WO2021109741A1 - 一种服务方法、装置、系统、设备及存储介质 - Google Patents

一种服务方法、装置、系统、设备及存储介质 Download PDF

Info

Publication number
WO2021109741A1
WO2021109741A1 PCT/CN2020/122755 CN2020122755W WO2021109741A1 WO 2021109741 A1 WO2021109741 A1 WO 2021109741A1 CN 2020122755 W CN2020122755 W CN 2020122755W WO 2021109741 A1 WO2021109741 A1 WO 2021109741A1
Authority
WO
WIPO (PCT)
Prior art keywords
answer
target
question
agent
module
Prior art date
Application number
PCT/CN2020/122755
Other languages
English (en)
French (fr)
Inventor
杜学明
Original Assignee
中兴通讯股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2021109741A1 publication Critical patent/WO2021109741A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
    • H04L51/02—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/903—Querying
    • G06F16/9032—Query formulation
    • G06F16/90332—Natural language query formulation or dialogue systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/903—Querying
    • G06F16/9032—Query formulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/903—Querying
    • G06F16/9038—Presentation of query results
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/01—Customer relationship services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services

Definitions

  • This application relates to the field of communication technology, and specifically to a service method, device, system, equipment, and storage medium.
  • the contact center is also called the customer service center. It makes full use of modern communication and computer technology, such as (Computer Telephone Integration, CTI), Interactive Voice Response (Voice Response, IVR), Automatic Call Distribution (Automatic Call Distribution) , ACD), etc., a complete integrated information service system connected to the enterprise, which can automatically and flexibly handle a large number of different incoming and outgoing calls.
  • the contact center is not only a service layer added by the enterprise to the outermost layer. In addition to serving external customers, it also plays a very important role in the unified coordination and promotion of the image, management, service, scheduling, and marketing of the entire enterprise. It can also provide query, summary, statistical analysis and other functions of all communication data of the enterprise to assist the enterprise in decision-making.
  • Inbound contact centers are characterized by answering customer calls and providing customers with a series of services and support, such as various technical support centers and customer services. Centers, telephone claims centers, etc.; outbound contact centers are generally engaged in marketing and telesales activities, and are the profit centers of enterprises, such as mail order companies, TV shopping, and direct sales companies.
  • the agent accesses or calls out the user through the contact center system.
  • the agent needs to complete the user's requirements in the business system, and then feedback the result to the user through the contact center system.
  • the user makes a call to check the balance of the call charge, and the agent accesses the user's phone in the contact center system.
  • the agent queries the balance of the call charge in the business system. Finally, the query result is fed back to the user through the call center system.
  • This application provides a service method, including: receiving a target question raised by a user; in the case of judging that the target question does not need to be answered by an agent based on the question rule, querying the corresponding target answer based on the target question; Answer Judgment: When the target question does not need to be answered by an agent, the target answer is sent to the user terminal; the target answer includes at least one of a rich text answer and a voice answer, and an action answer; When the answer judges that the target question needs to be answered by the agent, the agent answer to the target question provided by the agent is obtained, and the agent answer is fed back to the user terminal, where the agent answer includes a rich text answer and a voice answer At least one of and the action answer.
  • This application provides a service method, including: obtaining a target question raised by a user, and sending the target question to a backend; receiving an agent answer or a target answer of the target question fed back by the backend, 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 rich text answer is displayed; and the virtual service robot is instructed to display the voice answer and the action answer.
  • This application provides a service method, including: the user terminal obtains the target question raised by the user, and sends the target question to the backend; the backend receives the target question raised by the user; In the case that the target question does not require an agent to be answered, the corresponding target answer is inquired based on the target question; when the backend determines that the target question does not require an agent to be answered based on the target answer, the target answer is Send to the user terminal; the background terminal obtains the agent answer provided by the agent for the target question in the case of judging that the target question needs to be answered by the agent based on the target answer, and feeds back the agent answer to the user terminal; wherein , The agent answer or the target answer includes at least one of a rich text answer and a voice answer, as well as an action answer; the user terminal receives the agent answer or the target answer of the target question fed back by the background terminal; The user end displays the rich text answer; the user end instructs the virtual service robot to display the voice answer and the action answer.
  • the present application provides a service device, including: a service engine module, which is set to receive a target question raised by a user; and a service engine module, which is set to determine that the target question does not need to be answered by an agent based on the question rule.
  • the target question query corresponds to the target answer, or the contact center platform module is used to query the target answer corresponding to the target question; the service engine module is set to determine that the target question does not need to be answered by an agent based on the target answer Next, the target answer is sent to the user terminal; the agent module is used to obtain the agent answer provided by the agent for the target question when it is determined that the target question needs to be answered by the agent based on the target answer; 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; the service engine module is set to obtain the agent answer of the agent module through the contact center platform module, and The answer of the agent is fed back to the user terminal.
  • This application provides a service device, including: a service module; the service module includes a service screen sub-module and a virtual service robot sub-module; the virtual service robot sub-module, or the service screen sub-module is set to obtain the target proposed by the user Question; the virtual service robot submodule is set to send the target question to the backend; the virtual service robot submodule is set to receive the agent answer or target of the target question fed back by the backend Answer, the agent answer or the target answer, including at least one of a rich text answer and a voice answer, and an action answer; the service screen sub-module is set to display the rich text answer; the virtual service The robot sub-module is set to instruct the virtual service robot to display the voice answer and action answer.
  • This application provides a service system, including: a service module, which is set to obtain a target question raised by a user, and send the target question to the service engine module; the service engine module is set to determine the target question based on question rules In the case that no agent is required to answer, query the corresponding target answer based on the target question, or query the corresponding target answer based on the target question through the contact center platform module, and send the target answer to the user terminal; the agent The module is set to obtain the agent answer to the target question provided by the agent when it is determined that the target question needs to be answered by the agent based on the target answer; the service engine module is set to pass through the contact center platform module Obtain the seat answer of the seat module, and feed the seat answer back to the service module; the service module is set to receive the target answer or the seat answer, and the target answer includes at least one of a rich text answer and a voice answer And the action answer, and the rich text answer is displayed, instructing the virtual service robot to display the voice answer and the action answer.
  • the present application provides a device, including: one or more processors; a memory, used to store one or more programs; when the one or more programs are executed by the one or more processors, the one Or multiple processors implement any of the methods described in this application.
  • the present application provides a storage medium that stores a computer program, and when the computer program is executed by a processor, the method described in any one of the present applications is implemented.
  • Figure 1 is a flow chart of a service method provided by this application.
  • Figure 2 is a flow chart of a service method provided by this application.
  • Figure 3a is a flow chart of a service method provided by this application.
  • Figure 3b is a flow chart of a service method provided by this application.
  • Figure 4 is a structural block diagram of a service device provided by this application.
  • FIG. 5 is a structural block diagram of a service device provided by this application.
  • Fig. 6 is a schematic diagram of the structure of a service system provided by the present application.
  • Figure 7 is a flow chart of a service method using the service system provided by this application.
  • Figure 8 is a flow chart of a service method using the service system provided by this application.
  • Figure 9 is a flow chart of a service method using the service system provided by this application.
  • Figure 10 is a flow chart of a method for implementing a service using the service system provided by this application.
  • Figure 11 is a flow chart of a method for implementing a service using the service system provided by this application.
  • Fig. 12 is a schematic diagram of a device structure provided by the present application.
  • the self-built agent mode in the service mode of related technologies requires the recruitment of operators, who need professional training, and the place and corresponding equipment for the agent office; the physical robot mode in the service mode of related technologies requires equipment and physical robots Event venues, therefore, for enterprises, the construction cost is generally higher and the construction period is longer. At the same time, this model encounters professional problems that physical robots cannot answer.
  • the above-mentioned self-built seat mode and physical robot mode services are relatively inefficient in solving users, and the experience is not good.
  • FIG. 1 is a flowchart of a service method provided by the present application. As shown in FIG. 1, the method can be applied to the situation of answering user questions based on a virtual service robot.
  • the service device can be implemented, the device can be implemented by software and/or hardware, and the method can be applied to the backend.
  • the method provided by this application mainly includes:
  • the user end can obtain the target question raised by the user and send it to the backend end.
  • the backend receives the target question raised by the user, where the target question raised by the user may be a voice question or a text question.
  • the difficulty of the target question can be determined, and whether an agent needs to be answered is determined according to the difficulty of the question. For example, by judging whether the difficulty of the target question reaches a certain difficulty threshold, if the difficulty threshold is not reached, it is judged that the target question does not need to be answered by an agent.
  • the querying the corresponding target answer based on the target question includes: in the case that the target question is a process question, querying the corresponding answer based on the process question;
  • the question is a question-and-answer question
  • the corresponding answer is inquired based on the question-and-answer question.
  • process questions can be business process questions, and question-and-answer questions are a question-and-answer method, or can be regarded as ordinary questions.
  • the target answer is sent to the user terminal; the target answer includes at least one of a rich text answer and a voice answer, and an action answer.
  • the judge target question does not need to be answered by the agent.
  • the judgment target question needs to be answered by the agent.
  • the answer rule can be configured as needed, and the answer rule can be a matching rule between the answer and the question.
  • the target answer and the target question may be input into the model, the matching degree between the target answer and the target question can be calculated, and whether the target question needs to be answered by an agent is judged by the matching degree.
  • the matching degree is greater than the set matching degree, it can be judged that the target question does not need to be answered by an agent, and when the matching degree is less than the set matching degree, it can be judged that the target question needs an agent to answer.
  • the target answer is sent to the user terminal, and the user can understand the target answer through the user terminal.
  • S14 In the case of judging that the target question needs to be answered by an agent based on the target answer, obtain the agent answer provided by the agent for the target question, and feed back the agent answer to the user terminal, wherein the agent answer Include at least one of rich text answers and voice answers, as well as action answers.
  • the answer to the action can be an answer such as an expression of an action, an action guide, etc.
  • the rich text answer, voice answer, and action answer have the same time domain.
  • the sending the target answer to the user terminal includes: converting the rich text answer into a voice answer ; Feedback the rich text answer, the action answer, and the voice answer to the user terminal.
  • the receiving the target question raised by the user includes: receiving the voice question raised by the user; and converting the voice question into a text question as the target question.
  • the method provided in this application further includes: receiving user feedback information on the target answer; in the case of determining that the target question needs to be answered by an agent based on the feedback information, obtaining information provided by the agent For the agent answer of the target question, the agent answer is fed back to the user terminal.
  • the feedback information can be analyzed according to the feedback rules for the user, so as to determine whether the target question needs to be answered by an agent.
  • semantic and emotional analysis can be performed on the feedback information, and it can be determined based on the semantics in the feedback information, the information in the emotion, or the satisfaction with the target answer, whether an agent is required to answer. For example, when the user is judged to be angry, angry and other emotions based on the feedback information, it is judged that an agent is required to answer, or when the satisfaction with the target answer is lower than the set satisfaction, it is judged that an agent is required to answer, otherwise no agent is needed answer.
  • the method provided in the present application may further include: in the case of determining that the target question needs to be answered by an agent based on the question rule, obtaining an agent answer to the target question provided by the agent, and The answer of the agent is fed back to the user terminal.
  • the method provided in this application may further include: configuring the transfer rules, question rules, answer rules, rules for user feedback, and the configuration of questions and corresponding answers.
