CN113724036B

CN113724036B - Method for providing problem consultation service and electronic equipment

Info

Publication number: CN113724036B
Application number: CN202110867164.4A
Authority: CN
Inventors: 薛晶; 梁宇荣; 简剑; 王德胜; 狄兆龙; 李晓婧; 齐英辉; 王涛; 李明; 黄剑冰
Original assignee: Hangzhou Taotian E Commerce Technology Co ltd
Current assignee: Hangzhou Taotian E Commerce Technology Co ltd
Priority date: 2021-07-29
Filing date: 2021-07-29
Publication date: 2024-10-01
Anticipated expiration: 2041-07-29
Also published as: CN113724036A

Abstract

The embodiment of the application discloses a method for providing problem consultation service and electronic equipment, wherein the method comprises the following steps: receiving a target problem required to be consulted by a user in a target session; judging whether the target problem needs to be answered through intelligent customer service resources; and if so, determining answer content for answering the target questions through the intelligent customer service resources, wherein the answer content is generated by simulating manual customer service resources to answer the target questions according to a pre-established knowledge model. According to the embodiment of the application, the frequency of transferring the labor can be reduced, and the cost of transferring the labor is reduced.

Description

Method for providing problem consultation service and electronic equipment

Technical Field

The application relates to the technical field of intelligent customer service, in particular to a method for providing problem consultation service and electronic equipment.

Background

In the customer service system, a manual customer service resource can be provided to provide problem consultation service for users. However, in practical applications, there may be situations where the user initiates a consultation request, and the human customer service resource agent is not on line or is all busy, and in this case, some systems may provide a consultation service for the user through an intelligent customer service resource (e.g., "customer service robot" or the like). Such "customer service robot" systems rely on a pre-established knowledge base, which typically requires configuration and maintenance by configuration personnel, including adding information such as the title and content of a particular problem to the knowledge base. Thus, after receiving the consultation questions of the user, the customer service robot can search the knowledge base for the content which can be used for answering the specific consultation questions in a title matching mode and the like, and feed the content back to the user.

However, in the implementation manner in the prior art, the problems that the answer fed back by the customer service robot is relatively carved, the expression mode, the content and the like are not abundant often exist. In the process of communicating with the user through the customer service robot, the situation such as consultation interruption and the like may occur due to poor user experience and the like, so that resource waste is caused, the effect of the customer service robot cannot be really and effectively exerted, and finally, the customer service robot still needs to be converted into manual customer service resources to provide consultation services for the user.

Disclosure of Invention

The application provides a method for providing problem consultation service and electronic equipment, which can reduce the frequency of transferring manual work and reduce the cost of transferring manual work.

The application provides the following scheme:

a method of providing a problem consulting service, comprising:

receiving a target problem required to be consulted by a user in a target session;

judging whether the target problem needs to be answered through intelligent customer service resources;

and if so, determining answer content for answering the target questions through the intelligent customer service resources, wherein the answer content is generated by simulating manual customer service resources to answer the target questions according to a pre-established knowledge model.

A method of providing a problem consulting service, comprising:

Providing operation options for initiating a help request to an intelligent customer service resource in an interface where a target session window is located, wherein the target session window is used for a conversation between the artificial customer service resource and a problem consultant user;

and after receiving the help request of the manual customer service resource through the operation options, calling the intelligent customer service resource to obtain the answer content of the target question, wherein the answer content is generated by simulating the manual customer service resource to answer the target question according to a pre-established knowledge model.

An apparatus for providing a problem consulting service, comprising:

a target question receiving unit for receiving a target question required to be consulted by the user in the target session;

The judging unit is used for judging whether the target questions need to be answered through intelligent customer service resources;

And the answer content determining unit is used for determining answer content for answering the target questions through the intelligent customer service resources if required, wherein the answer content is generated by simulating the artificial customer service resources to answer the target questions according to a pre-established knowledge model.

An apparatus for providing a problem consulting service, comprising:

an operation option providing unit, configured to provide an operation option for initiating a help request to an intelligent customer service resource in an interface where a target session window is located, where the target session window is used for a conversation between the artificial customer service resource and a problem consultant user;

And the calling unit is used for calling the intelligent customer service resource to obtain the answer content of the target question after receiving the help request of the manual customer service resource through the operation option, wherein the answer content is generated by simulating the manual customer service resource to answer the target question according to a pre-established knowledge model.

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 the preceding claims.

An electronic device, comprising:

one or more processors; and

A memory associated with the one or more processors, the memory for storing program instructions that, when read for execution by the one or more processors, perform the steps of the method of any of the preceding claims.

According to the specific embodiment provided by the application, the application discloses the following technical effects:

According to the embodiment of the application, after the problem consultation request of the user is specifically received, whether intervention by the intelligent customer service resource is needed can be judged, if so, the answer content for answering the target problem through the intelligent customer service resource can be determined, and the answer content is generated by simulating the artificial customer service resource to answer the target problem according to a pre-established knowledge model. That is, in the embodiment of the application, although the intelligent customer service resource provides the consultation service for the user, the answer content provided by the intelligent customer service resource is generated by simulating the answer mode and the like when the artificial customer service resource answers the corresponding questions, so that the answer content of the intelligent customer service resource answer is closer to the dialogue requirement of the user in a daily communication scene, the answer content of the intelligent customer service resource answer can also have similar performance when the artificial customer service answer is received by the user, the frequency of transferring the manual is reduced, and the cost of transferring the manual is reduced.

The specific knowledge model can be established according to the historical conversation data original text content generated by the user related to the target organization in the process of using the related communication system, and the content generated in the specific historical conversation data also has the characteristics of divergent solution and the like, so that the richness of the knowledge base content is further facilitated to be improved.

