WO2021175007A1 - Online customer service consultation method and apparatus, medium, and electronic device - Google Patents

Online customer service consultation method and apparatus, medium, and electronic device Download PDF

Info

Publication number
WO2021175007A1
WO2021175007A1 PCT/CN2021/070750 CN2021070750W WO2021175007A1 WO 2021175007 A1 WO2021175007 A1 WO 2021175007A1 CN 2021070750 W CN2021070750 W CN 2021070750W WO 2021175007 A1 WO2021175007 A1 WO 2021175007A1
Authority
WO
WIPO (PCT)
Prior art keywords
target user
consultation
robot
manual
channel
Prior art date
Application number
PCT/CN2021/070750
Other languages
French (fr)
Chinese (zh)
Inventor
唐晟
Original Assignee
深圳壹账通智能科技有限公司
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 深圳壹账通智能科技有限公司 filed Critical 深圳壹账通智能科技有限公司
Publication of WO2021175007A1 publication Critical patent/WO2021175007A1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/332—Query formulation
    • G06F16/3329—Natural language query formulation or dialogue systems
    • 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
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0281—Customer communication at a business location, e.g. providing product or service information, consulting

Definitions

  • the present disclosure relates to the technical field of micro-expression recognition, and in particular to an online customer service consulting method, device, medium and electronic equipment.
  • the inventor realizes that if manual customer service is provided to provide consulting services to customers, manual customer service is often unable to provide services to a large number of customers at the same time, and customers may wait in line. Therefore, the service efficiency of manual customer service is low; Although customers provide consulting services, although it can improve service efficiency and reduce operating costs, the current capabilities of customer service robots are not comparable to those of humans. Therefore, customer service robots may not serve customers well, which will reduce the customer's consulting experience. Therefore, the implementation plan of online customer service consultation cannot achieve the balance between customer service efficiency and customer service quality.
  • an online customer service consulting method including:
  • the robot consultation channel is switched to a manual consultation channel to provide manual consultation services for the target user.
  • an online customer service consulting device includes:
  • the channel start module is configured to start a robot consulting channel when receiving a consultation request from a target user, so as to provide a robot consulting service for the target user through a customer service robot;
  • An obtaining module configured to obtain the face image sequence of the target user who is receiving the robot consulting service
  • the micro-expression recognition module is configured to perform micro-expression recognition on the face image sequence of the target user to determine the target user's satisfaction with the robot consulting service;
  • the switching module is configured to switch the robot consultation channel to a manual consultation channel when the satisfaction degree meets a predetermined condition, so as to provide manual consultation services for the target user.
  • a computer-readable storage medium which stores computer program instructions, and when the computer program instructions are executed by a computer, the computer executes the following steps:
  • the robot consultation channel is switched to a manual consultation channel to provide manual consultation services for the target user.
  • an electronic device including:
  • a memory where computer-readable instructions are stored, and when the computer-readable instructions are executed by the processor, the following steps are implemented:
  • the robot consultation channel is switched to a manual consultation channel to provide manual consultation services for the target user.
  • Fig. 1 is a schematic diagram showing a system architecture of an online customer service consulting method according to an exemplary embodiment
  • Fig. 2 is a flow chart showing a method for online customer service consulting according to an exemplary embodiment
  • Fig. 3 is a specific flow chart showing when the online customer service consulting method provided by the present disclosure is applied to the field of wealth management products according to an exemplary embodiment
  • FIG. 4 is a flowchart of steps after step 240 in an embodiment according to the embodiment corresponding to FIG. 2;
  • Fig. 5 is a block diagram showing an online customer service consulting device according to an exemplary embodiment
  • Fig. 6 is a block diagram showing an example of an electronic device implementing the above online customer service consulting method according to an exemplary embodiment
  • Fig. 7 shows a computer-readable storage medium for implementing the online customer service consulting method described above according to an exemplary embodiment.
  • the present disclosure first provides an online customer service consulting method.
  • Online customer service consultation refers to the process in which users communicate with customer service through network media, ask questions to customer service, and request customer service to answer questions based on the problem.
  • the data generated during the communication process is transmitted through network media.
  • the online customer service consulting method provided in the present disclosure can realize the adjustment of the online customer service consulting method based on the satisfaction degree based on micro-expression recognition.
  • the implementation terminal of the present disclosure can be any device with computing and processing functions.
  • the device can be connected to an external device for receiving or sending data.
  • it can be a portable mobile device, such as a smart phone, a tablet computer, a notebook computer, or a PDA ( Personal Digital Assistant), etc., can also be fixed devices, such as computer equipment, field terminals, desktop computers, servers, workstations, etc., or a collection of multiple devices, such as cloud computing physical infrastructure or server clusters.
  • the implementation terminal of the present disclosure may be a server or a physical infrastructure of cloud computing.
  • Fig. 1 is a schematic diagram showing a system architecture of an online customer service consulting method according to an exemplary embodiment.
  • the system architecture includes an execution server 110, a customer service terminal 120, a robot server 130, and a smart phone 140.
  • the smart phone 140 is used by the user
  • the customer service terminal 120 is used by the customer service
  • the smart phone 140, the customer service terminal 120, and the robot server 130 is respectively connected to the server 110 through a communication link, and can be used to receive and send data.
  • the server 110 is an implementation terminal of the present disclosure
  • a customer service robot is fixed on the robot server 130.
  • the user first sends a consultation request to the server 110 through the smart phone 140, and the robot server 130 connects to the smart phone 140 through the server 110 to provide the user with a robot consulting services; in the process of robot consulting services, the server 110 will obtain the user’s facial image, and then perform micro-expression recognition on the facial image, so as to obtain the user’s satisfaction with the robot consulting service; when the server 110 determines that the user is satisfied When the degree reaches a predetermined condition, the robot consulting service can be cut off, the customer service terminal 120 is connected to the smart phone 140, and the customer service using the customer service terminal 120 provides manual consulting services for the user.
  • Fig. 1 is only one embodiment of the present disclosure.
  • the implementing terminal in this embodiment is a server and the user terminal is a smart phone
  • the implementing terminal and user terminal of the present disclosure may be various terminals or devices as described above; although in this embodiment
  • the terminal where the implementation terminal, the user terminal, and the customer service robot of the present disclosure are located are different terminals, but in other embodiments or specific applications, any two of the implementation terminal, the user terminal, and the terminal where the customer service robot is located are either
  • the three terminals can be the same terminal.
  • the present disclosure does not make any limitation on this, and the protection scope of the present disclosure should not be limited in any way.
  • Fig. 2 is a flowchart showing an online customer service consulting method according to an exemplary embodiment.
  • the online customer service consulting method of this embodiment can be executed by a server, as shown in FIG. 2, and includes the following steps:
  • Step 210 When a consultation request from a target user is received, a robot consultation channel is activated to provide a robot consultation service for the target user through a customer service robot.
  • the consultation request may be a user's consultation request for various products and services.
  • the products here can be physical goods, such as computers, mobile phones, etc., or virtual goods, such as wealth management products.
  • the robot consultation channel is the data transmission channel between the target user and the customer service robot, such as HTTP (HyperText Transfer Protocol, Hypertext Transfer Protocol) under the long connection channel.
  • HTTP HyperText Transfer Protocol, Hypertext Transfer Protocol
  • Robot consulting service is a service that provides users with information or feedback information interactively through dialogue. This service generally lasts for a period of time.
  • Robot consulting services can be text-based consulting services (feeding back information to users through text), or voice-based consulting services (feeding back information to users through voice).
  • the customer service robot can be a robot built based on various models or algorithms that can interact with the target user and answer questions that the user consults.
  • customer service robots can be built based on machine learning models such as language models and speech models. For example, they can be BERT (Bidirectional Encoder Representations). from Transformers) model.
  • the method before receiving a consultation request from a target user, before starting a robot consultation channel to provide a robot consultation service for the target user through a customer service robot, the method further includes:
  • the data set used to train the customer service robot can be text data
  • the data set used to train the customer service robot can be a combination of text data and voice data for the consulting service that can provide voice form.
  • the robot consulting service is a text-based consulting service
  • the customer service robot provides robot consulting services to the target user in the following manner:
  • the key information extracted may include "early withdrawal”, “receivable income”, “what does n+1 represent, etc.”
  • Step 220 Obtain the face image sequence of the target user who is receiving the robot consulting service.
  • the customer service robot can run on the terminal of the target user, and can run on the server opposite to the target user.
  • the consultation request of the target user is sent through the client opposite to the server on the user terminal.
  • the terminal where the customer service robot is located, the terminal of the target user, and the implementation terminal of the present disclosure may be the same terminal.
  • this kind of terminal can be a vending machine installed in a public place. It can be connected to the Internet. It has a built-in customer service robot. It also has a camera and recording equipment. The user can directly communicate with the customer service robot inside the terminal through the terminal. Dialogue, you can also have a dialogue with a remote customer service through the network.
  • a face image sequence is a sequence composed of multiple face image information of the target user detected by a terminal or device with a camera or video function. These face image information sequences may not be absolutely continuous in time, but only represent multiple faces There is a sequence of image information in time. For example, it can be multiple face images obtained by continuous photos, or it can be multiple frames of continuous images to form video data.
  • the face image sequence of the target user can be obtained in this way: the target user sends a consultation request to the server running the customer service robot through a user terminal such as a mobile phone or computer with the client installed, that is, the target user’s terminal and the execution terminal of this application are Different terminals, when the customer service robot provides robot consulting services for the target user, the camera of the user terminal is called to obtain the face image sequence of the target user.
  • a user terminal such as a mobile phone or computer with the client installed, that is, the target user’s terminal and the execution terminal of this application are Different terminals
  • the customer service robot provides robot consulting services for the target user
  • the camera of the user terminal is called to obtain the face image sequence of the target user.
  • the face image sequence of the target user can also be obtained in this way: the terminal of the target user and the execution terminal of this application are the same terminal, and the terminal used by the target user is preset with a customer service robot, when the customer service robot provides robot consulting services for the target user At the time, call the camera of the terminal to obtain the face image sequence of the target user.
  • the acquiring the face image sequence of the target user who is receiving the robot consulting service includes:
  • the user Since consultation is a process of interaction between the two parties, the user’s facial expressions may change to the degree of satisfaction with the service only after the consultation information is fed back to the user. That is, under normal circumstances, the user must first ask the question before the robot consultation service is carried out. Corresponding answers, that is, it may be worthless to obtain face images in the time period between when the user asks the question for the first time and the robot consulting service answers. The amount of face image data reduces the computational overhead to a certain extent.
  • the acquiring the face image sequence of the target user who is receiving the robot consulting service includes:
  • the recorded face video of the target user is acquired in the form of a video stream as the face image sequence of the target user.
  • the latest face image of the target user can be quickly obtained, so that the real-time recognition can be improved.
  • the acquiring the face image sequence of the target user who is receiving the robot consulting service includes:
  • the face video of the target user recorded in the predetermined time period is acquired as the face image sequence of the target user.
  • Step 230 Perform micro-expression recognition on the face image sequence of the target user to determine the target user's satisfaction with the robot consulting service.
  • Micro-expression recognition can be realized based on various algorithms, models, and systems.
  • deep neural networks, deep learning algorithms, and reinforcement learning algorithms can be used for micro-expression recognition
  • Ping An’s Gamma intelligent micro-expression system can also be used for recognition.
  • Step 240 When the satisfaction degree meets a predetermined condition, switch the robot consultation channel to a manual consultation channel to provide manual consultation services for the target user.
  • the robot consulting service and the manual consulting service are both consulting services in text form.
  • the robot consulting service is a text-based consulting service
  • the manual consulting service is a voice-based consulting service
  • the robot consulting service and the manual consulting service are both in the form of voice consulting services.
