CN112905859A

CN112905859A - Service method, device, system, equipment and storage medium

Info

Publication number: CN112905859A
Application number: CN201911214770.5A
Authority: CN
Inventors: 杜学明
Original assignee: ZTE Corp
Current assignee: ZTE Corp
Priority date: 2019-12-02
Filing date: 2019-12-02
Publication date: 2021-06-04
Also published as: WO2021109741A1

Abstract

The application provides a service method, a device, a system, equipment and a storage medium, wherein the method comprises the following steps: a user side acquires a target problem proposed by a user and sends the target problem to a background side; the background end queries a corresponding target answer based on the target question under the condition that the target question does not need an agent answer based on the question rule; the background end sends the target answer to the user end under the condition that the target question does not need to be answered by an agent based on the target answer; the background end acquires the agent answer aiming at the target question provided by the agent under the condition that the target question needs the agent answer based on the target answer, and feeds back the agent answer to the user end; wherein the agent answer or the target answer comprises at least one of a rich text answer and a voice answer, and an action answer; the user side displays the rich text answers; and the user side instructs the virtual service robot to display the voice answer and the action answer.

Description

Service method, device, system, equipment and storage medium

Technical Field

The present application relates to the field of communications technologies, and in particular, to a service method, apparatus, system, device, and storage medium.

Background

The contact center is also called a customer service center, and is a complete comprehensive information service system which is connected with enterprises into a whole by fully utilizing modern communication and Computer technologies, such as Computer Telephone Integration (CTI), Interactive Voice Response (IVR), Automatic Call Distribution (ACD) and the like, and can automatically and flexibly process a large number of different telephone incoming and outgoing services. The contact center is not only a service layer added on the outermost layer of the enterprise, but also plays a very important role in unified coordination and promotion for the image, management, service, scheduling, marketing and the like of the whole enterprise besides serving external customers, and can provide functions of inquiring, summarizing, statistically analyzing and the like of all communication data of the enterprise to assist enterprise decision making. The contact centers are mainly divided into two types, namely an incoming call type contact center and an outgoing call type contact center, and the incoming call type contact center is characterized in that a client call is answered, and a series of services and supports are provided for the client, such as various technical support centers, client service centers, telephone claim settlement centers and the like; the call-out contact center is generally mainly used for marketing and telemarketing activities, and is a profit center of an enterprise, such as a mail order company, a television shopping company, a direct marketing company, and the like.

Often the business process personnel of a contact center are called agents. The seat accesses or calls out the user through the contact center system, for various requirements of the user, the seat needs to complete the requirements of the user in the service system, and then the result is fed back to the user through the contact center system. For example, the subscriber may make a call to inquire about the balance of the call and the agent may access the subscriber's phone in the contact center system. After obtaining the requirement of the user, the seat inquires the telephone charge balance in the service system. And finally, feeding back the query result to the user through the call center system.

With the continuous progress and development of society and science, the living standard of people is continuously improved, the service demand of users is continuously increased, and various innovations appear. Some enterprises (finance, medical treatment, retail, airports, exhibition halls, governments and the like) use the deep fusion of cloud computing, big data, artificial intelligence and mobile internet to release an entity robot, integrate the robot technology and the artificial intelligence technology into scenes, create an efficient intelligent scene service mode, realize multimedia marketing which cannot be done manually, and also can replace the work of assisting in manually doing consultation, shunting and shopping guide.

The two service modes, namely the self-establishment agent mode and the entity robot mode, have relatively low efficiency for solving the user problems and poor experience.

Disclosure of Invention

The application provides a service method, comprising:

receiving a target question proposed by a user;

under the condition that the target question does not need to be solved on the basis of a question rule, inquiring a corresponding target answer on the basis of the target question;

under the condition that the target question does not need to be solved by an agent based on the target answer, sending the target answer to a user side; the target answer comprises at least one of a rich text answer and a voice answer, and an action answer;

and under the condition that the target question needs a seat answer based on the target answer, obtaining a seat answer for the target question provided by a seat, and feeding back the seat answer to a user side, wherein the seat answer comprises at least one of a rich text answer and a voice answer, and an action answer.

The application provides a service method, comprising:

acquiring a target problem proposed by a user, and sending the target problem to a background end;

receiving an agent answer or a target answer of the target question fed back by the background end, wherein the agent answer or the target answer comprises at least one of a rich text answer and a voice answer, and an action answer;

displaying the rich text answers;

and instructing the virtual service robot to display the voice answer and the action answer.

The application provides a service method, comprising:

a user side acquires a target problem proposed by a user and sends the target problem to a background side;

the background end receives a target problem proposed by a user;

the background end queries a corresponding target answer based on the target question under the condition that the target question does not need an agent answer based on a question rule;

the background end sends the target answer to a user end under the condition that the target question does not need to be answered by an agent based on the target answer;

the background end acquires an agent answer aiming at the target question provided by an agent under the condition that the target question needs the agent answer based on the target answer, and feeds the agent answer back to the user end; wherein the agent answer or the target answer comprises at least one of a rich text answer and a voice answer, and an action answer;

the user side receives the seat answer or the target answer of the target question fed back by the background side;

the user side displays the rich text answers;

and the user side instructs the virtual service robot to display the voice answer and the action answer.

