Marketing display method and system based on multiple agents

Abstract

The invention provides a marketing display method and system based on multiple agents. Customized display schemes can be provided for different customer types, the transmission efficiency of effective information in the marketing display process is improved, and the user experience is improved. In addition, the quality of products can be improved; in addition, the embodiment of the invention has the advantages of being high in interpretability and expandability, capable of supporting demonstration and questions and answers in professional fields and the like.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence (AI) technology, specifically to a marketing display method and system based on multi-agent intelligence. Background Technology

[0002] Question-answering systems based on Large Language Models (LLM) have been widely used in natural language processing, intelligent customer service, smart homes, and many other fields. However, these systems may have shortcomings in some specific application scenarios. For example, when introducing products or proposals to potential clients at trade shows or business meetings, due to various reasons (such as insufficient prior knowledge of the client's background), it may be impossible to provide targeted and detailed introductions to visiting clients on-site, or to adequately prepare for potential questions. This results in low efficiency in conveying effective information, difficulty in meeting user needs, and limited effectiveness in promoting business cooperation.

[0003] A prior art technique (refer to Chinese patent application No. 202310979105.5) parses the model identity required to answer the question from the user's request, then retrieves matching agent information (e.g., identity description information of historical experts, doctors, etc.) from the database, combines it with the user's original question to generate a prompt, and then the LLM generates the corresponding answer in a virtual specific identity.

[0004] The aforementioned existing technologies can provide targeted answers to user questions and improve the user experience to some extent, but they still have limitations, including at least the following aspects:

[0005] 1. The answers are customized based solely on a single question asked by the user, without considering the actual backgrounds of different users. Users from different backgrounds will receive the same feedback when asking the same question.

[0006] 2. The product or proposal being demonstrated was not adapted or customized in a targeted manner based on a specific knowledge base.

[0007] 3. This approach is only suitable for scenarios involving real-time communication and relying entirely on LLM without human intervention. Given the current limitations of AI technology, especially when explaining specialized fields, AI often cannot completely replace human presenters. Furthermore, the aforementioned technologies cannot facilitate adequate pre-presentation preparation by the presenter.

[0008] 4. The explanation content was not iterated and summarized during or after the process. Summary of the Invention

[0009] At least one embodiment of this application provides a marketing display method and system based on multi-agent technology, which can provide customized display solutions for different customer types and improve the efficiency of effective information transmission during the marketing display process.

[0010] According to a first aspect of this application, at least one embodiment provides a multi-agent-based marketing display method, comprising:

[0011] The customer survey agent generates a customer survey report, which includes customer types and customer profiles or characteristics for each customer type.

[0012] The product survey agent generates a product survey report for the target product;

[0013] Based on the customer survey report and the product survey report, the material editing agent generates product explanation materials that match each customer type.

[0014] The digital demonstration agent selects product explanation materials that match the customer type at the site for demonstration.

[0015] Optionally, the customer survey agent generates a customer survey report, including:

[0016] Obtain customer-related information, which includes at least one of the following: exhibition name, confirmed list of participating units, predicted list of participating units, confirmed list of participating customers, and predicted list of participating customers;

[0017] Based on the customer-related information, customer attributes are obtained, including at least one of the following attributes: age, gender, language used, employer, occupation, position, and whether the employee is a technical or business professional.

[0018] Based on the customer attributes, determine the customer type of the customer and the customer profile or customer characteristics of each customer type.

[0019] Optionally, the product survey agent generates a product survey report for the target product, including:

[0020] Based on the existing product knowledge base, an investigation is conducted on the target product, and a product investigation report for the target product is generated. The product investigation report includes the content of at least one product information item, which includes: background knowledge, functions, application scenarios, application solutions, business value, advantageous technologies, and future plans.

[0021] Optionally, the material editing agent generates product explanation materials matching each customer type based on the customer survey report and the product survey report, including at least one of a first collaboration method, a second collaboration method, a third collaboration method, and a fourth collaboration method; wherein,

[0022] In the first collaboration mode, the customer survey agent and the product survey agent each generate survey reports independently; the material editing agent creates product explanation materials that match each customer type based on the survey reports generated independently by the customer survey agent and the product survey agent.

[0023] In the second collaborative method, the material editing agent and the product survey agent respectively generate survey reports and / or answers based on the survey requests and / or questions sent by the material editing agent in at least one interaction process; the material editing agent creates product explanation materials that match each customer type based on the survey reports and / or answers obtained in the at least one interaction process.

[0024] In the third collaboration method, the customer survey agent and the product survey agent generate corresponding survey reports according to the task schedule of the project manager agent; the material editing agent, based on the survey reports and according to the task schedule of the project manager agent, creates product explanation materials that match each customer type.

[0025] The fourth collaboration method is that, in the first, second, or third collaboration methods, after generating the first intermediate result, the relevant intelligent agent receives the user's correction and / or confirmation of the first intermediate result, and executes the next task according to the first intermediate result after the user's correction or confirmation. The first intermediate result includes at least one of the following: product survey report, customer survey report, questions generated by the material editing intelligent agent, answers generated by the material editing intelligent agent or product survey intelligent agent, and an outline or chapter of the explanatory material.

[0026] Optionally, the above methods also include:

[0027] When the material editing agent generates product explanation materials that match each customer type based on the customer survey report and the product survey report, it further generates explanation suggestions that match each customer type.

[0028] Optionally, the above methods also include:

[0029] For each customer type, the virtual customer agent and the virtual explanation agent generate or update the question-and-answer knowledge base corresponding to the customer type through at least one round of question-and-answer interaction.

[0030] During the question-and-answer interaction, the virtual customer agent simulates a customer of the customer type based on the customer profile or customer characteristics of the customer type, and raises questions based on product explanation materials that match the customer type; the virtual explanation agent generates answers to the questions raised by the virtual customer agent based on at least one of the product survey report, product explanation materials, explanation suggestions, and product knowledge base.

[0031] Optionally, the above methods also include:

[0032] After each round of question-and-answer interaction, for each customer type, the material editing agent updates the product explanation materials and / or explanation suggestions that match the customer type based on the question-and-answer knowledge base corresponding to that customer type.

[0033] Optionally, the updating methods for the product explanation materials and / or explanation suggestions include at least one of a first updating method, a second updating method, a third updating method, and a fourth updating method; wherein,

[0034] In the first update method, the virtual customer agent and the virtual explanation agent are the same agent, which generates a question-and-answer knowledge base corresponding to the customer type through a self-questioning and self-answering method; the material editing agent updates the product explanation materials and / or explanation suggestions based on the question-and-answer knowledge base;

[0035] In the second update method, the virtual customer agent and the virtual explanation agent are different agents; the material editing agent updates the product explanation materials and / or explanation suggestions based on the question-and-answer knowledge base and information obtained through interaction with the customer survey agent and the product survey agent.

[0036] In the third update method, the virtual customer agent and the virtual explanation agent are different agents; the virtual customer agent and the virtual explanation agent execute the question-and-answer interaction process and generate the question-and-answer knowledge base according to the task scheduling of the project manager agent; the material editing agent updates the product explanation materials and / or explanation suggestions based on the question-and-answer knowledge base according to the task scheduling of the project manager agent.

[0037] The fourth update method is that, in the first, second, or third update method, after generating the second intermediate result, the relevant intelligent agent receives the user's correction and / or confirmation of the second intermediate result, and executes the next task according to the user's corrected or confirmed second intermediate result. The second intermediate result includes at least one of the following: the question generated by the virtual customer intelligent agent, the answer generated by the virtual explanation intelligent agent, and the modification method of the product explanation materials and / or explanation suggestions.