Of course, it is not necessary for any one product to practice the application to achieve all of the advantages set forth above at the same time.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic diagram of a system architecture provided by an embodiment of the present application;

FIG. 2 is a flow chart of a first method provided by an embodiment of the present application;

FIGS. 3-1 and 3-2 are schematic diagrams of knowledge contents in a knowledge base according to an embodiment of the present application;

FIGS. 4-1 and 4-2 are schematic diagrams of interfaces provided by embodiments of the present application;

FIG. 5 is a flow chart of a second method provided by an embodiment of the present application;

FIG. 6 is a schematic diagram of a first apparatus provided by an embodiment of the present application;

FIG. 7 is a schematic diagram of a second apparatus provided by an embodiment of the present application;

fig. 8 is a schematic diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which are derived by a person skilled in the art based on the embodiments of the application, fall within the scope of protection of the application.

In order to facilitate understanding of the technical solution provided by the embodiments of the present application, it should be noted that, in the process that a merchant provides goods or services for a user through various modes such as online or offline, various channels for performing problem consultation may be provided for the user. For example, a hotline telephone channel, an online customer service channel in a merchandise object information system, an instant messaging channel, an offline self-service terminal channel, and the like may be included. In the process of purchasing or using specific goods or services, if a specific problem is encountered, the user can initiate consultation to the corresponding merchant through the various channels. Correspondingly, the merchant side can be provided with artificial customer service resources such as agents corresponding to various channels, so as to provide consultation services for users in a manual mode.

In order to facilitate the management of various consultation channels by merchants, and facilitate the same manual customer service resource to provide services for the consultation requests of various different consultation channels, some service providers develop intelligent customer service systems. By using the intelligent customer service system, merchants can uniformly route the consultation requests of various channels, and the manual customer service resources can provide services for the consultation requests of various channels only by one workbench without switching among various different terminal devices or application programs, so that the service efficiency of the customer service resources can be effectively improved.

The intelligent customer service system can be integrated into a specific communication system, particularly an instant communication system and the like which are dedicated to providing services such as intelligent office and business communication for enterprise users, and the intelligent customer service system can provide basic functions for the enterprise users and intelligent customer service management and the like for the enterprise users through the integration of the intelligent customer service system. For enterprise users such as specific merchants, such communication systems may be installed for employees of the enterprise, such that communication may be made through the communication systems, between employees and customers (suppliers, etc.), and so on.

In addition, under the condition of integrating the intelligent customer service system, a 'manual customer service' account can be provided for a specific employee in an enterprise, the employee can have an 'agent' identity by logging in to the 'manual customer service' account, and the employee can provide consultation service for a user in the 'agent' identity through operating options such as 'working' in an interface. Further, the intelligent customer service system may deploy consulting portals in a variety of channels, such as web pages, details pages of an associated merchandise object information system, related social networking systems, and so forth. Thus, in the process of purchasing and using a particular merchandise object or service by a particular user (typically a consumer user of the merchandise or service provided by a merchant, etc.), if some problem is encountered, including a return merchandise problem, etc., a consultation may be initiated through a variety of channels. After that, as the merchant deploys the instant messaging system integrated with the intelligent customer service system, the consultation problems of the channels can be uniformly routed, and the processing such as 'agent' allocation and the like can be performed. If a certain "agent" is assigned a certain consultation request, the intelligent customer service system can establish a session connection between the "agent" and the consumer user so that the two can communicate. At this time, the "agent" may perform a conversation with the consumer user through the instant messaging system integrated with the intelligent customer service system, and the consumer user may perform a conversation with the "agent" through the original channel (the channel used when the consultation is initiated) (the message may be opened between the intelligent customer service system and a specific channel).

Of course, the specific "agent" may provide the consultation service to the staff of the organization (including internal staff, or staff having a relationship such as outsourcing, practice, etc.) in addition to the consultation service to the consumer user, etc. That is, when staff of the organization create some problems during work, consultation can also be initiated to the "agent", at this time, staff can directly initiate consultation to the "agent" through a communication system associated with the intelligent customer service system, and so on.

In summary, if an organization (including the aforementioned merchants that specifically provide commodity objects or services) deploys a communication system that incorporates an intelligent customer service system, the relevant users will generate session data during use of the communication system. Such session data may occur from employee to employee, from employee to customer, from "agent" to consumer user, from "agent" to employee, and so forth. And, the session data contains a great deal of contents related to the consultation and reply of the questions. Of course, if the specific organization does not deploy the intelligent customer service system, the manual customer service resource provides the consultation service for the user through a plurality of different channels, and a large amount of session data can be generated in the process of providing the consultation service. These session data may be useful information to the user of new problem consultation requirements that may be generated later, and thus are valuable for the construction of the knowledge base.

Based on the analysis, in the embodiment of the application, session data generated by a user related to a specific organization in the process of using a communication system can be collected, and a knowledge model of the organization is generated by learning the collected session data. The training of the knowledge model can be specifically performed according to the acoustic information in the session data. The so-called original sound information is the original text content in the actual history session data. For example, in a session, a consumer user consults a question associated with a return shipment, a human customer service replies, and training of a knowledge model can be performed using the question and textual content of the reply. Thereafter, the knowledge model may also be maintained and updated as more session data is generated. In this way, the knowledge model generated in this way can be used specifically to provide specific problem consulting services to the user.