The application provides a service device, including:

a service engine module configured to receive a target question posed by a user;

the service engine module is used for inquiring corresponding target answers based on the target questions or inquiring corresponding target answers based on the target questions through the contact center platform module under the condition that the target questions do not need seat answers based on question rules;

the service engine module is used for sending the target answer to a user side under the condition that the target question does not need a seat answer based on the target answer;

the agent module is used for acquiring agent answers provided by an agent and aiming at the target questions under the condition that the target questions need to be solved by the agent based on the target answers; wherein the agent answer or the target answer comprises at least one of a rich text answer and a voice answer, and an action answer;

and the service engine module is used for acquiring the seat answer of the seat module through the contact center platform module and feeding the seat answer back to the user side.

The application provides a service device, including: a service module;

the service module comprises a service screen submodule and a virtual service robot submodule;

the virtual service robot submodule or the service screen submodule is set to acquire a target problem proposed by a user;

the virtual service robot submodule is arranged to send the target problem to a background end;

the virtual service robot submodule is configured to receive an agent answer or a target answer of the target question fed back by the background end, wherein the agent answer or the target answer comprises at least one of a rich text answer and a voice answer, and an action answer;

the service screen sub-module is configured to display the rich text answer;

and the virtual service robot submodule is arranged for indicating the virtual service robot to display the voice answer and the action answer.

The present application provides a service system, comprising:

the service module is used for acquiring a target problem proposed by a user and sending the target problem to the service engine module;

the service engine module is used for inquiring a corresponding target answer based on the target question or inquiring the corresponding target answer based on the target question through the contact center platform module under the condition that the target question does not need an agent answer based on a question rule and sending the target answer to the user side;

the agent module is configured to acquire an agent answer for the target question provided by an agent under the condition that the target answer is judged to be needed by the target question;

the service engine module is used for acquiring the seat answer of the seat module through the contact center platform module and feeding the seat answer back to the service module;

the service module is used for receiving the target answer or the agent answer, the target answer comprises at least one of a rich text answer and a voice answer and an action answer, displaying the rich text answer, and indicating the virtual service robot to display the voice answer and the action answer.

The present application provides an apparatus comprising:

one or more processors;

a memory for storing one or more programs;

when executed by the one or more processors, cause the one or more processors to implement the method of any one of the present applications.

A storage medium is provided, which stores a computer program that, when executed by a processor, implements the method of any of the present applications.

With regard to the above embodiments and other aspects of the present application and implementations thereof, further description is provided in the accompanying drawings description, detailed description and claims.

Drawings

FIG. 1 is a flow chart of a service method provided herein;

FIG. 2 is a flow chart of a service method provided by the present application;

FIG. 3a is a flow chart of a service method provided by the present application;

FIG. 3b is a flow chart of a service method provided by the present application;

FIG. 4 is a block diagram of a service device according to the present application;

FIG. 5 is a block diagram of a service device according to the present application;

FIG. 6 is a schematic diagram of a service system architecture provided in the present application;

FIG. 7 is a flow chart of a method for performing a service using the service system provided herein;

FIG. 8 is a flow chart of a method for performing a service using the service system provided herein;

FIG. 9 is a flow chart of a method for performing a service using the service system provided herein;

FIG. 10 is a flow chart of a method for performing a service using the service system provided herein;

FIG. 11 is a flow chart of a method for performing a service using the service system provided herein;

fig. 12 is a schematic structural diagram of an apparatus provided in the present application.

Detailed Description

To make the objects, technical solutions and advantages of the present application more apparent, embodiments of the present application will be described in detail below with reference to the accompanying drawings. It should be noted that the embodiments and features of the embodiments in the present application may be arbitrarily combined with each other without conflict.

The steps illustrated in the flow charts of the figures may be performed in a computer system such as a set of computer-executable instructions. Also, while a logical order is shown in the flow diagrams, in some cases, the steps shown or described may be performed in an order different than here.

In a service mode in the related technology, a self-establishment agent mode needs to recruit telephone operators, and the telephone operators need to be trained professionally and need agent places and corresponding equipment for office; in the related art, the entity robot mode in the service mode needs to invest in equipment and an activity site of the entity robot, so that the construction cost is high and the construction period is long for enterprises generally, and meanwhile, the entity robot cannot answer due to professional problems encountered in the mode. The self-establishment seat mode and the entity robot mode have low solving efficiency and poor experience for users.

In an exemplary embodiment, fig. 1 is a flowchart of a service method provided by the present application, which may be applied to a case where a virtual service robot solves a user question, as shown in fig. 1, the method may be performed by a service device, the device may be implemented by software and/or hardware, and the method may be applied to a backend.

As shown in fig. 1, the method provided by the present application mainly includes:

s11: and receiving a target question proposed by a user.

In the application, the user side can acquire the target problem proposed by the user and send the target problem to the background side. The background end receives a target question posed by the user, wherein the target question posed by the user can be a voice question or a text question.

S12: and under the condition that the target question does not need to be solved by an agent based on the question rule, inquiring a corresponding target answer based on the target question.

