Location recommendation method and device, computer device, readable storage medium and program product

Abstract

The application relates to a place recommendation method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: determining a candidate recommended place according to a current position of a target user and user characteristic information; determining a target associated user according to an overlap index of a historical trajectory path of the target user and historical trajectory paths of each associated user in a target associated user group; screening a target recommended place from the historical trajectory path of the target associated user; and performing trip planning based on the target recommended place to obtain a target trip planning result. The method can effectively improve the personalization and accuracy of place recommendation, and further generates a target trip planning result, thereby improving the trip planning efficiency.

Description

Technical Field

[0001] This application relates to the field of Internet technology, and in particular to a location recommendation method, apparatus, computer device, computer-readable storage medium, and computer program product. Background Technology

[0002] With the rapid development of internet tourism services, location services, and social networking technologies, various online tourism platforms and smart travel service software have emerged, and personalized recommendation technologies based on user location trajectories and travel preferences have been gradually implemented.

[0003] Traditional technologies often employ user behavior big data, collaborative filtering methods, and content matching tags to achieve this. These travel platforms and smart travel service software collect behavioral data from users across the internet, such as browsing, clicking, saving, and ordering, and statistically analyze indicators such as attraction popularity, ratings, and number of reviews. They then prioritize pushing high-popularity, high-traffic, and high-exposure attractions to users, thus forming a recommendation model centered on "popularity priority and traffic priority."

[0004] However, traditional recommendation models primarily focus on overall statistical patterns rather than the true preferences and social relationships of individual users. This approach results in highly homogenized recommendations and fragmented decision-making information, failing to accurately meet users' needs. Furthermore, the fragmented information requires users to manually organize and plan, leading to poor overall travel planning efficiency. Summary of the Invention

[0005] Therefore, it is necessary to provide a location recommendation method, device, computer equipment, computer-readable storage medium, and computer program product that can improve the matching degree between recommended locations and the actual travel preferences of target users, and accurately meet the recommendation needs of users, in order to address the above-mentioned technical problems.

[0006] Firstly, this application provides a location recommendation method, including:

[0007] Based on the target user's current location and user characteristics, candidate recommended locations are determined;

[0008] The target associated user is determined based on the overlap index between the historical trajectory path of the target user and the historical trajectory paths of each associated user in the target associated user group;

[0009] Target recommended locations are obtained by filtering from the historical trajectory paths of the target associated users;

[0010] Based on the target recommended location, a trip plan is performed to obtain the target trip plan result.

[0011] In one embodiment, determining the target associated user based on the overlap index between the target user's historical trajectory path and the historical trajectory paths of each associated user in the target associated user group includes:

[0012] Obtain a target associated user group that matches the target user, and calculate the overlap index of the historical trajectory paths of each associated user in the target associated user group and the target user on a preset grid map;

[0013] Based on the overlap index, target associated users are identified in the target associated user group.

[0014] In one embodiment, determining the target associated user in the target associated user group based on the overlap index includes:

[0015] By comparing the overlap index of each associated user with the target user, associated users whose overlap index reaches a preset threshold are selected as target associated users.

[0016] In one embodiment, the step of filtering out the target recommended location from the historical trajectory path of the target associated user includes:

[0017] Obtain information on each stop location included in the historical trajectory path of the target associated user;

[0018] Based on the frequency of occurrence of each of the aforementioned locations, the degree of overlap with the candidate recommended locations, and the degree of matching with the user characteristic information of the target user, corresponding weight coefficients are assigned to the candidate recommended locations.

[0019] The candidate recommended locations are reordered according to their weight coefficients from high to low to obtain a preset number of target recommended locations.

[0020] In one embodiment, the step of performing itinerary planning based on the target recommended location to obtain the target itinerary planning result includes:

[0021] Obtain the attribute information of each of the target recommended locations and the travel constraints of the target user;

[0022] Based on the attribute information of each of the target recommended locations and combined with the travel constraints, the target recommended locations are arranged in a time sequence to generate an initial travel planning result;

[0023] The dynamic environment data of the trip is obtained, and the initial trip planning result is verified and adjusted to obtain the target trip planning result.

[0024] In one embodiment, the method further includes:

[0025] Obtain map data;

[0026] The map data is hierarchically divided based on a preset spatial indexing algorithm to generate a grid map; the grid map is used to mark historical trajectory paths.

[0027] In one embodiment, the method further includes:

[0028] Obtain the historical trajectory information of the target user and each associated user in the target associated user group; the historical trajectory information includes the historical trajectory path formed by the target user and each associated user at each stop location node within a historical time period;

[0029] Based on a preset spatial gridding algorithm and the historical trajectory information, the trajectory paths of the target user and the associated users are fused in the grid map.

[0030] The grid map displays the trajectory paths of the target user and each of the associated users within the historical time period.

[0031] In one embodiment, obtaining the target user's historical trajectory information includes:

[0032] Obtain the authorization information of the target user, and periodically collect the stop location nodes of the target user within a historical time period based on the authorization information;

[0033] By integrating the aforementioned stop locations in chronological order, the historical trajectory information of the target user is obtained.

[0034] In one embodiment, the step of integrating the various stopover location nodes in chronological order to obtain the target user's historical trajectory information includes:

[0035] Geofencing and desensitization processing is performed on each of the aforementioned stop locations to hide the latitude, longitude, and time information corresponding to each of the aforementioned stop locations.

[0036] The anonymized stop locations are integrated in chronological order to obtain the target user's historical trajectory information.

[0037] In one embodiment, calculating the overlap index of the historical trajectory paths of each associated user in the target associated user group and the target user on a preset grid map includes:

[0038] Determine the grid area corresponding to the historical trajectory information of the target user and each associated user in the target associated user group;

[0039] The number and area of ​​overlap between the target user and the grid regions corresponding to the historical trajectory paths of each associated user are counted, and the overlap index with each associated user is calculated based on the number and area of ​​overlap.

[0040] In one embodiment, the method further includes:

[0041] A trajectory display page is shown, which includes a grid map marked with heat grids generated based on the target user's historical trajectory information;

[0042] In response to the selection operation of the target associated user, a heat grid corresponding to the historical trajectory information of the target associated user is overlaid and merged in the grid map.

[0043] In one embodiment, obtaining the target associated user group matching the target user includes:

[0044] Display a list of candidate associated user groups, and in response to a selection operation on a target associated user group in the list, retrieve the target associated user group; or...

[0045] Display a list of associations, and in response to a checkmark operation performed in the list of associations, generate a target associated user group based on each checked candidate user.

[0046] In one embodiment, the method further includes:

[0047] In response to a query operation on the target associated user group, the overlap index information corresponding to each associated user in the target associated user group is displayed on the list display page.

[0048] Secondly, this application also provides a location recommendation device, comprising:

[0049] The first determination module is used to determine candidate recommended locations based on the target user's current location and user characteristic information;

[0050] The second determining module is used to determine the target associated user based on the overlap index between the historical trajectory path of the target user and the historical trajectory paths of each associated user in the target associated user group.

