A method and system for establishing social relationships based on 5G message geographic location technical features

Abstract

The present application provides a method and system for establishing social relationships based on the 5G message geographic location technical features, and relates to the field of Internet communication technology. Among them, the method includes: obtaining the 5G message geographic location technical features of the target user, extracting key features from the 5G message geographic location technical features to form a user dynamic portrait, and calculating the similarity score between the target user and the known users based on the user dynamic portrait and the pre-built interest graph model; based on the similarity score, combined with the user's online status, location proximity and immediate context information, screening out the target potential social objects; generating personalized interactive verification tasks for the target user and the target potential social object to verify each other, and when the interactive verification result of the target user and the target potential social object indicates that the two-way verification is passed, establishing a social relationship between the target user and the target potential social object based on temporary sharing rules. The present application can improve the quality of social relationships.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of Internet communication technology, and in particular, to a method and system for establishing social relationships based on the technical features of 5G message geographic location. Background Art

[0002] With the popularization of the fifth generation mobile communication technology (5G) and the continuous enhancement of terminal device functions, users' demand for social interaction has also shifted from traditional text or picture-based communication to deeper and more context-aware interactions. Especially in social application scenarios with high real-time requirements and location-related, such as travel, event gatherings, temporary collaboration, etc., a technical solution that can quickly respond and accurately match potential social objects is needed to provide a more personalized and efficient social experience.

[0003] At present, most social platforms mainly rely on personal information provided by users (such as interests, hobbies, age, gender, etc.) to recommend potential social objects. Even in the face of complex and changing social application scenarios, this method still recommends the same potential social objects, thus affecting the accuracy and relevance of the recommendations, reducing the quality of social relationships, and resulting in a poor social experience for users. Summary of the invention

[0004] The embodiments of the present application provide a method and system for establishing social relationships based on the technical features of 5G message geographic location, so as to solve the problem of low quality of social relationships existing in the prior art.

[0005] In a first aspect, the embodiment of the present application provides a method for establishing a social relationship based on the technical features of 5G message geographic location, including:

[0006] In response to a social relationship establishment request sent by a target terminal device, obtaining a 5G message geographic location technical feature of a target user, wherein the 5G message geographic location technical feature includes: geographic location information, behavior pattern data, and environmental perception data; the target user is a user using the target terminal device;

[0007] Extract key features for characterizing the user's current state and activity scene from the geographic location information, behavior pattern data, and environmental perception data to form a dynamic user portrait, and calculate a similarity score between the target user and known users based on the dynamic user portrait and a pre-built interest graph model; the known users are users using other terminal devices;

[0008] Based on the similarity score, combined with the user's online status, location proximity and immediate context information, the target potential social objects are screened out; the target potential social objects are known users who meet the specified social scenario conditions;

[0009] Generate a personalized interaction verification task for the target user and the target potential social object to verify each other, send the personalized interaction verification task of each other to the target user and the target potential social object respectively, receive the interaction verification result of the target user and the target potential social object, and when the interaction verification result of the target user and the target potential social object indicates that the two-way verification is passed, obtain a temporary sharing rule defined by the smart contract, and establish a social relationship between the target user and the target potential social object based on the temporary sharing rule.

[0010] Optionally, the screening of target potential social objects based on the similarity score, combined with the user's online status, location proximity and immediate context information, includes:

[0011] Filtering out first potential social objects from the known user set to form a first potential social object set, wherein the first potential social objects are known users whose similarity scores with the target user are greater than or equal to a preset score threshold;

[0012] Dynamically generate personalized geo-fences based on target users’ geographic location information, behavioral pattern data, and environmental perception data;

[0013] Using a K-nearest neighbor algorithm to select second potential social objects from the first potential social object set to form a second potential social object set;

[0014] When the online status of the target user is online, a third potential social object is selected from the second potential social object set to form a third potential social object set; the third potential social object is the second potential social object whose online status is online;

[0015] Based on the activity type, activity time and weather conditions in the real-time context information of the target user, a target potential social object that meets a preset context matching rule is screened out from the third potential social object set.

[0016] Optionally, dynamically generating a personalized geographic fence based on the target user's geographic location information, behavior pattern data, and environmental perception data includes:

[0017] According to the geographical location information of the target user, a support vector machine is used to identify the type of place where the target user is currently located;

[0018] Obtaining an initial radius of a geo-fence corresponding to the type of venue from a preset radius table, combining the activity range, venue characteristics, and behavior pattern data of the target user, and using an adaptive polygon generation algorithm to dynamically adjust the initial boundary shape of the geo-fence according to the traffic flow and weather conditions in the environmental perception data;

[0019] Obtain the fence size satisfaction score and shape rationality score fed back by the user, and determine the feedback error according to the fence size satisfaction score and shape rationality score;

[0020] Based on the feedback error, a preset objective function is minimized using a gradient descent method to obtain optimized fence parameters, where the optimized fence parameters correspond to a personalized geographic fence.

[0021] Optionally, the using a K-nearest neighbor algorithm to select second potential social objects from the first potential social object set to form a second potential social object set includes:

[0022] Calculate the original distance from the first potential social object to the target user according to the geographic location information of each first potential social object in the first potential social object set and the geographic location information of the target user to generate an original distance matrix;

[0023] Designing a distance attenuation factor, and adjusting the original distance using the distance attenuation factor according to the original distance matrix to obtain a target distance, so as to generate a target distance matrix;

[0024] Based on the target distance matrix, first potential social objects whose target distance to the target user within the geo-fence is less than a preset distance threshold are screened out from the first potential social object set to form a preliminary screening result set;

[0025] sorting the target distances from all first potential social objects to the target user in the preliminary screening result set, and selecting K first potential social objects with the smallest distances as the intermediate screening result set;

[0026] Calculate the time matching degree based on the activity time data of the first potential social object in the intermediate screening result set and the activity time data of the target user; calculate the environmental feature similarity based on the environmental feature data of the first potential social object in the intermediate screening result set and the environmental feature data in the immediate context information of the target user, combined with an adaptive weighting mechanism; calculate the emotional state consistency based on the emotional state data of the first potential social object in the intermediate screening result set and the emotional state data in the immediate context information of the target user;

[0027] Based on the target distance, the time matching degree, the environmental feature similarity and the emotional state consistency, combined with the corresponding preset weight coefficient, the comprehensive score value of all first potential social objects in the intermediate screening result set is calculated; the value of the preset weight coefficient is based on the historical interactive behavior data of the target user and is dynamically adjusted by using a reinforcement learning mechanism;

[0028] Sort all first potential social objects in the intermediate screening result set according to the comprehensive score, and select the one with the largest comprehensive score. first potential social objects as second potential social objects to form a second potential social object set, Less than K.

