Cross-instant messaging platform accurate user linking method and system for resisting position error

Abstract

The invention relates to the technical field of big data processing, in particular to a cross-instant messaging platform accurate user linking method and system for resisting position errors, and the method comprises the steps: carrying out the grid transformation processing of cross-instant messaging platform user data, and obtaining a user grid track and a motion state track; obtaining a motion state distance between the target platform user track and the to-be-linked platform user track under the control of the time window, and obtaining a candidate track corresponding to the target platform user track according to the motion state distance; clustering the position points on the user track to obtain a cluster center distance between the user track of the target platform and the candidate track; and weighting the cluster center distance between the tracks according to a track similarity weight model, and calculating the similarity between the target platform user track and the candidate track, thereby obtaining a matching track of the target platform user track, and realizing cross-instant messaging platform user link. According to the method, the user characteristics can be accurately extracted under the condition that the position data has errors, so that the user link has higher accuracy.

Description

Technical Field

[0001] The present invention relates to the field of big data processing technology, and in particular to a method and system for accurately linking users across instant messaging platforms for combating location errors. Background Art

[0002] As a popular location-based social network (LBSN) today, instant messaging provides location-based social discovery services (LBSD), such as the "nearby people" function in WeChat and Momo, which enables users to obtain the identity and location information of other users near their current location, generating massive mobile location data. Cross-instant messaging platform user linking refers to linking accounts belonging to the same user on different instant messaging platforms. Since the registered accounts on different instant messaging platforms are independent of each other, linking a person's user information and behavior on different platforms helps to identify the user's multiple social identities and more accurately portray the user's portrait through data fusion. Linking cross-platform instant messaging users through user mobile trajectories has important application value in real-time trajectory supplementation, collaborative digital tracking, and trajectory prediction.

[0003] Existing cross-platform user linking methods are mainly divided into three categories: based on user attributes, network relationships, and location. The method based on user attributes links users by measuring the similarity of attribute information such as user names, birthdays, and hobbies. For example, cross-platform user association is achieved based on mobile phone numbers. Since the accuracy of attribute data registered by users cannot be guaranteed, and with the upgrade of privacy protection, most social networks restrict access to user attribute information, which limits the methods based on user attributes. The method based on network relationships mainly associates users from the friend relationship and network structure of social networks. For example, the latent semantics of the network structure is learned in an end-to-end manner, and the structural information of the anchor nodes is encoded by predicting the neighboring structure of the nodes in the network to align the network, or the cross-platform users are aligned through the social structure of the network. This type of method often requires learning potential knowledge from a large amount of prior data, and the data is difficult to obtain and the noise is large. The location-based method generally uses the similarity of user location factors to link cross-platform users, such as the k-BCT method based on the shortest distance to measure trajectory similarity and the user similarity measurement method based on stimulus signals. In order to accurately describe the movement characteristics of users under sparse data, the space can be divided into grids, and the kernel density estimation method based on entropy is used to evaluate the similarity of users. However, these methods often focus on locations such as the shortest distance or co-occurrence, ignoring the role of other locations. The grid distance method also ignores the actual distribution of user locations.

[0004] In summary, the existing research methods can solve the problem of cross-platform user links well under certain conditions, but they are still insufficient in dealing with inaccurate data information. The existing location-based methods mainly rely on the comparison and statistical results between locations. Unlike the trajectory composed of accurate locations, the location data in the trajectory of instant messaging users usually has random errors, and the number of location points cannot fully reflect the user's real movement state, resulting in the comparison and statistical results of location data cannot accurately reflect the relationship between real locations. As a result, the above methods are prone to misjudgment when solving cross-instant messaging platform user links, especially in dealing with high overlap of activity spaces, thereby reducing the accuracy of user links, and then there are problems such as low accuracy when solving cross-instant messaging platform user links. Summary of the invention

[0005] To this end, the present invention provides a method and system for accurately linking users across instant messaging platforms for combating location errors, which solves the problems of errors in existing location data based on instant messaging user trajectories and low accuracy of cross-platform user links.

