Internet insurance marketing method and system based on social network
By collecting and analyzing social network data in Internet insurance marketing, generating a personalized insurance product recommendation list, and adjusting it in real time, the problem of insufficient accuracy and timeliness in the existing technology is solved, and the user experience is improved.
Patent Information
- Application Number
- CN202510539342.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-27
- Publication Date
- 2025-08-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing technology lacks the ability to deeply mine user data and cannot fully utilize the information resources provided by social networks, resulting in insufficient accuracy and timeliness of Internet insurance recommendations, and lacks an effective feedback mechanism, which makes the user experience poor.
The data collection module obtains the target user's public data and basic insurance data, analyzes and processes it to identify insurance needs and risk preference scores, generate recommendation lists, and collects user feedback information in real time for adjustment.
It improves the accuracy and timeliness of Internet insurance recommendations, enhances user experience, and meets personalized needs through dynamic adjustment and optimization.
Smart Images
Figure CN120450874A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of monitoring and analysis technology, and in particular to a social network-based Internet insurance marketing method and system. Background Art
[0002] With the rapid development of the internet and social networks, the insurance industry is gradually shifting online, and leveraging social networking platforms for precision marketing has become a trend. Social networks not only provide a wealth of user data but also leverage information such as users' social behaviors, interests, and lifestyles to help insurance companies better understand customer needs and provide personalized insurance product recommendations. This data-driven marketing approach not only improves marketing precision but also enhances user engagement and satisfaction. Furthermore, leveraging the communication power of social networks, insurance products can reach potential customers more quickly, expanding market reach.
[0003] In related technologies, traditional marketing systems often lack the ability to deeply mine user data and are unable to fully utilize the rich information resources provided by social networks, thereby reducing the accuracy and timeliness of Internet insurance recommendations. They also lack an effective feedback mechanism and are unable to dynamically adjust and optimize based on real-time user feedback, resulting in poor user experience and areas for improvement. Summary of the Invention
[0004] In response to the deficiencies of the existing technology, the present application provides an Internet insurance marketing method and system based on social networks.
[0005] In a first aspect, the present application provides an Internet insurance marketing system based on a social network, comprising: Data collection module, used to collect public data corresponding to target users and basic data corresponding to each insurance; The analysis module is used to analyze and process the public data corresponding to the target user, and based on the analysis and processing results, identify the target user's corresponding insurance demand score and risk preference score, analyze and process the basic data corresponding to each insurance, and then determine the risk level assessment coefficient corresponding to each insurance; The recommendation module is used to comprehensively analyze the insurance demand score, risk preference score and risk level assessment coefficient of each insurance corresponding to the target user, generate a list of recommended insurance products, and then push the recommended insurance products list to the target user; The feedback module is used to collect user feedback on the insurance product recommendation list in real time, then determine the feedback score, and adjust the insurance product recommendation list based on the feedback score.
[0006] Preferably, the public data corresponding to the target user includes insurance demand data and risk preference data, and the basic data corresponding to each insurance includes product type, product coverage and product price.
[0007] Preferably, the public data corresponding to the target user is analyzed and processed, specifically including: Obtaining insurance demand data corresponding to the target user, extracting statistical feature scores, behavioral feature scores, and historical insurance data scores corresponding to the target user from the insurance demand data, and performing linear normalization processing on the statistical feature scores, behavioral feature scores, and historical insurance data scores; By formula , confirm the insurance demand score corresponding to the target user ,in, They are respectively represented as the statistical feature score, behavioral feature score, and historical insurance data score corresponding to the target user. Expressed as a preset weight coefficient; Obtaining risk preference data corresponding to the target user, extracting a behavioral risk characteristic score, a sentiment analysis score, and a historical insurance risk data score corresponding to the target user from the risk preference data, and performing linear normalization processing on the behavioral risk characteristic score, sentiment analysis score, and historical insurance risk data score corresponding to the target user; By formula , confirm the risk preference score corresponding to the target user ,in, They are respectively represented as the behavioral risk feature score, sentiment analysis score, and historical insurance risk data score corresponding to the target user. Expressed as a preset weight coefficient.