By adopting the mode, the knowledge base of the organization can be automatically established and automatically maintained and updated as long as the related communication system is deployed in the organization, session data are generated and accumulated for a period of time, so that the process of manually configuring the knowledge base is replaced, and the occupation of labor cost in the process of creating and maintaining the knowledge base is saved. Moreover, such a knowledge base may be built and used gradually as the use of the communication system by the relevant users of the organization proceeds, without having to first arrange how the owners will ask questions and answer.

And, the specific knowledge model may be trained according to the acoustic content in the historical session data, the trained knowledge model may take the consultation question proposed by the specific user as input, the output result may be answer content for answering the question, and the answer content may be generated by simulating the manual customer service resource to answer the question. Thus, the generated answer content is more close to the dialogue requirement of the user in the daily communication scene. For example, in the process of providing a customer user with a consultation service, a "seat" usually prefers to be spoken, and the expression mode is flexible, so that the knowledge model can be trained by using the acoustic information, the content of the "customer service robot" reply can also have similar performance in the process of manually providing the customer service reply, the content is easier to be accepted by the user, the frequency of transferring the personnel is reduced, and the cost of transferring the personnel is reduced. When the artificial customer service resource is allocated to the problem consultation request of the user, the intelligent customer service resource can be used for hosting when the artificial customer service resource temporarily leaves, or the intelligent customer service resource can be used for answering the user problem when the artificial customer service resource can not answer the user problem; in the process, the intelligent customer service resource can simulate the artificial customer service resource, so that the perception of switching between the artificial customer service resource and the intelligent customer service resource by a user can be reduced to a certain extent, and the user experience is improved.

Furthermore, the original text content generated in the specific historical session data has the characteristics of divergent solution, for example, regarding the problems of 'how to remove stains', etc., if a knowledge base is manually configured, only a unique standard answer is generally configured; however, in the actual session data, the specific session content is generated during the actual consultation process of the specific user, and the specific question mode, the problem details and the like may be various (for example, stains may be further divided into various stains including oil stains, fruit stains and the like), the given solutions are divergent, relatively professional solutions may be included, solutions that are not necessarily authenticated by professionals but can actually solve certain problems may be included, and the like. Therefore, the content richness of the knowledge base can be improved.

In addition, the method ensures that the data generated by the user in the conversation process can help other users to solve the problem, thereby converting the unidirectional user help mode into the mutual help mode among multiple users and realizing the toolization of the user conversation data content.

From the view of system architecture, referring to fig. 1, an embodiment of the present application mainly relates to an intelligent customer service system, where the intelligent customer service system may include a server and a client, where the server is mainly used for collecting data, creating a knowledge model, updating, maintaining, and the like; the client can be integrated in a communication system such as an instant messaging system (of course, the client can also be an independently operated client), the specific client can provide customer service resources for an organization, the organization can obtain the use right of the intelligent customer service system in a purchasing mode and the like, and then the specific customer service resources can provide consultation services for users through the intelligent customer service system. Specific users include consumer users outside the organization or employee users inside the organization. Customer users outside the organization can initiate consultation requests through various channels, staff users inside the organization can directly initiate consultation requests through the associated communication system, and the intelligent customer service system can perform uniform routing, so that customer service resources can provide services for the user consultation requests under various channels through the intelligent customer service system. The specific customer service resources may include "customer service robot" resources, and in the embodiment of the present application, the "customer service robot" resources may provide services for the consultant user by using a knowledge model. The specific knowledge model can be created, updated and maintained after the original sound information of the historical session data generated in the communication system process is collected, analyzed and processed, so that the customer service robot can simulate the manual customer service resource to answer the target problem, and the answer content given is closer to the state that the user carries out a session with the manual customer service in a daily session scene, thereby improving the user experience. Of course, the specific intelligent customer service system can also be directly integrated into various individual customer service channel systems.

The following describes the specific technical scheme provided by the embodiment of the application in detail.

Example 1

First, in view of the service side of the intelligent customer service system, the embodiment provides a method for providing problem consulting service, referring to fig. 2, the method may include:

S201: target questions of a user's desired consultation are received in a target session.

The target session may be created according to a problem consultation request of a user, for example, when a user browses information of a commodity object through an e-commerce information system in specific implementation, the problem consultation request may be initiated through an operation option such as "customer service" in a detail page, and at this time, the customer service system may create a corresponding session for the request of the user, and so on. After the session is created, the user can enter the target questions for the specific desired consultation through the window of the session.

S202: and judging whether the target problem needs to be answered through the intelligent customer service resource.

After receiving the target questions of the user's desired consultation through the target session, it may be first determined whether intelligent customer service resource intervention is required, i.e., whether the target questions need to be answered by the intelligent customer service resource. In particular, there may be a plurality of specific ways of determining. For example, if the target session is a session for which no artificial service resources have been allocated, i.e., may be a newly created session, etc., at this time, it may be determined whether artificial service resources are currently available, if so, the artificial service resources may be preferentially allocated, otherwise, if no artificial service resources are currently available (e.g., the current time may not be within the service time range of the artificial service resources, or the artificial service resources may be all busy, etc.), it may be determined that the target question needs to be answered by the intelligent service resources.

Or the target session may be a session of an allocated target artificial customer service resource, that is, it is assumed that a user initiates a problem consultation request, and the system allocates a certain artificial customer service resource to serve the user, and the intelligent customer service resource may also intervene at a proper time in the process of the user talking with the artificial customer service resource. Specifically, whether the target manual customer service resource cannot answer the target question can be judged, and if so, it is determined that the target question needs to be answered through the intelligent customer service resource. That is, in the process that a specific artificial customer service resource provides services for a user, a situation that a target problem of the user cannot be answered may occur, and at this time, the intelligent customer service resource may be switched to provide services for the user.