[0006] According to the design scheme provided by the present invention, on the one hand, a method for accurately linking users across instant messaging platforms for combating location errors is provided, comprising:

[0007] Acquire cross-instant messaging platform user data in a specified area, wherein the cross-instant messaging platform user data includes user sets and user trajectory sets in both a target platform and a platform to be linked; and perform grid transformation processing on the cross-instant messaging platform user data to obtain grid trajectories and motion state trajectories of users in each user set;

[0008] Under the time window control, the motion state distance between the target platform user trajectory and the to-be-linked platform user trajectory is obtained, so as to obtain a candidate trajectory corresponding to the target platform user trajectory according to the motion state distance;

[0009] Clustering the location points on the user trajectory according to the time window to obtain the cluster center distance between the target platform user trajectory and the candidate trajectory, wherein the time window adopts a rolling time window with adjustable step size;

[0010] The cluster center distances between trajectories are weighted according to the trajectory similarity weight model to obtain the similarity between the target platform user trajectory and other candidate trajectories. The trajectory similarity weight model is constructed using grid contribution and motion sequence similarity. The grid contribution is used to characterize the amount of user trajectory feature information in each grid in the grid trajectory and is obtained using grid trajectory entropy. The motion sequence similarity is obtained based on the motion state trajectory sequence and combined with the spatiotemporal co-occurrence between trajectories.

[0011] According to the similarity between the target platform user trajectory and other candidate trajectories, the candidate trajectory with the maximum similarity between trajectories is selected as the matching trajectory of the target platform user trajectory, and the cross-instant messaging platform users corresponding to the trajectory are linked.

[0012] As the cross-instant messaging platform accurate user linking method for combating position error of the present invention, further, grid transformation processing is performed on the cross-instant messaging platform user data, including:

[0013] Setting the spatiotemporal granularity for describing the size of the spatiotemporal grid, wherein the spatiotemporal granularity includes the side length of the grid area and the width of the time window;

[0014] Divide the specified area into grids and obtain the grid numbers corresponding to each position point on the user's trajectory;

[0015] Sort the grids according to the time sequence to generate grid tracks;

[0016] Slide the time window and traverse the grid trajectory, record the number of grid changes of the user trajectory in each time window, and combine the motion state in the previous time window to determine the motion state of the trajectory in the current time window to generate the motion state trajectory.

[0017] As a cross-platform precise user linking method for combating position error of the present invention, further, obtaining the motion state distance between the target platform user trajectory and the to-be-linked platform user trajectory under time window control includes:

[0018] Compare the trajectory of each target user in the target platform with the trajectory of the user in the platform to be linked, and obtain the trajectory motion state distance between the trajectory of each target user in the target platform and the trajectory of the user in the platform to be linked;

[0019] Obtaining a trajectory filtering score based on the trajectory motion state distance and the set and number of position co-occurrence time windows in the trajectory, wherein the trajectory filtering score is used to describe the mean difference in motion state of the trajectory to be compared and matched during the spatiotemporal co-occurrence of the position points;

[0020] According to the trajectory filtering score, the user trajectories in the platform to be linked that do not match the target user trajectory are deleted to obtain the candidate trajectories corresponding to the target user trajectories of the target platform.

[0021] As the cross-instant messaging platform accurate user linking method for combating location errors of the present invention, further, the location points on the user trajectory are clustered according to the time window, including:

[0022] Constructing a perception time window with a dynamically adjustable step size, and determining the time window width according to the distribution of the perception position data, wherein the time window width includes the time granularity of the spatiotemporal grid and the rolling step size;

[0023] The rolling step of the time window is dynamically adjusted according to the time interval between the trajectory segments of the target platform user trajectory, and the cluster center distance between the location points between the target platform user trajectory and the to-be-linked platform user trajectory in the corresponding time window is obtained.

[0024] As a cross-instant messaging platform accurate user linking method for combating location errors of the present invention, further, weighting the cluster center distances between trajectories according to a trajectory similarity weight model is performed to obtain the similarity between the target platform user trajectory and other candidate trajectories, including:

[0025] Obtain the basic similarity between the target platform user trajectory and the to-be-linked platform user trajectory based on the cluster center distance between the trajectories;

[0026] The trajectory entropy is obtained based on the number of grid cells contained in the grid trajectory and the number of location points where the user trajectory falls into each grid, and the contribution of the grid in the grid trajectory is obtained based on the trajectory entropy;

[0027] According to the motion state trajectory and combined with the spatiotemporal co-occurrence of the trajectories between the target platform and the platform to be linked, the motion sequence similarity between the target platform user trajectory and the platform to be linked user trajectory is obtained;

[0028] The similarity between the user trajectory of the target platform and the user trajectory of the platform to be linked is obtained based on basic similarity, grid contribution and motion sequence similarity.