  • the predetermined condition is to switch the robot consultation channel to the manual consultation channel, so as to realize the process of providing manual consultation services to the target users by the manual consultation channel.
  • the predetermined condition may indicate that the target user's satisfaction with the robot consulting service is low or lower than a certain threshold.
  • switching the robot consultation channel to a manual consultation channel to provide manual consultation services for the target user includes:
  • the consultation request whose request time is closest to the current time is fed back to the customer service, so that the customer service can grasp the questions of the target user in time and answer the corresponding questions. Smooth switching between robot consultation channel and manual consultation channel.
  • the performing micro-expression recognition on the face image sequence of the target user to determine the target user's satisfaction with the robot consulting service includes:
  • micro-expression recognition model to determine the satisfaction degree of each micro-expression segment as the target user's satisfaction with the robot consulting service during the time period where the corresponding micro-expression segment is located;
  • switching the robot consulting channel to a manual consulting channel to provide manual consulting services for the target user includes:
  • the robot consultation channel is switched to the manual consultation channel, and the robot consultation channel is switched to the manual consultation channel.
  • Target users provide manual consulting services.
  • the micro-expression recognition model can be established based on the aforementioned various algorithms or neural networks. Usually, the face image data is first used for model training before the model is used.
  • the performing micro-expression recognition on the face image sequence of the target user to determine the target user's satisfaction with the robot consulting service includes:
  • micro-expression recognition model to determine the satisfaction degree of each micro-expression segment as the target user's satisfaction with the robot consulting service during the time period where the corresponding micro-expression segment is located;
  • switching the robot consulting channel to a manual consulting channel to provide manual consulting services for the target user includes:
  • the robot consultation channel is switched to a manual consultation channel to provide manual consultation services for the target user.
  • the average value of satisfaction reflects the concentration of the user’s satisfaction with the robot consulting service during the time period composed of the micro-expression fragments.
  • the average value of the satisfaction degree and the corresponding threshold value To determine the time when the robot consulting channel is switched to the manual consulting channel, while using the robot consulting service to improve the consulting efficiency, the selected time to switch the robot consulting channel to the manual consulting channel is more reasonable.
  • the manual consulting method is Users provide more professional consulting services to ensure user experience.
  • the performing micro-expression recognition on the face image sequence of the target user to determine the target user's satisfaction with the robot consulting service includes:
  • micro-expression recognition model to determine the satisfaction degree of the micro-expression fragment corresponding to the time period closest to the current time as the target user's satisfaction with the robot consulting service
  • switching the robot consulting channel to a manual consulting channel to provide manual consulting services for the target user includes:
  • the robot consultation channel is switched to a manual consultation channel to provide manual consultation services for the target user.
  • the micro-expression segment corresponding to the time period closest to the current time reflects the latest micro-expression state of the target user, in this embodiment, according to the satisfaction of the micro-expression segment corresponding to the time period closest to the current time and the corresponding threshold To determine when to switch the robot consulting channel to the manual consulting channel, so that the target user’s latest satisfaction with the robot consulting service can be transmitted to whether to switch the robot consulting channel to the manual consulting channel, taking into account the consulting efficiency and user experience.
  • the customer service robot and manual customer service are simultaneously used to provide users with consulting services.
  • the use of manual customer service to provide users with consulting services is providing users with robots.
  • the user's satisfaction with the robot consulting service meets the predetermined conditions. Therefore, both the customer service efficiency and the customer service quality are taken into consideration.
  • the service efficiency is improved and the number of users is reduced.
  • the waiting time ensures the user experience and reduces the operating cost by reducing the number of manual customer services; on the other hand, after the user is identified with micro-expressions, it is determined that the user’s satisfaction with the robot consulting service meets the predetermined conditions, pass Providing users with manual consulting services, compared with simply using customer service robots, ensures the quality of service and avoids the poor user experience caused by robot consulting services and the loss of high-quality customers.
  • Fig. 3 is a specific flow chart when the online customer service consulting method provided by the present disclosure is applied to the field of wealth management products according to an exemplary embodiment.
  • the customer service robot appears in the form of an AI (Artificial Intelligence) assistant.
  • AI Artificial Intelligence
  • the specific process of the online customer service consultation can be as follows: Training, when a new wealth management product is to be sold, the user clicks on the wealth management product page through his own terminal to conduct online consultation.
  • the AI assistant first answers the question and obtains the user’s face image during the consultation process for real-time micro-expression recognition.
  • the AI assistant When it is found that the customer is still satisfied through the micro-expression recognition, the AI assistant will continue to answer the user's questions, and when the micro-expression recognition is found to be no longer satisfactory, the manual customer service will be connected, and the manual customer service will answer the user's questions.
  • FIG. 4 is a flowchart of steps after step 240 in an embodiment shown according to the embodiment corresponding to FIG. 2. As shown in Figure 4, it includes the following steps:
  • Step 250 Mark the target user as a manual service priority user.
  • the mark of "Manual Service Priority User" is an identification of the target user.
  • the target user can initiate a consultation request. Generally speaking, it has an account or identification. After the target user is marked, the mark can be combined with the user itself.
  • the account or ID of the account is stored in the database together for query.
  • Step 260 When the target user's consulting request is received again after the manual consulting service ends, a manual consulting channel is activated according to the target user's manual service priority user mark to provide the target user with a manual consulting service.
  • the consultation request is a purchase consultation request for a product
  • the method further includes:
  • the mark of the target user is cleared.
  • the information on the purchase consultation request page and the product purchase transaction information can be maintained by the server opposite to the user's client. If the server is the implementation terminal of the disclosure, then the server can learn which products the target user has completed Purchase transactions, and it is possible to know which of these products are targeted by the purchase consultation request of the target user, so that the server can know whether the target user has completed the purchase transaction of the product corresponding to the consultation request.
  • the target user purchases the product, there is no need to continue to invest the resources of manual customer service on the target user.
  • the target user’s mark is cleared, which saves Resources for human customer service.
  • the present disclosure also provides an online customer service consulting device.
  • the following are device embodiments of the present disclosure.
  • Fig. 5 is a block diagram showing an online customer service consulting device according to an exemplary embodiment. As shown in FIG. 5, the device 500 includes:
  • the channel activation module 510 is configured to activate a robot consulting channel when receiving a consultation request from a target user, so as to provide a robot consulting service for the target user through a customer service robot;
  • the obtaining module 520 is configured to obtain the face image sequence of the target user who is receiving the robot consulting service;
  • the micro-expression recognition module 530 is configured to perform micro-expression recognition on the face image sequence of the target user to determine the target user's satisfaction with the robot consulting service;
  • the switching module 540 is configured to switch the robot consultation channel to a manual consultation channel when the satisfaction degree meets a predetermined condition, so as to provide a manual consultation service for the target user.
  • an electronic device capable of implementing the above method.
  • the electronic device 600 according to this embodiment of the present application will be described below with reference to FIG. 6.
  • the electronic device 600 shown in FIG. 6 is only an example, and should not bring any limitation to the function and scope of use of the embodiments of the present application.
  • the electronic device 600 is represented in the form of a general-purpose computing device.
  • the components of the electronic device 600 may include, but are not limited to: the aforementioned at least one processing unit 610, the aforementioned at least one storage unit 620, and a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610).
  • the storage unit stores program code, and the program code can be executed by the processing unit 610, so that the processing unit 610 executes the various exemplary methods described in the "Methods of Embodiments" section of this specification. Steps of implementation.
  • the storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 621 and/or a cache storage unit 622, and may further include a read-only storage unit (ROM) 623.
  • RAM random access storage unit
  • ROM read-only storage unit
  • the storage unit 620 may also include a program/utility tool 624 having a set of (at least one) program module 625.
  • program module 625 includes but is not limited to: an operating system, one or more application programs, other program modules, and program data, Each of these examples or some combination may include the implementation of a network environment.
  • the bus 630 may represent one or more of several types of bus structures, including a storage unit bus or a storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local area using any bus structure among multiple bus structures. bus.
  • the electronic device 600 may also communicate with one or more external devices 800 (such as keyboards, pointing devices, Bluetooth devices, etc.), and may also communicate with one or more devices that enable a user to interact with the electronic device 600, and/or communicate with Any device (such as a router, modem, etc.) that enables the electronic device 600 to communicate with one or more other computing devices. This communication can be performed through an input/output (I/O) interface 650.
  • the electronic device 600 may also communicate with one or more networks (for example, a local area network (LAN), a wide area network (WAN), and/or a public network, such as the Internet) through the network adapter 660.
  • networks for example, a local area network (LAN), a wide area network (WAN), and/or a public network, such as the Internet
  • the network adapter 660 communicates with other modules of the electronic device 600 through the bus 630. It should be understood that although not shown in the figure, other hardware and/or software modules can be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives And data backup storage system, etc.
  • the example embodiments described here can be implemented by software, or can be implemented by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, U disk, mobile hard disk, etc.) or on the network , Including several instructions to make a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) execute the method according to the embodiments of the present disclosure.
  • a computing device which may be a personal computer, a server, a terminal device, or a network device, etc.
  • a computer-readable storage medium may be volatile or non-volatile.
  • Program product In some possible implementation manners, each aspect of the present application can also be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to make the The terminal device executes the steps according to various exemplary embodiments of the present application described in the above-mentioned "Exemplary Method" section of this specification.
  • a program product 700 for implementing the above method according to an embodiment of the present application is described. It can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be stored in a terminal device, For example, running on a personal computer.
  • CD-ROM compact disk read-only memory
  • the program product of this application is not limited to this.
  • the readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, device, or device.
  • the program product can use any combination of one or more readable media.
  • the readable medium may be a readable signal medium or a readable storage medium.
  • the readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or a combination of any of the above. More specific examples (non-exhaustive list) of readable storage media include: electrical connections with one or more wires, portable disks, hard disks, random access memory (RAM), read only memory (ROM), erasable Type programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • the computer-readable signal medium may include a data signal propagated in baseband or as a part of a carrier wave, and readable program code is carried therein. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • the readable signal medium may also be any readable medium other than a readable storage medium, and the readable medium may send, propagate, or transmit a program for use by or in combination with the instruction execution system, apparatus, or device.
  • the program code contained on the readable medium can be transmitted by any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.
  • the program code used to perform the operations of the present application can be written in any combination of one or more programming languages.
  • the programming languages include object-oriented programming languages—such as Java, C++, etc., as well as conventional procedural programming languages. Programming language-such as "C" language or similar programming language.
  • the program code can be executed entirely on the user's computing device, partly on the user's device, executed as an independent software package, partly on the user's computing device and partly executed on the remote computing device, or entirely on the remote computing device or server Executed on.
  • the remote computing device can be connected to a user computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (for example, using Internet service providers). Business to connect via the Internet).
  • LAN local area network
  • WAN wide area network
  • Internet service providers for example, using Internet service providers.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Accounting & Taxation (AREA)
  • Mathematical Physics (AREA)
  • General Physics & Mathematics (AREA)
  • Game Theory and Decision Science (AREA)
  • Human Computer Interaction (AREA)
  • Databases & Information Systems (AREA)
  • Computational Linguistics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Manipulator (AREA)