[0008] Preferably, the public data corresponding to the target user is analyzed and processed, specifically including: Obtaining insurance demand data corresponding to the target user, extracting statistical feature scores, behavioral feature scores, and historical insurance data scores corresponding to the target user from the insurance demand data, and performing linear normalization processing on the statistical feature scores, behavioral feature scores, and historical insurance data scores; By formula , confirm the insurance demand score corresponding to the target user ,in, They are respectively represented as the statistical feature score, behavioral feature score, and historical insurance data score corresponding to the target user. Expressed as a preset weight coefficient; Obtaining risk preference data corresponding to the target user, extracting a behavioral risk characteristic score, a sentiment analysis score, and a historical insurance risk data score corresponding to the target user from the risk preference data, and performing linear normalization processing on the behavioral risk characteristic score, sentiment analysis score, and historical insurance risk data score corresponding to the target user; By formula , confirm the risk preference score corresponding to the target user ,in, They are respectively represented as the behavioral risk feature score, sentiment analysis score, and historical insurance risk data score corresponding to the target user. Expressed as a preset weight coefficient.
[0009] Preferably, a comprehensive analysis is performed on the target user's corresponding insurance demand score, risk preference score, and risk level assessment coefficient of each insurance to generate a list of recommended insurance products, specifically including: Score the insurance needs of target users Risk preference score corresponding to the target user Substitute into the formula Then confirm the comprehensive evaluation score corresponding to the target user ,in, Used to control the weights of insurance needs and risk preferences corresponding to target users, Can be adjusted according to business strategy; The comprehensive evaluation score corresponding to the target user Risk level assessment coefficient corresponding to each insurance Match and then use the formula , confirm the matching score between the target user and each insurance ; The insurance products are sorted in a preset order according to the matching scores between the target user and each insurance, and a recommendation list of insurance products is generated based on the sorted insurance products, and then the recommendation list of insurance products is pushed to the target user.
[0010] Preferably, after pushing the insurance product recommendation list to the target user, the method further includes: Collect user feedback on the insurance product recommendation list in real time, including interaction data and feedback data. The interaction data includes click count, dwell time, and consultation score, and the feedback data includes user score and mark count. Get user feedback on the insurance product recommendation list through the formula , confirm the user's feedback score for each insurance product in the insurance product recommendation list ; in, Indicates the number of each insurance product in the recommended insurance product list. Represents the recommended list of insurance products Number of clicks, stay time, and consultation score corresponding to each insurance product, Indicates the preset reference stay time. Represents the recommended list of insurance products User ratings and marking times corresponding to each insurance product, e is a natural constant; Extract the matching scores between the target user and each insurance product in the recommended insurance product list from the matching scores between the target user and each insurance product, and mark them as ; Score the matching degree between the target user and each insurance product in the insurance product recommendation list and the user's feedback rating for each insurance product in the insurance product recommendation list Substitute into the formula Then confirm the recommended adjustment factors corresponding to each insurance product in the insurance product recommendation list ,in, Expressed as a preset weight coefficient; Based on the recommended adjustment factors for each insurance product in the insurance product recommendation list The recommended list of insurance products is readjusted and the adjusted recommended list of insurance products is confirmed.
[0011] Preferably, after confirming the user's feedback score for each insurance product in the insurance product recommendation list, the method further includes: During the preset time period, the user's feedback score for each insurance product in the insurance product recommendation list is collected in real time, and the average feedback score of the user for the insurance product recommendation list is determined by average calculation. , forming a time series, and using the function to convert the average feedback score into express; By formula , confirm the coefficient of change in the average feedback score of users on the insurance product recommendation list ,in, They are respectively represented as the preset standard average feedback score and the standard average feedback score difference; The coefficient of change in the average feedback score of users on the insurance product recommendation list The preset change threshold Make a comparison; If the coefficient of change in the average feedback score of the user on the insurance product recommendation list , it is determined that the recommended list of insurance products in the future needs to be adjusted.