[0029] As the cross-instant messaging platform accurate user linking method for combating position error of the present invention, further, the similarity calculation formula between trajectories is expressed as: Among them, T A , T B are the target platform user trajectory and the to-be-linked platform user trajectory, μ is the adjustment parameter used to reduce the distance value, D dist (T A ,T B ) represents the distance between trajectories, W A ∩W B is the set of time windows where positions co-occur in two trajectories, f num (·) is a function that controls the influence of the number of spatiotemporal co-occurrences between two trajectories on the similarity calculation, M sim (T A ,T B ) is the function for calculating the similarity of motion sequences between trajectories.

[0030] As the cross-instant messaging platform accurate user linking method for combating position error of the present invention, further, selecting the candidate trajectory with the maximum similarity between trajectories as the matching trajectory of the target platform user trajectory includes:

[0031] The similarities between the trajectories of each user on the target platform and the candidate trajectories are sorted, and several user trajectories with the highest similarity rankings are selected from the candidate trajectories as the winning trajectories that match the corresponding user trajectories on the target platform.

[0032] On the other hand, the present invention also provides a cross-platform accurate user linking system for combating location errors, comprising: a cross-platform user data acquisition module, a candidate user trajectory acquisition module, a trajectory location point clustering module, a trajectory similarity calculation module and a cross-platform user linking module, wherein:

[0033] A cross-platform user data acquisition module is used to acquire cross-instant messaging platform user data in a specified area, wherein the cross-instant messaging platform user data includes user sets and user trajectory sets in both the target platform and the platform to be linked; and grid transformation processing is performed on the cross-instant messaging platform user data to obtain grid trajectories and motion state trajectories of users in each user set;

[0034] The candidate user trajectory acquisition module is used to obtain the motion state distance between the target platform user trajectory and the to-be-linked platform user trajectory under the time window control, so as to obtain the candidate trajectory corresponding to the target platform user trajectory according to the motion state distance;

[0035] The trajectory location point clustering module is used to cluster the location points on the user trajectory according to the time window, and obtain the cluster center distance between the user trajectory of the target platform and the candidate trajectory. The time window adopts a rolling time window with adjustable step size;

[0036] The trajectory similarity calculation module is used to weight the cluster center distances between trajectories according to the trajectory similarity weight model to obtain the similarity between the target platform user trajectory and other candidate trajectories. The trajectory similarity weight model is constructed using grid contribution and motion sequence similarity. The grid contribution is used to characterize the amount of user trajectory feature information in each grid in the grid trajectory and is obtained using grid trajectory entropy. The motion sequence similarity is obtained based on the motion state trajectory sequence and combined with the spatiotemporal co-occurrence between trajectories.

[0037] The cross-platform user linking module is used to select the candidate trajectory with the maximum similarity between trajectories as the matching trajectory of the target platform user trajectory based on the similarity between the target platform user trajectory and other candidate trajectories, and link the cross-instant messaging platform users corresponding to the trajectory.

[0038] Beneficial effects of the present invention:

[0039] 1. The present invention uses multi-granularity spatiotemporal grids to divide the target area, and by constructing a spatiotemporal weight model that includes grid contribution and motion sequence similarity, weights are assigned to the grid cells passed by the trajectory and the similarity of the temporal movement patterns between different trajectories. In the trajectory similarity calculation, the importance of different feature vectors is distinguished by weights, so that user features can be accurately extracted when there are errors in the position data, making the user link more accurate.

[0040] 2. The present invention extracts the coarse-grained motion state of the trajectory and filters the candidate trajectory set accordingly. In order to comprehensively evaluate the filtering effect, the existing hit rate index is improved and the filtering efficiency index is proposed. Further experiments show that the filtering method effectively reduces the number of candidate trajectories and improves the efficiency of the user link algorithm.

[0041] 3. The present invention takes into account that the number of location points appearing on the trajectory of instant messaging users is subject to subjective control by the user and cannot fully reflect the user's actual movement status. By using the spatiotemporal co-occurrence window control, the cluster center distance of the trajectory in the time window is weighted according to the weight model, so that the similarity calculation is related to the spatiotemporal co-occurrence window between the two trajectories, reducing the dependence on the number of location points, which is helpful to mine the implicit user location and movement characteristics under sparse data.