Abstract

Provided are an online customer service consultation method and apparatus, a medium, and an electronic device, which relate to the field of micro-expression recognition. The method comprises: when a consultation request of a target user is received, starting a robot consultation channel, so as to provide a robot consultation service for the target user by means of a customer service robot (210); acquiring a facial image sequence of the target user who is receiving the robot consultation service (220); performing micro-expression recognition on the facial image sequence of the target user to determine the degree of satisfaction of the target user with the robot consultation service (230); and when the degree of satisfaction meets a predetermined condition, switching the robot consultation channel to a manual consultation channel to provide a manual consultation service for the target user (240). According to the method, switching between the robot consultation service and the manual consultation service is performed on the basis of the degree of satisfaction of the user with the robot consultation service, thereby taking both the customer service efficiency and the service quality into consideration.

Description

在线客服咨询方法、装置、介质及电子设备Online customer service consulting method, device, medium and electronic equipment
本申请要求于2020年3月2日提交中国专利局、申请号为CN202010136161.9、名称为“在线客服咨询方法、装置、介质及电子设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。This application claims the priority of a Chinese patent application filed with the Chinese Patent Office, the application number is CN202010136161.9, and the title is "online customer service consulting methods, devices, media and electronic equipment" on March 2, 2020, the entire content of which is incorporated by reference Incorporated in this application.
技术领域Technical field
本公开涉及微表情识别技术领域，特别涉及一种在线客服咨询方法、装置、介质及电子设备。The present disclosure relates to the technical field of micro-expression recognition, and in particular to an online customer service consulting method, device, medium and electronic equipment.
背景技术Background technique
随着互联网特别是移动互联网时代的到来，在线购买商品、选购服务已经在人们的日常生活中越来越常见。在线购买商品、服务时，为了为客户提供更好的服务体验，一般要通过设置机器人或人工客服为客户提供咨询服务，解答客户疑问。With the advent of the Internet, especially the mobile Internet era, online purchasing of goods and services has become more and more common in people's daily lives. When purchasing goods and services online, in order to provide customers with a better service experience, it is generally necessary to set up robots or manual customer service to provide customers with consulting services and answer customer questions.
技术问题technical problem
发明人意识到若通过设置人工客服来为客户提供咨询服务，人工客服常常无法同时为大量客户提供服务，可能出现客户排队等候的情况，因此，人工客服的服务效率低下；若通过设置机器人来为客户提供咨询服务，虽然可以提高服务效率、降低运营成本，但目前客服机器人的能力尚无法与人工媲美，因此客服机器人可能不能很好地服务好客户，这会降低客户的咨询体验。因此，在线客服咨询的实现方案无法实现客服服务效率与客服服务质量的兼顾。The inventor realizes that if manual customer service is provided to provide consulting services to customers, manual customer service is often unable to provide services to a large number of customers at the same time, and customers may wait in line. Therefore, the service efficiency of manual customer service is low; Although customers provide consulting services, although it can improve service efficiency and reduce operating costs, the current capabilities of customer service robots are not comparable to those of humans. Therefore, customer service robots may not serve customers well, which will reduce the customer's consulting experience. Therefore, the implementation plan of online customer service consultation cannot achieve the balance between customer service efficiency and customer service quality.
技术解决方案Technical solutions
根据本公开的一方面，提供了一种在线客服咨询方法，所述方法包括：According to an aspect of the present disclosure, there is provided an online customer service consulting method, the method including:
当接收到目标用户的咨询请求，启动机器人咨询通道，以通过客服机器人为所述目标用户提供机器人咨询服务；When receiving a consultation request from a target user, start a robot consultation channel to provide robot consultation services for the target user through a customer service robot;
获取正在接受所述机器人咨询服务的所述目标用户的人脸图像序列；Acquiring the face image sequence of the target user who is receiving the robot consulting service;
对所述目标用户的人脸图像序列进行微表情识别，以确定所述目标用户对所述机器人咨询服务的满意度；Performing micro-expression recognition on the face image sequence of the target user to determine the target user's satisfaction with the robot consulting service;
当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务。When the satisfaction degree satisfies a predetermined condition, the robot consultation channel is switched to a manual consultation channel to provide manual consultation services for the target user.
根据本公开的另一方面，提供了在线客服咨询装置，所述装置包括：According to another aspect of the present disclosure, an online customer service consulting device is provided, and the device includes:
通道启动模块，被配置为当接收到目标用户的咨询请求，启动机器人咨询通道，以通过客服机器人为所述目标用户提供机器人咨询服务；The channel start module is configured to start a robot consulting channel when receiving a consultation request from a target user, so as to provide a robot consulting service for the target user through a customer service robot;
获取模块，被配置为获取正在接受所述机器人咨询服务的所述目标用户的人脸图像序列；An obtaining module configured to obtain the face image sequence of the target user who is receiving the robot consulting service;
微表情识别模块，被配置为对所述目标用户的人脸图像序列进行微表情识别，以确定所述目标用户对所述机器人咨询服务的满意度；The micro-expression recognition module is configured to perform micro-expression recognition on the face image sequence of the target user to determine the target user's satisfaction with the robot consulting service;
切换模块，被配置为当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务。The switching module is configured to switch the robot consultation channel to a manual consultation channel when the satisfaction degree meets a predetermined condition, so as to provide manual consultation services for the target user.
根据本公开的另一方面，提供了一种计算机可读存储介质，其存储有计算机程序指令，当所述计算机程序指令被计算机执行时，使计算机执行如下步骤：According to another aspect of the present disclosure, a computer-readable storage medium is provided, which stores computer program instructions, and when the computer program instructions are executed by a computer, the computer executes the following steps:
当接收到目标用户的咨询请求，启动机器人咨询通道，以通过客服机器人为所述目标用户提供机器人咨询服务；When receiving a consultation request from a target user, start a robot consultation channel to provide robot consultation services for the target user through a customer service robot;
获取正在接受所述机器人咨询服务的所述目标用户的人脸图像序列；Acquiring the face image sequence of the target user who is receiving the robot consulting service;
对所述目标用户的人脸图像序列进行微表情识别，以确定所述目标用户对所述机器人咨询服务的满意度；Performing micro-expression recognition on the face image sequence of the target user to determine the target user's satisfaction with the robot consulting service;
当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务。When the satisfaction degree satisfies a predetermined condition, the robot consultation channel is switched to a manual consultation channel to provide manual consultation services for the target user.
根据本公开的另一方面，提供了一种电子设备，所述电子设备包括：According to another aspect of the present disclosure, there is provided an electronic device including:
处理器；processor;
存储器，所述存储器上存储有计算机可读指令，所述计算机可读指令被所述处理器执行时，实现如下步骤：A memory, where computer-readable instructions are stored, and when the computer-readable instructions are executed by the processor, the following steps are implemented:
当接收到目标用户的咨询请求，启动机器人咨询通道，以通过客服机器人为所述目标用户提供机器人咨询服务；When receiving a consultation request from a target user, start a robot consultation channel to provide robot consultation services for the target user through a customer service robot;
获取正在接受所述机器人咨询服务的所述目标用户的人脸图像序列；Acquiring the face image sequence of the target user who is receiving the robot consulting service;
对所述目标用户的人脸图像序列进行微表情识别，以确定所述目标用户对所述机器人咨询服务的满意度；Performing micro-expression recognition on the face image sequence of the target user to determine the target user's satisfaction with the robot consulting service;
当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务。When the satisfaction degree satisfies a predetermined condition, the robot consultation channel is switched to a manual consultation channel to provide manual consultation services for the target user.
此方法下，一方面，通过在接收到用户的咨询请求时，先用客服机器人为用户提供咨询服务，由于机器人可以服务大量用户，与单纯使用人工客服相比，提高了服务效率，减少了用户等待时间，保证了用户体验，也通过减少人工客服的数量降低了运营成本；另一方面，在对用户进行微表情识别后，判断用户对所述机器人咨询服务的满意度满足预定条件时，通过为用户提供人工咨询服务，与单纯使用客服机器人相比，保证了服务质量，避免了机器人咨询服务导致用户体验差从而导致优质客户流失。Under this method, on the one hand, by first using a customer service robot to provide consulting services to users when receiving a user’s consultation request, since the robot can serve a large number of users, compared with purely using manual customer service, the service efficiency is improved and the number of users is reduced. The waiting time ensures the user experience and reduces the operating cost by reducing the number of manual customer service. On the other hand, after the user is identified with micro-expressions, it is determined that the user’s satisfaction with the robot consulting service meets the predetermined conditions, Providing users with manual consulting services, compared with simply using customer service robots, guarantees the quality of service and avoids the poor user experience caused by robot consulting services and the loss of high-quality customers.
附图说明Description of the drawings
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本申请的实施例，并与说明书一起用于解释本申请的原理。The drawings herein are incorporated into the specification and constitute a part of the specification, show embodiments that conform to the application, and are used together with the specification to explain the principle of the application.
图1是根据一示例性实施例示出的一种在线客服咨询方法的***架构示意图；Fig. 1 is a schematic diagram showing a system architecture of an online customer service consulting method according to an exemplary embodiment;
图2是根据一示例性实施例示出的一种在线客服咨询方法的流程图；Fig. 2 is a flow chart showing a method for online customer service consulting according to an exemplary embodiment;
图3是根据一示例性实施例示出的本公开提供在线客服咨询方法应用于理财产品领域时的具体流程图；Fig. 3 is a specific flow chart showing when the online customer service consulting method provided by the present disclosure is applied to the field of wealth management products according to an exemplary embodiment;
图4是根据图2对应实施例示出的一实施例的步骤240之后步骤的流程图；FIG. 4 is a flowchart of steps after step 240 in an embodiment according to the embodiment corresponding to FIG. 2;
图5是根据一示例性实施例示出的一种在线客服咨询装置的框图；Fig. 5 is a block diagram showing an online customer service consulting device according to an exemplary embodiment;
图6是根据一示例性实施例示出的一种实现上述在线客服咨询方法的电子设备示例框图；Fig. 6 is a block diagram showing an example of an electronic device implementing the above online customer service consulting method according to an exemplary embodiment;
图7是根据一示例性实施例示出的一种实现上述在线客服咨询方法的计算机可读存储介质。Fig. 7 shows a computer-readable storage medium for implementing the online customer service consulting method described above according to an exemplary embodiment.
本发明的实施方式Embodiments of the present invention
这里将详细地对示例性实施例进行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本申请相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本申请的一些方面相一致的装置和方法的例子。The exemplary embodiments will be described in detail here, and examples thereof are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the application as detailed in the appended claims.
此外，附图仅为本公开的示意性图解，并非一定是按比例绘制。图中相同的附图标记表示相同或类似的部分，因而将省略对它们的重复描述。附图中所示的一些方框图是功能实体，不一定必须与物理或逻辑上独立的实体相对应。In addition, the drawings are only schematic illustrations of the present disclosure, and are not necessarily drawn to scale. The same reference numerals in the figures denote the same or similar parts, and thus their repeated description will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities.
本公开首先提供了一种在线客服咨询方法。在线客服咨询是指用户通过网络媒介与客服进行沟通，向客服提出问题，请求客服基于问题做出解答的过程，沟通过程中产生的数据通过网络媒介传输。本公开提供的在线客服咨询方法可以实现根据基于微表情识别的满意度进行在线客服咨询方式的调整。The present disclosure first provides an online customer service consulting method. Online customer service consultation refers to the process in which users communicate with customer service through network media, ask questions to customer service, and request customer service to answer questions based on the problem. The data generated during the communication process is transmitted through network media. The online customer service consulting method provided in the present disclosure can realize the adjustment of the online customer service consulting method based on the satisfaction degree based on micro-expression recognition.
本公开的实施终端可以是任何具有运算和处理功能的设备，该设备可以与外部设备相连，用于接收或者发送数据，具体可以是便携移动设备，例如智能手机、平板电脑、笔记本电脑、PDA（Personal Digital Assistant）等，也可以是固定式设备，例如，计算机设备、现场终端、台式电脑、服务器、工作站等，还可以是多个设备的集合，比如云计算的物理基础设施或者服务器集群。The implementation terminal of the present disclosure can be any device with computing and processing functions. The device can be connected to an external device for receiving or sending data. Specifically, it can be a portable mobile device, such as a smart phone, a tablet computer, a notebook computer, or a PDA ( Personal Digital Assistant), etc., can also be fixed devices, such as computer equipment, field terminals, desktop computers, servers, workstations, etc., or a collection of multiple devices, such as cloud computing physical infrastructure or server clusters.
可选地，本公开的实施终端可以为服务器或者云计算的物理基础设施。Optionally, the implementation terminal of the present disclosure may be a server or a physical infrastructure of cloud computing.
