Product recommendation method and device based on large model, equipment, medium and product

Abstract

The embodiment of the invention provides a product recommendation method and device based on a large model, equipment, a medium and a product, and belongs to the technical field of artificial intelligence. The method comprises the following steps: inputting employee health data of an enterprise customer into a first model to obtain an employee health portrait of the enterprise customer; inputting the business information of the enterprise customer into the second model to obtain an enterprise health portrait of the enterprise customer; inputting the employee health portrait and the enterprise health portrait into a third model, and determining a recommended product of the enterprise customer; inputting the enterprise information of the enterprise customer and the recommended product into a fourth model, and simulating a communication scene with the enterprise customer based on the enterprise information of the enterprise customer and the recommended product through the fourth model to obtain a simulated communication record; generating a communication strategy with the enterprise customer based on the simulated communication record and the recommended product; the communication strategy is used for guiding to recommend products to enterprise customers. The method can be applied to business scenes such as financial science and technology, medical health and the like, and the accuracy of existing product recommendation can be improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a product recommendation method, device, equipment, medium and product based on a large model. Background Art

[0002] With the rapid development of the insurance industry, group commercial health insurance is gradually transitioning to online and digital platforms. This transformation has brought about the need for more efficient and accurate insurance product recommendation systems.

[0003] However, existing insurance product recommendation systems often rely on generic health advice and lack in-depth analysis of customer information. This general approach results in a lack of targeted recommendations and a failure to fully consider corporate customers' insurance needs and business risks, resulting in low product recommendation accuracy. Summary of the Invention

[0004] The main purpose of the embodiments of the present application is to propose a product recommendation method, device, equipment, medium and product based on a large model, aiming to improve the accuracy of product recommendations.

[0005] To achieve the above objectives, a first aspect of an embodiment of the present application proposes a product recommendation method based on a large model, the method comprising:

[0006] Inputting employee health data of the enterprise customer into a first model, and using the first model to analyze the employee's health status and health trend based on the employee health data to obtain a health profile of the employee of the enterprise customer;

[0007] Inputting the business information of the corporate customer into a second model, and analyzing the health risks of the corporate customer based on the business information using the second model to obtain a corporate health profile of the corporate customer;

[0008] Inputting the employee health profile and the corporate health profile into a third model, determining, by the third model, the employee insurance needs of the corporate client based on the employee health profile, and determining the basic insurance needs of the corporate client based on the corporate health profile, and determining recommended products for the corporate client based on the employee insurance needs and the basic insurance needs;

[0009] Inputting the corporate customer's corporate information and the recommended products into a fourth model, and using the fourth model to simulate a communication scenario with the corporate customer based on the corporate customer's corporate information and the recommended products to obtain a simulated communication record;

[0010] Based on the simulated communication record and the recommended product, a communication strategy with the corporate customer is generated; wherein the communication strategy is used to guide the recommendation of the recommended product to the corporate customer.

[0011] In some embodiments, after generating a communication strategy with the corporate customer based on the simulated communication record and the recommended product, the method includes:

[0012] In response to the information call from the enterprise customer, displaying the communication strategy so that the user can recommend the recommended product to the enterprise customer based on the communication strategy;

[0013] In response to the corporate customer confirming the recommended product, generating the recommended initial subscription contract based on the recommended product;

[0014] Execute the signing operation of the initial subscription contract.

[0015] In some embodiments, after executing the signing operation of the initial subscription contract, the method further includes:

[0016] Performing a compliance check on the initial order contract and the corporate customer's historical transaction behavior to obtain a compliance check result for the corporate customer;

[0017] Inputting historical risk cases of the corporate customer into a risk assessment model, analyzing the historical risk cases through the risk assessment model to obtain the risk level of the corporate customer;

[0018] Determining the ordering qualifications of the corporate customer based on the risk level and the compliance check results;

[0019] If the order qualification is met, generating a target order contract for the recommended product based on the initial order contract;

[0020] Execute the signing operation of the target subscription contract.

[0021] In some embodiments, after executing the signing operation of the target subscription contract, the method further includes:

[0022] In response to a claim request initiated by the corporate customer based on the target subscription contract, classifying claim cases corresponding to the claim request based on claim materials in the claim request;

[0023] determining a claims process for the claim case based on the classification result of the claim case; wherein, if the classification result is a simple claim case, the claims process is an automated claims process; and if the classification result is a complex claim case, the claims process is a manual claims process;

[0024] Execute the claims process as described.

[0025] In some embodiments, after executing the claim settlement process, the method further includes:

[0026] Obtaining a claim record corresponding to the claim request; wherein the claim record includes at least one of the following: claim amount, claim time, and claim reason;

[0027] The claim records and the business information of the enterprise user are input into the second model, and the health risks of the enterprise customers are analyzed based on the claim records and the business information by the second model to obtain a new enterprise health profile.

[0028] In some embodiments, before inputting the enterprise client's employee health data into the first model and analyzing the employee's health status and health trend based on the employee health data using the first model to obtain the enterprise client's employee health profile, the method further includes:

[0029] Obtaining first information of an employee of a corporate client; wherein the first information includes at least one of the following: accompanying medical records, family doctor consultation records, and health records;

[0030] The first information is input into a fifth model, and the fifth model is used to analyze the employees' care needs based on the accompanying records to obtain first data of the employees of the corporate client; the employees' illness conditions are analyzed based on the family doctor consultation records to obtain second data of the employees of the corporate client; and the employees' genetic risks are analyzed based on the health records to obtain third data of the employees of the corporate client; and the health data of the employees of the corporate client is determined based on the first data, the second data and the third data.