[0042] 4. The present invention extracts the position and temporal movement features in the trajectory, calculates the similarity between trajectories based on the grid contribution and the motion sequence similarity, and then completes the user link across instant messaging platforms. Experiments were conducted on public data sets and self-built data sets. The results show that the accuracy of this solution has obvious advantages. Compared with the existing typical location-based methods k-BCT, GS and TF-IWF, the accuracy of this solution Acc@1 increased by an average of 32.86%, 44.8% and 14.4%, and Acc@3 increased by an average of 30.52%, 34.67% and 13.19%, respectively, and can be applied to user links across instant messaging platforms. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 Schematic diagram of a precise user linking process across instant messaging platforms for combating location errors in an embodiment;

[0044] Figure 2 This is a schematic diagram of the principle framework of the cross-instant messaging platform precise user linking algorithm in the embodiment;

[0045] Figure 3 Schematic diagram of a perception time window with dynamically adjustable step size in an embodiment;

[0046] Figure 4 This is a schematic diagram of the effect of the subset size on the filtering effect in the embodiment;

[0047] Figure 5This is a schematic diagram of the effect of subset size on hit rate in the embodiment;

[0048] Figure 6 This is a schematic diagram of the effect of subset size on accuracy in the embodiment;

[0049] Figure 7 Schematic diagram of the comparison results of the user link experiment in the embodiment. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solutions and advantages of the present invention clearer and more understandable, the present invention is further described in detail below in conjunction with the accompanying drawings and technical solutions.

[0051] Cross-instant messaging platform user links can link the accounts of the same user in different instant messaging systems, which is of great significance for the identification of multiple social identities of users and cross-platform association analysis. In order to facilitate reading and understanding of this case plan, we first introduce the data characteristics of instant messaging user trajectories.

[0052] Unlike trajectories consisting of accurate locations, IM user trajectories consist of inferred locations with errors, which increases the difficulty of cross-platform user links. IM user trajectories are obtained by locating and tracking target users using positioning methods. Due to the scrambling of user locations by IM platforms, the positioning result is the user's inferred location, which has errors compared to the actual location, and the errors are random. For example, in the study of WeChat user positioning, about 56% of the positioning errors were within 60 meters, and the maximum error was about 112 meters. Due to the different scrambling strategies for locations on different IM platforms, even if the same positioning method is used, the positioning error range for users on different platforms is different. For example, for the positioning of WeChat and Momo users, the average errors are 56.6 meters and 15.3 meters, respectively. Therefore, IM user trajectories are only a rough reflection of user movements, and the trajectories obtained for the same user movement on different IM platforms have large deviations.

[0053] There is also a data sparsity problem in the trajectories of instant messaging users. Users decide when and how long they use the instant messaging LBSD service. In addition, the instant messaging platform does not always display all nearby users in the "nearby people" query list, and generally limits the number of queries users can make on nearby users, which makes the location data on the trajectory often have a large temporal and spatial span and uneven sparsity, thus causing data sparsity problems. Since the number of location points on the trajectory is subjectively controlled by the user, the number of location points sometimes cannot directly reflect the importance of the location to the user, and it is necessary to find hidden user location features.

[0054] Cross-platform user linking based on location information is a typical method in current research. Such methods often calculate user similarity based on the check-in location, but the location data of instant messaging user trajectories has errors, resulting in low accuracy of user linking in such methods. Figure 1 As shown, a method for accurately linking users across instant messaging platforms for combating location errors is provided, comprising:

[0055] S101, obtaining cross-instant messaging platform user data in a specified area, wherein the cross-instant messaging platform user data includes user sets and user trajectory sets in both the target platform and the platform to be linked; and performing grid transformation processing on the cross-instant messaging platform user data to obtain grid trajectories and motion state trajectories of users in each user set;

[0056] S102, obtaining the motion state distance between the target platform user trajectory and the to-be-linked platform user trajectory under the time window control, so as to obtain a candidate trajectory corresponding to the target platform user trajectory according to the motion state distance;

[0057] S103, clustering the location points on the user trajectory according to the time window to obtain the cluster center distance between the target platform user trajectory and the candidate trajectory, wherein the time window adopts a rolling time window with an adjustable step size;

[0058] S104, weighting the cluster center distances between trajectories according to a trajectory similarity weight model to obtain the similarity between the target platform user trajectory and other candidate trajectories, wherein the trajectory similarity weight model is constructed using grid contribution and motion sequence similarity, wherein the grid contribution is used to characterize the amount of user trajectory feature information in each grid in the grid trajectory and is obtained using grid trajectory entropy, and the motion sequence similarity is obtained based on the motion state trajectory sequence and in combination with the spatiotemporal co-occurrence between trajectories;

[0059] S105 , based on the similarity between the target platform user trajectory and other candidate trajectories, select the candidate trajectory with the maximum similarity between the trajectories as the matching trajectory of the target platform user trajectory, and link the cross-instant messaging platform users corresponding to the trajectory.