[0051] The filtering module is used to filter and obtain target recommended locations from the historical trajectory paths of the target associated users;

[0052] The generation module is used to perform itinerary planning based on the target recommended location and obtain the target itinerary planning result.

[0053] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0054] Based on the target user's current location and user characteristics, candidate recommended locations are determined;

[0055] The target associated user is determined based on the overlap index between the historical trajectory path of the target user and the historical trajectory paths of each associated user in the target associated user group;

[0056] Target recommended locations are obtained by filtering from the historical trajectory paths of the target associated users;

[0057] Based on the target recommended location, a trip plan is performed to obtain the target trip plan result.

[0058] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0059] Based on the target user's current location and user characteristics, candidate recommended locations are determined;

[0060] The target associated user is determined based on the overlap index between the historical trajectory path of the target user and the historical trajectory paths of each associated user in the target associated user group;

[0061] Target recommended locations are obtained by filtering from the historical trajectory paths of the target associated users;

[0062] Based on the target recommended location, a trip plan is performed to obtain the target trip plan result.

[0063] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0064] Based on the target user's current location and user characteristics, candidate recommended locations are determined;

[0065] The target associated user is determined based on the overlap index between the historical trajectory path of the target user and the historical trajectory paths of each associated user in the target associated user group;

[0066] Target recommended locations are obtained by filtering from the historical trajectory paths of the target associated users;

[0067] Based on the target recommended location, a trip plan is performed to obtain the target trip plan result.

[0068] The aforementioned location recommendation method, apparatus, computer equipment, computer-readable storage medium, and computer program product determine candidate recommended locations by combining the target user's current location and user characteristic information. They then filter target associated users based on the overlap index of the historical trajectory paths of the target user and each associated user in the target associated user group. Furthermore, they accurately select target recommended locations from the historical trajectory paths of the target associated users, and finally generate target travel planning results based on the target recommended locations. This achieves a deep integration of user personalized preferences and social circle trajectory preferences. It not only makes location recommendations more aligned with users' travel habits and social association preferences, improving the accuracy and practicality of the recommendation results, but also enables the rapid generation of suitable travel planning schemes based on recommended locations, effectively simplifying the user's travel decision-making process and improving the efficiency of overall travel planning. Attached Figure Description

[0069] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0070] Figure 1 This is a diagram illustrating the application environment of a location recommendation method in one embodiment;

[0071] Figure 2 This is a flowchart illustrating a location recommendation method in one embodiment;

[0072] Figure 3 This is a flowchart illustrating the steps for determining the target associated user in one embodiment;

[0073] Figure 4 This is a flowchart illustrating the steps of filtering target associated users based on a preset threshold in one embodiment;

[0074] Figure 5 This is a flowchart illustrating the steps for filtering target recommended locations in one embodiment;

[0075] Figure 6 This is a flowchart illustrating the steps for generating the target route planning result in one embodiment;

[0076] Figure 7 This is a flowchart illustrating the steps of generating a grid map in one embodiment;

[0077] Figure 8 This is a flowchart illustrating the steps of merging the trajectory paths of the target user and each associated user in one embodiment.

[0078] Figure 9This is a flowchart illustrating the steps for obtaining historical trajectory information of a target user in one embodiment;

[0079] Figure 10 This is a flowchart illustrating the process of desensitizing the historical trajectory information of a target user in one embodiment.

[0080] Figure 11 This is a flowchart illustrating the steps for calculating the overlap index between the target user and each associated user in one embodiment.

[0081] Figure 12 This is a flowchart illustrating the steps of overlaying and displaying a heat map of the target-associated user's historical trajectory information in one embodiment.

[0082] Figure 13 This is a schematic diagram of the trajectory display page in one embodiment;

[0083] Figure 14 This is a flowchart illustrating the steps of displaying the overlap index information of each associated user on a list display page in one embodiment.

[0084] Figure 15 This is a schematic diagram of a list display page in one embodiment;

[0085] Figure 16 This is a structural block diagram of a location recommendation device in one embodiment;

[0086] Figure 17 This is an internal structural diagram of a computer device in one embodiment;

[0087] Figure 18 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0088] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0089] It should also be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0090] Before describing the embodiments of this application, it should be noted that the terms "in response to" and "based on" are used herein to indicate corresponding user operations or triggering conditions, such as selection operations, query operations, triggering operations, switching operations, etc. Subsequent actions are executed upon the occurrence of the corresponding operation or the fulfillment of a preset condition: for example, after the trajectory display page has loaded, based on the selection operation of a target associated user group, based on the achievement of an overlap index calculation condition, etc. The timing of the subsequent actions executed in response to the operation or condition is as follows: for example, calculating the trajectory overlap index between users, filtering target associated users, re-ranking candidate recommended locations by weight, displaying a trajectory heatmap on the map interface, etc. It is worth noting that the time of execution of the subsequent actions and the time when the operation occurs or the condition is met are not necessarily strongly correlated. For example, in some cases, subsequent actions can be executed immediately upon the occurrence of the operation or the fulfillment of the condition: for instance, after a user selects an associated user, the terminal immediately overlays and displays the corresponding trajectory heatmap information on the grid map. In other cases, subsequent actions may be executed only after a short processing period following the occurrence of the operation or the fulfillment of the condition: for instance, after a user triggers a location recommendation request, candidate location retrieval, weight calculation, and ranking optimization are performed based on the current location, user characteristics, and the historical trajectories of the target associated user. This process involves spatial grid matching, trajectory comparison, weight calculation, and other processing, requiring a short processing period. Furthermore, "triggering an operation" refers to an action performed by the user on the map interface of the location recommendation application through interactive methods such as clicking, checking, swiping, or tapping. These operations directly trigger the corresponding functional responses in this application, such as querying associated user groups, selecting target associated users, and refreshing location recommendation results—core processes.

[0091] Specifically, the location recommendation method provided in this application embodiment can be applied to, for example, Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or placed on a cloud or other network server. Server 104 receives the target user's current location and user characteristic information reported by terminal 102, and determines candidate recommended locations accordingly. Server 104 further obtains target associated user groups matching the target user, calculates the overlap index of the historical trajectory paths of each associated user and the target user on a preset grid map, and filters target associated users from the target associated user groups based on this overlap index. Finally, server 104 combines the stops in the historical trajectory paths of the filtered target associated users, re-ranks the candidate recommended locations by weight to obtain the target recommended location, and returns the target recommended location to terminal 102 for display. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, projection devices, etc. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted displays. Head-mounted displays can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. Server 104 can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server providing cloud computing services.

[0092] In one exemplary embodiment, such as Figure 2 As shown, a location recommendation method is provided, which can be applied to... Figure 1 The following explanation uses an application system where the terminal interacts with the server as an example, including steps 202 to 208. Wherein:

[0093] Step 202: Determine candidate recommended locations based on the target user's current location and user characteristic information.

[0094] In implementation, the server receives the target user's real-time location information uploaded by the terminal, along with user characteristic information related to the user profile. Subsequently, the server combines the target user's current location information to define the recommended geographical area, and simultaneously constructs a personalized preference model based on the user characteristic information. Then, it retrieves and filters locations matching the geographical area and user preferences from a pool of popular POIs (Points of Interest) resources such as scenic spots, restaurants, and tourist attractions, using these as preliminary candidate recommended locations to lay the foundation for subsequent precise recommendations.