[0038] Optionally, the digital demonstration agent selects product explanation materials matching the customer type of the on-site customer for demonstration, including: selecting a digital human image and demonstration method matching the customer type of the on-site customer; and demonstrating the product explanation materials matching the on-site customer through the selected digital human image and according to the selected demonstration method, wherein the demonstration method includes on-site display and / or playback of the product explanation materials; wherein, if the product explanation materials do not match the target language used by the on-site customer, the explanation text of the digital demonstration agent is converted into the target language and displayed.

[0039] When the digital demonstration agent selects product explanation materials that match the customer type of the on-site customer for demonstration, it further selects explanation suggestions that match the on-site customer and demonstrates the product explanation materials according to the selected explanation suggestions.

[0040] Optionally, the above methods also include:

[0041] The material editing agent generates product explanation materials that match the fusion type based on the customer survey report and the product survey report. The fusion type includes at least two customer types, which are predetermined or determined based on the customer types of on-site customers.

[0042] Optionally, the above methods also include:

[0043] Based on the question-and-answer knowledge base, the feedback collection agent interacts with on-site customers and collects questions, answers, and feedback from on-site customers during the interaction process; wherein, when the feedback collection agent cannot answer or the answer cannot meet the requirements of on-site customers, the feedback collection agent collects the answer provided by the on-site human guide.

[0044] The feedback collection agent updates the question-and-answer knowledge base based on the collected questions, answers, and feedback from on-site customers and provides it to the material editing agent and / or digital presentation agent;

[0045] The material editing agent updates the product explanation materials and / or explanation suggestions based on the updated question-and-answer knowledge base.

[0046] Optionally, the above methods also include:

[0047] The live recording agent records interactive information during the demonstration process and generates meeting minutes and / or customer feedback reports corresponding to customer types.

[0048] According to a second aspect of this application, at least one embodiment provides a multi-agent-based marketing presentation system, including a customer survey agent, a product survey agent, a material editing agent, and a digital presentation agent, wherein:

[0049] The customer survey intelligent agent is used to generate a customer survey report, which includes customer types and customer profiles or customer characteristics for each customer type.

[0050] The product survey agent is used to generate a product survey report for the target product.

[0051] The material editing agent is used to generate product explanation materials that match each customer type based on the customer survey report and the product survey report;

[0052] The digital demonstration agent is used to select product explanation materials that match the customer type at the site for demonstration.

[0053] According to a third aspect of this application, at least one embodiment provides a multi-agent-based marketing display system, including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the method as described in any of the first aspects.

[0054] According to a fourth aspect of this application, at least one embodiment provides a computer-readable storage medium storing a program that, when executed by a processor, implements the steps of the method as described in any of the first aspects.

[0055] According to a fifth aspect of this application, at least one embodiment provides a computer program product including computer instructions that, when executed by a processor, implement the steps of the method as described in any of the first aspects.

[0056] Compared with existing technologies, the marketing display method and system based on multi-agent technology provided in this application can offer customized display solutions for different customer types, improve the efficiency of conveying effective information during the marketing display process, and enhance user experience. Furthermore, this application also improves the quality of the generated output; moreover, this application has strong interpretability and scalability, and can also support demonstrations and Q&A in professional fields. Attached Figure Description

[0057] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0058] Figure 1 This is a schematic diagram of an interactive flow of a marketing display method according to an embodiment of this application;

[0059] Figure 2 This is a flowchart illustrating a marketing display method based on multiple agents according to an embodiment of this application;

[0060] Figure 3 A diagram illustrating the first collaborative method for creating explanatory materials;

[0061] Figure 4 A diagram illustrating the second collaborative method for creating explanatory materials;

[0062] Figure 5 A diagram illustrating the third collaborative method for creating explanatory materials;

[0063] Figure 6 This is a diagram illustrating the first collaborative method in the virtual question-and-answer phase.

[0064] Figure 7 This is a schematic diagram of the second collaborative method in the virtual question-and-answer phase;

[0065] Figure 8 This is a schematic diagram of the on-site question and answer phase in an embodiment of this application.

[0066] Figure 9 This is a schematic diagram of a marketing display system based on multiple agents according to an embodiment of this application;

[0067] Figure 10 This is another structural diagram of a marketing display system based on multiple agents, as described in this application. Detailed Implementation

[0068] Exemplary embodiments of the present application will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this application will be thorough and complete, and will fully convey the scope of the present application to those skilled in the art.

[0069] It should be understood that the phrase "one embodiment" or "an embodiment" throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of this application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus. The word "and / or" in the specification and claims indicates at least one of the connected objects.

[0070] In the various embodiments of this application, it should be understood that the sequence number of each process described below does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0071] The following description provides examples and is not intended to limit the scope, applicability, or configuration set forth in the claims. Changes may be made to the function and arrangement of the elements discussed without departing from the spirit and scope of this disclosure. Various procedures or components may be appropriately omitted, substituted, or added to the examples. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Furthermore, features described with reference to certain examples may be combined in other examples.

[0072] To facilitate understanding of this application, a brief explanation of the intelligent agent involved in this application will be given first.

[0073] An intelligent agent is an AI program or entity that possesses a certain level of intelligence and can complete specific tasks through thinking, planning, and action (using tools, interacting with people, the environment, or other agents). In this embodiment, an LLM (Limited Linear Model) is used as the brain of the intelligent agent to illustrate the core idea. In practical applications, the intelligent agent may also be implemented using other AI technologies as its brain.

[0074] Figure 1 This is a schematic diagram of an interactive flow of a marketing display method according to an embodiment of this application. Figure 1In this context, "customer investigator," "product investigator," "material editor," "virtual customer," "virtual presenter," "digital presenter," "feedback collector," "live recorder," and later "project manager," etc., are all intelligent agents. Their role definitions, task descriptions, input / output formats, etc., can be communicated to the agent's brain (e.g., LLM) by human developers through prompts, thereby guiding them to make reasonable decisions and actions according to specific role and task requirements. In the embodiments of this application, the aforementioned "customer investigator," "product investigator," "material editor," "virtual customer," "virtual presenter," "digital presenter," "feedback collector," "live recorder," and "project manager" are sometimes referred to as "customer investigation intelligent agent," "product investigation intelligent agent," "material editing intelligent agent," "virtual customer intelligent agent," "virtual presentation intelligent agent," "digital presentation intelligent agent," "feedback collection intelligent agent," "live recorder intelligent agent," and "project manager intelligent agent," respectively.

[0075] In this embodiment, we will use one entity for each of the above-mentioned intelligent agents as an example for illustration. It is understood that in practical applications, if the application scenario is relatively simple, multiple agent roles can be merged into one; if the application scenario is relatively complex, each role can have more than one agent entity, or multiple intelligent agent teams (each intelligent agent team can include various permutations and combinations of the above-mentioned intelligent agent roles) can each complete the work, for example, one agent team can serve each type of customer.

[0076] Each agent can be equipped with corresponding tools. Tools can be understood as functions or capabilities that the agent can call to enable the agent to interact with external knowledge and objects, generate output in a specific format, and so on. Examples include web search tools, knowledge base query tools, text-to-speech tools, etc., to help the agent complete its respective tasks.

[0077] The input to the marketing display system in this application embodiment can be provided through language descriptions, completed forms, or by providing materials or accessing material paths. This input includes a brief overview of the product display, such as potential clients (names, positions, and organizations of one or more clients), the setting (e.g., exhibition name, demonstration venue), or basic information about the product / solution to be introduced (e.g., product name, access paths to related materials). In this application embodiment, the product includes, but is not limited to, specific physical devices, software products, or solutions to specific problems.

[0078] Here are two examples:

[0079] Example 1:

[0080] Subject of display: Zhang San, Vice President of Company A (or visitor list);

[0081] Product to be introduced: XXXX Solution.