  • FIG. 2 is a flowchart of a service method provided by the present application. As shown in FIG. 2, the method can be applied to the situation of answering user questions based on a virtual service robot.
  • the service device can execute it, and the device can be implemented by software and/or hardware, and the method can be applied to the user side.
  • the target question can be a voice question or a text question.
  • the user end can obtain the target question raised by the user and send it to the backend end.
  • S22 Receive an agent answer or a target answer of the target question fed back by the backend end, 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 backend can query the corresponding target answer according to the target question, or the backend can obtain the agent answer provided by the agent, and feed back the target answer or the agent answer to the user end.
  • the user terminal receives the target answer or the agent answer.
  • the target answer or the agent answer includes a rich text answer, a voice answer, and an action answer.
  • the answer to the action can be an answer such as an expression of an action, an action guide, etc.
  • the rich text answer, voice answer, and action answer have the same time domain.
  • the virtual service robot can be displayed on the screen of the user terminal.
  • the rich text answer can be displayed, indicating that the virtual service robot will speak the voice answer and make an action answer.
  • the method provided in this application may further include: obtaining user feedback information for the target answer, and sending the feedback information to the backend.
  • the feedback information may carry user satisfaction information, or may reflect user emotional information, etc.
  • FIG. 3a is a flowchart of a service method provided by the present application. As shown in FIG. 3a, the method can be applied to a situation where a virtual service robot answers user questions.
  • S31 The user terminal obtains the target question raised by the user, and sends the target question to the background terminal.
  • S32 The backend receives the target question raised by the user.
  • S33 The backend queries the corresponding target answer based on the target question when it is determined based on the question rule that the target question does not need to be answered by an agent.
  • the background end sends the target answer to the user end when it is judged based on the target answer that the target question does not need to be answered by an agent.
  • the backend obtains the agent answer to the target question provided by the agent in the case of judging that the target question needs to be answered by the agent based on the target answer; wherein, the agent answer or the target answer includes rich At least one of a text answer and a voice answer, and an action answer.
  • S36 The user terminal receives the agent answer or the target answer of the target question, and the agent answer or the target answer fed back by the background terminal.
  • S37 The user terminal displays the rich text answer.
  • S38 The user terminal instructs the virtual service robot to display the voice answer and the action answer.
  • the method provided in the present application further includes: in the case of judging that the target question needs to be answered by an agent based on the question rule, obtaining an agent answer for the target question provided by the agent, and combining the agent The answer is fed back to the user.
  • the method provided in the present application further includes: receiving user feedback information on the target answer; in the case of determining that the target question needs to be answered by an agent based on the feedback information, obtaining the countermeasure provided by the agent The agent answer of the target question, and the agent answer is fed back to the user terminal.
  • FIG. 3b is a flowchart of a service method provided by the present application. As shown in FIG. 3b, the method can be applied to a situation where a virtual service robot answers user questions.
  • S311 Configure the shape and actions of the virtual service robot, configure the questions and answers, and configure the transfer agent rules.
  • the shape of the virtual service robot and the actions that can be issued are configured.
  • the configuration of questions and answers can include: general question and answer questions and their answer configuration, the answer configuration includes rich text, voice and action configuration, including the synchronization of the three time domains; process question, guide language and answer configuration, and the answer configuration includes rich Text, voice and action configuration, including the synchronization of the three time domains.
  • Transfer agent rule configuration including the configuration of the rule for the question, the configuration of the rule for the answer, the configuration of the rule for the user feedback, and the further rules can be defined by different companies.
  • the difficulty of the question can be configured to reach a certain level of difficulty Just transfer the seats and wait.
  • answer rules you can configure the answer to the expert agent if the matching degree is lower than a certain threshold; for user feedback rules, you can configure the user to be in a bad mood or obviously question the answer, transfer the agent, or pass
  • the virtual service robot will transfer the agent if the satisfaction degree of the automatic answer does not reach a certain threshold.
  • S312 The user asks a question.
  • S313 Perform semantic analysis and matching on the question to find the corresponding answer.
  • the answer includes a rich text answer, a voice answer, and an action answer.
  • the agent can intervene to obtain answers.
  • the timing of agent intervention can be calculated based on the question itself, the answer itself, and the three dimensions of user feedback.
  • the answers given by the agent after intervention also include rich text answers, voice answers and action answers .
  • S315 After obtaining the rich text answer, voice answer, and action answer of the user’s question, render and display the answer synchronously, where the rich text answer is rendered and displayed on the screen, and the virtual service robot is synchronously spoken Voice answer and action answer.
  • FIG. 4 is a service device provided by the present application.
  • the device is configured at the backend.
  • the device includes a service engine module 102, a contact center platform module 103, and an agent module 104.
  • the service engine module 102 is set to receive target questions raised by users
  • the service engine module 102 is configured to query the corresponding target answer based on the target question, or query the corresponding target answer based on the target question through the contact center platform module 103 when it is determined that the target question does not need to be answered by an agent ;
  • the service engine module 102 is configured to send the target answer to the user terminal when it is determined based on the target answer that the target question does not require an agent to answer;
  • the agent module 104 is configured to obtain an agent answer to the target question provided by an agent in the case of judging that the target question requires an agent answer based on the target answer; wherein, the agent answer or the target answer includes rich At least one of text answer and voice answer, and action answer;
  • the service engine module 102 is configured to obtain the seat answer of the seat module 104 through the contact center platform module 103, and feed back the seat answer to the user terminal.
  • the service engine module 102 includes a robot engine sub-module 108, a question and answer engine sub-module 109, and a process engine sub-module 110;
  • the contact center platform module 103 includes a semantic platform sub-module 116 and a knowledge service database sub-module. Module 117;
  • the robot engine sub-module 108 is set to receive the target question raised by the user
  • the question and answer engine sub-module 109 is configured to use the process engine sub-module 110 to obtain information from the knowledge service database sub-module 117 when it is determined that the target question does not need to be answered by an agent, and the target question is a process problem. Query the corresponding target answer based on the process question, and when it is judged that the target question does not need to be answered by an agent, and the target question is a question-and-answer question, use the semantic platform sub-module 116 to obtain the answer from the knowledge service library sub-module In 117, the corresponding answer is queried based on the question-and-answer question.
  • the process engine sub-module 110 is configured for session management, process guidance, and execution.
  • the robot engine sub-module 108 is configured to perform login control and session management.
  • the question answering engine sub-module 109 is configured to send the target answer to the user terminal through the robot engine sub-module 108 when it is determined that the target question does not need to be answered by an agent.
  • the contact center platform module 103 further includes a voice platform sub-module 114.
  • the robot engine sub-module 108 is set to The target answer sent by the question and answer engine submodule 109 is received, the voice platform submodule 114 is called to convert the rich text answer into a voice answer, and the rich text answer, the action answer, and the voice answer are fed back to the user terminal.
  • the service engine module 102 further includes a seat transfer sub-module 111; the contact center platform module 103 further includes a queuing platform sub-module; the seat module 104 includes a seat sub-module 112 and a business assistant Screen sub-module 113;
  • the robot engine sub-module 108 is configured to receive user feedback information on the target answer
  • the question and answer engine sub-module is configured to determine that the target question needs to be answered by an agent based on the feedback information, or determine that the target question needs to be answered by an agent based on the question rule, or determine the target based on the target answer
  • the notification transfer engine sub-module 111 informs the queuing platform sub-module 115 to transfer to the seat sub-module 112;
  • the seat sub-module 112 is configured to obtain the voice answer provided by the seat, and feed the voice answer back to the seat transfer engine sub-module 111 through the contact center platform module 103;
  • the business assistant screen module 113 is configured to obtain the rich text answers and action answers provided by the agents, and feed them back to the seat transfer engine sub-module 111 through the agent sub-module 112 and the contact center platform module 103;
  • the seat transfer engine submodule 111 is configured to feed back the rich text answer, voice answer, and action answer to the user terminal through the question answering engine module 109 and the robot engine submodule 108.
  • the queuing platform sub-module 115 can receive the request of the seat transfer engine sub-module 111, complete the queue of the seat, and route the request to the seat sub-module 112, and at the same time, can return the seat answer to the seat transfer engine sub-module 111 to transfer the seat
  • the engine sub-module 111 feeds back the seat answer to the question-and-answer engine sub-module 109, the question-and-answer engine sub-module 109 sends the seat answer to the robot engine sub-module 108, and the robot engine sub-module 108 feeds back the seat answer to the user terminal.
  • the agent answer includes rich text answer, voice answer and action answer.
  • the device provided in the present application further includes a configuration management module 105,
  • the configuration management module 105 includes a virtual service robot configuration submodule 118, a seat transfer rule configuration submodule 119, a question and answer configuration submodule 120, and a process and answer configuration submodule 121;
  • the virtual service robot configuration sub-module 118 is configured as the action configuration of the virtual service robot, and the configuration result is stored in the knowledge service database sub-module 117;
  • the transfer rule configuration sub-module 119 is configured to configure the question rule configuration, the answer rule configuration, and the rule configuration for user feedback, and the configuration result is stored in the knowledge service database sub-module 117;
  • the question and answer configuration submodule 120 is configured as a question-and-answer question and answer configuration.
  • the answers include rich text answers, action answers, and voice answers.
  • the configuration results are stored in the knowledge service database submodule 117; among them, rich text answers, Time domain synchronization of action answer and voice answer;
  • the process and answer configuration sub-module 121 is configured to configure process questions, introductory words, and answers.
  • the answers include rich text answers, action answers, and voice answers, and the configuration results are stored in the knowledge service library sub-module 117; among them, Time domain synchronization of rich text answer, action answer and voice answer.
  • the knowledge service database sub-module 117 can manage the data written by each module and query requests from other modules.
  • the various modules of the service device provided in this application are not limited to the above-mentioned division form, and the various modules of the service device can also be divided according to needs.
  • the division of each sub-module in the service engine module 102 and the contact center platform module 103 is not limited to the foregoing division form, and the sub-modules can be divided according to needs.
  • the above-mentioned device can execute the service method provided by the embodiment of the present application, and has the corresponding functional modules and beneficial effects of the execution method.
  • FIG. 5 is a service device provided by the present application, the device is configured on the user side, and the device includes a service module 101;
  • the service module includes a service screen sub-module 106 and a virtual service robot sub-module 107;
  • the virtual service robot sub-module 106 or the service screen sub-module 107 is set to obtain the target question raised by the user;
  • the virtual service robot sub-module 106 is configured to send the target question to the background end;
  • 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 back-end end, and the agent answer or the target answer includes at least one of a rich text answer and a voice answer , And the action answer;
  • the service screen sub-module 106 is configured to display the rich text answer
  • the virtual service robot sub-module 107 is configured to instruct the virtual service robot to display the voice answer and action answer.
  • the virtual service robot sub-module 106 or the service screen sub-module 107 is configured to obtain user feedback information for the target answer;
  • the virtual service robot sub-module 106 is configured to send the feedback information to the background end.
  • the specific virtual service robot sub-module 106 sends feedback information to the robot engine sub-module at the backend, and the robot engine sub-module feeds back the target answer or the seat answer to the virtual service robot sub-module 106, and the virtual service robot sub-module 107 will be rich
  • the text answer is sent to the service screen sub-module 106, the service screen sub-module 106 displays the rich text answer, and the virtual service robot sub-module 107 instructs the virtual service robot to display the voice answer and the action answer.
  • the above-mentioned device can execute the service method provided by the embodiment of the present application, and has the corresponding functional modules and beneficial effects of the execution method.
  • FIG. 6 is a service device provided by the present application.
  • the device 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 obtain the target question raised by the user, and send the target question to the service engine module 102;
