Interpersonal relationship search system based on big data

Abstract

The invention discloses an interpersonal relationship search system based on big data, and particularly relates to the technical field of interpersonal relationship search. The system comprises a scene intelligent environment perception module which is used for providing real-time social suggestions and scene perception support by capturing and analyzing environment and scene data of a user, and an emotion interaction experience design module which is used for improving social experience through technologies such as emotion recognition and virtual proxy. Through cooperative work of multiple modules, comprehensive capture, analysis and optimization of user social relations are achieved, the system can improve the social experience of the users through context awareness and emotion interaction, personalized social matching and interaction suggestions can be provided based on behavior data, interests and preferences of the users, and the social experience of the users is improved. And the system can predict the dynamic change of the social relationship of the user, simulate the evolution path of the potential relationship, and help the user more effectively manage and expand the interpersonal relationship, thereby improving the social efficiency and satisfaction.

Description

Technical Field

[0001] The present invention relates to the technical field of interpersonal relationship search, and in particular to an interpersonal relationship search system based on big data. Background Art

[0002] With the continuous development of big data technology, social networking platforms have become an indispensable part of people's daily lives. These platforms provide a wide range of social interaction opportunities by capturing users' behavioral data and interest preferences. However, traditional social networking systems still have many shortcomings in the management and optimization of users' social relationships. Existing social platforms mainly rely on users' active participation to maintain and manage interpersonal relationships, and lack intelligent and automated tools to analyze and predict the dynamic changes of users' social relationships. As the scale of user social networks continues to expand, how to use big data technology to accurately capture users' social relationships and provide personalized social recommendations and optimization solutions has become an important research direction in the current social networking field.

[0003] In the prior art, existing search engine systems are generally based on simple algorithms through social recommendation systems, such as mutual friend recommendations or interest tag matching. These methods cannot deeply explore the real needs and emotional states of users, resulting in low relevance and accuracy of recommendation results. In addition, when dealing with the dynamic changes of user social relationships, existing systems lack real-time and predictive capabilities, cannot capture and reflect the evolution of user relationships in a timely manner, and are difficult to predict the evolution path of future relationships, which limits users' effective management of potentially important interpersonal relationships. Therefore, we provide an interpersonal relationship search system based on big data. Summary of the invention

[0004] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a human relationship search system based on big data.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A big data-based interpersonal relationship search system, comprising a context-intelligence environment perception module for providing real-time social suggestions and context-aware support by capturing and analyzing a user's environment and context data, an emotional interaction experience design module for improving social experience through technologies such as emotion recognition and virtual agents, a personalized social engine module for providing personalized social matching and interaction suggestions based on a user's behavior, interests and preferences, a social influence relationship prediction module for evaluating a user's social influence and predicting dynamic changes in interpersonal relationships, and an engine search interface module for providing a user-friendly search interface supporting multi-dimensional interpersonal relationship query and data retrieval functions;

[0007] The contextual intelligent environment perception module includes a contextual social perception module for understanding the user's current context through sensors and environment data, an environment-triggered relationship prompting module for triggering and prompting relevant social opportunities and potential relationships based on the user's environment changes, a dynamic context simulation module for simulating different contexts through virtual reality technology, and a contextual perception data fusion module for fusing multi-source perception data to provide comprehensive contextual perception analysis;

[0008] The emotional interaction experience design module includes an emotional resonance analysis module for identifying and enhancing emotional resonance points by analyzing the user's communication content and interaction methods, a virtual emotional agent module for creating a virtual emotional agent through AI technology to represent the user in emotional communication and maintain relationships when the user is inconvenient to participate, an immersive emotional playback module for reproducing important emotional moments using augmented reality and virtual reality technology, a real-time emotional monitoring module for monitoring the user's emotional state in real time, and an interactive emotional sensing module for monitoring the user's emotional fluctuations in real time using wearable devices and biosensors.

