CN113079263A - Method, device, system and medium for intelligent customer service switching - Google Patents

Abstract

The disclosure provides a method, a device, a system and a medium for intelligent customer service switching. The method comprises the following steps: receiving a consultation problem of a user; identifying the user intention according to the consultation problem; replying the consultation problem based on a response knowledge point which is acquired from a response knowledge point base and matched with the user intention; determining whether the current man-machine conversation content triggers a manual conversion condition; if the current man-machine conversation content triggers a manual-switching condition, matching according to the historical man-machine conversation content and a pre-established mapping relation between the manual customer service group and the conversation information to obtain a response manual customer service group; and initiating a transfer request for designating the response manual customer service group to the manual customer service system. The method of the embodiment of the disclosure can match the manual customer service group with proper skills according to the mapping relation when the switching person works.

Description

Method, device, system and medium for intelligent customer service switching

Technical Field

The present disclosure relates to the field of internet technologies, and in particular, to a method, an apparatus, a system, and a medium for intelligent customer service switching.

Background

In the related art, the reply message of the customer service is automatically replied by the robot unless the customer specifies the type of the service to be manually serviced in case of a manual transfer request from the customer, so that the robot response system transfers the service to the manual customer service according to the type of the service.

In the course of implementing the disclosed concept, the inventors found that there are at least the following problems in the prior art: in some scenes, because the client does not know the service type corresponding to the switching requirement of the client, the client usually designates the service type at will or has a designation which is not practical, in this case, the skill of the switched manual customer service is not matched with the problem consulted by the client or does not belong to the responsibility category, so that the scene of secondary switching is needed, and the problems of resource waste of the manual customer service and failure in timely solution of the problem of the client are caused.

Disclosure of Invention

In view of the above, the present disclosure provides a method, an apparatus, a system, and a medium for intelligent customer service switching.

A first aspect of the present disclosure provides a method of intelligent customer service switching. The method comprises the following steps: receiving a consultation problem of a user; identifying the user intention according to the consultation problem; replying the consultation problem based on a response knowledge point which is acquired from a response knowledge point base and matched with the user intention; determining whether the current man-machine conversation content triggers a manual conversion condition; if the current man-machine conversation content triggers a manual-switching condition, matching according to the historical man-machine conversation content and a pre-established mapping relation between the manual customer service group and the conversation information to obtain a response manual customer service group; and initiating a transfer request for designating the response manual customer service group to the manual customer service system.

According to an embodiment of the present disclosure, the dialog information includes at least one of: consultation questions, identified user intentions, identified user emotions, answering knowledge points and answering answers of the user; in the mapping relationship between the artificial customer service group and the dialogue information, matching is performed based on skills of the artificial customer service group and at least one of the user's consultation questions, the user's intention, the user's emotion, the response knowledge point and the reply answer.

According to an embodiment of the present disclosure, the mapping relationship includes: a first mapping relation of the artificial customer service group-response knowledge points and a second mapping relation of the artificial customer service group-response answers; the first mapping relation and the second mapping relation have a preset priority order. Obtaining a response artificial customer service group according to the historical man-machine conversation content and the mapping relation between the pre-established artificial customer service group and the conversation information, wherein the response artificial customer service group comprises the following steps: matching a group of man-machine conversation contents in the historical man-machine conversation contents with an artificial customer service group based on a mapping relation with higher priority in the first mapping relation and the second mapping relation to obtain a response artificial customer service group; and under the condition that the response manual skill cannot be obtained by matching the group of man-machine conversation contents based on the mapping relation with higher priority, matching the group of man-machine conversation contents based on the mapping relation with lower priority.

According to the embodiment of the disclosure, the group of man-machine conversation contents is selected from the historical man-machine conversation contents in a time reverse order mode, and the next group of man-machine conversation contents is matched under the condition that the current group of man-machine conversation contents cannot be matched with the artificial customer service group.

According to an embodiment of the present disclosure, the method further includes: and establishing a mapping relation between the manual customer service group and the dialogue information in advance. The pre-established mapping relationship between the artificial customer service group and the session information comprises the following steps: acquiring historical reply answers corresponding to historical consultation questions of a user, identified user intentions and identified user emotions; acquiring all response knowledge points in a response knowledge point library; and matching the skills of the artificial customer service group with at least one of historical consultation questions, identified user intentions, identified user emotions, all response knowledge points and historical reply answers of the user to obtain the mapping relation of the artificial customer service group and the conversation information.

