Intelligent drill system, method, medium, terminal and program product based on RAG technology

Abstract

The application provides an intelligent rehearsal system, method, medium, terminal and program product based on RAG technology. The system comprises: a knowledge base construction module for constructing a private domain knowledge base of the insurance industry based on RAG technology; a rehearsal mode construction module for constructing a progressive rehearsal mode based on the Bloom's Taxonomy of Educational Objectives, classifying the data corresponding to the constructed rehearsal mode into a library, and linking to the corresponding private domain knowledge base according to the category of the rehearsal mode; a virtual customer creation module for creating a virtual customer in an insurance business scenario according to the category of the rehearsal mode; a retrieval generation module for retrieving the private domain knowledge base based on RAG technology and according to the dialogue content generated by the virtual customer, generating corresponding prompt content, and inputting the prompt content into a large language model to generate response content corresponding to each category of rehearsal mode. The system of the application can improve the training efficiency of insurance agents and reduce the training cost.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, in particular to an intelligent rehearsal system and method based on RAG technology, a medium, a terminal and a program product. BACKGROUND

[0002] In the current training mode of insurance agents, the insurance agent needs to conduct offline one-on-one rehearsal with the supervisor until passing the examination, so as to achieve the training goal.

[0003] From the effect of training, due to the uneven quality and level of supervisors, and the different standards for passing the course, the passing effect of insurance agents in the actual rehearsal process is affected. From the efficiency of training, the supervisor needs to spend a fixed time to conduct face-to-face simulation interviews with the agent. Since one supervisor needs to train multiple insurance agents, this process consumes a lot of time and energy of the supervisor. At the same time, the insurance agent needs to make an appointment in advance for the time and place of the supervisor's training, which has high communication cost and cannot be rehearsed anytime and anywhere, and it is difficult to repeat the rehearsal. From the data retention, the rehearsal process is difficult to retain and cannot be traced and analyzed as subsequent data.

[0004] Therefore, it is necessary to provide an intelligent rehearsal system and method based on RAG technology, a medium, a terminal and a program product to solve the above problems existing in the prior art. SUMMARY

[0005] In view of the above-mentioned shortcomings of the prior art, the purpose of the present application is to provide an intelligent rehearsal system and method based on RAG technology, a medium, a terminal and a program product, which are used to solve the technical problems of low efficiency and high cost of the traditional training mode of insurance agents.

[0006] To achieve the above-mentioned purposes and other related purposes, the first aspect of the present application provides an intelligent rehearsal system based on RAG technology, which comprises:

[0007] A knowledge base construction module is configured to construct a private domain knowledge base of the insurance industry based on RAG technology, wherein the private domain knowledge base comprises professional knowledge of the insurance industry, sales construction strategies, customer portrait problem solving strategies and laws and regulations of the insurance industry.

[0008] A rehearsal mode construction module is configured to construct a progressive rehearsal mode based on the Bloom's Taxonomy of Educational Objectives, to sort and classify the data corresponding to the constructed rehearsal mode into a library, and to link the rehearsal mode to the corresponding private domain knowledge base according to the category of the rehearsal mode.

[0009] a virtual customer creation module configured to create a virtual customer in an insurance business scenario according to a category of the rehearsal mode; the virtual customer is configured to generate dialogue content in the insurance business scenario;

[0010] a retrieval generation module configured to retrieve corresponding prompt content from the private domain knowledge base based on a RAG technique and according to the dialogue content generated by the virtual customer, input the prompt content into a large language model to generate response content corresponding to each category of the rehearsal mode.

[0011] In some embodiments of the first aspect of the present application, the retrieval generation module comprises: a context perception unit configured to analyze and understand the questions, demands and intentions of the virtual customer in the current dialogue context; a retrieval unit configured to retrieve relevant knowledge and information in the current dialogue context from the private domain knowledge base according to the questions, demands and intentions of the virtual customer perceived by the context perception unit; a thought and strategy suggestion unit configured to generate thought and strategy suggestions for the trainee based on the relevant knowledge and information in the current dialogue context retrieved.

[0012] In this way, the real intention behind the question raised by the virtual customer is first perceived, and then relevant knowledge and information are retrieved from the private domain knowledge base according to the perceived real intention, so that the generated thought and strategy suggestions can be more in line with the real needs of the virtual customer, providing more professional and personalized services for the customer and winning the recognition of the customer for the trainee.

[0013] In some embodiments of the first aspect of the present application, the knowledge base construction module comprises: a data acquisition unit configured to collect raw data related to various business scenarios of the insurance industry from internal and / or external sources; a data processing unit configured to format the acquired raw data to convert it into the same file format; a vectorization unit configured to convert the formatted text data in the same file format into a vector matrix based on a vector model; a data warehousing unit configured to construct an index for the data vectorized based on the vector matrix and write it into a database to form the private domain knowledge base of the insurance industry.