  • the service engine module 102 is configured to query the corresponding target answer based on the target question, or query the corresponding target question based on the target question through the contact center platform module 102 when it is determined that the target question does not need to be answered by an agent based on the question rule The target answer;
  • the agent module 104 is configured to obtain an agent answer to the target question provided by the agent when it is judged based on the target answer that the target question requires an agent answer; wherein, the agent answer or the target The answer includes at least one of a rich text answer and a voice answer, as well as an action answer;
  • the service engine module 102 is configured to feed back the seat answer obtained by the seat 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, as well as an action answer, and displays the rich text answer to indicate virtual
  • the service robot displays the voice answer and action answer.
  • 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: includes a robot engine sub-module Module 108, question and answer engine sub-module 109, process engine sub-module 110, and transfer seat engine sub-module 111.
  • the contact center platform module 103 includes a voice platform sub-module 114, a semantic platform sub-module 116, a queuing platform sub-module 115, and a knowledge service database sub-module 117.
  • the seat module 104 includes a seat sub-module 112 and a business assistant screen sub-module 113.
  • Configuration management module 103 includes a virtual service robot configuration submodule 118, a seat transfer rule configuration submodule 119, a question and answer configuration submodule 120, and a process and answer configuration submodule 121.
  • the introduction of each module and sub-module can refer to the above-mentioned embodiment, and the detailed description will not be repeated.
  • the virtual service robot proposed in this application can replace the seats or physical robots that enterprises originally need to invest, and can reduce costs and shorten the construction period for enterprises. It can be less dependent on the site, and can be more flexible and flexible and can be automatically deployed at the back-end;
  • the application provides simultaneous answers that display the answers on the screen and the sounds and actions of the virtual service robot, presenting the user's visual, auditory and tactile senses, improving the efficiency of user problem solving and experience problems;
  • this application can be integrated with traditional contact centers, generally Virtual service robots can answer questions on their own, and help solve difficult questions or agents that require agent intervention. The dimensions of intervention can be combined with various strategies and are more flexible.
  • FIG. 7 is a flowchart of a method of executing a service using the system provided by the present application. As shown in FIG. 7, the method provided by the present application mainly includes:
  • S71 User question input.
  • the virtual service robot sub-module sends the user question to the robot engine sub-module. If it is a voice input, it calls the voice-to-text interface of the voice platform sub-module, and then sends it to the question-and-answer engine sub-module.
  • the Q&A engine sub-module calculates whether to transfer the agent according to the configured question dimension rule, if the agent needs to be transferred, go to step S79, if there is no need to transfer the agent, go to step S73;
  • Step S73 The question answering engine submodule obtains the answers to the questions (including the rich text domain answer, the voice domain answer, and the answer in the rich text domain) through the process engine submodule (process question) or the semantic platform submodule (general question or question and answer question) to the knowledge service library Action domain answer).
  • process engine submodule process question
  • semantic platform submodule general question or question and answer question
  • Step S74 The question and answer engine sub-module calculates whether to transfer the agent according to the configured answer dimension rule, if the agent is to be transferred, go to step S79, if there is no need to transfer the agent, go to step S79;
  • Step S75 The question and answer engine sub-module returns the answer to the robot engine sub-module, and calls the text-to-speech interface of the voice platform sub-module to process the voice domain answer part.
  • Step S76 The robot engine sub-module returns answers to the user's question to the virtual service robot sub-module.
  • Step S77 The service screen sub-module renders rich text content, while the virtual service robot sub-module performs voice and action presentation, collects user feedback and sends it to the robot engine sub-module, and the robot engine sub-module sends it to the question-and-answer engine sub-module.
  • Step S78 The question and answer engine sub-module calculates whether to transfer the seat according to the configured user feedback dimension rule. If the seat is to be transferred, go to step S79. If the expert does not need to be transferred, the user question request is ended.
  • Step S79 The question and answer engine sub-module notifies the transfer seat engine sub-module, and the transfer seat engine sub-module notifies the queuing platform sub-module to transfer to the seat sub-module.
  • Step S791 According to the reported question, the agent issues the voice answer through the agent sub-module, issues the rich text answer and the action answer through the service assistant screen, and sends the answer to the transfer agent engine sub-module.
  • Step S792 The transfer seat engine sub-module delivers the answer to the question-answer engine sub-module, and the question-answer engine sub-module returns the answer to the robot engine sub-module.
  • Step S793 The robot engine sub-module returns answers to the user's question to the virtual service robot sub-module.
  • Step S794 The service screen sub-module displays the rich text answer, while the virtual service robot sub-module performs voice and action display, and ends the user's question request.
  • FIG. 8 is a flow chart of a method for implementing a service method using the system provided by the present application. The method is applied to the situation of small chat problems.
  • the technical solution provided by the present application mainly includes:
  • the semantic platform finds the answer from the gossip library.
  • the answer consists of three parts: 1. Rich text: It can be a form composed of text and pictures, used to display on the service screen; 2. Voice content: "My girlfriend sent me a message and said I am", used for the voice response of the virtual service robot; 3. Action expression: It can be cute, used for the action expression of the virtual service robot.
  • S84 The virtual service robot responds with voice, action expressions, and the service screen displays the answer content to assist in understanding, and the three are synchronized. This question and answer process ends.
  • FIG. 9 is a flowchart of a method of executing a service using the system provided by the present application, and the method is applied to the case of general question and answer.
  • the technical solutions provided by this application mainly include:
  • the question and answer engine sub-module judges that the question is a business question of China Construction Bank, and the question does not need to be assisted by an agent for the time being. At the same time, the question is a general question and answer question (not a process question).
  • S93 The semantic platform sub-module finds the answer from the general question and answer database.
  • the answer includes three parts: 1. Rich text: an introduction video can be used to display on the service screen; 2. Voice content: "You can use the mobile banking' homepage-Dragon Payment—red envelope—ordinary red envelope/fun red envelope "Send and receive dragon payment red envelope", used for voice response of virtual service robot; 3. Action expression: It can be some gesture-guided action, used for the action expression of virtual service robot.
  • S94 The question and answer engine sub-module judges that the answer does not need to be transferred to the agent to assist in processing, and can be directly answered by the virtual service robot;
  • the virtual service robot has voice answers, action expressions, and the service screen sub-modules show the answer content to assist in understanding, and the three are synchronized. This question and answer process ends.
  • FIG. 10 is a flowchart of a method of executing a service using the system provided by this application, and the method is applied to the situation of a business process problem.
  • the technical solutions provided by this application mainly include:
  • the question and answer engine sub-module judges that the question is a ticket reservation business question, and the question does not need to be assisted by an agent for the time being, and the question is a business process question (not a general question and answer);
  • the question and answer engine sub-module analyzes the question needs "departure date”, “departure place”, “destination”, and the user has a destination in Beijing in the question, and the user needs to specify the departure date and place of departure, so the answer: 1. Rich text: form for booking a flight, highlight the departure date and choice of departure, select Beijing as the destination, and display it on the service screen; 2. Voice content: "Please select the departure date and place of departure", for the virtual service robot Voice response; 3. Action expression: It can be a guided action of some gestures, which is used 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-modules show the answer content to assist in understanding, and the three are synchronized.
  • S136 The virtual service robot responds with voice, moves and expresses, and the sub-module of the service screen displays rich text content to assist understanding, and the three are synchronized.
  • FIG. 11 is a flowchart of a method of executing a service using the system provided by the present application, and the method is applied to the situation of a business process problem.
  • the technical solutions provided by this application mainly include:
  • the question and answer engine sub-module judges that the problem is a service problem of the broadband TV, and judges the problem according to the rules and requires assistance from an agent.
  • S143 The sub-module of the queuing platform is connected to the expert seat.
  • S144 The agent issues the guidance answer according to the question: 1. Rich text: Push the operation video, used to display the sub-module of the service screen; 2. Voice content: "Your camera is pointed at the TV fault screen", used for the virtual service robot's voice response; 3. Action expression: it can be a guided action of some gestures, used for the action expression of virtual service robot.
  • S145 The virtual service robot responds with voice, moves and expresses, and the sub-module of the service screen displays rich text content to assist understanding, and the three are synchronized.
  • S146 The virtual service robot responds with voice, moves and expresses, and the sub-module of the service screen displays rich text content to assist understanding, and the three are synchronized.
  • FIG. 12 is a schematic structural diagram of a device provided in this application.
  • the device provided in this application includes one or more processors 121 and a memory 122; There may be one or more processors 121 in the device.
  • 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 processed by the one or more programs.
  • the processor 121 executes, so that the one or more processors 121 implement the method described in the embodiment of the present invention.
  • the equipment also includes: 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 device may be connected through a bus or other methods.
  • the connection through a bus is taken as an example.
  • the input device 124 can be used to receive inputted numeric or character information, and generate key signal input related to user settings and function control of the device.
  • 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 transmit and receive information according to the control of the processor 121.
  • the memory 122 can be 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 in the service device). 102. Contact center platform module 103 and agent module 104), and program instructions/modules corresponding to the service method described in the embodiment 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 program storage area and a data storage area.
  • the program storage area may store an operating system and an application program required by at least one function; the data storage area may store data created according to the use of the device, and the like.
  • the memory 122 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices.
  • the memory 122 may further include a memory remotely provided with respect to the processor 121, and these remote memories may be connected to the device through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
  • the embodiment of the present application further provides a storage medium, the storage medium stores a computer program, and the computer program is executed by a processor to implement the method described in any of the embodiments of the present application.
  • the method includes: receiving a target question raised by a user; in the case of judging that the target question does not need to be answered by an agent based on the question rule, querying based on the target question Corresponding target answer; when it is determined based on the target answer that the target question does not need to be answered by an agent, the target answer is sent to the user terminal; when it is judged based on the target answer that the target question needs to be answered by an agent Next, obtain the agent answer to the target question provided by the agent; wherein the agent answer or the target answer includes at least one of a rich text answer and a voice answer, as well as an action answer; feedback the agent answer to user terminal.
  • the method includes: obtaining the target question raised by the user, and sending the target question to the back-end end; and the agent who receives the target question fed back by the back-end end
  • the answer or the target answer, the agent answer or the target answer including at least one of a rich text answer and a voice answer, and an action answer; display the rich text answer; instruct the virtual service robot to display the voice answer and action The answer is presented.
  • user terminal encompasses any suitable type of wireless user equipment, such as a mobile phone, a portable data processing device, a portable web browser, or a vehicle-mounted mobile station.
  • the various embodiments of the present application can be implemented in hardware or dedicated circuits, software, logic or any combination thereof.
  • some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device, although the present application is not limited thereto.
  • Computer program instructions can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code written in any combination of one or more programming languages or Object code.
  • ISA instruction set architecture
  • the block diagram of any logical decision in the drawings of this application may represent program steps, or may represent interconnected logic circuits, modules, and functions, or may represent a combination of program steps and logic circuits, modules, and functions.
  • the computer program can be stored on the memory.
  • the memory can be of any type suitable for the local technical environment and can 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 multi-function optical discs) DVD or CD) etc.
  • Computer-readable media may include non-transitory storage media.
  • the data processor can be any type suitable for the local technical environment, such as but not limited to general-purpose computers, special-purpose computers, microprocessors, digital signal processors (DSP), application-specific integrated circuits (ASIC), programmable logic devices (FGPA) And processors based on multi-core processor architecture.
  • DSP digital signal processors
  • ASIC application-specific integrated circuits
  • FGPA programmable logic devices

