Integrated customer service method and system based on multiple agents

Abstract

The invention relates to a multi-agent-based integrated customer service method and system, and the method comprises the steps: processing a consultation question proposed by an active incoming call user through a dialogue management agent, obtaining multi-dimensional data information, and generating a dialogue response of the consultation question according to the multi-dimensional data information; based on the feedback of the active incoming call user after the dialogue response, analyzing through an intention recognition agent to obtain the consultation intention of the active incoming call user; on the basis of the consultation intention and recent activity records of the active incoming call user, call-out operation needing to be executed is determined through a call-out decision agent; and the calling-out operation is executed through the calling-out execution agent. According to the method and the device, integrated customer service of multiple agents, collaborative division of labor of multiple different agents and specific business processes focused on the agents are realized, so that better service is provided for customers, customer data can be analyzed to actively call out to contact the customers, track customer problems or perform active marketing, and the satisfaction degree of the customers is effectively improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent customer service technology, and in particular to an integrated customer service method and system based on multiple agents. Background Art

[0002] With the rapid development of information technology, the communication needs between enterprises and customers are increasing, and customer service systems are playing an increasingly important role in enterprise operations. Early rule-based customer service systems were not intelligent enough, handled a single problem, and were unable to meet customer needs.

[0003] However, the existing agent-based customer service system also has limitations in flexibility, contextual understanding and emotional communication capabilities, and the knowledge base update is often delayed, making it difficult to generate high-quality answers based on specific customer questions. In addition, the traditional inbound customer service system mainly relies on the customer's active contact and lacks the ability to proactively serve customers. It is difficult to proactively track problems and actively market in limited customer interactions.

[0004] Currently, no effective solution has been proposed for the problem of how to improve the service capabilities of intelligent customer service in related technologies. Summary of the invention

[0005] The embodiments of the present application provide an integrated customer service method and system based on multiple agents to at least solve the problem of how to improve the service capabilities of intelligent customer service in related technologies.

[0006] In a first aspect, an embodiment of the present application provides an integrated customer service method based on multi-agents, the method comprising: Obtain consulting questions raised by active inbound users; The multi-dimensional data information of the active incoming user is obtained through the dialogue management agent, and a dialogue response to the consultation question is generated based on the multi-dimensional data information; Based on the feedback of the active incoming user after the dialogue response, the consultation intention of the active incoming user is obtained through intention recognition agent analysis; Based on the consultation intention and recent activity record of the active incoming user, determine the outgoing operation to be performed through the outgoing decision-making agent; The outgoing operation is executed by an outgoing execution agent to conduct an outgoing dialogue with the active incoming user.

[0007] In some embodiments, the method comprises: Analyzing the historical conversation records between the conversation management agent and the active incoming user through the knowledge management agent; If it is determined that the answer to the question given by the dialogue management agent does not match the consulting question raised by the active incoming user, the knowledge management agent marks the corresponding data entry in the knowledge base for manual modification, or makes suggestions for data supplement to the knowledge base.

[0008] In some embodiments, the method comprises: The dialogue management agent, the intention recognition agent, the outbound decision agent, the outbound execution agent and the knowledge management agent all iteratively optimize their respective execution strategies π under the premise of maximizing their respective value functions through reinforcement learning algorithms. i ( a | s ), where i represents the i-th agent, a is the state of the environment perceived by the agent, s An action performed by the agent.

[0009] In some embodiments, the multi-dimensional data information of the active incoming user obtained through the dialogue management agent processing includes: Converting the consultation questions of the active incoming user into streaming data; For streaming data that can be processed in real time by a voice activity detection model in a dialog management agent, the voice activity detection model is input for consumption to detect the start and end time points of effective speech in the consultation question; For streaming data that cannot be processed in real time by the voice activity detection model, it is not input into the voice activity detection model, but is consumed quickly through the data packets in the buffer; Then, the effective speech within the start and end time points is converted into natural language text through the automatic speech recognition model in the dialogue management agent, and the multi-dimensional data information of the active incoming user is obtained based on the natural language text.