[0014] In some embodiments of the first aspect of the present application, the rehearsal mode comprises any one or more of the following: a learning mode, a practice mode and a test mode; in the learning mode, the retrieval generation module generates standard dialogues for the trainee to learn to respond to the dialogue content generated by the virtual customer; the practice mode is switched from the learning mode, and the practice mode is used for the trainee to practice dialogue with the virtual customer in various insurance business scenarios; the test mode is switched from the practice mode, and the test mode is used to test the trainee's dialogue with the virtual customer in various insurance business scenarios.

[0015] In some embodiments of the first aspect of the application, the system is further configured with a trainee interactive interface configured to display an interactive conversation between a trainee and the virtual customer.

[0016] In some embodiments of the first aspect of the application, the system further comprises a virtual scene construction module for constructing various insurance business scenes for the virtual customer to converse with the trainee, the virtual scene construction module at least comprising a VR generation device for simulating a scene according to the age, gender, and occupation of the virtual customer and outputting a simulated practical scene.

[0017] To achieve the above object and other related objects, the second aspect of the present application provides an intelligent drilling method based on RAG technology, the method comprising:

[0018] An insurance industry private domain knowledge base is constructed based on RAG technology, the private domain knowledge base including professional knowledge of the insurance industry, sales construction strategies, customer portrait problem solving strategies, and laws and regulations of the insurance industry;

[0019] A progressive drilling mode based on Bloom's teaching goal principle is constructed, the data corresponding to the constructed drilling mode is sorted and classified into a library, and is linked to the corresponding private domain knowledge base according to the category of the drilling mode;

[0020] A virtual customer in an insurance business scene is created according to the category of the drilling mode; the virtual customer is configured to generate conversation content in the insurance business scene;

[0021] Based on RAG technology and according to the conversation content generated by the virtual customer, corresponding prompt content is retrieved from the private domain knowledge base, and the prompt content is input into a large language model to generate response content corresponding to each category of drilling mode.

[0022] To achieve the above object and other related objects, the third aspect of the present application provides a computer readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the method.

[0023] To achieve the above object and other related objects, the fourth aspect of the present application provides a computer program product comprising computer program code, when the computer program code is run on a computer, the computer program code causes the computer to implement the method.

[0024] To achieve the above object and other related objects, the fifth aspect of the present application provides an electronic terminal comprising a memory, a processor, and a computer program stored on the memory; the processor executes the computer program to implement the method.

[0025] As described above, the intelligent rehearsal system, method, medium, terminal and program product based on RAG technology of the present application have the following beneficial effects:

[0026] By constructing a private domain knowledge base of the insurance industry using RAG technology, and based on the Bloom's Taxonomy, a rehearsal mode is constructed. The data corresponding to the constructed rehearsal mode is sorted and classified into a library, and is linked to the corresponding private domain knowledge base according to the category of the rehearsal mode. At the same time, a plurality of virtual customers in the insurance business scenario are created according to the classification category of the rehearsal mode. Then, based on the RAG technology and according to the dialogue content generated by the virtual customers, the corresponding prompt content is retrieved from the private domain knowledge base and generated. The prompt content is input into a large language model to generate the response content corresponding to each category of rehearsal mode. This system not only improves the training efficiency and quality of insurance agents, but also reduces the cost of training, helps to improve the professional quality and working ability of insurance agents, realizes the comprehensive training of insurance agents from knowledge memory to creation, and at the same time, by constructing a private domain knowledge base, the system can provide more comprehensive training content to ensure that insurance agents master the latest market trends and industry trends, and enhance their professional quality and competitiveness. BRIEF DESCRIPTION OF DRAWINGS

[0027] Figure 1 The figure shows the framework schematic diagram of the intelligent rehearsal system based on RAG technology in an embodiment of the present application.

[0028] Figure 2 The figure shows the principle schematic diagram of the intelligent rehearsal system based on RAG technology in an embodiment of the present application.

[0029] Figure 3 The figure shows the application scenario schematic diagram of the intelligent rehearsal system based on RAG technology in an embodiment of the present application.

[0030] Figure 4 The figure shows the flow schematic diagram of the intelligent rehearsal method based on RAG technology in an embodiment of the present application.

[0031] Figure 5 The figure shows the structure schematic diagram of the electronic terminal in an embodiment of the present application. DETAILED DESCRIPTION

[0032] The embodiments of the present application are described below through specific and concrete examples, and those skilled in the art can easily understand other advantages and effects of the present application from the disclosure of the present specification. The present application can also be implemented or applied by different specific embodiments, and the details in the specification can be modified or changed based on different views and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0033] In the embodiments of the present application, the same items or similar items with basically the same functions and effects are distinguished by using "first", "second", and the like. For example, first XX and second XX are only used to distinguish different XXs, and do not limit the order. Those skilled in the art can understand that "first", "second", and the like do not limit the number and execution order, and "first", "second", and the like do not necessarily mean different.