In the application, whether the target question needs to be solved or not can be judged according to the question rule. In an exemplary embodiment, the difficulty of the target question may be determined, and whether an agent solution is needed may be determined according to the difficulty of the question. For example, by determining whether the difficulty of the target question reaches a certain difficulty threshold, if the difficulty threshold is not reached, it is determined that the target question does not need an agent to answer.

In an exemplary embodiment, the querying the corresponding target answer based on the target question includes: under the condition that the target question is a process question, inquiring a corresponding answer based on the process question; and under the condition that the target question is a question-answering question, inquiring a corresponding answer based on the question-answering question. The process question may be a business process question, and the question-and-answer question is a question-and-answer way, or may be regarded as a common question.

S13: under the condition that the target question does not need to be solved by an agent based on the target answer, sending the target answer to a user side; the target answer includes at least one of a rich text answer and a voice answer, and an action answer.

In the application, whether the target question needs to be answered by an agent or not can be judged according to the target answer. In one exemplary embodiment, it may be determined whether the target answer meets the answer rules. And under the condition that the target answer accords with the answer rule, judging that the target question does not need an agent to answer. And under the condition that the target answer does not accord with the answer rule, judging that the target question needs a seat to be solved. The answer rules can be configured according to needs, and the answer rules can be matching rules of answers and questions.

In one exemplary embodiment, whether the agent solution is needed or not may be determined based on the matching degree of the target answer and the target question. In an exemplary embodiment, the target answer and the target question may be input into a model, a matching degree of the target answer and the target question is calculated, and whether the target question needs an agent solution or not is determined according to the matching degree. And under the condition that the matching degree is less than the set matching degree, the target question can be judged to need the seat solution.

And under the condition that the target question does not need expert solution, the target answer is sent to the user side, and the user can know the target answer through the user side.

S14: and under the condition that the target question needs a seat answer based on the target answer, obtaining a seat answer for the target question provided by a seat, and feeding back the seat answer to a user side, wherein the seat answer comprises at least one of a rich text answer and a voice answer, and an action answer.

In the present application, the action answer may be an answer such as an action expression, an action guidance phrase, and the like.

In the present application, the time domain of the rich text answer, the voice answer, and the action answer is the same. In an exemplary embodiment, in the case that the agent answer or the target answer includes a rich text answer and an action answer, the sending the target answer to the user side includes: converting the rich-text answer to a voice answer; and feeding back the rich text answer, the action answer and the voice answer to the user side.

In an exemplary embodiment, the receiving a user-proposed target question includes: receiving a voice question proposed by a user; and converting the voice question into a text question as a target question.

In an exemplary embodiment, the method provided herein further comprises: receiving feedback information of a user on the target answer; and under the condition that the target question needs to be answered by the agent based on the feedback information, acquiring an agent answer aiming at the target question provided by the agent, and feeding back the agent answer to the user side.

The feedback information can be analyzed according to the feedback rule aiming at the user, so that whether the target problem needs to be solved or not is judged. In an exemplary embodiment, the feedback information may be subjected to semantic and emotion analysis, and whether an agent solution is needed or not may be determined based on the semantic, emotion information in the feedback information or the satisfaction degree of the target answer. For example, in the case where it is judged by the feedback information that the user belongs to an emotion such as anger, or the like, it is judged that the answer to the seat is required, or in the case where the satisfaction with the target answer is lower than the set satisfaction, it is judged that the answer to the seat is required, otherwise, the answer to the seat is not required.

In an exemplary embodiment, the method provided by the present application may further include: and under the condition that the target question needs to be solved by the agent based on the question rule, acquiring the agent answer aiming at the target question provided by the agent, and feeding back the agent answer to the user side.

In an exemplary embodiment, the method provided by the present application may further include: configuring the seat rules, the question rules, the answer rules, the rules for user feedback, and the configuration of the questions and the corresponding answers.

In an exemplary embodiment, fig. 2 is a flowchart of a service method provided by the present application, which may be applied to a case where a virtual service robot solves a user question, as shown in fig. 2, the method may be performed by a service device, the device may be implemented by software and/or hardware, and the method may be applied to a user terminal.

As shown in fig. 2, the technical solution provided by the present application mainly includes:

s21: and acquiring a target problem proposed by a user, and sending the target problem to a background end.

In the present application, the target question may be a speech question or may also be a text question. The user side can acquire the target problem proposed by the user and send the target problem to the background side.

S22: receiving an agent answer or a target answer of the target question fed back by the background end, wherein the agent answer or the target answer comprises at least one of a rich text answer and a voice answer, and an action answer.

In the application, the back end can query the corresponding target answer according to the target question, or the back end can obtain the agent answer provided by the agent and feed back the target answer or the agent answer to the user side. And the user side receives the target answer or the agent answer.

In one exemplary embodiment, the target answer or the agent answer includes a rich text answer, a voice answer, and an action answer.

In the present application, the action answer may be an answer such as an action expression, an action guidance phrase, and the like. The time domain of the rich text answer, the voice answer, and the action answer are the same.

S23: and displaying the rich text answers.

S24: and instructing the virtual service robot to display the voice answer and the action answer.

In the application, the virtual service robot may be displayed on a screen of the user side, and when the target answer or the agent answer is received, the rich text answer may be displayed to indicate that the virtual service robot will speak the voice answer and make an action answer.