[0060] In view of the low accuracy of existing location-based methods in processing cross-platform instant messaging user links, an accurate user linkage method across instant messaging platforms resisting trajectory errors (UeLP) is proposed in the embodiments of this case. Figure 2As shown in the figure, under the control of the perception time window, based on the distance between the center of the position point clusters between the trajectories, the position area and temporal movement features of the trajectory are extracted by calculating the grid contribution and the motion sequence similarity, so that the spatial and temporal features of the trajectory are combined to calculate the trajectory similarity and finally complete the user link.

[0061] To facilitate reading and understanding of the above algorithm, some symbols used and the problems to be solved are described as follows.

[0062] Table 1 Symbols

[0063]

[0064] Instant messaging user trajectory T u :For each user u∈U, the instant messaging user trajectory is recorded as Position points on the track The grid cell g into which it falls m Instead, the trajectory T u Transformed into user grid trajectory, denoted as A grid track is a collection of spatiotemporal grids arranged in time order, representing the time at time stamp t i u , user u is located in grid cell g m Inside.

[0065] Trajectory time window set W u :The trajectory time window set represents the time window set of location data on the trajectory of user u. For each user u∈U, the trajectory time window set is recorded as Among them, f time (·) is to and Δt are converted into a function of time period h and time window number k. Among them, Δt is the time window width, which is determined by the sparsity of trajectory data and is 1, 5, 10 minutes in the experiment.

[0066] Location data of instant messaging user trajectories In order to accurately extract the movement mode of the trajectory in the presence of errors, a “coarse-grained motion state” is proposed in the embodiment of this case.

[0067] Coarse-grained motion state s: Coarse-grained motion states are divided into three categories: static, dynamic, and unclear, represented by 0, 1, and 2 respectively. The "static" state does not mean that the user remains motionless, but means that within a certain time interval, the user's movement amplitude is less than the range E, such as a grid area. That is, when the user is in the "static" state, he may be moving, but his current movement mode does not exceed the range E. Correspondingly, the "dynamic" state means that the user's movement amplitude exceeds the range E within the time interval Δt. When there is no position data on the trajectory within the time window Δt, the motion state is uncertain.

[0068] Time window motion state For each user u∈U, the time window motion state is represented as It means that the coarse-grained motion state of the trajectory of user u in the kth time window of the hth period is s.

[0069] Trajectory time window set W u :The trajectory time window set represents the time window set of location data on the trajectory of user u. For each user u∈U, the trajectory time window set is recorded as Among them, f time (·) is to and Δt are converted into a function of time period h and time window number k. Among them, Δt is the time window width, which is determined by the sparsity of trajectory data and is 1, 5, 10 minutes in the experiment.

[0070] Motion state trajectory Ψ u :For each user u∈U, the motion state trajectory is expressed as It is a collection of coarse-grained motion states of trajectories arranged in time sequence.

[0071] The problem to be solved can be described as: Given two user sets U of different instant messaging platforms A and U B , and the instant messaging user trajectory set D generated by users on these two platforms A and D B , in the cross-platform track collection

[0072] {(T A,i ,T B,j )|T A,i ∈D A ,T B,j ∈D B}, find all trace pairs belonging to the same user, and thus link the cross-platform user accounts belonging to the same user.

[0073] Figure 2 The algorithm steps shown can be summarized as follows:

[0074] Step 1: Data preprocessing. Preprocessing is to replace the position points in the original trajectory with the grid they fall into, generate a grid trajectory; pay attention to the grid changes, extract the motion state of the trajectory in the time window, and generate a motion state trajectory.

[0075] Step 2: Trajectory filtering. Based on the motion state trajectory, under the control of the time window, the coarse-grained motion state distance between the target trajectory and the candidate trajectory is calculated, and the candidate trajectory set is filtered according to the score, and the trajectories that are obviously mismatched are filtered out to generate the corresponding candidate trajectory subset.

[0076] Step 3: Distance calculation. In a time window with a dynamically adjustable step size, cluster the position points on the trajectory and calculate the cluster center distance between the target trajectory and the candidate trajectory.

[0077] Step 4: Calculation of spatiotemporal weights. Construct a spatiotemporal weight model for grid contribution and motion sequence similarity, and assign weights to the grid cells that the trajectory passes through and the similarity of the temporal movement patterns of two different trajectories. Based on the grid trajectory, calculate the contribution weight of the grid passed by the trajectory; based on the motion state trajectory, calculate the motion sequence similarity weight between the trajectories to be compared.

