CN116909400A

CN116909400A - Method, device, equipment and medium for converting human service based on man-machine conversation

Info

Publication number: CN116909400A
Application number: CN202310901086.4A
Authority: CN
Inventors: 黄靓; 张佳琦; 郭欣怡; 陈思同
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2023-07-21
Filing date: 2023-07-21
Publication date: 2023-10-20

Abstract

The disclosure provides a method for transferring manual service, which can be used in the technical field of big data, and comprises the following steps: acquiring man-machine interaction information input by a user in a first time period, and judging whether the man-machine interaction information contains a conversion manual intention or not; responding to an instruction containing the transfer manual intention, judging whether attribute information of man-machine interaction information corresponding to the transfer manual intention meets preset conditions or not, wherein the preset conditions are used for determining the sufficient interaction condition of a user and a machine; responding to the instruction that the attribute information meets the preset condition, and transferring the user to a manual service seat; and responding to the instruction that the attribute information does not meet the preset condition, pushing a hot spot problem list and a manual service transferring entrance list to a user, wherein the hot spot problem list comprises at least one hot spot problem and a solution associated with the at least one hot spot problem, and the category of the manual service transferring entrance in the manual service transferring entrance list is the same as the category of the hot spot problem. An apparatus for transferring manual service, an electronic device and a storage medium are also provided.

Description

Method, device, equipment and medium for converting human service based on man-machine conversation

Technical Field

The present disclosure relates to the field of big data technology, and more particularly, to a method, an apparatus, an electronic device, a computer readable storage medium, and a computer program product for transferring a manual service based on a human-machine conversation.

Background

Along with the development of information technology, the Internet becomes an important channel for people to communicate and process daily transactions, and social media has a great influence and gradually permeates into the financial field. The bank effectively solves the related problems of the clients by adopting a new client service mode, for example, a communication bridge between a user group and the bank is constructed through intelligent customer service of an online man-machine conversation, the problem solving efficiency can be improved better, the cost of manual customer service personnel is reduced, and further the customer experience is improved.

Because of a certain limitation of a customer service mode of a man-machine conversation, for example, some problems of difficult and complicated problems or problems with low occurrence probability cannot be effectively solved by a man-machine conversation mode, and a user needs to be transferred to a manual seat for processing. However, when the man-machine conversation is adopted, many users directly skip the man-machine conversation step and enter the manual seat to wait for processing, on one hand, the manual seat is busy, the customer service pressure of the manual seat is increased, and on the other hand, for the simple problem, more time is spent, the labor cost of the manual seat is wasted, and meanwhile, the customer service experience of the user is reduced.

Disclosure of Invention

In view of the above problems, the present disclosure provides a method, an apparatus, an electronic device, a readable storage medium and a computer program product for transferring a human service based on a human-machine conversation, which can determine whether to transfer a user to a human service seat according to the sufficient interaction condition between the user and a machine after the user transfers the input of the transfer manual intention, effectively reduce the pressure of the human service seat, and improve the user experience.

One aspect of the present disclosure provides a method of transferring human services based on human-machine conversation, including but not limited to: acquiring man-machine interaction information input by a user in a first time period, and judging whether the man-machine interaction information contains a conversion manual intention or not; responding to an instruction containing the manual transfer intention, judging whether attribute information of man-machine interaction information corresponding to the manual transfer intention meets preset conditions or not, wherein the preset conditions are used for determining the sufficient interaction condition of a user and a machine; responding to the instruction that the attribute information meets the preset condition, and transferring the user to a manual service seat; and responding to an instruction that the attribute information does not meet a preset condition, pushing a hot spot problem list and a manual service transferring entrance list to a user, wherein the hot spot problem list comprises at least one hot spot problem and a solution associated with the at least one hot spot problem, and the category of the manual service transferring entrance in the manual service transferring entrance list is the same as the category of the hot spot problem.

In some embodiments of the present disclosure, the attribute information includes: when the man-machine interaction information associated with the transfer manual intention is input, the interaction turn of the user and the machine is performed; in the interaction turn of the user and the machine, the input times of man-machine interaction information associated with the transfer manual intention are counted; and when the man-machine interaction information associated with the manual intent is input, the interaction times of the user and the machine in the current interaction round are displayed.

In some embodiments of the present disclosure, determining whether attribute information of man-machine interaction information corresponding to the transfer manual intention satisfies a preset condition includes: when the man-machine interaction information related to the manual transfer intention is input, judging whether the interaction turn of the user and the machine meets a first set value; in the interaction turn of the user and the machine, judging whether the input times of the man-machine interaction information related to the transfer manual intention meet a second set value or not; and when the man-machine interaction information related to the manual intent is input, judging whether the interaction times of the user and the machine in the current interaction round meet a third set value or a fourth set value, wherein the fourth set value is smaller than the third set value.

In some embodiments of the present disclosure, the attribute information satisfying a preset condition includes: when the man-machine interaction information associated with the transfer manual intention is input, the interaction round of the user and the machine is smaller than or equal to a first set value, and in the interaction round of the user and the machine, the input times of the man-machine interaction information associated with the transfer manual intention are smaller than or equal to a second set value, and when the man-machine interaction information associated with the transfer manual intention is input, the interaction times of the user and the machine in the current interaction round are larger than a third set value.

In some embodiments of the present disclosure, the attribute information satisfying a preset condition includes: when the man-machine interaction information associated with the transfer manual intention is input, the interaction time of the user and the machine is larger than a first set value, and when the man-machine interaction information associated with the transfer manual intention is input, the interaction time of the user and the machine in the current interaction time is larger than a fourth set value.

In some embodiments of the present disclosure, the attribute information satisfying a preset condition includes: when the man-machine interaction information associated with the transfer manual intention is input, the interaction turn of the user and the machine is smaller than or equal to a first set value, and in the interaction turn of the user and the machine, the input times of the man-machine interaction information associated with the transfer manual intention are larger than a second set value.

In some embodiments of the present disclosure, responding to the instruction that the attribute information satisfies the preset condition, transferring the user to the manual service seat includes: responding to an instruction that the attribute information meets a preset condition, and determining the intention category of the transfer manual intention according to the man-machine interaction information; judging whether the intention category is contained in a first preset category set or not, if so, transferring the user into a manual service seat, wherein the category of the manual service seat is the same as the intention category; if the intention category is not included in the first preset category, pushing a high-frequency category list to the user, and transferring the user to a manual service seat with the same category as the determined category according to the category determined by the user from the high-frequency category list.

In some embodiments of the present disclosure, the hotspot problem includes a classification hotspot problem and a global hotspot problem, and in response to an instruction that the attribute information does not meet a preset condition, pushing a hotspot problem list and a manual service portal list to a user includes: responding to the instruction that the attribute information does not meet the preset condition, and determining the intention category of the transfer manual intention according to the man-machine interaction information; judging whether the intention category is contained in a second preset category set, if so, pushing a classified hot spot problem list and a manual service conversion inlet list to a user, wherein the category of the classified hot spot problem list and the category of the manual service conversion inlet list are the same as the intention category; if the intention category is not contained in the second preset category set, pushing a global hot spot problem list and a manual service transferring entrance list to a user, wherein the category of the global hot spot problem in the global hot spot problem list is the same as the category of the manual service transferring entrance in the manual service transferring entrance list, and the global hot spot problem in the global hot spot problem list is obtained by sorting the classified hot spot problems according to heat.

In some embodiments of the disclosure, the method further comprises: before pushing a hotspot problem list to a user, generating a hotspot problem, the hotspot problem having an associated solution, the generating the hotspot problem comprising: generating a hot spot problem according to man-machine interaction information of all users in a historical time period; generating a hot spot problem according to the interaction information of all users with the manual service seat in the historical time period; generating a hot spot problem according to user behavior data of a user in a historical time period, wherein the hot spot problem is associated with the user; and generating a hot spot problem according to the question and answer data in the third party database.