[0012] In a second aspect, the present application provides an Internet insurance marketing method based on a social network, comprising the following steps: Collect public data corresponding to target users and basic data corresponding to each insurance; Analyze and process the public data corresponding to the target user, and based on the results of the analysis and processing, identify the target user's corresponding insurance demand score and risk preference score, analyze and process the basic data corresponding to each insurance, and then determine the risk level assessment coefficient corresponding to each insurance; Comprehensively analyze the target user's corresponding insurance demand score, risk preference score, and the risk level assessment coefficient of each insurance, generate a list of recommended insurance products, and then push the recommended insurance products list to the target user; Collect user feedback on the insurance product recommendation list in real time, confirm the feedback score, and adjust the insurance product recommendation list based on the feedback score.
[0013] In a third aspect, the present application provides a computer-readable storage medium storing instructions, which, when executed on a computer, enables the computer to execute any one of the above-mentioned Internet insurance marketing systems based on a social network.
[0014] In summary, this application includes at least one of the following beneficial technical effects: 1. The present application provides an Internet insurance marketing system based on a social network. The system analyzes and processes the public data corresponding to the target user and the basic data corresponding to each insurance, thereby determining the insurance demand score, risk preference score and risk level assessment coefficient corresponding to each insurance corresponding to the target user. The system also determines the comprehensive assessment score corresponding to the target user based on the insurance demand score and risk preference score corresponding to the target user. The system then matches the comprehensive assessment score with the risk level assessment coefficient corresponding to each insurance, determines the matching score between the target user and each insurance, and sorts the insurance products in a preset order based on the matching score between the target user and each insurance. The system then generates an insurance product recommendation list based on the sorted insurance products, and then pushes the insurance product recommendation list to the target user. This effectively utilizes the rich information resources provided by the social network, thereby effectively improving the accuracy and timeliness of Internet insurance recommendations. 2. By collecting user feedback on the insurance product recommendation list in real time, and confirming the user's feedback score corresponding to each insurance product in the insurance product recommendation list, and then further confirming the recommendation adjustment factor corresponding to each insurance product in the insurance product recommendation list, the insurance product recommendation list is readjusted, and then effectively dynamically adjusted and optimized according to the user's real-time feedback, thereby effectively improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0016] Figure 1 This is a system diagram of Internet insurance marketing based on social networks in an embodiment of the present application.
[0017] Figure 2 This is a flow chart of a method for Internet insurance marketing based on social networks according to an embodiment of the present application. DETAILED DESCRIPTION
[0018] The following is combined with Figure 1-2 This application is described in further detail.
[0019] Example 1 The embodiments of the present application disclose an Internet insurance marketing system based on a social network.
[0020] Reference Figure 1 , an Internet insurance marketing system based on social network, comprising: Data collection module, used to collect public data corresponding to target users and basic data corresponding to each insurance; The analysis module is used to analyze and process the public data corresponding to the target user, and based on the analysis and processing results, identify the target user's corresponding insurance demand score and risk preference score, analyze and process the basic data corresponding to each insurance, and then determine the risk level assessment coefficient corresponding to each insurance; The recommendation module is used to comprehensively analyze the insurance demand score, risk preference score and risk level assessment coefficient of each insurance corresponding to the target user, generate a list of recommended insurance products, and then push the recommended insurance products list to the target user; The feedback module is used to collect user feedback on the insurance product recommendation list in real time, then determine the feedback score, and adjust the insurance product recommendation list based on the feedback score.
[0021] Furthermore, the public data corresponding to the target users include insurance demand data and risk preference data, and the basic data corresponding to each insurance include product type, product coverage and product price.