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Databases & Information Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • General Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • Development Economics (AREA)
  • Primary Health Care (AREA)
  • Human Resources & Organizations (AREA)
  • General Health & Medical Sciences (AREA)
  • Accounting & Taxation (AREA)
  • Health & Medical Sciences (AREA)
  • Finance (AREA)
  • Artificial Intelligence (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • User Interface Of Digital Computer (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

一种服务方法、装置、系统、设备及存储介质，该方法包括：用户端获取用户提出的目标问题，将目标问题发送至后台端；后台端在基于问题规则判断目标问题不需要坐席解答的情况下，基于目标问题查询对应的目标答案；后台端在基于目标答案判断目标问题不需要坐席解答的情况下，将目标答案发送至用户端；后台端在基于目标答案判断目标问题需要坐席解答的情况下，获取坐席提供的针对目标问题的坐席答案，并将坐席答案反馈给用户端；其中，坐席答案或者目标答案包括富文本答案和语音答案中的至少一种，以及动作答案；用户端将富文本答案进行展示；用户端指示虚拟服务机器人将语音答案和动作答案进行展现。

Description

一种服务方法、装置、系统、设备及存储介质
相关申请的交叉引用
本申请基于申请号为201911214770.5、申请日为2019年12月2日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本申请作为参考。
技术领域
本申请涉及通信技术领域，具体涉及一种服务方法、装置、系统、设备及存储介质。
背景技术
联络中心又叫客户服务中心，它是充分利用现代通信与计算机技术，如(计算机电话集成，Computer telephone integration，CTI)、交互式语音应答Interactive(voice response，IVR)、自动呼叫分配(Automatic call distribution，ACD)等，与企业连为一体的完整的综合信息服务系统，可以自动灵活地处理大量不同的电话呼入和呼出业务。联络中心不仅仅是企业在最外层加上的一个服务层，除了为外部客户服务外，也为整个企业的形象、管理、服务、调度、营销等起到非常重要的统一协调和提升作用，并可提供对企业所有通信数据的查询、汇总、统计分析等功能，辅助企业决策。联络中心主要分二种类型，呼入型联络中心和呼出型联络中心，呼入型联络中心的特点是接听客户来电，为客户提供一系列的服务与支持，如各种技术支持中心、客户服务中心、电话理赔中心等；而呼出型联络中心一般来说以从事市场营销和电话销售活动为主，是企业的利润中心，如邮购公司、电视购物、直销公司等。
通常联络中心的业务处理人员被称为坐席。坐席通过联络中心系统接入或者呼出用户，对于用户各种要求，坐席需要在业务系统中完成用户的要求，再通过联络中心系统将结果反馈给用户。例如，用户拨打电话来查询话费余额，坐席在联络中心系统中接入用户的电话。在获取了用户的要求后，坐席在业务系统中查询话费余额。最后通过呼叫中心系统将查询结果反馈给用户。
随着社会和科学的不断进步和发展，人们的生活水平不断得到提高，用户服务需求在不停的增加，出现了各种创新。一些企业(金融、医疗、零售、机场、展馆、政府等)利用云计算、大数据、人工智能、移动互联网的深度融合，推出了实体机器人，将机器人技术、人工智能技术融入场景，打造高效的智能场景服务模式，实现人工做不到的多媒体营销，也能替代辅助人工做咨询、分流、及导购的工作。
上述的两种服务模式，自建坐席模式和实体机器人模式，对用户问题的解决效率相对较低，体验不好。
发明内容
本申请提供一种服务方法，包括：接收用户提出的目标问题；在基于问题规则判断所述目标问题不需要坐席解答的情况下，基于所述目标问题查询对应的目标答案；在基于所述目标答案判断所述目标问题不需要坐席解答的情况下，将所述目标答案发送至用户端；所述目标答案包括富文本答案和语音答案中的至少一种，以及动作答案；在基于所述目标答案判断所述目标问题需要坐席解答的情况下，获取坐席提供的针对所述目标问题的坐席答案，并将所述坐席答案反馈给用户端，其中，所述坐席答案包括富文本答案和语音答案中的至少一种，以及动作答案。
本申请提供一种服务方法，包括：获取用户提出的目标问题，将所述目标问题发送至后台端；接收所述后台端反馈的所述目标问题的坐席答案或者目标答案，所述坐席答案或者目标答案，包括富文本答案和语音答案中的至少一种，以及动作答案；将所述富文本答案进行展示；指示虚拟服务机器人将所述语音答案和动作答案进行展现。
本申请提供一种服务方法，包括：用户端获取用户提出的目标问题，将所述目标问题发送至后台端；所述后台端接收用户提出的目标问题；所述后台端在基于问题规则判断所述目标问题不需要坐席解答的情况下，基于所述目标问题查询对应的目标答案；所述后台端在基于所述目标答案判断所述目标问题不需要坐席解答的情况下，将所述目标答案发送至用户端；所述后台端在基于所述目标答案判断所述目标问题需要坐席解答的情况下，获取坐席提供的针对所述目标问题的坐席答案，并将坐席答案反馈给用户端；其中，所述坐席答案或者所述目标答案包括富文本答案和语音答案中的至少一种，以及动作答案；所述用户端接收所述后台端反馈的所述目标问题的坐席答案或者目 标答案；所述用户端将所述富文本答案进行展示；所述用户端指示虚拟服务机器人将所述语音答案和动作答案进行展现。
本申请提供一种服务装置，包括：服务引擎模块，被设置为接收用户提出的目标问题；服务引擎模块，被设置为在基于问题规则判断所述目标问题不需要坐席解答的情况下，基于所述目标问题查询对应的目标答案，或者通过联络中心平台模块基于所述目标问题查询对应的目标答案；服务引擎模块，被设置为在基于所述目标答案判断所述目标问题不需要坐席解答的情况下，将所述目标答案发送至用户端；坐席模块，用于在基于所述目标答案判断所述目标问题需要坐席解答的情况下，获取坐席提供的针对所述目标问题的坐席答案；其中，所述坐席答案或者所述目标答案包括富文本答案和语音答案中的至少一种，以及动作答案；服务引擎模块，被设置为通过所述联络中心平台模块获取所述坐席模块的坐席答案，并将所述坐席答案反馈给用户端。
本申请提供一种服务装置，包括：服务模块；所述服务模块包括服务屏幕子模块和虚拟服务机器人子模块；所述虚拟服务机器人子模块，或者服务屏幕子模块被设置为获取用户提出的目标问题；所述虚拟服务机器人子模块，被设置为将所述目标问题发送至后台端；所述虚拟服务机器人子模块，被设置为接收所述后台端反馈的所述目标问题的坐席答案或者目标答案，所述坐席答案或者目标答案，包括富文本答案和语音答案中的至少一种，以及动作答案；所述服务屏幕子模块，被设置为将所述富文本答案进行展示；所述虚拟服务机器人子模块，被设置为指示虚拟服务机器人将所述语音答案和动作答案进行展现。
本申请提供一种服务系统，包括：服务模块，被设置为获取用户提出的目标问题，将所述目标问题发送至服务引擎模块；服务引擎模块，被设置为在基于问题规则判断所述目标问题不需要坐席解答的情况下，基于所述目标问题查询对应的目标答案，或者通过联络中心平台模块基于所述目标问题查询对应的目标答案，并将所述目标答案发送至用户端；所述坐席模块，被设置为在基于所述目标答案判断所述目标问题需要坐席解答的情况下，获取坐席提供的针对所述目标问题的坐席答案；服务引擎模块，被设置为通过所述联络中心平台模块获取所述坐席模块的坐席答案，将所述坐席答案反馈给服务模块；服务模块，被设置为接收所述目标答案或者坐席答案，所述目标答案，包括富文本答案和语音答案中的至少一种，以及动作答案，以及将所述富文本答案进行展示，指示虚拟服务机器人将所述语音答案和动作答案进行展现。
本申请提供一种设备，包括：一个或多个处理器；存储器，用于存储一个或多个程序；当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现本申请任一项所述的方法。
本申请提供一种存储介质，所述存储介质存储有计算机程序，所述计算机程序被处理器执行时实现本申请任一项所述的方法。
关于本申请的以上实施例和其他方面以及其实现方式，在附图说明、具体实施方式和权利要求中提供更多说明。
附图说明
图1是本申请提供的一种服务方法流程图；
图2是本申请提供的一种服务方法流程图；
图3a是本申请提供的一种服务方法流程图；
图3b是本申请提供的一种服务方法流程图；
图4是本申请提供的一种服务装置结构框图；
图5是本申请提供的一种服务装置结构框图；
图6是本申请提供的一种服务系统结构示意图；
图7是采用本申请提供的服务系统执行一种服务方法流程图；
图8是采用本申请提供的服务系统执行一种服务方法流程图；
图9是采用本申请提供的服务系统执行一种服务方法流程图；
图10是采用本申请提供的服务系统执行一种服务方法流程图；
图11是采用本申请提供的服务系统执行一种服务方法流程图；
图12是本申请提供的一种设备结构示意图。
具体实施方式
为使本申请的目的、技术方案和优点更加清楚明白，下文中将结合附图对本申请的实施例进行详细说明。需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互任意组合。