[0009] The present invention is further configured as follows: the personalized social engine module includes a personality identification and matching module for performing personalized social matching and recommendation by analyzing the user's behavior data, interests, hobbies and personality traits, a dynamic interest graph analysis module for constructing and updating the user's interest graph to dynamically adjust and recommend new interest points and social opportunities based on real-time data analysis, a social habit analysis module for analyzing the user's social habits and preferences, a relationship quality optimization module for analyzing the user's social interaction quality through an AI algorithm, and a personalized interaction script module for providing the user with a personalized social interaction script;

[0010] The social influence relationship prediction module includes a social influence evaluation module for analyzing and evaluating the influence of users in different social networks, a relationship dynamics prediction module for predicting the future dynamics of interpersonal relationships based on historical data and behavior patterns, a potential relationship mining module for analyzing the user's implicit relationship network to mine potentially valuable relationships, a social network evolution simulation module for simulating the user's social network evolution process using simulation technology, and a social influence propagation simulation module for simulating the propagation path and influence range of the user's social information in the network.

[0011] The present invention is further configured as follows: the dynamic interest graph analysis module includes a multi-source interest data collection module for collecting user interest-related data from multiple data sources, a real-time interest change monitoring module for monitoring user interest changes in real time by analyzing user real-time behavior and interaction data, an emotional perception interest inference module for inferring user interest changes and emerging interest points in combination with the user's current context, an interest association network construction module for constructing an association network of user interests to display the mutual relationship and influence between different interest points, a potential interest mining module for mining users' potential interests through deep learning models to determine areas that users may be interested in but have not yet expressed, an interest evolution prediction module for predicting users' future interest changes and evolution paths based on historical data and current trends, a personalized interest recommendation module for providing personalized content recommendations and interactive suggestions based on users' current and potential interests, an interest feedback and adaptation module for collecting user feedback on recommended content and automatically adjusting interest graphs and recommendation algorithms, and a comprehensive interest graph generation module for finally integrating the final data results to generate a user interest graph.

[0012] The present invention is further configured as follows: the real-time interest change detection module includes a real-time behavior monitoring branch and a user feedback analysis branch; the potential interest mining module includes a historical behavior analysis branch and a user portrait expansion branch;

[0013] The real-time behavior monitoring branch includes a real-time behavior frequency change module for monitoring the behavior frequency change of the user at different points of interest to identify the increase or decrease of interest and a short-term behavior pattern recognition module for analyzing the user's short-term behavior sequence to identify new behavior patterns and changes in points of interest;

[0014] The user feedback analysis branch includes a feedback frequency sentiment analysis module for counting the frequency of user feedback on recommended content and performing sentiment analysis to determine the positive and negative changes in interest, and a feedback behavior association analysis module for associating user feedback with actual behavior to comprehensively determine the true direction of interest change;

[0015] The historical behavior analysis branch includes a real-time behavior frequency change module for counting the user's behavior frequency at different interest points to identify high-frequency behavior patterns and a behavior sequence pattern mining module for analyzing user behavior sequences to mine potential interest tendencies and behavior patterns;

[0016] The user portrait expansion branch includes a similar user interest inference module for inferring the current user's potential interests based on similar users' interests and a behavior sequence pattern mining module for identifying related fields of the user's existing interests and determining potential interests through semantic analysis technology.

[0017] The present invention is further configured as follows: the multi-source interest data collection module collects user interest-related data from multiple data sources, and the generated comprehensive data is transmitted to the real-time interest change monitoring module to monitor the user's interest changes and identify new interest patterns by analyzing the user's real-time behavior and interaction data; the real-time interest change monitoring module determines interest changes by analyzing real-time behavior data, and transmits the monitoring results to the emotion-aware interest inference module, and infers the user's interest changes and emerging interest points in combination with the user's current context; the emotion-aware interest inference module combines contextual data and emotion analysis to infer the user's interest changes, and transmits the inference results to the interest association network construction module to construct an association network of user interests and show the relationships and influences between different interest points; the interest association network construction module constructs the user's interest association network based on the incoming data, and transmits the network construction results to the potential interest mining module, which is used to further mine the user's potential interests through a deep learning model and determine areas that the user may be interested in but has not yet expressed.

[0018] The present invention is further configured as follows: the potential interest mining module uses a deep learning model to analyze the user's potential interests, and transmits the analysis results to the interest evolution prediction module, which is used to predict the user's future interest changes and evolution paths based on historical data and current trends; the interest evolution prediction module predicts the user's interest evolution path based on historical data and trends, and transmits the prediction results to the personalized interest recommendation module, which is used to provide personalized content recommendations and interactive suggestions based on the user's current and potential interests; the personalized interest recommendation module provides personalized recommendations based on the user's interest data, and transmits the user's feedback data to the interest feedback and adaptation module, which is used to collect user feedback on the recommended content and automatically adjust the interest map and recommendation algorithm; the interest feedback and adaptation module collects user feedback and performs adaptive adjustments, and transmits the optimized data to the comprehensive interest map generation module, so as to finally integrate all data results to generate the user's dynamic interest map.