In some embodiments of the disclosure, the method further comprises: after the user is transferred to the manual service seat, determining the latest intention category of the transfer manual intention according to the man-machine interaction information input by the user in the second time period; and transferring the user from the current manual service position to the latest manual service position associated with the latest intention category according to the latest intention category.

Another aspect of the disclosed embodiments provides a device for transferring a manual service based on a man-machine conversation, including: the first judging module is configured to acquire man-machine interaction information input by a user in a first time period and judge whether the man-machine interaction information contains a conversion manual intention or not; the second judging module is configured to respond to the instruction containing the manual transfer intention and judge whether attribute information of man-machine interaction information corresponding to the manual transfer intention meets preset conditions or not, wherein the preset conditions are used for determining the sufficient interaction condition of a user and a machine; the manual transfer module is configured to transfer the user to a manual service seat in response to an instruction that the attribute information meets a preset condition; and the pushing module is configured to respond to an instruction that the attribute information does not meet a preset condition, push a hot spot problem list and a manual service transferring entrance list to a user, wherein the hot spot problem list comprises at least one hot spot problem and a solution associated with the at least one hot spot problem, and the category of the manual service transferring entrance in the manual service transferring entrance list is the same as the category of the hot spot problem.

In some embodiments of the present disclosure, the second determination module includes a determination subunit configured to: when the man-machine interaction information related to the manual transfer intention is input, judging whether the interaction turn of the user and the machine meets a first set value; in the interaction turn of the user and the machine, judging whether the input times of the man-machine interaction information related to the transfer manual intention meet a second set value or not; and when the man-machine interaction information related to the manual intent is input, judging whether the interaction times of the user and the machine in the current interaction round meet a third set value or a fourth set value, wherein the fourth set value is smaller than the third set value.

In some embodiments of the present disclosure, the transfer manual module includes a transfer manual unit configured to: responding to an instruction that the attribute information meets a preset condition, and determining the intention category of the transfer manual intention according to the man-machine interaction information; judging whether the intention category is contained in a first preset category set or not, if so, transferring the user into a manual service seat, wherein the category of the manual service seat is the same as the intention category; if the intention category is not included in the first preset category, pushing a high-frequency category list to the user, and transferring the user to a manual service seat with the same category as the determined category according to the category determined by the user from the high-frequency category list.

In some embodiments of the present disclosure, the hotspot problem includes a classification hotspot problem and a global hotspot problem, and the pushing module includes a pushing unit configured to: responding to the instruction that the attribute information does not meet the preset condition, and determining the intention category of the transfer manual intention according to the man-machine interaction information; judging whether the intention category is contained in a second preset category set, if so, pushing a classified hot spot problem list and a manual service conversion inlet list to a user, wherein the category of the classified hot spot problem list and the category of the manual service conversion inlet list are the same as the intention category; if the intention category is not contained in the second preset category set, pushing a global hot spot problem list and a manual service transferring entrance list to a user, wherein the category of the global hot spot problem in the global hot spot problem list is the same as the category of the manual service transferring entrance in the manual service transferring entrance list, and the global hot spot problem in the global hot spot problem list is obtained by sorting the classified hot spot problems according to heat.

In some embodiments of the present disclosure, the apparatus further includes a hotspot problem generation module configured to: before pushing a hotspot problem list to a user, generating a hotspot problem, the hotspot problem having an associated solution, the generating the hotspot problem comprising: generating a hot spot problem according to man-machine interaction information of all users in a historical time period; generating a hot spot problem according to the interaction information of all users with the manual service seat in the historical time period; generating a hot spot problem according to user behavior data of a user in a historical time period, wherein the hot spot problem is associated with the user; and generating a hot spot problem according to the question and answer data in the third party database.

In some embodiments of the present disclosure, the apparatus further comprises a switch module configured to: after the user is transferred to the manual service seat, determining the latest intention category of the transfer manual intention according to the man-machine interaction information input by the user in the second time period; and transferring the user from the current manual service position to the latest manual service position associated with the latest intention category according to the latest intention category.

Another aspect of the disclosure provides an electronic device comprising one or more processors and a storage device for storing executable instructions that when executed by the processors implement the method as above.

Another aspect of the present disclosure provides a computer-readable storage medium storing computer-executable instructions that, when executed, are configured to implement a method as above.

Another aspect of the present disclosure provides a computer program comprising computer executable instructions which when executed are for implementing a method as above.

According to the embodiment of the disclosure, after receiving the transfer manual intention of the user in the man-machine interaction information, whether the user performs sufficient interaction with the machine or not is judged, if the user performs sufficient interaction, the user is transferred to the manual service seat, and if the user does not perform sufficient interaction, the hot spot problem is pushed to the user, so that the problem that the pressure of the manual service seat is increased due to the fact that the user directly skips the man-machine interaction is avoided, and meanwhile, the hit rate of the user problem is improved by pushing the hot problem list to the user, and the user problem is effectively solved.

Drawings

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

FIG. 1 schematically illustrates a schematic diagram of a system architecture to which a human-to-machine conversation based method of manual service may be applied in accordance with embodiments of the present disclosure;

FIG. 2 schematically illustrates a flow chart of a method of transferring manual services based on a human-machine conversation in accordance with an embodiment of the present disclosure;

FIG. 3 schematically illustrates a flowchart of a method of transferring a manual service based on a human-machine conversation in operation S230, according to an embodiment of the present disclosure;

FIG. 4 schematically illustrates a flowchart of a method of transferring a manual service based on a human-machine conversation in operation S240, according to an embodiment of the present disclosure;

FIG. 5 schematically illustrates a flow chart of a method of manually servicing a human-machine based conversation in generating a hotspot problem, in accordance with an embodiment of the present disclosure;

FIG. 6 schematically illustrates a flow chart of a method of transferring manual services based on a human-machine conversation after transferring a user to a manual service agent in accordance with an embodiment of the present disclosure;

FIG. 7 schematically illustrates a process diagram of a method of transferring manual services based on a human-machine conversation in accordance with an embodiment of the present disclosure;

FIG. 8 schematically illustrates a block diagram of an apparatus for transferring manual services based on a human-machine conversation in accordance with an embodiment of the present disclosure; and

fig. 9 schematically illustrates a block diagram of an electronic device according to an embodiment of the 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 only exemplary 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 present disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. In addition, in the following description, descriptions of well-known structures and techniques are omitted so as not to 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/or 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 should be noted that the terms used herein should be construed to have meanings consistent with the context of the present specification and should not be construed in an idealized or overly formal manner.

Where a formulation similar to at least one of "A, B or C, etc." is used, in general such a formulation should be interpreted in accordance with the ordinary understanding of one skilled in the art (e.g. "a system with at least one of A, B or C" would include but not be limited to systems with 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 terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more features.

In the technical scheme of the disclosure, the acquisition, storage, application and the like of the related personal information of the user all conform to the regulations of related laws and regulations, necessary security measures are taken, and the public order harmony is not violated.

In the technical scheme of the disclosure, related operations such as acquisition, storage, application and the like of the personal information of the user are all authorized by the user.

In this context, the term "man-machine interaction information" refers to interaction information between a user and a machine, e.g. the user inputs a question to the machine, which gives a solution to the question according to the user input. The man-machine interaction information can be interaction information in a text form, and can also be interaction information in other forms such as voice, video and the like.

The term "turning to the artificial intention" refers to the intention of a user to turn to the intention of the user to perform a conversation with a human customer service in the process that the user performs communication in a system or platform of a human-computer conversation, and the "turning to the artificial intention" may be determined according to one or more human-computer interaction information input by the user, and the turning to the artificial intention may be directly in the human-computer interaction information or inferred from the one or more human-computer interaction information.

Herein, the term "attribute information" refers to data describing or defining characteristics of man-machine interaction information corresponding to a transfer manual intention, and may specifically refer to one or more characteristics of the man-machine interaction information, and in this embodiment, the attribute information may include, for example, an interaction round of the man-machine interaction information, the number of interactions per round, and the number of inputs of the man-machine interaction information corresponding to the transfer manual intention.