[0095] Optionally, user characteristic information includes, but is not limited to, data on user travel preferences, travel frequency, check-in types, interest tags, etc., to make preliminary location recommendations based on user characteristic information.

[0096] Step 204: Determine the target associated user based on the overlap index between the target user's historical trajectory path and the historical trajectory paths of each associated user in the target associated user group.

[0097] In practice, the server obtains the historical trajectory paths of the target user and each associated user in the target associated user group, calculates the overlap index of the two trajectories on a preset grid map, and then filters out associated users whose overlap index meets the preset threshold and identifies them as target associated users.

[0098] Specifically, the application or content recommendation platform used by the target user has built and stored its corresponding social relationship chain and social relationship network. Simultaneously, the application or content recommendation platform records various associated users and related user groups. Thus, when the target user initiates a location recommendation request within the application or content recommendation platform, the server displays all associated user groups to the user. The user can directly select a target associated user group from the existing ones, or independently filter and recombine from all associated users to construct a new target associated user group. Simultaneously, the server has divided the geographic space into a multi-level hexagonal pre-set grid map using the H3 spatial gridding algorithm and completed the grid mapping of the target user's and each user's historical trajectory paths (after geofencing anonymization) within the target associated user group. Subsequently, based on this grid map, the server performs spatial overlap matching between the target user's historical trajectory grid and the historical trajectory grids of each associated user. By calculating the proportion of shared access grids combined with social trust weights, the overlap index of historical trajectory information between each associated user and the target user is obtained. This overlap index characterizes the degree of spatial overlap between the historical trajectory paths of each associated user and the target user based on a preset grid map. It also integrates social trust correlation to comprehensively reflect the similarity and compatibility between the associated users and the target user in terms of travel trajectories and geographical preferences. The social trust weight is dynamically adjusted by social interaction indicators such as the frequency of private messages and the number of likes between users.

[0099] The server has a pre-set threshold for the overlap index. After the server calculates the overlap index between each associated user in the target user group and the target user, it compares the overlap index of each associated user in the target user group with the threshold and filters out associated users whose overlap index is higher than the threshold. At the same time, it can sort the users based on the overlap index value, and select the associated users with the higher index ranking. The users with the higher ranking are identified as target associated users. These target associated users have a higher similarity and fit with the target user in terms of travel trajectory and geographical preferences, and their historical trajectory information has higher reference value for the location recommendation of the target user.

[0100] Step 206: Filter out the target recommended locations from the historical trajectory paths of the target associated users.

[0101] In practice, the server extracts stop location information from the historical trajectory path of the target associated user, combines it with the user characteristic information of the target user, re-ranks the candidate recommended locations by weight, and selects the target recommended location.

[0102] Specifically, the server first extracts the marked stops in the historical trajectory paths of each target-related user, analyzes the characteristics of these stops such as type, frequency of access, and duration of stay, and then matches candidate recommended locations with the stops of the target-related users. Candidate recommended locations falling within the high-frequency stay grid area or high overlap index grid area of ​​the target-related user are given higher ranking weights, while candidate recommended locations with low matching degree with the stop features of the target-related user are given lower weights, thus completing the weight re-ranking of all candidate recommended locations. Finally, based on the weight ranking and recommendation quantity requirements, the server selects the top-ranked locations (e.g., top 5) as target recommended locations and pushes the recommendation results to the terminal for display, allowing target users to choose.

[0103] Step 208: Perform itinerary planning based on the target recommended location to obtain the target itinerary planning result.

[0104] In practice, the server plans the route and arranges the nodes based on the selected target recommended locations, combined with the target user's travel time, mode of transportation and preferences, thereby generating a target itinerary planning result that includes travel order, stay duration and transportation options.

[0105] Specifically, the server first acquires attribute information for each target recommended location, including geographical location, opening hours, recommended stay duration, attraction popularity, and transportation accessibility data. Simultaneously, it collects the target user's travel constraints, such as travel start and end times, daily playtime, transportation preferences, travel budget limits, and physical exertion requirements. Then, based on the attribute information of each target recommended location and the travel constraints, the server performs temporal arrangement and route optimization for each target recommended location. For example, it connects nodes according to geographical proximity, opening time order, or the user's preferred pace of play, generating an initial travel planning result that includes the visit order of each recommended location, arrival and departure times, and transportation connection schemes. Next, the server acquires dynamic environmental data for the travel itinerary. The dynamic environmental data for this trip includes real-time traffic conditions, visitor density at attractions, weather conditions, and estimated dynamic information such as temporary park closure notices. In this way, the server verifies and adjusts the initial trip planning results, such as replacing congested road sections, adjusting the order of attractions visited, increasing or decreasing the duration of stay, or providing alternative options. It corrects content in the initial trip that does not match the actual environment, and finally obtains the target trip planning result that takes into account user needs, recommended location attributes, and real-time environmental conditions.

[0106] The aforementioned location recommendation method determines candidate recommended locations by combining the target user's current location and user characteristic information. It then filters target related users based on the overlap index of the historical trajectory paths of the target user and each related user in the target related user group. Finally, it accurately selects target recommended locations from the historical trajectory paths of the target related users and generates target travel planning results based on the target recommended locations. This achieves a deep integration of user personalized preferences and social circle trajectory preferences. It not only makes location recommendations more in line with users' travel habits and social association preferences, improving the accuracy and practicality of the recommendation results, but also enables the rapid generation of suitable travel planning schemes based on recommended locations, effectively simplifying the user's travel decision-making process and improving the efficiency of overall travel planning.

[0107] In one exemplary embodiment, such as Figure 3 As shown, the specific processing steps of step 204 include:

[0108] Step 301: Obtain the target associated user group that matches the target user, and calculate the overlap index of the historical trajectory paths of each associated user in the target associated user group and the target user on the preset grid map.

[0109] In implementation, the server retrieves the target associated user group matched with the target user, collects the complete historical trajectory path data of each associated user in the target associated user group after being de-identified by geofencing, and loads a pre-defined grid map with pre-divided areas and numbered labels. The server maps the historical trajectory paths of the target user and each associated user to the corresponding grid cells on the grid map, counts the number of grids covered by both trajectories and the area of ​​overlapping regions, and performs a weighted calculation based on a pre-defined social trust weight to calculate the trajectory overlap index of each associated user relative to the target user, thus completing the quantitative calculation of multi-user trajectory similarity.

[0110] Step 302: Based on the overlap index, identify the target associated users in the target associated user group.

[0111] In implementation, the server aggregates the overlap index values ​​of all associated users within the target associated user group. Each overlap index value is then compared and verified against a pre-set threshold on the server, and associated users with an overlap index greater than or equal to the pre-set threshold are selected. These associated users have a higher degree of overlap with the target user's travel trajectories, and their travel and stay habits and preferences are more aligned. The server designates these qualified associated users as target associated users, using them as the core reference for subsequent location analysis and recommendations.