[0082] Example 2:

[0083] Exhibition Name: 20xxxxx Exhibition;

[0084] Product to be introduced: xxx instrument (model xxxx).

[0085] The main outputs of the marketing display system include: customized explanatory materials for various customer types, explanation suggestions, and a Q&A knowledge base. Other intermediate / secondary outputs may include: customer survey reports, product survey reports, communication records between agents, meeting minutes, and customer feedback reports.

[0086] This application provides a marketing display method based on multiple agents, which is... Figure 1 This is a comprehensive customer demonstration solution that utilizes multiple agents to collaborate and complete the entire process. Please refer to... Figure 2 The marketing display method based on multi-agent provided in this application includes the following steps:

[0087] Step 21: The customer survey agent generates a customer survey report, which includes customer types and customer profiles or characteristics for each customer type.

[0088] Obtain customer-related information, including but not limited to at least one of the following: exhibition name, confirmed list of participating companies, predicted list of participating companies, confirmed list of participating customers, and predicted list of participating customers. The confirmed list of participating customers may be provided by the user; for example, the user may provide a specific customer list. The customer list may also be predicted based on relevant information; for example, for a specific exhibition name, predictions may be made based on reports from previous exhibitions or official information released by the current exhibition. Similarly, the list of participating companies may be provided by the user or predicted based on relevant information. Participating companies include, but are not limited to, various organizations such as enterprises, institutions, and schools.

[0089] Then, the customer survey agent can obtain customer attributes based on the customer-related information. For example, the customer survey agent can invoke tools to conduct surveys on customers in the list of attendees to obtain customer attributes, which include at least one of the following: age, gender, language used, employer, occupation, position, whether technical or business personnel, etc. Furthermore, the customer survey agent can determine the customer type and customer profile or characteristics for each customer type based on the customer attributes. The customer type can be obtained by classifying the customer attributes, and the customer characteristics of a certain customer type reflect the common or main characteristics of customers in that type.

[0090] Step 22: The product survey agent generates a product survey report for the target product.

[0091] Here, the target product is the product that needs to be showcased. The product survey agent can conduct a survey on the target product based on an existing product knowledge base and generate a product survey report for the target product. The product survey report includes at least one product information item, which includes: background knowledge, functions, application scenarios, application solutions, commercial value, advantageous technologies, future plans, etc.

[0092] Step 23: The material editing agent generates product explanation materials that match each customer type based on the customer survey report and the product survey report.

[0093] Here, the material editing agent can generate corresponding product explanation materials based on the product survey report for each customer type in the customer survey report, thereby realizing customized product explanation materials.

[0094] Step 24: The digital demonstration agent selects product explanation materials that match the customer type of the on-site customer for demonstration.

[0095] Here, the customer type of the on-site customer can be determined by the on-site presenter, identified through facial recognition technology, or provided on-site. The digital demonstration agent selects matching product explanation materials for demonstration based on the customer type. For example, it selects a digital human image and demonstration method that matches the customer type, and then uses the selected digital human image and demonstration method to present the product explanation materials matching the on-site customer. The demonstration method includes on-site display and / or playback of the product explanation materials. If the product explanation materials do not match the target language used by the on-site customer, the digital demonstration agent can also convert the explanation text into the target language and display it.

[0096] Through the above steps, this application embodiment can generate customized product explanation materials for different customer types and conduct customized displays, thereby improving the efficiency of effective information transmission during the marketing display process and enhancing customer experience.

[0097] In step 23 above, the material editing agent can generate product explanation materials matching each customer type according to at least one of the first collaboration method, the second collaboration method, the third collaboration method, and the fourth collaboration method. The above collaboration methods are explained below.

[0098] (1) In the first collaboration mode, the customer survey agent and the product survey agent each generate survey reports independently; the material editing agent creates product explanation materials that match each customer type based on the survey reports generated independently by the customer survey agent and the product survey agent.

[0099] (2) In the second collaboration mode, the material editing agent and the product survey agent generate survey reports and / or answers based on the survey requests and / or questions sent by the material editing agent in at least one interaction process; the material editing agent creates product explanation materials that match each customer type based on the survey reports and / or answers obtained in the at least one interaction process.

[0100] (3) In the third collaboration mode, the customer survey agent and the product survey agent generate corresponding survey reports according to the task scheduling of the project manager agent; the material editing agent, according to the task scheduling of the project manager agent, creates product explanation materials that match each customer type based on the survey reports.

[0101] (4) The fourth collaboration mode is that, in the first collaboration mode, the second collaboration mode or the third collaboration mode, after the relevant intelligent agent generates the first intermediate result, it receives the user's correction and / or confirmation of the first intermediate result, and executes the next task according to the first intermediate result after the user's correction or confirmation. The first intermediate result includes at least one of the following: product survey report, customer survey report, questions generated by the material editing intelligent agent, answers generated by the material editing intelligent agent or the product survey intelligent agent, outlines or chapters of explanatory materials, etc.

[0102] Furthermore, the material editing agent can also generate explanation suggestions tailored to each customer type when generating product explanation materials based on the customer survey report and the product survey report. Thus, in step 24, when the digital demonstration agent selects product explanation materials matching the customer type at the site, it can also select explanation suggestions matching the customer and demonstrate the product explanation materials according to the selected suggestions.

[0103] To facilitate answering customer questions at the exhibition, this embodiment of the application also generates a corresponding QA knowledge base for each customer type. Specifically, for each customer type, the virtual customer agent and the virtual explanation agent generate or update the QA knowledge base corresponding to that customer type through at least one round of QA interaction. During the QA interaction, the virtual customer agent simulates a customer of that customer type based on the customer profile or characteristics of that customer type and raises questions based on product explanation materials matching that customer type. The virtual explanation agent generates answers to the questions raised by the virtual customer agent based on at least one of the following: product survey reports, product explanation materials, explanation suggestions, and the product knowledge base. In this way, the feedback collection agent interacts with on-site customers based on the QA knowledge base.

[0104] In addition, in order to improve the quality of the product explanation materials generated by the material editing intelligent agent, the embodiments of this application can also iteratively update the product explanation materials based on the question-and-answer knowledge base.

[0105] Specifically, after each round of question-and-answer interaction between the virtual customer agent and the virtual explanation agent, for each customer type, the material editing agent updates the product explanation materials and / or explanation suggestions that match the customer type based on the question-and-answer knowledge base corresponding to the customer type.

[0106] Similarly, the updating methods for the product explanation materials and / or explanation suggestions include at least one of the first updating method, the second updating method, the third updating method, and the fourth updating method. The above updating methods are described below.

[0107] (1) In the first update method, the virtual customer intelligent agent and the virtual explanation intelligent agent are the same intelligent agent, and generate the question and answer knowledge base corresponding to the customer type through a self-questioning and self-answering method; the material editing intelligent agent updates the product explanation materials and / or explanation suggestions based on the question and answer knowledge base.

[0108] (2) In the second update method, the virtual customer agent and the virtual explanation agent are different agents; the material editing agent updates the product explanation materials and / or explanation suggestions based on the question-and-answer knowledge base and the information obtained by interacting with the customer survey agent and the product survey agent.

[0109] (3) In the third update method, the virtual customer agent and the virtual explanation agent are different agents; the virtual customer agent and the virtual explanation agent execute the question-and-answer interaction process and generate the question-and-answer knowledge base according to the task scheduling of the project manager agent; the material editing agent updates the product explanation materials and / or explanation suggestions based on the question-and-answer knowledge base according to the task scheduling of the project manager agent.