As used herein, the term "hot spot problem" refers to the problem that the user consults most, or some associated technical feature that is the most likely to be faulty in a system, software, or program, over a period of time. The "hot spot problem" only occurs within a certain period of time, and as time passes and/or problems are resolved, the hot spot problem in the former period of time may become a non-hot spot problem in the latter period of time, and new hot spot problems will occur. In this embodiment, the hot spot problem may be obtained based on man-machine interaction information data, history data, third party data, or the like, or may be manually specified, where the hot spot problem has different categories.

Herein, the term "classifying the hot spot problem" refers to classifying the hot spot problem, and the hot spot problem satisfying the set heat is determined in each category. Herein, the term "global hot spot problem" refers to a hot spot problem that is obtained by sorting all hot spot problems and satisfies a set heat.

In this document, the term "manual service portal" refers to an interface that allows a user to talk to a real manual client when man-machine interaction is performed, and the user clicks or enters the manual service portal to change the state of the user to talk to the machine to the state of the user to talk to the manual, so as to solve the problem that the machine cannot solve.

As used herein, the term "interactive turn" refers to a turn of a user's interaction with a machine while opening or entering an interactive interface during a human-machine interaction. The interaction turn is determined according to the time when the user opens or enters the interaction interface, closes or leaves the interaction interface and the interaction time of the user at the interaction interface. For example, the user opens or enters the interactive interface as the beginning of each interactive turn, closes or leaves the interactive interface as the end of each interactive turn, and the user is one interactive turn when the interactive time of the interactive interface is less than a set value. When the interaction event of the user on the interaction interface is larger than the set value, determining each set value duration as an interaction round.

As used herein, the term "number of interactions" refers to the number of times a user enters information into a machine during a human-machine interaction, such as every time a portion of the content is entered, the content is submitted to the machine, and feedback information is received from the machine based on the entered content, the number of interactions being one.

The term "intention category" refers to a category to which the turning manual intention belongs, and the turning manual intention can be divided into different categories according to different man-machine interaction information input by a user, namely the intention category of the turning manual intention.

Herein, the term "high frequency category" refers to one or more categories having a higher frequency of occurrence among intention categories determined based on a trans-manual intention.

In the prior art, in order to improve the efficiency of customer service, the problem of simplicity is generally solved by setting a man-machine interaction system or platform. Specifically, for the problem that the user needs to consult, firstly, the problem of the user is judged through man-machine interaction, and a solution is further provided, when the problem of the user cannot be solved, or after the user proposes the intention of turning to manual, the user is turned to manual service to solve the problem of the user. However, because part of the user consultation habits or consider that the man-machine interaction cannot directly solve the problem, when the user enters a man-machine interaction system or platform to interact, the process of directly skipping the man-machine interaction often occurs, the user directly inputs the intention of converting to the manual service, and the user enters a manual service seat to wait in a queue. Because the number of the manual service personnel is limited, the problem that the manual service personnel is relatively simple can be solved through human-computer interaction, the manual service personnel can be directly transferred into the manual service seat to carry out queuing waiting, and after the manual service seat is accessed, the manual service seat needs to spend a certain time to know the customer problem and answer, and on one hand, the problem that the manual service can be simply solved through human-computer interaction is solved but the manual service is needed to answer, so that the waste of manual service resources is caused. On the other hand, after the manual service is accessed, a certain time is required to know the specific problem, and more time is wasted. In addition, after the user shifts to the manual service seat, the user needs to wait, so that the manual service resource is tense, and the consultation experience of the user is reduced.

In order to solve the above-mentioned problems, embodiments of the present disclosure provide a method, an apparatus, an electronic device, a readable storage medium, and a computer program product for transferring a manual service based on a man-machine conversation, which can determine whether to transfer a user to a manual service seat according to a sufficient interaction condition between the user and a machine after the user transfers the manual intention, effectively reduce the pressure of the manual service seat, and improve the user experience.

The method for transferring the manual service based on the man-machine conversation in the embodiment of the disclosure comprises the following steps of, but is not limited to: acquiring man-machine interaction information input by a user in a first time period, and judging whether the man-machine interaction information contains a conversion manual intention or not; responding to an instruction containing the transfer manual intention, judging whether attribute information of man-machine interaction information corresponding to the transfer manual intention meets preset conditions or not, wherein the preset conditions are used for determining the sufficient interaction condition of a user and a machine; responding to the instruction that the attribute information meets the preset condition, and transferring the user to a manual service seat; and responding to the instruction that the attribute information does not meet the preset condition, pushing a hot spot problem list and a manual service transferring entrance list to a user, wherein the hot spot problem list comprises at least one hot spot problem and a solution associated with the at least one hot spot problem, and the category of the manual service transferring entrance in the manual service transferring entrance list is the same as the category of the hot spot problem.

Fig. 1 schematically illustrates a schematic diagram of a system architecture to which a human-to-machine conversation-based method of transferring human services of embodiments of the present disclosure may be applied. It should be noted that fig. 1 is only an example of a system architecture to which embodiments of the present disclosure may be applied to assist those skilled in the art in understanding the technical content of the present disclosure, but does not mean that embodiments of the present disclosure may not be used in other devices, systems, environments, or scenarios. It should be noted that, the method for converting human-machine conversation into manual service provided by the embodiment of the present disclosure may be used in the big data technical field, the financial field in the relevant aspect of the big data field, and also may be used in any field other than the financial field, and the method and apparatus for converting human-machine conversation into manual service provided by the embodiment of the present disclosure do not limit the application field.

As shown in fig. 1, an exemplary system architecture 100, to which a human-to-human service based approach may be applied, may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various communication client applications, such as mail client applications, file processing class applications, shopping class applications, web browser applications, search class applications, instant messaging tools, mailbox clients, social platform software, etc., may be installed on the terminal devices 101, 102, 103, as just examples.

The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting functions of data input, file transmission, data analysis, data processing, web browsing, etc., including but not limited to smartphones, tablet computers, laptop and desktop computers, etc.

The server 105 may be a server providing various services, such as a background management server (by way of example only) providing support for a user to utilize data acquired by the terminal devices 101, 102, 103 or a browsed website. The background management server may analyze and process the received data such as the user request, and feed back the processing result (e.g., the web page, information, or data obtained or generated according to the user request) to the terminal device. The file or the like transmitted by the user may be analyzed or processed, and the terminal device may be controlled based on the processing result, for example, access to the terminal device may be restricted.

It should be noted that the method for transferring the manual service based on the man-machine conversation provided by the embodiments of the present disclosure may be generally performed by the server 105. Accordingly, the device for transferring the manual service based on the man-machine conversation provided by the embodiment of the disclosure may be generally provided in the terminal devices 101, 102, 103. The method for transferring the manual service based on the man-machine conversation provided by the embodiment of the disclosure may also be performed by a terminal device different from the terminal devices 101, 102, 103 and capable of communicating with the terminal devices 101, 102, 103. Accordingly, the device for transferring the man-machine conversation-based service provided by the embodiment of the present disclosure may also be provided in a terminal device different from the terminal devices 101, 102, 103 and capable of communicating with the terminal devices 101, 102, 103.

It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

The method of transferring a manual service based on a man-machine conversation according to an embodiment of the present disclosure will be described in detail with reference to fig. 2 to 6.

Fig. 2 schematically illustrates a flow chart of a method of transferring manual services based on a man-machine conversation in accordance with an embodiment of the present disclosure.

As shown in fig. 2, a flow 200 of a method of transferring a manual service based on a man-machine conversation according to an embodiment of the present disclosure includes operations S210 to S240.

In operation S210, the man-machine interaction information input by the user in the first period of time is acquired, and whether the man-machine interaction information includes a transfer intention is determined.

In some embodiments of the present disclosure, the first time period may refer to a set time period, for example, may be one day or 12 hours, and the time period of the first time period may be adjusted according to an actual application scenario.