Specifically, there may be various ways to determine whether the target artificial customer service resource cannot answer the target question. For example, whether the target human service resource does not read or answer the target question for a long time or fails to solve the target question after multiple rounds of interaction is determined, and if so, it may be determined that the target human service resource fails to answer the target question. If the target question posed by the user is not read for a long time, the target manual customer service resource is busy processing other things and answers the question of the user, and at the moment, the intelligent customer service resource can be intervened. If the current target artificial customer service resource does not answer the target question set forth by the user for a long time or the target question cannot be solved after multiple rounds of interaction, the current target artificial customer service resource may not have relevant knowledge or the relevant knowledge is relatively deficient. At this time, the intelligent customer service resource can also intervene to replace the current manual customer service resource to go back to the target problem of the user. In order to determine whether the target problem cannot be solved after multiple rounds of interaction, a relevant operation option may be provided at the user side of the consultant, for example, the user may be queried whether the problem is solved, the user may perform feedback by clicking the corresponding operation option, and accordingly, whether the target problem of the user is solved may be determined according to the feedback result of the user, and so on. Or in another mode, whether the target problem of the user is solved or not can be judged by carrying out natural language understanding and the like on the dialogue content between the user and the target manual customer service resource, and the like.

In another way, in order to avoid interference of automatic intervention of the intelligent customer service resource to the normal service process of the artificial customer service resource, an operation option for actively initiating a help request to the intelligent customer service resource can be provided on the target artificial customer service resource side, so that if the target artificial customer service resource needs to be temporarily separated in the process of providing the consultation service for the user or does not know how to answer the current target problem, help can be initiated to the intelligent customer service resource through the operation option. Correspondingly, if a help request initiated by the target artificial customer service resource to the intelligent customer service resource is received, it can also be determined that the target artificial customer service resource cannot answer the target question. Specifically, a corresponding operation entry may be provided in a client interface associated with the human customer service resource, for example, an "assistant panel" may be provided at a right side of the session interface, etc., through which the human customer service resource may actively initiate a request for assistance to the intelligent customer service resource. Or in another mode, when the intelligent customer service resource judges that the artificial customer service resource cannot answer the current target problem, prompt information can be provided for the artificial customer service resource to inquire whether the artificial customer service resource needs the help of the intelligent customer service resource, and if the artificial customer service resource selects 'need', the intelligent customer service resource is then involved in the session between the two.

S203: and if so, determining answer content for answering the target questions through the intelligent customer service resources, wherein the answer content is generated by simulating manual customer service resources to answer the target questions according to a pre-established knowledge model.

If the intelligent customer service resource is required to answer the target questions, an answer mode which is possibly used when the artificial customer service resource answers the target questions can be simulated according to a pre-established knowledge model, so that answer content is generated. Furthermore, the intelligent customer service resource can provide feedback information for the user by utilizing the answer content.

There are a number of ways in which a knowledge model can be created with respect to a particular knowledge model. For example, after an organization (including merchants that provide goods or services specifically, or other forms of corporate groups, etc.) obtains the usage rights of the intelligent customer service system, the intelligent customer service system may collect the textual content of historical session data generated by the relevant users of the organization during the usage of the associated communication system, and use the data to build, update and maintain a knowledge model, as described above. The related communication system, that is to say, the communication system specifically integrated with the intelligent customer service system, may be specifically an instant communication system or the like.

The specific historical session data may include: the manual customer service resource of the target organization provides session data generated in the process of problem consultation service for the consultant user. The counselor user herein may include a user external to an organization, for example, a merchant who is an organization providing a commodity object or service, and the particular counselor user may include a consumer user of such a commodity object or service. Or staff users inside the organization structure can be also included, for example, staff can initiate consultation to the manual customer service resources through the intelligent customer service system if some problems are encountered in daily work of staff, including the failure of some hardware devices in the company, and the like. In addition, since the intelligent customer service system is integrated in the communication system, the communication system can have functions of instant messaging and the like, staff users related to the target organization can communicate with each other in daily work through the communication tool, for example, some project groups are established, project discussion is carried out in the groups together, and the like. Thus, some session data may also be generated between staff users during the daily communication process. In the embodiment of the application, the session data can also be collected for constructing a specific knowledge base.

After specific historical session data is collected, the knowledge model may be trained using the collected historical session data. When training a specific knowledge model, user acoustic information in historical session data can be reserved. That is, the content, expression, etc. of the user who performs a conversation with the counterpart during the history session are reserved as the knowledge content for providing the service for the subsequent user consultation. The historical session data may include text data and may also include voice data, if the historical session data is voice data, specific acoustic information may include not only content, expression mode and the like of a specific dialogue, but also voice characteristic information of a user, so that, particularly when a mode of answering a question to a manual customer service resource is simulated, simulation of voice of a specific manual customer service resource can be realized, and specific voice content is generated.

Under a specific implementation manner, particularly when a knowledge model is generated, keyword extraction and statistics can be performed on various questions, and corresponding questions and answer contents can be provided for each specific keyword. The keywords may be in the form of word pairs, and information such as objects and actions may be represented in one keyword pair. For example, as shown in fig. 3-1, a plurality of keyword pairs may be extracted, and information such as the number of times each keyword pair appears may also be given. Where "change in price," represents that a particular session involves a problem associated with a modified price, "add an order," represents that a particular session involves a problem associated with an add order, and so on. In addition, questions and answers corresponding to each keyword pair may be given, for example, as shown in fig. 3-2, the questions and answers may retain original sound information of the user, that is, text content and expression mode of the user when asking a question or replying to the question, for example, the text content of the question is "price change", the corresponding reply text content may be "good, slightly lower", etc. The original text content is expressed in a biased spoken language mode, and the knowledge model is trained by directly utilizing the original text content, so that the situations that the intelligent customer service resource is too carved when answering the questions and the like are avoided, the conversation habit of people in the daily communication process is more met, and even the user cannot perceive that the conversation is being carried out with the intelligent customer service resource.