[0034] It should be noted that in the embodiments of the present application, "exemplary" or "for example" means an example, illustration or description. Any embodiment or design scheme described as "exemplary" or "for example" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the use of "exemplary" or "for example" is intended to present the relevant concept in a specific manner.

[0035] In the embodiments of the present application, "at least one" means one or more, and "multiple" means two or more. "And / or" describes the association between the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the following three cases: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after it. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b or c can represent a, b, c, a-b, a-c, b-c or a-b-c, where a, b and c can be single or multiple.

[0036] Before further detailing the present application, the terms and terms involved in the embodiments of the present application are explained, and the terms and terms involved in the embodiments of the present application are applicable to the following explanations:

[0037] <1> RAG (Retrieval-Augmented Generation) technology: an artificial intelligence technology that combines information retrieval technology and language generation model. This technology retrieves relevant information from an external knowledge base and inputs it as a prompt to a large language model (LLM) to enhance the model's ability to handle knowledge-intensive tasks such as question answering, text summarization, and content generation.

[0038] <2> Large Language Model (LLM): A type of artificial intelligence model that relies on vast amounts of text data for training and can perform a variety of tasks, including text summarization, translation, and sentiment analysis. These models typically contain billions of parameters and are able to capture complex patterns in language data. Most LLMs are based on deep learning architectures such as Transformers, which have demonstrated superior performance in various natural language processing tasks.

[0039] To facilitate understanding of the embodiments of the present application, first, in combination with Figure 1 Detailed description. Figure 1 A framework diagram of an intelligent rehearsal system based on RAG technology in an embodiment of the present application is shown. The intelligent rehearsal system based on RAG technology 100 in the embodiment includes:

[0040] A knowledge base construction module 101 for constructing a private domain knowledge base of the insurance industry based on RAG technology, the private domain knowledge base including professional knowledge of the insurance industry, sales construction strategies, customer portrait problem solving strategies, pre-set problem solving strategies, and laws and regulations of the insurance industry;

[0041] A rehearsal mode construction module 102 for constructing a progressive rehearsal mode based on Bloom's teaching goal principle, sorting and classifying the data corresponding to the constructed rehearsal mode into a library, and linking to the corresponding private domain knowledge base according to the category of the rehearsal mode;

[0042] A virtual customer creation module 103 for creating a plurality of virtual customers in an insurance business scenario according to the category of the rehearsal mode; the virtual customers are configured to generate dialogue content in the insurance business scenario;

[0043] A retrieval generation module 104 for retrieving corresponding prompt content from the private domain knowledge base based on RAG technology and according to the dialogue content generated by the virtual customer, inputting the prompt content into a large language model to generate response content corresponding to each category of rehearsal mode.

[0044] By utilizing the RAG technology to construct a private domain knowledge base containing the professional knowledge of the insurance industry, sales building strategies, customer portrait problem solving strategies, and laws and regulations of the insurance industry, and based on the Bloom's Taxonomy of Educational Objectives, a practice mode is constructed. The data corresponding to the constructed practice mode is sorted and classified into a library, and the practice mode is classified into learning mode, practice mode and test mode. According to the classification category, it is linked to the corresponding private domain knowledge base, and according to the classification category of the practice mode, a virtual customer in the insurance business scenario is created. The virtual customer is configured to generate dialogue content in each insurance business scenario, and then based on the RAG technology and according to the dialogue content generated by the virtual customer, the corresponding prompt content is retrieved from the private domain knowledge base to generate the corresponding response content corresponding to each category of practice mode. The system not only improves the training efficiency and quality of insurance agents, but also reduces the cost of training, helps to improve the professional quality and working ability of insurance agents, realizes the comprehensive training of insurance agents from knowledge memory to creation, and at the same time, by constructing a private domain knowledge base, the system can provide more comprehensive training content to ensure that insurance agents master the latest market trends and industry trends, and enhance their professional quality and competitiveness.

[0045] It should be understood that Bloom's Taxonomy of Educational Objectives is divided into six stages of knowledge, understanding, application, analysis, evaluation and creation, which is also applicable to insurance agent training. Specific examples of applying Bloom's Taxonomy of Educational Objectives to insurance agent training are as follows:

[0046] (1) Knowledge: This stage requires insurance agents to be able to recall or identify information. For example, when training new products, insurance agents need to remember the basic functions and features of the product.

[0047] (2) Understanding: This stage emphasizes the insurance agent's preliminary understanding of information, and is able to restate concepts or make simple explanations in their own words. For example, when understanding company policies, insurance agents should be able to explain the main points of the policy and its impact on their work.

[0048] (3) Application: In this stage, insurance agents need to apply what they have learned to their actual work. For example, after learning sales techniques, insurance agents should be able to use these techniques in actual sales to improve sales performance.

[0049] (4) Analysis: This stage requires insurance agents to be able to analyze information and identify relationships between materials. In insurance agent training, this may involve case studies, allowing insurance agents to analyze the best course of action in different situations.