[0029] Optionally, generating a personalized interaction verification task for the target user and the target potential social object to verify each other includes:

[0030] Build a user relationship graph and use graph neural networks to predict the potential relationship strength between the target user and the target potential social objects;

[0031] Determine the task type according to the potential relationship strength, so that when the potential relationship strength is less than a preset strength threshold, a first independent task for the target user to verify the target potential social object and a second independent task for the target potential social object to verify the target user are designed, and when the potential relationship strength is greater than or equal to the preset strength threshold, a cooperative task for the target user and the target potential social object to verify each other is designed; the first independent task is a task to be participated in by the target potential social object, the second independent task is a task to be participated in by the target user, and the cooperative task is a task to be participated in by the target user and the target potential social object together;

[0032] Based on the preference information of the target user and the target potential social object, selecting a task template corresponding to the preference information from a preset task template library corresponding to the task type;

[0033] Based on the personalized characteristics of the target user and the target potential social object, the corresponding task template is optimized to obtain an optimized template;

[0034] Based on the optimized template, a personalized interactive verification task is generated for the target user and target potential social object to verify each other.

[0035] Optionally, optimizing the corresponding task template based on the personalized characteristics of the target user and the target potential social object to obtain an optimized template includes:

[0036] Obtaining personalized characteristics of the target user and the target potential social object, and determining personalized needs of the target user and the target potential social object according to the personalized characteristics of the target user and the target potential social object, wherein the personalized characteristics include interests, communication style, and interaction frequency, and the personalized needs include content preferences, interaction methods, and task levels;

[0037] Performing preliminary customized adjustment on the corresponding task template according to the personalized needs to obtain an adjusted template;

[0038] Implement the adjusted template and collect template suggestion information fed back by the participants. For the adjusted template corresponding to the independent task, the participants are the target potential social objects or target users. For the adjusted template corresponding to the cooperative task, the participants are the target potential social objects and target users.

[0039] Based on the template suggestion information fed back by the target potential social object and the target user, the corresponding task template is optimized to obtain an optimized template.

[0040] Optionally, the acquiring of a temporary sharing rule defined by a smart contract, and establishing a social relationship between the target user and the target potential social object based on the temporary sharing rule, includes:

[0041] A distributed ledger query algorithm is used to obtain temporary sharing rules defined by a smart contract from a blockchain platform, wherein the temporary sharing rules include: the type of shared content, access rights, and validity period, wherein the type of shared content includes at least one of the following: geographic location information, activity records, and recommendations of points of interest, and the access rights include at least one of the following: viewing, commenting, and liking; a differential privacy algorithm is applied to set privacy protection measures for the temporary sharing rules, so that the temporary sharing rules contain privacy protection clauses and allow users to withdraw access rights at any time;

[0042] Adopting automated execution methods to automatically trigger smart contracts so that smart contracts automatically execute temporary sharing rules according to preset conditions;

[0043] After the smart contract successfully executes the temporary sharing rules, the social relationship initialization method is used to establish the social relationship between the target user and the target potential social object.

[0044] In a second aspect, the embodiment of the present application provides a social relationship establishment system based on the technical features of 5G message geographic location, including:

[0045] An acquisition module, configured to obtain, in response to a social relationship establishment request sent by a target terminal device, a 5G message geographic location technical feature of a target user, wherein the 5G message geographic location technical feature includes: geographic location information, behavior pattern data, and environmental perception data; the target user is a user using the target terminal device;

[0046] An extraction and calculation module is used to extract key features for characterizing the user's current state and activity scene from the geographic location information, behavior pattern data and environmental perception data to form a user dynamic portrait, and calculate a similarity score between the target user and a known user based on the user dynamic portrait and a pre-built interest graph model; the known user is a user using other terminal devices;

[0047] A screening module is used to screen out target potential social objects based on the similarity score, combined with the user's online status, location proximity and immediate context information; the target potential social objects are known users who meet the specified social scenario conditions;

[0048] A communication module is generated, which is used to generate a personalized interaction verification task for the target user and the target potential social object to verify each other, send the personalized interaction verification task of each other to the target user and the target potential social object respectively, receive the interaction verification result of the target user and the target potential social object, and when the interaction verification result of the target user and the target potential social object indicates that the two-way verification has passed, obtain a temporary sharing rule defined by the smart contract, and establish a social relationship between the target user and the target potential social object based on the temporary sharing rule.

[0049] In a third aspect, an embodiment of the present application provides a computing device, comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a method for establishing social relationships based on the 5G message geographic location technical features as described in any one of the first aspects.

[0050] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program. When the computer program is executed by a computer, it implements a method for establishing social relationships based on the 5G message geographic location technical features as described in any one of the first aspects.

[0051] In an embodiment of the present application, a method for establishing a social relationship based on the 5G message geographic location technical feature is provided, including: in response to a social relationship establishment request sent by a target terminal device, obtaining the 5G message geographic location technical feature of the target user, the 5G message geographic location technical feature including: geographic location information, behavior pattern data and environmental perception data; the target user is a user using the target terminal device; extracting key features for characterizing the user's current state and activity scene from the geographic location information, behavior pattern data and environmental perception data to form a user dynamic portrait, and calculating the similarity score between the target user and a known user based on the user dynamic portrait and a pre-built interest graph model; the known user is a user using other terminals Device users; based on similarity scoring, combined with user online status, location proximity and immediate context information, screen out target potential social objects; target potential social objects are known users that meet the specified social scenario conditions; generate personalized interaction verification tasks for the target user and the target potential social object to verify each other, send each other's personalized interaction verification tasks to the target user and the target potential social object respectively, receive the interaction verification results of the target user and the target potential social object, and when the interaction verification results of the target user and the target potential social object indicate that the two-way verification has passed, obtain the temporary sharing rules defined by the smart contract, and establish a social relationship between the target user and the target potential social object based on the temporary sharing rules.

[0052] The embodiment of the present application provides an intelligent, precise and secure method for establishing social relationships by integrating the technical features of 5G message geolocation and smart contracts. This method can not only perceive the current status and immediate situation of the target user in real time, but also ensure that the recommended potential social objects are highly consistent with the actual needs of the user through efficient screening and two-way verification mechanisms, thereby improving the quality of social relationships and the user's sense of security. Through multi-stage step-by-step screening, it is ensured that the final recommended potential social objects not only have similar interests, but are also online in real time, nearby in location, and meet the current situation conditions, thereby improving the accuracy of matching and the success rate of interaction. The introduction of personalized geographic fences makes the recommendation results closer to the user's actual activity scenarios, enhancing the user experience.

[0053] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0055] Figure 1 A flowchart of a method for establishing social relationships based on 5G message geographic location technical features provided in an embodiment of the present application;

[0056] Figure 2 A structural diagram of a social relationship establishment system based on 5G message geographic location technical features provided in an embodiment of the present application;

[0057] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0058] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0059] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The sequence numbers of the operations, such as 11, 12, etc., are only used to distinguish between different operations, and the sequence numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to different types.