In an exemplary embodiment, the method provided by the present application may further include: and acquiring feedback information of the user aiming at the target answer, and sending the feedback information to the background end. The feedback information may carry user satisfaction information, or may embody user emotion information and the like.

In an exemplary embodiment, fig. 3a is a flowchart of a service method provided by the present application, and as shown in fig. 3a, the method may be applied to a case where a robot solves a user question based on a virtual service.

As shown in fig. 3a, the technical solution provided by the present application includes:

s31: and the user side acquires the target problem proposed by the user and sends the target problem to the background side.

S32: the background end receives a target problem posed by a user.

S33: and the background end queries a corresponding target answer based on the target question under the condition that the target question does not need to be solved by an agent based on a question rule.

S34: and the background end sends the target answer to a user end under the condition that the target question does not need to be answered by an agent based on the target answer.

S35: the background end acquires an agent answer for the target question provided by an agent under the condition that the target answer is judged to be needed by the target question; wherein the agent answer or the target answer includes at least one of a rich text answer and a voice answer, and an action answer.

S36: and the user side receives the agent answer or the target answer of the target question fed back by the background side, and the agent answer or the target answer is received.

S37: and the user side displays the rich text answers.

S38: and the user side instructs the virtual service robot to display the voice answer and the action answer.

In an exemplary embodiment, the method provided herein further comprises: and under the condition that the target question needs to be solved by the agent based on the question rule, acquiring the agent answer aiming at the target question provided by the agent, and feeding back the agent answer to the user side.

In an exemplary embodiment, fig. 3b is a flowchart of a service method provided by the present application, and as shown in fig. 3b, the method may be applied to a case where a robot solves a user question based on a virtual service.

As shown in fig. 3b, the technical solution provided by the present application includes:

s311: the method comprises the steps of configuring the shape and the action of the virtual service robot, configuring questions and answers and configuring the transfer agent rule.

In the present application, the physical form and the possible actions of the virtual service robot are configured.

The configuration of questions and answers may include: the method comprises the steps of (1) common question-answering questions and answer configuration thereof, wherein the answer configuration comprises rich text, voice and action configuration, and comprises the synchronization of time domains of the three; the method comprises the steps of flow question, guide language and answer configuration thereof, wherein the answer configuration comprises rich text, voice and action configuration, and comprises the synchronization of time domains of the three.

The configuration of the forwarding seat rules includes configuration for the question rules, configuration for the answer rules, configuration for rules fed back by the user, and further rules, which can be defined by different enterprises, for example, for the question rules, the forwarding seat can be forwarded when the difficulty of configuring the question reaches a certain difficulty, and the like. Aiming at answer rules; the expert seats can be switched when the matching degree of the answers is lower than a certain threshold value; aiming at the feedback rule of the user, the user can be configured to switch the seat when the emotion is poor or the answer obviously proposed by the user is questioned, or the seat is switched when the satisfaction degree of the automatic answer through the virtual service robot does not reach a certain threshold value.

S312: the user raises a question.

S313: and performing semantic analysis and matching on the questions to find corresponding answers, wherein the answers comprise rich text answers, voice answers and action answers.

S314: the answer can be acquired by the agent intervention, the time of the agent intervention can be calculated for the question, the answer and the feedback of the user, and the answer given after the agent intervention also comprises a rich text answer, a voice answer and an action answer.

S315: and after three parts of answers, namely a rich text answer, a voice answer and an action answer, of the user question are acquired, rendering and displaying of the answers are synchronously given, wherein the rich text answer is rendered and displayed in a screen, and the voice answer and the action answer are synchronously spoken and made through a virtual service robot.

In an exemplary embodiment, fig. 4 is a service apparatus provided herein, the apparatus being configured at a backend, and the apparatus including: a service engine module 102, a contact center platform module 103, and an agent module 104.

A service engine module 102 configured to receive a target question posed by a user;

the service engine module 102 is configured to query a corresponding target answer based on the target question or query a corresponding target answer based on the target question through the contact center platform module 103 under the condition that the target question does not need an agent solution;

the service engine module 102 is configured to send the target answer to the user side under the condition that the target question does not need an agent answer based on the target answer;

the agent module 104 is configured to obtain an agent answer for the target question provided by an agent when it is determined that the target question needs the agent answer based on the target answer; wherein the agent answer or the target answer comprises at least one of a rich text answer and a voice answer, and an action answer;

the service engine module 102 is configured to obtain the agent answer of the agent module 104 through the contact center platform module 103, and feed back the agent answer to the user side.

In an exemplary embodiment, the service engine module 102 includes a robot engine sub-module 108, a question and answer engine sub-module 109, a flow engine sub-module 110; the contact center platform module 103 comprises a semantic platform submodule 116 and a knowledge service library submodule 117;

the robot engine submodule 108 is configured to receive a target question posed by a user;

the question-answering engine sub-module 109 is configured to query, through the process engine sub-module 110, a corresponding target answer from the knowledge service library sub-module 117 based on the process question if it is determined that the target question does not require an agent to answer and is a process question, and query, through the semantic platform sub-module 116, a corresponding answer from the knowledge service library sub-module 117 based on the question-answering question if it is determined that the target question does not require an agent to answer and is a question-answering question.

In an exemplary embodiment, the process engine sub-module 110 is configured for session management, process booting, and execution.