[0078] Step 5: User linking. The cluster center distances between trajectories are weighted according to the weight model to obtain the trajectory similarity. The maximum similarity result is selected as the matching trajectory, and the cross-platform user accounts corresponding to the two trajectories are linked.

[0079] Specifically, the grid transformation processing of user data across instant messaging platforms can be designed to include:

[0080] Setting the spatiotemporal granularity for describing the size of the spatiotemporal grid, wherein the spatiotemporal granularity includes the side length of the grid area and the width of the time window;

[0081] Divide the specified area into grids and obtain the grid numbers corresponding to each position point on the user's trajectory;

[0082] Sort the grids according to the time sequence to generate grid tracks;

[0083] Slide the time window and traverse the grid trajectory, record the number of grid changes of the user trajectory in each time window, and combine the motion state in the previous time window to determine the motion state of the trajectory in the current time window to generate the motion state trajectory.

[0084] The target area can be divided according to the multi-granularity spatiotemporal grid scheme, and then the location points on the original instant messaging user trajectory are transformed into a grid to generate a grid trajectory and a motion state trajectory. The preprocessing pseudo code is shown in Algorithm 1.

[0085]

[0086] First, a multi-granularity adaptable spatiotemporal grid solution is established. Since the location points on the IM user trajectory are inaccurate, in order to accurately describe the importance of the location area to the trajectory and the movement pattern of the trajectory, it is necessary to select the appropriate spatiotemporal granularity according to the geographic span of the trajectory, the frequency of data collection, and the processing steps of the algorithm, that is, to determine the size of the spatiotemporal grid, including the side length d of the grid area and the width Δt of the rolling time window. If the grid granularity is too small, the amount of information gathered in the location area will be insufficient; if the granularity is too large, the user characteristics per unit area will not be obvious.

[0087] Then, the map area is divided into grids (see line 1 of the algorithm). Next, for each position point on the trajectory, the grid number g in which it falls is calculated. m (5th row), arrange the grids in time sequence to generate the grid trajectory Φ u (Lines 4-10). Next, slide the time window, traverse the grid trajectory, record the number of grid changes in the trajectory in the current time window, and combine the motion state in the previous time window to determine the trajectory motion state in the current time window, and generate the motion state trajectory Ψ u (Lines 11-20).

[0088] Wherein, obtaining the motion state distance between the target platform user trajectory and the to-be-linked platform user trajectory under the time window control may include:

[0089] Compare the trajectory of each target user in the target platform with the trajectory of the user in the platform to be linked, and obtain the trajectory motion state distance between the trajectory of each target user in the target platform and the trajectory of the user in the platform to be linked;

[0090] Obtaining a trajectory filtering score based on the trajectory motion state distance and the set and number of position co-occurrence time windows in the trajectory, wherein the trajectory filtering score is used to describe the mean difference in motion state of the trajectory to be compared and matched during the spatiotemporal co-occurrence of the position points;

[0091] According to the trajectory filtering score, the user trajectories in the platform to be linked that do not match the target user trajectory are deleted to obtain the candidate trajectories corresponding to the target user trajectories of the target platform.

[0092] In the trajectory set D A and D B When you connect to a user in |D A |×|D B | comparison. To improve efficiency, D A Each trajectory T in A , filter out the candidate trajectory set D B The trajectories that are obviously mismatched in the , generate the candidate trajectory subset D ′ BThe main steps of filtering are summarized as follows:

[0093] Assume T A ∈D A is the target trajectory, which is compared with each T B ∈D B The motion state trajectory is compared with the motion state trajectory, and the distance of the motion state of the trajectory is calculated using formula (1):

[0094]

[0095] Here, the state distance calculation is allowed only when the state is clear, that is, 0 or 1. According to the motion state distance, the filtering score will be calculated using formula (2) to achieve a more accurate filtering effect.

[0096]

[0097] Among them, W A ∩W B It is the time window set where the location point data exist simultaneously in the two trajectories, which is called the location co-occurrence time window set. A ∩W B | represents the trajectory T A and T B The number of time windows of position co-occurrence between two trajectories reflects the number of spatiotemporal co-occurrences between two trajectories. The filtering score describes the mean difference in motion state between two trajectories during the period of spatiotemporal co-occurrence of positions. For example, trajectory T A , T B,1 and T B,2 After preprocessing by Algorithm 1, the corresponding motion state trajectory Ψ is obtained A , B,1 and B,2 , the motion state trajectory is shown in Table 2. Table 3 describes the trajectory T A The situation and calculation results of the position co-occurrence time window between the other two trajectories.