[0010] In some embodiments, obtaining multidimensional data information of the active incoming user through dialog management agent processing, and generating a dialog response to the consultation question based on the multidimensional data information includes: Processing the consultation questions of the active incoming user through the dialogue management agent to obtain user data information, emotion data information and answer data information of the active incoming user; Based on the user data information, the emotion data information and the answer data information, a dialogue response to the consulting question is generated by the dialogue management agent.

[0011] In some embodiments, based on the user data information, the emotion data information and the answer data information, generating a dialogue response to the consulting question by the dialogue management agent includes: Based on the emotional data information, the dialogue management agent determines whether manual customer service is needed, and if so, transfers the case to manual customer service for processing; If not, a dialogue response to the consulting question is generated by the dialogue management agent based on the user data information and the answer data information.

[0012] In some embodiments, based on the feedback of the active incoming user after the dialogue response, the consultation intention of the active incoming user obtained by analyzing the intention recognition agent includes: Based on the feedback of the active incoming user after the dialogue response, determining whether the consultation problem of the active incoming user has been solved through the intention recognition agent; If not, continue to process the consultation questions of the active incoming user through the dialogue management agent; If so, the current conversation with the active incoming user is terminated, and based on the content of the current conversation, the consultation intention of the active incoming user is obtained through intention recognition agent analysis.

[0013] In some embodiments, based on the consultation intention and recent activity record of the actively calling user, determining the outbound operation to be performed by the outbound decision agent includes: Based on the consultation intention of the active incoming user, determine the task type of the outbound operation to be performed through the outbound decision agent, wherein the task type includes coupon issuance, renewal reminder and product promotion; Based on the recent activity record of the active incoming user, the execution of the outgoing operation is triggered by the outgoing decision-making agent.

[0014] In some embodiments, executing the outgoing operation by an outgoing execution agent to conduct an outgoing dialogue with the active incoming user includes: In the case where the outbound decision agent triggers an outbound operation, based on the user contact information provided by the outbound decision agent and the task type of the outbound operation, the outbound operation is executed by the outbound execution agent to conduct an outbound dialogue with the active incoming user.

[0015] In a second aspect, an embodiment of the present application provides an integrated customer service system based on multiple agents, the system being used for the method described in the first aspect above, the system comprising a dialogue management module, a knowledge management module, an intention recognition module, an outbound decision module, and an outbound execution module; The dialogue management module is used to obtain the consulting questions raised by the active incoming user, obtain the multi-dimensional data information of the active incoming user through the dialogue management agent, and generate the dialogue response to the consulting question based on the multi-dimensional data information; The knowledge management module is used to analyze the historical conversation records between the dialogue management agent and the active incoming user through the knowledge management agent; if it is determined that the answer to the question given by the dialogue management agent does not match the consulting question raised by the active incoming user, the knowledge management agent is used to mark the corresponding data entry in the knowledge base for manual modification, or to make suggestions for data supplement to the knowledge base; The intention recognition module is used to obtain the consultation intention of the active incoming user through intention recognition agent analysis based on the feedback of the active incoming user after the dialogue response; The outbound call decision module is used to determine the outbound call operation to be performed through the outbound call decision agent according to the consultation intention and recent activity record of the active incoming call user; The outgoing call execution module is used to execute the outgoing call operation through the outgoing call execution agent to conduct an outgoing call dialogue with the active incoming call user.

