queried in the session record where the user request exists, or whether history request records corresponding to the target user identifier are queried in all session records stored in the platform database.

At this time, when the history request record corresponding to the target user identifier exists in the session record where the user request exists, if the history request record exists, determining that the history request record of the target user exists in the platform database, and then executing step S104; if no history request record exists, it is determined that no history request record of the target user exists in the platform database, and then step S106 is performed.

Further, when a history request record corresponding to the target user identifier is queried in all session records stored in the platform database, if the history request record is queried, determining that the history request record of the target user exists in the platform database, and then executing step S104; if no history request record exists, it is determined that no history request record of the target user exists in the platform database, and then step S106 is performed.

If it is detected that the history request record of the target user exists in the platform database, step S104 includes the following steps, see fig. 2, specifically as follows:

step S1042, obtaining a history request record of the target user;

Specifically, according to the target user identifier, a history request record of the target user can be searched from the platform database; if the history request records in the integrated service platform exist in an external database, the history request records of the target user can be searched from the external database.

Step S1044, performing intention recognition on the user request to obtain a target request intention of the user request;

specifically, the user request may be intent identified using a trained natural language understanding (Natural Language Understanding, simply: NLU) model to obtain the target request intent.

Specifically, the trained NLU model may be obtained by training a plurality of history request records, and as the number of users accessing the integrated service platform increases, the trained NLU model may be iterated and optimized by using the history request records corresponding to the increased users, so that the trained NLU model may be optimized along with the increase of the user access amount, and the result identified by the optimized trained NLU model is more accurate.

Step S1046, determining a target scene corresponding to the target request intention according to the history request record of the target user and the target request intention.

Specifically, the corresponding relation between the historical request intention of the target user and the historical conversation scene can be obtained according to the historical request record of the target user, whether the intention identical to the target request intention exists in the historical request intention or not is detected, and if so, the target scene is obtained according to the corresponding relation between the historical request intention and the historical conversation scene; if the target scene does not exist, acquiring the target scene according to a preset map corresponding table and the target request intention; therefore, the target scene can be identified more quickly and accurately through the corresponding relation between the historical request intention and the historical conversation scene in the historical request record, and the accuracy of the identified target customer service robot can be improved on the basis that the identified target scene is improved.

Specifically, the scene corresponding to the target request intention may be searched from the view correspondence table as the target scene with the target request intention as a search condition.

Step S1048, determining a target customer service robot corresponding to the target scene according to the preset correspondence between the scene and the customer service robot, and sending the user request to the target customer service robot.

In the embodiment of the present disclosure, the platform database may be preset with the map corresponding table, and the corresponding relationship between the scene and the customer service robot may be stored in the platform database through the Jing Fu corresponding table; thus, the target customer service robot corresponding to the target scene can be obtained according to the map scene corresponding table and the scene service corresponding table; then, obtaining the route information of the target customer service robot, and sending the user request to the target customer service robot through the route information of the target customer service robot; and after the target customer service robot acquires the user request, responding to the user request to obtain a response result, and returning the response result to the client corresponding to the user request.

Specifically, the account abnormal intention corresponds to a platform service scene, the b1 city public accumulation fund account query intention corresponds to a b1 city public accumulation fund service scene, and the b2 city social security account password abnormal intention corresponds to a b2 city social security service scene; correspondingly, the Jing Fu corresponding table comprises that the platform service scene corresponds to the platform customer service robot, the b1 city public accumulation service scene corresponds to the b1 city public accumulation customer service robot, and the b2 city social security service scene corresponds to the b2 city social security customer service robot.

For example, after receiving the user request of a sent by the client, the integrated service platform firstly uses the user ID 10258 carried in the user request of a to query in the platform database, and at this time, whether a history request record with the ID 10258 exists in the session record where the user request of a exists or whether a history request record with the ID 10258 exists in all the session records stored in the platform database can be queried; if the history request record with the ID of 10258 is inquired, the history request record with the ID of 10258 is obtained, then intention recognition is carried out on a user request (the password of the public accumulation account is forgotten) of a through a trained NLU model, and the target request intention of a is the abnormal intention of the password of the public accumulation account of b city.

Further, according to the history request record with the ID of 10258, determining the corresponding relation between the history request intention with the ID of 10258 and the history session scene, and if the corresponding relation between the b city public accumulation account password abnormal intention and the b city public accumulation service exists in the corresponding relation, acquiring a target scene corresponding to the user request with the ID of 10258 from the corresponding relation as the b city public accumulation service; and searching a target customer service robot corresponding to the b city public accumulation fund service from the corresponding table of the scene service by taking the b city public accumulation fund service as a search condition according to the corresponding table of the scene service stored in the platform database.

Of course, if the corresponding relation between the historical request intention with the ID 10258 and the historical session scene is determined according to the historical request record with the ID 10258, and then if the target scene corresponding to the user request with the ID 10258 is not obtained from the corresponding relation, the target scene of a may be obtained according to the view corresponding table in the platform database and the target request intention of a; and then obtaining the target customer service robot of a as the b city public accumulation customer service robot according to the target scene of a and the scene service corresponding table in the platform database.

Further, after the target customer service robot is the b city public accumulation service robot, sending a user request of a to the b city public accumulation service robot according to the routing information of the b city public accumulation service robot, responding to the user request of a by the b city public accumulation service robot, and returning a response result to a client where the user request of a is generated.