[0031] To achieve the above-mentioned objectives, a second aspect of the embodiments of the present application provides a product recommendation device based on a large model, the device comprising:

[0032] A first input module is configured to input employee health data of an enterprise client into a first model, and to analyze the employee's health status and health trend based on the employee health data using the first model to obtain a health profile of the employee of the enterprise client;

[0033] A second input module inputs the business information of the enterprise customer into a second model, and uses the second model to analyze the health risks of the enterprise customer based on the business information to obtain an enterprise health profile of the enterprise customer;

[0034] a third input module, inputting the employee health profile and the corporate health profile into a third model, determining, through the third model, the employee insurance needs of the corporate client based on the employee health profile, determining the basic insurance needs of the corporate client based on the corporate health profile, and determining recommended products for the corporate client based on the employee insurance needs and the basic insurance needs;

[0035] a fourth input module, inputting the corporate customer's corporate information and the recommended products into a fourth model, and using the fourth model to simulate a communication scenario with the corporate customer based on the corporate customer's corporate information and the recommended products to obtain a simulated communication record;

[0036] A generation module generates a communication strategy with the corporate customer based on the simulated communication record and the recommended product; wherein the communication strategy is used to guide the recommendation of the recommended product to the corporate customer. To achieve the above-mentioned purpose, a third aspect of an embodiment of the present application provides an electronic device, the electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the method described in the first aspect when executing the computer program.

[0037] To achieve the above-mentioned purpose, the fourth aspect of the embodiments of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the method described in the first aspect.

[0038] To achieve the above-mentioned purpose, the fifth aspect of the embodiments of the present application proposes a computer program product, which is stored in a storage medium and executed by at least one processor to implement the method described in the first aspect.

[0039] The large-model-based product recommendation method, device, equipment, medium and product proposed in this application first input the employee health data of the corporate customer into the first model, and analyze the employee's health status and health trend based on the employee health data through the first model to obtain the employee health portrait of the corporate customer; secondly, input the business information of the corporate customer into the second model, and analyze the health risks of the corporate customer based on the business information through the second model to obtain the corporate health portrait of the corporate customer; thirdly, input the employee health portrait and the corporate health portrait into the third model, and determine the employee insurance needs of the corporate customer based on the employee health portrait through the third model, and determine the basic insurance needs of the corporate customer based on the corporate health portrait, and determine the recommended products for the corporate customer based on the employee insurance needs and the basic insurance needs; input the corporate information and recommended products of the corporate customer into the fourth model, and simulate the communication scenario with the corporate customer based on the corporate information and recommended products of the corporate customer through the fourth model to obtain a simulated communication record; generate a communication strategy with the corporate customer based on the simulated communication record and the recommended products; wherein the communication strategy is used to guide the recommendation of products to the corporate customer. In this way, by comprehensively analyzing employee health portraits and corporate health portraits, we can provide personalized corporate customer insurance needs analysis and generate dynamically adjusted communication strategies to improve corporate customers' health management efficiency and the accuracy of product recommendations, thereby improving the accuracy of product recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a flowchart of a product recommendation method based on a large model provided in an embodiment of the present application;

[0041] Figure 2 yes Figure 1 Flowchart of step S105 in FIG.

[0042] Figure 3 yes Figure 2 The flowchart after step S203 in FIG.

[0043] Figure 4 yes Figure 3 The flowchart after step S305 in FIG.

[0044] Figure 5 yes Figure 4 The flowchart after step S403 in FIG.

[0045] Figure 6 yes Figure 1 The flowchart before step S101 in FIG.

[0046] Figure 7 This is a schematic diagram of the structure of the service processing device provided in an embodiment of the present application;

[0047] Figure 8This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0049] It should be noted that although the device schematics illustrate functional module divisions and the flowcharts illustrate logical sequences, in certain circumstances, the steps shown or described may be performed in a sequence that differs from the module divisions in the device or the sequence in the flowcharts. The terms "first," "second," and so on, in the specification, claims, and drawings, are used to distinguish similar items and are not necessarily used to describe a specific sequence or precedence.

[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0051] First, let’s analyze some of the terms used in this application:

[0052] Artificial intelligence (AI) is a new technical discipline that studies and develops theories, methods, technologies, and application systems for simulating, extending, and expanding human intelligence. A branch of computer science, AI seeks to understand the essence of intelligence and produce new intelligent machines that can respond in a manner similar to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing, and expert systems. AI can simulate the information processes of human consciousness and thinking. It also encompasses the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, to perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results.

[0053] Natural language processing (NLP): NLP uses computers to process, understand, and apply human languages ​​(such as Chinese and English). A branch of artificial intelligence, NLP is an interdisciplinary field between computer science and linguistics, often referred to as computational linguistics. Natural language processing encompasses grammatical analysis, semantic analysis, and discourse comprehension. Natural language processing is commonly used in technical fields such as machine translation, handwritten and printed character recognition, speech recognition and text-to-speech conversion, information intent recognition, information extraction and filtering, text classification and clustering, public opinion analysis, and opinion mining. It encompasses data mining, machine learning, knowledge acquisition, knowledge engineering, artificial intelligence research related to language processing, and linguistics research related to language computing.