In the problem consultation scenario described in the embodiment of the present application, a merchant generally provides a consultation service for a consumer user or provides a consultation service for staff in an enterprise, so that the knowledge model may be constructed by taking an organization as a unit. That is, each organization may correspond to a different knowledge model, and is established based on session data generated by the respective associated user during use of the communication system associated with the intelligent customer service system.

It should be noted that, the specific knowledge model may be created in other manners, for example, may be implemented by a configuration manner, but unlike the knowledge base configuration in the prior art, in the embodiment of the present application, the specific knowledge base may be a knowledge content related to answering a question by simulating a manual customer service resource, and not just configuring a scored "standard answer" for the specific question.

Because the knowledge model is established in advance, when the current target questions need to be answered through the intelligent customer service resources, the knowledge model can be utilized to simulate the 'kiss' of the manual customer service resources for answering the target questions, and corresponding answer contents are generated. This answer content may be used to answer the target question currently being consulted by the user.

For example, as shown in fig. 4-1, assuming that the target question input by the counselor user for a commodity object is "i need a vertical interface", in the prior art, the question may not be recorded in a manually configured knowledge base, or the expression of the user may not be so standardized that it cannot be understood by a common "customer service robot", so that the reply made by the common "customer service robot" may be "parent", and the question may be asked in another way. Or even if a common "customer service robot" can give a reply, it may appear to be relatively stiff. In the embodiment of the application, because the knowledge model can be created according to the user acoustic information in the historical session data, the counselor user is more likely to be understood by a customer service robot than a random expression mode, and the application can simulate the kiss of the artificial intelligent customer service when answering the questions, and provide the knowledge content which is less rigid and more suitable for conversations in the daily communication occasion of the user. For example, as shown in fig. 4-2, for the same user consultation problem, the answer given by the "customer service robot" in the embodiment of the present application may be "you turn you that interface over, be it vertical, and not buy. Such reply content would allow the consultant user to have an experience of directly talking to the human customer service resource. Of course, in specific implementation, the reply content made by the "customer service robot" may also be marked, for example, as shown in fig. 4-2, before the specific reply content, prompt information such as "model training through historical sound" may be provided.

The intelligent customer service resource may be involved in a specific session during the session between the user and the target artificial customer service resource, so as to provide assistance for the artificial customer service resource or the user. In this case, the problem of switching from the artificial customer service resource to the intelligent customer service resource is involved, so in a preferred embodiment of the present application, the knowledge content in the specific knowledge model may further include language habit information of the target artificial customer service resource. At this time, specific answer content may be generated by simulating the manner in which the artificial customer service resource (not specifically speaking to a specific artificial customer service resource) answers the target question and the language habit of the target artificial customer service resource. For example, first, the manner in which the human customer service resource answers the target question may be simulated according to a knowledge model to generate the original answer content. Then, according to the language habit of the current target artificial customer service resource, the original answer content is adjusted, for example, some words are replaced by words which are liked to be used by the current target artificial customer service resource, or expression symbols which are liked to be used by the current target artificial customer service resource are added into the original answer content, and the like.

That is, different human customer service resources may have different language habits, including some word habits, language styles (e.g., some likes to a naughty, some likes to a sink, etc.), and so forth. The language habit information can be reflected from the historical session data of the manual customer service resource. Therefore, in the process of creating the knowledge model by utilizing the historical session data, the statistical analysis of the historical session data can be performed by taking specific artificial customer service resources as units, and language habit information of each artificial customer service resource can be respectively learned from the statistical analysis. Thus, if the current target session is allocated with a specific artificial customer service resource and needs to be switched to an intelligent customer service resource, the answer content generated by the specific knowledge model not only can simulate the artificial customer resource to answer the target problem, but also can simulate the language habit of the current specific artificial customer service resource. By the method, the perception of the switching event from the manual customer service resource to the intelligent customer service resource by the user can be further reduced, and the user experience is improved.

In addition, in practical application, the manual customer service resource may answer the questions of the user by text input or may answer by voice in the process of providing the questions consulting service for the user. For the former, answer content may be directly output into the target session. And for the latter, the generated answer content can be converted into voice content and then output to the target session. Or in a preferred embodiment, the knowledge content in the specific knowledge model may further include: and the voice characteristic information of the target artificial customer service resource is such that if the target artificial customer service is in a conversation with a user in a voice manner in the historical conversation data of the target conversation, voice content can be generated according to the answer content for outputting the voice content in the target conversation, wherein specific voice content can be generated by simulating the target artificial customer service resource to dictate the answer content according to the knowledge model.

That is, different artificial customer service resources have different voice characteristics, which may specifically include voiceprint characteristics, etc., and the characteristics may also be represented by historical voice session data of the specific artificial customer service resources, so that when learning and training of the knowledge model are performed by using the historical session data, original voice acoustic information may also be retained. Thus, the voice characteristic information of the specific artificial customer service resource can be learned by taking the artificial customer service resource as a unit. Furthermore, when the intelligent customer service system takes over or replaces the previous target artificial customer service resource to answer the target problem of the user, the voice, the language and the like of the target artificial customer service resource can be simulated, so that the generated voice content sounds more like the previous target artificial customer service resource to be dictated in person. In this way, the user's perception of the switching event from the artificial customer service resource to the intelligent customer service resource can be further reduced.