[0016] Compared with the related art, the embodiment of the present application provides an integrated customer service method and system based on multiple agents, wherein the method obtains consulting questions raised by active incoming users; obtains multi-dimensional data information of active incoming users through dialogue management agent processing, and generates dialogue responses to consulting questions based on the multi-dimensional data information; obtains the consulting intention of the active incoming users through intention recognition agent analysis based on the feedback of the active incoming users after the dialogue response; determines the outgoing operation to be performed through the outgoing decision agent based on the consulting intention and recent activity records of the active incoming users; performs the outgoing operation through the outgoing execution agent to conduct an outgoing dialogue with the active incoming users, thereby realizing integrated customer service of multiple agents, collaborative division of labor among multiple different agents, each focusing on its specific business process, such as context understanding, sentiment analysis, knowledge updating, intention understanding, etc., so as to provide customers with more professional and personalized services, and can also actively call out to contact customers by analyzing customer data, track customer problems or conduct proactive marketing, which can effectively improve customer satisfaction, help to establish more stable customer relationships, and solve the problem of how to improve the service capabilities of intelligent customer service. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1is a flowchart of the steps of the integrated customer service method based on multiple agents according to an embodiment of the present application; Figure 2 is a structural diagram of an integrated customer service system based on multiple agents according to an embodiment of the present application; Figure 3 It is a schematic diagram of the internal structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0019] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0020] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0021] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantity limitation, and may indicate the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0022] The present application embodiment provides an integrated customer service method based on multi-agents. Figure 1 is a flowchart of the steps of the integrated customer service method based on multiple agents according to an embodiment of the present application, such as Figure 1 As shown, the method includes: Step S102, obtaining the consulting question raised by the active incoming user; Step S104, obtaining multi-dimensional data information of the active incoming user through the dialogue management agent, and generating a dialogue response to the consultation question based on the multi-dimensional data information; Step S104 specifically includes the following steps: Step S1041, converting the consultation questions of the active incoming user into streaming data; Step S1042: For streaming data that can be processed in real time by the voice activity detection model in the dialogue management agent, the streaming data is input into the voice activity detection model for consumption to detect the start and end time points of the effective speech in the consultation question; Step S1043, for streaming data that cannot be processed in real time by the voice activity detection model, the streaming data is not input into the voice activity detection model, but is consumed quickly by the data packets in the buffer; Step S1044, through the automatic speech recognition model in the dialogue management intelligent agent, the effective speech within the start and end time points is converted into natural language text, and the multi-dimensional data information of the active incoming user is obtained based on the natural language text, wherein the multi-dimensional data information includes user data information, emotion data information and answer data information.

[0023] It should be noted that Figure 2 is a schematic diagram of the structure of an integrated customer service system based on multiple agents according to an embodiment of the present application. Figure 2 As shown in the figure, the dialogue management agent is responsible for handling the consultations and questions raised by customers over the phone. The agent integrates streaming VAD technology, which can monitor the customer's voice input in real time. When the customer asks a question, the ASR technology (automatic speech recognition) is used to first recognize the audio as natural language, then quickly find the most appropriate answer by matching the data in the internal knowledge base and database, and finally the answer is processed by TTS technology (text to audio) and returned to the telephone link to be played for the customer to listen to.

[0024] It should be further explained that the main function of the VAD (Voice Activity Detection) model is to detect the start and end time point information of valid speech in the input audio, and input the detected valid audio segments into the recognition engine for recognition, thereby reducing recognition errors caused by invalid speech. This embodiment uses a voice activity detection model based on the FSMN architecture (Feed-forward Sequential Memory Network), which can effectively capture long-distance sequence dependencies, which is particularly important for long-term characteristics in speech signals. At the same time, the model has a fast inference speed and is suitable for determining the end point of customer audio in streaming recognition scenarios.

[0025] In the process of converting the customer's consultation questions - telephone signal data packets (RTP, Real-time Transport Protocol) into streaming VAD model input data, since the receiving speed of RTP is much faster than the processing speed of RTP, the unprocessed RTP will be temporarily stored in the receiving buffer allocated by the operating system for the socket. However, during the processing of the streaming VAD model, the RTP packets in the system buffer interfere with the process link, mainly the impact of RTP buffering on VAD recognition, which makes the VAD model tail point redundantly recognized. Therefore, this embodiment designs a fast consumption solution for the RTP buffer, that is, the data packets of the non-buffer are input into the VAD model for consumption; the data packets of the buffer are consumed quickly without passing through the VAD model, so that the link can accurately handle customer problems.

[0026] It should be further explained that the main function of the ASR (Automatic Speech Recognition) model is to convert customer speech into human natural language for subsequent matching model query answers. This patent adopts an end-to-end speech recognition framework. Based on the original knowledge of the model, the model is fine-tuned using the customer conversation audio accumulated by the business, making the model's recognition effect more accurate, providing an important foundation for the processing of subsequent processes.