[0110] (4) The fourth update method is that, in the first update method, the second update method or the third update method, after the relevant intelligent agent generates the second intermediate result, it receives the user's correction and / or confirmation of the second intermediate result, and executes the next task according to the second intermediate result after the user's correction or confirmation. The second intermediate result includes at least one of the following: the question generated by the virtual customer intelligent agent, the answer generated by the virtual explanation intelligent agent, the modification method of the product explanation materials and / or explanation suggestions, etc.

[0111] In practical applications, participating customers may include multiple customer types simultaneously. In this embodiment, the material editing agent can generate product explanation materials matching the fusion type based on the customer survey report and the product survey report. The fusion type includes at least two customer types, which are predetermined or determined based on the customer types of the customers present. That is, if the fusion type can be predetermined, product explanation materials matching the fusion type can be generated in advance. If it cannot be predetermined, the fusion type can be determined based on the types of customers present, and then product explanation materials matching the fusion type can be generated on-site.

[0112] During the on-site demonstration, customers may ask questions and expect answers. In this embodiment, the feedback collection agent can interact with on-site customers based on the question-and-answer knowledge base, and can also collect questions, answers, and feedback from on-site customers during the interaction. When the feedback collection agent cannot answer or the answer does not meet the on-site customer's requirements, the feedback collection agent collects answers provided by a live on-site presenter. Furthermore, the feedback collection agent can update the question-and-answer knowledge base based on the collected questions, answers, and on-site customer feedback and provide it to the material editing agent and / or the digital demonstration agent. The material editing agent can then update the product explanation materials and / or explanation suggestions based on the updated question-and-answer knowledge base. The digital demonstration agent can conduct subsequent on-site demonstrations based on the updated question-and-answer knowledge base.

[0113] In addition, in this embodiment of the application, the live recording agent records the interaction information during the demonstration process and generates meeting minutes and / or customer feedback reports corresponding to the customer type.

[0114] The main flow of the marketing display method according to the embodiments of this application has been described above. The following section will combine... Figure 1 , Figures 3-8 The accompanying drawings, along with more specific examples, further illustrate the above method.

[0115] Figure 1 The marketing demonstration method involves two stages: the pre-event preparation stage and the on-site demonstration stage, which will be introduced below.

[0116] 1. Pre-event preparation stage

[0117] This stage mainly includes two steps: creating explanatory materials and conducting virtual Q&A sessions.

[0118] 1) Creating Explanatory Materials: Through multi-agent collaboration among customer surveyors, product surveyors, material editors, and project managers (optional), the product content to be introduced is matched with customer interests, and targeted explanatory materials and suggestions are customized for different customers.

[0119] The explanatory materials described in this application embodiment may include various forms and combinations thereof, such as explanatory texts, display boards, PPTs, audio narration, videos, and digital avatars. Explanation suggestions, on the other hand, are guidance provided to digital or live presenters regarding demonstration schemes for specific types of clients, including but not limited to client preferences (such as preferred presentation methods for product explanatory materials, digital avatars, etc.), key points of interest to the client, narration language, and narration style.

[0120] Below is a brief introduction to the various agents and their main tasks.

[0121] The "Customer Investigator" agent can investigate potential customers and their categories, create customer profiles, output customer classifications and investigation reports for each category, and answer various customer-related questions from other agents.

[0122] The "Product Investigator" agent can conduct research on the product being introduced based on an existing product knowledge base, generate a product investigation report, and answer various product-related questions from other agents.

[0123] The "Material Editor" Agent will generate product explanation materials that match the characteristics of each type of customer and provide explanation suggestions tailored to that type of customer.

[0124] The "Project Manager" agent is an optional role. It can develop plans, break down tasks, delegate tasks, monitor task progress, and ultimately coordinate a team of multiple agents to complete the task. This agent role can be added in more complex application scenarios to better accomplish tasks.

[0125] Each agent has tools that can be invoked to empower or enhance their ability to perform their respective tasks.

[0126] For example, the tools equipped by the "Customer Investigator" and "Product Investigator" agents may include: web search tools, database QA (Question Answering) tools, knowledge base QA tools (such as RAG tools: Retrieval Augmented Generation, a tool that can retrieve the most relevant information from a knowledge base and answer questions), and file reading and writing tools. By using these tools, the "Customer Investigator" and "Product Investigator" agents can obtain the information needed to generate reports from the web, databases, and knowledge bases (files, tables, knowledge graphs, etc.) and create reports.

[0127] The "Material Editor" Agent is equipped with tools such as file reading and writing tools, and various multimedia material generation tools (e.g., generators for PPT, audio, video, digital humans, and other materials), enabling it to create various forms of explanatory materials and generate explanatory suggestions.

[0128] The basic process for creating explanatory materials includes: investigating potential customer demonstration scenarios and creating explanatory materials for each type of customer demonstration scenario.

[0129] Investigating potential customer demonstration scenarios involves conducting a preliminary investigation and estimation of potential demonstration targets (customers) and demonstration scenarios based on system input information, determining what types of explanatory materials might be needed. For example, this might involve conducting background checks on visiting clients based on a client list, or searching relevant websites based on the exhibition name to make a preliminary conclusion: demonstration materials for the exhibition need to be prepared separately for technical personnel and corporate executives.

[0130] Then, for each type of customer demonstration scenario, customer investigators, product investigators, and material editors collaborate to generate explanatory materials and suggestions (detailed below).

[0131] The inputs for the presentation material creation stage include: a brief overview of the product demonstration, existing data required for customer / product surveys, and a knowledge base. The main outputs include: customized presentation materials for different customer demonstration scenarios and presentation suggestions. Secondary / intermediate outputs include: customer survey reports, product survey reports, and communication records between agents.

[0132] When creating explanatory materials, agents can collaborate in various ways. Each collaboration method offers different task descriptions and degrees of freedom for each agent, making it suitable for creating explanatory materials with varying needs, from simple to complex. The following examples illustrate this (in reality, there can be many more agent collaboration methods, not limited to the four shown in the examples):

[0133] a) First collaborative method: Investigate first, then summarize. For example... Figure 3 As shown, customer surveyors and product surveyors first conduct surveys on potential customers and the products to be introduced, and each generates a survey report independently. Finally, the materials editor compiles and produces the reports.

[0134] Customer surveyors can generate customer survey reports, including potential customer categories and customer profiles / typical characteristics for each category. This includes information such as the customer's occupation, age group, and whether they are technical personnel (more focused on technical details) or business personnel (more focused on commercial value). When the customer list is known, research can be conducted directly based on the list or existing customer information. When the customer list is unknown (e.g., at large trade shows), online searches (e.g., reports from past trade shows, official information from this year's show), and knowledge inherent in LLM (Lifecycle Management) can be used to predict the customer group's classification and characteristics.

[0135] Product investigators can produce product investigation reports, such as product background information, feature introduction, business value, key technologies, future plans, and so on.

[0136] Then, the material editor agent, based on the survey reports from the previous two agents (usually provided as context), uses various multimedia material production tools to create tailored explanatory materials for each customer type, and can provide explanation suggestions for each customer type. For example, for researchers / domain experts, the explanatory materials would focus on the product's technical highlights, using a digital avatar or voice of a "professional and rigorous domain expert"; for corporate leaders and executives, the focus would be on the product's commercial value and business model, using a digital avatar of a "capable business elite"; and for young customers like students, the emphasis would be on the product's practical functions, stylish design, and affordable price, using a "lively, humorous, and approachable student" digital avatar.

[0137] In this process, the task descriptions of each agent are usually designed in advance by human developers and written into the program of each agent (e.g., informed to the LLM in the form of a prompt word).

[0138] This process can be used for more basic applications such as surveys of single / small customer groups and the generation of explanatory materials with simple structures.