In addition, if the input data carried by the user request of a is "how the account cannot be logged in" so as to hit the account abnormal intention, then searching a scene corresponding to the account abnormal intention from the intention corresponding table as a platform service scene, and searching a customer service robot corresponding to the platform service scene from the map service corresponding table as a platform customer service robot, at this time, although the user a enters a unified customer service interface of the comprehensive service platform from the b city public accumulation page, the user request of a is sent to the platform customer service robot instead of the b city public accumulation service robot; and then the platform customer service robot responds to the user request of a, and returns a response result to the client where the user request of a is generated.

In this way, after the user request of the target user is obtained, firstly, historical request record judgment is carried out, and when the historical request record exists, the target request intention identified according to the historical request record and the intention is determined according to the two constraint conditions, so that the accuracy of the determined target customer service robot is higher; and determining the target customer service robot according to the embedded point information of the last service page carried in the user request when the history request record does not exist, so that the target customer service robot is determined according to the embedded point information of the last service page, and further, the accuracy of the determined target customer service robot is higher, namely, the matching degree of the target customer service robot and the user request is higher, and the accuracy of responding to the user request can be improved on the basis that the matching degree of the target customer service robot and the user request is higher.

If no history request record corresponding to the target user identifier is searched from the platform database, determining that no history request record of the target user exists in the platform database, and then executing step S106, where in the process of executing step S106, since no history request record of the target user exists in the platform database, it may be determined that the target user accesses the integrated platform server for the first time, where the steps may include the following steps, as shown in fig. 3:

Step S302, carrying out intention recognition on the user request.

Specifically, the trained NLU model may be used to identify the intent of the user request, and determine whether the identified intent is any of a plurality of preset intents; if the identified intention is any one of the preset intents, taking the identified intention as the target request intention, and then sequentially executing steps S304-S306; if it is determined that the identified intention is not any one of the plurality of preset intents, it is determined that the target request intention of the user request is not identified, and then steps S404 to S406 are sequentially performed.

For example, the plurality of preset intents include an account abnormal intention, an public accumulation account query intention, a social security account password abnormal intention and a gas account query intention, if the user request of the user a1 is identified by the NLU model, the identified intention is a tax query intention, and since the tax query intention is not among the plurality of preset intents, steps S404 to S406 are further executed; if the user request of the user a1 is identified by the NLU model, the identified intention is an account abnormal intention, and steps S304-S306 are further executed because the account abnormal intention is among the plurality of preset intents.

Step S304, if the target request intention corresponding to the user request is identified, acquiring the target scene according to the view corresponding table and the target request intention.

Specifically, if the target request intention is identified in step S302, the map corresponding table is obtained from the platform database, the target request intention is used to query in the map corresponding table, and a scene corresponding to the target request intention is found from the map corresponding table as the target scene.

For example, the account abnormal intention corresponds to a platform service scene, the b1 city public accumulation account query intention corresponds to a b1 city public accumulation service scene, and the b2 city social security account password abnormal intention corresponds to a b2 city social security service scene; if the user request of a1 is identified in step S302, and the identified target request intention is an account abnormal intention, the account abnormal intention is used as a search condition, and the corresponding scene is searched from the view corresponding table to be a platform service scene, so that the target scene can be determined to be the platform service scene.

And step S306, determining a target customer service robot corresponding to the target scene according to the corresponding relation between the scene and the customer service robot, and sending the user request to the target customer service robot.

In the embodiment of the present disclosure, the platform database may be preset with the map corresponding table, and the corresponding relationship between the scene and the customer service robot may be stored in the platform database through the Jing Fu corresponding table; in this way, the target scene can be used for inquiring in the scene service corresponding table, and the customer service robot corresponding to the target scene can be searched from the scene service corresponding table to serve as the target customer service robot; then, obtaining the route information of the target customer service robot, and sending the user request to the target customer service robot through the route information of the target customer service robot; and after the target customer service robot acquires the user request, responding to the user request to obtain a response result, and returning the response result to the client corresponding to the user request.

In particular, the specific implementation process of step S306 may refer to the description of step S1048, which is not repeated herein for brevity of description.

For example, taking the user request of the user a as an example, if the user ID 10258 carried in the user request of the user a is used for inquiring in the platform database, inquiring whether a history request record with the ID 10258 exists or not; if no history request record with ID 10258 is found, the NLU model is used for carrying out intention recognition on the user request of a, and the recognized intention is account abnormal intention.

Further, if the identified account abnormal intention is in the preset intents, searching a scene corresponding to the account abnormal intention from the view corresponding table, wherein the account abnormal intention corresponds to a platform service scene in the view corresponding table, and then searching the scene corresponding to the account abnormal intention as the platform service scene; and searching a customer service robot corresponding to the account abnormal intention from the scene service corresponding table to be a platform customer service robot, namely, a target customer service robot of the user a is the platform customer service robot, further sending a user request of the user a to the platform customer service robot, responding the user request of the platform customer service robot to the user request of the user a, and returning a response result to the client where the user a is located.

When the history request records do not exist, the user request is subjected to intention recognition, and the intention recognition model is a trained NLU model which is obtained by training a plurality of history request records, so that the target request intention recognized by the trained NLU model is more accurate, and the accuracy of the target customer service robot determined according to the target request intention is also improved on the basis that the target request intention is more accurate.

And if the target request intention corresponding to the user request is not identified, the method comprises the following steps, specifically as shown in fig. 4:

and step S402, analyzing the user request to obtain embedded point information of the last service page, acquiring a service scene corresponding to the last service page, and taking the service scene as the target scene.

In this embodiment of the present disclosure, the comprehensive service platform buries a scene where a user is located before entering the unified customer service interface, and stores a mapping relationship between the buries and the service scene in the platform database.

Specifically, the user request may be first parsed to obtain the embedded point information of the previous service page, and the service scene is obtained according to the embedded point where the embedded point information is located and the point scene mapping relationship, and the service scene is used as the target scene.