[0054] Information Extraction: A text processing technology that extracts specified types of entity, relationship, event, and other factual information from natural language text and forms structured data output. Information extraction is a technology that extracts specific information from text data. Text data is composed of some specific units, such as sentences, paragraphs, and chapters. Text information is composed of some small specific units, such as characters, words, phrases, sentences, paragraphs, or a combination of these specific units. Extracting noun phrases, names, place names, etc. from text data is all text information extraction. Of course, the information extracted by text information extraction technology can be of various types.

[0055] Image description generates a natural language description for an image and uses the generated description to help applications understand the semantics expressed in the image's visual scene. For example, image description can convert image retrieval into text retrieval, which is used to classify images and improve image retrieval results. People can usually describe the details of an image's visual scene with just a quick glance, but automatically adding descriptions to images is a comprehensive and arduous computer vision task that requires converting the complex information contained in the image into a natural language description. Compared to ordinary computer vision tasks, image captioning not only requires identifying objects from images, but also requires associating the identified objects with natural semantics and describing them in natural language. Therefore, image description requires people to extract deep features of the image, associate them with semantic features, and convert them to generate descriptions.

[0056] Models are a crucial concept in technology, particularly in data analysis, machine learning, and artificial intelligence. A model is a mathematical or computational framework used to describe, analyze, and predict patterns and relationships in data. Models can be built using a variety of algorithms and techniques to solve diverse problems, such as classification, regression, and clustering.

[0057] Insurance is a risk transfer mechanism that, through an insurance contract, transfers the risk of losses faced by individuals or businesses to an insurance company. In return for premiums, the insurance company provides financial protection to the insured against potential insurance accidents. The core functions of insurance are risk diversification, financial compensation, and wealth management.

[0058] Insurance products are financial instruments designed to provide individuals or businesses with financial protection against potential losses from specific risk events (such as illness, accidents, and natural disasters). Insurance products distribute risk among multiple policyholders through premiums. When an insured person experiences an insurance accident, the insurance company pays compensation or provides corresponding services as agreed in the contract. Common insurance products include life insurance, health insurance, property insurance, accident insurance, liability insurance, and trust insurance.

[0059] Claims settlement is the process by which an insurance company handles a claim for compensation or payment from the insured or beneficiary, according to the terms of the insurance contract, after the occurrence of an insurance event. Claims settlement is a crucial aspect of the insurance industry, directly impacting both the interests of customers and the reputation of the insurance company.

[0060] With the rapid development of the insurance industry, group commercial health insurance is gradually transitioning to an online and digital model. This transformation has created a demand for more efficient and accurate insurance product recommendation systems. However, existing insurance product recommendation systems often rely on general health advice and lack in-depth analysis of customer information. This general approach results in a lack of targeted recommendations and a failure to fully consider corporate customers' insurance needs and business risks, resulting in low product recommendation accuracy.

[0061] Based on this, the embodiments of the present application provide a product recommendation method, device, equipment, medium and product based on a large model, aiming to improve the accuracy of existing product recommendations.

[0062] The large-model-based product recommendation method, apparatus, device, medium, and product provided in the embodiments of the present application are specifically illustrated through the following embodiments. First, the large-model-based product recommendation method in the embodiments of the present application is described.

[0063] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0064] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0065] The product recommendation method based on a large model provided in the embodiment of the present application relates to the field of computer processing technology. The product recommendation method based on a large model provided in the embodiment of the present application can be applied to a terminal, can be applied to a server side, or can be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or as a server cluster or distributed system composed of multiple physical servers, or as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements a product recommendation method based on a large model, etc., but is not limited to the above forms.

[0066] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0067] It should be noted that in each specific embodiment of the present application, when it comes to the need to perform relevant processing based on data related to the user's identity or characteristics, such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of such data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0068] It should be noted that the recommended products in this application may be insurance products, medical products, or other types of products.

[0069] Figure 1 This is an optional flowchart of the product recommendation method based on a large model provided in an embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S106.

[0070] Step S101: inputting employee health data of an enterprise customer into a first model, and using the first model to analyze the employee's health status and health trend based on the employee health data to obtain a health profile of the employee of the enterprise customer;

[0071] In step S101 of some embodiments, employee health data of a corporate client is obtained, and the employee health data is input into a first model. The first model analyzes the employee's health status and health trend based on the employee health data and outputs an employee health portrait.

[0072] It should be noted that employee health data may include employees' care needs, illness conditions, genetic risks, physical examination reports and lifestyle data (such as exercise, diet, sleep, etc.).

[0073] Employee health profiles can be detailed health status and health trend analyses generated based on employee health data.

[0074] Step S102: inputting the business information of the enterprise customer into a second model, and analyzing the health risk of the enterprise customer based on the business information by the second model to obtain an enterprise health profile of the enterprise customer;

[0075] In step S102 of some embodiments, business information of the corporate customer is obtained and input into the second model. The second model analyzes the health risks of the enterprise based on the business information and outputs a health portrait of the enterprise.