[0139] b) Second collaborative method: Investigation and production proceed simultaneously. For example... Figure 4 As shown, this is the material creation process led by the material editor agent. During material creation, the material editor agent proactively submits survey requests to customer surveyors and product surveyors, or requests answers from customer surveyors / product surveyors regarding information needed for material creation and any questions that arise. The explanatory material is then iteratively completed through multiple communications.

[0140] In this collaborative approach, the task descriptions for the Material Editor Agent are typically designed in advance by human developers (e.g., providing task implementation steps, ideas, or material outlines), while the task descriptions for the Customer Investigator and Product Investigator Agents can be generated spontaneously by the Material Editor Agent (without human developer involvement, or only by providing task templates). This is equivalent to the Material Editor Agent autonomously assigning tasks to the Customer Investigator and Product Investigator.

[0141] This method can be used to generate more complex explanatory materials, such as those that need to be completed in chapters or multiple steps.

[0142] c) Third collaboration method: Project manager model. For example... Figure 5As shown, above the aforementioned customer investigators, product investigators, and material editors, a project manager agent is added. This project manager is responsible for planning the overall process and scheduling and assigning tasks to other agents. For example, the project manager first breaks down the task flow, designs the chapters of the explanatory materials, and develops separate task plans. Then, the project manager assigns customer investigators, product investigators, and material editors to complete the production of the explanatory materials step by step, according to different customers and different chapters.

[0143] In this approach, the difference from collaboration method 2 lies in the fact that the task descriptions and communication / collaboration methods for the three agents—customer investigator, product investigator, and material editor—can be entirely arranged autonomously by the project manager agent. Human developers only need to inform the project manager agent of the overall material task description, expected outputs, and functional descriptions of the other agents. In this approach, the agent (or AI) has the greatest autonomy in decision-making.

[0144] This approach can handle application scenarios with a wider variety of clients and materials that require more complex document structures.

[0145] d) Fourth Collaboration Method: Human Feedback Model. Human feedback mechanisms can be incorporated into each stage of the three collaboration methods described above. For example, certain intermediate results generated by the Agent (material outlines, investigation reports, etc.) require human confirmation, correction, or feedback before proceeding. If humans provide negative feedback or suggestions for improvement, some tasks may need to be returned to the original Agent for redoing.

[0146] This method allows for timely manual verification of the results during the generation process, ensuring the quality of the final generated results to the greatest extent possible when AI capabilities are insufficient or when there are high requirements for the final result.

[0147] 2) Virtual Q&A and Material Improvement: The Q&A process is simulated through the interaction between virtual customers and virtual guides, simulating scenarios that may occur when interacting with customers during on-site demonstrations. The explanation materials and Q&A knowledge base are then continuously improved based on the results.

[0148] This step may involve agent roles such as: virtual customer, virtual presenter, material editor, project manager, etc.

[0149] The "virtual customer" agent can preset its own role based on a certain type of customer profile given in the customer profile file, simulate a specific type of customer, and ask questions about the product based on the explanatory materials.

[0150] The "virtual tour guide" agent provides targeted answers to questions from virtual customer agents based on product research reports, explanatory materials, explanation suggestions (tailored to this type of customer), and product knowledge base.

[0151] The "Materials Editor" Agent refers to the QA knowledge base (QA record set) generated by the two types of Agents mentioned above, and iteratively updates the explanatory materials and suggestions for this type of customer, such as adding explanatory information and preparing appendix pages.

[0152] The virtual customer and virtual guide agents can be equipped with file reading and writing tools, knowledge base QA / RAG tools, etc. The tools available to the material editor are similar to those described in the "Creating Explanatory Materials" section, and will not be repeated here. In practical applications, the material editor agent from the "Creating Explanatory Materials" section can be reused, or a separate agent can be created.

[0153] This phase includes two basic processes: virtual Q&A and the refinement of explanatory materials (which can go through single or multiple iterations). Virtual Q&A involves the agent simulating a question-and-answer process between the customer and the presenter to generate a QA knowledge base. The refinement of explanatory materials is based on the QA knowledge base generated from the virtual Q&A, used to improve the explanatory materials and suggestions.

[0154] The inputs for this stage include: the explanatory materials (draft) generated in the previous step, the explanatory suggestions (draft), the customer survey report, the product survey report, and the product knowledge base. The main outputs include: a QA knowledge base customized for different customer demonstration scenarios, revised explanatory materials, and explanatory suggestions. Secondary / intermediate outputs may include: communication records between agents.

[0155] Similar to the previous section, this stage can also be achieved by multiple agents through different collaboration methods to meet application scenarios of varying complexity. Here are a few examples:

[0156] a) First collaboration method (corresponding to the first update method mentioned above): Virtual customer / guide combined. For example... Figure 6 As shown, for simpler scenarios, the virtual customer and virtual presenter can be combined into one. This agent can directly generate a self-answering QA document based on customer profile documents, product explanation documents, and the product knowledge base using RAG tools. Then, the material editor agent updates the original explanation materials and suggestions. After one or more rounds of iteration, the final explanation materials, suggestions, and QA knowledge base are obtained.

[0157] b) Second collaboration method (corresponding to the second update method mentioned above): interaction between virtual customers and virtual guides. For example... Figure 7As shown, for slightly more complex scenarios, virtual customers and virtual presenters can be implemented by different agents. Furthermore, when updating materials, material editors can consult with customer investigators or product investigators to obtain other necessary information.

[0158] c) Third Collaboration Method (corresponding to the third update method mentioned above): Project Manager Mode. Similar to the "Creating Explanatory Materials" collaboration method, a Project Manager Agent is added in addition to the Agents mentioned above. The Project Manager Agent intelligently plans, dynamically designs and allocates tasks for the entire process (generation of the QA knowledge base, modification of explanatory materials / explanation suggestions), and autonomously coordinates the entire team to complete the task. For example, based on the explanatory materials, the QA knowledge base is generated step by step according to structural units such as pages, paragraphs, and chapters.

[0159] d) Fourth collaboration method (corresponding to the fourth update method mentioned above): Human feedback mode. Similar to the collaboration method of "creating explanatory materials," human feedback mechanisms can be added to each stage of the above three collaboration methods. This will not be elaborated further here.

[0160] For each type of customer, corresponding explanatory materials, explanatory suggestions, and QA knowledge bases can be generated by following the above processes.

[0161] In practical applications, another possible scenario is that, in a specific context, it is necessary to simultaneously present to multiple different types of customers in a single session (for example, at a meeting, simultaneously demonstrating to senior leaders and technical experts of the visiting organization).

[0162] If this situation can be anticipated during the preparation phase, it can be communicated when inputting into the system. In this way, the agent editor will also take this situation into account when generating materials and produce explanatory materials that can cater to various types of customers.

[0163] If this situation is not anticipated during the preparation phase but occurs on-site, the material editor (Agent) can edit and synthesize the pre-made explanatory materials for these types of clients on-site, generating a merged explanatory material in real time.

[0164] 2. On-site demonstration phase

[0165] This phase mainly includes on-site explanations with real users, QA and feedback collection and iteration, and on-site recording and summarization.

[0166] 1) On-site explanation

[0167] For each customer, the most suitable customer type is selected (either by AI or program recognition, input by a human presenter, or chosen by the customer themselves). Then, a digital presenter (Agent) uses pre-generated materials tailored to this customer type to provide a customized presentation. During the presentation, a digital human (with a specific appearance and voice) matching the customer type can be used for demonstration.

[0168] The inputs for a digital presenter agent can include: customer survey reports (including customer profile descriptions), explanatory materials, and explanation suggestions. Outputs are achieved through on-site display / playback of explanatory materials (display boards, PPTs, audio, video, or digital human demonstrations, etc.).