In an exemplary embodiment, the robot engine submodule 108 is configured to perform login control and session management.

In an exemplary embodiment, the question-answering engine submodule 109 is configured to send the target answer to the user side through the robot engine submodule 108 if it is determined that the target question does not need the agent solution.

In an exemplary embodiment, the contact center platform module 103 further comprises: and the voice platform sub-module 114, in the case that the target answer comprises a rich text answer and an action answer, the robot engine sub-module 108 is configured to receive the target answer sent by the question-answering engine sub-module 109, call the voice platform sub-module 114 to convert the rich text answer into a voice answer, and feed the rich text answer, the action answer and the voice answer back to the user terminal.

In an exemplary embodiment, the service engine module 102 further includes a seating sub-module 111; the contact center platform module 103 further comprises a queuing platform sub-module; the seat module 104 comprises a seat table module 112 and a business auxiliary screen sub-module 113;

the robot engine sub-module 108 is configured to receive feedback information of the user on the target answer;

the question-answer engine submodule is configured to notify the seat-transferring engine submodule 111 to notify the queuing platform submodule 115 to transfer to the seat table submodule 112 when the target question is judged to need a seat solution based on the feedback information, or the target question is judged to need a seat solution based on the question rule, or the target question is judged to need a seat solution based on the target answer;

the seat table module 112 is configured to obtain a voice answer provided by a seat, and feed back the voice answer to the seat transfer engine sub-module 111 through the contact center platform module 103;

the business auxiliary screen module 113 is configured to obtain rich text answers and action answers provided by the agent, and feed back the rich text answers and the action answers to the agent transfer engine submodule 111 through the agent table submodule 112 and the contact center platform module 103;

and the seating engine submodule 111 is configured to feed back the rich text answers, the voice answers and the action answers to the user side through the question-answering engine module 109 and the robot engine submodule 108.

The queuing platform submodule 115 may receive a request of the agent transfer engine submodule 111, complete queuing of an agent, route the request to the agent table submodule 112, return an agent answer to the agent transfer engine submodule 111, and feed the agent answer back to the question and answer engine submodule 109, the question and answer engine submodule 109 sends the agent answer to the robot engine submodule 108, and the robot engine submodule 108 feeds the agent answer back to the user side. The agent answers include rich text answers, voice answers, and action answers.

In an exemplary embodiment, the apparatus provided herein further comprises a configuration management module 105,

the configuration management module 105 comprises a virtual service robot configuration sub-module 118, a seat transfer rule configuration sub-module 119, a question and answer configuration sub-module 120 and a flow and answer configuration sub-module 121;

the virtual service robot configuration submodule 118 is configured to configure the actions of the virtual service robot, and the configuration result is stored in the knowledge service library submodule 117;

the agent transferring rule configuration submodule 119 is configured to configure a question rule, an answer rule and a rule for user feedback, and a configuration result is stored in the knowledge service base submodule 117;

the question and answer configuration sub-module 120 is configured to configure question and answer, the answer includes rich text answer, action answer and voice answer, and the configuration result is stored in the knowledge service base sub-module 117; wherein the time domains of the rich text answer, the action answer and the voice answer are synchronous;

the flow and answer configuration sub-module 121 is configured to configure a flow question, a guidance language and an answer, the answer includes a rich text answer, an action answer and a voice answer, and store the configuration result in the knowledge service library sub-module 117; wherein the time domains of the rich text answer, the action answer, and the voice answer are synchronized.

The knowledge service library sub-module 117 may manage data written by each module and query requests of other modules.

It should be noted that the modules of the service device provided in the present application are not limited to the above-described division form, and the modules of the service device may be divided as needed. The division of each sub-module in the service engine module 102 and the contact center platform module 103 is not limited to the above division form, and the sub-modules may be divided as needed.

The device can execute the service method provided by the embodiment of the application, and has the corresponding functional modules and beneficial effects of the execution method.

In an exemplary embodiment, fig. 5 is a service device provided herein, where the service device is configured at a user side, and the service device includes a service module 101;

the service module comprises a service screen sub-module 106 and a virtual service robot sub-module 107;

the virtual service robot submodule 106 or the service screen submodule 107 is configured to obtain a target question posed by a user;

the virtual service robot submodule 106 is configured to send the target problem to a background terminal;

the virtual service robot sub-module 106 is configured to receive an agent answer or a target answer of the target question fed back by the backend, where the agent answer or the target answer includes at least one of a rich text answer and a voice answer, and an action answer;

the service screen sub-module 106 configured to present the rich text answer;

the virtual service robot submodule 107 is configured to instruct the virtual service robot to present the voice answer and the action answer.

In an exemplary embodiment, the virtual service robot sub-module 106, or the service screen sub-module 107, is configured to obtain feedback information of the user for the target answer;

the virtual service robot submodule 106 is configured to send the feedback information to a backend.

The specific virtual service robot submodule 106 sends feedback information to a robot engine submodule at a background end, the robot engine submodule feeds a target answer or an agent answer back to the virtual service robot submodule 106, the virtual service robot submodule 107 sends a rich text answer to the service screen submodule 106, the service screen submodule 106 displays the rich text answer, and the virtual service robot submodule 107 indicates the virtual service robot to display a voice answer and an action answer.