[0027] Step S1045, based on the user data information, emotion data information and answer data information, a dialogue response to the consulting question is generated through the dialogue management agent.

[0028] Specifically, step S1045 determines whether manual customer service is needed based on the emotional data information through the dialogue management agent, and if so, transfers the call to manual customer service for processing; If not, a dialogue response to the consultation question is generated by the dialogue management agent based on the user data information and the answer data information.

[0029] It should be noted that the dialogue management agent also has emotion recognition capabilities and can analyze the emotional fluctuations in customer questions. If it detects that the customer is emotionally agitated or the problem is complex and requires human intervention, the agent will transfer the matter to manual customer service to ensure that the customer receives more personalized service. Step S106, based on the feedback of the active incoming user after the dialogue response, the consultation intention of the active incoming user is obtained through the intention recognition agent analysis; Specifically, step S106 determines, based on the feedback of the active incoming user after the dialogue response, whether the consultation problem of the active incoming user has been solved through the intention recognition agent; if not, continue to process the consultation problem of the active incoming user through the dialogue management agent; if so, end the current conversation with the active incoming user, and based on the content of the current conversation, obtain the consultation intention of the active incoming user through the intention recognition agent analysis.

[0030] It should be noted that if Figure 2 As shown in the figure, the intent recognition agent plays a vital role both during and after the customer's incoming call. During the conversation, by analyzing the customer's input, it is determined whether the customer's inquiry has been fully answered, and then it is decided whether the current call needs to be ended. After the call is over, the content of the entire call is identified and analyzed, and the customer's inquiry intention is classified and identified, such as whether to purchase a new package, renew an existing service, or inquire about available discounts and problems that require manual assistance. The intent classification identified by the incoming call intent recognition agent provides decision support for subsequent collaborative outbound services to ensure that customer needs are fully met.

[0031] Step S108, based on the consultation intention and recent activity record of the active incoming user, the outgoing decision agent determines the outgoing operation to be performed; Specifically, step S108 determines the task type of the outgoing operation to be performed based on the consultation intention of the active incoming user through the outgoing decision-making agent, wherein the task types include coupon issuance, renewal reminders and product promotion; and triggers the execution of the outgoing operation through the outgoing decision-making agent based on the recent activity record of the active incoming user.

[0032] It should be noted that if Figure 2 As shown, the outbound decision agent is responsible for analyzing the customer's incoming call intention, the customer's recent activity records, and comparing it with the preset task types (such as issuing coupons, reminding renewals, or promoting packages, etc.) to determine whether an outbound call operation is required. For example, in the inbound call mode, the customer inquires about product renewals, and the dialogue management agent will provide immediate renewal guidance. If the customer's renewal operation has not been completed within the preset working day, the outbound decision agent will capture this behavioral data and determine whether an outbound call operation is required. Once it is determined that an outbound call is required, the outbound execution agent will proactively contact the customer according to the instructions of the outbound decision agent to remind them to renew or provide further assistance to ensure service continuity and improve customer satisfaction.

[0033] Step S110, executing an outgoing operation through an outgoing execution agent to conduct an outgoing dialogue with the active incoming user.

[0034] Specifically, in step S110, when the outgoing decision agent triggers an outgoing operation, based on the user contact information provided by the outgoing decision agent and the task type of the outgoing operation, the outgoing operation is executed by the outgoing execution agent to conduct an outgoing dialogue with the active incoming user.

[0035] It should be noted that if Figure 2 As shown in the figure, the outbound call execution agent is responsible for executing specific outbound call operations based on the customer contact information and preset tasks provided by the outbound call decision agent. Preset tasks include issuing coupons, reminding renewals, promoting packages, or assisting customers in operations. The outbound call execution agent uses streaming VAD technology and dialogue intent recognition capabilities to perform corresponding operations for the tasks specified by the outbound call decision agent, ensuring that customers can successfully complete the set operations, thereby achieving efficient interaction with customers.