[0112] In this embodiment, the server relies on a standardized grid map to achieve spatial comparison of trajectory data. It accurately calculates the trajectory overlap index between users through quantitative indicators and uses the overlap index threshold as a screening criterion to accurately screen target related users with high matching degree from the target related user group. This provides an accurate and suitable reference data source for subsequent steps such as extracting stop locations, allocating candidate location weights, and personalizing itinerary planning, ensuring the rationality and accuracy of the overall location recommendation scheme.

[0113] In one exemplary embodiment, such as Figure 4 As shown, the specific processing steps of step 302 include:

[0114] Step 401: Compare the overlap index between each associated user and the target user, and select the associated users whose overlap index reaches a preset threshold as the target associated users.

[0115] In implementation, the server compares the trajectory overlap index of each associated user within the target user group with that of the target user. Each index value is matched against a preset overlap index threshold. Users with index values ​​greater than or equal to this threshold are selected as target associated users and used as references for subsequent candidate location optimization. The preset threshold for selecting target associated users can be flexibly adjusted according to the required accuracy of location recommendations to ensure a higher degree of matching between the selected target associated users and the target user in terms of travel trajectory preferences. This ensures that the historical locations of these users provide greater reference value for personalized location recommendations to the target user.

[0116] In this embodiment, by comparing the overlap index of each associated user with a preset threshold and selecting those who meet the criteria as target associated users, it is possible to quickly and accurately identify target associated users who have a high degree of fit with the trajectory preferences of the target users. This provides a high-value trajectory data basis for the subsequent weight re-sorting of candidate recommended locations, effectively improving the personalization and accuracy of location recommendations.

[0117] In one exemplary embodiment, such as Figure 5 As shown, the specific processing steps of step 206 include:

[0118] Step 501: Obtain information on each stop location contained in the historical trajectory path of the target associated user.

[0119] In implementation, the server extracts all anonymized stop location information from the historical trajectory paths of the identified target users. This stop location information includes core content such as the grid area to which the stop location belongs, POI type, access frequency, and stop characteristics. At the same time, the extracted stop location information is structured and organized to provide accurate and standardized reference data for subsequent weight coefficient allocation.

[0120] Step 502: Assign corresponding weight coefficients to candidate recommended locations based on the frequency of occurrence of each stop location, the degree of overlap with candidate recommended locations, and the degree of matching with the user characteristic information of the target user.

[0121] In implementation, after the server extracts the stop location information from the historical trajectory path information of each target-related user, the server matches the candidate recommended locations with the stop locations of the target-related users. It then assigns weight coefficients to each candidate recommended location based on multi-dimensional indicators. Candidate recommended locations falling within the high-frequency stop grid area or the high overlap index grid area of ​​the target-related user have their ranking weight increased, while candidate recommended locations with low matching degree with the stop location characteristics of the target-related user have their weight decreased. Specifically, the server compares the stop locations corresponding to the target-related user with the candidate recommended locations. Based on the overlap between each stop location and the candidate recommended locations, it determines whether there are candidate recommended locations identical to the stop locations. If candidate recommended locations identical to the stop locations are found, the frequency of occurrence of that stop location is used as the basic standard for weight allocation; the higher the frequency of occurrence, the higher the weight percentage of the candidate recommended point. Furthermore, it combines user characteristic information such as the target user's travel preferences and interest tags to match the fit between the candidate recommended locations and user characteristics. The higher the fit, the higher the weight is assigned. Finally, the comprehensive weight coefficient of each candidate recommended location is obtained through multi-dimensional weighted calculation.

[0122] Step 503: Re-sort the candidate recommended locations according to the weight coefficient from high to low, and filter to obtain a preset number of target recommended locations.

[0123] In implementation, the server sorts all candidate recommended locations in descending order of comprehensive weight coefficient. Based on the display requirements and accuracy requirements of the application or content recommendation platform for location recommendations, a preset number is set. From the sorted candidate recommended locations, the server selects the top-ranked preset number of locations and determines them as the final target recommended locations. At the same time, the server completes the structured encapsulation of the recommendation results to prepare for push to the terminal for display.

[0124] In this embodiment, by extracting target-related user stay location information from multiple dimensions, and combining stay frequency, location overlap, and user feature matching degree, weight coefficients are assigned to candidate recommended locations, and target recommended locations are filtered according to weight. This effectively improves the matching degree between the recommendation results and the travel needs of target users. At the same time, through quantitative weight calculation and sorting filtering, the location recommendation process is made more standardized, ensuring the accuracy and personalization of the recommendation results.

[0125] In one exemplary embodiment, such as Figure 6 As shown, the specific processing steps of step 208 include:

[0126] Step 601: Obtain the attribute information of each target recommended location and the travel constraints of the target user.

[0127] During implementation, the server retrieves all filtered target recommended location data and collects complete attribute information for each target recommended location in batches, including geographical coordinates, location type, opening hours, recommended stay duration, attraction popularity, transportation accessibility, and tourism service characteristics. Simultaneously, the server reads the target user's travel constraints from local storage or uploaded by the terminal, covering available travel time (start and end times), daily playtime, transportation preferences, itinerary pace requirements, travel budget, activity range restrictions, physical exertion requirements, and personalized travel restrictions, providing comprehensive basic data support for subsequent itinerary arrangement and planning calculations.

[0128] Step 602: Based on the attribute information of each target recommended location and combined with the travel constraints, arrange the target recommended locations in a time sequence to generate the initial travel planning result.

[0129] In implementation, the server uses the inherent attributes of each target recommended location as the basis for arrangement, and performs comprehensive matching calculations based on the target user's various travel constraints. Specifically, it arranges all target recommended locations in a reasonable time sequence and spatial route according to their spatial distance, opening time, reasonable connection between routes, and the user's personal travel preferences. Subsequently, the server uniformly plans the access order, arrival time, stay duration, and route connection methods for each location, integrating multi-dimensional arrangement content into a structured whole to generate a logically complete initial itinerary planning result that meets the user's basic needs.

[0130] Step 603: Obtain dynamic environmental data of the itinerary, verify and adjust the initial itinerary planning results, and obtain the target itinerary planning results.

[0131] During implementation, the server pulls real-time dynamic environmental data from external data sources, including real-time traffic conditions, regional weather information, venue crowd load, temporary control notices, and the temporary opening and closing status of attractions. The server matches and verifies the dynamic environmental data with the initial itinerary planning results item by item, identifying unreasonable content such as route congestion, time period conflicts, and environmental incompatibility. It then makes targeted adjustments to the order of location visits, travel plans, dwell time, or replaces alternative locations to optimize and correct the initial itinerary content, ultimately generating a target itinerary planning result that adapts to the real-time environment and meets user constraints.

[0132] In this embodiment, the target itinerary planning result is generated by combining multi-dimensional static attribute data with real-time dynamic data, which effectively avoids the limitations of single-condition planning. The itinerary arrangement takes into account rationality, feasibility and real-time performance. It not only fully meets the personalized travel restrictions and preferences of the target users, but also adapts to the real-time changes in the external environment, greatly improving the practicality, adaptability and reference value of the itinerary planning result.

[0133] In one exemplary embodiment, such as Figure 7 As shown, the method also includes:

[0134] Step 701: Obtain map data.