[0169] 2) On-site Q&A

[0170] like Figure 8 As shown, the "Feedback Collector" agent automatically answers each customer's question based on the QA knowledge base and collects genuine customer feedback. When a customer's question exceeds the scope of the QA knowledge base, or when the customer or the live presenter is dissatisfied with the agent's answer, the live presenter can assist in responding. These QA results are also collected by the Feedback Collector agent to update the QA knowledge base and provide it to other agents such as the Material Editor agent and the Digital Presenter agent, to update the presentation materials and suggestions in a timely manner for use in subsequent demonstration activities.

[0171] 3) Live recording

[0172] The "live recorder" agent records the daily meeting / exhibition proceedings (audio or text) and generates meeting minutes and customer feedback reports by customer category after the meeting, providing reference suggestions for subsequent demonstrations and business activities.

[0173] Each of the above sub-tasks is completed by an Agent with a specific identity using the tools at their disposal, while maintaining interaction with other Agents, and human participation can be introduced when necessary.

[0174] In summary, it can be seen that the embodiments of this application have at least the following technical effects:

[0175] 1. Improve the efficiency of information transmission in business communication and enhance user experience.

[0176] 1) Customer Customization: Prior background research and customer profiling were conducted on the target customer group. Therefore, tailored explanations can be generated by extracting relevant sections from product presentation materials for different customer types. The QA knowledge base is also customized for each customer, ensuring different answers even when different types of customers ask the same questions. The presentation style and image are chosen to suit the specific customer type, enhancing the customer experience and facilitating effective business communication.

[0177] 2) Product customization: The explanatory materials and QA knowledge base are generated based on relevant information or specific knowledge bases of the product (or proposal) to be demonstrated. Compared with the general Q&A capabilities that only use a large language model, the answers are more professional and more in line with the product itself.

[0178] 3) Low latency: Explanatory materials and QA knowledge bases can be pre-generated for different customer groups before the formal demonstration, rather than being generated in real time on-site. After collecting customer feedback on-site, the explanatory materials and QA knowledge base can be updated during off-peak hours of the demonstration. These designs can reduce on-site latency and the computational requirements of the system.

[0179] 4) Assisting Human Guides: Due to the limitations of current AI technology, especially in explaining specialized fields, AI often cannot completely replace human guides. Therefore, human guides are often still needed on-site. Existing technologies typically aim to improve the capabilities of the system itself. However, this application embodiment conducts in-depth investigations into the client's background beforehand, generating client survey reports and explanation suggestions. Furthermore, through interaction between virtual clients and virtual guides, a QA knowledge base is pre-generated. These outputs can assist human guides in making more thorough preparations before the formal presentation. Therefore, this application embodiment, in addition to improving the capabilities of the AI ​​system, also significantly enhances the on-site performance of human guides.

[0180] 2. Improve the quality of the products:

[0181] 1) Complex Task Processing Capability: Different multi-agent collaboration methods are designed based on the complexity of the task, allowing complex tasks to be broken down into simpler sub-tasks, which are then completed collaboratively by agents with specific roles. Therefore, in addition to producing simple explanatory materials, this system can also handle the production of more complex and larger-scale materials.

[0182] 2) Autonomous Iteration Capability: The system incorporates autonomous reflection and iteration capabilities for agents in multiple places. For example, during the material creation phase, the material editor proactively initiates multiple survey requests to customer and product surveyors based on the completion progress; during the virtual Q&A phase, there are multiple rounds of interaction between virtual customers and virtual presenters, and the material editor iterates the presentation materials multiple times based on updates to the QA knowledge base; during the feedback collection phase, feedback from real customers is continuously collected, and the presentation materials and QA knowledge base are updated; after the meeting, meeting minutes are compiled, and customer feedback is analyzed, etc. These measures ensure that the quality of the system's generated results continuously improves through autonomous multi-round iteration.

[0183] 3) Human intervention: Human intervention mechanisms can be added to the workflow to monitor and control the quality of the deliverables at each stage.

[0184] 3. Other:

[0185] 1) Professionalism: Due to the introduction of the RAG tool, the system can perform demonstrations and Q&A in professional fields without model fine-tuning, rather than just relying on the general Q&A capabilities of large language models or other Q&A systems.

[0186] 2) Interpretability: The system can generate various intermediate files during the process and record the "communication records" between agents, as well as the agents' own thinking / decision-making processes. Therefore, compared with the black-box process of directly using LLM, the cooperation process between agents and the generated results are more interpretable and easier for manual monitoring and tracking.

[0187] 3) Scalability: Each Agent can access and operate external data and devices by calling various tools. Therefore, in the future, it may be able to connect to more types of data sources and knowledge bases, or generate more explanatory materials in more presentation formats, and is not limited to the examples in this manual.

[0188] Please refer to Figure 9 The present application provides a structure for a multi-agent-based marketing display system, comprising a customer survey agent 901, a product survey agent 902, a material editing agent 903, and a digital presentation agent 904, wherein:

[0189] The customer survey agent 901 is used to generate a customer survey report, which includes customer types and customer profiles or customer characteristics for each customer type.

[0190] The product survey agent 902 is used to generate a product survey report for the target product.

[0191] The material editing agent 903 is used to generate product explanation materials that match each customer type based on the customer survey report and the product survey report;

[0192] The digital demonstration agent 904 is used to select product explanation materials that match the customer type of the on-site customer for demonstration.

[0193] Through the above modules, the embodiments of this application can provide customized display solutions for different customer types, thereby improving the efficiency of conveying effective information during the marketing display process.

[0194] Optionally, the customer survey agent is also used for:

[0195] Obtain customer-related information, which includes at least one of the following: exhibition name, confirmed list of participating units, predicted list of participating units, confirmed list of participating customers, and predicted list of participating customers;

[0196] Based on the customer-related information, customer attributes are obtained, including at least one of the following attributes: age, gender, language used, employer, occupation, position, and whether the employee is a technical or business professional.

[0197] Based on the customer attributes, determine the customer type of the customer and the customer profile or customer characteristics of each customer type.

[0198] Optionally, the product survey agent is also used for:

[0199] Based on the existing product knowledge base, an investigation is conducted on the target product, and a product investigation report for the target product is generated. The product investigation report includes the content of at least one product information item, which includes: background knowledge, functions, application scenarios, application solutions, business value, advantageous technologies, and future plans.

[0200] Optionally, the material editing agent generates product explanation materials matching each customer type based on the customer survey report and the product survey report, including at least one of a first collaboration method, a second collaboration method, a third collaboration method, and a fourth collaboration method; wherein,

[0201] In the first collaboration mode, the customer survey agent and the product survey agent each generate survey reports independently; the material editing agent creates product explanation materials that match each customer type based on the survey reports generated independently by the customer survey agent and the product survey agent.

[0202] In the second collaborative method, the material editing agent and the product survey agent respectively generate survey reports and / or answers based on the survey requests and / or questions sent by the material editing agent in at least one interaction process; the material editing agent creates product explanation materials that match each customer type based on the survey reports and / or answers obtained in the at least one interaction process.

[0203] In the third collaboration method, the customer survey agent and the product survey agent generate corresponding survey reports according to the task schedule of the project manager agent; the material editing agent, based on the survey reports and according to the task schedule of the project manager agent, creates product explanation materials that match each customer type.

[0204] The fourth collaboration method is that, in the first, second, or third collaboration methods, after generating the first intermediate result, the relevant intelligent agent receives the user's correction and / or confirmation of the first intermediate result, and executes the next task according to the first intermediate result after the user's correction or confirmation. The first intermediate result includes at least one of the following: product survey report, customer survey report, questions generated by the material editing intelligent agent, answers generated by the material editing intelligent agent or product survey intelligent agent, and an outline or chapter of the explanatory material.