[0076] It should be noted that business information may include the company's industry type, common industry diseases, number of employees, business scale, financial status, etc. The corporate health profile can be a comprehensive health risk assessment generated based on the company's business information. The corporate health profile can include data such as business information and the health risks corresponding to the business information.

[0077] Step S103: Inputting the employee health profile and the corporate health profile into a third model, using the third model to determine the corporate client's employee insurance needs based on the employee health profile, and to determine the corporate client's basic insurance needs based on the corporate health profile, and finally determining recommended products for the corporate client based on the employee insurance needs and the basic insurance needs;

[0078] In step S103 of some embodiments, the employee health profile and the corporate health profile are input into a third model. The third model determines the employee insurance needs based on the employee health profile, determines the basic insurance needs based on the corporate health profile, and determines the recommended products based on the two needs.

[0079] It should be noted that insurance needs can be the types and range of insurance products that employees and companies may need based on health profile analysis. Recommended products can be specific insurance products determined based on insurance needs.

[0080] Step S104: inputting the corporate customer's corporate information and the recommended products into a fourth model, and using the fourth model to simulate a communication scenario with the corporate customer based on the corporate customer's corporate information and the recommended products to obtain a simulated communication record;

[0081] In step S104 of some embodiments, the enterprise information and recommended products are input into the fourth model, and the fourth model simulates the communication scenario with the enterprise customer and generates a simulated communication record.

[0082] It should be noted that simulated communication records can be generated by simulating the process of communicating with corporate customers through the model, generating possible conversation content and customer feedback. Corporate information is used by the fourth model to identify the corresponding corporate customers.

[0083] Step S105 , generating a communication strategy with the corporate customer based on the simulated communication record and the recommended product; wherein the communication strategy is used to guide the recommendation of the recommended product to the corporate customer.

[0084] In step S105 of some embodiments, a communication strategy with the corporate customer is generated based on the simulated communication records and recommended products. The communication strategy is used to guide how to recommend recommended products determined based on the two needs to the corporate customer.

[0085] It should be noted that communication strategies can be generated based on simulated communication records and recommended products to guide specific strategies for communicating with corporate customers.

[0086] In some implementations, a decision tree can be used to analyze recommended products and historical communication records to generate a communication strategy.

[0087] In other embodiments, situational simulation techniques (eg, role playing, case analysis) can be used to generate communication strategies.

[0088] Steps S101 to S104 shown in the embodiment of the present application first input the employee health data of the corporate customer into the first model, and analyze the health status and health trends of the employees based on the employee health data through the first model to obtain the employee health portrait of the corporate customer; secondly, input the business information of the corporate customer into the second model, and analyze the health risks of the corporate customer based on the business information through the second model to obtain the corporate health portrait of the corporate customer; thirdly, input the employee health portrait and the corporate health portrait into the third model, and determine the employee insurance needs of the corporate customer based on the employee health portrait through the third model, and determine the basic insurance needs of the corporate customer based on the corporate health portrait, and determine the recommended products for the corporate customer based on the employee insurance needs and the basic insurance needs; input the corporate information and recommended products of the corporate customer into the fourth model, and simulate the communication scenario with the corporate customer based on the corporate information and recommended products of the corporate customer through the fourth model to obtain a simulated communication record; based on the simulated communication record and the recommended products, generate a communication strategy with the corporate customer; wherein the communication strategy is used to guide the recommendation of products to the corporate customer. In this way, by comprehensively analyzing employee health portraits and corporate health portraits, we can provide personalized corporate customer insurance needs analysis and generate dynamically adjusted communication strategies to improve corporate customers' health management efficiency and the accuracy of product recommendations, thereby improving the accuracy of product recommendations.

[0089] See also Figure 2 In some embodiments, step S105 may include but is not limited to steps S201 to S204:

[0090] Step S201, in response to the information call of the corporate customer, displaying the communication strategy so that the user can recommend the recommended product to the corporate customer based on the communication strategy;

[0091] In step S201 of some embodiments, an information call request from a corporate customer is obtained, the information call request from the corporate customer is responded to, and a previously generated communication strategy is displayed.

[0092] It should be noted that information calls can be corporate customers' requests to view recommended products and communication strategies. Recommended products can be insurance products determined based on the corporate customer's employee health profile and corporate health profile.

[0093] Step S202 , in response to the corporate customer confirming the recommended product, generating the recommended initial order contract based on the recommended product;

[0094] In step S202 of some embodiments, after receiving confirmation information of the corporate customer for the recommended product, an initial order contract is quickly generated.

[0095] It should be noted that the initial order contract can be a preliminary contract generated after the corporate customer confirms the recommended product, which includes product details, price, terms and other information.

[0096] Step S203: executing the signing operation of the initial order contract.

[0097] In step S203 of some embodiments, a contract signing operation is performed, and the signing operation may include steps such as electronic signature, contract sending, and confirmation.

[0098] It should be noted that the signing operation may be the process of completing the contract signing.

[0099] In some implementations, the final contract signing operation can be achieved through technologies such as electronic signatures.

[0100] In some implementations, the final contract signing operation can be completed through manual on-site confirmation.