The information that the user is interacting with the machine is man-machine interaction information, such as user sent questions, and the machine generates solutions based on the questions sent by the user. The man-machine interaction information input by the user can directly or indirectly comprise the transfer manual intention. For example, the user may send "change to manual service", "change to manual", etc. to the machine directly including the change to manual intent human-computer interaction information, and for example, the user may send "you cannot solve my problem", "solution error", "cannot solve", etc. to the machine indirectly including the change to manual intent human-computer interaction information.

According to the embodiment of the disclosure, whether the man-machine interaction information contains the conversion manual intention is judged, so that the pre-judgment and the quick response aiming at the user requirement are realized, and the user experience of the user in service is improved.

In operation S220, in response to the instruction including the transfer manual intention, it is determined whether the attribute information of the man-machine interaction information corresponding to the transfer manual intention satisfies a preset condition, where the preset condition is used for determining a sufficient interaction condition between the user and the machine.

In some embodiments of the present disclosure, when it is determined that the human-computer interaction information includes a human-computer interaction intention, it is further determined whether attribute information of the human-computer interaction information corresponding to the human-computer interaction intention satisfies sufficient interaction between the user and the machine. After confirming that the user and the machine are fully interacted, the user can be transferred to a manual service seat to solve the problem of the user. When the user does not fully interact with the machine, the hot problem list is pushed to the user, so that the problem that the workload of manual service is increased caused by the fact that the user does not fully interact with the machine is avoided, meanwhile, the effective information of the problem to be consulted with the user is further obtained by pushing the hot problem list to the user and transferring the manual service entrance list, the time required by the manual user to determine the problem after transferring the manual service is reduced, the communication time is shortened, and the user experience is improved.

For example, the attribute information of the man-machine interaction information corresponding to the transfer manual intention may include: and when the man-machine interaction information associated with the transfer manual intention is input, the interaction turn of the user and the machine is performed.

The interaction turn of the user and the machine refers to the turn of the user when opening or entering the man-machine interaction interface to interact with the machine in the man-machine interaction process. The interaction turn is determined according to the time when the user opens or enters the interaction interface, closes or leaves the interaction interface and the interaction time of the user at the interaction interface. For example, the user opens or enters the interactive interface as the beginning of each interactive turn, closes or leaves the interactive interface as the end of each interactive turn, and the user is one interactive turn when the interactive time of the interactive interface is less than a set value. Or when the interaction event of the user on the interaction interface is larger than the set value, determining each set value duration as one interaction round. For example, the set duration of one interaction round is 5 minutes, and when the user enters the man-machine interaction interface to interact with the machine and closes the man-machine interaction interface within 5 minutes, the set duration is one interaction round. For another example, when the user enters the human-machine interaction interface to interact with the machine and closes the human-machine interaction interface within 13 th minute, one interaction round is determined every 5 minutes, and the total is 3 interaction rounds.

For example, the attribute information of the man-machine interaction information corresponding to the transfer manual intention may further include: and in the interaction turn of the user and the machine, the input times of the man-machine interaction information associated with the transfer manual intention are counted.

For example, when it is determined that the human-computer interaction information includes the transfer manual intention, the count of the input times of the human-computer interaction information associated with the transfer manual intention is determined to be increased by 1, for example, in one interaction round, when the user inputs 3 human-computer interaction information including the transfer manual intention, the input times of the human-computer interaction information associated with the transfer manual intention is determined to be 3.

For example, the attribute information of the man-machine interaction information corresponding to the transfer manual intention may further include: and when the man-machine interaction information associated with the manual intention is input, the interaction times of the user and the machine in the current interaction turn are counted.

The interaction times refer to the times that a user inputs information to a machine in each interaction round, for example, each time a part of content is input, the content is submitted to the machine, and after the machine receives the content input by the user, the machine receives feedback information based on the input content, and the interaction times are one interaction times, namely, in one interaction round, one answer is one interaction times of the interaction round.

According to the embodiment of the disclosure, the full interaction condition of the user and the machine is more accurately judged by determining the interaction times, the input times and the interaction times.

In some embodiments of the present disclosure, whether the attribute information of the man-machine interaction information corresponding to the transfer manual intention satisfies the preset condition is determined according to one or more of the attribute information.

In some embodiments of the present disclosure, determining whether attribute information of man-machine interaction information corresponding to a transfer manual intention satisfies a preset condition includes: and when the man-machine interaction information related to the manual intention is input, judging whether the interaction turn of the user and the machine meets a first set value. In the interaction turn of the user and the machine, judging whether the input times of the man-machine interaction information related to the transfer manual intention meet a second set value. When the man-machine interaction information related to the manual intention is input, judging whether the interaction times of the user and the machine in the current interaction round meet a third set value or a fourth set value, wherein the fourth set value is smaller than the third set value.

In some embodiments of the present disclosure, the user's full interaction with the machine is determined by determining whether the attribute information of the human-machine interaction information satisfies one or more of the above-mentioned preset conditions.

For example, the first setting value may be 1, that is, when the man-machine interaction information associated with the transfer manual intention is input, it is determined whether the interaction round of the user with the machine is less than or equal to 1.

The second set value may be 1, that is, in the interaction round of the user and the machine, whether the input number of times of the man-machine interaction information associated with the transfer manual intention is less than or equal to 1 time is judged.

The third set value may be 10, that is, when the man-machine interaction information associated with the transfer manual intention is input, it is determined whether the number of interactions between the user and the machine in the current interaction round is greater than 10.

The fourth set value may be 5, that is, when the man-machine interaction information associated with the transfer manual intention is input, it is determined whether the number of interactions between the user and the machine in the current interaction round is greater than 5.

In some optional embodiments, the first setting value, the second setting value, the third setting value and the fourth setting value may be set and adjusted according to actual needs, so as to meet the needs of different application scenarios.

And by combining the results of the preset conditions, whether the user and the machine interact sufficiently or not is further judged based on the combined results. The problem of communication efficiency reduction caused by the fact that a user does not interact with a machine fully and shifts to a manual service seat is prevented. According to the human-computer interaction information input by the user even if the human-computer interaction information comprises the human-computer interaction intention, whether the attribute information of the human-computer interaction information meets the preset condition is judged, so that the full interaction condition of the user and the machine is accurately judged.

In some embodiments of the present disclosure, the attribute information satisfying the preset condition includes: when the man-machine interaction information associated with the transfer manual intention is input, the interaction round of the user and the machine is smaller than or equal to a first set value, and in the interaction round of the user and the machine, the input times of the man-machine interaction information associated with the transfer manual intention are smaller than or equal to a second set value, and when the man-machine interaction information associated with the transfer manual intention is input, the interaction times of the user and the machine in the current interaction round are larger than a third set value.

For example, when the man-machine interaction information input by the user includes a transfer manual intention, it is firstly determined whether the interaction round of the user and the machine is less than or equal to 1 time, if the interaction round of the user and the machine is 1 time, it is further determined whether the input time of the man-machine interaction information associated with the transfer manual intention is less than or equal to 1 time when the man-machine interaction information including the transfer manual intention is received, if yes, it is further determined whether the interaction time of the user and the machine in the current interaction round is more than 10 times, if the interaction time of the user and the machine in the current interaction round is more than 10 times, the attribute information satisfies the preset condition, if the interaction time of the user and the machine in the current interaction round is not more than 10 times, if not, the attribute information does not satisfy the preset condition.

In some embodiments of the present disclosure, the attribute information satisfying the preset condition includes: when the man-machine interaction information associated with the transfer manual intention is input, the interaction round of the user and the machine is larger than a first set value, and when the man-machine interaction information associated with the transfer manual intention is input, the interaction time of the user and the machine in the current interaction round is larger than a fourth set value.

For example, when the man-machine interaction information input by the user includes a transfer manual intention, firstly judging whether the interaction round of the user and the machine is smaller than or equal to 1 time, if the interaction round of the user and the machine is larger than 1 time, further judging whether the interaction time of the user and the machine in the current interaction round is larger than 5 times when the man-machine interaction information related to the transfer manual intention is input, and if the interaction time of the user and the machine in the current interaction round is larger than 5 times, the attribute information meets the preset condition. If the interaction times of the user and the machine in the current interaction round are not more than 5 times, the attribute information does not meet the preset condition.