In an exemplary embodiment, fig. 6 is a service apparatus provided by the present application, and the apparatus includes a service module 101, a service engine module 102, a contact center platform module 103, and an agent module 104.

The service module 101 is configured to acquire a target question provided by a user and send the target question to the service engine module 102;

the service engine module 102 is configured to query a corresponding target answer based on the target question or query a corresponding target answer based on the target question through the contact center platform module 102 under the condition that the target question does not need an agent solution based on a question rule;

the agent module 104 is configured to obtain an agent answer provided by an agent for the target question when it is determined that the target question needs an agent answer based on the target answer; wherein the agent answer or the target answer comprises at least one of a rich text answer and a voice answer, and an action answer;

the service engine module 102 is configured to feed back the agent answer obtained by the agent module 104 to the service module 101 through the contact center platform module 103;

the service module 101 is configured to receive the target answer or the agent answer, the target answer includes at least one of a rich text answer and a voice answer, and an action answer, and display the rich text answer, and instruct the virtual service robot to display the voice answer and the action answer.

In an exemplary embodiment, the system provided by the present application may further include a configuration management module 105, wherein the service module 101 includes a service screen sub-module 106 and a virtual service robot sub-module 107, and the service engine module 102: comprises a robot engine submodule 108, a question-answering engine submodule 109, a flow engine submodule 110 and a seat transferring engine submodule 111. The contact center platform module 103 includes a speech platform submodule 114, a semantic platform submodule 116, a queuing platform submodule 115, and a knowledge services library submodule 117. The agent module 104 includes an agent table sub-module 112 and a business assistance screen sub-module 113. The configuration management module 105: the virtual service robot configuration sub-module 118, the agent transferring rule configuration sub-module 119, the question and answer configuration sub-module 120 and the flow and answer configuration sub-module 121 are included. The description of each module and sub-module may refer to the above embodiments, and will not be repeated.

The virtual service robot provided by the application can replace an agent or an entity robot which is required to be put into an enterprise originally, can reduce the cost input for the enterprise, shorten the construction period, does not depend on a field too much, and can perform flexible elastic expansion and automatic deployment of a background end; the method and the system have the advantages that the answer is displayed through the screen and synchronously answered with the sound and the action of the virtual service robot, the vision, the hearing and the touch of a user are presented integrally, and the problem solving efficiency and the experience problem of the user are improved; the intelligent virtual service robot can be organically integrated with a traditional contact center, a general problem virtual service robot can solve and answer by itself, a difficult problem or an agent needing agent intervention assists in solving and answering, and intervention dimensionality can be combined by various strategies and is flexible.

In an exemplary embodiment, fig. 7 is a flowchart of a method for executing a service by using the system provided by the present application, and as shown in fig. 7, the method provided by the present application mainly includes:

s71: and (3) inputting a user question, wherein the virtual service robot submodule sends the user question to the robot engine submodule, if the user question is input by voice, an interface voice of the voice platform submodule is called to convert text, and then the text is sent to the question-answering engine submodule.

S72: the question-answering engine submodule calculates whether to transfer the seat according to the configured question dimension rule, if so, the step S79 is carried out, and if not, the step S73 is carried out;

step S73: the question-answering engine sub-module obtains answers (including rich text domain answers, voice domain answers and action domain answers) of the questions from the knowledge service library sub-module through the process engine sub-module (process questions) or the semantic platform sub-module (common questions or question-answering questions).

Step S74: the question-answering engine submodule calculates whether to transfer the seat according to the configured answer dimension rule, if so, the step S79 is carried out, and if not, the step S79 is carried out;

step S75: the question-answering engine submodule returns answers to the robot engine submodule and calls an interface text of the voice platform submodule to be converted into a voice processing voice domain answer part.

Step S76: the robot engine submodule returns the answer of the user question to the virtual service robot submodule.

Step S77: the service screen submodule renders rich text content, the virtual service robot submodule performs voice and action display, feedback of the user is collected and sent to the robot engine submodule, and the robot engine submodule sends the feedback to the question and answer engine submodule.

Step S78: and the question-answering engine submodule calculates whether to transfer the seat according to the configured user feedback dimension rule, if so, the step S79 is carried out, and if not, the request of the user question is ended.

Step S79: the question-answering engine submodule informs the agent transferring engine submodule and the agent transferring engine submodule informs the queuing platform submodule to transfer to the agent platform submodule.

Step S791: the seat issues voice answers through the seat table module according to the reported problems, issues rich text answers and action answers through the service auxiliary screen, and issues the answers to the seat transfer engine submodule.

Step S792: the seat transferring engine submodule issues answers to the question and answer engine submodule, and the question and answer engine submodule returns the answers to the robot engine submodule.

Step S793: the robot engine submodule returns the answer of the user question to the virtual service robot submodule.

Step S794: the service screen sub-module displays rich text answers, and the virtual service robot sub-module displays voice and actions at the same time, and the request of the user question is ended.

In an exemplary embodiment, fig. 8 is a flowchart of a service method executed by a system provided in the present application, where the method is applied to a chat problem, as shown in fig. 8, a technical solution provided in the present application mainly includes:

s81: the user asks: "how to open the heart";

s82: the semantic platform submodule judges that the problem is a chatting problem.