图1是根据一示例性实施例示出的一种在线客服咨询方法的***架构示意图。如图1所示，该***架构包括执行服务器110、客服终端120、机器人服务器130及智能手机140，智能手机140由用户使用，客服终端120由客服使用，智能手机140、客服终端120及机器人服务器130分别通过通信链路与服务器110相连，可用于接收和发送数据。在本实施例中，服务器110为本公开的实施终端，机器人服务器130上固设有客服机器人。当本公开提供的在线客服咨询方法应用于图1所示的***架构中时，用户首先通过智能手机140向服务器110发送咨询请求，机器人服务器130通过服务器110接通智能手机140，为用户提供机器人咨询服务；在进行机器人咨询服务的过程中，服务器110会获取用户的人脸图像，然后对人脸图像进行微表情识别，从而得到该用户对机器人咨询服务的满意度；当服务器110判断该满意度达到预定条件时，就可以切断机器人咨询服务，将客服终端120与智能手机140接通，由使用客服终端120的客服为该用户提供人工咨询服务。Fig. 1 is a schematic diagram showing a system architecture of an online customer service consulting method according to an exemplary embodiment. As shown in Figure 1, the system architecture includes an execution server 110, a customer service terminal 120, a robot server 130, and a smart phone 140. The smart phone 140 is used by the user, the customer service terminal 120 is used by the customer service, and the smart phone 140, the customer service terminal 120, and the robot server 130 is respectively connected to the server 110 through a communication link, and can be used to receive and send data. In this embodiment, the server 110 is an implementation terminal of the present disclosure, and a customer service robot is fixed on the robot server 130. When the online customer service consultation method provided by the present disclosure is applied to the system architecture shown in FIG. 1, the user first sends a consultation request to the server 110 through the smart phone 140, and the robot server 130 connects to the smart phone 140 through the server 110 to provide the user with a robot Consulting services; in the process of robot consulting services, the server 110 will obtain the user’s facial image, and then perform micro-expression recognition on the facial image, so as to obtain the user’s satisfaction with the robot consulting service; when the server 110 determines that the user is satisfied When the degree reaches a predetermined condition, the robot consulting service can be cut off, the customer service terminal 120 is connected to the smart phone 140, and the customer service using the customer service terminal 120 provides manual consulting services for the user.
需要指出的是，图1仅为本公开的一个实施例。虽然在本实施例中的实施终端为服务器、用户终端为智能手机，但在其他实施例中，本公开的实施终端和用户终端可以为如前所述的各种终端或设备；虽然在本实施例中，本公开的实施终端、用户终端及客服机器人所在终端为不同的终端，但在其他实施例或者具体应用中，本公开的实施终端、用户终端及客服机器人所在终端中的任意两个或者三个终端可以为同一终端。本公开对此不作任何限定，本公开的保护范围也不应因此而受到任何限制。It should be pointed out that Fig. 1 is only one embodiment of the present disclosure. Although the implementing terminal in this embodiment is a server and the user terminal is a smart phone, in other embodiments, the implementing terminal and user terminal of the present disclosure may be various terminals or devices as described above; although in this embodiment In the example, the terminal where the implementation terminal, the user terminal, and the customer service robot of the present disclosure are located are different terminals, but in other embodiments or specific applications, any two of the implementation terminal, the user terminal, and the terminal where the customer service robot is located are either The three terminals can be the same terminal. The present disclosure does not make any limitation on this, and the protection scope of the present disclosure should not be limited in any way.
图2是根据一示例性实施例示出的一种在线客服咨询方法的流程图。本实施例的在线客服咨询方法可以由服务器执行，如图2所示，包括以下步骤：Fig. 2 is a flowchart showing an online customer service consulting method according to an exemplary embodiment. The online customer service consulting method of this embodiment can be executed by a server, as shown in FIG. 2, and includes the following steps:
步骤210，当接收到目标用户的咨询请求，启动机器人咨询通道，以通过客服机器人为所述目标用户提供机器人咨询服务。Step 210: When a consultation request from a target user is received, a robot consultation channel is activated to provide a robot consultation service for the target user through a customer service robot.
咨询请求可以是用户对各种产品、服务的咨询请求。这里的产品可以是实物商品，比如电脑、手机等，也可以是虚拟商品，比如理财产品等。The consultation request may be a user's consultation request for various products and services. The products here can be physical goods, such as computers, mobile phones, etc., or virtual goods, such as wealth management products.
机器人咨询通道即目标用户与客服机器人之间的数据传输通道，比如可以是HTTP（HyperText Transfer Protocol,超文本传输协议）下的长连接通道。The robot consultation channel is the data transmission channel between the target user and the customer service robot, such as HTTP (HyperText Transfer Protocol, Hypertext Transfer Protocol) under the long connection channel.
机器人咨询服务为通过对话的方式交互的为用户提供信息或反馈信息的服务，这个服务一般会持续一段时间。Robot consulting service is a service that provides users with information or feedback information interactively through dialogue. This service generally lasts for a period of time.
机器人咨询服务可以是文本形式的咨询服务（通过文字的方式向用户反馈信息），也可以是语音形式的咨询服务（通过语音的方式向用户反馈信息）。Robot consulting services can be text-based consulting services (feeding back information to users through text), or voice-based consulting services (feeding back information to users through voice).
客服机器人可以是基于各种模型或算法建立的能够与目标用户进行互动，并回答用户咨询的问题的机器人。比如客服机器人可以基于语言模型、语音模型等机器学习模型建立，例如可以是BERT (Bidirectional Encoder Representations from Transformers)模型。The customer service robot can be a robot built based on various models or algorithms that can interact with the target user and answer questions that the user consults. For example, customer service robots can be built based on machine learning models such as language models and speech models. For example, they can be BERT (Bidirectional Encoder Representations). from Transformers) model.
在一个实施例中，在当接收到目标用户的咨询请求，启动机器人咨询通道，以通过客服机器人为所述目标用户提供机器人咨询服务之前，所述方法还包括：In an embodiment, before receiving a consultation request from a target user, before starting a robot consultation channel to provide a robot consultation service for the target user through a customer service robot, the method further includes:
获取预设的数据集，对客服机器人进行训练。Obtain the preset data set and train the customer service robot.
对于可以提供文本形式的咨询服务，用来训练客服机器人的数据集可以为文本数据，对于可以提供语音形式的咨询服务，用来训练客服机器人的数据集可以为文本数据和语音数据的结合。For the consulting service that can provide text form, the data set used to train the customer service robot can be text data, and the data set used to train the customer service robot can be a combination of text data and voice data for the consulting service that can provide voice form.
在一个实施例中，所述机器人咨询服务为文本形式的咨询服务，所述客服机器人通过如下方式为所述目标用户提供机器人咨询服务：In one embodiment, the robot consulting service is a text-based consulting service, and the customer service robot provides robot consulting services to the target user in the following manner:
获取所述目标用户提交的文本信息；Acquiring the text information submitted by the target user;
提取所述文本信息中的关键信息；Extract key information in the text information;
从预设的数据库中查询与所述关键信息匹配的答案信息，并将所述答案信息发送给所述目标用户。Query answer information matching the key information from a preset database, and send the answer information to the target user.
当目标用户的咨询请求为针对理财产品的咨询请求时，提取的关键信息可以包括“提前支取”、“可获收益”、“n+1代表什么等”。When the consultation request of the target user is a consultation request for a wealth management product, the key information extracted may include "early withdrawal", "receivable income", "what does n+1 represent, etc.".
步骤220，获取正在接受所述机器人咨询服务的所述目标用户的人脸图像序列。Step 220: Obtain the face image sequence of the target user who is receiving the robot consulting service.
客服机器人可以运行于目标用户的终端，可以运行于与目标用户相对的服务端。当客服机器人运行于与目标用户相对的服务端时，目标用户的咨询请求通过用户终端上与服务端相对的客户端发送。当客服机器人运行于目标用户的终端时，客服机器人所在终端、目标用户的终端及本公开的实施终端可以为同一终端。比如，这种终端可以是设置于公共场所的自动售卖机，它可以连接网络，内部固设有客服机器人，它还设有摄像头和录音设备，用户可以通过该终端与终端内部的客服机器人直接进行对话，还可以通过网络与远程的客服进行对话。The customer service robot can run on the terminal of the target user, and can run on the server opposite to the target user. When the customer service robot runs on the server opposite to the target user, the consultation request of the target user is sent through the client opposite to the server on the user terminal. When the customer service robot runs on the terminal of the target user, the terminal where the customer service robot is located, the terminal of the target user, and the implementation terminal of the present disclosure may be the same terminal. For example, this kind of terminal can be a vending machine installed in a public place. It can be connected to the Internet. It has a built-in customer service robot. It also has a camera and recording equipment. The user can directly communicate with the customer service robot inside the terminal through the terminal. Dialogue, you can also have a dialogue with a remote customer service through the network.
人脸图像序列即具有拍照或录像功能的终端或设备侦测得到的目标用户的多个人脸图像信息组成的序列，这些人脸图像信息的序列不一定在时间上绝对连续，仅表示多个人脸图像信息在时间上存在先后顺序。比如可以是连续拍照得到的多张人脸图像，也可以是连续多帧图像组成视频数据。A face image sequence is a sequence composed of multiple face image information of the target user detected by a terminal or device with a camera or video function. These face image information sequences may not be absolutely continuous in time, but only represent multiple faces There is a sequence of image information in time. For example, it can be multiple face images obtained by continuous photos, or it can be multiple frames of continuous images to form video data.
可以通过这样的方式获取目标用户的人脸图像序列：目标用户通过安装了客户端的手机、电脑等用户终端向运行客服机器人的服务端发送咨询请求，即目标用户的终端与本申请的执行终端为不同的终端，当客服机器人为目标用户提供机器人咨询服务时，调用用户终端的摄像头，来获取目标用户的人脸图像序列。The face image sequence of the target user can be obtained in this way: the target user sends a consultation request to the server running the customer service robot through a user terminal such as a mobile phone or computer with the client installed, that is, the target user’s terminal and the execution terminal of this application are Different terminals, when the customer service robot provides robot consulting services for the target user, the camera of the user terminal is called to obtain the face image sequence of the target user.
还可以通过这样的方式获取目标用户的人脸图像序列：目标用户的终端与本申请的执行终端为同一终端，目标用户使用的终端预置有客服机器人，当客服机器人为目标用户提供机器人咨询服务时，调用本终端的摄像头来获取目标用户的人脸图像序列。The face image sequence of the target user can also be obtained in this way: the terminal of the target user and the execution terminal of this application are the same terminal, and the terminal used by the target user is preset with a customer service robot, when the customer service robot provides robot consulting services for the target user At the time, call the camera of the terminal to obtain the face image sequence of the target user.
在一个实施例中，所述获取正在接受所述机器人咨询服务的所述目标用户的人脸图像序列，包括：In an embodiment, the acquiring the face image sequence of the target user who is receiving the robot consulting service includes:
响应所述目标用户的咨询请求并在向所述目标用户首次反馈咨询信息时，开始获取所述目标用户的人脸图像序列。Responding to the consultation request of the target user and starting to obtain the face image sequence of the target user when the target user is fed back with the consultation information for the first time.
由于咨询是双方互动的过程，只有在向用户反馈了咨询信息后，用户的人脸表情才可能有对服务满意程度的变化，即，一般情况下，首先要用户提出问题，机器人咨询服务才进行相应解答，即在用户首次提出问题与机器人咨询服务进行解答之间的时间段获取人脸图像可能是没有价值的，本实施例通过在更合理的时刻获取人脸图像序列，减少了获取的人脸图像的数据量，在一定程度上降低了计算开销。Since consultation is a process of interaction between the two parties, the user’s facial expressions may change to the degree of satisfaction with the service only after the consultation information is fed back to the user. That is, under normal circumstances, the user must first ask the question before the robot consultation service is carried out. Corresponding answers, that is, it may be worthless to obtain face images in the time period between when the user asks the question for the first time and the robot consulting service answers. The amount of face image data reduces the computational overhead to a certain extent.
在一个实施例中，所述获取正在接受所述机器人咨询服务的所述目标用户的人脸图像序列，包括：In an embodiment, the acquiring the face image sequence of the target user who is receiving the robot consulting service includes:
以视频流的方式获取录制的所述目标用户的人脸视频，作为所述目标用户的人脸图像序列。The recorded face video of the target user is acquired in the form of a video stream as the face image sequence of the target user.
通过视频流可以快速获取目标用户最新的人脸图像，从而可以提高识别的实时性。Through the video stream, the latest face image of the target user can be quickly obtained, so that the real-time recognition can be improved.
在一个实施例中，所述获取正在接受所述机器人咨询服务的所述目标用户的人脸图像序列，包括：In an embodiment, the acquiring the face image sequence of the target user who is receiving the robot consulting service includes:
每隔预定时间段，获取在该预定时间段内录制的所述目标用户的人脸视频，作为所述目标用户的人脸图像序列。Every predetermined time period, the face video of the target user recorded in the predetermined time period is acquired as the face image sequence of the target user.
步骤230，对所述目标用户的人脸图像序列进行微表情识别，以确定所述目标用户对所述机器人咨询服务的满意度。Step 230: Perform micro-expression recognition on the face image sequence of the target user to determine the target user's satisfaction with the robot consulting service.
微表情识别可以基于各种算法、模型、***来实现，比如可以利用深度神经网络、深度学***安的Gamma智能微表情***来识别。Micro-expression recognition can be realized based on various algorithms, models, and systems. For example, deep neural networks, deep learning algorithms, and reinforcement learning algorithms can be used for micro-expression recognition, and Ping An’s Gamma intelligent micro-expression system can also be used for recognition.
步骤240，当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务。Step 240: When the satisfaction degree meets a predetermined condition, switch the robot consultation channel to a manual consultation channel to provide manual consultation services for the target user.
在一个实施例中，所述机器人咨询服务和所述人工咨询服务均为文本形式的咨询服务。In one embodiment, the robot consulting service and the manual consulting service are both consulting services in text form.