In some embodiments of the present disclosure, the attribute information satisfying the preset condition includes: when the man-machine interaction information associated with the transfer manual intention is input, the interaction turn of the user and the machine is smaller than or equal to a first set value, and in the interaction turn of the user and the machine, the input time of the man-machine interaction information associated with the transfer manual intention is larger than a second set value.

For example, when the man-machine interaction information input by the user includes the transfer manual intention, it is first determined whether the interaction round of the user and the machine is less than or equal to 1 time, if the interaction round of the user and the machine is less than or equal to 1 time, it is further determined whether the input time of the man-machine interaction information associated with the transfer manual intention is less than or equal to 1 time when the man-machine interaction information including the transfer manual intention is received, and if the input time of the man-machine interaction information associated with the transfer manual intention is greater than 1 time, the attribute information satisfies the preset condition.

In operation S230, the user is transferred to the manual service seat in response to the instruction that the attribute information satisfies the preset condition. When the attribute information meets the preset condition, the user is fully interacted with the machine, and the user is transferred to the manual service seat.

Fig. 3 schematically illustrates a flowchart of a method of transferring a manual service based on a man-machine conversation according to an embodiment of the present disclosure in operation S230.

As shown in fig. 3, operation S230 includes operations S231 to S232 and operations S2321 and S2322.

In operation S231, an intention type of the transfer manual intention is determined according to the man-machine interaction information in response to an instruction that the attribute information satisfies a preset condition.

In some embodiments of the present disclosure, when the attribute information satisfies a preset condition, it is explained that the user has interacted sufficiently with the machine, the man-machine interaction information is obtained, and the intention type of the transfer manual intention is determined according to the content in the man-machine interaction information.

For example, the intention category refers to a specific category of a problem that a user needs to consult, for example, in a consultation scene of a bank, the intention category of transferring manual intention can be determined to be a credit card category, a non-credit card category, a fund category and the like according to man-machine interaction information. In some other scenarios there may be more or fewer categories.

For example, determining the intention category of the transfer manual intention from the man-machine interaction information may be determined according to natural language processing technology, such as semantic determination, keyword extraction, and the like.

In operation S232, it is determined whether the intention category is included in the first preset category set.

In some embodiments of the present disclosure, the first set of preset categories is, for example, a category generated by the human-computer interaction system based on specific data, the category set including a plurality of categories, by categorizing the data, thereby facilitating resolution of the problem of user consultation based on the categories.

For example, the intention category is compared with the categories contained in the first preset category set, so as to judge whether the intention category is contained in the first preset category set.

In operation S2321, if the intention category is included in the first preset category set, the user is transferred to the manual service seat, and the category to which the manual service seat belongs is the same as the intention category.

In the embodiment of the disclosure, each manual service seat has a corresponding belonging category, and a more accurate and professional solution can be provided for the user by transferring the user to the still service seat with the corresponding category.

In operation S2322, if the intention category is not included in the first preset category, a high-frequency category list is pushed to the user, and the user is transferred to the manual service seat having the same category as the determined category according to the category determined by the user from the high-frequency category list.

The high-frequency category list may be, for example, obtained by sorting the number of questions in each category, where the frequency of occurrence of the corresponding questions in the high-frequency category is higher. When the intention category of the user's manual intention cannot be determined, the high frequency category is pushed to the user, so that the possibility of hitting the problem to be consulted by the user is improved. The high-frequency category list comprises a plurality of categories, and when the user selects the category to be consulted with the problem from the plurality of categories, the user is transferred to the manual service seat of the category.

In operation S240, in response to the instruction that the attribute information does not meet the preset condition, a hotspot problem list and a manual service transfer portal list are pushed to the user, where the hotspot problem list includes at least one hotspot problem and a solution associated with the at least one hotspot problem, and a category of the manual service transfer portal in the manual service transfer portal list is the same as a category of the hotspot problem.

In some embodiments of the present disclosure, when the attribute information does not meet the preset condition, it indicates that the user does not interact with the machine sufficiently, and further determination of a problem that the user may have is required.

Fig. 4 schematically illustrates a flowchart of a method of transferring a manual service based on a man-machine conversation according to an embodiment of the present disclosure in operation S240.

As shown in fig. 4, operation S240 includes operations S241 to S242 and operations S2421 and S2422.

In some embodiments of the present disclosure, the hotspot problems include a classification hotspot problem and a global hotspot problem.

In operation S241, an intention type of the transfer manual intention is determined according to the man-machine interaction information in response to an instruction that the attribute information does not satisfy the preset condition.

When the attribute information does not meet the preset condition, further determining the intention category of the transfer manual art map according to the man-machine interaction information input by the user.

In operation S242, it is determined whether the intention category is included in the second preset category set.

In some embodiments of the present disclosure, the second preset category set includes a plurality of categories, and by comparing whether the intent category matches the plurality of categories in the second preset category set, if the intent category matches a certain category in the second preset category set, it indicates that the intent category is included in the second preset category set.

Alternatively, the second set of preset categories may be the same as the first set of preset categories, or may be different from the first set of preset categories. For example, the category range in the second preset category set is larger than the category range in the first preset category set. When the attribute information does not meet the preset condition, the fact that the user and the machine do not perform sufficient interaction is indicated, and the fact that the input man-machine interaction information is less is possible is indicated, and the second preset category in the second preset category set can be hit the intention category better conveniently by enabling the category range in the second preset category set to be larger than the category range in the first preset category set.

In operation S2421, if the intention category is included in the second preset category set, pushing the classified hot spot question list and the manual service entry list to the user, wherein the classified hot spot question list and the manual service entry list are the same as the intention category.

In some embodiments of the present disclosure, each category has a corresponding classified hotspot problem, the classified hotspot problems under each category are listed, and a classified hotspot problem list is generated. And when the intention category is matched with one category in the second preset category set, pushing the hot spot problem list under the matched category to the user. Meanwhile, each classified hot spot problem is provided with a corresponding manual service entrance list. The category of the classified hotspot problem list and the category of the manual service entry list are the same as the intention category.

Specifically, each classified hotspot problem in the classified hotspot problem list has a corresponding sub-classification, each classified hotspot problem corresponds to a manual-to-manual service portal in the manual-to-manual service portal list, and each manual-to-manual service portal has a corresponding sub-classification. That is, the sub-classification of each classified hot spot problem is the same as the sub-classification of the manual service portal, thereby facilitating the user to determine the classification of the problem to be consulted by himself.

In operation S2422, if the intention category is not included in the second preset category set, pushing a global hotspot problem list and a manual service transfer entry list to the user, wherein the category of the global hotspot problem in the global hotspot problem list is the same as the category of the manual service transfer entry in the manual service transfer entry list, and the global hotspot problem in the global hotspot problem list is obtained by sorting the classified hotspot problems according to the hotness.

In some embodiments of the present disclosure, the global hot spot problem refers to ordering all hot spot problems, and the obtained hot spot problem meeting the set heat. For example, all the hot spot problems are ranked according to the heat degree, so that hot spots before ranking test are selected as global hot spot problems. The category of each manual-transferring service portal in the manual-transferring service portal list is the same as the category of the global people point problem in the global hot point problem list, so that a user can conveniently select the corresponding manual-transferring service portal.

Fig. 5 schematically illustrates a flowchart of a method of converting a manual service based on a man-machine conversation in generating a hotspot problem according to an embodiment of the present disclosure.

Before pushing the hotspot problem list to the user, a hotspot problem is generated, the hotspot problem having an associated solution, the generating the hotspot problem comprising operation S300.

As shown in fig. 5, operation S300 includes operation S310, operation S320, operation S330, and operation S340.

In operation S310, a hotspot problem is generated according to human-computer interaction information of all users in the historical time period.

In some embodiments of the present disclosure, in a human-computer interaction process, by performing statistics processing on human-computer interaction information of all users in a historical time period, for example, performing statistics on all users based on the same problem, the number of consultation times of different problems is obtained, and the problem with the set number of problems in the top order is used as a hot spot problem.