[0036] Through the above steps in the embodiment of the present application, the integrated processing of incoming and outgoing calls is realized to improve the customer experience, efficiency and quality of intelligent services. Not only can it timely resolve customer emotions and effectively solve customer problems, but it can also continue to pay attention to and respond to subsequent feedback from customers, thereby enhancing customer satisfaction, reducing the risk of customer churn, and enhancing the market competitiveness of products. The results of different intelligent body modules are integrated in the form of data streams, and reinforcement learning technology is used to enhance the learning and understanding ability of the intelligent body, so that it can more accurately identify and meet customer needs and provide customized solutions. In the process of providing solutions, the intelligent body will make outgoing calls in a timely manner according to the customer's response and interaction, ensuring the continuity and initiative of the service, thereby achieving effective communication and problem solving with customers. In addition, the method will also continuously optimize the question-and-answer knowledge base based on customer feedback, improve the problem-solving rate, and improve the quality of service through continuous learning and adaptation to adapt to the ever-changing customer needs and market environment.

[0037] In some embodiments, such as Figure 2 As shown, the integrated customer service method based on multiple agents also includes a knowledge management agent; The knowledge management agent analyzes the historical conversation records between the dialogue management agent and the active incoming user; if it is determined that the answer to the question given by the dialogue management agent does not match the consulting question raised by the active incoming user, the knowledge management agent marks the corresponding data entry in the knowledge base for manual modification, or makes suggestions for data supplement to the knowledge base.

[0038] It should be noted that the knowledge management agent undertakes the important task of carefully evaluating the quality and comprehensiveness of answers in historical conversations. By analyzing the historical conversation records between the inbound conversation management agent and the customer, it carefully checks whether the answers in the knowledge base match the questions raised by the customer. When it is found that the answers in the knowledge base are incorrect or incomplete, the agent will mark these entries for manual review and modification to ensure that the information provided to the customer is accurate and reliable. If the knowledge base lacks answers to certain questions, the agent will make supplementary suggestions and submit them for manual review to ensure that the knowledge base can fully cover the questions that customers may ask, so as to avoid "hallucination questions", that is, wrong or fictitious answers generated by the large model without sufficient information support. Through these operations, the agent can make necessary additions and modifications to the knowledge base in a timely manner, improve the accuracy and coverage of the knowledge base, and ensure that higher quality and more comprehensive answers can be provided in subsequent conversations.

[0039] In some of the embodiments, during the operation of the dialogue management agent, the intention recognition agent, the outbound decision agent, the outbound execution agent, and the knowledge management agent in the above embodiments, each agent continuously performs self-adaptation and self-learning to improve its own processing capabilities. Specifically: The dialogue management agent, intent recognition agent, outbound decision agent, outbound execution agent, and knowledge management agent all use reinforcement learning algorithms to iteratively optimize their respective execution strategies π while maximizing their respective value functions. i ( a | s ), where i represents the i-th agent, a is the state of the environment perceived by the agent, s An action performed by the agent.

[0040] It should be noted that the improvement of the capabilities of multiple agents is optimized through the idea of ​​reinforcement learning. In a multi-agent environment, each agent has its own strategy π i and the value function Q i (s, a), the goal of the agent is to maximize its cumulative reward, corresponding to improving indicators such as customer satisfaction and conversion rate. For each agent i, update its value function:

[0041] Among them, s represents the state of the environment perceived by the agent; a represents the action that the agent can perform; y represents the discount factor of future rewards, and then the value function is used to improve the strategy to obtain the maximum value of each agent: .

[0042] Through the above-mentioned multi-agent linkage reinforcement learning, the capabilities of the entire multi-agent system are improved: ① the agents learn how to coordinate incoming and outgoing tasks more effectively, thereby providing more efficient intelligent scheduling solutions; ② the agents are able to adapt to the strategy changes of other agents; ③ the system remains stable in the face of environmental changes or unexpected behaviors of other agents.