在附图的流程图示出的步骤可以在诸如一组计算机可执行指令的计算机系统中执行。并且，虽然在流程图中示出了逻辑顺序，但是在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤。
相关技术中服务模式中的自建坐席模式需要招聘话务人员，话务人员需要经过专业培训，需要坐席办公的场地和相应设备；相关技术中服务模式中的实体机器人模式需要投入设备和实体机器人活动场地，因此，对企业来说一般建设的成本较高、建设的周期较长，同时这种模式遇见专业问题，实体机器人无法解答。上述的自建坐席模式和实体机器人模式的服务，对用户的解决效率相对低下，体验不好。
在一个示例性实施方式中，图1是本申请提供的一种服务方法的流程图，如图1所示，所述方法可以应用于基于虚拟服务机器人解答用户问题的情况，所述方法可以由服务装置来执行，所述装置可以由软件和/或硬件来实现，所述方法可以应用于后台端。
如图1所示，本申请提供的方法主要包括：
S11：接收用户提出的目标问题。
在本申请中，用户端可以获取用户提出的目标问题，并发送至后台端。后台端接收用户提出的目标问题，其中，用户提出的目标问题可以是语音问题，或者也可以是文本问题。
S12：在基于问题规则判断所述目标问题不需要坐席解答的情况下，基于所述目标问题查询对应的目标答案。
在本申请中，可以根据问题规则判断目标问题是否需要坐席解答。在一个示例性的实施方式中，可以确定目标问题的难度，根据问题难度判断是否需要坐席解答。例如，通过判断目标问题的难度是否达到某个难度阈值，在没有达到该难度阈值的情况下，判断目标问题不需要坐席解答。
在一个示例性的实施方式中，所述基于所述目标问题查询对应的目标答案，包括：在所述目标问题为流程问题的情况下，基于所述流程问题查询对应的答案；在所述目标问题为问答性问题的情况下，基于所述问答性问题查询对应的答案。其中，流程问题可以是业务流程性的问题，问答性问题是采用的方式属于一问一答的方式，或者可以认为是普通问题。
S13：在基于所述目标答案判断所述目标问题不需要坐席解答的情况下，将所述目标答案发送至用户端；所述目标答案包括富文本答案和语音答案中的至少一种，以及动作答案。
在本申请中，可以根据目标答案判断目标问题是否需要坐席解答。在一个示例性的实施方式中，可以判断目标答案是否符合答案规则。在目标答案符合答案规则的情况下，判断目标问题不需要坐席解答。在目标答案不符合答案规则的情况下，判断目标问题需要坐席解答。答案规则可以根据需要进行配置，答案规则可以是答案与问题的匹配规则。
在一个示例性的实施方式中，可以基于目标答案与目标问题的匹配度判断是否需要坐席解答。在一个示例性的实施方式中，可以将目标答案和目标问题输入到模型中，计算目标答案与目标问题的匹配度，通过匹配度判断目标问题是否需要坐席解答。在匹配度大于设定匹配度的情况下，可以判断目标问题不需要坐席解答，在匹配度小于设定匹配度的情况下，可以判断目标问题需要坐席解答。
在目标问题不需要专家解答的情况下，将目标答案发送至用户端，用户可以通过用户端了解该目标答案。
S14：在基于所述目标答案判断所述目标问题需要坐席解答的情况下，获取坐席提供的针对所述目标问题的坐席答案，并将所述坐席答案反馈给用户端，其中，所述坐席答案包括富文本答案和语音答案中的至少一种，以及动作答案。
在本申请中，动作答案可以是动作表情、动作引导语等答案。
在本申请中，富文本答案、语音答案以及动作答案的时间域相同。在一个示例性的实施方式中，在坐席答案或者目标答案包括富文本答案和动作答案的情况下，所述将所述目标答案发送至用户端，包括：将所述富文本答案转换成语音答案；将所述富文本答案、所述动作答案和所述语音答案反馈给用户端。
在一个示例性的实施方式中，所述接收用户提出的目标问题，包括：接收用户提出的语音问题；将所述语音问题转换成文本问题，作为目标问题。
在一个示例性的实施方式中，本申请提供的方法还包括：接收用户对所述目标答案的反馈信息；在基于所述反馈信息判断所述目标问题需要坐席解答的情况下，获取坐席提供的针对所述目标问题的坐席答案，并将所述坐席答案反馈给用户端。
其中，可以根据针对用户的反馈规则对反馈信息进行分析，从而判断目标问题是否需要坐席解答。在一个示例性的实施方式中，可以对反馈信息进行语义、情感分析，可以基于反馈信息中的语义、情感中信息、或者对目标答案的满意度判断是否需要坐席解答。例如，在通过反馈信息判断用户属于生气、愤怒等情绪的情况下，判断需要坐席解答，或者在对目标答案的满意度低于设定满意度的情况下，判断需要坐席解答，否则不需要坐席解答。
在一个示例性的实施方式中，本申请提供的方法还可以包括：在基于所述问题规则判断所述目标问题需要坐席解答的情况下，获取坐席提供的针对所述目标问题的坐席答案，并将所述坐席答案反馈给用户端。
在一个示例性的实施方式中，本申请提供的方法还可以包括：对转坐席规则、问题规则、答案规则、针对用户反馈的规则进行配置，以及问题与对应答案的配置。
在一个示例性实施方式中，图2是本申请提供的一种服务方法的流程图，如图2所示，所述方法可以应用于基于虚拟服务机器人解答用户问题的情况，所述方法可以由服务装置来执行，所述装置可以由软件和/或硬件来实现，所述方法可以应用于用户端。
如图2所示，本申请提供的技术方案主要包括：
S21：获取用户提出的目标问题，将所述目标问题发送至后台端。
在本申请中，目标问题可以是语音问题，或者也可以是文本问题。用户端可以获取用户提出的目标问题，并发送至后台端。
S22：接收所述后台端反馈的所述目标问题的坐席答案或者目标答案，所述坐席答案或者目标答案，包括富文本答案和语音答案中的至少一种，以及动作答案。
在本申请中，后台端可以根据目标问题查询对应的目标答案，或者后台端可以获取坐席提供的坐席答案，并将目标答案或者坐席答案反馈给用户端。用户端接收目标答案或者坐席答案。
在一个示例性的实施方式中，目标答案或者坐席答案包括富文本答案、语音答案以及动作答案。
在本申请中，动作答案可以是动作表情、动作引导语等答案。富文本答案、语音答案以及动作答案的时间域相同。
S23：将所述富文本答案进行展示。
S24：指示虚拟服务机器人将所述语音答案和动作答案进行展现。
在本申请中，虚拟服务机器人可以显示在用户端的屏幕上，在接收到目标答案或者坐席答案的情况下，可以将富文本答案进行展示，指示虚拟服务机器人将说出语音答案，并做出动作答案。
在一个示例性的实施方式中，本申请提供的方法还可以包括：获取用户针对所述目标答案的反馈信息，将所述反馈信息发送至后台端。其中，反馈信息可以携带用户满意度信息，或者可以体现用户情绪信息等。
在一个示例性实施方式中，图3a是本申请提供的一种服务方法的流程图，如图3a所示，所述方法可以应用于基于虚拟服务机器人解答用户问题的情况。
如图3a所示，本申请提供的技术方案包括：
S31：用户端获取用户提出的目标问题，将所述目标问题发送至后台端。
S32：所述后台端接收用户提出的目标问题。
S33：所述后台端在基于问题规则判断所述目标问题不需要坐席解答的情况下，基于所述目标问题查询对应的目标答案。
S34：所述后台端在基于所述目标答案判断所述目标问题不需要坐席解答的情况下，将所述目标答案发送至用户端。
S35：所述后台端在基于所述目标答案判断所述目标问题需要坐席解答的情况下，获取坐席提供的针对所述目标问题的坐席答案；其中，所述坐席答案或者所述目标答案包括富文本答案和语音答案中的至少一种，以及动作答案。
S36：所述用户端接收所述后台端反馈的所述目标问题的坐席答案或者目标答案，所述坐席答案或者目标答案。
S37：所述用户端将所述富文本答案进行展示。
S38：所述用户端指示虚拟服务机器人将所述语音答案和动作答案进行展现。
在一个示例性实施方式中，本申请提供的方法还包括：在基于问题规则判断所述目标问题需要坐席解答的情况下，获取坐席提供的针对所述目标问题的坐席答案，并将所述坐席答案反馈给用户端。
在一个示例性实施方式中，本申请提供的方法还包括：接收用户对所述目标答案的反馈信息；在基于所述反馈信息判断所述目标问题需要坐席解答的情况下，获取坐席提供的针对所述目标问题的坐席答案，并将所述坐席答案反馈给用户端。
在一个示例性实施方式中，图3b是本申请提供的一种服务方法的流程图，如图3b所示，所述方法可以应用于基于虚拟服务机器人解答用户问题的情况。
如图3b所示，本申请提供的技术方案包括：
S311：对虚拟服务机器人形体、动作进行配置，问题与答案进行配置，以及转接坐席规则配置。
在本申请中，对虚拟服务机器人的形体、可以发出的动作进行配置。
问题与答案的配置可以包括：普通问答性问题及其答案配置，答案配置包括富文本、语音和动作配置，包括三者时间域的同步；流程问题、引导语及其答案配置，答案配置包括富文本、语音和动作配置，包括三者时间域的同步。
转接坐席规则配置，包括针对问题规则的配置，针对答案规则的配置，针对用户反馈的规则配置，进一步的规则，不同企业可以自己定义，如针对问题规则，可以配置问题的难度达到某个难度就转接坐席等。针对答案规则；可以配置答案的匹配度低于某个阀值就转接专家坐席等；针对用户的反馈规则，可以配置用户情绪差或者用户明显提出的对答案有质疑，转接坐席，或者通过虚拟服务机器人自动回答的满意度没有达到某个阀值就转接坐席。
S312：用户提出问题。
S313：对问题进行语义分析和匹配，找到相应的答案，答案包括富文本答案、语音答案、动作答案。
S314：可以坐席介入获取答案，坐席介入的时机可以针对问题本身、可以针对答案本身、可以针对用户反馈三个维度进行计算，坐席介入后给出的答案也包括富文本答案、语音答案和动作答案。
S315：获取到用户的问题的富文本答案、语音答案、动作答案三部分答案后，同步给出答案的渲染和展现，其中，通过屏幕中渲染和展示富文本答案，通过虚拟服务机器人同步说出语音答案和做出动作答案。
在一个示例性实施方式中，图4是本申请提供的一种服务装置，所述装置配置在后台端，所述装置包括：服务引擎模块102、联络中心平台模块103和坐席模块104。
服务引擎模块102，被设置为接收用户提出的目标问题；
服务引擎模块102，被设置为在判断所述目标问题不需要坐席解答的情况下，基于所述目标问题查询对应的目标答案，或者通过联络中心平台模块103基于所述目标问题查询对应的目标答案；