[0050] (5) Synthesis: In this stage, insurance agents are encouraged to integrate multiple sources of information or concepts into a new whole, such as developing a marketing plan, combining different technologies and resources to achieve specific marketing goals.

[0051] (6) Evaluation: This is the highest level of learning stage, which requires insurance agents to evaluate and critically think about information or situations. In insurance agent training, the evaluation ability of insurance agents can be trained through simulated decision-making scenarios, enabling them to judge and select the effectiveness of various strategies.

[0052] It should be noted that the data contained in the private domain knowledge base is simulated customer data based on real data structure. These data are desensitized to ensure the safety of customer information and the compliance of data. The private domain knowledge base also includes historical successful conversation records, pre-set question answering strategies, etc.

[0053] In some embodiments of the present application, the rehearsal mode includes any one or more of the following: learning mode, practice mode, and test mode; in the learning mode, the retrieval generation module generates standard dialogues for the learner to learn the standard dialogues for responding to the conversation content generated by the virtual customer; switching from the learning mode to the practice mode, the practice mode is for the learner to practice dialogues with the virtual customer in various insurance business scenarios, such as sales, recruitment, etc.; switching from the practice mode to the test mode, the test mode is used to test the learner's dialogue with the virtual customer in various insurance business scenarios.

[0054] In some specific embodiments, the rehearsal mode creation module 102 creates three rehearsal modes based on the Bloom's Taxonomy of Educational Objectives, namely learning mode, practice mode, and test mode. It should be noted that the learning mode, practice mode, and test mode can be applied in stages, or in a progressive rehearsal mode of learning mode-practice mode-test mode. Such a progressive rehearsal mode can achieve the internalization of insurance agents from rote learning to understanding and creation. Specifically:

[0055] (1) Learning mode: learners can quickly learn under the guidance of mechanical knowledge. In the process of dialogue with the virtual customer, when the virtual customer mentions some objection problems, the learner can reproduce the response dialogue content according to the system prompt, so as to achieve the effect of strengthening learning. In this rehearsal mode, all dialogues and response dialogues are not pre-set scripts, aiming to let the agent learn the knowledge and dialogues in the private domain knowledge base from the simulated dialogue interview, so as to achieve the purpose of learning dialogues.

[0056] (2) Practice mode: In this practice mode, the virtual customer has a dialogue with the trainee in a specific situation. The system gives guidance on the solution in the process. The questions raised by the virtual customer are monitored during the dialogue, and the solution to each specific objection question is given in combination with the situation of the customer. The problems that occur in the simulated interview process are corrected in time, so as to assist the trainee and achieve the purpose of practicing the dialogue.

[0057] (3) Test mode: The trainee can choose a specific customer or a specific topic to freely carry out a dialogue and test the training content. In this test mode, the trainee can freely guide the dialogue, so as to get the different results of the virtual customer's acceptance of the transaction and rejection of the transaction with the judgment ability after the RAG retrieval training, and achieve the purpose of testing the pass.

[0058] Through the progressive and systematic training mode of the above learning mode-practice mode-test mode, the trainee can improve his professional quality and work ability, so as to better cope with market challenges and customer needs; at the same time, the training efficiency of the trainee is greatly improved, the training cost is reduced, and the practice process of the trainee and the virtual customer can be retained as subsequent data for tracing and analysis.

[0059] In some embodiments of the present application, as shown in Figure 2 The retrieval generation module 104 includes a situation awareness unit 1041 for analyzing and understanding the questions, needs and intentions of the virtual customer in the current dialogue situation; a retrieval unit 1042 for retrieving relevant knowledge and information in the current dialogue situation from the private domain knowledge base according to the questions, needs and intentions of the virtual customer perceived by the situation awareness unit; and a thought and strategy suggestion unit 1043 for generating thought and strategy suggestions for the trainee based on the relevant knowledge and information in the current dialogue situation retrieved. By designing the retrieval generation module 104 including the situation awareness unit 1041, the retrieval unit 1042 and the thought and strategy suggestion unit 1043, it is realized that in the practice mode, the real intention behind the questions raised by the virtual customer can be first perceived, then the relevant knowledge and information are retrieved from the private domain knowledge base according to the perceived real intention, and finally the generated thought and strategy suggestions can be more suitable for the real needs of the virtual customer, providing more professional and personalized services for the customer.

[0060] In some embodiments of the present application, as shown in Figure 2As shown, the knowledge base construction module 101 includes a data acquisition unit 1011 configured to collect raw data related to various business scenarios of the insurance industry from internal and / or external sources; a data processing unit 1012 configured to format the acquired raw data to convert it into the same file format; a vectorization unit 1013 configured to convert the processed text data in the same file format into a vector matrix based on a vector model; and a data warehousing unit 1014 configured to index and write the data vectorized based on the vector matrix into a database to form a private domain knowledge base of the insurance industry. By designing the knowledge base construction module 101 including the data acquisition unit 1011, the data processing unit 1012, the vectorization unit 1013, and the data warehousing unit 1014, a private domain knowledge base containing internal information and / or publicly known knowledge information of the insurance industry can be formed, thereby providing more abundant and accurate databases for students.