[0022] It should be noted that the analysis and processing of the public data corresponding to the target users specifically includes: Obtaining insurance demand data corresponding to the target user, extracting statistical feature scores, behavioral feature scores, and historical insurance data scores corresponding to the target user from the insurance demand data, and performing linear normalization processing on the statistical feature scores, behavioral feature scores, and historical insurance data scores; Specifically, in the embodiment of the present application, the statistical feature score, the behavioral feature score, and the historical insurance data score can all be obtained by training a preset machine learning model. Among them, the statistical feature score can be obtained by the impact of the target user's age, gender, and occupation on insurance demand, the behavioral feature score can be obtained by the target user's corresponding search keywords and click records, and the historical insurance data score can be obtained by the number of historical purchases and claims. By formula , confirm the insurance demand score corresponding to the target user ,in, They are respectively represented as the statistical feature score, behavioral feature score, and historical insurance data score corresponding to the target user. Expressed as a preset weight coefficient; Obtaining risk preference data corresponding to the target user, extracting a behavioral risk characteristic score, a sentiment analysis score, and a historical insurance risk data score corresponding to the target user from the risk preference data, and performing linear normalization processing on the behavioral risk characteristic score, sentiment analysis score, and historical insurance risk data score corresponding to the target user; Specifically, the behavioral risk feature score can be obtained by analyzing the target user's first-time behavior and consumption habits. The sentiment analysis score can be obtained by analyzing the positive and negative sentiment tendencies of the target user in the social network. The historical insurance risk data score can be obtained by fitting whether the target user has ever had high-risk claims. By formula , confirm the risk preference score corresponding to the target user ,in, They are respectively represented as the behavioral risk feature score, sentiment analysis score, and historical insurance risk data score corresponding to the target user. Expressed as a preset weight coefficient.
[0023] It should be noted that the basic data corresponding to each insurance is analyzed and processed to determine the risk level assessment coefficient corresponding to each insurance, including: Evaluate the risk level corresponding to each insurance, and the evaluation process is as follows: By formula , confirm the risk level assessment coefficient corresponding to each insurance ; in, Indicates the number corresponding to each insurance. Indicated as number The product type coefficient corresponding to the insurance, Indicated as number The product coverage coefficient corresponding to the insurance, Represented as numbers The product price and reference price corresponding to the insurance.
[0024] Furthermore, a comprehensive analysis is conducted on the target user's corresponding insurance demand score, risk preference score, and the risk level assessment coefficient of each insurance, to generate a list of recommended insurance products, including: Score the insurance needs of target users Risk preference score corresponding to the target user Substitute into the formula Then confirm the comprehensive evaluation score corresponding to the target user ,in, Used to control the weights of insurance needs and risk preferences corresponding to target users, Can be adjusted according to business strategy; The comprehensive evaluation score corresponding to the target user Risk level assessment coefficient corresponding to each insurance Match and then use the formula , confirm the matching score between the target user and each insurance ; Specifically, in the embodiment of the present application, the smaller the matching score between the target user and each insurance, the more the target user is matched with each insurance; The insurance products are sorted in a preset order according to the matching scores between the target user and each insurance, and a recommendation list of insurance products is generated based on the sorted insurance products, and then the recommendation list of insurance products is pushed to the target user.
[0025] It should be noted that after pushing the insurance product recommendation list to the target user, the following steps are also included: Collect user feedback on the insurance product recommendation list in real time, including interaction data and feedback data. The interaction data includes click count, dwell time, and consultation score, and the feedback data includes user score and mark count. Get user feedback on the insurance product recommendation list through the formula , confirm the user's feedback score for each insurance product in the insurance product recommendation list ; in, Indicates the number of each insurance product in the recommended insurance product list. Represents the recommended list of insurance products Number of clicks, stay time, and consultation score corresponding to each insurance product, Indicates the preset reference stay time. Represents the recommended list of insurance products User ratings and marking times corresponding to each insurance product, e is a natural constant; Extract the matching scores between the target user and each insurance product in the recommended insurance product list from the matching scores between the target user and each insurance product, and mark them as ; Score the matching degree between the target user and each insurance product in the insurance product recommendation list and the user's feedback rating for each insurance product in the insurance product recommendation list Substitute into the formula Then confirm the recommended adjustment factors corresponding to each insurance product in the insurance product recommendation list ,in, Expressed as a preset weight coefficient; Based on the recommended adjustment factors for each insurance product in the insurance product recommendation list The recommended list of insurance products is readjusted and the adjusted recommended list of insurance products is confirmed.
[0026] Specifically, by collecting user feedback information on the insurance product recommendation list in real time, and confirming the user's feedback score corresponding to each insurance product in the insurance product recommendation list, and then further confirming the recommendation adjustment factor corresponding to each insurance product in the insurance product recommendation list, the insurance product recommendation list is readjusted, and then effectively dynamically adjusted and optimized according to the user's real-time feedback, thereby effectively improving the user experience.