According to an embodiment of the present disclosure, the determining whether the current content of the human-computer session triggers the manual condition includes: if the number of times that the user intention identified by the consultation problem of the user in the current human-computer conversation is the same as the user intention identified in the historical human-computer conversation of the human-computer conversation interface exceeds a set value is detected, triggering a manual-switching condition; if the number of times of continuous repetition of the consultation problem of the user is identified to exceed a preset value, triggering a manual condition; if the dissatisfaction emotion of the user is determined to reach the preset degree according to the consultation problem of the user in the current human-computer session, triggering a manual condition; and if the consultation problem of the user in the current human-computer conversation comprises the relevant expression of manual conversion, triggering the manual conversion condition.

According to the embodiment of the disclosure, if the current man-machine conversation content triggers the manual-to-manual condition, a manual-to-manual machine response message is generated; and under the condition that the response artificial customer service group is matched, adding the identification of the response artificial customer service group into the manual machine response message. The sending a transfer request for designating the response manual customer service group to the manual customer service system includes: and converting the manual-to-manual machine response message carrying the identification of the response manual customer service group into a message protocol format recognizable by the manual customer service system and then sending the message protocol format to the manual customer service system.

A second aspect of the present disclosure provides an apparatus for intelligent customer service switching. The above-mentioned device includes: the system comprises a receiving module, an intention identifying module, a replying module, a determining module, a manual customer service group matching module and a request sending module. The receiving module is used for receiving the consultation problem of the user. The intention identification module is used for identifying the user intention according to the consultation problem. And the reply module is used for replying the consultation problem based on the response knowledge point which is acquired from the response knowledge point base and is matched with the user intention. The determining module is used for determining whether the current man-machine conversation content triggers a manual-manual condition. And the artificial customer service group matching module is used for matching according to the historical human-computer conversation content and the pre-established mapping relation between the artificial customer service group and the conversation information to obtain a response artificial customer service group under the condition that the current human-computer conversation content is triggered to be changed into an artificial condition. The request sending module is used for sending a transfer request for appointing the response manual customer service group to the manual customer service system.

A third aspect of the present disclosure provides an intelligent customer service system. The intelligent customer service system comprises: one or more processors; and storage means for storing one or more programs. Wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement any of the methods described above.

A fourth aspect of the present disclosure provides a customer service system. The customer service system includes: the intelligent customer service switching device or the intelligent customer service system and the artificial customer service system are adopted. The artificial customer service system is used for receiving the switching request initiated by the device or the intelligent customer service system and carrying out idle artificial customer service switching in a response artificial customer service group appointed by the switching request.

A fifth aspect of the present disclosure provides a computer-readable storage medium. The above-described computer-readable storage medium has stored thereon executable instructions that, when executed by a processor, cause the processor to implement any of the methods described above.

A sixth aspect of the present disclosure provides a computer program product. The computer program product comprises computer executable instructions which, when executed, are operable to implement any of the methods as described above.

According to the embodiment of the disclosure, based on the mapping relation between the pre-established artificial customer service group and the conversation information, the artificial customer service group with proper skills can be matched according to the mapping relation during the man-hour of switching, so that the situation that the skills of the switched artificial customer service are not matched with the problems consulted by the client or the situation that secondary switching is needed because the client does not know the service type corresponding to the self switching requirement or does not belong to the responsibility category of the client is avoided, and the problems of resource waste of the artificial customer service and untimely solution of the problems of the client can be at least partially solved.

Drawings

The above and other objects, features and advantages of the present disclosure will become more apparent from the following description of embodiments of the present disclosure with reference to the accompanying drawings, in which:

FIG. 1 schematically illustrates a system architecture suitable for implementing a method of intelligent customer service switching, in accordance with an embodiment of the present disclosure;

FIG. 2 schematically illustrates a flow diagram of a method of intelligent customer service transitioning, according to an embodiment of the present disclosure;

fig. 3 schematically illustrates a detailed implementation flowchart of operation S25 according to an embodiment of the present disclosure;

FIG. 4 schematically illustrates a flow diagram of a method of intelligent customer service transitioning, according to another embodiment of the present disclosure;

fig. 5 schematically illustrates a detailed implementation flowchart of operation S20 according to an embodiment of the present disclosure;

FIG. 6 schematically illustrates a flow diagram of a method of intelligent customer service transitioning, according to yet another embodiment of the present disclosure;

FIG. 7 schematically illustrates a block diagram of an apparatus for intelligent customer service switching, in accordance with an embodiment of the present disclosure;

FIG. 8 schematically illustrates a block diagram of an intelligent customer service system according to an embodiment of the present disclosure; and

fig. 9 schematically shows a block diagram of a customer service system according to an embodiment of the present disclosure.