[0060] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0061] Figure 1 A flowchart of a method for establishing a social relationship based on the 5G message geographic location technical features provided in an embodiment of the present application, such as Figure 1 As shown, the method includes:

[0062] S11. In response to the social relationship establishment request sent by the target terminal device, the 5G message geographic location technical characteristics of the target user are obtained. The 5G message geographic location technical characteristics include: geographic location information, behavior pattern data and environmental perception data; the target user is the user using the target terminal device.

[0063] Among them, the target terminal device refers to the electronic device used by the user who initiates the request to establish a social relationship, such as a smartphone, tablet computer, etc. As the main medium for users to interact with social platforms, it is responsible for sending users' geographic location information, behavior pattern data and environmental perception data, and receiving information and services from social platforms. The 5G message geographic location technical characteristics refer to the technical characteristics of the user's geographic location contained in the message transmitted through the 5G network, including but not limited to geographic location information (such as longitude and latitude), behavior pattern data (such as movement speed, dwell time) and environmental perception data (such as the noise level and temperature of the surrounding environment). These features help social platforms understand users' real-time status and context more accurately, and provide users with more personalized services.

[0064] Optionally, this embodiment may use a differential global navigation satellite system algorithm to enhance the geographic location information to obtain the geographic location coordinates of the target user with sub-meter accuracy.

[0065] S12. Extract key features used to characterize the user's current status and activity scenarios from geographic location information, behavior pattern data, and environmental perception data to form a user dynamic portrait. Based on the user dynamic portrait and a pre-built interest graph model, calculate the similarity score between the target user and known users.

[0066] Among them, known users are users who use other terminal devices. The key features extracted from the geographic location information may include latitude and longitude coordinates, venue type, moving speed and direction, residence time, etc. The key features extracted from the behavior pattern data may include daily activity tracks, activity preferences, liveliness frequency and social interaction frequency, etc. The key features extracted from the environmental perception data may include weather conditions, traffic flow, air quality, surrounding facilities and services. By extracting the above key features, the current state and activity scene of the user can be fully characterized. The user dynamic portrait is a comprehensive description of the current state and activity scene of the user based on geographic location information, behavior pattern data and environmental perception data. It is used to accurately reflect the living habits, interests and immediate needs of the target user in order to better match similar users or provide personalized recommendations. The interest graph model is a pre-built mathematical model used to represent the interest correlation between different users. By calculating the similarity score between the target user and the known user, the social objects that may be of interest are predicted and recommended, thereby improving the success rate of matching. The similarity score is a quantitative indicator to measure the similarity of interests or living habits between two users. It is used to screen out potential social objects with high similarity to the target user to improve the possibility and quality of establishing contact between the two parties.

[0067] The user dynamic portrait in the embodiment of the present application can not only consider the long-term interests of the target user, but also dynamically reflect the target user's immediate status and situation. Through real-time situation perception, it is ensured that the recommended potential social objects are more in line with the user's current needs, improving the accuracy and timeliness of matching.

[0068] S13: Based on the similarity score, combined with the user's online status, location proximity and immediate context information, the target potential social objects are screened out, wherein the target potential social objects are known users that meet the specified social scenario conditions.

[0069] Among them, online status indicates whether the user is currently in a contactable state, such as online, busy or offline. Online status can ensure that the recommended social objects are currently active and willing to accept new social relationships, thereby improving the success rate of interaction. Location proximity reflects the physical distance between the target user and known users. Considering the possibility of actual meeting or interaction, users with close geographical locations are recommended as potential social objects. Real-time context information can refer to the specific situation or activities that the user is currently in, such as attending a party, working hours, etc. According to the user's real-time context, social suggestions that are more in line with current needs are provided to increase the relevance and effectiveness of interaction.

[0070] This process not only takes into account the similarity of users' interests, but also comprehensively evaluates factors in multiple dimensions to ensure that the recommendation results are closer to the actual needs of users. Through multi-dimensional comprehensive evaluation, the accuracy of recommendations and user satisfaction are improved.

[0071] S14. Generate personalized interaction verification tasks for the target user and the target potential social object to verify each other, send the personalized interaction verification tasks of each other to the target user and the target potential social object respectively, receive the interaction verification results of the target user and the target potential social object, and when the interaction verification results of the target user and the target potential social object indicate that the two-way verification has passed, obtain the temporary sharing rules defined by the smart contract, and establish a social relationship between the target user and the target potential social object based on the temporary sharing rules.

[0072] Among them, the personalized interactive verification task can be a cooperative task, and a cooperative task requires the participation of both the target user and the target potential social object. Alternatively, the personalized interactive verification task can be two independent tasks, wherein independent task A is a task used by the target user to verify the target potential social object, which will be sent to the target potential social object later so that the target potential social object can complete it independently; independent task B is a task used by the target potential social object to verify the target user, which will be sent to the target user later so that the target user can complete it independently. Both cooperative tasks and independent tasks can achieve two-way verification.

[0073] When two-way verification is passed, temporary sharing rules are defined through smart contracts to formally establish social relationships. This mechanism not only enhances the authenticity and effectiveness of the interaction, but also provides a transparent and secure rule framework. The two-way verification mechanism provided in this embodiment can avoid the influence of false information and bad users, and improves the authenticity and security of the interaction through two-way verification and smart contract protection.

[0074] The embodiment of the present application provides a method for establishing social relationships based on the technical features of 5G message geolocation, which improves the intelligence, personalization and security of the social relationship establishment process through user dynamic profiling, multi-dimensional screening mechanism, two-way verification and smart contract protection. These technologies not only solve the problems of inaccurate matching and poor interaction effects in the prior art, but also provide a more efficient and reliable social relationship establishment mechanism through intelligent and adaptive technical means, enhancing the trust and interactive experience of target users.

[0075] In some possible embodiments, S13, based on the similarity score, combined with the user's online status, location proximity and immediate context information, screening out target potential social objects includes:

[0076] Step 131: Filter out first potential social objects from the known user set to form a first potential social object set, where the first potential social objects are known users whose similarity scores with the target user are greater than or equal to a preset score threshold.

[0077] Among them, the known user set can refer to the set of all users who have registered and used terminal devices in the social platform, which serves as the basic data source for screening potential social objects, ensuring that there are enough candidate users to choose from. Similarity scores can be used to reflect similar interests. For example, if the target user likes outdoor sports and photography, then users with high similarity scores may also be interested in these activities. The preset scoring threshold is a minimum similarity scoring standard set to filter out known users who do not meet the requirements. Ensure that the potential social objects screened out reach at least a certain level of similarity to avoid recommending irrelevant users. For example, the preset scoring threshold is set to 0.7, and known users with a similarity score greater than or equal to 0.7 are selected as the first potential social objects. Compared with the known user set, the first potential social object set narrows the scope of potential social objects, making subsequent screening more efficient.