[0101] This embodiment of the application provides users with a clear communication guide by displaying a communication strategy, helping them communicate more effectively with corporate clients and improving communication efficiency. After the corporate client confirms the recommended product, a contract is quickly generated. This not only reduces manual intervention and improves the efficiency and accuracy of contract generation, but also allows for rapid response to customer needs and enhanced customer trust in the partnership. Signing ensures that the transaction between the corporate client and the insurance company is officially effective, enhancing security.

[0102] See also Figure 3 In some embodiments, after step S203, the following steps may be performed, but not limited to, steps S301 to S304:

[0103] Step S301: Perform a compliance check on the initial order contract and the corporate customer's historical transaction behavior to obtain a compliance check result for the corporate customer;

[0104] In step S301 of some embodiments, the initial order contract and the historical transaction behavior data of the corporate customer are obtained, and a compliance check is performed on the initial order contract and the historical transaction behavior of the corporate customer to consider whether the contract content and transaction behavior comply with relevant laws, regulations and company policies, and then obtain compliance check results.

[0105] It should be noted that compliance checks can be checks on whether contracts and transactions comply with laws, regulations, and company policies. Historical transaction behavior can be the past transaction records and behavior data of corporate customers.

[0106] In some implementations, compliance checking can be performed using automated tools and rule engines.

[0107] In other implementations, compliance checks may be performed manually by compliance experts.

[0108] Step S302: Inputting historical risk cases of the enterprise customer into a risk assessment model, analyzing the historical risk cases through the risk assessment model, and obtaining the risk level of the enterprise customer;

[0109] In step S302 of some embodiments, historical risk case data of enterprise customers is obtained, and the historical risk case data is input into a risk assessment model. The model analyzes the historical risk cases and assesses the risk level of the enterprise.

[0110] It should be noted that the risk assessment model may be a model used to assess the risk level of a corporate client. Historical risk cases may be past risk events and cases of the corporate client. The risk level may be the result of the corporate client's risk level assessment.

[0111] In some embodiments, a machine learning model can be used to analyze historical risk cases and assess risk levels.

[0112] In other implementations, pre-set rules and thresholds may be used to perform risk assessment and determine risk levels.

[0113] Step S303: determining the subscription qualification of the corporate customer based on the risk level and the compliance check result;

[0114] In step S303 of some embodiments, whether the corporate customer has the ordering qualifications is determined in combination with the risk level and the compliance check result.

[0115] It should be noted that ordering qualifications can refer to whether the corporate customer is eligible to sign a contract.

[0116] In some implementations, subscription eligibility can be determined using automated tools and a rules engine.

[0117] In other implementations, the order qualifications may be manually reviewed by qualification review experts.

[0118] In some implementations, if the enterprise customer's risk level is low and the inspection is compliant, the subscription qualification is qualified.

[0119] In some implementations, if a customer's risk level is medium and they pass the inspection, they are considered eligible for the order. Even if they are eligible, the enterprise customer will still need to meet additional conditions (such as providing a guarantee or adjusting the contract terms) before the contract can be signed.

[0120] In some implementations, if the customer's risk level is high or the inspection is non-compliant, the subscription qualification is disqualified.

[0121] Step S304: if the order qualification is qualified, generating a target order contract for the recommended product based on the initial order contract;

[0122] In step S304 of some embodiments, if the ordering qualifications are met, a final target ordering contract is generated based on the initial ordering contract.

[0123] It should be noted that the target ordering contract may be the final generated contract, and the target ordering contract may include information such as product details, price, and terms.

[0124] In some implementations, a contract generation tool may be used to automatically generate a target subscription contract.

[0125] In other implementations, contract experts may manually draft and review the contract to obtain the target ordering contract.

[0126] Step S305: executing the signing operation of the target ordering contract.

[0127] In step S305 of some embodiments, a signing operation of the target ordering contract is performed. The signing operation may include steps such as electronic signature, contract sending, and confirmation to obtain a signed contract.

[0128] The embodiments of the present application can ensure that contracts and transaction behaviors comply with laws and regulations and reduce potential legal disputes by conducting compliance checks on initial order contracts and historical transaction behaviors of corporate customers. By conducting risk assessments on corporate customers, a basis can be provided for determining subsequent order qualifications. Through qualification review, risks are controlled and the security of transactions is ensured. At the same time, cooperation with qualified corporate customers is ensured to improve business quality. By generating target order contracts for recommended products, manual intervention can be reduced, the efficiency and accuracy of contract generation can be improved, and the consistency and completeness of contract content can be ensured, reducing errors and omissions.

[0129] See also Figure 4 In some embodiments, after step S305, the following steps may be performed, but not limited to, steps S401 to S402:

[0130] Step S401: In response to a claim request initiated by the corporate customer based on the target subscription contract, classify the claim cases corresponding to the claim request based on the claim materials in the claim request;

[0131] In step S401 of some embodiments, after receiving the claim request from the customer, the claim cases are classified according to the claim materials submitted by the corporate customer.

[0132] It should be noted that a claim request can be a compensation request submitted by a corporate customer under a target order contract. Claim materials can be various documents and information used to support the claim request. A claim case can be a specific claim incident corresponding to a claim request, including all related requests and handling procedures.