In operation S320, a hotspot problem is generated according to the interaction information of all users with the manual service agent in the historical time period.

In some embodiments of the present disclosure, when human-computer interaction cannot solve a problem of a user, a solution is generated for the user by transferring the user to a manual service seat, and the number of consultations of different problems is obtained by performing statistical processing on interaction information between all users and the manual service seat in a historical time period, and the problem of the number of problems set in the front order is regarded as a hot problem.

In operation S330, a hotspot problem is generated from the user behavior data of the user over the historical period of time, the hotspot problem being associated with the user.

In some embodiments of the present disclosure, each user has corresponding user behavior data, such as banking users, including transfers, deposits, purchases of financial products, and the like. According to the behavior data of the user in the historical time period, extracting the problems associated with the behavior data, sorting the problems, and generating hot spot problems, wherein the hot spot problems are associated with the user, and when the behavior data of the user in the historical time period is different, the hot spot problems corresponding to the user are also different. By generating the hotspot problem based on the user behavior data, the hotspot problem can be pushed to the user more accurately under the condition that the user does not interact fully with the machine.

In operation S340, a hotspot question is generated according to the question-answer data in the third party database.

In embodiments of the present disclosure, the third party database may be, for example, a different database than the database of the current human-machine conversation system or platform. By acquiring the question and answer data in the third party database, the coverage of man-machine interaction can be improved.

Fig. 6 schematically illustrates a flow chart of a method of transferring manual services based on a man-machine conversation after transferring a user to a manual service agent according to an embodiment of the present disclosure.

As shown in fig. 6, the method for transferring a manual service based on a man-machine conversation according to an embodiment of the present disclosure further includes a flow 400. The flow 400 includes operations S410 through S420.

In operation S410, after the user is transferred to the manual service seat, the latest intention category of the transfer manual intention is determined according to the man-machine interaction information input by the user in the second period of time.

For example, after the user is transferred to the manual service seat, there may be a problem that the judgment of the intention type of the user is wrong or the intention type of the user is changed, and the latest intention type of the transfer manual intention is more accurately determined by acquiring the man-machine interaction information input by the user in the second time period.

In operation S420, the user is transferred from the current manual service position to the latest manual service position associated with the latest intention category according to the latest intention category.

According to the embodiment of the disclosure, the user is transferred from the current manual service position to the latest manual service position associated with the latest intention category, so that more accurate manual service is provided for the user, the user is enabled to transfer the intention category without sense, and the communication efficiency and the user experience are improved.

Fig. 7 schematically illustrates a process diagram of a method of transferring manual services based on a human-machine conversation in accordance with an embodiment of the present disclosure.

As shown in fig. 7, a process 500 of a method of transferring a manual service based on a human-machine conversation includes operations S501 to S507.

As shown in fig. 7, first, in S501, a transfer manual intention is determined, which is determined according to man-machine interaction information input by a user in a first period of time.

Next, operation S502 is performed, and when the man-machine interaction information associated with the transfer manual intention is input, it is determined whether the interaction round of the user with the machine is less than or equal to the first set value. If yes, operation S503 is executed, and if no, operation S507 is executed.

In operation S503, in the interaction round of the user with the machine, it is determined whether the input number of the man-machine interaction information associated with the transfer manual intention is less than or equal to the second set value. If yes, operation S504 is executed, and if no, operation S505 is executed.

In operation S504, it is determined whether the number of interactions of the user with the machine in the current interaction round is greater than a third set value when the man-machine interaction information associated with the transfer manual intention is input. If yes, operation S505 is executed, and if no, operation S506 is executed.

In operation S505, the attribute information satisfies a preset condition, and the user is transferred to the manual service location. The specific flow of operation S505 may refer to the specific process of operation S230 described above.

In operation S506, the attribute information does not satisfy the preset condition, and the hot spot problem list and the manual service portal list are pushed to the user. The specific flow of operation S506 may refer to the specific process of operation S240 described above.

In operation S507, it is determined whether the number of interactions of the user with the machine in the current interaction round is greater than a fourth set value when the man-machine interaction information associated with the transfer manual intention is input. If yes, operation S505 is executed, and if no, operation S506 is executed.

The following describes details of a method for transferring a human service based on a human-machine conversation in detail in connection with a specific application scenario.

Step one: the user sends and changes the manual intention on the customer service interaction page.

Step two: the intelligent multi-round interaction flow judges whether the user changes the manual intention uploading to occur in the first round of conversation of the day.

Step three: if the judgment result is that the user-to-manual intention uploading occurs in the first-round conversation of the day, further judging whether the user-to-manual intention is triggered for the first time in the communication conversation.

Step four: if the judgment result is that the user is manually and intentionally uploaded at the time of the first time of the communication session, further judging whether the intelligent interaction round before the user is manually and manually uploaded at the time of the communication session is more than 10 times or not.

Step five: if the judgment result is that the intelligent interaction round before the user changes the manual intention to upload in the communication session is more than 10 times, judging the manual service classification in the manual intention of the client through a natural language processing technology.

Step six: (1) If the natural language processing technology judges that the manual service in the manual intention of the customer is classified into credit card service, non-credit card service and fund service, a manual service entrance of the corresponding credit card seat, non-credit card seat and fund seat is returned to the customer, and the customer clicks the entrance and then routes to the queuing sequence of the corresponding seat group to perform manual service; (2) If the natural language processing technology judges that no manual service classification is converted from the customer manual intention, high-frequency classification is returned to the customer at the same time, for example, the high-frequency classification comprises a credit card seat and a non-credit card seat manual service entrance, the customer selects according to the needs by himself, clicks the corresponding entrance and then routes to the corresponding seat group queuing sequence to perform manual service.

Step seven: if the judgment result in the step four is that the intelligent interaction round before the client changes the manual intention to send in the communication session is less than or equal to 10 times, judging whether the related hot spot problem of automatic grabbing or manual configuration exists currently through the intelligent multi-round interaction flow.

Step eight: if the judgment result is that the related hot spot problem of intelligent grabbing or manual configuration exists at present, the manual service classification in the manual intention of the customer is judged through a natural language processing technology.

Step nine: (1) If the natural language processing technology judges that the transfer manual service in the customer transfer manual intention is classified into credit card service, non-credit card service and fund service, a corresponding credit card seat, non-credit card seat and fund seat intelligent grabbing or manually configured hot spot problem 'guessing' list and a corresponding credit card seat, non-credit card seat and fund seat manual service entrance are returned to the customer, and the customer automatically selects to click the "guessing you want to ask" problem to obtain an intelligent question-answering result, or clicks the manual service entrance and then routes to a corresponding seat group queuing sequence to perform manual service; (2) If the natural language processing technology judges that no manual service classification is converted in the manual intention of the client, a 'guessing you want to ask' list of related hot problems which are intelligently captured or manually configured by the whole seat group and a credit card seat, a manual service entrance of a non-credit card seat are returned to the client, and the client automatically selects to click the 'guessing you want to ask' problem which is needed to be consulted to obtain an intelligent question-answering result, or clicks the manual service entrance and then routes the intelligent question-answering result to a queuing sequence of the corresponding seat group to perform manual service.

Step ten: if the judgment result in the step three is that the client-to-manual intention illegal communication session is triggered for the first time, the manual-to-manual business classification in the client-to-manual intention is judged through a natural language processing technology.

Step eleven: in the same step six

Step twelve: if the judgment result in the second step is that the manual intention uploading of the client does not occur in the first-round conversation of the current day, further judging whether the intelligent interaction round before the manual intention uploading of the client is more than 5 times in the communication conversation.

Step thirteen: if the judgment result is that the intelligent interaction round before the client changes the manual intention to be sent up in the communication session is more than 5 times, the classification of the manual business in the client changes the manual intention is judged through a natural language processing technology.

Step fourteen: and step six.

Fifteen steps: if the judgment result in the step twelve is that the intelligent interaction round before the client changes the manual intention to send in the communication session is less than or equal to 5 times, judging whether the related hot spot problem of automatic grabbing or manual configuration exists currently through the intelligent multi-round interaction flow.