[0027] Furthermore, after confirming the user's feedback score for each insurance product in the insurance product recommendation list, the following is also included: During the preset time period, the user's feedback score for each insurance product in the insurance product recommendation list is collected in real time, and the average feedback score of the user for the insurance product recommendation list is determined by average calculation. , forming a time series, and using the function to convert the average feedback score into express; By formula , confirm the coefficient of change in the average feedback score of users on the insurance product recommendation list ,in, They are respectively represented as the preset standard average feedback score and the standard average feedback score difference; The coefficient of change in the average feedback score of users on the insurance product recommendation list The preset change threshold Make a comparison; If the coefficient of change in the average feedback score of the user on the insurance product recommendation list , it is determined that the recommended list of insurance products in the future needs to be adjusted.
[0028] Example 2 The embodiments of the present application also disclose an Internet insurance marketing method based on social networks.
[0029] Reference Figure 2 , an Internet insurance marketing method based on social network, comprising the following steps: Collect public data corresponding to target users and basic data corresponding to each insurance; Analyze and process the public data corresponding to the target user, and based on the results of the analysis and processing, identify the target user's corresponding insurance demand score and risk preference score, analyze and process the basic data corresponding to each insurance, and then determine the risk level assessment coefficient corresponding to each insurance; Comprehensively analyze the target user's corresponding insurance demand score, risk preference score, and the risk level assessment coefficient of each insurance, generate a list of recommended insurance products, and then push the recommended insurance products list to the target user; Collect user feedback on the insurance product recommendation list in real time, confirm the feedback score, and adjust the insurance product recommendation list based on the feedback score.
[0030] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in similar ways. As long as they do not deviate from the concept of the invention, they should all fall within the scope of protection of the present invention.
[0031] Throughout this specification, references to terms such as "one embodiment," "example," or "specific example" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
[0032] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to specific embodiments. Obviously, many modifications and variations are possible based on the contents of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention.
Claims
1. An Internet insurance marketing system based on social network, characterized by: include: Data collection module, used to collect public data corresponding to target users and basic data corresponding to each insurance; The analysis module is used to analyze and process the public data corresponding to the target user, and based on the analysis and processing results, identify the target user's corresponding insurance demand score and risk preference score, analyze and process the basic data corresponding to each insurance, and then determine the risk level assessment coefficient corresponding to each insurance; The recommendation module is used to comprehensively analyze the insurance demand score, risk preference score and risk level assessment coefficient of each insurance corresponding to the target user, generate a list of recommended insurance products, and then push the recommended insurance products list to the target user; The feedback module is used to collect user feedback on the insurance product recommendation list in real time, then determine the feedback score, and adjust the insurance product recommendation list based on the feedback score.
2. The Internet insurance marketing system based on social network according to claim 1, characterized in that: The public data corresponding to the target users include insurance demand data and risk preference data, and the basic data corresponding to each insurance include product type, product coverage and product price.
3. The Internet insurance marketing system based on social network according to claim 2, characterized in that: Analyze and process the public data corresponding to the target users, including: Obtaining insurance demand data corresponding to the target user, extracting statistical feature scores, behavioral feature scores, and historical insurance data scores corresponding to the target user from the insurance demand data, and performing linear normalization processing on the statistical feature scores, behavioral feature scores, and historical insurance data scores; By formula , confirm the insurance demand score corresponding to the target user ,in, They are respectively represented as the statistical feature score, behavioral feature score, and historical insurance data score corresponding to the target user. Expressed as a preset weight coefficient; Obtaining risk preference data corresponding to the target user, extracting a behavioral risk characteristic score, a sentiment analysis score, and a historical insurance risk data score corresponding to the target user from the risk preference data, and performing linear normalization processing on the behavioral risk characteristic score, sentiment analysis score, and historical insurance risk data score corresponding to the target user; By formula , confirm the risk preference score corresponding to the target user ,in, They are respectively represented as the behavioral risk feature score, sentiment analysis score, and historical insurance risk data score corresponding to the target user. Expressed as a preset weight coefficient.