Furthermore, the knowledge content in the specific knowledge base may further include: the problem category information of each of the plurality of artificial customer service resources in the associated target organization is good for answering (for example, the problem category information can be specifically determined according to high-frequency keywords in historical session data associated with the artificial customer service resources). At this time, after determining that the current target artificial customer service resource cannot answer the current target question, the intelligent customer service resource cannot determine answer content capable of answering the target question, other artificial customer service resources good at answering the target question may also be determined according to the question category information to which the target question belongs, and the other artificial customer service resources may be accessed into the target session so that the target question is answered by the other artificial customer service resources. That is, in the process of constructing the knowledge model, specific session data can be analyzed in the dimension of the artificial customer service resources, so that information such as the field of the good quality of the artificial customer service resources can be obtained. Therefore, if the intelligent customer service resource is encountered, the user problems and the like cannot be solved, the intelligent customer service resource can be used for switching other artificial customer service resources for the user. For example, in the process of serving a user, the artificial customer service resource a finds that a problem posed by the user cannot be solved, at this time, a "customer service robot" may be requested to intervene, after the "customer service robot" intervenes, it is found that no content directly corresponding to the problem posed by the user exists in the knowledge base, and then the artificial customer service resource B that may be good at solving the problem of the user may be transferred to the user, and so on. Therefore, the capability of the customer service robot can not only search answers for questions presented by the user in a title matching mode and the like, but also help the user to transfer more suitable manual customer service resources aiming at specific questions presented by the user, so that the capability of the customer service robot is expanded.

In addition, knowledge content in the specific knowledge model can also include question scene information applicable to various answer content. For example, if keywords used in some comparatively formal occasions are included in some answer contents, it may be determined that the answer contents are more suitable for use in scenes such as work, and so on. In this way, particularly when answer content is generated for the current target question, the question scene information of the current consultation requirement can be determined according to the submitting time, place and the like of the current target question. For example, if the current time is a work time of a work day, it may be determined that the target user is on duty, in a work scenario, and so on. Correspondingly, according to a pre-established knowledge model, the artificial customer service resource can be simulated to answer the target questions in the questioning scene so as to generate specific answer contents. For example, if it is determined that the current target user is in a work scenario, feedback results may be provided to the current target user based on answer content more suitable for use in the work scenario, and so on.

It should be noted that, in practical application, the specific user with the requirement of problem consultation may further include: staff users associated with the target organization. That is, staff users can also initiate consultation to customer service resources of the organization if problems are encountered during daily work. In this case, the consultation can also be directly initiated to the "customer service robot", or the "customer service robot" can intervene when the manual customer service resource is not on line or is all busy, or an unresolved problem is encountered in the process of communicating with the manual customer service resource, and the like. The specific process may be the same as when facing a user outside of an organization, such as a consumer user, and will not be described again here.

However, the processing mode is slightly different from that of the case of facing the user outside the organization, in that when session data is collected, session data in the process of communicating with the consultant user through the manual customer service resource can be included, and session data in the process of daily work of the organization staff can be collected, so that when a knowledge base is established, knowledge content can be established from the dimension of the staff user, and specific knowledge content can include information about the field, problem category and the like which are good for the specific staff user respectively. For example, if it is found that a certain employee user frequently uses certain key words in the course of a conversation with other users, it may be determined that the employee user has relatively rich knowledge in the domain to which the key words correspond, and so on. In this way, the "customer service robot" can not only reply to the consultation questions presented by the staff users by utilizing the knowledge content in the knowledge base or transfer other manual customer service resources to the staff users, but also recommend other staff users capable of solving the consultation questions to the staff users by utilizing the knowledge content in the knowledge base in the process of providing services to the staff in the organization. That is, for staff users inside an organization, when they encounter some aspect of problem, the "customer service robot" can tell him who to find.

The meaning of the mode is as follows: in some large organizations, the number of staff is numerous, and it is almost impossible for each staff to know each other, especially the staff of different departments; however, in daily work, there may be a problem of a certain employee, and just another employee can answer. At this time, if two employees know each other, communication with the other party can be directly performed, but if they do not know each other, it is not known which employee can solve the own problem, and communication with the other party cannot be established. For example, staff a of a certain legal department, its own computer equipment, staff of a real technical department may help to solve its problems, but since staff of other departments are not known, consultation may be initiated to the "customer service robot". In the process of consultation, if the problem that the customer service robot cannot answer is encountered, or the problem that the customer service robot needs to go to a station of an employee to solve the problem manually, another employee B can be recommended to the current employee A according to the knowledge content in the knowledge base, so that the employees A, B can communicate with each other by themselves, or the employee A is directly connected with the employee B, and the like.

In summary, through the embodiment of the application, after the problem consultation request of the user is specifically received, whether intervention by the intelligent customer service resource is needed or not can be judged, if so, the answer content for answering the target problem through the intelligent customer service resource can be determined, and the answer content is generated by simulating the artificial customer service resource to answer the target problem according to a pre-established knowledge model. That is, in the embodiment of the application, although the intelligent customer service resource provides the consultation service for the user, the answer content provided by the intelligent customer service resource is generated by simulating the answer mode and the like when the artificial customer service resource answers the corresponding questions, so that the answer content of the intelligent customer service resource answer is closer to the dialogue requirement of the user in a daily communication scene, the answer content of the intelligent customer service resource answer can also have similar performance when the artificial customer service answer is received by the user, the frequency of transferring the manual is reduced, and the cost of transferring the manual is reduced.