[0019] The present invention is further configured as follows: the situational social perception module understands the user's current situation through sensors and environmental data, generates situational data and transmits it to the environmental trigger relationship prompting module, which is used to trigger and prompt relevant social opportunities and potential relationships based on the user's environmental changes; the dynamic situation simulation module uses virtual reality technology to simulate different interactive situations, generates simulation results and transmits them to the situational perception data fusion module, which is used to fuse multi-source perception data and provide comprehensive situational perception analysis.

[0020] The present invention is further configured as follows: the emotional resonance analysis module analyzes the user's communication content and interaction methods, identifies and enhances emotional resonance points, generates emotional analysis results and transmits them to the virtual emotional agent module, which is used to create a virtual emotional agent through AI technology, and acts as an agent for the user to conduct emotional exchanges and maintain relationships when the user is inconvenient to participate; the immersive emotional playback module uses augmented reality and virtual reality technology to reproduce important emotional moments, and the generated emotional playback data is transmitted to the real-time emotional monitoring module, which is used to monitor the user's emotional state in real time to ensure the accuracy and real-time nature of the emotional playback.

[0021] The present invention is further configured as follows: the personality identification and matching module analyzes the user's behavior data, interests and personality traits, performs personalized social matching, generates matching results and transmits them to the dynamic interest graph analysis module, which is used to construct and update the user's interest graph, dynamically adjust and recommend new points of interest and social opportunities; the social habit analysis module analyzes the user's social habits and preferences, generates social habit data and transmits it to the relationship quality optimization module, analyzes the user's social interaction quality through an AI algorithm, and optimizes the user's social relationship quality.

[0022] The present invention is further configured as follows: the social influence assessment module generates an influence assessment result by analyzing the influence of the user in different social networks, and transmits it to the relationship dynamic prediction module, which is used to predict the future dynamic changes of interpersonal relationships based on historical data and behavior patterns; the potential relationship mining module analyzes the user's implicit relationship network, mines potentially valuable relationships, and generates mining results and transmits them to the social network evolution simulation module, which is used to simulate the user's social network evolution process using simulation technology; the social influence propagation simulation module simulates the propagation path and influence range of the user's social information in the network, generates propagation simulation data and transmits it to the social network evolution simulation module, which is used to more accurately simulate and predict the evolution and information propagation of the social network.

[0023] The beneficial effects of the present invention are:

[0024] 1. The present invention realizes the comprehensive capture, analysis and optimization of users' social relationships through the collaborative work of multiple modules, enhances users' social experience through situational awareness and emotional interaction, and provides personalized social matching and interaction suggestions based on users' behavioral data, interests and preferences. At the same time, it can predict the dynamic changes of users' social relationships and simulate the evolution path of potential relationships, helping users to manage and expand interpersonal relationships more effectively, thereby improving social efficiency and satisfaction.

[0025] 2. The present invention further enhances the personalized recommendation capability of the system through the dynamic interest graph analysis module. By real-time monitoring and analyzing the user's interest changes, the module can accurately identify emerging interest points, and combine the user's current situation and emotional state to predict the future interest evolution trend. The module also mines the user's potential interests through a deep learning model, provides more targeted content recommendations, and continuously optimizes the recommendation algorithm through feedback and adaptive mechanisms to ensure that the system can timely reflect the user's interest changes, provide more accurate personalized suggestions, and improve the user experience while also improving the accuracy and relevance of the recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 Schematic diagram of the system in the present invention.

[0027] Figure 2 It is a schematic diagram of the flow of the dynamic interest graph analysis module in the present invention. DETAILED DESCRIPTION

[0028] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0029] Example 1

[0030] like Figure 1 As shown, a big data-based interpersonal relationship search system includes a situational intelligent environment perception module for providing real-time social suggestions and situational awareness support by capturing and analyzing the user's environment and situational data, an emotional interaction experience design module for improving the social experience through technologies such as emotion recognition and virtual agents, a personalized social engine module for providing personalized social matching and interaction suggestions based on the user's behavior, interests and preferences, a social influence relationship prediction module for evaluating the user's social influence and predicting the dynamic changes of interpersonal relationships, and an engine search interface module for providing a user-friendly search interface to support multi-dimensional interpersonal relationship query and data retrieval functions;