[0135] In implementation, the server retrieves regional map data matching the target user's current location from a geospatial data resource library. This map data includes core information such as geographic latitude and longitude coordinates, road network distribution, business districts and administrative boundaries, and the geographic location and attribute classification of various POIs. Simultaneously, the server dynamically clips and adapts the map data to the target user's location recommendation needs, either acquiring full-area map data to support cross-regional recommendations or focusing on local map data around the user's current location to improve processing efficiency. This ensures that the acquired map data matches the scope and accuracy requirements of subsequent gridding, providing complete and accurate geospatial data support for the generation of grid maps.

[0136] Step 702: Divide the map data into layers based on a preset spatial indexing algorithm to generate a grid map.

[0137] Among them, the grid map is used to mark historical trajectory paths.

[0138] In implementation, the server uses the H3 hexagonal spatial indexing algorithm as the preset spatial indexing algorithm. For the acquired map data, it performs multi-level hexagonal grid division according to the latitude and longitude range of the geographic space. The specific grid division level can be flexibly adjusted according to the trajectory matching accuracy and location recommendation granularity. The higher the level, the finer the geographic granularity of the grid, and the higher the accuracy of the corresponding trajectory overlap calculation and location recommendation. Through this algorithm, continuous geographic space is discretized into regular and non-overlapping hexagonal grid units, and a unique spatial index identifier is assigned to each grid unit. At the same time, various POIs, geographic boundaries and other information in the map data are accurately mapped to the corresponding grid units. Finally, a hexagonal grid map that matches the target user's current location and can support trajectory path overlap calculation and visualization is generated.

[0139] In this embodiment, by first acquiring map data that matches the target user's current location, and then generating a grid map by hierarchically dividing the map data based on a preset spatial indexing algorithm, a standardized and structured geospatial carrier can be provided for subsequent trajectory overlap index calculation. The hierarchical division can flexibly adapt to trajectory matching and location recommendation requirements of different precisions. At the same time, the spatial indexing algorithm can divide the geographic space evenly and without overlap, effectively improving the accuracy and consistency of historical trajectory path mapping.

[0140] In one exemplary embodiment, such as Figure 8 As shown, the method also includes:

[0141] Step 802: Obtain the historical trajectory information of the target user and each associated user in the target associated user group.

[0142] The historical trajectory information includes the historical trajectory paths formed by the target user and each associated user at each stop point within a historical time period.

[0143] In implementation, with the authorization of each user, the server retrieves the latitude and longitude coordinates of the target user and each associated user in the target user group within a preset historical time period. Subsequently, the server aggregates the collected original latitude and longitude coordinates of the target user and each associated user in the target user group, extracts the stop locations of the target user and each associated user in each geographical area, and strings these stop locations together in chronological order to form a complete trajectory path, thereby obtaining the historical trajectory information corresponding to the target user and each associated user. At the same time, during the acquisition process, all historical trajectory information is subjected to geofencing desensitization processing, blurring the specific latitude and longitude and arrival time information, and retaining only the regional location information at the street and business district level. While obtaining valid trajectory data, the server also ensures the security protection of each user's location privacy.

[0144] Step 804: Based on the preset spatial gridding algorithm and historical trajectory information, the trajectory paths of the target user and each associated user are fused in the grid map.

[0145] The grid map displays the trajectory paths of the target user and its associated users within a historical time period.

[0146] In implementation, the server relies on a pre-generated grid map to geospatially map the anonymized historical trajectory information of the target user and the historical trajectory information of each associated user, accurately matching the stop locations and trajectory paths of both to the corresponding hexagonal grid cells. Subsequently, through trajectory fusion technology, the trajectory paths of the target user and each associated user are overlaid and displayed on the same grid map. The trajectory paths of the target user and each associated user are differentiated and marked on the grid map, clearly showing the trajectory direction and stop grid areas of each user within the historical time period. At the same time, it can intuitively show the intersection and difference areas of different user trajectory paths in the grid map, providing intuitive geospatial support for subsequent trajectory overlap index calculation and visualization.

[0147] In this embodiment, by combining the historical trajectory information of the target user and each associated user with the H3 spatial gridding algorithm to merge and mark the trajectory paths of multiple users in the same grid map, it is possible to achieve standardized spatial mapping and visualization fusion of the historical trajectories of multiple users while ensuring the privacy and security of user locations. This allows the trajectory relationship between the target user and each associated user to be presented intuitively in the grid map, effectively improving the user's perception efficiency of trajectory relationship.

[0148] In one exemplary embodiment, such as Figure 9 As shown, to ensure the security of user information, an authorization request needs to be sent to the target user before collecting the target user's historical trajectory information. Only after obtaining the user's authorization can the subsequent historical trajectory information acquisition operation be performed. Thus, the specific processing procedure for obtaining the target user's historical trajectory information in step 802 includes the following steps:

[0149] Step 901: Obtain the authorization information of the target user, and periodically collect the stop location nodes of the target user within a historical time period based on the authorization information.

[0150] In implementation, the server first displays an authorization request for location information collection to the target user through the terminal, clarifying the scope, period, purpose, and privacy protection measures for collection. After obtaining the target user's explicit authorization information, the server collects the target user's geographical location data within a historical time period through the terminal according to a preset collection period (e.g., it can be flexibly set by hour, day, week, etc.). At the same time, the server filters and aggregates the raw collected data, removes invalid and abnormal location points, and extracts the stop location nodes (latitude and longitude coordinate data) where the target user has stopped in various geographical areas.

[0151] Step 902: Integrate the nodes at each stop in chronological order to obtain the historical trajectory information of the target user.

[0152] In implementation, the server calibrates and sorts all the collected and filtered stopover location nodes in terms of time dimension. It then connects and integrates all the stopover location nodes in the order of the target user's arrival at each stopover location node. At the same time, it performs geofencing desensitization processing on the integrated location nodes, and uses feature area information such as streets and business districts to blur the specific latitude and longitude of the actual nodes, hiding the specific time information of the user's arrival at each node, thereby achieving privacy filtering of user trajectory data. Finally, it forms the target user's historical trajectory information composed of desensitized stopover location nodes in chronological order. This historical trajectory information of the target user can be directly used for subsequent trajectory mapping and overlap analysis.

[0153] In this embodiment, under the premise of strictly following the user authorization agreement, original user trajectory data with practical reference value is collected. At the same time, the privacy protection mechanism of geofencing desensitization can hide sensitive location and time details while integrating and generating historical trajectory information, effectively protecting the location privacy and security of the target user.

[0154] In one exemplary embodiment, such as Figure 10 As shown, the specific processing steps of step 902 include:

[0155] Step 1001: Perform geofencing desensitization processing on each stop location node to hide the latitude, longitude and time information corresponding to each stop location node.

[0156] In implementation, the server uses geofencing technology to perform privacy desensitization processing on each stop location node of the target user. The precise latitude and longitude coordinates of the nodes are no longer retained. Instead, they are blurred and mapped to regional geographical areas such as streets, business districts, and administrative areas, retaining only the regional location information with trajectory reference value. At the same time, the actual arrival and stay time information corresponding to each node is hidden. The specific time point or duration details are no longer recorded. Only the time sequence logic between nodes is retained. This desensitization method achieves privacy filtering of sensitive location and time data of users, which not only avoids the leakage of precise information, but also ensures the integrity of trajectory information and the usability of subsequent analysis, and follows the privacy protection agreement authorized by the user throughout the process.