Specifically, after the embedded point information of the last service page is obtained through analysis, the point scene mapping relation is obtained from the platform database, then the embedded point where the embedded point information is located is used for inquiring in the point scene mapping relation, a scene obtained through inquiring is used as a service scene of the last service page, and a scene obtained through inquiring is used as the target scene.

For example, the point view mapping relationship includes a scene corresponding to a b1 city public accumulation service page with a buried point position being b1 city public accumulation service scene, a scene corresponding to a b2 city social security service page with a buried point position being b2 city social security service scene, and a scene corresponding to a b3 city gas service page with a buried point position being b3 city gas service scene; and if the user request of the user a2 is analyzed to obtain that the burial point where the burial point information of the last service page is located is the b3 city gas service page, inquiring in the point scene mapping relation by using the b3 city gas service page, and inquiring the b3 city gas service scene as a target scene of a 3.

And step S404, acquiring customer service robots corresponding to the service scene from the M customer service robots according to the corresponding relation between the scene and the customer service robots, taking the acquired customer service robots as the target customer service robots, and sending the user request to the target customer service robots.

Specifically, a customer service robot corresponding to the service scene is acquired, the customer service robot corresponding to the service scene is used as the target customer service robot, and the user request is sent to the target customer service robot.

Specifically, after the customer service robot corresponding to the service scene is taken as the target customer service robot, the route information of the target customer service robot can be acquired, and the user request is sent to the target customer service robot through the route information of the target customer service robot; and after the target customer service robot acquires the user request, responding to the user request to obtain a response result, and returning the response result to a client corresponding to the user request through the comprehensive service platform.

Specifically, the specific implementation process of step S404 may refer to the description of step S1048, which is omitted for brevity.

In the embodiment of the specification, when a certain customer service robot responds to the user request, firstly searching whether a response result corresponding to the user request exists in a database of the customer service robot according to the user request, and if so, directly returning the response result to a corresponding client through the comprehensive service platform; if the user request does not exist, determining one response operation from a plurality of preset response operations as a final response operation, responding to the user request by utilizing the final response operation, obtaining the response result and returning the response result to the corresponding client.

In this embodiment of the present disclosure, after the target scene corresponding to the target request intention is obtained in steps S302-S304 and the service scene of the previous service page is obtained in step S402, one scene is selected from the two scenes to be used as the target scene of the user request through the set selection condition, then the target customer service robot is determined according to the target scene of the user request, and then the user request is sent to the target customer service robot.

In the embodiment of the present disclosure, the plurality of response operations include a manual response operation, a no-answer response operation, and the like, when the final response operation is a manual response operation, acquiring a manual channel supported by a service provider corresponding to the target customer service robot, and packaging the acquired manual channel into a service card for rendering at a client, so that the target user enters a subsequent response step of the manual channel according to the service card; when the final response operation is an answer-free response operation, the artificial channel supported by the service provider corresponding to the target customer service robot can be obtained, and the obtained artificial channel is packaged into a service card to be rendered at the client, so that the target user enters a subsequent response step of the artificial channel according to the service card; and the method can also directly return the preset answer-free prompt information to the corresponding client, create an answer-free work order and then perform data analysis and service optimization on the answer-free work order.

Specifically, the response mode of the manual response operation is a manual spam mode, namely, the acquired manual channel is packaged into a service card to be rendered at the client, so that the target user enters a subsequent response step of the manual channel according to the service card; the answer-free response operation response mode can be an artificial spam mode or a work order spam mode, the work order spam mode is that answer-free prompt information is directly returned, and then an answer-free work order is created to carry out data analysis and service optimization for operators in corresponding scenes.

In another embodiment of the present disclosure, a method for determining a problem category based on a user request is provided, and the method is applied to an integrated service platform, where the integrated service platform includes a platform customer service robot, and can call a three-party customer service robot that hosts a service provider of the integrated service platform, and knowledge base contents relied on by the three-party customer service robot are maintained by the corresponding service provider, and the method includes the following steps:

a1, obtaining a user request of a target user;

the specific implementation process of step A1 refers to the description of S102, and is not repeated here for brevity of description.

A2, carrying out intention recognition on the user request to obtain an intention recognition result;

a3, if the history request record of the target user exists, determining a target scene corresponding to the user request according to the intention recognition result and the history request record of the target user;

the specific implementation process of steps A2 and A3 refers to the description of step S104.

Step A4, if the history request record of the target user does not exist and the intention recognition result is that the target request intention is recognized, acquiring a target scene corresponding to the user request according to the corresponding relation between the preset request intention and the scene; if the intention recognition result is that the intention of the target request is not recognized and the user request carries embedded point information of the last service page, determining a target scene corresponding to the user request according to the embedded point information;

step A5, selecting the platform customer service robot or a certain three-party customer service robot as a target customer service robot according to the corresponding relation between a preset scene and the customer service robot; and sending the user request to the target customer service robot.

The specific implementation process of steps A4 and A5 refers to the description of step S106.

In another embodiment of the present disclosure, a method for determining a problem category based on a user request is provided, including:

step B1, obtaining a user request of a target user;

the specific implementation process of step B1 refers to the description of S102, and is not repeated here for brevity of description.

Step B2, carrying out intention recognition on the user request to obtain an intention recognition result;

step B3, if the history request record of the target user exists, determining a target scene corresponding to the user request according to the history request record of the target user and the target request intention;

the implementation process of steps B2 and B3 refers to the description of step S104.