[0061] It should be understood that the vector (Embedding) model is a technique for mapping complex, high-dimensional or sparse data (such as text, images, classification features, etc.) into a low-dimensional, dense vector space. This vector representation preserves the semantic or structural information of the original data and is widely used in machine learning and deep learning to process text, images, user behavior, etc.

[0062] In some embodiments of the present application, the system is further configured with a student interactive interface configured to display an interactive conversation between a student and the virtual customer. By designing the student interactive interface, the conversation interaction between the student and the virtual customer is realized.

[0063] In some embodiments of the present application, the system further includes a virtual scene construction module for constructing various insurance business scenarios for the virtual customer to converse with the student, the virtual scene construction module at least includes a VR generation device for simulating a scene according to the age, gender, and occupation of the virtual customer and outputting a simulated practical scene. Through the VR generation device, the real working scene in which the virtual user and the student are having an insurance business conversation can be simulated. Thus, the student can truly immerse in this conversation training. It should be noted that the virtual scene construction module can also simulate the real business scene in other implementation manners, which is not limited here.

[0064] As Figure 3The RAG technology-based intelligent rehearsal system of the embodiments of the present application is illustrated in specific insurance business scenarios. First, a specific business insurance scenario of dialogue between a virtual customer and a trainee is constructed, and in this specific business scenario, the virtual customer communicates with the trainee. This training method simulates a real work scenario, aiming to improve the trainee's ability to deal with various complex situations in a safe and stress-free environment. The rehearsal system not only plays the role of the other party in the dialogue, but also assumes the roles of monitoring, analyzing and guiding, ensuring that the trainee can grow in each interaction. Exemplarily, a business scenario is described as follows: Ms. Li, a 28-year-old young woman, is newly married, has a stable job, is unfamiliar with the concept of personal pension insurance, and believes that retirement is very far away and there is no need to consider this aspect of insurance at this stage.

[0065] In the learning mode, trainee A first starts the dialogue: Hello Ms. Li, I heard that you just got married, congratulations! The virtual customer Ms. Li responds: Hey, A, you are really well-informed, but I don't want to hear about insurance, don't recommend insurance to me. In this learning mode, the rehearsal system integrates RAG technology, which gives the rehearsal system the ability to understand deeply and respond instantly. Therefore, when the trainee encounters challenges in discussing professional content such as the above dialogue scenario and pension insurance clauses, RAG technology will analyze the customer's questions through advanced natural language processing technology, accurately capturing the core of the problem. Subsequently, the technology quickly searches the private knowledge base for the most matching clause explanation or related cases. Once the most relevant information is found, the retrieval generation module generates an accurate and easy-to-understand answer draft for the trainee to refer to or directly adopt, i.e., the standard dialogue: Trainee A: Ms. Li, you misunderstood, I heard that you just got married and thought you might need new family protection needs, so I talked to you, completely in the mood of a friend to help you consider. This process not only speeds up the trainee's understanding of complex concepts, but also teaches them how to communicate information in a customer-friendly way, enhancing their communication skills.

[0066] In the practice mode, the rehearsal system does not directly provide standard scripts, but focuses on guiding the trainees on how to think and find ways to solve the customer's problems, thereby improving their professional competence and problem-solving ability. For example, trainee A first starts the conversation: Hello, Ms. Li, I heard that you just got married, congratulations; virtual customer Ms. Li responds: Oh, A, you are really well-informed, but I don't want to hear about insurance, don't recommend insurance to me. In the face of such a business scenario, the situation awareness unit 1041 enables the rehearsal system to deeply understand the content of the conversation, including the customer's problems, needs, and underlying emotions and intentions. Through natural language processing technology, the rehearsal system can identify key information and potential problem points in the conversation. The retrieval unit 1042 retrieves relevant knowledge and information related to the current conversation context from the private domain knowledge base, which may include insurance clauses, product characteristics, market trends, past successful or failed cases, etc., so as to quickly find the most matching knowledge to the virtual customer's needs and provide background information and support for the trainee. The idea and strategy suggestion unit 1043 generates solution ideas and strategy suggestions based on the retrieved relevant knowledge and understanding of the current conversation context, which guides the trainee on how to think about the problem from different angles and how to combine the virtual customer's needs and insurance product characteristics to develop a solution. For example, the response idea generated by the idea and strategy suggestion unit 1043: A should not directly promote at this time, but can chat about Ms. Li's recent marital life, and then naturally transition to the protection function of insurance, especially long-term planning such as pension, emphasizing that this is not a sales pitch, but a concern for her financial security from a friend's perspective. In the practice mode, the rehearsal system focuses on guiding the trainee to form independent thinking and problem-solving ability, rather than simply providing standard scripts. Through real-time analysis of conversation content, retrieval of relevant knowledge, provision of solution ideas and strategy suggestions, and immediate feedback and improvement suggestions, the trainee can continuously learn and grow in actual operation, and eventually become an insurance expert who can handle the job independently. In addition, the rehearsal system will also evaluate the quality of the trainee's answers, using the feedback mechanism of the RAG technology to immediately point out the shortcomings in the answers, such as unclear logic, missing information, or improper expression, etc. Based on these specific feedback, the rehearsal system will provide targeted improvement suggestions to guide the trainee on how to adjust strategies and optimize expression to achieve higher professional level.