在一个实施例中，所述机器人咨询服务为文本形式的咨询服务，所述人工咨询服务为语音形式的咨询服务。In one embodiment, the robot consulting service is a text-based consulting service, and the manual consulting service is a voice-based consulting service.
在一个实施例中，所述机器人咨询服务和所述人工咨询服务均为语音形式的咨询服务。In one embodiment, the robot consulting service and the manual consulting service are both in the form of voice consulting services.
预定条件是将机器人咨询通道切换至人工咨询通道，以实现由人工咨询通道为目标用户提供人工咨询服务的过程。一般地，预定条件可以表示目标用户对机器人咨询服务的满意度较低或低于一定阈值。The predetermined condition is to switch the robot consultation channel to the manual consultation channel, so as to realize the process of providing manual consultation services to the target users by the manual consultation channel. Generally, the predetermined condition may indicate that the target user's satisfaction with the robot consulting service is low or lower than a certain threshold.
在一个实施例中，所述当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务，包括：In one embodiment, when the satisfaction degree meets a predetermined condition, switching the robot consultation channel to a manual consultation channel to provide manual consultation services for the target user includes:
当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道并确定人工咨询请求以将所述人工咨询请求发送至所述人工咨询通道供人工客服为所述目标用户提供人工咨询服务，其中，将请求时间距离当前时间最近的咨询请求作为人工咨询请求。When the satisfaction degree meets a predetermined condition, switch the robot consultation channel to a manual consultation channel and determine a manual consultation request to send the manual consultation request to the manual consultation channel for manual customer service to provide manual consultation for the target user Service, where the consultation request whose request time is closest to the current time is regarded as a manual consultation request.
在本实施例中，通过在将机器人咨询通道切换至人工咨询通道时，将请求时间距离当前时间最近的咨询请求反馈给客服，使得客服可以及时掌握目标用户的疑问并进行相应的解答，实现了机器人咨询通道和人工咨询通道之间的平滑切换。In this embodiment, when the robot consultation channel is switched to the manual consultation channel, the consultation request whose request time is closest to the current time is fed back to the customer service, so that the customer service can grasp the questions of the target user in time and answer the corresponding questions. Smooth switching between robot consultation channel and manual consultation channel.
在一个实施例中，所述对所述目标用户的人脸图像序列进行微表情识别，以确定所述目标用户对所述机器人咨询服务的满意度，包括：In one embodiment, the performing micro-expression recognition on the face image sequence of the target user to determine the target user's satisfaction with the robot consulting service includes:
将所述人脸图像序列分为至少两个微表情片段；Dividing the face image sequence into at least two micro-expression fragments;
利用微表情识别模型确定每一微表情片段的满意度，作为所述目标用户在相应微表情片段所在时间段对所述机器人咨询服务的满意度；Using a micro-expression recognition model to determine the satisfaction degree of each micro-expression segment as the target user's satisfaction with the robot consulting service during the time period where the corresponding micro-expression segment is located;
所述当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务，包括：When the satisfaction degree meets a predetermined condition, switching the robot consulting channel to a manual consulting channel to provide manual consulting services for the target user includes:
当所述人脸图像序列对应的微表情片段的满意度中最大满意度与最小满意度的差值大于预定满意度差值阈值，则将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务。When the difference between the maximum satisfaction degree and the minimum satisfaction degree in the satisfaction degree of the micro-expression segment corresponding to the face image sequence is greater than the predetermined satisfaction degree difference threshold, the robot consultation channel is switched to the manual consultation channel, and the robot consultation channel is switched to the manual consultation channel. Target users provide manual consulting services.
微表情识别模型可以基于前述的各种算法或神经网络来建立，通常在使用模型之前首先要利用人脸图像数据进行模型的训练。The micro-expression recognition model can be established based on the aforementioned various algorithms or neural networks. Usually, the face image data is first used for model training before the model is used.
当在各微表情片段的满意度中，最大满意度与最小满意度的差值足够大时，说明客服机器人为所述目标用户提供的机器人咨询服务使目标用户的情绪波动较大，机器人咨询服务的体验较差，不能为用户提供令人满意的服务，此时通过为目标用户提供人工咨询服务，保证了服务质量，提高了用户满意度。When the difference between the maximum satisfaction and the minimum satisfaction in the satisfaction of each micro-expression segment is large enough, it means that the robot consulting service provided by the customer service robot for the target user makes the target user's mood fluctuate greatly, and the robot consulting service The user experience is poor and cannot provide satisfactory services to users. At this time, by providing manual consulting services for target users, the service quality is guaranteed and user satisfaction is improved.
在一个实施例中，所述对所述目标用户的人脸图像序列进行微表情识别，以确定所述目标用户对所述机器人咨询服务的满意度，包括：In one embodiment, the performing micro-expression recognition on the face image sequence of the target user to determine the target user's satisfaction with the robot consulting service includes:
将所述人脸图像序列分为至少两个微表情片段；Dividing the face image sequence into at least two micro-expression fragments;
利用微表情识别模型确定每一微表情片段的满意度，作为所述目标用户在相应微表情片段所在时间段对所述机器人咨询服务的满意度；Using a micro-expression recognition model to determine the satisfaction degree of each micro-expression segment as the target user's satisfaction with the robot consulting service during the time period where the corresponding micro-expression segment is located;
所述当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务，包括：When the satisfaction degree meets a predetermined condition, switching the robot consulting channel to a manual consulting channel to provide manual consulting services for the target user includes:
确定各微表情片段的满意度的平均值；Determine the average value of satisfaction of each micro-expression segment;
当所述平均值小于预定满意度平均值阈值，则将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务。When the average value is less than a predetermined satisfaction average value threshold, the robot consultation channel is switched to a manual consultation channel to provide manual consultation services for the target user.
满意度的平均值从整体上反映了用户在微表情片段组成的时间段内对机器人咨询服务的满意程度的集中程度，本实施例中通过根据各微表情片段的满意度的平均值与相应阈值的比较来确定将机器人咨询通道切换至人工咨询通道的时刻，在利用机器人咨询服务提高咨询效率的同时，使选择的将机器人咨询通道切换至人工咨询通道的时刻更为合理，利用人工咨询方式为用户提供更加专业咨询服务，保证了用户体验。The average value of satisfaction reflects the concentration of the user’s satisfaction with the robot consulting service during the time period composed of the micro-expression fragments. In this embodiment, the average value of the satisfaction degree and the corresponding threshold value To determine the time when the robot consulting channel is switched to the manual consulting channel, while using the robot consulting service to improve the consulting efficiency, the selected time to switch the robot consulting channel to the manual consulting channel is more reasonable. The manual consulting method is Users provide more professional consulting services to ensure user experience.
在一个实施例中，所述对所述目标用户的人脸图像序列进行微表情识别，以确定所述目标用户对所述机器人咨询服务的满意度，包括：In one embodiment, the performing micro-expression recognition on the face image sequence of the target user to determine the target user's satisfaction with the robot consulting service includes:
将所述人脸图像序列分为至少两个微表情片段；Dividing the face image sequence into at least two micro-expression fragments;
利用微表情识别模型确定距离当前时间最近的时间段对应的微表情片段的满意度，作为所述目标用户对所述机器人咨询服务的满意度；Using the micro-expression recognition model to determine the satisfaction degree of the micro-expression fragment corresponding to the time period closest to the current time as the target user's satisfaction with the robot consulting service;
所述当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务，包括：When the satisfaction degree meets a predetermined condition, switching the robot consulting channel to a manual consulting channel to provide manual consulting services for the target user includes:
当所述满意度小于预定满意度阈值，则将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务。When the satisfaction degree is less than a predetermined satisfaction threshold, the robot consultation channel is switched to a manual consultation channel to provide manual consultation services for the target user.
由于距离当前时间最近的时间段对应的微表情片段反映了目标用户最新的微表情的状态，在本实施例中，通过根据距离当前时间最近的时间段对应的微表情片段的满意度与相应阈值的比较来确定何时将机器人咨询通道切换至人工咨询通道，使目标用户对机器人咨询服务的最新满意度能够传导至是否将机器人咨询通道切换至人工咨询通道上面，兼顾了咨询效率和用户体验。Since the micro-expression segment corresponding to the time period closest to the current time reflects the latest micro-expression state of the target user, in this embodiment, according to the satisfaction of the micro-expression segment corresponding to the time period closest to the current time and the corresponding threshold To determine when to switch the robot consulting channel to the manual consulting channel, so that the target user’s latest satisfaction with the robot consulting service can be transmitted to whether to switch the robot consulting channel to the manual consulting channel, taking into account the consulting efficiency and user experience.
综上所述，根据图2实施例提供的在线客服咨询方法，通过同时利用客服机器人和人工客服两种方式为用户提供咨询服务，其中，使用人工客服为用户提供咨询服务是在为用户提供机器人咨询服务过程中用户对机器人咨询服务的满意度满足预定条件的情况下进行的，因此，兼顾了客服服务效率与客服服务质量。具体而言，一方面，通过在接收到用户的咨询请求时，先用客服机器人为用户提供咨询服务，由于机器人可以服务大量用户，与单纯使用人工客服相比，提高了服务效率，减少了用户等待时间，保证了用户体验，也通过减少人工客服的数量降低了运营成本；另一方面，在对用户进行微表情识别后，判断用户对所述机器人咨询服务的满意度满足预定条件时，通过为用户提供人工咨询服务，与单纯使用客服机器人相比，保证了服务质量，避免了机器人咨询服务导致用户体验差从而导致优质客户流失。To sum up, according to the online customer service consulting method provided by the embodiment in FIG. 2, the customer service robot and manual customer service are simultaneously used to provide users with consulting services. Among them, the use of manual customer service to provide users with consulting services is providing users with robots. During the consulting service process, the user's satisfaction with the robot consulting service meets the predetermined conditions. Therefore, both the customer service efficiency and the customer service quality are taken into consideration. Specifically, on the one hand, by first using a customer service robot to provide consulting services to users when receiving a user’s consultation request, since the robot can serve a large number of users, compared with purely using manual customer service, the service efficiency is improved and the number of users is reduced. The waiting time ensures the user experience and reduces the operating cost by reducing the number of manual customer services; on the other hand, after the user is identified with micro-expressions, it is determined that the user’s satisfaction with the robot consulting service meets the predetermined conditions, pass Providing users with manual consulting services, compared with simply using customer service robots, ensures the quality of service and avoids the poor user experience caused by robot consulting services and the loss of high-quality customers.
图3是根据一示例性实施例示出的本公开提供在线客服咨询方法应用于理财产品领域时的具体流程图。在图3实施例中，客服机器人是以AI（Artificial Intelligence，人工智能）助手的方式出现的，参照图3所示，该在线客服咨询的具体过程可以是这样的：首先，通过对AI助手进行训练，当要发售新的理财产品时，用户通过自身的终端点击该理财产品页面进行在线咨询，咨询首先由AI助手进行答疑，并在咨询过程中获取用户的人脸图像实时进行微表情识别，当通过微表情识别发现客户依然满意时，继续由AI助手为用户进行答疑，而当过微表情识别发现不再满意时，就接通人工客服，由人工客服为用户答疑。Fig. 3 is a specific flow chart when the online customer service consulting method provided by the present disclosure is applied to the field of wealth management products according to an exemplary embodiment. In the embodiment of FIG. 3, the customer service robot appears in the form of an AI (Artificial Intelligence) assistant. As shown in FIG. 3, the specific process of the online customer service consultation can be as follows: Training, when a new wealth management product is to be sold, the user clicks on the wealth management product page through his own terminal to conduct online consultation. The AI assistant first answers the question and obtains the user’s face image during the consultation process for real-time micro-expression recognition. When it is found that the customer is still satisfied through the micro-expression recognition, the AI assistant will continue to answer the user's questions, and when the micro-expression recognition is found to be no longer satisfactory, the manual customer service will be connected, and the manual customer service will answer the user's questions.
图4是根据图2对应实施例示出的一实施例的步骤240之后步骤的流程图。如图4所示，包括以下步骤：FIG. 4 is a flowchart of steps after step 240 in an embodiment shown according to the embodiment corresponding to FIG. 2. As shown in Figure 4, it includes the following steps:
步骤250，将所述目标用户标记为人工服务优先用户。Step 250: Mark the target user as a manual service priority user.
“人工服务优先用户”这一标记是对目标用户的一种标识，目标用户能够发起咨询请求，一般而言其本身就具有一个账户或者标识，对目标用户进行标记后，该标记可以和用户自身的账户或者标识一起存储到数据库中，以供查询。The mark of "Manual Service Priority User" is an identification of the target user. The target user can initiate a consultation request. Generally speaking, it has an account or identification. After the target user is marked, the mark can be combined with the user itself. The account or ID of the account is stored in the database together for query.
步骤260，当在所述人工咨询服务结束后再次接收到所述目标用户的咨询请求，依据所述目标用户的人工服务优先用户标记启动人工咨询通道，以为所述目标用户提供人工咨询服务。Step 260: When the target user's consulting request is received again after the manual consulting service ends, a manual consulting channel is activated according to the target user's manual service priority user mark to provide the target user with a manual consulting service.