Step B4, if the history request record of the target user does not exist and the intention recognition result is that the target request intention is recognized, acquiring a target scene corresponding to the user request according to the corresponding relation between the preset request intention and the scene; if the intention recognition result is that the intention of the target request is not recognized and the user request carries embedded point information of the last service page, determining a target scene corresponding to the user request according to the embedded point information;

And B5, determining a target customer service robot corresponding to the target scene from the preset M customer service robots according to the corresponding relation between the preset scene and the customer service robots, and sending the user request to the target customer service robot, wherein M is an integer greater than 1.

The specific implementation process of steps B4 and B5 refers to the description of step S106.

For example, taking the user request of the user a as an example, if the user ID 10258 carried in the user request of the user a is used for inquiring in the platform database, inquiring whether a history request record with the ID 10258 exists or not; if no history request record with ID 10258 is queried, using an NLU model to identify the intention of the user request of a, wherein the identified intention is the false intention of the public accumulation gold account.

Further, if the identified false intention of the public accumulation account number is in the preset intents, acquiring embedded point information of a last service page carried by a user request, and determining that a target scene is a b1 public accumulation service scene according to the embedded point information of the last service page, wherein the embedded point is a b1 public accumulation service page, and the point-scene mapping relation comprises that a scene corresponding to the embedded point is the b1 public accumulation service page is the b1 public accumulation service scene; and searching a customer service robot corresponding to the b1 city public accumulation service scene from the scene service corresponding table to obtain a b1 city public accumulation service robot, namely, a target customer service robot of a user a is the b1 city public accumulation service robot, further sending a user request of a to the b1 city public accumulation service robot, responding to the user request of a by the b1 city public accumulation service robot, and returning a response result to a client where the a is located.

And in the process that the b1 city public accumulation service robot responds to the user request of a, if the response result corresponding to the user request of a exists in the database of the b1 city public accumulation service robot, directly returning the response result to the corresponding client; if the service card does not exist, the manual response operation selected by the user aiming at the response operations is obtained as a final response operation, then the manual channel of the b1 city public accumulation fund manager corresponding to the b1 city public accumulation fund customer service robot is obtained, and the obtained manual channel is packaged into the service card to be rendered at the client, so that the user a enters the subsequent response step of the manual channel according to the service card.

When a history request record does not exist and the user request is identified as hitting the preset intention through intention recognition, a service scene corresponding to the last service page is obtained according to the embedded point information of the last service page carried by the user request, and the service scene is taken as the target scene; and on the basis of stronger relevance between the target scene and the user request, the relevance between the determined target customer service robot and the user request is also enhanced, so that the accuracy of the determined target customer service robot is further improved, namely, the matching degree of the target customer service robot and the user request is higher, and on the basis of higher matching degree of the target customer service robot and the user request, the accuracy of responding to the user request is also improved.

In addition, because the M customer service robots not only include platform customer service robots, but also include third party customer service robots, and each customer service robot is provided with service support by its corresponding service provider, so that each customer service robot is maintained by its corresponding service provider, so that the comprehensive service platform does not need to perform knowledge base entry in the whole industry, and does not need to collect a large amount of data in the early stage to perform service identification training, and only through the comprehensive service platform 51 and the third party service provider, the third party service provider inputs knowledge content in the service range of its customer service robot, and the comprehensive service platform completes its own responsible general service intention configuration, and can complete one-stop intelligent customer service implementation of the comprehensive service platform quickly, thereby enabling service support to multiple services.

In a second aspect, as shown in fig. 5, the embodiment of the present disclosure further provides a problem category determining system based on a user request, including a client 50, a comprehensive service platform 51, and M customer service robots 52, where M is an integer greater than 1, and includes:

the client 50 is configured to obtain input data of a target user, generate a user request, and send the user request to the integrated service platform 51;

The integrated service platform 51 is configured to receive the user request sent by the client 50, and if there is a history request record corresponding to the target user, perform intent recognition on the user request to obtain a target request intent of the user request; determining a target scene corresponding to the target request intention according to the history request record of the target user and the target request intention; the method comprises the steps of carrying out a first treatment on the surface of the Determining a target customer service robot corresponding to the target scene from M customer service robots 52 according to the corresponding relation between the scene and the customer service robots, and sending the user request to the target customer service machine; if the buried point information carried by the user request is acquired; determining a target customer service robot corresponding to the user request from the M customer service robots 52 according to the buried point information;

the target customer service robot is configured to receive the user request sent by the integrated service platform 51; responding to the user request to obtain a response result; and returns the response result to the client 50 through the integrated service platform 51.

Accordingly, the integrated service platform 51 includes a platform customer service robot, and can call a three-party customer service robot of a service provider residing in the integrated service platform, and the content of a knowledge base relied on by the three-party customer service robot is maintained by the corresponding service provider, so as to obtain a user request of a target user; performing intention recognition on the user request to obtain an intention recognition result; if the history request record of the target user exists, determining a target scene corresponding to the user request according to the intention recognition result and the history request record of the target user; if the history request record of the target user does not exist and the intention recognition result is that the target request intention is recognized, acquiring a target scene corresponding to the user request according to the corresponding relation between the preset request intention and the scene; if the intention recognition result is that the intention of the target request is not recognized and the user request carries embedded point information of the last service page, determining a target scene corresponding to the user request according to the embedded point information; according to the corresponding relation between a preset scene and the customer service robot, selecting the platform customer service robot or a certain three-party customer service robot as a target customer service robot; and sending the user request to the target customer service robot.