Example two

In a second embodiment, from the perspective of an intelligent customer service system client associated with a manual customer service resource, a method for providing a problem consultation service is provided, and referring to fig. 5, the method may include:

s501: receiving a target problem required to be consulted by a user in a target session;

S502: providing operation options for initiating a help request to an intelligent customer service resource in an interface where a target session window is located, wherein the target session window is used for a conversation between the artificial customer service resource and a problem consultant user;

S503: and after receiving the help request of the manual customer service resource through the operation options, calling the intelligent customer service resource to obtain the answer content of the target question, wherein the answer content is generated by simulating the manual customer service resource to answer the target question according to a pre-established knowledge model.

For the undescribed portions of the second embodiment, reference may be made to the description of the first embodiment, and the description is omitted here.

It should be noted that, in the embodiment of the present application, the use of user data may be involved, and in practical application, the user specific personal data may be used in the solution described herein within the scope allowed by the applicable legal regulations in the country under the condition of meeting the applicable legal regulations in the country (for example, the user explicitly agrees to the user to notify practically, etc.).

Corresponding to the first embodiment, the embodiment of the present application further provides an apparatus for providing a problem consulting service, referring to fig. 6, the apparatus may include:

a target question receiving unit 601, configured to receive a target question that a user needs to consult in a target session;

A judging unit 602, configured to judge whether the target question needs to be answered by an intelligent customer service resource;

and an answer content determining unit 603, configured to determine, if necessary, answer content for answering the target question through the intelligent customer service resource, where the answer content is generated by simulating a human customer service resource to answer the target question according to a pre-established knowledge model.

Wherein the target session comprises a session to which no artificial customer service resource has been allocated;

At this time, the judging unit may specifically be configured to:

if no artificial customer service resources are currently available, determining that the target question needs to be answered by the intelligent customer service resources.

Or the target session comprises a session of the allocated target artificial customer service resource;

At this time, the judging unit may specifically be configured to:

and judging whether the target manual customer service resource cannot answer the target question, if so, determining that the target question needs to be answered through the intelligent customer service resource.

Specifically, the judging unit may specifically be configured to:

And judging whether the target manual customer service resource does not read or answer the target question for a long time or fails to solve the target question after multiple rounds of interaction, and if so, determining that the target manual customer service resource fails to answer the target question.

Or the judging unit may specifically be configured to:

and if a help request initiated by the target artificial customer service resource to the intelligent customer service resource is received, determining that the target artificial customer service resource cannot answer the target question.

In an alternative implementation, the knowledge content in the knowledge model may include: language habit information of the target artificial customer service resource;

At this time, the answer content is generated by simulating the mode of the artificial customer service resource for answering the target question and the language habit of the target artificial customer service resource according to the knowledge model.

Or the knowledge content in the knowledge model may also include: the voice characteristic information of the target artificial customer service resource;

If the target manual customer service carries out a dialogue with the user in a voice mode in the historical dialogue data of the target session, the device further comprises:

And the voice content generation unit is used for generating voice content according to the answer content so as to be used for outputting the voice content in the target session, wherein the voice content is generated by simulating the target manual customer service resource to dictate the answer content according to the knowledge model.

In addition, the knowledge content in the knowledge model may further include: the plurality of manual customer service resources in the associated target organization are respectively good at solving the problem category information;

The apparatus may further include:

The manual customer service resource determining unit is used for determining other manual customer service resources which are good at solving the target problem according to the problem category information of the target problem if the answer content cannot be determined;

and the switching unit is used for switching the other manual customer service resources into the target session so as to answer the target questions by the other manual customer service resources.

In addition, the apparatus may further include:

the questioning scene determining unit is used for determining a questioning scene corresponding to the target question;

At this time, the answer content is generated by simulating the manual customer service resource to answer the target question under the questioning scene according to a pre-established knowledge model.

In particular, the knowledge model may be established based on historical conversational data textual content generated by users associated with the target organization during use of the associated communication system.

Wherein the historical session data comprises: the manual customer service resource of the target organization provides session data generated in the process of problem consultation service for the consultant user and/or session data generated in the process of daily communication of staff users related to the target organization.

Corresponding to the embodiment, the embodiment of the application also provides a device for providing problem consultation service, referring to fig. 7, the device may include:

A target question receiving unit 701, configured to receive a target question that a user needs to consult in a target session;

an operation option providing unit 702, configured to provide an operation option for initiating a help request to an intelligent customer service resource in an interface where a target session window is located, where the target session window is used for a conversation between a manual customer service resource and a problem consultant user;

And a calling unit 703, configured to call the intelligent customer service resource to obtain answer content of the target question after receiving the help request of the manual customer service resource through the operation option, where the answer content is generated by simulating the manual customer service resource to answer the target question according to a pre-established knowledge model.

In addition, the embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, which when being executed by a processor, implements the steps of the method of any one of the previous method embodiments.

And an electronic device comprising:

one or more processors; and

A memory associated with the one or more processors for storing program instructions that, when read for execution by the one or more processors, perform the steps of the method of any of the preceding method embodiments.

Fig. 8, among other things, illustrates an architecture of an electronic device, for example, device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, an aircraft, and so forth.

Referring to fig. 8, device 800 may include one or more of the following components: a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, a sensor component 814, and a communication component 816.

The processing component 802 generally controls overall operation of the device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing element 802 may include one or more processors 820 to execute instructions to perform all or part of the steps of the methods provided by the disclosed subject matter. Further, the processing component 802 can include one or more modules that facilitate interactions between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

The memory 804 is configured to store various types of data to support operations at the device 800. Examples of such data include instructions for any application or method operating on device 800, contact data, phonebook data, messages, pictures, videos, and the like. The memory 804 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.