[0078] Step 132: Dynamically generate a personalized geographic fence based on the target user's geographic location information, behavior pattern data, and environmental perception data.

[0079] Among them, personalized geo-fence is a virtual boundary dynamically generated based on the target user's geographic location information, behavioral pattern data and environmental perception data. It is used to limit the geographical scope of potential social objects, which can ensure that the recommended potential social objects are close to the target user in physical distance, increasing the possibility of meeting or interaction.

[0080] For example, if the target user is taking a walk in a park, the social platform generates a geo-fence with a radius of 1 km centered on the park, and gives priority to recommending users who are active within this range.

[0081] As a possible implementation, step 132, dynamically generating a personalized geo-fence according to the target user's geographic location information, behavior pattern data, and environmental perception data, includes:

[0082] Step a1: Based on the geographic location information of the target user, a support vector machine is used to identify the type of place where the target user is currently located. A support vector machine is a supervised learning model used for classification and regression analysis. In this embodiment, it is used to identify the type of place where the target user is currently located to ensure the accuracy of fence generation. For example, based on the geographic location information of the target user, the support vector machine can identify whether the user is currently in a park, a shopping mall, or an office.

[0083] Step a2: Obtain the initial radius of the geo-fence corresponding to the venue type from the preset radius table, combine the target user's activity range, venue characteristics and behavior pattern data, and use an adaptive polygon generation algorithm to dynamically adjust the initial boundary shape of the geo-fence according to the traffic flow and weather conditions in the environmental perception data.

[0084] Among them, the preset radius table contains a table of the initial radius of the geo-fence corresponding to different types of venues, providing a default geo-fence radius for different types of venues as a basis for dynamic adjustment. For example, for a park, the default radius may be 1 km; for a cafe, the default radius may be 0.5 km. The activity range may refer to the size of the area where the target user usually moves, which can be derived based on historical behavior pattern data to help adjust the boundaries of the geo-fence to ensure that the fence covers the actual activity area of ​​the user. The venue characteristics are parameters that describe the characteristics of the venue, such as the function of the venue, the density of people flow, etc. In combination with the venue characteristics, the fence generation algorithm is optimized to make the fence more suitable for the actual scene. For example, in a shopping mall with a large flow of people, the fence may be set slightly larger to cover more potential objects; while in a quiet library, the fence may be smaller to reduce interference. Behavior pattern data is data that records the daily activity patterns of users, including but not limited to activity time, frequency, preferences, etc. It is used to refine the fence adjustment rules to ensure that the fence adapts to the habits and needs of users. For example, if the target user runs in the park from 8 to 9 am every day, the social platform appropriately adjusts the fence during this time period to cover more known users of similar activities. The adaptive polygon generation algorithm is an algorithm that can dynamically adjust the polygon shape based on environmental perception data. It dynamically adjusts the boundary shape of the fence to make it more reasonable based on real-time data such as traffic flow and weather conditions. For example, during busy traffic hours or in bad weather conditions, the social platform reduces the fence range to improve matching accuracy and interaction quality.

[0085] Step a3: Obtain the fence size satisfaction score and shape rationality score from user feedback, and determine the feedback error based on the fence size satisfaction score and shape rationality score. For example, if the fence size satisfaction score is 0.8 and the shape rationality score is 0.9, then the feedback error is (1-0.8)+(1-0.9)=0.3.

[0086] If the feedback error is greater than or equal to the preset error value, step a4 can be performed; if the feedback error is less than the preset error value, the current fence parameters can be used as the final fence parameters. The fence parameters include fence size and fence shape.

[0087] Step a4: Based on the feedback error, the preset objective function is minimized using the gradient descent method to obtain optimized fence parameters, and the optimized fence parameters correspond to the personalized geographic fence.

[0088] Among them, the gradient descent method is used to optimize the fence parameters so that the fence is more in line with the user's needs and actual situation. Personalized geo-fencing can ensure that the fence not only meets the user's personalized needs but also adapts to the actual situation. The preset objective function can be adopted as follows:

[0089] ;

[0090] in, is a set of fence parameters The corresponding objective function value is and are the target users’ satisfaction scores on the size and shape of the fence, and is the ideal score for the preset fence size and the ideal score for the shape, and is the weight coefficient of the fence size scoring item and the shape scoring item, which is used to determine the importance of the two scoring items. and are the weights of different penalty terms, and They are the penalty functions for areas that are too large or too small and for unreasonable shapes.

[0091] In the above formula, the penalty function for an area that is too large or too small can be expressed as follows:

[0092] ;

[0093] in, is a set of fence parameters The actual area of ​​the corresponding fence, and are the minimum and maximum allowed values ​​of the fence area respectively.

[0094] The penalty function for unreasonable shape can be expressed as follows:

[0095] ;

[0096] in, is a set of fence parameters Corresponding metrics for measuring the shape complexity of fences, such as perimeter-to-area ratio, number of polygon vertices, etc.; is the maximum allowed value of fence shape complexity.

[0097] The objective function after introducing the penalty term can more comprehensively evaluate the rationality of the fence parameters, ensuring that the generated fence not only meets the personalized needs of users, but also avoids unreasonable area and shape problems, thereby improving user experience and interactive effects.

[0098] For example, a personalized geo-fence may be an irregular polygon that accurately covers places frequented by target users and takes into account factors such as traffic flow and weather conditions.

[0099] By executing steps a1 to a4, this embodiment dynamically adjusts the size and shape of the geo-fence through an intelligent algorithm to ensure that the geo-fence is more in line with the actual needs of the target user and environmental changes, thereby improving the flexibility and accuracy of matching. By introducing a user feedback mechanism and continuously optimizing fence parameters, the satisfaction of the target user and the adaptive ability of the geo-fence are improved.

[0100] Step 133: Use a K-nearest neighbor algorithm to filter out second potential social objects from the first potential social object set to form a second potential social object set.

[0101] Among them, the second batch of potential social objects screened by the K nearest neighbor algorithm not only have high similarity scores, but are also located within the personalized geographic fence. Compared with the first set of potential social objects, the second set of potential social objects further narrows the scope of potential social objects and increases the accuracy of recommendations.

[0102] For example, after screening by the K-nearest neighbor algorithm, a set of 10 known users is obtained, and they are very compatible with the target user in terms of interests and geographic locations.

[0103] As a possible implementation manner, step 133, using a K-nearest neighbor algorithm to screen out second potential social objects from the first potential social object set to form a second potential social object set, includes:

[0104] Step b1: Calculate the original distance from the first potential social object to the target user based on the geographic location information of each first potential social object in the first potential social object set and the geographic location information of the target user to generate an original distance matrix. For example, if there are five potential social objects B1, B2, B3, B4, B5 around the target user A, the original distance matrix will record the distance from A to B1, B2, B3, B4, B5.