[0067] In the test mode, the trainees are placed in a highly simulated real work environment, where they independently think and respond to various challenges without any pre-set scripts or ideas. For example, Trainee A: Hello, Ms. Li, I heard you just got married, congratulations! Virtual customer Ms. Li responds: Hey, A, you're really on the ball, but I don't want to hear about insurance, don't recommend insurance to me. In the test mode, the trainee completely faces Ms. Li and answers her doubts. The test mode is designed to test whether the trainee has truly mastered the knowledge learned and their ability to apply this knowledge in actual work. During this process, the trainee may encounter various types of customers, each with unique needs and problems, which requires the trainee to flexibly use the sales skills and communication strategies learned to effectively interact with different types of customers. At the same time, the trainee may need to delve into specific topics or issues, which helps to assess their understanding and mastery of professional knowledge, fully meeting the strict requirements of the training pass. To ensure the fairness and effectiveness of the test, the test mode usually includes a series of evaluation criteria and indicators. These criteria may include the trainee's communication skills, problem-solving skills, emotional processing skills, and other aspects. Through these comprehensive evaluations, the trainee's actual ability and level can be more accurately judged.

[0068] It should be noted that the insurance business scenarios and dialogue content constructed in the learning mode, practice mode and test mode can be different, which is only illustrative.

[0069] In some embodiments of the present application, the large language model is a GPT large model.

[0070] It should be understood that the division of modules in the embodiments of the present application is illustrative, and is only a logical functional division. In actual implementation, there can be another division method. In addition, each functional module in each embodiment of the present application can be integrated in one processor, or can be physically separate, or two or more modules can be integrated in one module. The integrated module can be realized in the form of hardware or in the form of a software functional module.

[0071] Embodiments of the present application also provide an intelligent rehearsal method based on RAG technology, Figure 4 The method flowchart is shown. The intelligent rehearsal method based on RAG technology in this embodiment includes the following steps:

[0072] Step S41: Constructing an insurance industry private domain knowledge base based on RAG technology, the private domain knowledge base includes professional knowledge of the insurance industry, sales construction strategies, customer portrait problem solving strategies, and laws and regulations of the insurance industry.

[0073] Step S42: Construct a progressive practice mode based on the Bloom teaching goal principle, organize and classify the data corresponding to the constructed practice mode into a library, and link to the corresponding private domain knowledge base according to the category of the practice mode.

[0074] Step S43: Create a virtual customer in an insurance business scenario according to the category of the practice mode; the virtual customer is configured to generate conversation content in the insurance business scenario.

[0075] Step S44: Based on the RAG technology and according to the conversation content generated by the virtual customer, retrieve the corresponding prompt content from the private domain knowledge base, input the prompt content into a large language model to generate response content corresponding to each category of practice mode.

[0076] It should be noted that the intelligent practice method based on the RAG technology of the present embodiment can realize the functions of the intelligent practice system based on the RAG technology described above, which will not be described here.

[0077] Figure 5 is a schematic block diagram of an electronic terminal provided by the present application. As shown in Figure 5 , the electronic terminal 500 includes at least one processor 501, a memory 502, at least one network interface 503, and a user interface 505. The various components in the electronic terminal 500 are coupled together through a bus system 504. It can be understood that the bus system 504 is used to realize the connection and communication between the components. In addition to including a data bus, the bus system 504 also includes a power bus, a control bus, and a status signal bus. However, in order to clearly illustrate, all kinds of buses are marked as a bus system in Figure 5 .

[0078] Among them, the user interface 505 can include a display, a keyboard, a mouse, a trackball, a click gun, a key, a button, a touchpad, or a touch screen, etc.

[0079] It is to be understood that the memory 502 can be volatile or nonvolatile memory, or both. The nonvolatile memory can be read-only memory (ROM), programmable ROM (PROM), which is used as an external cache. By way of example, and not limitation, many forms of RAM can be used, such as static random access memory (SRAM), synchronous static random access memory (SSRAM). The memory described in the embodiments of the present application is intended to include, but not be limited to, these and any other suitable type of memory.