Accordingly, the integrated service platform 51 is configured to obtain a user request of the target user; performing intention recognition on the user request to obtain an intention recognition result; if the history request record of the target user exists, determining a target scene corresponding to the user request according to the history request record of the target user and the target request intention; if the history request record of the target user does not exist and the intention recognition result is that the target request intention is recognized, acquiring a target scene corresponding to the user request according to the corresponding relation between the preset request intention and the scene; if the intention recognition result is that the intention of the target request is not recognized and the user request carries embedded point information of the last service page, determining a target scene corresponding to the user request according to the embedded point information; according to the corresponding relation between a preset scene and the customer service robots, determining a target customer service robot corresponding to the target scene from M preset customer service robots, and sending the user request to the target customer service robot, wherein M is an integer greater than 1.

In the embodiment of the present disclosure, the integrated service platform 51 provides a unified intelligent customer service portal for all services, and the service provider who is in the integrated service platform 51 needs to provide own call information of the customer service robots, that is, each customer service robot in the M customer service robots 52 provides call information of the customer service robot by the corresponding service provider, and the call information accesses parameters required by the customer service robot question-answer interface: including robot numbering (typically a unique label), signature verification, and encryption, and key information (specifically used to secure communication), so that the integrated service platform 51 can call each customer service robot according to the call information of each customer service robot to process the user request.

In this embodiment of the present disclosure, the M customer service robots include a platform customer service robot of the integrated service platform and a third party customer service robot provided by a third party service party.

In the embodiment of the present disclosure, after entering from the customer service portal provided by the integrated service platform 51, the user carries the embedded point information of the previous service page and accesses the intelligent customer service client interface (i.e. platform page) provided by the integrated service platform 51; in this way, the user request carries embedded point information of the last service page, wherein the embedded point information comprises service body information of the last service page.

As shown in fig. 6, the integrated service platform 51 includes a platform intelligent customer service server 53 and an intelligent routing system 54, and the integrated service platform 51 provides a plurality of customer service portals including a customer service portal 61 for an integrated service, a customer service portal 62 for a social security service, and a customer service portal 63 for other three-party services, so that a user may enter the platform intelligent customer service server 53 through each customer service portal in the plurality of customer service portals, and access the platform intelligent customer service server 53, so that a user request for accessing the platform intelligent customer service server 53 enters the intelligent routing system 54 after passing through the platform intelligent customer service server 53.

In this embodiment of the present disclosure, as shown in fig. 6, the content of the knowledge base corresponding to each customer service robot in the M customer service robots 52 is maintained by each service provider, and the M customer service robots 52 include a platform customer service robot 520, a public accumulation customer service robot 521, a social security customer service robot 522 and a three-party customer service robot 523, where the platform customer service robot 520 is maintained by the integrated service platform 51, so that general support about the capability and service of the platform itself can be provided for the user.

Thus, the user request of the intelligent customer service server 53 of the user access platform carries the embedded point information of the last service page; receiving the user request at the intelligent routing system 54, the intelligent routing system 54 comprehensively judges a target customer service robot of the user request according to information such as embedded point information, intention recognition results, user history call data and platform knowledge matching results of the last service page; and then sending the user request to the target customer service robot.

And, the intelligent routing system 54 receives the response result returned by the target customer service robot to analyze, and pushes the response result to the platform intelligent customer service server 53 when knowledge or recommended content exists; when no answer is available, the request is forwarded to the platform customer service robot again, and the platform customer service robot performs bottom-covering treatment; during the bottom-covering processing of the platform customer service robot, the processing process data is preserved, the comprehensive service platform 51 performs data analysis regularly, and the service provider is pushed to perfect a knowledge base or adjust and optimize a routing strategy according to specific reasons, so that the overall customer service answering rate of the comprehensive service platform 51 is pushed to be improved.

As shown in fig. 7, a target user 70 may enter a unified customer service interface 531 provided by a platform intelligent customer service terminal 53 through a platform page 53 or a service page 71, where the platform page 53, the service page 71 and the unified customer service interface 531 are displayed on a display screen of a client 50; the target user 70 generates a corresponding user request through input data in the unified customer service interface 531, the user request first enters into the session management unit 540 in the intelligent routing system 54, and the session management unit 540 searches the session flow meter according to the user identifier sessionId of the user request.

The intelligent routing system 54 includes a session management unit 540, where the session management unit 540 first receives the user request sent by the client 50, and searches a session flow meter according to a user identifier sessionId of the user request by using a history session loading module 5401 in the session management unit 540; if the history request record is found, loading the history session, and at the moment, loading only the found history request record, and loading the history route data and scene configuration in the history request record, and taking the history route data and scene configuration into a subsequent module as a route judgment basis.

And, the session management unit 540 further includes a session recording module 5402, configured to perform session flow record processing after each customer service robot is successfully invoked and before returning to the customer service end 50; the recorded content comprises user request information, a subsequent module processing result and response content of the robot, and is associated to the sessionId, so that the subsequent round of multiplexing of user requests is facilitated.

Further, the intelligent routing system 54 further includes an algorithm engine unit 541, configured to, after the history session loading module 5401 detects that a history request record exists and loads the history request record, perform intent recognition on the user request through an intent recognition module 5411 in the algorithm engine unit 541, and determine a service scenario according to the history routing data and the scenario configuration. Specifically, when the identified intention hits the historical intention corresponding to the historical route data, a service scene corresponding to the historical intention is used as a route result of the request. Subsequent robot calls will be made based on the content of the service scenario configuration. For example, the questioning content of the user hits account abnormal intention, the intention association scene is platform service, and even if the user enters from Hangzhou principals service pages, the request can be routed to the platform robot for service support; wherein, the intent and the service scene associated with the intent configured in the algorithm engine 514 can be iterated and optimized continuously along with the upgrading of the platform and the expansion of the service content.