[0205] Optionally, the material editing agent is further configured to generate explanation suggestions that match each customer type when generating product explanation materials that match each customer type based on the customer survey report and the product survey report.

[0206] Optionally, the above system also includes a virtual customer agent and a virtual explanation agent;

[0207] For each customer type, the virtual customer agent and the virtual explanation agent generate or update the question-and-answer knowledge base corresponding to the customer type through at least one round of question-and-answer interaction.

[0208] During the question-and-answer interaction, the virtual customer agent simulates a customer of the customer type based on the customer profile or customer characteristics of the customer type, and raises questions based on product explanation materials that match the customer type; the virtual explanation agent generates answers to the questions raised by the virtual customer agent based on at least one of the product survey report, product explanation materials, explanation suggestions, and product knowledge base.

[0209] Optionally, after each round of question-and-answer interaction, for each customer type, the material editing agent updates the product explanation materials and / or explanation suggestions that match the customer type based on the question-and-answer knowledge base corresponding to the customer type.

[0210] Optionally, the updating methods for the product explanation materials and / or explanation suggestions include at least one of a first updating method, a second updating method, a third updating method, and a fourth updating method; wherein,

[0211] In the first update method, the virtual customer agent and the virtual explanation agent are the same agent, which generates a question-and-answer knowledge base corresponding to the customer type through a self-questioning and self-answering method; the material editing agent updates the product explanation materials and / or explanation suggestions based on the question-and-answer knowledge base;

[0212] In the second update method, the virtual customer agent and the virtual explanation agent are different agents; the material editing agent updates the product explanation materials and / or explanation suggestions based on the question-and-answer knowledge base and information obtained through interaction with the customer survey agent and the product survey agent.

[0213] In the third update method, the virtual customer agent and the virtual explanation agent are different agents; the virtual customer agent and the virtual explanation agent execute the question-and-answer interaction process and generate the question-and-answer knowledge base according to the task scheduling of the project manager agent; the material editing agent updates the product explanation materials and / or explanation suggestions based on the question-and-answer knowledge base according to the task scheduling of the project manager agent.

[0214] The fourth update method is that, in the first, second, or third update method, after generating the second intermediate result, the relevant intelligent agent receives the user's correction and / or confirmation of the second intermediate result, and executes the next task according to the user's corrected or confirmed second intermediate result. The second intermediate result includes at least one of the following: the question generated by the virtual customer intelligent agent, the answer generated by the virtual explanation intelligent agent, and the modification method of the product explanation materials and / or explanation suggestions.

[0215] Optionally, the digital demonstration agent is further configured to select product explanation materials matching the customer type of the on-site customer for demonstration, including: selecting a digital human image and demonstration method matching the customer type of the on-site customer; and demonstrating the product explanation materials matching the on-site customer through the selected digital human image and according to the selected demonstration method, wherein the demonstration method includes on-site display and / or playback of the product explanation materials; wherein, if the product explanation materials do not match the target language used by the on-site customer, the explanation text of the digital demonstration agent is converted into the target language and displayed.

[0216] The digital demonstration agent is also used to further select explanation suggestions that match the on-site customer when selecting product explanation materials that match the customer type of the on-site customer for demonstration, and to demonstrate the product explanation materials according to the selected explanation suggestions.

[0217] Optionally, the material editing agent is also used to generate product explanation materials that match the fusion type based on the customer survey report and the product survey report. The fusion type includes at least two customer types, which are predetermined or determined based on the customer types of on-site customers.

[0218] Optionally, the above system may also include:

[0219] The feedback collection agent is used to interact with on-site customers based on the question-and-answer knowledge base and collect questions, answers and feedback from on-site customers during the interaction process; wherein, when the feedback collection agent cannot answer or the answer cannot meet the requirements of on-site customers, the feedback collection agent collects the answer provided by the on-site human guide.

[0220] The feedback collection agent is also used to update the question-and-answer knowledge base based on the collected questions, answers, and feedback from on-site customers, and provide it to the material editing agent and / or digital presentation agent;

[0221] The material editing agent is also used to update the product explanation materials and / or explanation suggestions based on the updated question-and-answer knowledge base.

[0222] Optionally, the above system may also include:

[0223] The live recording agent is used to record interactive information during the presentation and generate meeting minutes and / or customer feedback reports corresponding to customer types.

[0224] It should be noted that the systems provided in the above embodiments are devices corresponding to the above-described marketing display method based on multi-agent intelligence. The implementation methods in the above embodiments are applicable to the embodiments of this device and can achieve the same technical effect. The device provided in this application can implement all the method steps implemented in the above method embodiments and can achieve the same technical effect. Here, the parts that are the same as those in the method embodiments and the beneficial effects will not be described in detail.

[0225] Please refer to Figure 10 The present application provides a schematic diagram of another marketing display system based on multi-agent technology. The device includes: a processor 1001, a transceiver 1002, a memory 1003, a user interface 1004, and a bus interface.

[0226] In this embodiment of the application, the device further includes a program stored on memory 1003 and executable on processor 1001.

[0227] The transceiver 1002 is used to send and receive data under the control of the processor;

[0228] The processor 1001 is configured to read the computer program in the memory and perform the following operations:

[0229] A customer survey report is generated by a customer survey intelligent agent. The customer survey report includes customer types and customer profiles or customer characteristics for each customer type.

[0230] Generate product survey reports for target products using a product survey agent;

[0231] Based on the customer survey report and the product survey report, the material editing agent generates product explanation materials that match each customer type.

[0232] The digital demonstration agent selects product explanation materials that match the customer type at the scene for demonstration.

[0233] Understandably, in this embodiment of the application, when the computer program is executed by the processor 1001, it can implement the various processes of the above-described multi-agent-based marketing display method embodiment and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0234] exist Figure 10 In this context, the bus architecture can include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors represented by processor 1001 and memory represented by memory 1003 together. The bus architecture can also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. The transceiver 1002 can be multiple elements, including transmitters and receivers, providing a unit for communicating with various other devices over a transmission medium. For different user equipment, the user interface 1004 can also be an interface capable of connecting external or internal devices, including but not limited to keypads, displays, speakers, microphones, joysticks, etc.

[0235] The processor 1001 is responsible for managing the bus architecture and general processing, and the memory 1003 can store the data used by the processor 1001 when performing operations.

[0236] It should be noted that the device in this embodiment corresponds to the aforementioned marketing display method based on multiple agents. The implementation methods in the above embodiments are all applicable to the embodiments of this device and can achieve the same technical effect. In this device, the transceiver 1002 and the memory 1003, as well as the transceiver 1002 and the processor 1001, can be connected via a bus interface. The functions of the processor 1001 can also be implemented by the transceiver 1002, and vice versa. It should be noted that the device provided in this application embodiment can implement all the method steps implemented in the above method embodiments and achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiments will not be described in detail here.

[0237] In some embodiments of this application, a computer-readable storage medium is also provided, on which a program is stored, which, when executed by a processor, performs the following steps:

[0238] A customer survey report is generated by a customer survey intelligent agent. The customer survey report includes customer types and customer profiles or customer characteristics for each customer type.

[0239] Generate product survey reports for target products using a product survey agent;

[0240] Based on the customer survey report and the product survey report, the material editing agent generates product explanation materials that match each customer type.

[0241] The digital demonstration agent selects product explanation materials that match the customer type at the scene for demonstration.

[0242] When executed by the processor, this program can implement all the above-mentioned marketing display methods based on multi-agent systems and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0243] This application also provides a computer program product, including computer instructions. When the computer instructions are executed by a processor, they implement the various processes of the above-described multi-agent-based marketing display method embodiment and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0244] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0245] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0246] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0247] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of this application, depending on actual needs.