[0031] The contextual intelligent environment perception module includes a contextual social perception module for understanding the user's current context through sensors and environment data, an environment-triggered relationship prompting module for triggering and prompting relevant social opportunities and potential relationships based on the user's environment changes, a dynamic context simulation module for simulating different contexts through virtual reality technology, and a contextual perception data fusion module for fusing multi-source perception data to provide comprehensive contextual perception analysis;

[0032] The emotional interaction experience design module includes an emotional resonance analysis module for identifying and enhancing emotional resonance points by analyzing the user's communication content and interaction mode, a virtual emotional agent module for creating a virtual emotional agent through AI technology to communicate and maintain relationships on behalf of the user when the user is inconvenient to participate, an immersive emotional playback module for reproducing important emotional moments using augmented reality and virtual reality technology, a real-time emotional monitoring module for monitoring the user's emotional state in real time, and an interactive emotional sensing module for monitoring the user's emotional fluctuations in real time using wearable devices and biosensors;

[0033] The personalized social engine module includes a personality identification and matching module for performing personalized social matching and recommendation by analyzing the user's behavior data, interests, hobbies and personality traits, a dynamic interest graph analysis module for constructing and updating the user's interest graph to dynamically adjust and recommend new points of interest and social opportunities based on real-time data analysis, a social habit analysis module for analyzing the user's social habits and preferences, a relationship quality optimization module for analyzing the user's social interaction quality through an AI algorithm, and a personalized interaction script module for providing users with personalized social interaction scripts;

[0034] The social influence relationship prediction module includes a social influence evaluation module for analyzing and evaluating the influence of users in different social networks, a relationship dynamics prediction module for predicting the future dynamics of interpersonal relationships based on historical data and behavior patterns, a potential relationship mining module for analyzing the user's implicit relationship network to mine potentially valuable relationships, a social network evolution simulation module for simulating the user's social network evolution process using simulation technology, and a social influence propagation simulation module for simulating the propagation path and influence range of the user's social information in the network;

[0035] The situational social perception module understands the user's current situation through sensors and environmental data, generates situational data and transmits it to the environmental trigger relationship prompting module, which is used to trigger and prompt relevant social opportunities and potential relationships based on the user's environmental changes; the dynamic situation simulation module uses virtual reality technology to simulate different interactive situations, generates simulation results and transmits them to the situational perception data fusion module, which is used to fuse multi-source perception data and provide comprehensive situational perception analysis;

[0036] The emotional resonance analysis module analyzes the user's communication content and interaction methods, identifies and enhances emotional resonance points, generates emotional analysis results and transmits them to the virtual emotional agent module, which is used to create a virtual emotional agent through AI technology to communicate emotions and maintain relationships on behalf of users when it is inconvenient for users to participate; the immersive emotional playback module uses augmented reality and virtual reality technology to reproduce important emotional moments, and the generated emotional playback data is transmitted to the real-time emotional monitoring module for real-time monitoring of the user's emotional state to ensure the accuracy and real-time nature of the emotional playback;

[0037] The personality identification and matching module analyzes the user's behavior data, interests and personality traits, performs personalized social matching, generates matching results and transmits them to the dynamic interest graph analysis module, which is used to build and update the user's interest graph, dynamically adjust and recommend new points of interest and social opportunities; the social habit analysis module analyzes the user's social habits and preferences, generates social habit data and transmits it to the relationship quality optimization module, analyzes the user's social interaction quality through AI algorithms, and optimizes the user's social relationship quality;

[0038] The social influence assessment module generates influence assessment results by analyzing the influence of users in different social networks, and transmits them to the relationship dynamic prediction module, which is used to predict the future dynamic changes of interpersonal relationships based on historical data and behavior patterns; the potential relationship mining module analyzes the user's implicit relationship network, mines potentially valuable relationships, and generates mining results and transmits them to the social network evolution simulation module, which is used to simulate the user's social network evolution process using simulation technology; the social influence propagation simulation module simulates the propagation path and influence range of the user's social information in the network, generates propagation simulation data and transmits it to the social network evolution simulation module, which is used to more accurately simulate and predict the evolution of the social network and information propagation.