Step sixteen: and the same as in step eight.

Seventeenth step: and step nine.

The above is a specific application scenario of the man-machine conversation-based manual service conversion in the embodiment of the present disclosure. According to the embodiment of the disclosure, after receiving the transfer manual intention of the user in the man-machine interaction information, whether the user performs sufficient interaction with the machine or not is judged, if the user performs sufficient interaction, the user is transferred to the manual service seat, and if the user does not perform sufficient interaction, the hot spot problem is pushed to the user, so that the problem that the pressure of the manual service seat is increased due to the fact that the user directly skips the man-machine interaction is avoided, and meanwhile, the hit rate of the user problem is improved by pushing the hot problem list to the user, and the user problem is effectively solved.

Another aspect of the present disclosure provides an apparatus for transferring a manual service based on a human-machine conversation.

Fig. 8 schematically illustrates a block diagram of an apparatus for transferring manual services based on man-machine conversation according to an embodiment of the present disclosure.

As shown in fig. 8, the device 600 for transferring a manual service based on a man-machine conversation includes a first judging module 601, a second judging module 602, a transferring manual module 603, and a pushing module 604.

The first determining module 601 is configured to obtain man-machine interaction information input by a user in a first period of time, and determine whether the man-machine interaction information includes a human intention. In an embodiment, the first determining module 601 may be configured to perform the operation S210 described above, which is not described herein.

The second judging module 602 is configured to respond to the instruction containing the transfer manual intention, and judge whether the attribute information of the man-machine interaction information corresponding to the transfer manual intention meets a preset condition, where the preset condition is used for determining the sufficient interaction condition between the user and the machine. In an embodiment, the second determining module 602 may be configured to perform the operation S220 described above, which is not described herein.

The manual transfer module 603 is configured to transfer the user to the manual service seat in response to an instruction that the attribute information satisfies a preset condition. In an embodiment, the manual transferring module 603 may be used to perform the operation S230 described above, which is not described herein.

The pushing module 604 is configured to push, to the user, a hotspot question list and a manual service transfer entry list in response to an instruction that the attribute information does not satisfy the preset condition, where the hotspot question list includes at least one hotspot question and a solution associated with the at least one hotspot question, and a category of the manual service transfer entry in the manual service transfer entry list is the same as a category of the hotspot question. In an embodiment, the pushing module 604 may be configured to perform the operation S240 described above, which is not described herein.

In some embodiments of the present disclosure, the second determination module includes a determination subunit configured to: when man-machine interaction information related to the manual intention is input, judging whether the interaction turn of the user and the machine meets a first set value or not; in the interaction turn of the user and the machine, judging whether the input times of the man-machine interaction information related to the transfer manual intention meet a second set value or not; and when the man-machine interaction information related to the manual intention is input, judging whether the interaction times of the user and the machine in the current interaction round meet a third set value or a fourth set value, wherein the fourth set value is smaller than the third set value.

In some embodiments of the present disclosure, the transfer manual module includes a transfer manual unit configured to: responding to an instruction that the attribute information meets a preset condition, and determining an intention category of converting the manual intention according to the man-machine interaction information; judging whether the intention category is contained in a first preset category set or not, if the intention category is contained in the first preset category set, transferring the user into a manual service seat, wherein the category of the manual service seat is the same as the intention category; if the intention category is not included in the first preset category, pushing a high-frequency category list to the user, and transferring the user to a manual service seat with the same category as the determined category according to the category determined by the user from the high-frequency category list.

In some embodiments of the present disclosure, the hotspot questions include a classification hotspot question and a global hotspot question, and the pushing module includes a pushing unit configured to: responding to the instruction that the attribute information does not meet the preset condition, and determining the intention category of the transfer manual intention according to the man-machine interaction information; judging whether the intention category is contained in a second preset category set, if so, pushing a classified hot spot problem list and a manual service entrance switching list to the user, wherein the category of the classified hot spot problem list and the category of the manual service entrance switching list are the same as the intention category; if the intention category is not contained in the second preset category set, pushing a global hot spot problem list and a manual service transferring entrance list to a user, wherein the category of the global hot spot problem in the global hot spot problem list is the same as the category of the manual service transferring entrance in the manual service transferring entrance list, and the global hot spot problem in the global hot spot problem list is obtained by sorting the classified hot spot problems according to the heat degree.

In some embodiments of the present disclosure, the apparatus further comprises a hotspot problem generation module configured to: before pushing the hotspot problem list to the user, generating a hotspot problem, the hotspot problem having an associated solution, the generating the hotspot problem comprising: generating a hot spot problem according to man-machine interaction information of all users in a historical time period; generating a hot spot problem according to the interaction information of all users with the manual service seat in the historical time period; generating a hot spot problem according to user behavior data of a user in a historical time period, wherein the hot spot problem is associated with the user; and generating a hot spot problem according to the question and answer data in the third party database.

In some embodiments of the present disclosure, the apparatus further comprises a switch module configured to: after the user is transferred to the manual service seat, determining the latest intention type of the transfer manual intention according to the man-machine interaction information input by the user in the second time period; and transferring the user from the current manual service position to the latest manual service position associated with the latest intention category according to the latest intention category.

According to an embodiment of the present disclosure, any of the first determining module 601, the second determining module 602, the manual converting module 603, and the pushing module 604 may be combined in one module to be implemented, or any of the modules may be split into a plurality of modules. Alternatively, at least some of the functionality of one or more of the modules may be combined with at least some of the functionality of other modules and implemented in one module. According to embodiments of the present disclosure, at least one of the first determination module 601, the second determination module 602, the manual transfer module 603, and the push module 604 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 hardware or firmware in any other reasonable manner of integrating or packaging the circuits, or in any one of or a suitable combination of three of software, hardware, and firmware. Alternatively, at least one of the first judgment module 601, the second judgment module 602, the transfer manual module 603, and the push module 604 may be at least partially implemented as a computer program module, which when executed, may perform the corresponding functions.

Fig. 9 schematically illustrates a block diagram of an electronic device according to an embodiment of the disclosure. The electronic device shown in fig. 9 is merely an example, and should not impose any limitations on the functionality and scope of use of embodiments of the present disclosure.

As shown in fig. 9, an electronic device 700 according to an embodiment of the present disclosure includes a processor 701 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 702 or a program loaded from a storage section 708 into a Random Access Memory (RAM) 703. The processor 701 may include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or an associated chipset and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), or the like. The processor 701 may also include on-board memory for caching purposes. The processor 701 may comprise a single processing unit or a plurality of processing units for performing different actions of the method flows according to embodiments of the disclosure.

In the RAM 703, various programs and data necessary for the operation of the electronic apparatus 700 are stored. The processor 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. The processor 701 performs various operations of the method flow according to the embodiments of the present disclosure by executing programs in the ROM 702 and/or the RAM 703. Note that the program may be stored in one or more memories other than the ROM 702 and the RAM 703. The processor 701 may also perform various operations of the method flow 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 electronic device 700 may further include an input/output (I/O) interface 705, the input/output (I/O) interface 705 also being connected to the bus 704. The electronic device 700 may also include one or more of the following components connected to the I/O interface 705: an input section 706 including a keyboard, a mouse, and the like; an output portion 707 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage section 708 including a hard disk or the like; and a communication section 709 including a network interface card such as a LAN card, a modem, or the like. The communication section 709 performs communication processing via a network such as the internet. The drive 710 is also connected to the I/O interface 705 as needed. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 710 as necessary, so that a computer program read therefrom is mounted into the storage section 708 as necessary.

The present disclosure also provides a computer-readable storage medium that may be embodied in the apparatus/device/system described in the above embodiments; or may exist alone without being assembled into the apparatus/device/system. The computer-readable storage medium carries one or more programs which, when executed, implement methods in accordance with embodiments of the present 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 context of this 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, the computer-readable storage medium may include ROM 702 and/or RAM 703 and/or one or more memories other than ROM 702 and RAM 703 described above.