[0157] Step 1002: Integrate the desensitized stop locations in chronological order to obtain the target user's historical trajectory information.

[0158] In implementation, the server calibrates and integrates all stopover location nodes after geofencing and desensitization according to their original time sequence. Following the user's actual travel trajectory, the stopover location nodes at each region level are sequentially connected to form a complete and continuous trajectory path. At the same time, a unique user identifier and time period label are added to the integrated trajectory path to complete the structured storage of trajectory information. The final result is the target user's historical trajectory information, which combines privacy and security, temporal integrity, and structured features. This historical trajectory information can be directly used for subsequent operations such as trajectory mapping in the grid map, trajectory fusion with related users, and overlap index calculation.

[0159] In this embodiment, by geofencing the stopover location nodes to desensitize them and hide sensitive latitude and longitude coordinates and time information, and then integrating the desensitized nodes in chronological order to generate historical trajectory information, it is possible to not only ensure the location and time privacy of the target user and meet data compliance requirements, but also retain the temporal logic and regional location characteristics of the trajectory information, providing a standardized and secure trajectory data foundation for subsequent trajectory fusion and overlap analysis.

[0160] In one exemplary embodiment, such as Figure 11 As shown, the specific processing procedure of step 301 includes steps 1101 to 1102, wherein:

[0161] Step 1101: Determine the grid area corresponding to the historical trajectory information of the target user and each associated user in the target associated user group.

[0162] In implementation, the server retrieves the historical trajectory information of the target user that has undergone geofencing desensitization processing, as well as the historical trajectory information of each associated user in the target associated user group. Based on the pre-generated grid map, the stop locations on the historical trajectory paths of the target user and each associated user are precisely mapped to the corresponding hexagonal grid cells one by one. Through spatial matching of trajectory paths, all grid areas covered by the historical trajectory of the target user and all grid areas covered by the historical trajectory of each associated user are determined. At the same time, the server marks the index identifier and coverage of the grid area corresponding to the trajectory of each user, forming a precise correspondence between user trajectory and grid area.

[0163] Step 1102: Count the number and area of ​​overlap between the target user and the grid regions corresponding to the historical trajectory paths of each associated user, and calculate the overlap index with each associated user based on the number and area of ​​overlap.

[0164] In implementation, the server spatially compares the target user's trajectory grid area with the trajectory grid areas of each associated user, counting the number of overlapping grids (i.e., the number of hexagonal grid cells jointly covered) and the overlapping area (i.e., the sum of the geographical areas of all overlapping grid cells). Then, using a pre-defined calculation model, the number and area of ​​overlap are used as core quantitative indicators, while incorporating the social trust weight (STW) between the target user and each associated user. Through a weighted calculation method, the trajectory overlap index corresponding to the target user and each associated user is calculated. The social trust weight between users can be dynamically adjusted based on social interaction indicators such as the frequency of private messages and the number of likes and interactions. In this way, the calculated overlap index takes into account both the actual degree of overlap at the geographical trajectory level and the trust correlation at the social relationship level, allowing the final overlap index to more accurately reflect the compatibility and reference value of the users' travel preferences.

[0165] The specific calculation model for the overlap index is shown in the following formula:

[0166] Overlap Index = (Number of grids in locations visited by both the associated user and the target user) / (Total number of grids visited by the target user) * Social Trust Weight.

[0167] In this embodiment, by accurately matching the grid areas corresponding to the historical trajectories of the target user and the target associated user group, the number and area of ​​overlapping trajectory grids are quantitatively counted and the overlap index is calculated by integrating social trust weights. This provides a quantifiable indicator for the similarity of user trajectory preferences and breaks through the limitations of simple geographical trajectory matching. The overlap index is made to better reflect the user's real social circle preferences and travel reference needs, providing a scientific quantitative basis for subsequent screening of target associated users and optimization of location recommendation weight ranking, effectively improving the personalization and accuracy of location recommendations.

[0168] In one exemplary embodiment, such as Figure 12 As shown, the method also includes:

[0169] Step 1201: Display the trajectory display page containing a grid map.

[0170] The grid map includes heat grids generated based on the target user's historical trajectory information.

[0171] In implementation, the terminal displays a trajectory display page with a hexagonal grid map to the target user. The grid map presented on the trajectory display page is generated based on the H3 algorithm hierarchical division, and the target user's historical trajectory information has been mapped to the corresponding grid cells. Furthermore, heat grids are generated and marked according to the dwell frequency and coverage duration of each grid mapped from the target user's historical trajectory information. Different visual depths are used to distinguish the trajectory heat, intuitively presenting the grid areas where the target user frequently travels and stays. At the same time, the terminal's display page is equipped with interactive function entry points such as trajectory viewing and friend selection, providing an operation and display platform for subsequently overlaying friend trajectory heat grids.

[0172] Step 1202: In response to the selection operation of the target associated user, the heat grid corresponding to the historical trajectory information of the target associated user is overlaid and merged in the grid map.

[0173] In implementation, the terminal responds to the target user's clicks, checkmarks, or other selection operations on the trajectory display page regarding target-related users. It overlays and merges the heatmaps corresponding to the selected target-related users' historical trajectory information onto the same grid map. Differentiated visual identifiers distinguish the heatmaps of the target user and the target-related users, and special visual markings are used for overlapping grid areas, clearly presenting the intersection areas and unique high-frequency areas of both trajectories. This allows users to intuitively perceive the degree of alignment between their trajectory preferences and those of the target-related users. For example... Figure 13As shown, in response to the target user's click or checkmark selection of the target associated user at the bottom of the trajectory display page, the terminal overlays and merges the heatmap corresponding to the historical trajectory information of the selected target associated user into the same hexagonal grid map. Differentiated visual identifiers are used to distinguish different user trajectories; for example, the target user's own footprints are marked with a blue heatmap, while the selected friend's footprints are marked with a red heatmap. The overlapping grid areas of the two trajectories are highlighted in yellow for special visual marking, intuitively presenting the intersection area of ​​the two trajectories and their respective unique high-frequency dwell areas.

[0174] In this embodiment, by first displaying a grid map page with a heatmap of the target user's trajectory, and then responding to the selection operation of the target associated user, the heatmaps of the target user and the target associated user are overlaid and merged, realizing the visual fusion display of the historical trajectories between users. This transforms the abstract trajectory overlap index into an intuitive heatmap visual effect. At the same time, differentiated visual markers and special markings for overlapping areas allow users to quickly identify common preference areas with the target associated user and high-frequency areas unique to friends. This not only enhances the interactive experience and social stickiness of the product, but also provides users with an intuitive reference for travel decisions, further strengthening the practicality of personalized location recommendations.