[0043] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0044] The embodiment of the present application provides an integrated customer service system based on multi-agents, which includes a dialogue management module, a knowledge management module, an intention recognition module, an outbound decision module and an outbound execution module; The dialogue management module is used to obtain the consulting questions raised by the active incoming users, obtain the multi-dimensional data information of the active incoming users through the dialogue management intelligent agent, and generate dialogue responses to the consulting questions based on the multi-dimensional data information; The knowledge management module is used to analyze the historical conversation records between the dialogue management agent and the active incoming user through the knowledge management agent; if it is determined that the answer to the question given by the dialogue management agent does not match the consulting question raised by the active incoming user, the knowledge management agent marks the corresponding data entry in the knowledge base for manual modification, or proposes data supplement suggestions for the knowledge base; The intention recognition module is used to obtain the consultation intention of the active incoming user through the intention recognition agent analysis based on the feedback of the active incoming user after the dialogue response; The outbound decision module is used to determine the outbound operation to be performed through the outbound decision agent based on the consultation intention and recent activity records of the active inbound user; The outgoing call execution module is used to execute the outgoing call operation through the outgoing call execution agent to conduct an outgoing call dialogue with the active incoming user.

[0045] Through the dialogue management module, intent recognition module, outbound decision module and outbound execution module in the embodiments of the present application, integrated customer service of multiple intelligent agents is realized, and the collaborative division of labor of multiple different intelligent agents is achieved. Each intelligent agent focuses on its specific business process, such as context understanding, sentiment analysis, knowledge updating, intent understanding, etc., so as to provide customers with more professional and personalized services. In addition, by analyzing customer data, the agent can proactively call out to contact customers, track customer issues or conduct proactive marketing, which can effectively improve customer satisfaction, help establish more stable customer relationships, and solve the problem of how to improve the service capabilities of intelligent customer service.

[0046] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0047] This embodiment further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0048] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0049] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0050] In addition, in combination with the integrated customer service method based on multiple agents in the above embodiments, the present application embodiment can provide a storage medium for implementation. The storage medium stores a computer program; when the computer program is executed by a processor, any one of the integrated customer service methods based on multiple agents in the above embodiments is implemented.

[0051] In one embodiment, a computer device is provided, which may be a terminal. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, an integrated customer service method based on multiple agents is implemented. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball, or touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0052] In one embodiment, Figure 3 is a schematic diagram of the internal structure of an electronic device according to an embodiment of the present application, such as Figure 3 As shown, an electronic device is provided, which may be a server, and its internal structure diagram may be as shown in Figure 3 As shown. The electronic device includes a processor, a network interface, an internal memory and a non-volatile memory connected through an internal bus, wherein the non-volatile memory stores an operating system, a computer program and a database. The processor is used to provide computing and control capabilities, the network interface is used to communicate with an external terminal through a network connection, the internal memory is used to provide an environment for the operation of the operating system and the computer program, the computer program is executed by the processor to implement an integrated customer service method based on multiple agents, and the database is used to store data.

[0053] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0054] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0055] Those skilled in the art should understand that the technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0056] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. An integrated customer service method based on multi-agents, characterized in that: The method comprises: Obtain consulting questions raised by active inbound users; The multi-dimensional data information of the active incoming user is obtained through the dialogue management agent, and a dialogue response to the consultation question is generated based on the multi-dimensional data information; Based on the feedback of the active incoming user after the dialogue response, the consultation intention of the active incoming user is obtained through intention recognition agent analysis; Based on the consultation intention and recent activity record of the active incoming user, determine the outgoing operation to be performed through the outgoing decision-making agent; The outgoing operation is executed by an outgoing execution agent to conduct an outgoing dialogue with the active incoming user.

2. The method according to claim 1, characterized in that The method comprises: Analyzing the historical conversation records between the conversation management agent and the active incoming user through the knowledge management agent; If it is determined that the answer to the question given by the dialogue management agent does not match the consulting question raised by the active incoming user, the knowledge management agent marks the corresponding data entry in the knowledge base for manual modification, or makes suggestions for data supplement to the knowledge base.

3. The method according to claim 2, characterized in that The method comprises: The dialogue management agent, the intention recognition agent, the outbound decision agent, the outbound execution agent and the knowledge management agent all iteratively optimize their respective execution strategies π under the premise of maximizing their respective value functions through reinforcement learning algorithms. i ( a | s ), where i represents the i-th agent, a is the state of the environment perceived by the agent, s An action performed by the agent.