And, the intelligent routing system 54 further includes a scenario policy engine unit 542 configured to, after the session management unit 540 does not find the history request record, if the intention recognition module 5411 recognizes the target request intention corresponding to the user request, load relevant service information of the target scenario configuration according to the scenario configuration loading module 5422 in the scenario policy engine unit 542, where the relevant service information includes a call parameter of the customer service robot associated with the target scenario, a transfer person and a spam policy of the target scenario, and so on; and transmits the acquired related service information to the robot routing unit 543 in the scene policy engine unit 542.

And after the session management unit 540 does not find the history request record and the intention recognition module 5411 does not recognize the intention of the target request corresponding to the user request, the embedded point analysis module 5421 in the scene policy engine unit 542 analyzes the embedded point information of the last service page carried by the user request to obtain a corresponding target scene, and the scene configuration loading module 5422 loads the relevant service information of the target scene configuration; and transmits the acquired related service information to the robot routing unit 543 in the scene policy engine unit 542.

And, after receiving the related service information sent by the scene policy engine unit 542, the robot routing unit 543 encapsulates the call information of the target customer service robot and the user request according to the robot request encapsulation module 5430 in the robot routing unit 543, and sends the encapsulated call information and the user request to the target customer service robot, where the target customer service robot may be any one of the M customer service robots 52.

Further, if the history request record is not found, the session management unit 540 identifies the questioning intention of the user by using the NLU through the intention identification module 5411, and if the target request intention corresponding to the user request is not identified, the service scene corresponding to the last service page is obtained according to the embedded point information of the last service page carried by the user request, and the service scene is used as the target scene; and acquiring the customer service robot corresponding to the service scene according to the corresponding relation between the scene and the customer service robot, and sending the user request to the customer service robot corresponding to the service scene.

In addition, the robot routing unit 543 further includes an parsing unit 5431 for differentially encapsulating the request message and standardizing the response message of each customer service robot; and the scenario policy engine unit 542 may also include a traffic optimization processing module 5423.

Further, the scene policy engine unit 542 may further include a service optimization processing module 5423, configured to perform service optimization processing on two response cases of "manual conversion" and "no answer" after determining the standardized response of the target customer service robot; the method comprises the following steps of converting manual response optimization logic, obtaining a manual channel (an online workbench, a hot wire telephone and the like) which can be supported by a corresponding service provider (a service providing mechanism or platform) under a scene, packaging into a clickable service card, rendering the service card at a client, and enabling a user to quickly enter a subsequent step of the manual channel after clicking. And the non-answer response optimizing logic is also combined with the routing result and the scene configuration, the substitution of the non-answer response is carried out by using two modes of manual spam or work order spam, the manual spam processing logic is the same as a, the work order spam directly returns a user-friendly default text prompt, and then a non-answer work order is created for operators corresponding to the scene to carry out data analysis and service optimization.

Therefore, the comprehensive service platform 51 does not need to input a knowledge base of the whole industry, does not need to collect a large amount of data in the early stage to perform service identification training, and only the comprehensive service platform 51 and the service provider conduct service attribution division, and the third party service provider inputs knowledge contents in the service range of the customer service robot, so that the comprehensive service platform 51 completes the configuration of the general service intention in charge of the customer service robot, and the one-stop intelligent customer service implementation of the comprehensive service platform 51 can be completed quickly, and service support to a plurality of services can be realized quickly.

In the embodiment of the present disclosure, an intelligent routing system 54 is introduced, and is configured to uniformly accept access requests of all users in the comprehensive service platform 51, and determine a target customer service robot based on various technical means such as a history request record, a buried point technology, an intention recognition module, etc., so that the accuracy of the identified target customer service robot is higher; the implementation idea is summarized as follows: the integrated service platform 51 provides a unified intelligent customer service portal to receive customer requests such as customer complaints and consultations from all users. Requesting to carry embedded point information when a service page enters an intelligent customer service page of a platform, and transmitting upstream page information carried by embedded point information and login session ID of a user when an intelligent customer service client initiates a request to the service end; the intelligent routing system 54 performs pre-knowledge filtering according to the intention recognition model, filters common problems supported by the platform, transfers the common problems to the platform customer service robot for bearing, performs secondary service routing according to the embedded point information and the user questioning content, and selects the correct customer service robot, so that the accuracy of the determined target customer service robot is improved, namely, the matching degree of the identified target customer service robot and the request is higher.

In addition, based on response content and user-defined configuration of each service scene, service optimization processing can be performed on response results such as manual conversion and no answer, corresponding manual channels are directly presented to users with service cards, users do not need to search for the service cards by themselves, and further response steps after optimization can be effectively shortened, response efficiency is improved, and user experience is better.

The comprehensive service platform in the embodiment of the specification can provide a unified entrance for a user to transact various transactions such as social security, tax, public accumulation, water, electricity, coal, medical treatment and the like, for example, urban service version of citizen cloud, guangdong province, payment treasures and various banking apps.

In a third aspect, based on the same technical idea, an embodiment of the present disclosure provides a problem category determining apparatus based on a user request, as shown in fig. 8, including:

a user request acquiring unit 801, configured to acquire a user request of a target user;

a target customer service robot determining unit 802, configured to identify the intention of the user request if there is a history request record of the target user, and obtain a target request intention of the user request; determining a target scene corresponding to the target request intention according to the history request record of the target user and the target request intention; determining a target customer service robot corresponding to the target scene from M preset customer service robots according to the corresponding relation between the scene and the customer service robots, wherein M is an integer greater than 1; if the history request record of the target user does not exist, determining a target customer service robot corresponding to the user request from the M customer service robots according to at least one data of the target request intention and the embedded point information of the last service page, wherein the embedded point information of the last service page is carried in the user request

And a user request sending unit 803, configured to send the user request to the target customer service robot.