[0105] Step b2: Design a distance decay factor, and adjust the original distance using the distance decay factor according to the original distance matrix to obtain the target distance, so as to generate a target distance matrix. It should be understood that the target distance matrix more accurately reflects the real proximity between the potential social objects and the target user, and is used for screening and sorting.

[0106] The distance attenuation factor is a function or coefficient used to adjust the original distance and consider the impact of distance on the matching effect. By introducing the attenuation factor, the impact of distance on the possibility of social interaction can be more reasonably reflected, avoiding reliance on straight-line distance. For example, the longer the distance, the more the attenuation factor gradually weakens the impact of distance.

[0107] Exemplarily, the target distance can be calculated using the following function:

[0108] ;

[0109] in is the target distance, is the distance decay factor, is the original distance matrix.

[0110] Step b3: Based on the target distance matrix, first potential social objects whose target distance to the target user within the geo-fence is less than a preset distance threshold are screened from the first potential social object set to form a preliminary screening result set. It should be understood that compared with the first potential social object set, the preliminary screening result set narrows the scope of potential social objects and improves the efficiency of subsequent screening.

[0111] Step b4: Sort the target distances from all first potential social objects to the target user in the preliminary screening result set, and select K first potential social objects with the smallest distances as the intermediate screening result set. The intermediate screening result set further refines the screening results to ensure that the potential social objects closest to the target user are selected. For example, K=5, the social platform selects the 5 users with the smallest distances to form the intermediate screening result set.

[0112] Step b5: Calculate the time matching degree based on the activity time data of the first potential social object in the intermediate screening result set and the activity time data of the target user; calculate the environmental feature similarity based on the environmental feature data of the first potential social object in the intermediate screening result set and the environmental feature data in the immediate context information of the target user, combined with an adaptive weighting mechanism; calculate the emotional state consistency based on the emotional state data of the first potential social object in the intermediate screening result set and the emotional state data in the immediate context information of the target user.

[0113] Among them, time matching is an indicator that measures the degree of overlap between the activity times of two users, ensuring that the recommended potential social objects have a high degree of overlap in activity time and improving the success rate of interaction. Environmental feature similarity is an indicator that measures the degree of similarity between the environmental features of two users (such as venue type, weather conditions, etc.), ensuring that the environmental conditions of the recommended potential social objects are similar, increasing the relevance and effectiveness of interaction. Emotional state consistency is an indicator that measures the consistency of the current emotional states of two users, ensuring that the recommended potential social objects have a high degree of fit in emotional state and increasing the quality and comfort of interaction.

[0114] Step b6: Based on the target distance, time matching, environmental feature similarity and emotional state consistency, combined with the corresponding preset weight coefficients, calculate the comprehensive score values ​​of all first potential social objects in the intermediate screening result set; the value of the preset weight coefficient is based on the historical interactive behavior data of the target user, and is dynamically adjusted using the reinforcement learning mechanism.

[0115] Exemplarily, the calculation formula of the comprehensive score is as follows:

[0116] ;

[0117] in, Is the first potential social target The comprehensive rating value of The target user With the first potential social object The time matching between The target user With the first potential social object The similarity of environmental characteristics between The target user With the first potential social object The consistency of emotional states. They are the preset weight coefficients of target distance, time matching, environmental feature similarity and emotional state consistency.

[0118] Step b7: Sort all first potential social objects in the intermediate screening result set according to the comprehensive score, and select the one with the largest comprehensive score. first potential social objects as second potential social objects to form a second potential social object set, Less than K. For example, K=5, =3.

[0119] By executing steps b1 to b7, this embodiment can combine multiple dimensional factors such as target distance, time matching, environmental feature similarity, and emotional state consistency to perform a comprehensive score, ensuring that the recommended potential social objects are not only geographically close, but also highly meet the needs of the target user in many aspects. The preset weight coefficients are dynamically adjusted using the reinforcement learning mechanism, so that the embodiment of the application can continuously optimize the screening strategy based on the user's historical interactive behavior data, thereby improving the accuracy and personalization of the recommendation.

[0120] Step 134: When the target user is online, select a third potential social object from the second potential social object set to form a third potential social object set; the third potential social object is the second potential social object whose online status is online. If the target user wants to find a user to communicate with immediately, the social platform can recommend a user who is currently online. The third batch of potential social objects not only have high similarity scores and are geographically close to the target user, but are also online.

[0121] Exemplarily, after online status screening, a set of 5 known users is obtained, and the known users in the set meet the interest and geographic location conditions and are currently online.

[0122] Step 135: based on the activity type, activity time and weather conditions in the target user's immediate context information, select target potential social objects that meet the preset context matching rules from the third potential social object set. The preset context matching rules may refer to a series of predefined rules for determining whether the potential social objects match the target user's immediate context. The preset context matching rules are used to ensure that the recommended potential social objects not only match in terms of interests and geographic location, but are also suitable for interaction in a specific context.

[0123] By executing steps 131 to 135, this embodiment can achieve multi-stage step-by-step screening to ensure that the potential social objects finally recommended are not only of similar interests, but also online in real time, close in location, and meet the current situation conditions, thereby improving the accuracy of matching and the success rate of interaction. The introduction of personalized geo-fencing makes the recommendation results closer to the user's actual activity scene, enhancing the user experience.

[0124] Therefore, this embodiment further refines and optimizes the screening process of potential social objects based on steps S11 to S14. Through multi-stage screening, personalized geo-fence generation and multi-dimensional comprehensive evaluation, the accuracy, flexibility and user experience of matching are improved. These improvements not only solve the problems of inaccurate matching and poor interaction effects in the prior art, but also provide a more personalized and efficient method for establishing social relationships through intelligent and adaptive technical means.

[0125] In some possible embodiments, S14, generating a personalized interaction verification task for the target user and the target potential social object to verify each other, includes:

[0126] Step 141: Build a user relationship graph and use a graph neural network to predict the potential relationship strength between the target user and the target potential social object. The graph neural network can more accurately predict the potential relationship strength between the target user and the target potential social object based on historical interaction data and multi-dimensional features. The user relationship graph can be updated in real time to ensure that the prediction results always reflect the latest changes in user relationships.

[0127] Step 142: determine the task type according to the potential relationship strength, so that when the potential relationship strength is less than a preset strength threshold, a first independent task for the target user to verify the target potential social object and a second independent task for the target potential social object to verify the target user are designed; when the potential relationship strength is greater than or equal to the preset strength threshold, a cooperative task for the target user and the target potential social object to verify each other is designed; the first independent task is a task to be participated in by the target potential social object, the second independent task is a task to be participated in by the target user, and the cooperative task is a task to be participated in by the target user and the target potential social object together.

[0128] It should be understood that different potential relationship strengths reflect different development stages of relationships between users, and different types of tasks need to be designed to adapt to these stages. By setting a threshold, the potential relationship strength can be divided into two categories, and independent tasks and cooperative tasks can be designed respectively to better guide the development of relationships.