4. The method according to claim 1, characterized in that The multi-dimensional data information of the active incoming user obtained by the dialogue management agent includes: Converting the consultation questions of the active incoming user into streaming data; For streaming data that can be processed in real time by a voice activity detection model in a dialog management agent, the voice activity detection model is input for consumption to detect the start and end time points of effective speech in the consultation question; For streaming data that cannot be processed in real time by the voice activity detection model, it is not input into the voice activity detection model, but is consumed quickly through the data packets in the buffer; Then, the effective speech within the start and end time points is converted into natural language text through the automatic speech recognition model in the dialogue management agent, and the multi-dimensional data information of the active incoming user is obtained based on the natural language text.

5. The method according to claim 1, characterized in that: The multi-dimensional data information of the active incoming user is obtained by processing the dialogue management agent, and the dialogue response to the consultation question is generated based on the multi-dimensional data information, including: Processing the consultation questions of the active incoming user through the dialogue management agent to obtain user data information, emotion data information and answer data information of the active incoming user; Based on the user data information, the emotion data information and the answer data information, a dialogue response to the consulting question is generated by the dialogue management agent.

6. The method according to claim 5, characterized in that Generating a dialogue response to the consulting question by the dialogue management agent based on the user data information, the emotion data information and the answer data information includes: Based on the emotional data information, the dialogue management agent determines whether manual customer service is needed, and if so, transfers the case to manual customer service for processing; If not, a dialogue response to the consulting question is generated by the dialogue management agent based on the user data information and the answer data information.

7. The method according to claim 1, characterized in that Based on the feedback of the active incoming user after the dialogue response, the consultation intention of the active incoming user obtained by the intention recognition agent analysis includes: Based on the feedback of the active incoming user after the dialogue response, determining whether the consultation problem of the active incoming user has been solved through the intention recognition agent; If not, continue to process the consultation questions of the active incoming user through the dialogue management agent; If so, the current conversation with the active incoming user is terminated, and based on the content of the current conversation, the consultation intention of the active incoming user is obtained through intention recognition agent analysis.

8. The method according to claim 1, characterized in that: Based on the consultation intention and recent activity record of the active incoming call user, the outgoing call decision agent determines that the outgoing call operation to be performed includes: Based on the consultation intention of the active incoming user, determine the task type of the outbound operation to be performed through the outbound decision agent, wherein the task type includes coupon issuance, renewal reminder and product promotion; Based on the recent activity record of the active incoming user, the execution of the outgoing operation is triggered by the outgoing decision-making agent.

9. The method according to claim 8, characterized in that Executing the outgoing operation through an outgoing execution agent to conduct an outgoing dialogue with the active incoming user includes: In the case where the outbound decision agent triggers an outbound operation, based on the user contact information provided by the outbound decision agent and the task type of the outbound operation, the outbound operation is executed by the outbound execution agent to conduct an outbound dialogue with the active incoming user.

10. An integrated customer service system based on multi-agents, characterized in that: The system is used to execute the method according to any one of claims 1 to 9, and the system includes a dialogue management module, a knowledge management module, an intention recognition module, an outbound decision module and an outbound execution module; The dialogue management module is used to obtain the consulting questions raised by the active incoming user, obtain the multi-dimensional data information of the active incoming user through the dialogue management agent, and generate the dialogue response to the consulting question based on the multi-dimensional data information; The knowledge management module is used to analyze the historical conversation records between the dialogue management agent and the active incoming user through the knowledge management agent; if it is determined that the answer to the question given by the dialogue management agent does not match the consulting question raised by the active incoming user, the knowledge management agent is used to mark the corresponding data entry in the knowledge base for manual modification, or to make suggestions for data supplement to the knowledge base; The intention recognition module is used to obtain the consultation intention of the active incoming user through intention recognition agent analysis based on the feedback of the active incoming user after the dialogue response; The outbound call decision module is used to determine the outbound call operation to be performed through the outbound call decision agent according to the consultation intention and recent activity record of the active incoming call user; The outgoing call execution module is used to execute the outgoing call operation through the outgoing call execution agent to conduct an outgoing call dialogue with the active incoming call user.

Images