In an optional implementation manner, a target customer service robot determining unit 802 is configured to obtain, according to a history request record of the target user, a correspondence between a history request intention of the target user and a history session scene; detecting whether the historical request intention has the same intention as the target request intention, if so, acquiring the target scene according to the corresponding relation between the historical request intention and a historical session scene; if the target scene does not exist, the target scene is obtained according to a preset map corresponding table and the target request intention.

In an alternative embodiment, the target customer service robot determining unit 802 is configured to use a trained natural language understanding model to identify the intention of the user request, and obtain the intention of the target request.

In an alternative embodiment, the target customer service robot determining unit 802 is configured to perform intention recognition on the user request; if the target request intention is identified, determining the target scene according to the view corresponding table and the target request intention; and determining a target customer service robot corresponding to the target scene according to the corresponding relation between the scene and the customer service robot, and sending the user request to the target customer service robot.

In an optional implementation manner, the target customer service robot determining unit 802 is configured to parse the user request to obtain embedded point information of the previous service page, obtain a service scenario corresponding to the previous service page, and take the service scenario as the target scenario; and acquiring customer service robots corresponding to the service scene from the M customer service robots according to the corresponding relation between the scene and the customer service robots, taking the acquired customer service robots as the target customer service robots, and sending the user request to the target customer service robots.

In an alternative embodiment, the M customer service robots include a platform customer service robot and a third party customer service robot of the integrated service platform.

According to a fourth aspect, based on the same technical concept, an embodiment of the present disclosure provides a problem category determining device based on a user request, which is applied to an integrated service platform, where the integrated service platform includes a platform customer service robot, and can call a three-party customer service robot that hosts a service provider of the integrated service platform, and content of a knowledge base on which the three-party customer service robot depends is maintained by the corresponding service provider, including:

A request acquisition unit for acquiring a user request of a target user;

In a fifth aspect, based on the same technical idea, embodiments of the present disclosure provide a problem category determining apparatus based on a user request, including:

In a sixth aspect, based on the same inventive concept as the method for determining a problem category based on a user request in the foregoing embodiment, the present embodiment further provides an electronic device, as shown in fig. 9, including a memory 904, a processor 902, and a computer program stored on the memory 904 and executable on the processor 902, where the processor 902 implements the steps of any of the methods for determining a problem category based on a user request described above when the processor 902 executes the program.

Where in FIG. 9 a bus architecture (represented by bus 900), bus 900 may include any number of interconnected buses and bridges, with bus 900 linking together various circuits, including one or more processors, represented by processor 902, and memory, represented by memory 904. Bus 900 may also link together various other circuits such as peripheral devices, voltage regulators, power management circuits, etc., as are well known in the art and, therefore, will not be described further herein. The bus interface 905 provides an interface between the bus 900 and the receiver 901 and the transmitter 903. The receiver 901 and the transmitter 903 may be the same element, i.e. a transceiver, providing a unit for communicating with various other apparatus over a transmission medium. The processor 902 is responsible for managing the bus 900 and general processing, while the memory 904 may be used to store data used by the processor 902 in performing operations.

In a seventh aspect, based on the inventive concept as the user request based problem category determination method in the foregoing embodiments, the present specification embodiment further provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of any one of the user request based problem category determination methods described above.

The present description is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the specification. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While preferred embodiments of the present description have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the disclosure.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present specification without departing from the spirit or scope of the specification. Thus, if such modifications and variations of the present specification fall within the scope of the claims and the equivalents thereof, the present specification is also intended to include such modifications and variations.

Claims

1. A method for determining a problem category based on a user request, comprising:

Acquiring a user request of a target user;

if the history request record of the target user exists, carrying out intention recognition on the user request to obtain the target request intention of the user request; determining a target scene corresponding to the target request intention according to the history request record of the target user and the target request intention; determining a target customer service robot corresponding to the target scene from M preset customer service robots according to the corresponding relation between the scene and the customer service robots, and sending the user request to the target customer service robot, wherein M is an integer greater than 1;

if the history request record of the target user does not exist, determining a target customer service robot corresponding to the user request from the M customer service robots according to at least one of target request intention and embedded point information of a last service page, including: if the history request record of the target user does not exist, and the intention recognition result is that the target request intention is recognized, determining the target customer service robot according to the target request intention; if the history request record of the target user does not exist, and the intention recognition result is that the target request intention is not recognized, determining the target customer service robot according to the embedded point information of the last service page;

And sending the user request to the target customer service robot, wherein the embedded point information of the last service page is carried in the user request, and the target request intention is obtained by carrying out intention recognition on the user request.

2. The determining method according to claim 1, wherein the determining a target scene corresponding to the target request intention according to the history of the target user and the target request intention comprises:

acquiring the corresponding relation between the historical request intention of the target user and a historical session scene according to the historical request record of the target user;

detecting whether the historical request intention has the same intention as the target request intention, if so, acquiring the target scene according to the corresponding relation between the historical request intention and a historical session scene; if the target scene does not exist, the target scene is obtained according to a preset map corresponding table and the target request intention.

3. The determining method as claimed in claim 2, wherein the performing intention recognition on the user request to obtain the target request intention of the user request includes:

and carrying out intention recognition on the user request by using a trained natural language understanding model, and acquiring the target request intention.

4. The determination method of claim 3, wherein the determining a target customer service robot corresponding to the user request from the M customer service robots according to at least one of the target request intention and the embedded point information of the previous service page comprises:

performing intention recognition on the user request;

if the target request intention is identified, determining the target scene according to the view corresponding table and the target request intention;

and determining a target customer service robot corresponding to the target scene according to the corresponding relation between the scene and the customer service robot, and sending the user request to the target customer service robot.