服务引擎模块102，被设置为在基于所述目标答案判断所述目标问题不需要坐席解答的情况下，将所述目标答案发送至用户端；
坐席模块104，用于在基于所述目标答案判断所述目标问题需要坐席解答的情况下，获取坐席提供的针对所述目标问题的坐席答案；其中，所述坐席答案或者所述目标答案包括富文本答案和语音答案中的至少一种，以及动作答案；
服务引擎模块102，被设置为通过联络中心平台模块103获取所述坐席模块104的坐席答案，并将所述坐席答案反馈给用户端。
在一个示例性的实施方式中，服务引擎模块102包括机器人引擎子模块108、问答引擎子模块109、流程引擎 子模块110；所述联络中心平台模块103包括语义平台子模块116和知识业务库子模块117；
所述机器人引擎子模块108，被设置为接收用户提出的目标问题；
所述问答引擎子模块109，被设置为在判断所述目标问题不需要坐席解答，且所述目标问题为流程问题的情况下，通过流程引擎子模块110从所述知识业务库子模块117中基于所述流程问题查询对应的目标答案，以及在判断所述目标问题不需要坐席解答，且所述目标问题为问答性问题的情况下，通过语义平台子模块116从所述知识业务库子模块117中基于所述问答性问题查询对应的答案。
在一个示例性的实施方式中，流程引擎子模块110，被设置为会话管理、流程引导和执行。
在一个示例性的实施方式中，机器人引擎子模块108，被设置为进行登录控制、会话管理。
在一个示例性的实施方式中，所述问答引擎子模块109，被设置为在判断所述目标问题不需要坐席解答的情况下，通过机器人引擎子模块108将所述目标答案发送至用户端。
在一个示例性的实施方式中，所述联络中心平台模块103还包括：语音平台子模块114，在所述目标答案包括富文本答案和动作答案的情况下，机器人引擎子模块108，被设置为接收问答引擎子模块109发送的目标答案，调用语音平台子模块114将所述富文本答案转换成语音答案，并将所述富文本答案、所述动作答案和所述语音答案反馈给用户端。
在一个示例性的实施方式中，所述服务引擎模块102还包括转坐席子模块111；所述联络中心平台模块103还包括排队平台子模块；所述坐席模块104包括坐席台子模块112和业务辅助屏幕子模块113；
所述机器人引擎子模块108，被设置为接收用户对所述目标答案的反馈信息；
所述问答引擎子模块，被设置为在基于所述反馈信息判断所述目标问题需要坐席解答，或者基于所述问题规则判断所述目标问题需要坐席解答，或者基于所述目标答案判断所述目标问题需要坐席解答的情况下，通知转坐席引擎子模块111通知排队平台子模块115转接到坐席台子模块112；
所述坐席台子模块112，被设置为获取坐席提供的语音答案，并将所述语音答案通过联络中心平台模块103反馈至转坐席引擎子模块111；
所述业务辅助屏幕模块113，被设置为获取坐席提供的富文本答案和动作答案，并通过坐席台子模块112以及联络中心平台模块103反馈至转坐席引擎子模块111；
转坐席引擎子模块111，被设置为通过问答引擎模块109以及机器人引擎子模块108将所述富文本答案、语音答案和动作答案反馈至用户端。
其中，排队平台子模块115，可以接收转坐席引擎子模块111的请求，并完成坐席的排队，并将请求路由到坐席台子模块112，同时可以返回坐席答案到转坐席引擎子模块111，转坐席引擎子模块111，将坐席答案反馈到问答引擎子模块109，问答引擎子模块109将坐席答案发送至机器人引擎子模块108，机器人引擎子模块108将坐席答案反馈至用户端。坐席答案包括富文本答案、语音答案和动作答案。
在一个示例性的实施方式中，本申请提供的装置还包括配置管理模块105，
所述配置管理模块105包括虚拟服务机器人配置子模块118、转坐席规则配置子模块119、问题及答案配置子模块120和流程及答案配置子模块121；
所述虚拟服务机器人配置子模块118，被配置为虚拟服务机器人的动作配置，配置结果存储到知识业务库子模块117；
所述转坐席规则配置子模块119，被配置为对问题规则的配置、答案规则的配置、以及针对用户反馈的规则配置，配置结果存储到知识业务库子模块117；
所述问题及答案配置子模块120，被配置为问答性问题及答案配置，答案包括富文本答案、动作答案和语音答案，将配置结果存储到知识业务库子模块117；其中，富文本答案、动作答案和语音答案的时间域同步；
所述流程及答案配置子模块121，被配置为流程问题、引导语及答案配置，所述答案包括富文本答案、动作答案和语音答案，将配置结果存储到知识业务库子模块117；其中，富文本答案、动作答案和语音答案的时间域同步。
其中，知识业务库子模块117，可以管理各个模块写入的数据和其他模块的查询请求。
需要说明的是，本申请中提供的服务装置的各个模块并不局限于上述的划分形式，还可以根据需要对服务装置的各个模块进行划分。其中，服务引擎模块102和联络中心平台模块103中的各个子模块的划分并不局限于上述的划分形式，可根据需要进行划分子模块。
上述装置可执行本申请实施例所提供的服务方法，具备执行方法相应的功能模块和有益效果。
在一个示例性实施方式中，图5是本申请提供的一种服务装置，所述装置配置在用户端，所述装置包括服务模块101；
所述服务模块包括服务屏幕子模块106和虚拟服务机器人子模块107；
所述虚拟服务机器人子模块106，或者服务屏幕子模块107被设置为获取用户提出的目标问题；
所述虚拟服务机器人子模块106，被设置为将所述目标问题发送至后台端；
所述虚拟服务机器人子模块106，被设置为接收所述后台端反馈的所述目标问题的坐席答案或者目标答案，所述坐席答案或者目标答案，包括富文本答案和语音答案中的至少一种，以及动作答案；
所述服务屏幕子模块106，被设置为将所述富文本答案进行展示；
所述虚拟服务机器人子模块107，被设置为指示虚拟服务机器人将所述语音答案和动作答案进行展现。
在一个示例性的实施方式中，所述虚拟服务机器人子模块106，或者服务屏幕子模块107被设置为获取用户针对所述目标答案的反馈信息；
所述虚拟服务机器人子模块106，被设置为将所述反馈信息发送至后台端。
其中，具体的虚拟服务机器人子模块106，将反馈信息发送至后台端的机器人引擎子模块，机器人引擎子模块将目标答案或者坐席答案反馈给虚拟服务机器人子模块106，虚拟服务机器人子模块107将富文本答案发送至服务屏幕子模块106，服务屏幕子模块106将富文本答案进行展示，虚拟服务机器人子模块107指示虚拟服务机器人将语音答案和动作答案进行展现。
上述装置可执行本申请实施例所提供的服务方法，具备执行方法相应的功能模块和有益效果。
在一个示例性实施方式中，图6是本申请提供的一种服务装置，所述装置包括服务模块101、服务引擎模块102、联络中心平台模块103和坐席模块104。
服务模块101，被设置为获取用户提出的目标问题，将所述目标问题发送至服务引擎模块102；
服务引擎模块102，被设置为在基于问题规则判断所述目标问题不需要坐席解答的情况下，基于所述目标问题查询对应的目标答案，或者通过联络中心平台模块102基于所述目标问题查询对应的目标答案；
所述坐席模块104，被设置为在基于所述目标答案判断所述目标问题需要坐席解答的情况下，获取坐席提供的针对所述目标问题的坐席答案；其中，所述坐席答案或者所述目标答案包括富文本答案和语音答案中的至少一种，以及动作答案；
服务引擎模块102，被设置为通过所述联络中心平台模块103将所述坐席模块104获取的所述坐席答案反馈给服务模块101；
服务模块101，被设置为接收所述目标答案或者坐席答案，所述目标答案，包括富文本答案和语音答案中的至少一种，以及动作答案，以及将所述富文本答案进行展示，指示虚拟服务机器人将所述语音答案和动作答案进行展现。
在一个示例性的实施方式中，本申请提供的系统还可以包括配置管理模块105，其中，服务模块101包括服务屏幕子模块106和虚拟服务机器人子模块107，服务引擎模块102：包括机器人引擎子模块108、问答引擎子模块109、流程引擎子模块110和转坐席引擎子模块111。联络中心平台模块103包括语音平台子模块114、语义平台子模块116、排队平台子模块115和知识业务库子模块117。坐席模块104包括坐席台子模块112和业务辅助屏幕子模块113。配置管理模块103：包括虚拟服务机器人配置子模块118、转坐席规则配置子模块119、问题及答案配置子模块120和流程及答案配置子模块121。其中，各个模块以及子模块的介绍可以参考上述实施例，不再累述。
本申请提出的虚拟服务机器人能替代企业原先需要投入的坐席或者实体机器人，能为企业降低成本投入、缩短 建设周期，可以不太依赖场地，可以做较灵活的弹性伸缩和后台端的自动部署；本申请提供将答案通过屏幕展现和虚拟服务机器人声音和动作的同步解答，给用户视觉、听觉和触觉一体的呈现，提高用户问题解决效率和体验问题；本申请可以和传统的联络中心有机集成，一般问题虚拟服务机器人自行解答，疑难问题或者需要坐席介入的坐席协助解答，介入的维度可以各种策略组合，比较灵活。
在一个示例性实施方式中，图7是采用本申请提供的系统执行一种服务方法流程图，如图7所示，本申请提供的该方法主要包括：
S71：用户问题输入，虚拟服务机器人子模块把用户问题送给机器人引擎子模块，如果是语音输入，调用语音平台子模块的接口语音转文本，然后送到问答引擎子模块。
S72：问答引擎子模块根据配置的问题维度规则计算是否要转接坐席，如果要转接坐席，进入步骤S79，如果不需要转接坐席，进入步骤S73；
步骤S73：问答引擎子模块通过流程引擎子模块(流程问题)或者语义平台子模块(普通问题或者问答性问题)到知识业务库子模块获取问题的答案(包括富文本域答案，语音域答案和动作域答案)。
步骤S74：问答引擎子模块根据配置的答案维度规则计算是否要转接坐席，如果要转接坐席，进入步骤S79，如果不需要转接坐席，进入步骤S79；
步骤S75：问答引擎子模块回送答案到机器人引擎子模块，调用语音平台子模块的接口文本转语音处理语音域答案部分。
步骤S76：机器人引擎子模块回送用户问题的答案到虚拟服务机器人子模块。