Detailed Description

Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is illustrative only and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.

All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.

Where a convention analogous to "at least one of A, B and C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B and C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).

The embodiment of the disclosure provides an intelligent customer service switching method, an intelligent customer service switching device, an intelligent customer service system, a customer service system and a computer-readable storage medium. The method can be applied to an intelligent customer service system. The method comprises the following steps: receiving a consultation problem of a user; identifying the user intention according to the consultation problem; replying the consultation problem based on a response knowledge point which is acquired from a response knowledge point base and matched with the user intention; determining whether the current man-machine conversation content triggers a manual conversion condition; if the current man-machine conversation content triggers a manual-switching condition, matching according to the historical man-machine conversation content and a pre-established mapping relation between the manual customer service group and the conversation information to obtain a response manual customer service group; and initiating a transfer request for designating the response manual customer service group to the manual customer service system.

Fig. 1 schematically illustrates a system architecture suitable for implementing a method of intelligent customer service switching according to an embodiment of the present disclosure. It should be noted that fig. 1 is only an example of a system architecture to which the embodiments of the present disclosure may be applied to help those skilled in the art understand the technical content of the present disclosure, and does not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments or scenarios.

Referring to fig. 1, asystem architecture 100 suitable for implementing a method for intelligent customer service switching includes:customer premise equipment 101, an intelligentcustomer service system 102 and an artificialcustomer service system 103.

Thecustomer premise equipment 101 has a customer service operation interface for contacting customer service, and may further have installed various communication client applications, such as a shopping application, a web browser application, a search application, an instant messaging tool, a mailbox client, social platform software, and the like (for example only).

The intelligentcustomer service system 102 may be disposed in thecustomer premise equipment 101, or the intelligentcustomer service system 102 and thecustomer premise equipment 101 are two main bodies, and the two main bodies can be in communication connection. The intelligentcustomer service system 102 provides background data support and service for the customer service operation interface on thecustomer premise equipment 101.

The artificialcustomer service system 103 is in communication connection with the intelligentcustomer service system 102 and theuser end device 101, the intelligentcustomer service system 102 in theuser end device 101 is used for sending the artificial transfer request to the artificialcustomer service system 103, and the artificial customer service distributed by the artificialcustomer service system 103 provides answers for questions consulted by users. Or, thecustomer premise equipment 101 sends the manual forwarding request to the intelligentcustomer service system 102, and the intelligentcustomer service system 102 forwards the manual forwarding request to the manualcustomer service system 103.

In an exemplary embodiment, referring to the single arrow in fig. 1, the user can reply to the user's consultation question by the intelligentcustomer service system 102 based on the customer service operation interface of thecustomer premise equipment 101 inputting the consultation question.

In another exemplary embodiment, referring to the double-headed arrow in FIG. 1, when a question consulted by the user triggers a manual transfer condition, a manual transfer request is sent by the intelligentcustomer service system 102 to the manualcustomer service system 103, so that the manual customer service distributed by the manualcustomer service system 103 provides a solution to the question consulted by the user.

The method for intelligent customer service switching provided by the embodiment of the present disclosure can be executed by thecustomer premise equipment 101 or the intelligentcustomer service system 102. Accordingly, the means for intelligent customer service switching may be disposed in thecustomer premise equipment 101 or the intelligentcustomer service system 102.

A first exemplary embodiment of the present disclosure provides a method of intelligent customer service switching.

FIG. 2 schematically illustrates a flow diagram of a method of intelligent customer service transitioning, according to an embodiment of the present disclosure.

Referring to fig. 2, a method for intelligent customer service transfer provided by the embodiment of the present disclosure includes the following operations: s21, S22, S23, S24, S25 and S26.

In operation S21, a consultation question of the user is received.

In operation S22, a user intention is identified according to the above-described consultation problem.

In operation S23, the consultation question is replied based on the response knowledge point matching the user' S intention acquired from the response knowledge point library.

In operation S24, it is determined whether the current human-machine session content triggers a manual-to-manual condition.

In operation S25, if the current man-machine conversation content triggers a manual condition, a response manual service group is obtained according to the historical man-machine conversation content and the pre-established mapping relationship between the manual service group and the dialog information.