[0039] In the above embodiment, the current situation of the user is understood through the situational intelligent environment perception module, and relevant social opportunities are prompted according to environmental changes. At the same time, the dynamic situation simulation module is used to simulate different interactive situations to provide comprehensive situation analysis. Subsequently, the emotional interaction experience design module enhances the user's emotional resonance through emotional resonance analysis, and the virtual emotional agent conducts emotional communication and relationship maintenance when the user is inconvenient to participate. The immersive emotional playback module uses augmented reality technology to reproduce important emotional moments to ensure real-time monitoring and feedback of the user's emotional state. Next, the personalized social engine module analyzes the user's behavioral data, interests and personality characteristics through the personality identification and matching module, dynamically updates the interest map and recommends new social opportunities, and improves the user's social interaction quality through social habit analysis and relationship quality optimization. Finally, the social influence relationship prediction module predicts the future dynamic changes of interpersonal relationships by analyzing the user's influence in the social network, and identifies and simulates the propagation path of potentially valuable relationships and social information through potential relationship mining and social network evolution simulation. Through the coordinated operation of these modules, the system can capture, analyze and optimize the user's social behavior in real time, provide personalized social suggestions and matching, and help users effectively manage and expand interpersonal relationships.

[0040] Example 2

[0041] like Figure 1-2 As shown, a human relationship search system based on big data, the dynamic interest graph analysis module includes a multi-source interest data collection module for collecting user interest-related data from multiple data sources, a real-time interest change monitoring module for monitoring user interest changes in real time by analyzing user real-time behavior and interaction data, an emotional perception interest inference module for inferring user interest changes and emerging interest points in combination with the user's current context, an interest association network construction module for constructing an association network of user interests to display the mutual relationship and influence between different interest points, a potential interest mining module for mining user potential interests through a deep learning model to determine the areas that the user may be interested in but has not yet expressed, an interest evolution prediction module for predicting user future interest changes and evolution paths based on historical data and current trends, a personalized interest recommendation module for providing personalized content recommendations and interactive suggestions based on the user's current and potential interests, an interest feedback and adaptation module for collecting user feedback on recommended content and automatically adjusting the interest graph and recommendation algorithm, and a comprehensive interest graph generation module for finally integrating the final data results to generate a user interest graph;

[0042] The real-time interest change detection module includes a real-time behavior monitoring branch and a user feedback analysis branch; the potential interest mining module includes a historical behavior analysis branch and a user portrait expansion branch;

[0043] The real-time behavior monitoring branch includes a real-time behavior frequency change module for monitoring the behavior frequency change of the user at different points of interest to identify the increase or decrease of interest and a short-term behavior pattern recognition module for analyzing the user's short-term behavior sequence to identify new behavior patterns and changes in points of interest;

[0044] The user feedback analysis branch includes a feedback frequency sentiment analysis module for counting the frequency of user feedback on recommended content and performing sentiment analysis to determine the positive and negative changes in interest, and a feedback behavior association analysis module for associating user feedback with actual behavior to comprehensively determine the true direction of interest change;

[0045] The historical behavior analysis branch includes a real-time behavior frequency change module for counting the user's behavior frequency at different interest points to identify high-frequency behavior patterns and a behavior sequence pattern mining module for analyzing user behavior sequences to mine potential interest tendencies and behavior patterns;

[0046] The user portrait expansion branch includes a similar user interest inference module for inferring the potential interests of the current user based on the interests of similar users and a behavior sequence pattern mining module for identifying the relevant fields of the user's existing interests and determining the potential interests through semantic analysis technology;

[0047] The multi-source interest data collection module collects user interest-related data from multiple data sources, and transmits the generated comprehensive data to the real-time interest change monitoring module to monitor the user's interest changes and identify new interest patterns by analyzing the user's real-time behavior and interaction data; the real-time interest change monitoring module determines interest changes by analyzing real-time behavior data, and transmits the monitoring results to the emotion perception interest inference module, which infers the user's interest changes and emerging interest points in combination with the user's current context; the emotion perception interest inference module combines context data and emotion analysis to infer the user's interest changes, and transmits the inference results to the interest association network construction module to construct an association network of the user's interests and show the mutual relationship and influence between different interest points; the interest association network construction module constructs the user's interest association network based on the incoming data, and transmits the network construction results to the potential interest mining module, which is used to further mine the user's potential interests through a deep learning model and determine the areas that the user may be interested in but has not yet expressed;