步骤S77：服务屏幕子模块渲染富文本内容，同时虚拟服务机器人子模块进行语音和动作展现，并收集用户的反馈送给机器人引擎子模块，机器人引擎子模块送给问答引擎子模块。
步骤S78：问答引擎子模块根据配置的用户反馈维度规则计算是否要转接坐席，如果要转接坐席，进入步骤S79，如果不需要转接专家，结束本次用户问题的请求。
步骤S79：问答引擎子模块通知转坐席引擎子模块、转坐席引擎子模块通知排队平台子模块转接到坐席台子模块。
步骤S791：坐席根据上报的问题，通过坐席台子模块下发语音答案，通过业务辅助屏幕下发富文本答案和动作答案，并下发答案到转坐席引擎子模块。
步骤S792：转坐席引擎子模块下发答案给问答引擎子模块，问答引擎子模块回送答案到机器人引擎子模块。
步骤S793：机器人引擎子模块回送用户问题的答案到虚拟服务机器人子模块。
步骤S794：服务屏幕子模块展现富文本答案，同时虚拟服务机器人子模块进行语音和动作展现，结束本次用户问题的请求。
在一个示例性实施方式中，图8是采用本申请提供的系统执行一种服务方法流程图，该方法应用于闲聊问题的情况，如图8所示，本申请提供的技术方案主要包括：
S81：用户问：“怎么这么开心呀”；
S82：语义平台子模块判断该问题是闲聊问题。
S83，语义平台从闲聊库中找到答案，答案包括三部分：1、富文本：可以是文字和图片组成的表单，用于服务屏幕展现；2、语音内容：“女朋友给我发讯息说想我啦”，用于虚拟服务机器人语音回答；3、动作表情：可以是卖萌的，用于虚拟服务机器人的动作表情。
S84：虚拟服务机器人语音回答，动作表情，服务屏幕展现答案内容协助理解，并且三者同步，本次问答流程结束。
在一个示例性实施方式中，图9是采用本申请提供的系统执行一种服务方法流程图，该方法应用于普通问答的情况。如图9所示，本申请提供的技术方案主要包括：
S91：用户问：“如何使用龙支付红包功能”。
S92：问答引擎子模块判断该问题是建设银行的业务问题，该问题暂不需接续坐席来协助，同时该问题是普通 问答问题(非流程问题)。
S93：语义平台子模块从普通问答库中找到答案，答案包括三部分：1、富文本：可以一段介绍视频，用于服务屏幕展现；2、语音内容：“您可通过手机银行‘首页—龙支付—红包—普通红包/趣味红包’收发龙支付红包”，用于虚拟服务机器人语音回答；3、动作表情：可以是一些手势引导的动作，用于虚拟服务机器人的动作表情。
S94：问答引擎子模块判断该答案不需要转接坐席协助处理，可以直接让虚拟服务机器人来回答；
S95：虚拟服务机器人语音回答，动作表情，服务屏幕子模块展现答案内容协助理解，并且三者同步，本次问答流程结束。
在一个示例性实施方式中，图10是采用本申请提供的系统执行一种服务方法流程图，该方法应用于业务流程问题的情况。如图10所示，本申请提供的技术方案主要包括：
S131，用户问：“我要预订一张到北京的机票”；
S132，问答引擎子模块判断该问题是机票预定业务问题，该问题暂不需接坐席来协助，同时该问题是一个业务流程问题(非普通问答)；
S133，问答引擎子模块分析该问题需要“出发日期”，“出发地”，“目的地”，并且用户问题中已经有目的地北京，还需要用户明确出发日期和出发地，因此答案：1、富文本：预定航班的表单，高亮出发日期和出发的选择，目的地选择好北京，用于服务屏幕展现；2、语音内容：“请您选择出发日期和出发地”，用于虚拟服务机器人语音回答；3、动作表情：可以是一些手势的引导动作，用于虚拟服务机器人的动作表情。
S134：虚拟服务机器人语音回答，动作表情、服务屏幕子模块展现答案内容协助理解，并且三者同步。
S135：用户选择某个航班后，平台完成预定。答案：1、富文本：预定成功确认表单界面，用于服务屏幕展现；2、语音内容：“您的航班已经生成预定单，请确认下”，用于虚拟服务机器人语音回答；3、动作表情：可以是一些手势的引导动作，用于虚拟服务机器人的动作表情。
S136：虚拟服务机器人语音回答，动作表情，服务屏幕子模块展现富文本内容协助理解，并且三者同步。
S137：用户确认OK，本流程结束。
在一个示例性实施方式中，图11是采用本申请提供的系统执行一种服务方法流程图，该方法应用于业务流程问题的情况。如图11所示，本申请提供的技术方案主要包括：
S141：用户问：“我的宽带电视咋不能播放了”。
S142：问答引擎子模块判断该问题是宽带电视的业务问题，根据规则判断该问题需接坐席来协助。
S143：排队平台子模块接续到专家坐席。
S144：坐席根据问题下发指导答案：1、富文本：推送操作视频，用于服务屏幕子模块展现；2、语音内容：“你摄像头对准电视故障画面”，用于虚拟服务机器人语音回答；3、动作表情：可以是一些手势的引导动作，用于虚拟服务机器人的动作表情。
S145：虚拟服务机器人语音回答，动作表情，服务屏幕子模块展现富文本内容协助理解，并且三者同步。
S146：用户拍摄的内容同步到坐席的业务协助屏后，调出指导答案：1、富文本：推送操作视频，用于服务屏幕子模块展现；2、语音内容：“请重启下你的机顶盒”，用于虚拟服务机器人语音回答；3、动作表情：可以是一些手势的引导动作，用于虚拟服务机器人的动作表情。
S146：虚拟服务机器人语音回答，动作表情，服务屏幕子模块展现富文本内容协助理解，并且三者同步。
S147：用户确认OK，本流程结束。
本申请实施例还提供了一种设备，图12为本申请提供的一种设备的结构示意图，如图12所示，本申请提供的设备，包括一个或多个处理器121和存储器122；该设备中的处理器121可以是一个或多个，图12中以一个处理器121为例；存储器122用于存储一个或多个程序；所述一个或多个程序被所述一个或多个处理器121执行，使得所述一个或多个处理器121实现如本发明实施例中所述的方法。
设备还包括：通信装置123、输入装置124和输出装置125。
设备中的处理器121、存储器122、通信装置123、输入装置124和输出装置125可以通过总线或其他方式连接， 图12中以通过总线连接为例。
输入装置124可用于接收输入的数字或字符信息，以及产生与设备的用户设置以及功能控制有关的按键信号输入。输出装置125可包括显示屏等显示设备。
通信装置123可以包括接收器和发送器。通信装置123设置为根据处理器121的控制进行信息收发通信。
存储器122作为一种计算机可读存储介质，可设置为存储软件程序、计算机可执行程序以及模块，如本申请实施例所述服务方法对应的程序指令/模块(例如，服务装置中的服务引擎模块102、联络中心平台模块103和坐席模块104)，再如本申请实施例所述服务方法对应的程序指令/模块(例如，服务装置中的服务屏幕子模块106和虚拟服务机器人子模块107)。存储器122可包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序；存储数据区可存储根据设备的使用所创建的数据等。此外，存储器122可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他非易失性固态存储器件。在一些实例中，存储器122可进一步包括相对于处理器121远程设置的存储器，这些远程存储器可以通过网络连接至设备。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
本申请实施例还提供一种存储介质，所述存储介质存储有计算机程序，所述计算机程序被处理器执行时实现本申请实施例中任一所述的方法。
实现本申请实施例中任一所述的服务方法时，所述方法包括：接收用户提出的目标问题；在基于问题规则判断所述目标问题不需要坐席解答的情况下，基于所述目标问题查询对应的目标答案；在基于所述目标答案判断所述目标问题不需要坐席解答的情况下，将所述目标答案发送至用户端；在基于所述目标答案判断所述目标问题需要坐席解答的情况下，获取坐席提供的针对所述目标问题的坐席答案；其中，所述坐席答案或者所述目标答案包括富文本答案和语音答案中的至少一种，以及动作答案；将所述坐席答案反馈给用户端。
实现本申请实施例中任一所述的服务方法时，所述方法包括：获取用户提出的目标问题，将所述目标问题发送至后台端；接收所述后台端反馈的所述目标问题的坐席答案或者目标答案，所述坐席答案或者目标答案，包括富文本答案和语音答案中的至少一种，以及动作答案；将所述富文本答案进行展示；指示虚拟服务机器人将所述语音答案和动作答案进行展现。
以上所述，仅为本申请的示例性实施例而已，并非用于限定本申请的保护范围。
本领域内的技术人员应明白，术语用户终端涵盖任何适合类型的无线用户设备，例如移动电话、便携数据处理装置、便携网络浏览器或车载移动台。
一般来说，本申请的多种实施例可以在硬件或专用电路、软件、逻辑或其任何组合中实现。例如，一些方面可以被实现在硬件中，而其它方面可以被实现在可以被控制器、微处理器或其它计算装置执行的固件或软件中，尽管本申请不限于此。
本申请的实施例可以通过移动装置的数据处理器执行计算机程序指令来实现，例如在处理器实体中，或者通过硬件，或者通过软件和硬件的组合。计算机程序指令可以是汇编指令、指令集架构(ISA)指令、机器指令、机器相关指令、微代码、固件指令、状态设置数据、或者以一种或多种编程语言的任意组合编写的源代码或目标代码。
本申请附图中的任何逻辑判决的框图可以表示程序步骤，或者可以表示相互连接的逻辑电路、模块和功能，或者可以表示程序步骤与逻辑电路、模块和功能的组合。计算机程序可以存储在存储器上。存储器可以具有任何适合于本地技术环境的类型并且可以使用任何适合的数据存储技术实现，例如但不限于只读存储器(ROM)、随机访问存储器(RAM)、光存储器装置和系统(数码多功能光碟DVD或CD光盘)等。计算机可读介质可以包括非瞬时性存储介质。数据处理器可以是任何适合于本地技术环境的类型，例如但不限于通用计算机、专用计算机、微处理器、数字信号处理器(DSP)、专用集成电路(ASIC)、可编程逻辑器件(FGPA)以及基于多核处理器架构的处理器。
通过示范性和非限制性的示例，上文已提供了对本申请的示范实施例的详细描述。但结合附图和权利要求来考虑，对以上实施例的多种修改和调整对本领域技术人员来说是显而易见的，但不偏离本发明的范围。因此，本发明的恰当范围将根据权利要求确定。