4. The Internet insurance marketing system based on social network according to claim 2, characterized in that: Analyze and process the basic data corresponding to each insurance, and then determine the risk level assessment coefficient corresponding to each insurance, including: Evaluate the risk level corresponding to each insurance, and the evaluation process is as follows: By formula , confirm the risk level assessment coefficient corresponding to each insurance ; in, Indicates the number corresponding to each insurance. Indicated as number The product type coefficient corresponding to the insurance, Indicated as number The product coverage coefficient corresponding to the insurance, Represented as numbers The product price and reference price corresponding to the insurance.
5. The Internet insurance marketing system based on social network according to claim 4, characterized in that: Comprehensively analyze the target user's insurance demand score, risk preference score, and the risk level assessment coefficient of each insurance, and generate a list of recommended insurance products, including: Score the insurance needs of target users Risk preference score corresponding to the target user Substitute into the formula Then confirm the comprehensive evaluation score corresponding to the target user ,in, Used to control the weights of insurance needs and risk preferences corresponding to target users, Can be adjusted according to business strategy; The comprehensive evaluation score corresponding to the target user Risk level assessment coefficient corresponding to each insurance Match and then use the formula , confirm the matching score between the target user and each insurance ; The insurance products are sorted in a preset order according to the matching scores between the target user and each insurance, and a recommended list of insurance products is generated based on the sorted insurance products, which is then pushed to the target user.
6. The Internet insurance marketing system based on social network according to claim 5, characterized in that: After pushing the insurance product recommendation list to the target user, the following steps are also included: Collect user feedback on the insurance product recommendation list in real time, including interaction data and feedback data. The interaction data includes click count, dwell time, and consultation score, and the feedback data includes user score and mark count. Get user feedback on the insurance product recommendation list through the formula , confirm the user's feedback score for each insurance product in the insurance product recommendation list ; in, Indicates the number of each insurance product in the recommended insurance product list. Represents the recommended list of insurance products Number of clicks, stay time, and consultation score corresponding to each insurance product, Indicates the preset reference stay time. Represents the recommended list of insurance products User ratings and marking times corresponding to each insurance product, e is a natural constant; Extract the matching scores between the target user and each insurance product in the recommended insurance product list from the matching scores between the target user and each insurance product, and mark them as ; Score the matching degree between the target user and each insurance product in the insurance product recommendation list and the user's feedback rating for each insurance product in the insurance product recommendation list Substitute into the formula Then confirm the recommended adjustment factors corresponding to each insurance product in the insurance product recommendation list ,in, Expressed as a preset weight coefficient; Based on the recommended adjustment factors for each insurance product in the insurance product recommendation list The recommended list of insurance products is readjusted and the adjusted recommended list of insurance products is confirmed.
7. The Internet insurance marketing system based on social network according to claim 6, characterized in that: After confirming the user's feedback score for each insurance product in the insurance product recommendation list, it also includes: During the preset time period, the user's feedback score for each insurance product in the insurance product recommendation list is collected in real time, and the average feedback score of the user for the insurance product recommendation list is determined by average calculation. , forming a time series, and using the function to convert the average feedback score into express; By formula , confirm the coefficient of change in the average feedback score of users on the insurance product recommendation list ,in, They are respectively represented as the preset standard average feedback score and the standard average feedback score difference; The coefficient of change in the average feedback score of users on the insurance product recommendation list The preset change threshold Make a comparison; If the coefficient of change in the average feedback score of the user on the insurance product recommendation list , it is determined that the recommended list of insurance products in the future needs to be adjusted.
8. A social network-based internet insurance marketing method, applied to a social network-based internet insurance marketing system according to any one of claims 1 to 7, characterized in that: The following steps are involved: Collect public data corresponding to target users and basic data corresponding to each insurance; Analyze and process the public data corresponding to the target user, and based on the results of the analysis and processing, identify the target user's corresponding insurance demand score and risk preference score, analyze and process the basic data corresponding to each insurance, and then determine the risk level assessment coefficient corresponding to each insurance; Comprehensively analyze the target user's corresponding insurance demand score, risk preference score, and the risk level assessment coefficient of each insurance, generate a list of recommended insurance products, and then push the recommended insurance products list to the target user; Collect user feedback on the insurance product recommendation list in real time, confirm the feedback score, and adjust the insurance product recommendation list based on the feedback score.
9. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are run on a computer, the computer is caused to execute an Internet insurance marketing system based on a social network as described in any one of claims 1 to 7.