[0080] The memory 502 in the embodiments of the present application is configured to store various types of data to support the operation of the electronic terminal 500. Examples of the data include any executable programs for operating on the electronic terminal 500, such as an operating system 5021 and an application program 5022. The operating system 5021 contains various system programs, such as a framework layer, a core library layer, a driver layer, and the like, for implementing various basic services and processing hardware-based tasks. The application program 5022 can contain various application programs, such as a media player, a browser, and the like, for implementing various application services. The intelligent rehearsal method based on the RAG technology provided by the embodiments of the present application can be included in the application program 5022.

[0081] The method disclosed in the embodiments of the present application can be applied to the processor 501 or implemented by the processor 501. The processor 501 can be an integrated circuit chip having a processing capability of signals. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor 501 or an instruction in the form of software. The processor 501 described above can be a general-purpose processor, a digital signal processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc. The processor 501 can implement or execute the disclosed methods, steps, and logic block diagrams in the embodiments of the present application. The general-purpose processor 501 can be a microprocessor or any conventional processor, etc. The steps of the accessory optimization method provided in conjunction with the embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module can be located in a storage medium, which is located in the memory. The processor reads the information in the memory and combines the hardware to complete the steps of the above method.

[0082] In an exemplary embodiment, the electronic terminal 500 can be implemented by one or more Application Specific Integrated Circuits (ASICs), DSPs, Programmable Logic Devices (PLDs), Complex Programmable Logic Devices (CPLDs), or the like, for performing the aforementioned methods.

[0083] According to the intelligent rehearsal method based on the RAG technology provided by the embodiment of the application, the application further provides a computer program product, which comprises computer program code, and when the computer program code is executed on a computer, the computer is caused to perform the method of any one of the embodiments shown in the embodiments. Figure 4 The method of any one of the embodiments shown in the embodiments.

[0084] According to the intelligent rehearsal method based on the RAG technology provided by the embodiment of the application, the application further provides a computer readable storage medium, which stores program code, and when the program code is executed on a computer, the computer is caused to perform the method of any one of the embodiments shown in the embodiments. Figure 4 The method of any one of the embodiments shown in the embodiments.

[0085] The terms "component," "module," "system," and the like used in the present specification are used to represent computer-related entities, hardware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable, a thread of execution, a program, and / or a computer. By way of illustration, both an application running on a computing device and the computing device can be a component. One or more components can reside within a process and / or thread of execution, and a component can be localized on one computer and / or distributed between two or more computers. In addition, these components can execute from various computer-readable media having various data structures stored thereon. The components can communicate by way of local and / or remote processes such as in accordance with a signal having one or more data packets (e.g., data from programs, data included in a management information base, etc.), such as data in a signal provided through a network infrastructure, such as the Internet, a local area network, a wide area network, a wired network, or a wireless network.

[0086] Those of skill in the art would understand that the various illustrative logical blocks and steps described in connection with the embodiments disclosed herein can be implemented as electronic hardware, or a combination of computer software and electronic hardware. The choice of hardware or software, or combination thereof, would be dependent on the specific application and design constraints imposed on the overall system. Skilled artisans can implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

[0087] Those of skill in the art would understand that, for the described convenience and conciseness, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0088] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described device embodiments are merely illustrative, for example, the division of units is only a logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed units can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0089] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0090] In addition, the functional units in each embodiment of the present application can be integrated into a processing unit, or each unit can be physically present alone, or two or more units can be integrated into one unit.

[0091] In the above embodiments, the functions of the various functional units can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, the functions can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions (programs). When the computer program instructions (programs) are loaded and executed on a computer, the whole or part of the processes or functions according to the embodiments of the present application are generated. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be transferred from one website, computer, server or data center to another website, computer, server or data center through wired (for example, coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (for example, infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center, etc. containing one or more available media. The available media can be magnetic media (for example, floppy disk, hard disk, magnetic tape), optical media (for example, high-density digital video disc (digital video disc, DVD), or semiconductor media (for example, solid state disk (solid state disk, SSD) and the like.

[0092] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that make contributions to the prior art or parts of the technical solutions can be embodied in the form of software products. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The storage medium mentioned above includes: U disk, mobile hard disk, read-only memory (read-only memory, ROM), random access memory (random access memory, RAM), magnetic disk or optical disk and various media that can store program codes.

[0093] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0094] In summary, since the traditional agent training method often relies on face-to-face teaching and simulated dialogue, this method is not only costly but also inefficient, and with the development of artificial intelligence technology, it is possible to use RAG technology for intelligent analysis and guidance, so that artificial intelligence can more accurately understand and respond to user needs, especially in the intelligent man-machine sparring scene of the insurance industry, therefore the present application provides a kind of intelligent exercise system, method, medium, terminal and program product based on RAG technology, by constructing a powerful private domain knowledge base containing professional knowledge, product details and industry rules of the insurance industry based on RAG technology, when the virtual customer generates dialogue content, the exercise system can retrieve the associated information in the private domain knowledge base in real time, and combine the specific needs of the virtual customer, so as to generate more rich and accurate response content; In addition, RAG technology can also optimize the dialogue experience according to the user's portrait and chat records, through the analysis of user behavior and the review of historical dialogue, the exercise system can better understand the user's intention and preference, so as to provide more user demand-oriented services, for example, if the exercise system detects that the user is interested in a certain type of insurance product, it can retrieve relevant product information through RAG technology and actively provide these information in the dialogue to enhance user experience; At the same time, the exercise system can more intelligently handle complex dialogue scenarios and provide more professional and personalized services to users. Therefore, the present application effectively overcomes the shortcomings of the prior art and has high industrial utilization value.