[0048] The potential interest mining module uses a deep learning model to analyze the user's potential interests, and transmits the analysis results to the interest evolution prediction module, which is used to predict the user's future interest changes and evolution paths based on historical data and current trends; the interest evolution prediction module predicts the user's interest evolution path based on historical data and trends, and transmits the prediction results to the personalized interest recommendation module, which is used to provide personalized content recommendations and interactive suggestions based on the user's current and potential interests; the personalized interest recommendation module provides personalized recommendations based on user interest data, and transmits the user's feedback data to the interest feedback and adaptation module, which is used to collect user feedback on recommended content and automatically adjust the interest map and recommendation algorithm; the interest feedback and adaptation module collects user feedback and performs adaptive adjustments, and transmits the optimized data to the comprehensive interest map generation module, so as to finally integrate all data results to generate the user's dynamic interest map.

[0049] In the above embodiment, the multi-source interest data collection module collects user interest-related data from multiple data sources and transmits the comprehensive data to the real-time interest change monitoring module, which identifies interest changes and emerging interest patterns by monitoring the user's real-time behavior and interaction data. Subsequently, the emotion perception interest inference module combines the user's current context and emotion analysis to infer the user's interest changes, and transmits the results to the interest association network construction module for building and displaying the association network between different interest points. Next, the potential interest mining module further mines the user's potential interests through a deep learning model, and transmits the data of these potential interests to the interest evolution prediction module, which predicts the user's future interest changes and evolution paths based on historical data and current trends. The personalized interest recommendation module provides personalized content recommendations based on the user's current and potential interests, and transmits the user's feedback data to the interest feedback and adaptation module, which automatically adjusts the interest map and recommendation algorithm by collecting user feedback. Finally, the optimized data is integrated by the comprehensive interest map generation module to generate the user's dynamic interest map, ensuring that the system can timely reflect the user's interest changes and provide accurate personalized suggestions.

[0050] Among them, the real-time behavior frequency change module monitors the changes in the user's behavior frequency at different points of interest, identifies the increase or decrease in interest, generates corresponding data and transmits it to the short-term behavior pattern recognition module to further analyze these behavior data, identify new behavior patterns and changes in points of interest; the feedback frequency sentiment analysis module counts the user's feedback frequency on recommended content and performs sentiment analysis, determines the positive and negative changes in interest, generates corresponding data and transmits it to the feedback behavior association analysis module to associate these feedbacks with the user's actual behavior, and comprehensively determine the true direction of the interest change.

[0051] Among them, the similar user interest inference module infers the possible potential interests of the current user based on the interests of similar users, generates corresponding data and transmits it to the semantic analysis and association module to identify the relevant fields of the user's existing interests through semantic analysis technology and further determine the potential interests; the behavior frequency analysis module counts the user's behavior frequency at different interest points, identifies high-frequency behavior patterns, generates corresponding data and transmits it to the behavior sequence pattern mining module to further analyze the user's behavior sequence and mine potential interest tendencies and behavior patterns.

[0052] Working principle: When the present invention is in use, it captures the user's current situation in real time through the comprehensive application of situational social perception modules and environmental data, and intelligently reminds potential social opportunities according to situational changes. Then, through dynamic situation simulation and data fusion analysis, it can provide more accurate situational analysis, helping users make more correct decisions in different social scenarios. After that, it uses technologies such as emotional resonance analysis, virtual emotional agent and immersive emotional playback to maintain and strengthen the user's emotional connection with others when it is inconvenient for the user to participate, and monitor the user's emotional state in real time to ensure that the user obtains continuous emotional support and feedback during the interaction process. With the help of dynamic interest map analysis and social habit analysis, the system can recommend new social opportunities to users, and help users identify and cultivate potentially valuable relationships by evaluating and predicting the user's influence in social networks. Through comprehensive analysis and recommendation functions, the quality of users' social interactions is improved, and strong support is provided for users to navigate in complex social networks, thereby maximizing social benefits and significantly improving user satisfaction.