In the mapping relationship between the artificial customer service group and the session information, the session information may include at least one of the following: consultation questions of the user, identified user intentions, identified user emotions, answering knowledge points, answering answers, and the like. In the mapping relation, based on at least one of the skill of the artificial customer service group and the consultation problem, the user intention, the user emotion, the response knowledge point and the reply answer of the user, the artificial customer service in the artificial customer service group can provide targeted service for the user, continuity of conversation information between the intelligent customer service system and the artificial customer service system is achieved, the skill of the artificial customer service can be better matched with the requirement of the user, and the satisfaction degree of the user is improved. For example, matching human customer service may answer a certain class of questions well or be good at handling bad-minded customers. In addition, the skills of the manual customer service group can be graded or scored, and the appropriate manual customer service group can be matched according to the requirements of the user in the conversation information, for example, the manual customer service group with higher comprehensive grade is matched for service preferentially, and the like.

In operation S26, a transfer request specifying the above-mentioned answering human customer service group is initiated to the human customer service system.

The operations S21-S26 can be executed by thecustomer premise equipment 101 or the intelligentcustomer service system 102.

The intelligent customer service switching method provided by the embodiment of the disclosure can be used for matching a suitable-skill artificial customer service group according to the mapping relation based on the pre-established artificial customer service group-conversation information when switching people, and the matched artificial customer service group can provide good service on at least one aspect of soothing the emotion of a user, solving the problem of user consultation and the like, so that a scene that the skill of the switched artificial customer service is not matched with the problem consulted by the client or needs secondary switching due to the fact that the client does not know the service type corresponding to the switching requirement of the client or does not belong to the responsibility category of the client is avoided, and the problems of resource waste of the artificial customer service and the problem that the problem of the client is not solved in time can be at least partially solved.

According to an embodiment of the present disclosure, the mapping relationship includes: the first mapping relation of the artificial customer service group-response knowledge points and the second mapping relation of the artificial customer service group-response answers. The first mapping relation and the second mapping relation have a preset priority order.

According to an embodiment of the present disclosure, the determining whether the current content of the human-computer session triggers the manual transfer condition includes: if the number of times that the user intention identified by the consultation problem of the user in the current human-computer conversation is the same as the user intention identified in the historical human-computer conversation of the human-computer conversation interface exceeds a set value is detected, triggering a manual-switching condition; if the number of times of continuous repetition of the consultation problems of the user is identified to exceed a preset value, triggering a work-in condition; if the dissatisfaction emotion of the user is determined to reach the preset degree according to the consultation problem of the user in the current human-computer session, triggering a manual condition; and if the consultation problem of the user in the current human-computer conversation comprises the relevant expression of manual conversion, triggering the manual conversion condition. The manual condition is triggered as long as one of the conditions is met.

Fig. 3 schematically shows a detailed implementation flowchart of operation S25 according to an embodiment of the present disclosure.

According to the embodiment of the present disclosure, referring to fig. 3, the operation S25 of obtaining the response artificial customer service group according to the mapping relationship between the historical human-machine conversation content and the pre-established artificial customer service group-conversation information matching includes the following sub-operations: s251 and S252.

In sub-operation S251, a group of man-machine conversation contents in the historical man-machine conversation contents is matched with a manual customer service group based on a higher priority mapping relationship in the first mapping relationship and the second mapping relationship, so as to obtain a response manual customer service group.

In sub-operation S252, in a case that the matching of the group of human-machine conversation contents based on the mapping relationship with the higher priority does not result in the response human-machine service group, the matching of the human-machine conversation contents based on the mapping relationship with the lower priority is performed on the group of human-machine conversation contents.

Therefore, the manual customer service group matching is preferentially carried out on the group of man-machine conversation contents based on the mapping relation with higher priority, and the response manual customer service group with higher matching degree is preferentially obtained. And under the condition that the response manual customer service group cannot be obtained through matching, matching the manual customer service group on the basis of the mapping relation with lower priority on the human-computer conversation content of the group, and effectively ensuring the realization of the matching of the manual customer service group.

In an embodiment, according to the actual evaluation effect, the reply answer has a higher matching degree to the user's intention than the reply knowledge point, and can reflect the actual requirement of the user, so that the priority order of the second mapping relationship of the artificial customer service group-reply answer is set to be higher than the first mapping relationship of the artificial customer service group-reply knowledge point.

Matching of the manual customer service group can be preferentially carried out on a group of man-machine conversation contents based on the second mapping relation of the manual customer service group and the reply answers; and if the artificial customer service group is obtained through matching, the artificial customer service group obtained through matching is the response artificial customer service group. And if the artificial customer service group cannot be obtained through matching, further performing artificial customer service group matching on the group of man-machine conversation contents based on the first mapping relation of the artificial customer service group and the response knowledge point.