当为一个用户提供咨询服务时，如果他对机器人咨询服务的满意程度低，并且用人工咨询服务为该用户提供了服务，说明机器人咨询服务不能很好的为该用户提供咨询服务，此时，通过对该用户进行标记，当再次接收到该用户发来的咨询请求时，根据该用户具有该标记，直接为该用户提供人工咨询服务，在最大程度上保证了不适合采用机器人咨询服务的目标用户的体验，提高了服务质量。When providing consulting services to a user, if he is not satisfied with the robot consulting service and provides the user with manual consulting services, it means that the robot consulting service cannot provide the user with consulting services. At this time, By marking the user, when the user's consultation request is received again, according to the user's mark, the user is directly provided with manual consultation services, which guarantees the goal of not being suitable for the use of robot consultation services to the greatest extent The user experience improves the quality of service.
在一个实施例中，所述咨询请求为针对产品的购买咨询请求，在将所述目标用户标记为人工服务优先用户之后，所述方法还包括：In an embodiment, the consultation request is a purchase consultation request for a product, and after the target user is marked as a manual service priority user, the method further includes:
当所述目标用户完成对所述咨询请求对应的产品的购买交易，清除对所述目标用户的标记。When the target user completes the purchase transaction of the product corresponding to the consultation request, the mark of the target user is cleared.
购买咨询请求页面的信息和对产品的购买交易信息可以由与用户的客户端相对的服务端在维护，若服务端为本公开的实施终端，那么，服务端可以获知目标用户对哪些产品完成了购买交易，并且可以获知这些产品中哪些是目标用户的购买咨询请求所针对的，从而可以是服务端获知目标用户是否已经完成对所述咨询请求对应的产品的购买交易。The information on the purchase consultation request page and the product purchase transaction information can be maintained by the server opposite to the user's client. If the server is the implementation terminal of the disclosure, then the server can learn which products the target user has completed Purchase transactions, and it is possible to know which of these products are targeted by the purchase consultation request of the target user, so that the server can know whether the target user has completed the purchase transaction of the product corresponding to the consultation request.
当目标用户购买完产品后，就不需要继续在该目标用户身上投入人工客服的资源，在本实施例中，通过在目标用户完成了对产品的购买交易后，清除目标用户的标记，节约了人工客服的资源。After the target user purchases the product, there is no need to continue to invest the resources of manual customer service on the target user. In this embodiment, after the target user completes the product purchase transaction, the target user’s mark is cleared, which saves Resources for human customer service.
本公开还提供了一种在线客服咨询装置，以下是本公开的装置实施例。The present disclosure also provides an online customer service consulting device. The following are device embodiments of the present disclosure.
图5是根据一示例性实施例示出的一种在线客服咨询装置的框图。如图5所示，装置500包括：Fig. 5 is a block diagram showing an online customer service consulting device according to an exemplary embodiment. As shown in FIG. 5, the device 500 includes:
通道启动模块510，被配置为当接收到目标用户的咨询请求，启动机器人咨询通道，以通过客服机器人为所述目标用户提供机器人咨询服务；The channel activation module 510 is configured to activate a robot consulting channel when receiving a consultation request from a target user, so as to provide a robot consulting service for the target user through a customer service robot;
获取模块520，被配置为获取正在接受所述机器人咨询服务的所述目标用户的人脸图像序列；The obtaining module 520 is configured to obtain the face image sequence of the target user who is receiving the robot consulting service;
微表情识别模块530，被配置为对所述目标用户的人脸图像序列进行微表情识别，以确定所述目标用户对所述机器人咨询服务的满意度；The micro-expression recognition module 530 is configured to perform micro-expression recognition on the face image sequence of the target user to determine the target user's satisfaction with the robot consulting service;
切换模块540，被配置为当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务。The switching module 540 is configured to switch the robot consultation channel to a manual consultation channel when the satisfaction degree meets a predetermined condition, so as to provide a manual consultation service for the target user.
根据本公开的第三方面，还提供了一种能够实现上述方法的电子设备。According to the third aspect of the present disclosure, there is also provided an electronic device capable of implementing the above method.
所属技术领域的技术人员能够理解，本申请的各个方面可以实现为***、方法或程序产品。因此，本申请的各个方面可以具体实现为以下形式，即：完全的硬件实施方式、完全的软件实施方式（包括固件、微代码等），或硬件和软件方面结合的实施方式，这里可以统称为“电路”、“模块”或“***”。Those skilled in the art can understand that various aspects of the present application can be implemented as a system, a method, or a program product. Therefore, each aspect of the present application can be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which can be collectively referred to herein as "Circuit", "Module" or "System".
下面参照图6来描述根据本申请的这种实施方式的电子设备600。图6显示的电子设备600仅仅是一个示例，不应对本申请实施例的功能和使用范围带来任何限制。The electronic device 600 according to this embodiment of the present application will be described below with reference to FIG. 6. The electronic device 600 shown in FIG. 6 is only an example, and should not bring any limitation to the function and scope of use of the embodiments of the present application.
如图6所示，电子设备600以通用计算设备的形式表现。电子设备600的组件可以包括但不限于：上述至少一个处理单元610、上述至少一个存储单元620、连接不同***组件（包括存储单元620和处理单元610）的总线630。As shown in FIG. 6, the electronic device 600 is represented in the form of a general-purpose computing device. The components of the electronic device 600 may include, but are not limited to: the aforementioned at least one processing unit 610, the aforementioned at least one storage unit 620, and a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610).
其中，所述存储单元存储有程序代码，所述程序代码可以被所述处理单元610执行，使得所述处理单元610执行本说明书上述“实施例方法”部分中描述的根据本申请各种示例性实施方式的步骤。Wherein, the storage unit stores program code, and the program code can be executed by the processing unit 610, so that the processing unit 610 executes the various exemplary methods described in the "Methods of Embodiments" section of this specification. Steps of implementation.
存储单元620可以包括易失性存储单元形式的可读介质，例如随机存取存储单元（RAM）621和/或高速缓存存储单元622，还可以进一步包括只读存储单元（ROM）623。The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 621 and/or a cache storage unit 622, and may further include a read-only storage unit (ROM) 623.
存储单元620还可以包括具有一组（至少一个）程序模块625的程序/实用工具624，这样的程序模块625包括但不限于：操作***、一个或者多个应用程序、其它程序模块以及程序数据，这些示例中的每一个或某种组合中可能包括网络环境的实现。The storage unit 620 may also include a program/utility tool 624 having a set of (at least one) program module 625. Such program module 625 includes but is not limited to: an operating system, one or more application programs, other program modules, and program data, Each of these examples or some combination may include the implementation of a network environment.
总线630可以为表示几类总线结构中的一种或多种，包括存储单元总线或者存储单元控制器、***总线、图形加速端口、处理单元或者使用多种总线结构中的任意总线结构的局域总线。The bus 630 may represent one or more of several types of bus structures, including a storage unit bus or a storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local area using any bus structure among multiple bus structures. bus.
电子设备600也可以与一个或多个外部设备800（例如键盘、指向设备、蓝牙设备等）通信，还可与一个或者多个使得用户能与该电子设备600交互的设备通信，和/或与使得该电子设备600能与一个或多个其它计算设备进行通信的任何设备（例如路由器、调制解调器等等）通信。这种通信可以通过输入/输出（I/O）接口650进行。并且，电子设备600还可以通过网络适配器660与一个或者多个网络（例如局域网（LAN），广域网（WAN）和/或公共网络，例如因特网）通信。如图所示，网络适配器660通过总线630与电子设备600的其它模块通信。应当明白，尽管图中未示出，可以结合电子设备600使用其它硬件和/或软件模块，包括但不限于：微代码、设备驱动器、冗余处理单元、外部磁盘驱动阵列、RAID***、磁带驱动器以及数据备份存储***等。The electronic device 600 may also communicate with one or more external devices 800 (such as keyboards, pointing devices, Bluetooth devices, etc.), and may also communicate with one or more devices that enable a user to interact with the electronic device 600, and/or communicate with Any device (such as a router, modem, etc.) that enables the electronic device 600 to communicate with one or more other computing devices. This communication can be performed through an input/output (I/O) interface 650. In addition, the electronic device 600 may also communicate with one or more networks (for example, a local area network (LAN), a wide area network (WAN), and/or a public network, such as the Internet) through the network adapter 660. As shown in the figure, the network adapter 660 communicates with other modules of the electronic device 600 through the bus 630. It should be understood that although not shown in the figure, other hardware and/or software modules can be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives And data backup storage system, etc.
通过以上的实施方式的描述，本领域的技术人员易于理解，这里描述的示例实施方式可以通过软件实现，也可以通过软件结合必要的硬件的方式来实现。因此，根据本公开实施方式的技术方案可以以软件产品的形式体现出来，该软件产品可以存储在一个非易失性存储介质（可以是CD-ROM，U盘，移动硬盘等）中或网络上，包括若干指令以使得一台计算设备（可以是个人计算机、服务器、终端装置、或者网络设备等）执行根据本公开实施方式的方法。Through the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described here can be implemented by software, or can be implemented by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, U disk, mobile hard disk, etc.) or on the network , Including several instructions to make a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) execute the method according to the embodiments of the present disclosure.
根据本公开的第四方面，还提供了一种计算机可读存储介质，所述计算机可读存储介质可以是易失性，也可以是非易失性，其上存储有能够实现本说明书上述方法的程序产品。在一些可能的实施方式中，本申请的各个方面还可以实现为一种程序产品的形式，其包括程序代码，当所述程序产品在终端设备上运行时，所述程序代码用于使所述终端设备执行本说明书上述“示例性方法”部分中描述的根据本申请各种示例性实施方式的步骤。According to the fourth aspect of the present disclosure, there is also provided a computer-readable storage medium. The computer-readable storage medium may be volatile or non-volatile. Program product. In some possible implementation manners, each aspect of the present application can also be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to make the The terminal device executes the steps according to various exemplary embodiments of the present application described in the above-mentioned "Exemplary Method" section of this specification.
参考图7所示，描述了根据本申请的实施方式的用于实现上述方法的程序产品700，其可以采用便携式紧凑盘只读存储器(CD-ROM)并包括程序代码，并可以在终端设备，例如个人电脑上运行。然而，本申请的程序产品不限于此，在本文件中，可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行***、装置或者器件使用或者与其结合使用。Referring to FIG. 7, a program product 700 for implementing the above method according to an embodiment of the present application is described. It can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be stored in a terminal device, For example, running on a personal computer. However, the program product of this application is not limited to this. In this document, the readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, device, or device.
所述程序产品可以采用一个或多个可读介质的任意组合。可读介质可以是可读信号介质或者可读存储介质。可读存储介质例如可以为但不限于电、磁、光、电磁、红外线、或半导体的***、装置或器件，或者任意以上的组合。可读存储介质的更具体的例子（非穷举的列表）包括：具有一个或多个导线的电连接、便携式盘、硬盘、随机存取存储器（RAM）、只读存储器（ROM）、可擦式可编程只读存储器（EPROM或闪存）、光纤、便携式紧凑盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。The program product can use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or a combination of any of the above. More specific examples (non-exhaustive list) of readable storage media include: electrical connections with one or more wires, portable disks, hard disks, random access memory (RAM), read only memory (ROM), erasable Type programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了可读程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。可读信号介质还可以是可读存储介质以外的任何可读介质，该可读介质可以发送、传播或者传输用于由指令执行***、装置或者器件使用或者与其结合使用的程序。The computer-readable signal medium may include a data signal propagated in baseband or as a part of a carrier wave, and readable program code is carried therein. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The readable signal medium may also be any readable medium other than a readable storage medium, and the readable medium may send, propagate, or transmit a program for use by or in combination with the instruction execution system, apparatus, or device.
可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于无线、有线、光缆、RF等等，或者上述的任意合适的组合。The program code contained on the readable medium can be transmitted by any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.
可以以一种或多种程序设计语言的任意组合来编写用于执行本申请操作的程序代码，所述程序设计语言包括面向对象的程序设计语言—诸如Java、C++等，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算设备上执行、部分地在用户设备上执行、作为一个独立的软件包执行、部分在用户计算设备上部分在远程计算设备上执行、或者完全在远程计算设备或服务器上执行。在涉及远程计算设备的情形中，远程计算设备可以通过任意种类的网络，包括局域网（LAN）或广域网（WAN），连接到用户计算设备，或者，可以连接到外部计算设备（例如利用因特网服务提供商来通过因特网连接）。The program code used to perform the operations of the present application can be written in any combination of one or more programming languages. The programming languages include object-oriented programming languages—such as Java, C++, etc., as well as conventional procedural programming languages. Programming language-such as "C" language or similar programming language. The program code can be executed entirely on the user's computing device, partly on the user's device, executed as an independent software package, partly on the user's computing device and partly executed on the remote computing device, or entirely on the remote computing device or server Executed on. In the case of a remote computing device, the remote computing device can be connected to a user computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (for example, using Internet service providers). Business to connect via the Internet).
此外，上述附图仅是根据本申请示例性实施例的方法所包括的处理的示意性说明，而不是限制目的。易于理解，上述附图所示的处理并不表明或限制这些处理的时间顺序。另外，也易于理解，这些处理可以是例如在多个模块中同步或异步执行的。In addition, the above-mentioned drawings are merely schematic illustrations of the processing included in the method according to the exemplary embodiments of the present application, and are not intended for limitation. It is easy to understand that the processing shown in the above drawings does not indicate or limit the time sequence of these processings. In addition, it is easy to understand that these processes can be executed synchronously or asynchronously in multiple modules, for example.
应当理解的是，本申请并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围执行各种修改和改变。本申请的范围仅由所附的权利要求来限制。It should be understood that the present application is not limited to the precise structure that has been described above and shown in the drawings, and various modifications and changes can be performed without departing from its scope. The scope of the application is only limited by the appended claims.