[0129] It should also be understood that for users with weaker potential relationships, designing independent tasks can gradually build trust; for users with stronger potential relationships, designing cooperative tasks can directly promote interaction. The transition from independent tasks to cooperative tasks can help users gradually deepen their understanding and avoid the discomfort that may come from entering high-intensity interactions too early. Through targeted design, the success rate of two-way verification can be significantly improved, ensuring that the social relationship ultimately established is more solid.

[0130] Step 143: Based on the preference information of the target user and the target potential social object, a task template corresponding to the preference information is selected from a preset task template library corresponding to the task type.

[0131] Among them, the preset task template library contains various types of tasks, covering different areas of interest and interaction methods, providing rich resources for personalized selection. Each user has different interests and preferences. Selecting a task template corresponding to the preference information can ensure that the task content is more in line with the user's actual needs. The task content is in line with the user's interests, which increases the user's enthusiasm and involvement in participation.

[0132] Step 144: Based on the personalized characteristics of the target user and the target potential social object, the corresponding task template is optimized to obtain an optimized template.

[0133] In step 144, this embodiment can further consider the personalized characteristics of the target user and target potential social objects (such as interests, communication style, interaction frequency, etc.), optimize the task template, and ensure that the task not only meets the user's long-term interests, but also can dynamically adapt to their current specific needs and situations. In addition, a feedback mechanism is introduced to enable the task template to be continuously optimized to meet the user's latest needs.

[0134] As a possible implementation method, step 144, based on the personalized characteristics of the target user and the target potential social object, the corresponding task template is optimized to obtain the optimized template, including:

[0135] Step c1: Obtain personalized characteristics of the target user and target potential social objects, and determine personalized needs of the target user and target potential social objects based on the personalized characteristics of the target user and target potential social objects. The personalized characteristics include interests, communication styles, and interaction frequencies, and the personalized needs include content preferences, interaction methods, and task levels.

[0136] For example, in the personalized features, regarding hobbies, user A likes outdoor sports (such as running and cycling), and user B likes outdoor sports (such as running). Regarding communication style, user A prefers a concise and direct communication method, and user B prefers a humorous and interesting communication method. Regarding interaction frequency, user A participates in outdoor activities 2-3 times a week, and user B participates in outdoor activities 3-4 times a week.

[0137] In terms of personalized needs, regarding content preferences, user A hopes that the task content is related to healthy living, while user B is interested in fitness tips. Regarding interaction methods, user A hopes to communicate through short messages or instant messaging tools, while user B prefers to interact through video calls. Regarding task levels, user A prefers simple and easy tasks, while user B is willing to try tasks that are somewhat challenging.

[0138] Step c2: Perform preliminary customized adjustments on the corresponding task template according to personalized needs to obtain an adjusted template.

[0139] Among them, the adjusted template contains task content, which is used as an independent task or a cooperative task. In the initial customized adjustment process, this embodiment is designed to be an independent task for verifying user A. A simple running route planning task can be designed, requiring user A to complete a new running route within a week and share the experience. To design an independent task for verifying user B, this embodiment can design a fun running challenge task, requiring user B to try a challenging running route and record a short video to share the experience. Or, when designing a cooperative task for verifying user A and user B, this embodiment can require user A and user B to plan a weekend hiking trip together, including selecting a route, preparing equipment, etc., and discussing the details of the plan through a video call.

[0140] Step c3: Implement the adjusted template and collect template suggestion information fed back by the participants. For the adjusted template corresponding to the independent task, the participants are the target potential social objects or target users. For the adjusted template corresponding to the cooperative task, the participants are the target potential social objects and target users.

[0141] For example, user A gives feedback: the running route planning task is interesting, but I hope there will be more content about running skills next time. User B gives feedback: the fun running challenge task is very exciting, but I think video recording is a bit troublesome. Or, both user A and user B think that the video call discussion in the cooperative task is very effective, but they hope that the difficulty of the task can be increased appropriately.

[0142] Step c4: Based on the template suggestion information fed back by the target potential social objects and the target users, the corresponding task template is optimized to obtain an optimized template.

[0143] Among them, the optimized template can be used as an optimized independent task or cooperative task. Exemplarily, the independent task used to verify user A is a small challenge task involving running skills, requiring user A to learn and practice a new running skill within two weeks and share the experience through short messages. The independent task used to verify user B can simplify the video recording requirements and change it to taking photos and attaching a brief text description to share a more challenging running experience. The cooperative task can increase the difficulty of the task and design a more challenging outdoor activity task, requiring user A and user B to plan a mountaineering activity together, including selecting routes, preparing equipment and formulating safety measures, and discussing the details of the plan through video calls.

[0144] By executing steps c1 to c4, this embodiment optimizes the task template based on personalized features and introduces a feedback-driven continuous optimization mechanism, so that the generated task template not only highly meets the personalized needs of users, but also can continuously adapt to the changes of users, thereby improving the accuracy and interactive effect of tasks. Therefore, this embodiment provides a more refined and dynamic task template optimization method, which enhances user experience and interactive quality.

[0145] Step 145: Based on the optimized template, generate a personalized interaction verification task for the target user and the target potential social object to verify each other.

[0146] By executing steps 141 to 145, this embodiment introduces dynamic adjustment of task types based on relationship strength, two-way verification and independent task design, personalized template selection and optimization, and comprehensive consideration of multi-dimensional factors. Based on steps S11 to S14, this embodiment further improves the intelligence, personalization, and flexibility of the social relationship establishment method. The above technology not only solves the problems of inaccurate matching and poor interaction effect in the prior art, but also provides a more diversified and efficient interaction verification mechanism through intelligent and adaptive technical means, thereby enhancing user experience and interaction effect.

[0147] In some possible embodiments, in step S14, a temporary sharing rule defined by a smart contract is obtained, and a social relationship between a target user and a target potential social object is established based on the temporary sharing rule, including:

[0148] Step 146: Use a distributed ledger query algorithm to obtain temporary sharing rules defined by smart contracts from the blockchain platform. The temporary sharing rules include: the type of shared content, access rights and validity period. The shared content type includes at least one of the following: geographic location information, activity records and POI recommendations. The access rights include at least one of the following: viewing, commenting and liking. Apply a differential privacy algorithm to set privacy protection measures for the temporary sharing rules so that the temporary sharing rules contain privacy protection clauses and allow users to withdraw access rights at any time.

[0149] Step 147: Use an automated execution method to automatically trigger the smart contract, so that the smart contract automatically executes the temporary sharing rules according to preset conditions.

[0150] Step 148: After the smart contract successfully executes the temporary sharing rule, a social relationship initialization method is used to establish a social relationship between the target user and the target potential social object.