[0098] Table 2 Trajectory examples

[0099]

[0100] Table 3 Example of location co-occurrence time window

[0101]

[0102] According to the sample data in Table 2 and Table 3, the filtering scores of the two groups of trajectory pairs are calculated according to formula (2): Track T A and T B,1 The filter score is higher.

[0103] Among them, clustering the location points on the user trajectory according to the time window can be designed to include:

[0104] Constructing a perception time window with a dynamically adjustable step size, and determining the time window width according to the distribution of the perception position data, wherein the time window width includes the time granularity of the spatiotemporal grid and the rolling step size;

[0105] The rolling step of the time window is dynamically adjusted according to the time interval between the trajectory segments of the target platform user trajectory, and the cluster center distance between the location points between the target platform user trajectory and the to-be-linked platform user trajectory in the corresponding time window is obtained.

[0106] Taking the distance between trajectories as the basic element for similarity judgment, the distance calculation can be divided into two stages.

[0107] Phase 1: Construct a perception time window with dynamically adjustable step size. Due to the problem of missing data, the temporal and spatial spans of adjacent location points in the trajectories of instant messaging users are often large. To improve the efficiency of trajectory comparison, a perception time window with dynamically adjustable step size is constructed. The width of the time window, i.e., the time granularity of the spatiotemporal grid, and the rolling step size are determined by sensing the distribution of location data, such as Figure 3 When calculating the distance, the target trajectory T A As a benchmark, according to T A The time interval between the track segments in the window is used to dynamically adjust the scrolling step size of the window.

[0108] The second stage: Calculate the distance between the cluster centers of the position points between the trajectories. Under the control of the rolling time window, the basic similarity of the two trajectories is calculated based on the distance between the cluster centers of the position points between the trajectories, as shown in formula (3):

[0109]

[0110] in,

[0111]

[0112]

[0113] Where (h,k)∈W A ∩W B , K T (h,k,Δt)K T The (h,k,Δt) function is used to calculate the center coordinates of all location clusters of trajectory T in the kth time window of period h, N h is the number of time periods involved in the distance calculation, N kis the number of time windows involved in distance calculation within time period h, r is the radius of the earth, and the distance is in meters. In order to more accurately describe the differences in different distances in the similarity function Sim(·), the distance value can be reduced by adjusting the parameter μ to achieve more refined similarity calculation.

[0114] Specifically, the cluster center distances between trajectories are weighted according to the trajectory similarity weight model to obtain the similarity between the target platform user trajectory and other candidate trajectories, which can be designed to include:

[0115] Obtain the basic similarity between the target platform user trajectory and the to-be-linked platform user trajectory based on the cluster center distance between the trajectories;

[0116] The trajectory entropy is obtained based on the number of grid cells contained in the grid trajectory and the number of location points where the user trajectory falls into each grid, and the contribution of the grid in the grid trajectory is obtained based on the trajectory entropy;

[0117] According to the motion state trajectory and combined with the spatiotemporal co-occurrence of the trajectories between the target platform and the platform to be linked, the motion sequence similarity between the target platform user trajectory and the platform to be linked user trajectory is obtained;

[0118] The similarity between the user trajectory of the target platform and the user trajectory of the platform to be linked is obtained based on basic similarity, grid contribution and motion sequence similarity.

[0119] User behavior has certain regularities and uniqueness, and the trajectory is the product of the user's personal behavior. Therefore, finding the important positions and movement pattern characteristics of the trajectory is helpful to characterize the user's behavior characteristics, and the trajectory features are extracted using the grid contribution and motion sequence similarity.

[0120] Due to different personal living habits and movement patterns, the frequency of occurrence of each location in the trajectory is different. It is generally believed that the more frequently a location appears in a trajectory, the greater the importance it carries. However, sometimes a high frequency only means that the location is important, but the location may not be able to characterize more user characteristics. For example, "home" is an important location, but when the trajectory is composed entirely of the location of the home, the amount of information about the user's characteristics contained in the trajectory is very small, and it is difficult to distinguish it from people living nearby. Inspired by information entropy and grid Shannon entropy, the calculation formula for grid-based trajectory entropy can be expressed as:

[0121]

[0122] Where |T| is the number of position points contained in the trajectory T, that is, the number of grid cells contained in the corresponding grid trajectory, N T (g m ) is the trajectory T that falls into the grid g mThe larger the trajectory entropy value, the more information related to user features the trajectory contains. Based on the trajectory entropy, the calculation formula of the grid contribution can be expressed as follows:

[0123]

[0124] The grid contribution is a product term of formula (6). The grid contribution C T (g m ) is larger, the grid g m The more information contributed to the trajectory entropy of trajectory T, the more information the grid has about user features. Based on the grid contribution, the trajectory similarity can be redefined as:

[0125]

[0126] g i Representative trajectory T A The cluster center coordinates K TA The grid number that (h, k, Δt) falls into; correspondingly, g j is the trajectory T B The cluster center position K TB The grid number where (h,k,Δt) is located.