Claims (14)

  1. 一种服务方法，包括：
    接收用户提出的目标问题；
    在基于问题规则判断所述目标问题不需要坐席解答的情况下，基于所述目标问题查询对应的目标答案；
    在基于所述目标答案判断所述目标问题不需要坐席解答的情况下，将所述目标答案发送至用户端，其中，所述目标答案包括富文本答案和语音答案中的至少一种，以及动作答案；
    在基于所述目标答案判断所述目标问题需要坐席解答的情况下，获取坐席提供的针对所述目标问题的坐席答案，并将所述坐席答案反馈给用户端，其中，所述坐席答案包括富文本答案和语音答案中的至少一种，以及动作答案。
  2. 根据权利要求1所述的方法，还包括：
    接收用户对所述目标答案的反馈信息；
    在基于所述反馈信息判断所述目标问题需要坐席解答的情况下，获取坐席提供的针对所述目标问题的坐席答案，并将所述坐席答案反馈给用户端。
  3. 根据权利要求2所述的方法，其中，在所述目标答案包括富文本答案和动作答案的情况下，所述将所述目标答案发送至用户端，包括：
    将所述富文本答案转换成语音答案；
    将所述富文本答案、所述动作答案和所述语音答案反馈给用户端。
  4. 根据权利要求1所述的方法，还包括：
    在基于所述问题规则判断所述目标问题需要坐席解答的情况下，获取坐席提供的针对所述目标问题的坐席答案，并将所述坐席答案反馈给用户端。
  5. 根据权利要求1所述的方法，其中，所述接收用户提出的目标问题，包括：
    接收用户提出的语音问题；
    将所述语音问题转换成文本问题，作为目标问题。
  6. 根据权利要求1所述的方法，其中，所述基于所述目标问题查询对应的目标答案，包括：
    在所述目标问题为流程问题的情况下，基于所述流程问题查询对应的答案；
    在所述目标问题为问答性问题的情况下，基于所述问答性问题查询对应的答案。
  7. 一种服务方法，其中，包括：
    获取用户提出的目标问题，将所述目标问题发送至后台端；
    接收所述后台端反馈的所述目标问题的坐席答案或者目标答案，所述坐席答案或者目标答案，包括富文本答案和语音答案中的至少一种，以及动作答案；
    将所述富文本答案进行展示；
    指示虚拟服务机器人将所述语音答案和动作答案进行展现。
  8. 根据权利要求1所述的方法，还包括：
    获取用户针对所述目标答案的反馈信息，将所述反馈信息发送至后台端。
  9. 一种服务方法，包括：
    用户端获取用户提出的目标问题，将所述目标问题发送至后台端；
    所述后台端接收用户提出的目标问题；
    所述后台端在基于问题规则判断所述目标问题不需要坐席解答的情况下，基于所述目标问题查询对应的目标答案；
    所述后台端在基于所述目标答案判断所述目标问题不需要坐席解答的情况下，将所述目标答案发送至用户端；
    所述后台端在基于所述目标答案判断所述目标问题需要坐席解答的情况下，获取坐席提供的针对所述目标问题的坐席答案，并将坐席答案反馈给用户端；其中，所述坐席答案或者所述目标答案包括富文本答案和语音答案中的至少一种，以及动作答案；
    所述用户端接收所述后台端反馈的所述目标问题的坐席答案或者目标答案；
    所述用户端将所述富文本答案进行展示；
    所述用户端指示虚拟服务机器人将所述语音答案和动作答案进行展现。
  10. 一种服务装置，包括：服务引擎模块和坐席模块；其中：
    所述服务引擎模块被设置为接收用户提出的目标问题；
    所述服务引擎模块被设置为在基于问题规则判断所述目标问题不需要坐席解答的情况下，基于所述目标问题查询对应的目标答案，或者通过联络中心平台模块基于所述目标问题查询对应的目标答案；
    所述服务引擎模块被设置为在基于所述目标答案判断所述目标问题不需要坐席解答的情况下，将所述目标答案发送至用户端；
    所述坐席模块用于在基于所述目标答案判断所述目标问题需要坐席解答的情况下，获取坐席提供的针对所述目标问题的坐席答案；其中，所述坐席答案或者所述目标答案包括富文本答案和语音答案中的至少一种，以及动作答案；
    所述服务引擎模块被设置为通过所述联络中心平台模块获取所述坐席模块的坐席答案，并将所述坐席答案反馈给用户端。
  11. 一种服务装置，包括：服务模块；其中：
    所述服务模块包括服务屏幕子模块和虚拟服务机器人子模块；其中：
    所述虚拟服务机器人子模块，或者服务屏幕子模块，被设置为获取用户提出的目标问题；
    所述虚拟服务机器人子模块，被设置为将所述目标问题发送至后台端；
    所述虚拟服务机器人子模块，被设置为接收所述后台端反馈的所述目标问题的坐席答案或者目标答案，所述坐席答案或者目标答案，包括富文本答案和语音答案中的至少一种，以及动作答案；
    所述服务屏幕子模块，被设置为将所述富文本答案进行展示；
    所述虚拟服务机器人子模块，被设置为指示虚拟服务机器人将所述语音答案和动作答案进行展现。
  12. 一种服务系统，包括：服务模块、服务引擎模块、坐席模块；其中：
    所述服务模块被设置为获取用户提出的目标问题，将所述目标问题发送至服务引擎模块；
    所述服务引擎模块被设置为在基于问题规则判断所述目标问题不需要坐席解答的情况下，基于所述目标问题查询对应的目标答案，或者通过联络中心平台模块基于所述目标问题查询对应的目标答案，并将所述目标答案发送至用户端；
    所述坐席模块被设置为在基于所述目标答案判断所述目标问题需要坐席解答的情况下，获取坐席提供的针对所述目标问题的坐席答案；
    所述服务引擎模块被设置为通过所述联络中心平台模块获取所述坐席模块的坐席答案，将所述坐席答案反馈给服务模块；
    所述服务模块被设置为接收所述目标答案或者坐席答案，所述目标答案，包括富文本答案和语音答案中的至少一种，以及动作答案，以及将所述富文本答案进行展示，指示虚拟服务机器人将所述语音答案和动作答案进行展现。
  13. 一种设备，包括：
    一个或多个处理器；
    存储器，用于存储一个或多个程序；
    当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如权利要求1-8任一项所述的方法。
  14. 一种存储介质，存储有计算机程序，所述计算机程序被处理器执行时实现权利要求1-8任一项所述的方法。
PCT/CN2020/122755 2019-12-02 2020-10-22 一种服务方法、装置、系统、设备及存储介质 WO2021109741A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201911214770.5A CN112905859A (zh) 2019-12-02 2019-12-02 一种服务方法、装置、系统、设备及存储介质
CN201911214770.5 2019-12-02

Publications (1)

Publication Number Publication Date
WO2021109741A1 true WO2021109741A1 (zh) 2021-06-10

Family

ID=76104225

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/122755 WO2021109741A1 (zh) 2019-12-02 2020-10-22 一种服务方法、装置、系统、设备及存储介质

Country Status (2)

Country Link
CN (1) CN112905859A (zh)
WO (1) WO2021109741A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105207890A (zh) * 2015-08-24 2015-12-30 北京智齿博创科技有限公司 一种在线客服的方法
CN105591882A (zh) * 2015-12-10 2016-05-18 北京中科汇联科技股份有限公司 一种智能机器人与人混合客服的方法及系统
CN105592237A (zh) * 2014-10-24 2016-05-18 中国移动通信集团公司 一种会话切换的方法、装置及智能客服机器人
CN108900726A (zh) * 2018-06-28 2018-11-27 北京首汽智行科技有限公司 基于语音机器人的人工客服转接方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105592237A (zh) * 2014-10-24 2016-05-18 中国移动通信集团公司 一种会话切换的方法、装置及智能客服机器人
CN105207890A (zh) * 2015-08-24 2015-12-30 北京智齿博创科技有限公司 一种在线客服的方法
CN105591882A (zh) * 2015-12-10 2016-05-18 北京中科汇联科技股份有限公司 一种智能机器人与人混合客服的方法及系统
CN108900726A (zh) * 2018-06-28 2018-11-27 北京首汽智行科技有限公司 基于语音机器人的人工客服转接方法

Also Published As

Publication number Publication date
CN112905859A (zh) 2021-06-04

Similar Documents

Publication Publication Date Title
US11956187B2 (en) Natural language processing for information extraction
CN109873909B (zh) 一种语音呼叫方法、装置和设备及计算机存储介质
US9866693B2 (en) System and method for monitoring progress of automated chat conversations
US9912810B2 (en) System and method for chat automation
EP3453160B1 (en) System and method for managing and transitioning automated chat conversations
US10038783B2 (en) System and method for handling interactions with individuals with physical impairments
CN105592237B (zh) 一种会话切换的方法、装置及智能客服机器人
US7606718B2 (en) Apparatus and method for processing service interactions
US10951554B1 (en) Systems and methods facilitating bot communications
US20210157989A1 (en) Systems and methods for dialog management
CN106202301A (zh) 一种基于深度学习的智能应答系统
US11232791B2 (en) Systems and methods for automating voice commands
JP7297797B2 (ja) 保留を管理するための方法および装置
CN114500757A (zh) 语音交互方法、装置、计算机设备及存储介质
CN113724036A (zh) 提供问题咨询服务的方法及电子设备
US10862841B1 (en) Systems and methods for automating voice commands
WO2021109741A1 (zh) 一种服务方法、装置、系统、设备及存储介质
US20220366427A1 (en) Systems and methods relating to artificial intelligence long-tail growth through gig customer service leverage
US11763318B2 (en) Systems and methods relating to providing chat services to customers
WO2022239053A1 (ja) 情報処理装置、情報処理方法および情報処理プログラム
CA3143953A1 (en) Systems and methods for automating voice commands

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20896168

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20896168

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 21/02/2023)

122 Ep: pct application non-entry in european phase

Ref document number: 20896168

Country of ref document: EP

Kind code of ref document: A1