[0151] By executing steps 146 to 148, this embodiment applies a differential privacy algorithm to set privacy protection measures for temporary sharing rules to ensure that temporary sharing rules contain privacy protection clauses. This not only protects the user's sensitive information, but also allows the user to withdraw access rights at any time. A distributed ledger query algorithm is used to obtain temporary sharing rules from the blockchain platform, and an automated execution method is used to automatically trigger the smart contract. This method ensures the transparency and immutability of temporary sharing rules while improving execution efficiency. Through the detailed design of temporary sharing rules, a more flexible content sharing and permission management mechanism is provided, enhancing user experience and interactive effects. After the smart contract successfully executes the temporary sharing rules, a social relationship initialization method is used to formally establish a social relationship between the target user and the target potential social object. This process ensures that the establishment of social relationships is based on clear rules and conditions, avoiding arbitrariness and uncertainty.

[0152] Figure 2 A structural diagram of a social relationship establishment system based on 5G message geographic location technical features provided in an embodiment of the present application, such as Figure 2 As shown, the system includes:

[0153] The acquisition module 21 is used to respond to the social relationship establishment request sent by the target terminal device and obtain the 5G message geographic location technical characteristics of the target user. The 5G message geographic location technical characteristics include: geographic location information, behavior pattern data and environmental perception data; the target user is the user using the target terminal device.

[0154] The extraction and calculation module 22 is used to extract key features for characterizing the user's current state and activity scene from the geographic location information, behavior pattern data and environmental perception data to form a user dynamic portrait, and calculate the similarity score between the target user and known users based on the user dynamic portrait and a pre-built interest graph model; the known users are users using other terminal devices.

[0155] The screening module 23 is used to screen out target potential social objects based on similarity scores, combined with user online status, location proximity and real-time context information; the target potential social objects are known users that meet the specified social scenario conditions.

[0156] Generate a communication module 24, which is used to generate a personalized interaction verification task for the target user and the target potential social object to verify each other, send the personalized interaction verification task of the target user and the target potential social object to each other, receive the interaction verification result of the target user and the target potential social object, and when the interaction verification result of the target user and the target potential social object indicates that the two-way verification has passed, obtain the temporary sharing rule defined by the smart contract, and establish a social relationship between the target user and the target potential social object based on the temporary sharing rule.

[0157] Figure 2 The social relationship establishment system based on the 5G message geographic location technical characteristics can be executed Figure 1 The implementation principle and technical effect of the method for establishing social relationships based on the 5G message geographic location technical features described in the illustrated embodiment will not be repeated. For the social relationship establishment system based on the 5G message geographic location technical features in the above embodiment, the specific way in which each module and unit performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0158] In one possible design, Figure 2 The social relationship establishment system based on the 5G message geographic location technical features of the illustrated embodiment can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32 .

[0159] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0160] The processing component 32 is used to: in response to a social relationship establishment request sent by a target terminal device, obtain the 5G message geographic location technical features of the target user, the 5G message geographic location technical features including: geographic location information, behavior pattern data and environmental perception data; the target user is a user using the target terminal device; extract key features used to characterize the user's current state and activity scene from the geographic location information, behavior pattern data and environmental perception data to form a user dynamic portrait, and calculate the similarity score between the target user and known users based on the user dynamic portrait and a pre-built interest graph model; the known user is a user using other terminal devices; based on the similarity score, combined with the user's online status, location proximity and immediate context information, screen out target potential social objects; the target potential social object is a known user that meets the specified social scene conditions; generate personalized interaction verification tasks for the target user and the target potential social object to verify each other, send each other's personalized interaction verification tasks to the target user and the target potential social object respectively, receive the interaction verification results of the target user and the target potential social object, and when the interaction verification results of the target user and the target potential social object indicate that the two-way verification has passed, obtain the temporary sharing rules defined by the smart contract, and establish a social relationship between the target user and the target potential social object based on the temporary sharing rules.

[0161] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0162] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as random access memory (RAM), static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0163] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0164] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0165] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0166] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0167] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The illustrated embodiment is a method for establishing social relationships based on the 5G message geographic location technical features.

[0168] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0169] The system embodiment described above is merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0170] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0171] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for establishing social relationships based on the technical features of 5G message geographic location, characterized in that: include: In response to a social relationship establishment request sent by a target terminal device, obtaining a 5G message geographic location technical feature of a target user, wherein the 5G message geographic location technical feature includes: geographic location information, behavior pattern data, and environmental perception data; the target user is a user using the target terminal device; Extract key features for characterizing the user's current state and activity scene from the geographic location information, behavior pattern data, and environmental perception data to form a dynamic user portrait, and calculate a similarity score between the target user and known users based on the dynamic user portrait and a pre-built interest graph model; the known users are users using other terminal devices; Based on the similarity score, combined with the user's online status, location proximity and immediate context information, the target potential social objects are screened out; the target potential social objects are known users who meet the specified social scenario conditions; Generate a personalized interaction verification task for the target user and the target potential social object to verify each other, send the personalized interaction verification task of each other to the target user and the target potential social object respectively, receive the interaction verification result of the target user and the target potential social object, and when the interaction verification result of the target user and the target potential social object indicates that the two-way verification has passed, obtain a temporary sharing rule defined by the smart contract, and establish a social relationship between the target user and the target potential social object based on the temporary sharing rule; The method of screening target potential social objects based on the similarity score and combining the user's online status, location proximity and real-time context information includes: Filtering out first potential social objects from the known user set to form a first potential social object set, wherein the first potential social objects are known users whose similarity scores with the target user are greater than or equal to a preset score threshold; Dynamically generate personalized geo-fences based on target users’ geographic location information, behavioral pattern data, and environmental perception data; In combination with the geo-fence, a K-nearest neighbor algorithm is used to filter out second potential social objects from the first potential social object set to form a second potential social object set; When the online status of the target user is online, a third potential social object is selected from the second potential social object set to form a third potential social object set; the third potential social object is the second potential social object whose online status is online; Based on the activity type, activity time and weather conditions in the real-time context information of the target user, a target potential social object that meets a preset context matching rule is screened out from the third potential social object set.

2. The method according to claim 1, characterized in that The method of dynamically generating a personalized geographic fence based on the target user's geographic location information, behavior pattern data, and environmental perception data includes: According to the geographical location information of the target user, a support vector machine is used to identify the type of place where the target user is currently located; Obtaining an initial radius of a geo-fence corresponding to the type of venue from a preset radius table, combining the activity range, venue characteristics, and behavior pattern data of the target user, and using an adaptive polygon generation algorithm to dynamically adjust the initial boundary shape of the geo-fence according to the traffic flow and weather conditions in the environmental perception data; Obtain the fence size satisfaction score and shape rationality score fed back by the user, and determine the feedback error according to the fence size satisfaction score and shape rationality score; Based on the feedback error, a preset objective function is minimized using a gradient descent method to obtain optimized fence parameters, where the optimized fence parameters correspond to a personalized geographic fence.