[0175] In an exemplary embodiment, the method for obtaining the target associated user group matching the target user in step 301 includes, but is not limited to, the following two methods:

[0176] Method 1: Display a list of candidate associated user groups, and in response to the selection operation of the target associated user group in the list, obtain the target associated user group.

[0177] In implementation, the terminal displays a list of candidate associated user groups pre-built by the application and content recommendation platform in the interactive interface for trajectory analysis or location recommendation. Each candidate associated user group in the list consists of users who have social connections with the target user, such as default friend groups, travel enthusiast groups, mutual contact groups, etc. in the application or platform. This embodiment does not limit the specific composition of each candidate associated user group, and each associated user group is labeled with the corresponding user group name and core characteristics. In this way, the terminal responds in real time to the target user's click, selection or other selection operations on a candidate associated user group in the list, determines the candidate associated user group selected by the user as the target associated user group, and synchronizes the target associated user group information to the server, thus completing the acquisition of the target associated user group.

[0178] Method 2: Display a list of associations and generate a target associated user group based on the selected candidate users in response to a checkmark operation performed in the list of associations.

[0179] In implementation, the terminal displays a complete list of the target user's relationships on the interactive interface. This list includes all individual candidate users with social connections to the target user, and each user is accompanied by reference information such as trajectory similarity and social trust weight. For example, it can be presented as a communication list containing reference information such as trajectory similarity and social trust weight. Subsequently, the terminal responds to the target user's selection of one or more candidate users in this complete list of relationships, collects the user's selection results in real time, dynamically integrates all selected candidate users, and automatically generates a brand-new custom target associated user group. At the same time, the composition information of this custom user group is synchronized to the server to meet the user's personalized analysis and recommendation needs.

[0180] In this embodiment, by providing two different methods for obtaining target associated user groups, users can quickly select pre-existing target associated user groups, improving operational efficiency. Alternatively, users can select individual associated users to generate new, custom target associated user groups based on their own needs, fully satisfying personalized trajectory analysis and location recommendation requirements. Both methods are based on the user's existing social relationship chain stored on the platform, closely aligning with the user's actual social connections. This allows subsequent trajectory overlap calculations and location recommendations based on target associated user groups to better match the user's social circle preferences, further improving the accuracy and practicality of the recommendation results.

[0181] In one exemplary embodiment, such as Figure 14 As shown, the method also includes:

[0182] Step 1401: In response to the query operation on the target associated user group, display the overlap index information of each associated user in the target associated user group on the list display page.

[0183] In implementation, the terminal responds to data query operations initiated by the target user in the trajectory analysis and location recommendation interactive interface for the selected target associated user group. It retrieves the calculated trajectory overlap index data between each associated user in the target associated user group and the target user from the server, and displays the basic information of each associated user and the corresponding overlap index information in a structured format on the terminal's list display page. For example... Figure 15 As shown, Figure 15 The display shows the overlap index data of three related users. Optionally, in addition to user nicknames, social relationship tags, overlap index information, and other specific data, the basic information of each related user on the list display page can also be accompanied by a visual index progress bar, sorting indicators, etc. It also supports sorting the list by overlap index from high to low or from low to high, allowing target users to intuitively and clearly see the degree of fit between the trajectory preferences of each related user in the group and themselves.

[0184] In this embodiment, by responding to the query operation of the target associated user group and displaying the overlap index information of each associated user in the list, the quantified trajectory matching data can be presented to the user in an intuitive list format. This allows the user to clearly understand the similarity of the trajectory preferences of each associated user in the group to their own, providing a clear data reference for the user to further filter high-value target associated users and adjust personalized recommendation strategies. At the same time, the structured list display and sorting function improves the efficiency of users viewing and filtering data, making personalized recommendations based on social relationships and trajectory overlap more interactive and transparent, further optimizing the user's operating experience and decision-making efficiency.

[0185] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0186] Based on the same inventive concept, this application also provides a location recommendation apparatus for implementing the location recommendation method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more location recommendation apparatus embodiments provided below can be found in the limitations of the location recommendation method described above, and will not be repeated here.

[0187] In one exemplary embodiment, such as Figure 16 As shown, a location recommendation device 1600 is provided, including: a first determining module 1601, a second determining module 1602, a filtering module 1603, and a generating module 1604, wherein:

[0188] The first determining module 1601 is used to determine candidate recommended locations based on the target user's current location and user characteristic information;

[0189] The second determining module 1602 is used to determine the target associated user based on the overlap index between the target user's historical trajectory path and the historical trajectory paths of each associated user in the target associated user group.

[0190] The filtering module 1603 is used to filter and obtain recommended locations for the target from the historical trajectory paths of the target associated users;

[0191] The generation module 1604 is used to perform itinerary planning based on the target recommended location and obtain the target itinerary planning result.

[0192] In one exemplary embodiment, the second determining module 1602 is specifically used to obtain the target associated user group that matches the target user, and calculate the overlap index of the historical trajectory path of each associated user in the target associated user group and the target user on a preset grid map.

[0193] Based on the overlap index, target associated users are identified in the target associated user group.

[0194] In one exemplary embodiment, the second determining module 1602 is specifically used to compare the overlap index of each associated user with the target user, and filter out the associated users whose overlap index reaches a preset threshold as the target associated users.

[0195] In one exemplary embodiment, the filtering module 1603 is specifically used to obtain information on each stop location contained in the historical trajectory path of the target associated user;

[0196] Based on the frequency of occurrence of each stop location, the degree of overlap with candidate recommended locations, and the degree of matching with the user characteristic information of the target user, corresponding weight coefficients are assigned to the candidate recommended locations.

[0197] The candidate recommended locations are reordered according to their weight coefficients from high to low, and a preset number of target recommended locations are obtained.

[0198] In one exemplary embodiment, the generation module 1604 is specifically used to obtain the attribute information of each target recommended location and the travel constraints of the target user;

[0199] Based on the attribute information of each target recommended location and combined with the travel constraints, the target recommended locations are arranged in time sequence to generate the initial travel planning results;

[0200] Acquire dynamic environmental data of the trip, verify and adjust the initial trip planning results, and obtain the target trip planning results.

[0201] In one exemplary embodiment, the location recommendation device 1600 further includes:

[0202] The first acquisition module is used to acquire map data;

[0203] The generation module is used to divide map data into layers based on a preset spatial indexing algorithm and generate a grid map; the grid map is used to mark historical trajectory paths.

[0204] In one exemplary embodiment, the location recommendation device 1600 further includes:

[0205] The second acquisition module is used to acquire the historical trajectory information of the target user and each associated user in the target associated user group; the historical trajectory information includes the historical trajectory path formed by the target user and each associated user at each stop location node within a historical time period;

[0206] The trajectory fusion module is used to merge the trajectory paths of the target user and each associated user in the grid map based on the preset spatial gridding algorithm and historical trajectory information.

[0207] The grid map displays the trajectory paths of the target user and its associated users within a historical time period.

[0208] In one exemplary embodiment, the second acquisition module is specifically used to acquire the authorization information of the target user and periodically collect the stop location nodes of the target user within a historical time period based on the authorization information;

[0209] By integrating the various stop locations in chronological order, the historical trajectory information of the target user can be obtained.