[0133] Step S402: Determine the claim settlement process for the claim case based on the classification result of the claim case; if the classification result is a simple claim case, the claim settlement process is an automated claim settlement process; if the classification result is a complex claim case, the claim settlement process is a manual claim settlement process;

[0134] In step S402 of some embodiments, a claim processing procedure is determined based on the classification result. Simple claim cases adopt an automated claim processing procedure, while complex claim cases adopt a manual claim processing procedure.

[0135] It should be noted that the claims process can refer to the steps and procedures for handling claims requests. Simple claims cases are those with complete claim documentation, clear facts, clear responsibilities, and no need for further investigation. Complex claims cases are those with incomplete claim documentation, unclear facts, unclear responsibilities, requiring further investigation, or disputed. An automated claims process is one that handles simple claims through pre-set rules and automated systems. For example, the claims system automatically reviews claim documentation and calculates compensation amounts. A manual claims process is one that handles complex claims with human intervention. For example, it involves on-site inspections, manual review of claim documentation, and negotiation of compensation plans with the customer.

[0136] Step S403: executing the claim settlement process.

[0137] In some embodiments, in step S403, the claim request is processed according to the determined claims process. Automated processes are automatically completed by the system, while manual processes are handled by dedicated personnel. The claims process may include compensation calculation, payment execution, and customer communication, ensuring transparency and fairness in the claims process.

[0138] For example, after a customer uploads their claim materials, the claims system automatically identifies key information (such as medical receipts and diagnostic reports) and quickly completes the review. For complex cases, the claims system automatically assigns them to human reviewers, further improving claims processing efficiency.

[0139] The embodiments of the present application can quickly process claims requests and reduce customer waiting time through the reasonable allocation of automated and manual processes. Appropriate processing procedures are selected according to the complexity of the claims case to provide services that better meet the needs of corporate customers. At the same time, 7×24 hours of efficient service are provided to corporate customers to improve corporate customer satisfaction. Simple claims cases are handled through automated processes, and complex claims cases are handled through manual processes, which rationally allocates corporate resources and improves overall case processing efficiency. A transparent and fair claims process can enhance corporate customers' trust in the user company and improve customer loyalty.

[0140] See also Figure 5 In some embodiments, after step S403, the following steps may be performed, but not limited to, steps S501 to S502:

[0141] Step S501: Obtain a claim record corresponding to the claim request; wherein the claim record includes at least one of the following: claim amount, claim time, and claim reason;

[0142] In step S501 of some embodiments, a claim record related to the claim request is obtained, and the claim record includes at least the claim amount, claim time and claim reason.

[0143] It should be noted that the claim record can be detailed information related to the claim request, including the claim amount, claim time and claim reason, etc.

[0144] In some implementations, automated tools may be used to extract claim records from the claims system.

[0145] In other implementations, the claim record may be entered manually by staff.

[0146] Step S502: Input the claim settlement record and the business information of the enterprise user into the second model, analyze the health risk of the enterprise customer based on the claim settlement record and the business information through the second model, and obtain a new enterprise health profile.

[0147] It should be noted that the second model may be a model for analyzing the health risks of corporate customers.

[0148] In step S502 of some embodiments, claim records and business information of corporate customers are obtained, and the claim records and business information are input into a second model. The model analyzes the health risks of the enterprise based on the claim records and business information of the corporate customers and generates a new corporate health profile.

[0149] In some implementations, machine learning models can be used to analyze claims records and business information to generate new enterprise health profiles.

[0150] In other implementations, health risk assessment experts may perform manual analysis to generate a new corporate health profile.

[0151] The embodiment of the present application collects detailed information on claim requests, i.e., claim records, to provide data support for subsequent health risk analysis. By updating the enterprise health profile to reflect the latest health status and risk changes, the accuracy of health risk assessment is improved.

[0152] See also Figure 6 In some embodiments, before step S101, the following steps may be included but not limited to steps S601 to S602:

[0153] Step S601: Acquire first information of an employee of a corporate client; wherein the first information includes at least one of the following: medical accompaniment records, family doctor consultation records, and health records;

[0154] In step S601 of some embodiments, first information of employees of the corporate client is collected, where the first information includes at least medical accompaniment records, family doctor consultation records, and health records.

[0155] It should be noted that the first information can be corporate client employee information, including medical accompaniment records, family doctor consultation records, and health records. Medical accompaniment records can be specific records of an employee's medical accompaniment, including the time, reason, and results of the appointment. Family doctor consultation records can be specific records of an employee's consultation with their family doctor, including the time, content, and results of the consultation. Health records can be the employee's health records, including personal medical history, family medical history, and lifestyle.

[0156] In some implementations, an automated tool may be used to extract the first information from the business client's information system.

[0157] In other implementations, the first information may be obtained through questionnaires, manual recording, and the like.

[0158] Step S602: input the first information into a fifth model, analyze the nursing needs of the employees based on the accompanying records through the fifth model, and obtain the first data of the employees of the corporate client; analyze the illness conditions of the employees based on the family doctor consultation records to obtain the second data of the employees of the corporate client; and analyze the genetic risks of the employees based on the health records to obtain the third data of the employees of the corporate client; and determine the health data of the employees of the corporate client based on the first data, the second data and the third data.