Claims (20)

  1. 一种在线客服咨询方法，其中，所述方法包括：An online customer service consulting method, wherein the method includes:
    当接收到目标用户的咨询请求，启动机器人咨询通道，以通过客服机器人为所述目标用户提供机器人咨询服务；When receiving a consultation request from a target user, start a robot consultation channel to provide robot consultation services for the target user through a customer service robot;
    获取正在接受所述机器人咨询服务的所述目标用户的人脸图像序列；Acquiring the face image sequence of the target user who is receiving the robot consulting service;
    对所述目标用户的人脸图像序列进行微表情识别，以确定所述目标用户对所述机器人咨询服务的满意度；Performing micro-expression recognition on the face image sequence of the target user to determine the target user's satisfaction with the robot consulting service;
    当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务。When the satisfaction degree satisfies a predetermined condition, the robot consultation channel is switched to a manual consultation channel to provide manual consultation services for the target user.
  2. 根据权利要求1所述的方法，其中，所述获取正在接受所述机器人咨询服务的所述目标用户的人脸图像序列，包括：The method according to claim 1, wherein said acquiring a face image sequence of said target user who is receiving said robot consulting service comprises:
    响应所述目标用户的咨询请求并在向所述目标用户首次反馈咨询信息时，开始获取所述目标用户的人脸图像序列。Responding to the consultation request of the target user and starting to obtain the face image sequence of the target user when the target user is fed back with the consultation information for the first time.
  3. 根据权利要求1或2所述的方法，其中，所述对所述目标用户的人脸图像序列进行微表情识别，以确定所述目标用户对所述机器人咨询服务的满意度，包括：The method according to claim 1 or 2, wherein the performing micro-expression recognition on the face image sequence of the target user to determine the target user’s satisfaction with the robot consulting service comprises:
    将所述人脸图像序列分为至少两个微表情片段；Dividing the face image sequence into at least two micro-expression fragments;
    利用微表情识别模型确定每一微表情片段的满意度，作为所述目标用户在相应微表情片段所在时间段对所述机器人咨询服务的满意度；Using a micro-expression recognition model to determine the satisfaction degree of each micro-expression segment as the target user's satisfaction with the robot consulting service during the time period where the corresponding micro-expression segment is located;
    所述当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务，包括：When the satisfaction degree meets a predetermined condition, switching the robot consulting channel to a manual consulting channel to provide manual consulting services for the target user includes:
    当所述人脸图像序列对应的微表情片段的满意度中最大满意度与最小满意度的差值大于预定满意度差值阈值，则将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务。When the difference between the maximum satisfaction degree and the minimum satisfaction degree in the satisfaction degree of the micro-expression segment corresponding to the face image sequence is greater than the predetermined satisfaction degree difference threshold, the robot consultation channel is switched to the manual consultation channel, and the robot consultation channel is switched to the manual consultation channel. Target users provide manual consulting services.
  4. 根据权利要求1或2所述的方法，其中，所述对所述目标用户的人脸图像序列进行微表情识别，以确定所述目标用户对所述机器人咨询服务的满意度，包括：The method according to claim 1 or 2, wherein the performing micro-expression recognition on the face image sequence of the target user to determine the target user’s satisfaction with the robot consulting service comprises:
    将所述人脸图像序列分为至少两个微表情片段；Dividing the face image sequence into at least two micro-expression fragments;
    利用微表情识别模型确定距离当前时间最近的时间段对应的微表情片段的满意度，作为所述目标用户对所述机器人咨询服务的满意度；Using the micro-expression recognition model to determine the satisfaction degree of the micro-expression fragment corresponding to the time period closest to the current time as the target user's satisfaction with the robot consulting service;
    所述当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务，包括：When the satisfaction degree meets a predetermined condition, switching the robot consulting channel to a manual consulting channel to provide manual consulting services for the target user includes:
    当所述满意度小于预定满意度阈值，则将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务。When the satisfaction degree is less than a predetermined satisfaction threshold, the robot consultation channel is switched to a manual consultation channel to provide manual consultation services for the target user.
  5. 根据权利要求1所述的方法，其中，所述当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务，包括：The method according to claim 1, wherein when the satisfaction degree meets a predetermined condition, switching the robot consultation channel to a manual consultation channel to provide manual consultation services for the target user comprises:
    当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道并确定人工咨询请求以将所述人工咨询请求发送至所述人工咨询通道供人工客服为所述目标用户提供人工咨询服务，其中，将请求时间距离当前时间最近的咨询请求作为人工咨询请求。When the satisfaction degree meets a predetermined condition, switch the robot consultation channel to a manual consultation channel and determine a manual consultation request to send the manual consultation request to the manual consultation channel for manual customer service to provide manual consultation for the target user Service, where the consultation request whose request time is closest to the current time is regarded as a manual consultation request.
  6. 根据权利要求1或2所述的方法，其中，在当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务之后，所述方法还包括：The method according to claim 1 or 2, wherein, when the satisfaction degree meets a predetermined condition, the robot consulting channel is switched to a manual consulting channel to provide manual consulting services for the target user, the method further include:
    将所述目标用户标记为人工服务优先用户；Marking the target user as a manual service priority user;
    当在所述人工咨询服务结束后再次接收到所述目标用户的咨询请求，依据所述目标用户的人工服务优先用户标记启动人工咨询通道，以为所述目标用户提供人工咨询服务。When the consultation request of the target user is received again after the manual consultation service ends, the manual consultation channel is activated according to the manual service priority user mark of the target user, so as to provide the manual consultation service for the target user.
  7. 根据权利要求6所述的方法，其中，所述咨询请求为针对产品的购买咨询请求，在将所述目标用户标记为人工服务优先用户之后，所述方法还包括：The method according to claim 6, wherein the consultation request is a purchase consultation request for a product, and after the target user is marked as a manual service priority user, the method further comprises:
    当所述目标用户完成对所述咨询请求对应的产品的购买交易，清除对所述目标用户的标记。When the target user completes the purchase transaction of the product corresponding to the consultation request, the mark of the target user is cleared.
  8. 一种在线客服咨询装置，其中，所述装置包括：An online customer service consulting device, wherein the device includes:
    通道启动模块，被配置为当接收到目标用户的咨询请求，启动机器人咨询通道，以通过客服机器人为所述目标用户提供机器人咨询服务；The channel start module is configured to start a robot consulting channel when receiving a consultation request from a target user, so as to provide a robot consulting service for the target user through a customer service robot;
    获取模块，被配置为获取正在接受所述机器人咨询服务的所述目标用户的人脸图像序列；An obtaining module configured to obtain the face image sequence of the target user who is receiving the robot consulting service;
    微表情识别模块，被配置为对所述目标用户的人脸图像序列进行微表情识别，以确定所述目标用户对所述机器人咨询服务的满意度；The micro-expression recognition module is configured to perform micro-expression recognition on the face image sequence of the target user to determine the target user's satisfaction with the robot consulting service;
    切换模块，被配置为当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务。The switching module is configured to switch the robot consultation channel to a manual consultation channel when the satisfaction degree meets a predetermined condition, so as to provide manual consultation services for the target user.
  9. 一种计算机可读存储介质，其中，其存储有计算机程序指令，当所述计算机程序指令被计算机执行时，使计算机执行如下步骤：A computer-readable storage medium, in which computer program instructions are stored, and when the computer program instructions are executed by a computer, the computer executes the following steps:
    当接收到目标用户的咨询请求，启动机器人咨询通道，以通过客服机器人为所述目标用户提供机器人咨询服务；When receiving a consultation request from a target user, start a robot consultation channel to provide robot consultation services for the target user through a customer service robot;
    获取正在接受所述机器人咨询服务的所述目标用户的人脸图像序列；Acquiring the face image sequence of the target user who is receiving the robot consulting service;
    对所述目标用户的人脸图像序列进行微表情识别，以确定所述目标用户对所述机器人咨询服务的满意度；Performing micro-expression recognition on the face image sequence of the target user to determine the target user's satisfaction with the robot consulting service;
    当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务。When the satisfaction degree satisfies a predetermined condition, the robot consultation channel is switched to a manual consultation channel to provide manual consultation services for the target user.
  10. 根据权利要求9所述的计算机可读存储介质，其中，所述获取正在接受所述机器人咨询服务的所述目标用户的人脸图像序列，包括：9. The computer-readable storage medium according to claim 9, wherein said acquiring the face image sequence of said target user who is receiving said robot consulting service comprises:
    响应所述目标用户的咨询请求并在向所述目标用户首次反馈咨询信息时，开始获取所述目标用户的人脸图像序列。Responding to the consultation request of the target user and starting to obtain the face image sequence of the target user when the target user is fed back with the consultation information for the first time.
  11. 根据权利要求9或10所述的计算机可读存储介质，其中，所述对所述目标用户的人脸图像序列进行微表情识别，以确定所述目标用户对所述机器人咨询服务的满意度，包括：The computer-readable storage medium according to claim 9 or 10, wherein the micro-expression recognition is performed on the face image sequence of the target user to determine the target user’s satisfaction with the robot consulting service, include:
    将所述人脸图像序列分为至少两个微表情片段；Dividing the face image sequence into at least two micro-expression fragments;
    利用微表情识别模型确定每一微表情片段的满意度，作为所述目标用户在相应微表情片段所在时间段对所述机器人咨询服务的满意度；Using a micro-expression recognition model to determine the satisfaction degree of each micro-expression segment as the target user's satisfaction with the robot consulting service during the time period where the corresponding micro-expression segment is located;
    所述当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务，包括：When the satisfaction degree meets a predetermined condition, switching the robot consulting channel to a manual consulting channel to provide manual consulting services for the target user includes:
    当所述人脸图像序列对应的微表情片段的满意度中最大满意度与最小满意度的差值大于预定满意度差值阈值，则将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务。When the difference between the maximum satisfaction degree and the minimum satisfaction degree in the satisfaction degree of the micro-expression segment corresponding to the face image sequence is greater than the predetermined satisfaction degree difference threshold, the robot consultation channel is switched to the manual consultation channel, and the robot consultation channel is switched to the manual consultation channel. Target users provide manual consulting services.
  12. 根据权利要求9或10所述的计算机可读存储介质，其中，所述对所述目标用户的人脸图像序列进行微表情识别，以确定所述目标用户对所述机器人咨询服务的满意度，包括：The computer-readable storage medium according to claim 9 or 10, wherein the micro-expression recognition is performed on the face image sequence of the target user to determine the target user’s satisfaction with the robot consulting service, include:
    将所述人脸图像序列分为至少两个微表情片段；Dividing the face image sequence into at least two micro-expression fragments;
    利用微表情识别模型确定距离当前时间最近的时间段对应的微表情片段的满意度，作为所述目标用户对所述机器人咨询服务的满意度；Using the micro-expression recognition model to determine the satisfaction degree of the micro-expression fragment corresponding to the time period closest to the current time as the target user's satisfaction with the robot consulting service;
    所述当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务，包括：When the satisfaction degree meets a predetermined condition, switching the robot consulting channel to a manual consulting channel to provide manual consulting services for the target user includes:
    当所述满意度小于预定满意度阈值，则将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务。When the satisfaction degree is less than a predetermined satisfaction threshold, the robot consultation channel is switched to a manual consultation channel to provide manual consultation services for the target user.
  13. 根据权利要求9所述的计算机可读存储介质，其中，所述当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务，包括：9. The computer-readable storage medium according to claim 9, wherein the switching the robot consultation channel to a manual consultation channel when the satisfaction degree satisfies a predetermined condition to provide manual consultation services for the target user comprises:
    当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道并确定人工咨询请求以将所述人工咨询请求发送至所述人工咨询通道供人工客服为所述目标用户提供人工咨询服务，其中，将请求时间距离当前时间最近的咨询请求作为人工咨询请求。When the satisfaction degree meets a predetermined condition, switch the robot consultation channel to a manual consultation channel and determine a manual consultation request to send the manual consultation request to the manual consultation channel for manual customer service to provide manual consultation for the target user Service, where the consultation request whose request time is closest to the current time is regarded as a manual consultation request.
  14. 根据权利要求9或10所述的计算机可读存储介质，其中，在当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务之后，所述计算机程序指令被计算机执行时还实现如下步骤：The computer-readable storage medium according to claim 9 or 10, wherein, after the satisfaction degree meets a predetermined condition, the robot consultation channel is switched to a manual consultation channel to provide manual consultation services for the target user, When the computer program instructions are executed by the computer, the following steps are also implemented:
    将所述目标用户标记为人工服务优先用户；Marking the target user as a manual service priority user;
    当在所述人工咨询服务结束后再次接收到所述目标用户的咨询请求，依据所述目标用户的人工服务优先用户标记启动人工咨询通道，以为所述目标用户提供人工咨询服务。When the consultation request of the target user is received again after the manual consultation service ends, the manual consultation channel is activated according to the manual service priority user mark of the target user, so as to provide the manual consultation service for the target user.
  15. 根据权利要求14所述的计算机可读存储介质，其中，所述咨询请求为针对产品的购买咨询请求，在将所述目标用户标记为人工服务优先用户之后，所述计算机程序指令被计算机执行时还实现如下步骤：The computer-readable storage medium according to claim 14, wherein the consultation request is a purchase consultation request for a product, and after the target user is marked as a manual service priority user, when the computer program instructions are executed by a computer Also implement the following steps:
    当所述目标用户完成对所述咨询请求对应的产品的购买交易，清除对所述目标用户的标记。When the target user completes the purchase transaction of the product corresponding to the consultation request, the mark of the target user is cleared.
  16. 一种电子设备，其中，所述电子设备包括：An electronic device, wherein the electronic device includes:
    处理器；processor;
    存储器，所述存储器上存储有计算机可读指令，所述计算机可读指令被所述处理器执行时，实现如下步骤：A memory, where computer-readable instructions are stored, and when the computer-readable instructions are executed by the processor, the following steps are implemented:
    当接收到目标用户的咨询请求，启动机器人咨询通道，以通过客服机器人为所述目标用户提供机器人咨询服务；When receiving a consultation request from a target user, start a robot consultation channel to provide robot consultation services for the target user through a customer service robot;
    获取正在接受所述机器人咨询服务的所述目标用户的人脸图像序列；Acquiring the face image sequence of the target user who is receiving the robot consulting service;
    对所述目标用户的人脸图像序列进行微表情识别，以确定所述目标用户对所述机器人咨询服务的满意度；Performing micro-expression recognition on the face image sequence of the target user to determine the target user's satisfaction with the robot consulting service;
    当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务。When the satisfaction degree satisfies a predetermined condition, the robot consultation channel is switched to a manual consultation channel to provide manual consultation services for the target user.
  17. 根据权利要求16所述的电子设备，其中，所述获取正在接受所述机器人咨询服务的所述目标用户的人脸图像序列，包括：The electronic device according to claim 16, wherein said acquiring the face image sequence of said target user who is receiving said robot consulting service comprises:
    响应所述目标用户的咨询请求并在向所述目标用户首次反馈咨询信息时，开始获取所述目标用户的人脸图像序列。Responding to the consultation request of the target user and starting to obtain the face image sequence of the target user when the target user is fed back with the consultation information for the first time.
  18. 根据权利要求16或17所述的电子设备，其中，所述对所述目标用户的人脸图像序列进行微表情识别，以确定所述目标用户对所述机器人咨询服务的满意度，包括：The electronic device according to claim 16 or 17, wherein the micro-expression recognition on the face image sequence of the target user to determine the target user’s satisfaction with the robot consulting service comprises:
    将所述人脸图像序列分为至少两个微表情片段；Dividing the face image sequence into at least two micro-expression fragments;
    利用微表情识别模型确定每一微表情片段的满意度，作为所述目标用户在相应微表情片段所在时间段对所述机器人咨询服务的满意度；Using a micro-expression recognition model to determine the satisfaction degree of each micro-expression segment as the target user's satisfaction with the robot consulting service during the time period where the corresponding micro-expression segment is located;
    所述当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务，包括：When the satisfaction degree meets a predetermined condition, switching the robot consulting channel to a manual consulting channel to provide manual consulting services for the target user includes:
    当所述人脸图像序列对应的微表情片段的满意度中最大满意度与最小满意度的差值大于预定满意度差值阈值，则将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务。When the difference between the maximum satisfaction degree and the minimum satisfaction degree in the satisfaction degree of the micro-expression segment corresponding to the face image sequence is greater than the predetermined satisfaction degree difference threshold, the robot consultation channel is switched to the manual consultation channel, and the robot consultation channel is switched to the manual consultation channel. Target users provide manual consulting services.
  19. 根据权利要求16或17所述的电子设备，其中，所述对所述目标用户的人脸图像序列进行微表情识别，以确定所述目标用户对所述机器人咨询服务的满意度，包括：The electronic device according to claim 16 or 17, wherein the micro-expression recognition on the face image sequence of the target user to determine the target user’s satisfaction with the robot consulting service comprises:
    将所述人脸图像序列分为至少两个微表情片段；Dividing the face image sequence into at least two micro-expression fragments;
    利用微表情识别模型确定距离当前时间最近的时间段对应的微表情片段的满意度，作为所述目标用户对所述机器人咨询服务的满意度；Using the micro-expression recognition model to determine the satisfaction degree of the micro-expression fragment corresponding to the time period closest to the current time as the target user's satisfaction with the robot consulting service;
    所述当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务，包括：When the satisfaction degree meets a predetermined condition, switching the robot consulting channel to a manual consulting channel to provide manual consulting services for the target user includes:
    当所述满意度小于预定满意度阈值，则将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务。When the satisfaction degree is less than a predetermined satisfaction threshold, the robot consultation channel is switched to a manual consultation channel to provide manual consultation services for the target user.
  20. 根据权利要求16所述的电子设备，其中，所述当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道，以为所述目标用户提供人工咨询服务，包括：The electronic device according to claim 16, wherein said switching said robot consultation channel to a manual consultation channel when said satisfaction degree satisfies a predetermined condition, so as to provide manual consultation service for said target user, comprises:
    当所述满意度满足预定条件，将所述机器人咨询通道切换至人工咨询通道并确定人工咨询请求以将所述人工咨询请求发送至所述人工咨询通道供人工客服为所述目标用户提供人工咨询服务，其中，将请求时间距离当前时间最近的咨询请求作为人工咨询请求。When the satisfaction degree meets a predetermined condition, switch the robot consultation channel to a manual consultation channel and determine a manual consultation request to send the manual consultation request to the manual consultation channel for manual customer service to provide manual consultation for the target user Service, where the consultation request whose request time is closest to the current time is regarded as a manual consultation request.
PCT/CN2021/070750 2020-03-02 2021-01-08 Online customer service consultation method and apparatus, medium, and electronic device WO2021175007A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010136161.9A CN111460112A (en) 2020-03-02 2020-03-02 Online customer service consultation method, device, medium and electronic equipment
CN202010136161.9 2020-03-02