[0210] In one exemplary embodiment, the second acquisition module is specifically used to perform geofencing desensitization processing on each stop location node, hiding the latitude and longitude information and time information corresponding to each stop location node;

[0211] By integrating the anonymized stop locations in chronological order, the historical trajectory information of the target user is obtained.

[0212] In one exemplary embodiment, the second acquisition module is specifically used to determine the grid area corresponding to the historical trajectory information of the target user and each associated user in the target associated user group;

[0213] The number and area of ​​overlap between the target user and the grid regions corresponding to the historical trajectory paths of each associated user are counted, and the overlap index with each associated user is calculated based on the number and area of ​​overlap.

[0214] In one exemplary embodiment, the location recommendation device 1600 further includes:

[0215] The first display module is used to display a trajectory display page containing a grid map, in which heat grids generated based on the target user's historical trajectory information are marked;

[0216] The second display module is used to overlay and merge the heat grid corresponding to the historical trajectory information of the target associated user in the grid map in response to the selection operation of the target associated user.

[0217] In one exemplary embodiment, the second determining module 1602 is specifically configured to display a list of candidate associated user groups, and in response to a selection operation on a target associated user group in the list, obtain the target associated user group; or...

[0218] Display a list of associations and generate a target associated user group based on the selected candidate users in response to a checkmark operation performed in the list of associations.

[0219] In one exemplary embodiment, the location recommendation device 1600 further includes:

[0220] The list display module is used to respond to query operations on the target associated user group and display the overlap index information of each associated user in the target associated user group on the list display page.

[0221] The modules in the aforementioned location recommendation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0222] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 17 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores historical trajectory information of target users and associated users, grid map data, trajectory overlap index data, social trust weight data, candidate and target recommended location data, user characteristic information, and social relationship chain data. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a location recommendation method.

[0223] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 18As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When executed by the processor, the computer program implements a location recommendation method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0224] Those skilled in the art will understand that Figure 18 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0225] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0226] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0227] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0228] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0229] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0230] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0231] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A location recommendation method, characterized in that, The method includes: Based on the target user's current location and user characteristics, candidate recommended locations are determined; The target associated user is determined based on the overlap index between the historical trajectory path of the target user and the historical trajectory paths of each associated user in the target associated user group; Target recommended locations are obtained by filtering from the historical trajectory paths of the target associated users; Based on the target recommended location, a trip plan is performed to obtain the target trip plan result.

2. The method according to claim 1, characterized in that, The step of determining the target associated user based on the overlap index between the target user's historical trajectory path and the historical trajectory paths of each associated user in the target associated user group includes: Obtain a target associated user group that matches the target user, and calculate the overlap index of the historical trajectory paths of each associated user in the target associated user group and the target user on a preset grid map; Based on the overlap index, target associated users are identified in the target associated user group.

3. The location recommendation method according to claim 1, characterized in that, The step of determining the target associated user in the target associated user group based on the overlap index includes: By comparing the overlap index of each associated user with the target user, associated users whose overlap index reaches a preset threshold are selected as target associated users.

4. The location recommendation method according to claim 1, characterized in that, The step of filtering out target recommended locations from the historical trajectory paths of the target associated user includes: Obtain information on each stop location included in the historical trajectory path of the target associated user; Based on the frequency of occurrence of each of the aforementioned locations, the degree of overlap with the candidate recommended locations, and the degree of matching with the user characteristic information of the target user, corresponding weight coefficients are assigned to the candidate recommended locations. The candidate recommended locations are reordered according to their weight coefficients from high to low to obtain a preset number of target recommended locations.

5. The method according to claim 1, characterized in that, The process of planning the itinerary based on the target recommended location to obtain the target itinerary planning result includes: Obtain the attribute information of each of the target recommended locations and the travel constraints of the target user; Based on the attribute information of each of the target recommended locations and combined with the travel constraints, the target recommended locations are arranged in a time sequence to generate an initial travel planning result; The dynamic environment data of the trip is obtained, and the initial trip planning result is verified and adjusted to obtain the target trip planning result.

6. The location recommendation method according to claim 1, characterized in that, The method further includes: Obtain map data; The map data is hierarchically divided based on a preset spatial indexing algorithm to generate a grid map; the grid map is used to mark historical trajectory paths.

7. The location recommendation method according to claim 6, characterized in that, The method further includes: Obtain the historical trajectory information of the target user and each associated user in the target associated user group; the historical trajectory information includes the historical trajectory path formed by the target user and each associated user at each stop location node within a historical time period; Based on a preset spatial gridding algorithm and the historical trajectory information, the trajectory paths of the target user and the associated users are fused in the grid map. The grid map displays the trajectory paths of the target user and each of the associated users within the historical time period.

8. The location recommendation method according to claim 7, characterized in that, The step of obtaining the target user's historical trajectory information includes: Obtain the authorization information of the target user, and periodically collect the stop location nodes of the target user within a historical time period based on the authorization information; By integrating the aforementioned stop locations in chronological order, the historical trajectory information of the target user is obtained.

9. The location recommendation method according to claim 8, characterized in that, The step of integrating the various stop locations in chronological order to obtain the target user's historical trajectory information includes: Geofencing and desensitization processing is performed on each of the aforementioned stop locations to hide the latitude, longitude, and time information corresponding to each of the aforementioned stop locations. The anonymized stop locations are integrated in chronological order to obtain the target user's historical trajectory information.

10. The location recommendation method according to claim 2, characterized in that, The calculation of the overlap index of the historical trajectory paths of each associated user in the target associated user group and the target user on a preset grid map includes: Determine the grid area corresponding to the historical trajectory information of the target user and each associated user in the target associated user group; The number and area of ​​overlap between the target user and the grid regions corresponding to the historical trajectory paths of each associated user are counted, and the overlap index with each associated user is calculated based on the number and area of ​​overlap.

11. The location recommendation method according to claim 6 or 7, characterized in that, The method further includes: A trajectory display page is shown, which includes a grid map marked with heat grids generated based on the target user's historical trajectory information; In response to the selection operation of the target associated user, a heat grid corresponding to the historical trajectory information of the target associated user is overlaid and merged in the grid map.

12. The location recommendation method according to claim 2, characterized in that, The step of obtaining the target associated user group that matches the target user includes: Display a list of candidate associated user groups, and in response to a selection operation on a target associated user group in the list, retrieve the target associated user group; or... Display a list of associations, and in response to a checkmark operation performed in the list of associations, generate a target associated user group based on each checked candidate user.

13. The location recommendation method according to claim 2, characterized in that, The method further includes: In response to a query operation on the target associated user group, the overlap index information corresponding to each associated user in the target associated user group is displayed on the list display page.

14. A location recommendation device, characterized in that, The device includes: The first determination module is used to determine candidate recommended locations based on the target user's current location and user characteristic information; The second determining module is used to determine the target associated user based on the overlap index between the historical trajectory path of the target user and the historical trajectory paths of each associated user in the target associated user group. The filtering module is used to filter and obtain target recommended locations from the historical trajectory paths of the target associated users; The generation module is used to perform itinerary planning based on the target recommended location and obtain the target itinerary planning result.

15. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 13.

Images