[0248] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0249] If the aforementioned functions are implemented as 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 solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0250] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A marketing display method based on multi-agent intelligence, characterized in that, include: The customer survey agent generates a customer survey report, which includes customer types and customer profiles or characteristics for each customer type. The product survey agent generates a product survey report for the target product; Based on the customer survey report and the product survey report, the material editing agent generates product explanation materials that match each customer type. The digital demonstration agent selects product explanation materials that match the customer type at the site for demonstration.

2. The method as described in claim 1, characterized in that, The customer survey agent generates a customer survey report, including: Obtain customer-related information, which includes at least one of the following: exhibition name, confirmed list of participating units, predicted list of participating units, confirmed list of participating customers, and predicted list of participating customers; Based on the customer-related information, customer attributes are obtained, including at least one of the following attributes: age, gender, language used, employer, occupation, position, and whether the employee is a technical or business professional. Based on the customer attributes, determine the customer type of the customer and the customer profile or customer characteristics of each customer type.

3. The method as described in claim 1, characterized in that, The product survey agent generates a product survey report for the target product, including: Based on the existing product knowledge base, an investigation is conducted on the target product, and a product investigation report for the target product is generated. The product investigation report includes the content of at least one product information item, which includes: background knowledge, functions, application scenarios, application solutions, business value, advantageous technologies, and future plans.

4. The method as described in claim 1, characterized in that, The material editing agent generates product explanation materials matching each customer type based on the customer survey report and the product survey report, including at least one of a first collaboration method, a second collaboration method, a third collaboration method, and a fourth collaboration method; wherein... In the first collaboration mode, the customer survey agent and the product survey agent each generate survey reports independently; the material editing agent creates product explanation materials that match each customer type based on the survey reports generated independently by the customer survey agent and the product survey agent. In the second collaborative method, the material editing agent and the product survey agent respectively generate survey reports and / or answers based on the survey requests and / or questions sent by the material editing agent in at least one interaction process; the material editing agent creates product explanation materials that match each customer type based on the survey reports and / or answers obtained in the at least one interaction process. In the third collaboration method, the customer survey agent and the product survey agent generate corresponding survey reports according to the task schedule of the project manager agent; the material editing agent, based on the survey reports and according to the task schedule of the project manager agent, creates product explanation materials that match each customer type. The fourth collaboration method is that, in the first, second, or third collaboration methods, after generating the first intermediate result, the relevant intelligent agent receives the user's correction and / or confirmation of the first intermediate result, and executes the next task according to the first intermediate result after the user's correction or confirmation. The first intermediate result includes at least one of the following: product survey report, customer survey report, questions generated by the material editing intelligent agent, answers generated by the material editing intelligent agent or product survey intelligent agent, and an outline or chapter of the explanatory material.

5. The method as described in claim 1, characterized in that, Also includes: When the material editing agent generates product explanation materials that match each customer type based on the customer survey report and the product survey report, it further generates explanation suggestions that match each customer type.

6. The method as described in claim 5, characterized in that, Also includes: For each customer type, the virtual customer agent and the virtual explanation agent generate or update the question-and-answer knowledge base corresponding to the customer type through at least one round of question-and-answer interaction. During the question-and-answer interaction, the virtual customer agent simulates a customer of the customer type based on the customer profile or customer characteristics of the customer type, and raises questions based on product explanation materials that match the customer type; the virtual explanation agent generates answers to the questions raised by the virtual customer agent based on at least one of the product survey report, product explanation materials, explanation suggestions, and product knowledge base.

7. The method as described in claim 6, characterized in that, Also includes: After each round of question-and-answer interaction, for each customer type, the material editing agent updates the product explanation materials and / or explanation suggestions that match the customer type based on the question-and-answer knowledge base corresponding to that customer type.

8. The method as described in claim 7, characterized in that, The updating methods for the product explanation materials and / or explanation suggestions include at least one of the following: a first updating method, a second updating method, a third updating method, and a fourth updating method; wherein, In the first update method, the virtual customer agent and the virtual explanation agent are the same agent, which generates a question-and-answer knowledge base corresponding to the customer type through a self-questioning and self-answering method; the material editing agent updates the product explanation materials and / or explanation suggestions based on the question-and-answer knowledge base; In the second update method, the virtual customer agent and the virtual explanation agent are different agents; the material editing agent updates the product explanation materials and / or explanation suggestions based on the question-and-answer knowledge base and information obtained through interaction with the customer survey agent and the product survey agent. In the third update method, the virtual customer agent and the virtual explanation agent are different agents; the virtual customer agent and the virtual explanation agent execute the question-and-answer interaction process and generate the question-and-answer knowledge base according to the task scheduling of the project manager agent; the material editing agent updates the product explanation materials and / or explanation suggestions based on the question-and-answer knowledge base according to the task scheduling of the project manager agent. The fourth update method is that, in the first, second, or third update method, after generating the second intermediate result, the relevant intelligent agent receives the user's correction and / or confirmation of the second intermediate result, and executes the next task according to the user's corrected or confirmed second intermediate result. The second intermediate result includes at least one of the following: the question generated by the virtual customer intelligent agent, the answer generated by the virtual explanation intelligent agent, and the modification method of the product explanation materials and / or explanation suggestions.

9. The method as described in claim 1, characterized in that, The digital demonstration agent selects product explanation materials that match the customer type of the on-site customer for demonstration. This includes: selecting a digital human image and demonstration method that match the customer type of the on-site customer; and demonstrating the product explanation materials that match the on-site customer through the selected digital human image and according to the selected demonstration method. The demonstration method includes on-site display and / or playback of the product explanation materials. If the product explanation materials do not match the target language used by the on-site customer, the digital demonstration agent's explanation text is converted into the target language and displayed. When the digital demonstration agent selects product explanation materials that match the customer type of the on-site customer for demonstration, it further selects explanation suggestions that match the on-site customer and demonstrates the product explanation materials according to the selected explanation suggestions.

10. The method as described in claim 1, characterized in that, Also includes: The material editing agent generates product explanation materials that match the fusion type based on the customer survey report and the product survey report. The fusion type includes at least two customer types, which are predetermined or determined based on the customer types of on-site customers.

11. The method as described in claim 6 or 7, characterized in that, Also includes: Based on the question-and-answer knowledge base, the feedback collection agent interacts with on-site customers and collects questions, answers, and feedback from on-site customers during the interaction process; wherein, when the feedback collection agent cannot answer or the answer cannot meet the requirements of on-site customers, the feedback collection agent collects the answer provided by the on-site human guide. The feedback collection agent updates the question-and-answer knowledge base based on the collected questions, answers, and feedback from on-site customers and provides it to the material editing agent and / or digital presentation agent; The material editing agent updates the product explanation materials and / or explanation suggestions based on the updated question-and-answer knowledge base.

12. The method as described in claim 6 or 7, characterized in that, Also includes: The live recording agent records interactive information during the demonstration process and generates meeting minutes and / or customer feedback reports corresponding to customer types.

13. A marketing display system based on multi-agent systems, characterized in that, This includes customer survey agents, product survey agents, material editing agents, and digital presentation agents, among which: The customer survey intelligent agent is used to generate a customer survey report, which includes customer types and customer profiles or customer characteristics for each customer type. The product survey agent is used to generate a product survey report for the target product. The material editing agent is used to generate product explanation materials that match each customer type based on the customer survey report and the product survey report; The digital demonstration agent is used to select product explanation materials that match the customer type at the site for demonstration.

14. A computer program product, characterized in that, Includes computer instructions that, when executed by a processor, implement the steps of the method as described in any one of claims 1 to 12.

Images