Publications (1)

Publication Number Publication Date
WO2021175007A1 true WO2021175007A1 (en) 2021-09-10

Family

ID=71679990

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/070750 WO2021175007A1 (en) 2020-03-02 2021-01-08 Online customer service consultation method and apparatus, medium, and electronic device

Country Status (2)

Country Link
CN (1) CN111460112A (en)
WO (1) WO2021175007A1 (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114047995A (en) * 2021-11-25 2022-02-15 中国建设银行股份有限公司 Method, device and equipment for determining label color and storage medium
CN114070937A (en) * 2021-11-10 2022-02-18 京东科技信息技术有限公司 Multi-modal client consultation method and related equipment
CN114117157A (en) * 2021-11-19 2022-03-01 招联消费金融有限公司 Session processing method, device, computer equipment and storage medium
CN114710471A (en) * 2022-03-21 2022-07-05 京东科技信息技术有限公司 Network-based customer service voice communication method, device, electronic equipment and medium
CN115297078A (en) * 2022-07-06 2022-11-04 北京北信源软件股份有限公司 Consultation response method, consultation response device, computer equipment and storage medium
CN115396389A (en) * 2022-07-07 2022-11-25 深圳市华汇数据服务有限公司 Internet of things information technology customer service system based on emotion energy perception
CN116112630A (en) * 2023-04-04 2023-05-12 成都新希望金融信息有限公司 Intelligent video face tag switching method

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111460112A (en) * 2020-03-02 2020-07-28 深圳壹账通智能科技有限公司 Online customer service consultation method, device, medium and electronic equipment
CN112347236A (en) * 2020-11-16 2021-02-09 友谊国际工程咨询股份有限公司 Intelligent engineering consultation method and system based on AI (Artificial Intelligence) calculated quantity and computer equipment thereof
CN112543185B (en) * 2020-11-23 2022-09-06 建信金融科技有限责任公司 Customer service method, device and system
CN112929591A (en) * 2021-01-28 2021-06-08 联通(辽宁)产业互联网有限公司 5G tax video customer service platform and operation method thereof
CN113065362B (en) * 2021-03-19 2024-06-21 联想(北京)有限公司 Intelligent reply method and device
CN113379229A (en) * 2021-06-08 2021-09-10 北京沃东天骏信息技术有限公司 Resource scheduling method and device

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108418981A (en) * 2018-03-16 2018-08-17 苏州思必驰信息科技有限公司 The method and device of dialogue service is provided for client
CN109015690A (en) * 2018-08-31 2018-12-18 中通天鸿（北京）通信科技股份有限公司 active interactive dialogue robot system and method
CN110472023A (en) * 2019-07-10 2019-11-19 深圳追一科技有限公司 Customer service switching method, device, computer equipment and storage medium
CN110705349A (en) * 2019-08-26 2020-01-17 深圳壹账通智能科技有限公司 Customer satisfaction recognition method, device, terminal and medium based on micro expression
CN111460112A (en) * 2020-03-02 2020-07-28 深圳壹账通智能科技有限公司 Online customer service consultation method, device, medium and electronic equipment

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20150121305A (en) * 2014-04-18 2015-10-29 현철우 System for consultation service upon online and method for consultation service upon online therefor

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108418981A (en) * 2018-03-16 2018-08-17 苏州思必驰信息科技有限公司 The method and device of dialogue service is provided for client
CN109015690A (en) * 2018-08-31 2018-12-18 中通天鸿（北京）通信科技股份有限公司 active interactive dialogue robot system and method
CN110472023A (en) * 2019-07-10 2019-11-19 深圳追一科技有限公司 Customer service switching method, device, computer equipment and storage medium
CN110705349A (en) * 2019-08-26 2020-01-17 深圳壹账通智能科技有限公司 Customer satisfaction recognition method, device, terminal and medium based on micro expression
CN111460112A (en) * 2020-03-02 2020-07-28 深圳壹账通智能科技有限公司 Online customer service consultation method, device, medium and electronic equipment

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114070937A (en) * 2021-11-10 2022-02-18 京东科技信息技术有限公司 Multi-modal client consultation method and related equipment
CN114117157A (en) * 2021-11-19 2022-03-01 招联消费金融有限公司 Session processing method, device, computer equipment and storage medium
CN114117157B (en) * 2021-11-19 2024-04-09 招联消费金融股份有限公司 Session processing method, apparatus, computer device and storage medium
CN114047995A (en) * 2021-11-25 2022-02-15 中国建设银行股份有限公司 Method, device and equipment for determining label color and storage medium
CN114710471A (en) * 2022-03-21 2022-07-05 京东科技信息技术有限公司 Network-based customer service voice communication method, device, electronic equipment and medium
CN115297078A (en) * 2022-07-06 2022-11-04 北京北信源软件股份有限公司 Consultation response method, consultation response device, computer equipment and storage medium
CN115297078B (en) * 2022-07-06 2023-09-01 北京北信源软件股份有限公司 Consultation response method, consultation response device, computer equipment and storage medium
CN115396389A (en) * 2022-07-07 2022-11-25 深圳市华汇数据服务有限公司 Internet of things information technology customer service system based on emotion energy perception
CN115396389B (en) * 2022-07-07 2023-09-22 深圳市华汇数据服务有限公司 Emotion energy perception-based Internet of things information technology customer service system
CN116112630A (en) * 2023-04-04 2023-05-12 成都新希望金融信息有限公司 Intelligent video face tag switching method

Also Published As

Publication number Publication date
CN111460112A (en) 2020-07-28

Similar Documents

Publication Publication Date Title
WO2021175007A1 (en) Online customer service consultation method and apparatus, medium, and electronic device
WO2020078300A1 (en) Method for controlling screen projection of terminal and terminal
WO2020147380A1 (en) Human-computer interaction method and apparatus, computing device, and computer-readable storage medium
CN112559865B (en) Information processing system, computer-readable storage medium, and electronic device
JP2019091429A (en) Method and apparatus for processing information
WO2021237923A1 (en) Smart dubbing method and apparatus, computer device, and storage medium
JP7250946B2 (en) Intent-driven contact center
US11269591B2 (en) Artificial intelligence based response to a user based on engagement level
US11250855B1 (en) Ambient cooperative intelligence system and method
WO2021114834A1 (en) Customer service question update method and system, terminal device, and computer storage medium
WO2021068493A1 (en) Method and apparatus for processing information
US11763318B2 (en) Systems and methods relating to providing chat services to customers
TWM607509U (en) Voice serving system
CN117176864A (en) Outbound communication data management method, system, medium and equipment based on AI
TWI782442B (en) An online interview method and system
CN111556096B (en) Information pushing method, device, medium and electronic equipment
WO2022105137A1 (en) Case handling method and apparatus, and computer device and computer-readable storage medium
WO2022012107A1 (en) Method and apparatus for displaying plug-in
CN114143344A (en) AI multimedia customer service system and application method
JP6944920B2 (en) Smart interactive processing methods, equipment, equipment and computer storage media
EP4055590A1 (en) Systems and methods for automating voice commands
CN107894972A (en) A kind of session tokens method, apparatus, aggregate server and storage medium
CN109471525A (en) Business handling method, apparatus, computer equipment and storage medium
CN112100338B (en) Dialog theme extension method, device and system for intelligent robot
JPH10293709A (en) Information processor and storage medium

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: 21763894

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

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 160123)

122 Ep: pct application non-entry in european phase

Ref document number: 21763894

Country of ref document: EP

Kind code of ref document: A1