According to the embodiment of the disclosure, the group of man-machine conversation contents is selected from the historical man-machine conversation contents in a time reverse order mode, and the next group of man-machine conversation contents is matched under the condition that the current group of man-machine conversation contents cannot be matched with the artificial customer service group.

The historical man-machine conversation content is in a question-answering mode, the historical man-machine conversation content is selected in a reverse order to be matched, matching is carried out according to the latest time priority, and the actual requirements of the user can be reflected with high probability. In addition, in the second mapping relationship, besides matching the skills of the artificial customer service group with the answer to reply, the skills of the artificial customer service group may also be simultaneously matched with at least one of the emotion of the user and the intention of the user, that is, in the second mapping relationship, the skills of the artificial customer service group are simultaneously matched with the answer to reply and the emotion of the user, or simultaneously matched with the answer to reply, the emotion of the user and the intention of the user. The manual skill set is adept at answering the questions/intentions to which the answers relate and at the same time at dealing with the user's mood.

Fig. 4 schematically illustrates a flow diagram of a method of intelligent customer service transitioning, according to another embodiment of the present disclosure.

According to the embodiment of the present disclosure, referring to fig. 4, the method for intelligent customer service switching provided by the embodiment of the present disclosure includes operations S20, in addition to operations S21 to S26 described above: and establishing a mapping relation between the manual customer service group and the dialogue information in advance.

Fig. 5 schematically shows a detailed implementation flowchart of operation S20 according to an embodiment of the present disclosure.

Referring to fig. 5, operation S20 of pre-establishing a mapping relationship between an artificial customer service group and session information according to the embodiment of the present disclosure includes the following sub-operations: s201, S202, S203 and S204.

In operation S201, a history reply answer corresponding to a history consultation question of a user, a corresponding user intention, and an identified user emotion are acquired.

In operation S202, all the response knowledge points in the response knowledge point library are acquired.

In operation S203, a mapping relationship between the artificial customer service group and the dialog information is obtained based on matching of skills of the artificial customer service group with at least one of historical consultation questions of the user, the identified user intention, the identified user emotion, all response knowledge points, and historical reply answers.

For example, a first mapping relationship of the artificial customer service group-response knowledge point is established with all response knowledge points in the response knowledge point library according to the skill excellence of the artificial customer service group.

And establishing a second mapping relation of the manual customer service group and the reply answers according to the skill excellence of the manual customer service group and the historical reply answers. In the second mapping relationship, besides matching the skills of the artificial customer service group with the answer to reply, the skills of the artificial customer service group can be simultaneously matched with at least one of the emotion of the user and the intention of the user.

The first mapping relationship and the second mapping relationship are stored, for example, in a database of the intelligentcustomer service system 102, and may be called when needed. For example, the first mapping relationship and the second mapping relationship are stored in a distributed database.

In addition, the stored first mapping relationship and second mapping relationship may be updated, where the updating includes: add, delete, modify, etc. The above-described updating may be performed directly in the database. The updated timing comprises: at least one of the response knowledge points in the response knowledge point library, the historical response answers corresponding to the historical consultation questions or the skill excellence of the manual customer service group changes, and in this case, the mapping relationship is updated.

FIG. 6 schematically illustrates a flow diagram of a method of intelligent customer service transitioning, according to yet another embodiment of the present disclosure.

According to an embodiment of the present disclosure, referring to fig. 6, the method for intelligent customer service switching provided by the embodiment of the present disclosure includes the following operations in addition to the previously described operations S21, S22, S23, S24, and S25: s31, S32, and S33.

In operation S31, if the current human-machine session content triggers a manual-to-manual condition, a manual-to-manual machine response message is generated.

In operation S32, in case of matching to the responding artificial service group, the identifier of the responding artificial service group is added to the manual machine response message.

In operation S33, the manual-to-manual machine response message carrying the identifier of the response manual service group is converted into a message protocol format recognizable by the manual service system and then sent to the manual service system.

The operation S31 is performed after the operation S24, the operation S32 is performed after the operation S25, and the operation S33 is a specific embodiment of the operation S26.

A second exemplary embodiment of the present disclosure provides an apparatus for intelligent customer service switching.

Fig. 7 schematically shows a block diagram of an apparatus for intelligent customer service switching according to an embodiment of the present disclosure.

Referring to fig. 7, anapparatus 400 provided in an embodiment of the present disclosure includes: a receiving module 40l, anintent recognition module 402, areply module 403, adetermination module 404, a manual customer servicegroup matching module 405, and arequest sending module 406.

The receivingmodule 401 is used for receiving the consultation problem of the user.