S83, finding an answer from the chat library by the semantic platform, wherein the answer comprises three parts: 1. rich text: the form can be a form composed of characters and pictures and used for displaying a service screen; 2. voice content: "a girl friend sends a message to me to say that me wants to cheer", which is used for the virtual service robot to answer in voice; 3. action expression: may be sold for use in the action expression of the virtual service robot.

S84: the virtual service robot answers by voice, acts on expressions and displays the content of the answers on the service screen to assist understanding, the three are synchronous, and the question-answering process is finished.

In an exemplary embodiment, fig. 9 is a flow chart of a method for performing a service using the system provided herein, which is applied to the case of a general question-answering. As shown in fig. 9, the technical solution provided by the present application mainly includes:

s91: the user asks: "how to use dragon to pay red envelope function".

S92: the question-answering engine submodule judges that the question is a business question for building a bank, the question is temporarily not needed to be assisted by a continuous seat, and the question is a common question-answering question (non-flow question).

S93: the semantic platform submodule finds an answer from a common question-answer library, and the answer comprises three parts: 1. rich text: a piece of introduction video can be used for displaying a service screen; 2. voice content: "you can pay by cell phone bank 'home page-dragon-red packet-common red packet/fun red packet' receive and dispatch dragon payment red packet" for virtual service robot voice answer; 3. action expression: there may be some gesture-guided actions for the action expression of the virtual service robot.

S94: the question-answering engine submodule judges that the answer does not need to be transferred to an agent for assisting processing and can directly enable the virtual service robot to answer the answer;

s95: the virtual service robot responds by voice, acts on expressions and service screen submodules show answer contents to assist understanding, the three are synchronous, and the question-answering process is finished.

In an exemplary embodiment, fig. 10 is a flow chart of a method for performing a service using the system provided herein, the method being applied to a business process problem scenario. As shown in fig. 10, the technical solution provided by the present application mainly includes:

s131, the user asks: "I want to book an airline ticket to Beijing";

s132, the question-answering engine submodule judges that the question is an air ticket reservation service question, the question is not needed to be assisted by an agent temporarily, and the question is a service flow question (non-ordinary question-answering);

s133, the question-answering engine sub-module analyzes that the question requires "departure date", "place of departure", "destination", and the user question has been purposefully beijing, and further requires the user to specify the departure date and place of departure, so the answer: 1. rich text: reserving a form of a flight, highlighting the departure date and the selection of the departure, and selecting Beijing as the destination for displaying on a service screen; 2. voice content: "please select a departure date and a departure place" for the virtual service robot to answer in voice; 3. action expression: a guiding action, which may be some gesture, for the action expression of the virtual service robot.

S134: the virtual service robot responds by voice, the action expression and the service screen sub-module display the answer content to assist understanding, and the three are synchronous.

S135: after the user selects a flight, the platform completes the reservation. And (3) answer: 1. rich text: reserving a successful confirmation form interface for service screen display; 2. voice content: "your flight has generated the reservation order, please confirm it down" for the virtual service robot voice answer; 3. action expression: a guiding action, which may be some gesture, for the action expression of the virtual service robot.

S136: the virtual service robot responds by voice, acts on expressions and the service screen submodule displays rich text content to assist understanding, and the three modules are synchronous.

S137: the user confirms OK and the process ends.

In an exemplary embodiment, fig. 11 is a flowchart of a method for performing a service using the system provided herein, where the method is applied to a business process problem. As shown in fig. 11, the technical solution provided by the present application mainly includes:

s141: the user asks: "my broadband television was suddenly unable to play".

S142: and the question-answering engine submodule judges that the question is a service question of the broadband television and judges that the question needs to be assisted by an agent according to rules.

S143: the queuing platform submodule is connected to the expert seat.

S144: the seat issues a guidance answer according to the question: 1. rich text: pushing an operation video for showing the service screen submodule; 2. voice content: "you camera is aimed at the television fault picture" for the virtual service robot voice answer; 3. action expression: a guiding action, which may be some gesture, for the action expression of the virtual service robot.

S145: the virtual service robot responds by voice, acts on expressions and the service screen submodule displays rich text content to assist understanding, and the three modules are synchronous.

S146: after the content shot by the user is synchronized to the service assistance screen of the seat, a guidance answer is called out: 1. rich text: pushing an operation video for showing the service screen submodule; 2. voice content: please restart your set-top box for the virtual service robot voice answer; 3. action expression: a guiding action, which may be some gesture, for the action expression of the virtual service robot.

S146: the virtual service robot responds by voice, acts on expressions and the service screen submodule displays rich text content to assist understanding, and the three modules are synchronous.

S147: the user confirms OK and the process ends.

Fig. 12 is a schematic structural diagram of an apparatus provided in the present application, and as shown in fig. 12, the apparatus provided in the present application includes one or more processors 121 and a memory 122; the processor 121 in the device may be one or more, and one processor 121 is taken as an example in fig. 12; the memory 122 is used to store one or more programs; the one or more programs are executed by the one or more processors 121, so that the one or more processors 121 implement the method as described in the embodiment of the present invention.

The apparatus further comprises: a communication device 123, an input device 124, and an output device 125.