3. The method according to claim 1, characterized in that: The combining the geo-fence and using a K-nearest neighbor algorithm to select second potential social objects from the first potential social object set to form a second potential social object set includes: Calculate the original distance from the first potential social object to the target user according to the geographic location information of each first potential social object in the first potential social object set and the geographic location information of the target user to generate an original distance matrix; Designing a distance attenuation factor, and adjusting the original distance using the distance attenuation factor according to the original distance matrix to obtain a target distance, so as to generate a target distance matrix; Based on the target distance matrix, first potential social objects whose target distance to the target user within the geo-fence is less than a preset distance threshold are screened out from the first potential social object set to form a preliminary screening result set; sorting the target distances from all first potential social objects to the target user in the preliminary screening result set, and selecting K first potential social objects with the smallest distances as the intermediate screening result set; Calculate the time matching degree based on the activity time data of the first potential social object in the intermediate screening result set and the activity time data of the target user; calculate the environmental feature similarity based on the environmental feature data of the first potential social object in the intermediate screening result set and the environmental feature data in the immediate context information of the target user, combined with an adaptive weighting mechanism; calculate the emotional state consistency based on the emotional state data of the first potential social object in the intermediate screening result set and the emotional state data in the immediate context information of the target user; Based on the target distance, the time matching degree, the environmental feature similarity and the emotional state consistency, combined with the corresponding preset weight coefficient, the comprehensive score value of all first potential social objects in the intermediate screening result set is calculated; the value of the preset weight coefficient is based on the historical interactive behavior data of the target user and is dynamically adjusted by using a reinforcement learning mechanism; Sort all first potential social objects in the intermediate screening result set according to the comprehensive score, and select the one with the largest comprehensive score. first potential social objects as second potential social objects to form a second potential social object set, Less than K.

4. The method according to claim 1, characterized in that: The generating of a personalized interactive verification task for a target user and a target potential social object to verify each other includes: Build a user relationship graph and use graph neural networks to predict the potential relationship strength between the target user and the target potential social objects; Determine the task type according to the potential relationship strength, so that when the potential relationship strength is less than a preset strength threshold, a first independent task for the target user to verify the target potential social object and a second independent task for the target potential social object to verify the target user are designed, and when the potential relationship strength is greater than or equal to the preset strength threshold, a cooperative task for the target user and the target potential social object to verify each other is designed; the first independent task is a task to be participated in by the target potential social object, the second independent task is a task to be participated in by the target user, and the cooperative task is a task to be participated in by the target user and the target potential social object together; Based on the preference information of the target user and the target potential social object, selecting a task template corresponding to the preference information from a preset task template library corresponding to the task type; Based on the personalized characteristics of the target user and the target potential social object, the corresponding task template is optimized to obtain an optimized template; Based on the optimized template, a personalized interactive verification task is generated for the target user and target potential social object to verify each other.

5. The method according to claim 4, characterized in that The step of optimizing the corresponding task template based on the personalized characteristics of the target user and the target potential social object to obtain an optimized template includes: Obtaining personalized characteristics of the target user and the target potential social object, and determining personalized needs of the target user and the target potential social object according to the personalized characteristics of the target user and the target potential social object, wherein the personalized characteristics include interests, communication style, and interaction frequency, and the personalized needs include content preferences, interaction methods, and task levels; Performing preliminary customized adjustment on the corresponding task template according to the personalized needs to obtain an adjusted template; Implement the adjusted template and collect template suggestion information fed back by the participants. For the adjusted template corresponding to the independent task, the participants are the target potential social objects or target users. For the adjusted template corresponding to the cooperative task, the participants are the target potential social objects and target users. Based on the template suggestion information fed back by the target potential social object and the target user, the corresponding task template is optimized to obtain an optimized template.

6. The method according to claim 1, characterized in that The step of acquiring a temporary sharing rule defined by a smart contract and establishing a social relationship between a target user and a target potential social object based on the temporary sharing rule includes: A distributed ledger query algorithm is used to obtain temporary sharing rules defined by a smart contract from a blockchain platform, wherein the temporary sharing rules include: the type of shared content, access rights, and validity period, wherein the type of shared content includes at least one of the following: geographic location information, activity records, and recommendations of points of interest, and the access rights include at least one of the following: viewing, commenting, and liking; a differential privacy algorithm is applied to set privacy protection measures for the temporary sharing rules, so that the temporary sharing rules contain privacy protection clauses and allow users to withdraw access rights at any time; Adopting automated execution methods to automatically trigger smart contracts so that smart contracts automatically execute temporary sharing rules according to preset conditions; After the smart contract successfully executes the temporary sharing rules, the social relationship initialization method is used to establish the social relationship between the target user and the target potential social object.

7. A social relationship establishment system based on the 5G message geographic location technical features, characterized in that: include: An acquisition module, configured to obtain, in response to a social relationship establishment request sent by a target terminal device, a 5G message geographic location technical feature of a target user, wherein the 5G message geographic location technical feature includes: geographic location information, behavior pattern data, and environmental perception data; the target user is a user using the target terminal device; An extraction and calculation module is used to extract key features for characterizing the user's current state and activity scene from the geographic location information, behavior pattern data and environmental perception data to form a user dynamic portrait, and calculate a similarity score between the target user and a known user based on the user dynamic portrait and a pre-built interest graph model; the known user is a user using other terminal devices; A screening module is used to screen out target potential social objects based on the similarity score, combined with the user's online status, location proximity and immediate context information; the target potential social objects are known users who meet the specified social scenario conditions; Generate a communication module, which is used to generate a personalized interaction verification task for the target user and the target potential social object to verify each other, send the personalized interaction verification task of each other to the target user and the target potential social object respectively, receive the interaction verification result of the target user and the target potential social object, and when the interaction verification result of the target user and the target potential social object indicates that the two-way verification has passed, obtain a temporary sharing rule defined by the smart contract, and establish a social relationship between the target user and the target potential social object based on the temporary sharing rule; The method of screening target potential social objects based on the similarity score and combining the user's online status, location proximity and real-time context information includes: Filtering out first potential social objects from the known user set to form a first potential social object set, wherein the first potential social objects are known users whose similarity scores with the target user are greater than or equal to a preset score threshold; Dynamically generate personalized geo-fences based on target users’ geographic location information, behavioral pattern data, and environmental perception data; In combination with the geo-fence, a K-nearest neighbor algorithm is used to filter out second potential social objects from the first potential social object set to form a second potential social object set; When the online status of the target user is online, a third potential social object is selected from the second potential social object set to form a third potential social object set; the third potential social object is the second potential social object whose online status is online; Based on the activity type, activity time and weather conditions in the real-time context information of the target user, a target potential social object that meets a preset context matching rule is screened out from the third potential social object set.

8. A computing device, characterized in that It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a method for establishing social relationships based on the 5G message geographic location technical features as described in any one of claims 1 to 6.

9. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, a method for establishing social relationships based on the 5G message geographic location technical features as described in any one of claims 1 to 6 is implemented.

Images