5. The determination method of claim 3, wherein the determining a target customer service robot corresponding to the user request from the M customer service robots according to at least one of the target request intention and the embedded point information of the previous service page comprises:

analyzing the user request to obtain embedded point information of the last service page; acquiring a service scene corresponding to the last service page according to the embedded point information, and taking the service scene as the target scene;

And acquiring customer service robots corresponding to the service scene from the M customer service robots according to the corresponding relation between the scene and the customer service robots, taking the acquired customer service robots as the target customer service robots, and sending the user request to the target customer service robots.

6. The determination method of any one of claims 1-5, the M customer service robots comprising a platform customer service robot and a third party customer service robot of a comprehensive service platform.

7. The utility model provides a problem category determining method based on user request, which is applied to a comprehensive service platform, wherein the comprehensive service platform comprises a platform customer service robot and can call a three-party customer service robot of a service provider residing in the comprehensive service platform, and knowledge base content relied on by the three-party customer service robot is maintained by the corresponding service provider, and the method comprises the following steps:

acquiring a user request of a target user;

8. A method for determining a problem category based on a user request, comprising:

acquiring a user request of a target user;

9. A problem category determination device based on a user request, comprising:

a user request acquisition unit for acquiring a user request of a target user;

the target customer service robot determining unit is used for carrying out intention recognition on the user request if a history request record of the target user exists, so as to obtain a target request intention of the user request; determining a target scene corresponding to the target request intention according to the history request record of the target user and the target request intention; determining a target customer service robot corresponding to the target scene from M preset customer service robots according to the corresponding relation between the scene and the customer service robots, wherein M is an integer greater than 1; if the history request record of the target user does not exist, determining a target customer service robot corresponding to the user request from the M customer service robots according to at least one data of the target request intention and embedded point information of a last service page, wherein the determining comprises the following steps: if the history request record of the target user does not exist, and the intention recognition result is that the target request intention is recognized, determining the target customer service robot according to the target request intention; if the history request record of the target user does not exist, and the intention recognition result is that the target request intention is not recognized, determining the target customer service robot according to the embedded point information of the last service page; the embedded point information of the last service page is carried in the user request;

10. The device of claim 9, wherein the target customer service robot determining unit is configured to obtain, according to the history request record of the target user, a correspondence between a history request intention of the target user and a history session scene; detecting whether the historical request intention has the same intention as the target request intention, if so, acquiring the target scene according to the corresponding relation between the historical request intention and a historical session scene; if the target scene does not exist, the target scene is obtained according to a preset map corresponding table and the target request intention.

11. The apparatus of claim 10, the target customer service robot determining unit configured to use a trained natural language understanding model to identify intent of the user request and obtain the target request intent.

12. The apparatus of claim 11, the target customer service robot determining unit configured to perform intent recognition on the user request; if the target request intention is identified, determining the target scene according to the view corresponding table and the target request intention; and determining a target customer service robot corresponding to the target scene according to the corresponding relation between the scene and the customer service robot, and sending the user request to the target customer service robot.

13. The device of claim 12, wherein the target customer service robot determining unit is configured to parse the user request to obtain embedded point information of the previous service page, obtain a service scenario corresponding to the previous service page, and take the service scenario as the target scenario; and acquiring customer service robots corresponding to the service scene from the M customer service robots according to the corresponding relation between the scene and the customer service robots, taking the acquired customer service robots as the target customer service robots, and sending the user request to the target customer service robots.

14. The apparatus of any of claims 9-13, the M customer service robots comprising a platform customer service robot and a third party customer service robot of a comprehensive service platform.

15. The utility model provides a problem category determining device based on user's request, is applied to in the comprehensive service platform, comprehensive service platform includes platform customer service robot to can call the three party customer service robot that resides the service provider of comprehensive service platform, the knowledge base content that three party customer service robot relies on is maintained by its corresponding service provider, includes:

A request acquisition unit for acquiring a user request of a target user;

16. A problem category determination device based on a user request, comprising:

a scene determining unit, configured to determine, if there is a history request record of the target user, a target scene corresponding to the user request according to the history request record of the target user and a target request intention; if the history request record of the target user does not exist and the intention recognition result is that the target request intention is recognized, acquiring a target scene corresponding to the user request according to the corresponding relation between the preset request intention and the scene; if the intention recognition result is that the intention of the target request is not recognized and the user request carries embedded point information of the last service page, determining a target scene corresponding to the user request according to the embedded point information;

17. A problem category determining system based on a user request comprises a client, a comprehensive service platform and M customer service robots, wherein M is an integer greater than 1, and the system comprises:

the comprehensive service platform is used for receiving the user request sent by the client, and if a history request record corresponding to the target user exists, carrying out intention recognition on the user request to obtain a target request intention of the user request; determining a target scene corresponding to the target request intention according to the history request record of the target user and the target request intention; determining a target customer service robot corresponding to the target scene from the M customer service robots according to the corresponding relation between the scene and the customer service robots, and sending the user request to the target customer service robot; if no history request record of the target user exists, and the intention recognition result is that the target request intention is recognized, determining a target customer service robot from the M customer service robots according to the target request intention; if no history request record of the target user exists and the intention recognition result is that the intention of the target request is not recognized, acquiring embedded point information of a last service page carried by the user request; determining a target customer service robot corresponding to the user request from the M customer service robots according to the embedded point information of the last service page;

18. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method of any one of claims 1-8 when the program is executed.

19. A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method of any of claims 1-8.