[0159] In step S602 of some embodiments, the accompanying medical records are input into a fifth model to analyze the employee's care needs, obtaining first data. The family doctor consultation records are input into the fifth model to analyze the employee's medical conditions, obtaining second data. The health records are input into the fifth model to analyze the employee's genetic risks, obtaining third data. The first, second, and third data are combined to determine the corporate client's employee health data, which includes care needs, medical conditions, and genetic risks.

[0160] It should be noted that the fifth model can be used to analyze employee health data, capable of processing multi-dimensional data and generating comprehensive health data. The first data can be employee care needs data obtained through analysis of accompanying medical records. The second data can be employee illness data obtained through analysis of family doctor consultation records. The third data can be employee genetic risk data obtained through analysis of health records.

[0161] In some embodiments, a machine learning model can be used to analyze accompanying medical records, family doctor consultation records, and health records to generate employee health data.

[0162] In other implementations, health experts may perform manual analysis to obtain employee health data.

[0163] By collecting employee information from corporate clients, this embodiment of the application ensures that the collected data is comprehensive and facilitates subsequent analysis. By assessing employee health from multiple perspectives, more comprehensive employee health data can be provided, which can also provide accurate data support for subsequent insurance product recommendations.

[0164] See also Figure 7 The present application also provides a large-model-based product recommendation device that can implement the above-mentioned large-model-based product recommendation method. The device includes:

[0165] A first input module 701 is configured to input employee health data of an enterprise client into a first model, and to analyze the employee's health status and health trend based on the employee health data using the first model to obtain a health profile of the employee of the enterprise client;

[0166] A second input module 702 inputs the business information of the enterprise customer into a second model, and uses the second model to analyze the health risk of the enterprise customer based on the business information to obtain an enterprise health profile of the enterprise customer;

[0167] A third input module 703 inputs the employee health profile and the corporate health profile into a third model, determines the corporate client's employee insurance needs based on the employee health profile, determines the corporate client's basic insurance needs based on the corporate health profile, and determines recommended products for the corporate client based on the employee insurance needs and the basic insurance needs.

[0168] A fourth input module 704 inputs the corporate customer's corporate information and the recommended products into a fourth model, and uses the fourth model to simulate a communication scenario with the corporate customer based on the corporate customer's corporate information and the recommended products to obtain a simulated communication record;

[0169] The generation module 705 generates a communication strategy with the corporate customer based on the simulated communication record and the recommended product; wherein the communication strategy is used to guide the recommendation of the recommended product to the corporate customer.

[0170] The specific implementation of the large model-based product recommendation device is basically the same as the specific embodiment of the large model-based product recommendation method described above, and will not be repeated here.

[0171] The present application also provides an electronic device comprising a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the aforementioned large-model-based product recommendation method. The electronic device can be any smart terminal, including a tablet computer and an in-vehicle computer.

[0172] See also Figure 8 , Figure 8 The hardware structure of an electronic device according to another embodiment is shown. The electronic device includes:

[0173] The processor 801 may be implemented as a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application.

[0174] The memory 802 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 802 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 802 and is called by the processor 801 to execute the large model-based product recommendation method of the embodiments of this application.

[0175] Input / output interface 803, used to implement information input and output;

[0176] Communication interface 804, used to implement communication interaction between this device and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WiFi, Bluetooth, etc.);

[0177] Bus 805 , which transmits information between various components of the device (e.g., processor 801 , memory 802 , input / output interface 803 , and communication interface 804 );

[0178] The processor 801 , the memory 802 , the input / output interface 803 and the communication interface 804 are connected to each other in communication within the device via a bus 805 .

[0179] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned large model-based product recommendation method.

[0180] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0181] In addition, an embodiment of the present application provides a computer program product, which is stored in a storage medium and is executed by at least one processor to implement the various processes of the above-mentioned large model-based product recommendation method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0182] The embodiments of the present application provide a large-model-based product recommendation method, apparatus, equipment, medium, and product. First, by inputting the employee health data of the corporate customer into a first model, the first model analyzes the employee's health status and health trend based on the employee health data to obtain the employee health portrait of the corporate customer; secondly, the business information of the corporate customer is input into a second model, and the second model analyzes the health risks of the corporate customer based on the business information to obtain the corporate health portrait of the corporate customer; thirdly, the employee health portrait and the corporate health portrait are input into a third model, and the third model determines the employee insurance needs of the corporate customer based on the employee health portrait, and determines the basic insurance needs of the corporate customer based on the corporate health portrait, and determines the recommended products for the corporate customer based on the employee insurance needs and the basic insurance needs; the corporate information and recommended products of the corporate customer are input into a fourth model, and the fourth model simulates the communication scenario with the corporate customer based on the corporate information and recommended products to obtain a simulated communication record; based on the simulated communication record and the recommended products, a communication strategy with the corporate customer is generated; wherein the communication strategy is used to guide product recommendations to the corporate customer. In this way, by comprehensively analyzing employee health portraits and corporate health portraits, we can provide personalized corporate customer insurance needs analysis and generate dynamically adjusted communication strategies to improve corporate customers' health management efficiency and the accuracy of product recommendations, thereby improving the accuracy of product recommendations.