Theintention identifying module 402 is used to identify the user intention according to the consultation problem described above.

The replyingmodule 403 is configured to reply to the consultation problem based on the response knowledge point matching the user intention and acquired from the response knowledge point library.

Thedetermination module 404 is used to determine whether the current human-machine session content triggers a go-to-human condition.

According to an embodiment of the present disclosure, the determining whether the current content of the human-computer session triggers the manual transfer condition includes: if the number of times that the user intention identified by the consultation problem of the user in the current human-computer conversation is the same as the user intention identified in the historical human-computer conversation of the human-computer conversation interface exceeds a set value is detected, triggering a manual-switching condition; if the number of times of continuous repetition of the consultation problem of the user is identified to exceed a preset value, triggering a manual condition; if the dissatisfaction emotion of the user is determined to reach the preset degree according to the consultation problem of the user in the current human-computer session, triggering a manual condition; and if the consultation problem of the user in the current human-computer conversation comprises the relevant expression of manual conversion, triggering the manual conversion condition. The manual condition is triggered as long as one of the conditions is met.

The artificial customer servicegroup matching module 405 is configured to match the current human-machine conversation content with a pre-established artificial customer service group-conversation information mapping relationship according to the historical human-machine conversation content under the condition that the current human-machine conversation content is triggered to be changed into an artificial condition, so as to obtain a response artificial customer service group.

The manual customer servicegroup matching module 405 includes functional sub-modules for implementing the operations S251 and S252 described above.

According to the embodiment of the disclosure, the group of man-machine conversation contents is selected from the historical man-machine conversation contents in a time reverse order mode, and the next group of man-machine conversation contents is matched under the condition that the current group of man-machine conversation contents cannot be matched with the artificial customer service group.

Therequest sending module 406 is configured to initiate a forwarding request designating the answering human customer service group to the human customer service system.

Any number of modules, sub-modules, units, sub-units, or at least part of the functionality of any number thereof according to embodiments of the present disclosure may be implemented in one module. Any one or more of the modules, sub-modules, units, and sub-units according to the embodiments of the present disclosure may be implemented by being split into a plurality of modules. Any one or more of the modules, sub-modules, units, sub-units according to embodiments of the present disclosure may be implemented at least in part as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in any other reasonable manner of hardware or firmware by integrating or packaging a circuit, or in any one of or a suitable combination of software, hardware, and firmware implementations. Alternatively, one or more of the modules, sub-modules, units, sub-units according to embodiments of the disclosure may be at least partially implemented as a computer program module, which when executed may perform the corresponding functions.

For example, any number of the receivingmodule 401, theintention identifying module 402, the replyingmodule 403, the determiningmodule 404, the manual customer servicegroup matching module 405, and therequest sending module 406 may be combined in one module to be implemented, or any one of the modules may be split into a plurality of modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of the other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the receivingmodule 401, theintention identifying module 402, the replyingmodule 403, the determiningmodule 404, the manual customer servicegroup matching module 405, and therequest sending module 406 may be at least partially implemented as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented by hardware or firmware in any other reasonable manner of integrating or packaging a circuit, or implemented by any one of three implementations of software, hardware, and firmware, or by a suitable combination of any of them. Alternatively, at least one of the receivingmodule 401, theintent recognition module 402, the replyingmodule 403, the determiningmodule 404, the artificial customer servicegroup matching module 405, and therequest sending module 406 may be at least partially implemented as a computer program module that, when executed, may perform corresponding functions.

A third exemplary embodiment of the present disclosure provides an intelligent customer service system. The intelligent customer service system comprises: one or more processors; and storage means for storing one or more programs. Wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement any of the methods described above.

FIG. 8 schematically illustrates a block diagram of an intelligent customer service system according to an embodiment of the present disclosure.

Referring to fig. 8, an intelligentcustomer service system 500 according to an embodiment of the present disclosure includes aprocessor 501 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)502 or a program loaded from astorage section 508 into a Random Access Memory (RAM) 503. Theprocessor 501 may comprise, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or associated chipset, and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), among others. Theprocessor 501 may also include onboard memory for caching purposes.Processor 501 may include a single processing unit or multiple processing units for performing different actions of a method flow according to embodiments of the disclosure.

In theRAM 503, various programs and data necessary for the operation of the intelligentcustomer service system 500 are stored. Theprocessor 501, the ROM502, and theRAM 503 are connected to each other by abus 504. Theprocessor 501 performs various operations of the method flows according to the embodiments of the present disclosure by executing programs in the ROM502 and/or theRAM 503. Note that the programs may also be stored in one or more memories other than the ROM502 and theRAM 503. Theprocessor 501 may also perform various operations of method flows according to embodiments of the present disclosure by executing programs stored in the one or more memories.