[0053] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A interpersonal relationship search system based on big data, It is characterized in that It includes a situational intelligence environment perception module for providing real-time social suggestions and situational awareness support by capturing and analyzing the user's environment and situational data, an emotional interaction experience design module for improving social experience through technologies such as emotion recognition and virtual agents, a personalized social engine module for providing personalized social matching and interaction suggestions based on the user's behavior, interests and preferences, a social influence relationship prediction module for evaluating the user's social influence and predicting the dynamic changes in interpersonal relationships, and an engine search interface module for providing a user-friendly search interface to support multi-dimensional interpersonal relationship query and data retrieval functions; The contextual intelligent environment perception module includes a contextual social perception module for understanding the user's current context through sensors and environment data, an environment-triggered relationship prompting module for triggering and prompting relevant social opportunities and potential relationships based on the user's environment changes, a dynamic context simulation module for simulating different contexts through virtual reality technology, and a contextual perception data fusion module for fusing multi-source perception data to provide comprehensive contextual perception analysis; The emotional interaction experience design module includes an emotional resonance analysis module for identifying and enhancing emotional resonance points by analyzing the user's communication content and interaction methods, a virtual emotional agent module for creating a virtual emotional agent through AI technology to represent the user in emotional communication and maintain relationships when the user is inconvenient to participate, an immersive emotional playback module for reproducing important emotional moments using augmented reality and virtual reality technology, a real-time emotional monitoring module for monitoring the user's emotional state in real time, and an interactive emotional sensing module for monitoring the user's emotional fluctuations in real time using wearable devices and biosensors.

2. According to the big data-based interpersonal relationship search system of claim 1, It is characterized in that The personalized social engine module includes a personality identification and matching module for performing personalized social matching and recommendation by analyzing the user's behavior data, interests, hobbies and personality traits, a dynamic interest graph analysis module for constructing and updating the user's interest graph to dynamically adjust and recommend new points of interest and social opportunities based on real-time data analysis, a social habit analysis module for analyzing the user's social habits and preferences, a relationship quality optimization module for analyzing the user's social interaction quality through an AI algorithm, and a personalized interaction script module for providing users with personalized social interaction scripts; The social influence relationship prediction module includes a social influence evaluation module for analyzing and evaluating the influence of users in different social networks, a relationship dynamics prediction module for predicting the future dynamics of interpersonal relationships based on historical data and behavior patterns, a potential relationship mining module for analyzing the user's implicit relationship network to mine potentially valuable relationships, a social network evolution simulation module for simulating the user's social network evolution process using simulation technology, and a social influence propagation simulation module for simulating the propagation path and influence range of the user's social information in the network.

3. According to the big data-based interpersonal relationship search system of claim 2, It is characterized in that The dynamic interest graph analysis module includes a multi-source interest data collection module for collecting user interest-related data from multiple data sources, a real-time interest change monitoring module for monitoring user interest changes in real time by analyzing user real-time behavior and interaction data, an emotion-aware interest inference module for inferring user interest changes and emerging interest points in combination with the user's current context, an interest association network construction module for constructing an association network of user interests to display the relationships and influences between different interest points, a potential interest mining module for mining users' potential interests through deep learning models to determine areas that users may be interested in but have not yet expressed, an interest evolution prediction module for predicting users' future interest changes and evolution paths based on historical data and current trends, a personalized interest recommendation module for providing personalized content recommendations and interactive suggestions based on users' current and potential interests, an interest feedback and adaptation module for collecting user feedback on recommended content and automatically adjusting interest graphs and recommendation algorithms, and a comprehensive interest graph generation module for finally integrating the final data results to generate a user interest graph.

4. According to the big data-based interpersonal relationship search system of claim 3, It is characterized in that The real-time interest change detection module includes a real-time behavior monitoring branch and a user feedback analysis branch; the potential interest mining module includes a historical behavior analysis branch and a user portrait expansion branch; The real-time behavior monitoring branch includes a real-time behavior frequency change module for monitoring the behavior frequency change of the user at different points of interest to identify the increase or decrease of interest and a short-term behavior pattern recognition module for analyzing the user's short-term behavior sequence to identify new behavior patterns and changes in points of interest; The user feedback analysis branch includes a feedback frequency sentiment analysis module for counting the frequency of user feedback on recommended content and performing sentiment analysis to determine the positive and negative changes in interest, and a feedback behavior association analysis module for associating user feedback with actual behavior to comprehensively determine the true direction of interest change; The historical behavior analysis branch includes a real-time behavior frequency change module for counting the user's behavior frequency at different interest points to identify high-frequency behavior patterns and a behavior sequence pattern mining module for analyzing user behavior sequences to mine potential interest tendencies and behavior patterns; The user portrait expansion branch includes a similar user interest inference module for inferring the current user's potential interests based on similar users' interests and a behavior sequence pattern mining module for identifying related fields of the user's existing interests and determining potential interests through semantic analysis technology.