Embodiments of the present disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowcharts. The program code, when executed in a computer system, causes the computer system to perform the methods provided by embodiments of the present disclosure.

The above-described functions defined in the system/apparatus of the embodiments of the present disclosure are performed when the computer program is executed by the processor 701. The systems, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the disclosure.

In one embodiment, the computer program may be based 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 over a network medium in the form of signals, downloaded and installed via the communication section 709, and/or installed from the removable medium 711. The computer program may include program code that may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 709, and/or installed from the removable medium 711. The above-described functions defined in the system of the embodiments of the present disclosure are performed when the computer program is executed by the processor 701. The systems, devices, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the disclosure.

According to embodiments of the present disclosure, program code for performing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, such computer programs may be implemented in high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. Programming languages include, but are not limited to, such as Java, c++, python, "C" or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, 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., connected via the Internet using an Internet service provider).

The flowcharts 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 the features recited in the various embodiments of the disclosure and/or in the claims may be provided in a variety of combinations and/or combinations, even if such combinations or combinations are not explicitly recited in the disclosure. In particular, the features recited in the various embodiments of the present disclosure and/or the claims may be variously combined and/or combined without departing from the spirit and teachings of the present disclosure. All such combinations and/or combinations fall within the scope of the present disclosure.

The embodiments of the present disclosure are 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 above separately, this does not mean that the measures in the embodiments cannot be used advantageously in combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be made by those skilled in the art without departing from the scope of the disclosure, and such alternatives and modifications are intended to fall within the scope of the disclosure.

Claims

1. A method for converting human services based on human-machine interaction, comprising:

acquiring man-machine interaction information input by a user in a first time period, and judging whether the man-machine interaction information contains a conversion manual intention or not;

Responding to an instruction containing the manual transfer intention, judging whether attribute information of man-machine interaction information corresponding to the manual transfer intention meets preset conditions or not, wherein the preset conditions are used for determining the sufficient interaction condition of a user and a machine;

responding to the instruction that the attribute information meets the preset condition, and transferring the user to a manual service seat;

and responding to an instruction that the attribute information does not meet a preset condition, pushing a hot spot problem list and a manual service transferring entrance list to a user, wherein the hot spot problem list comprises at least one hot spot problem and a solution associated with the at least one hot spot problem, and the category of the manual service transferring entrance in the manual service transferring entrance list is the same as the category of the hot spot problem.

2. The method of claim 1, wherein,

the attribute information includes:

when the man-machine interaction information associated with the transfer manual intention is input, the interaction turn of the user and the machine is performed;

in the interaction turn of the user and the machine, the input times of man-machine interaction information associated with the transfer manual intention are counted; and

and when the man-machine interaction information associated with the manual intent is input, the number of interactions between the user and the machine in the current interaction round.

3. The method of claim 2, wherein,

judging whether the attribute information of the man-machine interaction information corresponding to the manual intention meets the preset condition or not comprises the following steps:

when the man-machine interaction information related to the manual transfer intention is input, judging whether the interaction turn of the user and the machine meets a first set value;

in the interaction turn of the user and the machine, judging whether the input times of the man-machine interaction information related to the transfer manual intention meet a second set value or not; and

when the man-machine interaction information related to the manual intent is input, judging whether the interaction times of the user and the machine in the current interaction round meet a third set value or a fourth set value, wherein the fourth set value is smaller than the third set value.

4. A method according to claim 3, wherein the attribute information satisfying a preset condition comprises:

when the man-machine interaction information associated with the transfer manual intention is input, the interaction round of the user and the machine is smaller than or equal to a first set value, and in the interaction round of the user and the machine, the input times of the man-machine interaction information associated with the transfer manual intention are smaller than or equal to a second set value, and when the man-machine interaction information associated with the transfer manual intention is input, the interaction times of the user and the machine in the current interaction round are larger than a third set value.

5. A method according to claim 3, wherein the attribute information satisfying a preset condition comprises:

when the man-machine interaction information associated with the transfer manual intention is input, the interaction time of the user and the machine is larger than a first set value, and when the man-machine interaction information associated with the transfer manual intention is input, the interaction time of the user and the machine in the current interaction time is larger than a fourth set value.

6. A method according to claim 3, wherein the attribute information satisfying a preset condition comprises:

when the man-machine interaction information associated with the transfer manual intention is input, the interaction turn of the user and the machine is smaller than or equal to a first set value, and in the interaction turn of the user and the machine, the input times of the man-machine interaction information associated with the transfer manual intention are larger than a second set value.

7. The method of claim 1, wherein,

responding to the instruction that the attribute information meets the preset condition, transferring the user to a manual service seat, comprising:

responding to an instruction that the attribute information meets a preset condition, and determining the intention category of the transfer manual intention according to the man-machine interaction information;

determining whether the intention category is included in a first preset category set,

If the intention category is contained in the first preset category set, transferring the user to a manual service seat, wherein the category of the manual service seat is the same as the intention category;

if the intention category is not included in the first preset category, pushing a high-frequency category list to the user, and transferring the user to a manual service seat with the same category as the determined category according to the category determined by the user from the high-frequency category list.

8. The method of claim 1, wherein the hotspot questions comprise a classification hotspot question and a global hotspot question,

and responding to the instruction that the attribute information does not meet the preset condition, pushing a hot spot problem list and a manual service entrance list to a user, wherein the method comprises the following steps:

responding to the instruction that the attribute information does not meet the preset condition, and determining the intention category of the transfer manual intention according to the man-machine interaction information;

determining whether the intention category is included in a second preset category set,

if the intention category is contained in the second preset category set, pushing a classified hot spot problem list and a manual service transfer entry list to a user, wherein the category of the classified hot spot problem list and the category of the manual service transfer entry list are the same as the intention category;

If the intention category is not contained in the second preset category set, pushing a global hot spot problem list and a manual service transferring entrance list to a user, wherein the category of the global hot spot problem in the global hot spot problem list is the same as the category of the manual service transferring entrance in the manual service transferring entrance list, and the global hot spot problem in the global hot spot problem list is obtained by sorting the classified hot spot problems according to heat.

9. The method of claim 1, further comprising:

before pushing a hotspot problem list to a user, a hotspot problem is generated, the hotspot problem having an associated solution,

generating the hotspot problem includes:

generating a hot spot problem according to man-machine interaction information of all users in a historical time period;

generating a hot spot problem according to the interaction information of all users with the manual service seat in the historical time period;

generating a hot spot problem according to user behavior data of a user in a historical time period, wherein the hot spot problem is associated with the user;

and generating a hot spot problem according to the question and answer data in the third party database.

10. The method of claim 1, further comprising:

after the user is transferred to the manual service location,

According to the man-machine interaction information input by the user in the second time period, determining the latest intention category of the transfer manual intention;

and transferring the user from the current manual service position to the latest manual service position associated with the latest intention category according to the latest intention category.

11. An apparatus for converting manual services based on human-machine conversation, comprising:

the first judging module is configured to acquire man-machine interaction information input by a user in a first time period and judge whether the man-machine interaction information contains a conversion manual intention or not;

the second judging module is configured to respond to the instruction containing the manual transfer intention and judge whether attribute information of man-machine interaction information corresponding to the manual transfer intention meets preset conditions or not, wherein the preset conditions are used for determining the sufficient interaction condition of a user and a machine;

the manual transfer module is configured to transfer the user to a manual service seat in response to an instruction that the attribute information meets a preset condition;

and the pushing module is configured to respond to an instruction that the attribute information does not meet a preset condition, push a hot spot problem list and a manual service transferring entrance list to a user, wherein the hot spot problem list comprises at least one hot spot problem and a solution associated with the at least one hot spot problem, and the category of the manual service transferring entrance in the manual service transferring entrance list is the same as the category of the hot spot problem.

12. One or more processors;

storage means for storing executable instructions which when executed by the processor implement the method according to any one of claims 1 to 10.

13. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, implement the method according to any of claims 1 to 10.

14. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 10.