According to an embodiment of the present disclosure, the intelligentcustomer service system 500 may further include an input/output (I/O)interface 505, the input/output (I/O)interface 505 also being connected to thebus 504. The intelligentcustomer service system 500 may also include one or more of the following components connected to the I/O interface 505: aninput portion 506 including a keyboard, a mouse, and the like; anoutput portion 507 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; astorage portion 508 including a hard disk and the like; and acommunication section 509 including a network interface card such as a Local Area Network (LAN) card, a modem, or the like. Thecommunication section 509 performs communication processing via a network such as the internet. Thedriver 510 is also connected to the I/O interface 505 as necessary. Aremovable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on thedrive 510 as necessary, so that a computer program read out therefrom is mounted into thestorage section 508 as necessary.

A fourth exemplary embodiment of the present disclosure provides a customer service system. The customer service system includes: the intelligent customer service switching device or the intelligent customer service system and the artificial customer service system are adopted. The artificial customer service system is used for receiving the switching request initiated by the device or the intelligent customer service system and carrying out idle artificial customer service switching in a response artificial customer service group appointed by the switching request.

Fig. 9 schematically shows a block diagram of a customer service system according to an embodiment of the present disclosure.

In fig. 9, thecustomer service system 600 includes an intelligentcustomer service system 601 and an artificialcustomer service system 602 as an example. In this embodiment, the manualcustomer service system 602 is configured to receive a forwarding request initiated by the intelligent customer service system, and perform idle manual customer service forwarding in a response manual customer service group specified by the forwarding request.

A fifth exemplary embodiment of the present disclosure provides a computer-readable storage medium. The above-described computer-readable storage medium has stored thereon executable instructions that, when executed by a processor, cause the processor to implement any of the methods described above.

The computer-readable storage medium may be embodied in the apparatus/device/system described in the above embodiments; or may exist separately and not be assembled into the device/apparatus/system. The computer-readable storage medium carries one or more programs which, when executed, implement the method according to an embodiment of the disclosure.

According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the present disclosure, a computer-readable storage medium may include ROM502 and/orRAM 503 and/or one or more memories other than ROM502 andRAM 503 described above.

A sixth exemplary embodiment of the present disclosure provides a computer program product. The computer program product comprises computer executable instructions which, when executed, are operable to implement any of the methods as described above.

The computer program product of an embodiment of the disclosure includes a computer program, carried on a computer-readable storage medium, containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through thecommunication section 509, and/or installed from theremovable medium 511. The computer program, when executed by theprocessor 501, performs the above-described functions defined in the system of the embodiments of the present disclosure. The systems, devices, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.

The computer program, when executed by theprocessor 501, performs the above-described functions defined in the system/apparatus of the embodiments of the present disclosure. The systems, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.

In one embodiment, the computer program may be hosted on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program may also be transmitted, distributed in the form of a signal on a network medium, downloaded and installed through thecommunication section 509, and/or installed from theremovable medium 511. The computer program containing program code may be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

In accordance with embodiments of the present disclosure, program code for executing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, these computer programs may be implemented using high level procedural and/or object oriented programming languages, and/or assembly/machine languages. The programming language includes, but is not limited to, programming languages such as Java, C + +, python, the "C" language, or the like. The program code may execute entirely on the user computing device, partly on the user device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Those skilled in the art will appreciate that various combinations and/or combinations of features recited in the various embodiments and/or claims of the present disclosure can be made, even if such combinations or combinations are not expressly recited in the present disclosure. In particular, various combinations and/or combinations of the features recited in the various embodiments and/or claims of the present disclosure may be made without departing from the spirit or teaching of the present disclosure. All such combinations and/or associations are within the scope of the present disclosure.

The embodiments of the present disclosure have been described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described separately above, this does not mean that the measures in the embodiments cannot be used in advantageous combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be devised by those skilled in the art without departing from the scope of the present disclosure, and such alternatives and modifications are intended to be within the scope of the present disclosure.

Claims (11)

1. A method of intelligent customer service switching, the method comprising:

receiving a consultation problem of a user;

identifying a user intention according to the consultation problem;

replying the consultation problem based on a response knowledge point which is acquired from a response knowledge point base and matched with the user intention;

determining whether the current man-machine conversation content triggers a manual conversion condition;

if the current man-machine conversation content triggers a manual-switching condition, matching according to the historical man-machine conversation content and a pre-established mapping relation between the manual customer service group and the conversation information to obtain a response manual customer service group; and

and initiating a transfer request for designating the response manual customer service group to the manual customer service system.