The power supply component 806 provides power to the various components of the device 800. The power components 806 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the device 800.

The multimedia component 808 includes a screen between the device 800 and the user that provides an output interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or sliding action, but also the duration and pressure associated with the touch or sliding operation. In some embodiments, the multimedia component 808 includes a front camera and/or a rear camera. The front camera and/or the rear camera may receive external multimedia data when the device 800 is in an operational mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 further includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be a keyboard, click wheel, buttons, etc. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.

The sensor assembly 814 includes one or more sensors for providing status assessment of various aspects of the device 800. For example, the sensor assembly 814 may detect an on/off state of the device 800, a relative positioning of the components, such as a display and keypad of the device 800, the sensor assembly 814 may also detect a change in position of the device 800 or a component of the device 800, the presence or absence of user contact with the device 800, an orientation or acceleration/deceleration of the device 800, and a change in temperature of the device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 816 is configured to facilitate communication between the device 800 and other devices, either wired or wireless. The device 800 may access a wireless network based on a communication standard, such as WiFi, or a mobile communication network of 2G, 3G, 4G/LTE, 5G, etc. In one exemplary embodiment, the communication part 816 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the apparatus 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for executing the methods described above.

In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as memory 804 including instructions executable by processor 820 of device 800 to perform the methods provided by the disclosed subject matter. For example, the non-transitory computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

From the above description of embodiments, it will be apparent to those skilled in the art that the present application may be implemented in software plus a necessary general hardware platform. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the embodiments or some parts of the embodiments of the present application.

In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for a system or system embodiment, since it is substantially similar to a method embodiment, the description is relatively simple, with reference to the description of the method embodiment being made in part. The systems and system embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.

The method and electronic device for providing problem consultation service provided by the application are described in detail, and specific examples are applied to illustrate the principle and implementation of the application, and the description of the examples is only used for helping to understand the method and core idea of the application; also, it is within the scope of the present application to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the application.

Claims

1. A method for providing problem consulting services, comprising:

Receiving a target problem required to be consulted by a user in a target session; wherein the user comprises a consumer user outside the organization or an employee user inside the organization; the target session comprises a session of the allocated target artificial customer service resource;

If so, determining answer content for answering the target questions through the intelligent customer service resources, wherein the answer content is generated by simulating language habits of the target manual customer service resources according to a pre-established knowledge model, determining a scene where a target user is located according to the submitting time and place of the target questions, and when the scene is a working scene, the answer content comprises keywords suitable for formal occasions; the knowledge model is built by taking organization institutions as units, and the knowledge model corresponding to each organization institution is built according to historical session data original text contents related to problem consultation and response generated by respective related users in the process of using a communication system associated with an intelligent customer service system; the historical session data original text content comprises: content, expression, and/or voice characteristic information of the history session; the knowledge content in the knowledge model comprises language habit information of the target manual customer service resource.

2. The method of claim 1, wherein the step of determining the position of the substrate comprises,

The target session also comprises a session not yet allocated with manual customer service resources;

the determining whether the target question needs to be answered by the intelligent customer service resource includes:

3. The method of claim 1, wherein the step of determining the position of the substrate comprises,

4. The method of claim 3, wherein the step of,

The determining whether the target human customer service resource cannot answer the target question includes:

5. The method of claim 3, wherein the step of,

6. The method of claim 3, wherein the step of,

The knowledge content in the knowledge model comprises: the voice characteristic information of the target artificial customer service resource;

if the target manual customer service carries out a dialogue with the user in a voice mode in the historical dialogue data of the target session, the method further comprises the following steps:

And generating voice content according to the answer content, wherein the voice content is used for outputting the voice content in the target session, and is generated by simulating the target manual customer service resource to dictate the answer content according to the knowledge model.

7. The method of claim 3, wherein the step of,

The knowledge content in the knowledge model further comprises: the plurality of manual customer service resources in the associated target organization are respectively good at solving the problem category information;

The method further comprises the steps of:

If the answer content cannot be determined, other manual customer service resources which are good at solving the target problem are determined according to the problem category information of the target problem;

And accessing the other manual customer service resources into the target session so as to answer the target questions by the other manual customer service resources.

8. The method of claim 7, wherein the step of determining the position of the probe is performed,

The historical session data includes: the manual customer service resource of the target organization provides session data generated in the process of problem consultation service for the consultant user and/or session data generated in the process of daily communication of staff users related to the target organization.

9. A method for providing problem consulting services, comprising:

After receiving the help request of the manual customer service resource through the operation options, calling the intelligent customer service resource to obtain the answer content of the target problem, wherein the answer content is generated by simulating the language habit of the target manual customer service resource according to a pre-established knowledge model, and determining the scene of the target user according to the submitting time and place of the target problem, and when the scene is a working scene, the answer content comprises keywords suitable for formal occasions; the knowledge model is built by taking organization institutions as units, and the knowledge model corresponding to each organization institution is built according to historical session data original text contents related to problem consultation and response generated by respective related users in the process of using a communication system associated with an intelligent customer service system; the historical session data original text content comprises: content, expression, and/or voice characteristic information of the history session; the knowledge content in the knowledge model comprises language habit information of the target manual customer service resource.

10. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the steps of the method according to any one of claims 1 to 9.

11. An electronic device, comprising:

one or more processors; and

A memory associated with the one or more processors for storing program instructions that, when read for execution by the one or more processors, perform the steps of the method of any of claims 1 to 9.