[0095] The above embodiments only exemplarily illustrate the principles and effects of the present application, and are not intended to limit the present application. Any person skilled in the art can modify or change the above embodiments without departing from the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by those skilled in the art without departing from the spirit and technical idea of the present application should be covered by the claims of the present application.

Claims

1. An intelligent training system based on RAG technology, characterized in that, The system includes: The knowledge base construction module is used to build a private domain knowledge base for the insurance industry based on RAG technology. The private knowledge base includes professional knowledge of the insurance industry, sales development strategies, customer profiling problem-solving strategies, and laws and regulations of the insurance industry. The exercise mode construction module is used to construct progressive exercise modes based on Bloom's teaching objectives principle, organize and classify the data corresponding to the constructed exercise modes into a library, and link them to the corresponding private domain knowledge base according to the category of the exercise mode. The virtual customer creation module is used to create virtual customers for insurance business scenarios based on the category of the exercise mode. The virtual customer is configured to generate dialogue content in an insurance business scenario; The retrieval and generation module is used to retrieve corresponding prompts from the private knowledge base based on RAG technology and the dialogue content generated by the virtual client, and input the prompts into the large language model to generate response content corresponding to each category of exercise mode.

2. The intelligent training system based on RAG technology according to claim 1, characterized in that, The retrieval generation module includes: Context-aware units are used to analyze and understand the questions, needs, and intentions of virtual customers in the current conversation context; The retrieval unit is used to retrieve relevant knowledge and information in the current dialogue context from the private domain knowledge base based on the questions, needs, and intentions of the virtual customer perceived by the context awareness unit. The "Thoughts and Strategies Suggestions" unit is used to generate thought and strategy suggestions for trainees to extract based on relevant knowledge and information retrieved in the current dialogue context.

3. The intelligent training system based on RAG technology according to claim 1, characterized in that, The knowledge base construction module includes: The data acquisition unit is used to collect raw data related to various business scenarios in the insurance industry from internal and / or external sources. The data processing unit is used to process the acquired raw data to convert it into the same file format; Vectorization unit, used to convert processed text data of the same file format into vector matrices based on a vector model; The data entry unit is used to build an index for the data after vectorization based on the vector matrix and write it into the database to form the private domain knowledge base of the insurance industry.

4. The intelligent training system based on RAG technology according to claim 1, characterized in that, The training mode includes any one or more of the following: learning mode, practice mode, and test mode; in the learning mode, the retrieval and generation module generates standard scripts for trainees to learn in response to the dialogue content generated by the virtual customer; switching from the learning mode to the practice mode, the practice mode allows trainees to practice dialogue with the virtual customer in various insurance business scenarios; Switch from practice mode to test mode, which is used to test trainees' dialogues with the virtual customer in various insurance business scenarios.

5. The intelligent training system based on RAG technology according to claim 1, characterized in that, The system is also equipped with a student interactive interface, which is configured to display interactive dialogue between the student and the virtual client.

6. The intelligent training system based on RAG technology according to claim 1, characterized in that, The system also includes a virtual scene construction module, which is used to construct various insurance business scenarios in which virtual customers and trainees converse. The virtual scene construction module includes at least a VR generation device, which is used to simulate scenarios based on the age, gender, and occupation of the virtual customer and output simulated practical scenarios.

7. A smart drill method based on RAG technology, characterized in that, The method includes: A private knowledge base for the insurance industry is built based on RAG technology. The private knowledge base includes professional knowledge of the insurance industry, sales development strategies, customer profiling problem-solving strategies, and laws and regulations of the insurance industry. A progressive exercise model based on Bloom's principles of instructional objectives is constructed. The data corresponding to the constructed exercise model is organized and classified into a library, and linked to the corresponding private knowledge base according to the category of the exercise model. Virtual customers are created in an insurance business scenario based on the category of the exercise mode; the virtual customers are configured to generate dialogue content in the insurance business scenario; Based on RAG technology and the dialogue content generated by the virtual customer, the system retrieves corresponding prompts from the private knowledge base and inputs them into the large language model to generate response content for each category of training mode.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of claim 7.

9. A computer program product, characterized in that, The computer program product includes computer program code that, when run on a computer, causes the computer to implement the method as described in claim 7.

10. An electronic terminal, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the method of claim 7.

Images