2. The method of claim 1, wherein the dialog information comprises at least one of: consultation questions, identified user intentions, identified user emotions, answering knowledge points and answering answers of the user; in the mapping relationship between the artificial customer service group and the dialogue information, matching is performed based on skills of the artificial customer service group and at least one of the consultation questions of the user, the user intention, the user emotion, the response knowledge point and the reply answer.

3. The method of claim 1, wherein the mapping relationship comprises: a first mapping relation of the artificial customer service group-response knowledge points and a second mapping relation of the artificial customer service group-response answers; the first mapping relation and the second mapping relation have a preset priority order;

the step of obtaining the response artificial customer service group according to the historical man-machine conversation content and the mapping relation between the pre-established artificial customer service group and the conversation information in a matching mode comprises the following steps:

matching a group of man-machine conversation contents in historical man-machine conversation contents with an artificial customer service group based on a mapping relation with higher priority in the first mapping relation and the second mapping relation to obtain a response artificial customer service group;

and under the condition that the response manual skill cannot be obtained by matching the group of man-machine conversation contents based on the mapping relation with higher priority, matching the group of man-machine conversation contents based on the mapping relation with lower priority.

4. The method of claim 3, wherein the set of human-machine conversation contents is selected from the historical human-machine conversation contents in a time-reversed manner, and the matching of the next set of human-machine conversation contents is performed in the case that the current set of human-machine conversation contents does not match the human-machine service group.

5. The method of claim 1, further comprising: establishing a mapping relation of an artificial customer service group and dialogue information in advance;

the pre-established mapping relationship between the artificial customer service group and the dialogue information comprises the following steps:

acquiring historical reply answers corresponding to historical consultation questions of a user, identified user intentions and identified user emotions;

acquiring all response knowledge points in a response knowledge point library; and

and matching the skills of the artificial customer service group with at least one of the historical consultation questions of the user, the identified user intention, the identified user emotion, all the response knowledge points and the historical reply answers to obtain the mapping relation of the artificial customer service group and the conversation information.

6. The method of claim 1, wherein said determining whether current human machine session content triggers a manual condition comprises:

if the number of times that the user intention identified by the consultation problem of the user in the current human-computer conversation is the same as the user intention identified in the historical human-computer conversation of the human-computer conversation interface exceeds a set value is detected, triggering a manual-switching condition;

if the number of times of continuous repetition of the consultation problem of the user is identified to exceed a preset value, triggering a manual condition;

if the dissatisfaction emotion of the user is determined to reach the preset degree according to the consultation problem of the user in the current human-computer session, triggering a manual condition;

and if the consultation problem of the user in the current human-computer conversation comprises the relevant expression of manual conversion, triggering the manual conversion condition.

7. The method of claim 1, wherein,

if the current man-machine conversation content triggers a manual-to-manual condition, generating a manual-to-manual machine response message;

under the condition that a response artificial customer service group is matched, adding the identification of the response artificial customer service group into the manual machine response message;

the sending a transfer request for designating the response manual customer service group to the manual customer service system comprises:

and converting the manual machine response message carrying the identification of the response manual customer service group into a message protocol format recognizable by the manual customer service system and then sending the message protocol format to the manual customer service system.

8. An apparatus for intelligent customer service switching, comprising:

the receiving module is used for receiving the consultation problem of the user;

the intention identification module is used for identifying the intention of the user according to the consultation question;

the reply module is used for replying the consultation problem based on the response knowledge point which is acquired from the response knowledge point base and matched with the user intention;

the determining module is used for determining whether the current man-machine conversation content triggers a manual conversion condition;

the artificial customer service group matching module is used for matching according to the historical human-computer conversation content and the mapping relation between the pre-established artificial customer service group and the conversation information to obtain a response artificial customer service group under the condition that the current human-computer conversation content is triggered to be changed into an artificial condition; and

and the request sending module is used for sending a switching request for appointing the answering manual customer service group to the manual customer service system.

9. An intelligent customer service system comprising:

one or more processors; and

a storage device for storing one or more programs,

wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-6.

10. A customer service system comprising:

the apparatus of claim 8 or the intelligent customer service system of claim 9; and

and the artificial customer service system is used for receiving the switching request initiated by the device or the intelligent customer service system and carrying out idle artificial customer service switching in a response artificial customer service group appointed by the switching request.

11. A computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to implement the method of any one of claims 1-7.

Images