[0183] The embodiments described in the embodiments of this application are intended to more clearly illustrate the technical solutions of the embodiments of this application and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0184] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0185] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0186] Those skilled in the art will appreciate that all or some of the steps in the methods, systems, and functional modules / units in the devices disclosed above may be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0187] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0188] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0189] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the above-mentioned units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0190] The units described above as separate components may or may not be physically separate, and 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 these units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0191] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0192] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes multiple instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes various media that can store programs, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0193] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but are not intended to limit the scope of the present invention. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and essence of the present invention should be within the scope of the present invention.

Claims

1. A product recommendation method based on a large model, characterized in that: The method comprises: Inputting employee health data of the enterprise customer into a first model, and using the first model to analyze the employee's health status and health trend based on the employee health data to obtain a health profile of the employee of the enterprise customer; Inputting the business information of the corporate customer into a second model, and analyzing the health risks of the corporate customer based on the business information using the second model to obtain a corporate health profile of the corporate customer; Inputting the employee health profile and the corporate health profile into a third model, determining, by the third model, the employee insurance needs of the corporate client based on the employee health profile, and determining the basic insurance needs of the corporate client based on the corporate health profile, and determining recommended products for the corporate client based on the employee insurance needs and the basic insurance needs; Inputting the corporate customer's corporate information and the recommended products into a fourth model, and using the fourth model to simulate a communication scenario with the corporate customer based on the corporate customer's corporate information and the recommended products to obtain a simulated communication record; Based on the simulated communication record and the recommended product, a communication strategy with the corporate customer is generated; wherein the communication strategy is used to guide the recommendation of the recommended product to the corporate customer.

2. The method according to claim 1, wherein After generating a communication strategy with the corporate customer based on the simulated communication record and the recommended product, the method includes: In response to the information call from the enterprise customer, displaying the communication strategy so that the user can recommend the recommended product to the enterprise customer based on the communication strategy; In response to the corporate customer confirming the recommended product, generating the recommended initial subscription contract based on the recommended product; Execute the signing operation of the initial subscription contract.

3. The method according to claim 2, wherein After the execution of the signing operation of the initial subscription contract, the method further includes: Performing a compliance check on the initial order contract and the corporate customer's historical transaction behavior to obtain a compliance check result for the corporate customer; Inputting historical risk cases of the corporate customer into a risk assessment model, analyzing the historical risk cases through the risk assessment model to obtain the risk level of the corporate customer; Determining the ordering qualifications of the corporate customer based on the risk level and the compliance check results; If the order qualification is met, generating a target order contract for the recommended product based on the initial order contract; Execute the signing operation of the target subscription contract.

4. The method according to claim 3, wherein After executing the signing operation of the target subscription contract, the method further includes: In response to a claim request initiated by the corporate customer based on the target subscription contract, classifying claim cases corresponding to the claim request based on claim materials in the claim request; determining a claims process for the claim case based on the classification result of the claim case; wherein, if the classification result is a simple claim case, the claims process is an automated claims process; and if the classification result is a complex claim case, the claims process is a manual claims process; Execute the claims process as described.

5. The method according to claim 4, wherein After executing the claim settlement process, the method further includes: Obtaining a claim record corresponding to the claim request; wherein the claim record includes at least one of the following: claim amount, claim time, and claim reason; The claim records and the business information of the enterprise user are input into the second model, and the health risks of the enterprise customers are analyzed based on the claim records and the business information by the second model to obtain a new enterprise health profile.

6. The method according to claim 1, wherein Before inputting the employee health data of the enterprise client into the first model, and analyzing the employee's health status and health trend based on the employee health data using the first model to obtain the employee health profile of the enterprise client, the method further includes: Obtaining first information of an employee of a corporate client; wherein the first information includes at least one of the following: accompanying medical records, family doctor consultation records, and health records; The first information is input into a fifth model, and the fifth model is used to analyze the employees' care needs based on the accompanying records to obtain first data of the employees of the corporate client; the employees' illness conditions are analyzed based on the family doctor consultation records to obtain second data of the employees of the corporate client; and the employees' genetic risks are analyzed based on the health records to obtain third data of the employees of the corporate client; and the health data of the employees of the corporate client is determined based on the first data, the second data and the third data.

7. A product recommendation device based on a large model, characterized in that: The device comprises: A first input module is configured to input employee health data of an enterprise client into a first model, and to analyze the employee's health status and health trend based on the employee health data using the first model to obtain a health profile of the employee of the enterprise client; A second input module inputs the business information of the enterprise customer into a second model, and uses the second model to analyze the health risks of the enterprise customer based on the business information to obtain an enterprise health profile of the enterprise customer; a third input module, inputting the employee health profile and the corporate health profile into a third model, determining, through the third model, the employee insurance needs of the corporate client based on the employee health profile, determining the basic insurance needs of the corporate client based on the corporate health profile, and determining recommended products for the corporate client based on the employee insurance needs and the basic insurance needs; a fourth input module, inputting the corporate customer's corporate information and the recommended products into a fourth model, and using the fourth model to simulate a communication scenario with the corporate customer based on the corporate customer's corporate information and the recommended products to obtain a simulated communication record; A generation module generates a communication strategy with the corporate customer based on the simulated communication record and the recommended product; wherein the communication strategy is used to guide the recommendation of the recommended product to the corporate customer.

8. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the large model-based product recommendation method according to any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the product recommendation method based on a large model according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the large model-based product recommendation method according to any one of claims 1 to 6.

Images