The processor 121, the memory 122, the communication device 123, the input device 124 and the output device 125 in the apparatus may be connected by a bus or other means, and the connection by the bus is exemplified in fig. 12.

The input device 124 may be used to receive entered numeric or character information and to generate key signal inputs relating to user settings and function control of the apparatus. The output device 125 may include a display device such as a display screen.

The communication device 123 may include a receiver and a transmitter. The communication device 123 is configured to perform information transceiving communication according to the control of the processor 121.

The memory 122 is a computer readable storage medium configured to store software programs, computer executable programs, and modules, such as program instructions/modules corresponding to the service method described in the embodiments of the present application (for example, the service engine module 102, the contact center platform module 103, and the agent module 104 in the service device), and program instructions/modules corresponding to the service method described in the embodiments of the present application (for example, the service screen sub-module 106 and the virtual service robot sub-module 107 in the service device). The memory 122 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the device, and the like. Further, the memory 122 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory 122 may further include memory located remotely from the processor 121, which may be connected to the device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The embodiments of the present application also provide a storage medium, where a computer program is stored, and when the computer program is executed by a processor, the method described in any one of the embodiments of the present application is implemented.

When the service method described in any of the embodiments of the present application is implemented, the method includes:

receiving a target question proposed by a user;

under the condition that the target question does not need to be solved by an agent based on the target answer, sending the target answer to a user side;

under the condition that the target question needs a seat answer based on the target answer, obtaining a seat answer for the target question provided by a seat; wherein the agent answer or the target answer comprises at least one of a rich text answer and a voice answer, and an action answer;

and feeding back the seat answer to the user side.

displaying the rich text answers;

The above description is only exemplary embodiments of the present application, and is not intended to limit the scope of the present application.

It will be clear to a person skilled in the art that the term user terminal covers any suitable type of wireless user equipment, such as a mobile phone, a portable data processing device, a portable web browser or a car mounted mobile station.

In general, the various embodiments of the application may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. For example, some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device, although the application is not limited thereto.

Embodiments of the application may be implemented by a data processor of a mobile device executing computer program instructions, for example in a processor entity, or by hardware, or by a combination of software and hardware. The computer program instructions may be assembly instructions, Instruction Set Architecture (ISA) instructions, machine related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages.

Any logic decision block diagram in the figures of the present application may represent a program step, or may represent interconnected logic circuits, modules, and functions, or may represent a combination of a program step and a logic circuit, module, and function. The computer program may be stored on a memory. The memory may be of any type suitable to the local technical environment and may be implemented using any suitable data storage technology, such as, but not limited to, Read Only Memory (ROM), Random Access Memory (RAM), optical storage devices and systems (digital versatile disks, DVDs, or CD discs), etc. The computer readable medium may include a non-transitory storage medium. The data processor may be of any type suitable to the local technical environment, such as but not limited to general purpose computers, special purpose computers, microprocessors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), programmable logic devices (FGPAs), and processors based on a multi-core processor architecture.

The foregoing has provided by way of exemplary and non-limiting examples a detailed description of exemplary embodiments of the present application. Various modifications and adaptations to the foregoing embodiments may become apparent to those skilled in the relevant arts in view of the following drawings and the appended claims without departing from the scope of the invention. Therefore, the proper scope of the invention is to be determined according to the claims.

Claims

1. A method of servicing, comprising:

receiving a target question proposed by a user;

under the condition that the target question does not need an agent answer based on the target answer, sending the target answer to a user side, wherein the target answer comprises at least one of a rich text answer and a voice answer and an action answer;

2. The method of claim 1, further comprising:

receiving feedback information of a user on the target answer;

and under the condition that the target question needs to be answered by the agent based on the feedback information, acquiring an agent answer aiming at the target question provided by the agent, and feeding back the agent answer to the user side.

3. The method according to claim 2, wherein in the case that the target answer includes a rich text answer and an action answer, the sending the target answer to the user side includes:

converting the rich-text answer to a voice answer;

and feeding back the rich text answer, the action answer and the voice answer to the user side.

4. The method of claim 1, further comprising:

and under the condition that the target question needs to be solved by the agent based on the question rule, acquiring the agent answer aiming at the target question provided by the agent, and feeding back the agent answer to the user side.

5. The method of claim 1, wherein receiving a user-posed target question comprises:

receiving a voice question proposed by a user;

and converting the voice question into a text question as a target question.

6. The method of claim 1, wherein the querying the corresponding target answer based on the target question comprises:

under the condition that the target question is a process question, inquiring a corresponding answer based on the process question;

and under the condition that the target question is a question-answering question, inquiring a corresponding answer based on the question-answering question.

7. A method of servicing, comprising:

displaying the rich text answers;

8. The method of claim 1, further comprising:

and acquiring feedback information of the user aiming at the target answer, and sending the feedback information to the background end.

9. A method of servicing, comprising:

the background end receives a target problem proposed by a user;

the user side displays the rich text answers;

10. A service device, comprising:

11. A service device, comprising: a service module;

the service screen sub-module is configured to display the rich text answer;

12. A service system, comprising:

13. An apparatus, comprising:

one or more processors;

a memory for storing one or more programs;

when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-8.

14. A storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method of any one of claims 1-8.