5. According to the big data-based interpersonal relationship search system of claim 4, It is characterized in that The multi-source interest data collection module collects user interest-related data from multiple data sources, and transmits the generated comprehensive data to the real-time interest change monitoring module to monitor the user's interest changes and identify new interest patterns by analyzing the user's real-time behavior and interaction data; the real-time interest change monitoring module determines interest changes by analyzing real-time behavior data, and transmits the monitoring results to the emotion perception interest inference module to infer the user's interest changes and emerging interest points in combination with the user's current context; The emotion-aware interest inference module combines contextual data and sentiment analysis to infer changes in user interests, and transmits the inference results to the interest association network construction module to construct an association network of user interests and show the relationships and influences between different interest points; the interest association network construction module constructs the user's interest association network based on the incoming data, and transmits the network construction results to the potential interest mining module, which is used to further mine the user's potential interests through a deep learning model and determine areas that the user may be interested in but has not yet expressed.

6. A big data-based interpersonal relationship search system according to claim 5, It is characterized in that The potential interest mining module uses a deep learning model to analyze the user's potential interests, and transmits the analysis results to the interest evolution prediction module, which is used to predict the user's future interest changes and evolution paths based on historical data and current trends; the interest evolution prediction module predicts the user's interest evolution path based on historical data and trends, and transmits the prediction results to the personalized interest recommendation module, which is used to provide personalized content recommendations and interactive suggestions based on the user's current and potential interests; the personalized interest recommendation module provides personalized recommendations based on user interest data, and transmits the user's feedback data to the interest feedback and adaptation module, which is used to collect user feedback on recommended content and automatically adjust the interest map and recommendation algorithm; the interest feedback and adaptation module collects user feedback and performs adaptive adjustments, and transmits the optimized data to the comprehensive interest map generation module, so as to finally integrate all data results to generate the user's dynamic interest map.

7. The interpersonal relationship search system based on big data according to claim 2, It is characterized in that The situational social perception module understands the user's current situation through sensors and environmental data, generates situational data and transmits it to the environmental trigger relationship prompting module, which is used to trigger and prompt relevant social opportunities and potential relationships based on the user's environmental changes; the dynamic situation simulation module uses virtual reality technology to simulate different interactive situations, generates simulation results and transmits them to the situational perception data fusion module, which is used to fuse multi-source perception data and provide comprehensive situational perception analysis.

8. The interpersonal relationship search system based on big data according to claim 2, It is characterized in that The emotional resonance analysis module analyzes the user's communication content and interaction methods, identifies and enhances emotional resonance points, generates emotional analysis results and transmits them to the virtual emotional agent module, which is used to create a virtual emotional agent through AI technology to act on behalf of the user to conduct emotional exchanges and maintain relationships when the user is inconvenient to participate; the immersive emotional playback module uses augmented reality and virtual reality technology to reproduce important emotional moments, and the generated emotional playback data is transmitted to the real-time emotional monitoring module, which is used to monitor the user's emotional state in real time to ensure the accuracy and real-time nature of the emotional playback.

9. The interpersonal relationship search system based on big data according to claim 2, It is characterized in that The personality identification and matching module analyzes the user's behavior data, interests and personality traits, performs personalized social matching, generates matching results and transmits them to the dynamic interest graph analysis module, which is used to build and update the user's interest graph, dynamically adjust and recommend new points of interest and social opportunities; the social habit analysis module analyzes the user's social habits and preferences, generates social habit data and transmits it to the relationship quality optimization module, analyzes the user's social interaction quality through AI algorithms, and optimizes the user's social relationship quality.

10. The interpersonal relationship search system based on big data according to claim 2, It is characterized in that The social influence assessment module generates influence assessment results by analyzing the influence of users in different social networks and transmits them to the relationship dynamics prediction module for predicting future dynamic changes in interpersonal relationships based on historical data and behavior patterns; The potential relationship mining module analyzes the user's implicit relationship network, mines potentially valuable relationships, and generates mining results and transmits them to the social network evolution simulation module for simulating the user's social network evolution process using simulation technology; The social influence propagation simulation module simulates the propagation path and influence range of the user's social information in the network, generates propagation simulation data and transmits it to the social network evolution simulation module for more accurately simulating and predicting the evolution and information propagation of the social network.

Images