[0127] In the similarity calculation, since the grid contribution emphasizes the position characteristics of the trajectory again, in order to prevent the target trajectory from being misjudged with other trajectories that highly overlap with its activity area, formula (8) introduces the function f num (·) is used to control the influence of the number of spatiotemporal co-occurrences between two trajectories on the similarity calculation.

[0128] When the activity areas between trajectories overlap a lot, such as students in a school or employees in a company, their trajectories are often difficult to distinguish. However, everyone has their own unique life rules and habits, which makes the movement patterns of user trajectories in time series different. In the case of data errors, the motion state sequence of the trajectory is generated by coarse-grained motion state, and the user's private movement mode is extracted by combining the spatiotemporal co-occurrence between trajectories. The motion sequence similarity of two trajectories is calculated by formula (11).

[0129]

[0130] As mentioned above, since the number of location points on the instant messaging user trajectory does not fully represent the importance of the location to the user, the parameter θ is used to adjust the number of co-occurrence time windows |W A ∩W B | Similarity of motion sequence M simBased on the similarity of motion sequences, the trajectory similarity calculation formula can be redefined as follows:

[0131]

[0132] Grid contribution and motion sequence similarity are fine-grained extractions of the location and mobility pattern features of trajectory users. When calculating these two weights, a smaller grid system can be used. For example, the grid size is set to 220 meters in the experiment. Unlike formulas (3) and (8), formula (12) introduces grid contribution when calculating trajectory similarity, which more effectively distinguishes the contribution of different location areas on the trajectory to the trajectory identification of user features. At the same time, formula (12) also combines motion sequence similarity and considers the similarity of mobility patterns between different user trajectories. This enables the trajectory similarity calculation to more comprehensively characterize user features in terms of both geography and time sequence, and improves the accuracy of trajectory matching.

[0133] After constructing the weights based on grid contribution and motion sequence similarity, for the trajectory set D A Each trajectory T in A , and the candidate trajectory subset D′ B For each trajectory in , the trajectory similarity is calculated according to formula (12). In the similarity calculation results, the top n trajectories are selected as the winning trajectories and regarded as the target trajectory T A The matching trajectory of A The account is associated with the account information of the winning track, thereby completing the link between cross-platform users.

[0134] In summary, after Figure 2 The algorithm IMUL in this case completes the user linking across instant messaging platforms through the five steps in the above. The pseudo code of the method can be shown in Algorithm 2. It includes data preprocessing (2 lines), filtering the trajectory library according to the target trajectory (4 lines), calculating the weights including grid contribution (6-7 lines) and motion sequence similarity (8-9 lines), calculating trajectory similarity (10 lines), and finally taking the top n users with the highest similarity value to complete the linking with the target user (12-13 lines).

[0135]

[0136] Further, based on the above method, an embodiment of the present invention also provides a cross-platform accurate user linking system for combating location errors, comprising: a cross-platform user data acquisition module, a candidate user trajectory acquisition module, a trajectory location point clustering module, a trajectory similarity calculation module and a cross-platform user linking module, wherein:

[0137] A cross-platform user data acquisition module is used to acquire cross-instant messaging platform user data in a specified area, wherein the cross-instant messaging platform user data includes user sets and user trajectory sets in both the target platform and the platform to be linked; and grid transformation processing is performed on the cross-instant messaging platform user data to obtain grid trajectories and motion state trajectories of users in each user set;

[0138] The candidate user trajectory acquisition module is used to obtain the motion state distance between the target platform user trajectory and the to-be-linked platform user trajectory under the time window control, so as to obtain the candidate trajectory corresponding to the target platform user trajectory according to the motion state distance;

[0139] The trajectory location point clustering module is used to cluster the location points on the user trajectory according to the time window, and obtain the cluster center distance between the user trajectory of the target platform and the candidate trajectory. The time window adopts a rolling time window with adjustable step size;

[0140] The trajectory similarity calculation module is used to weight the cluster center distances between trajectories according to the trajectory similarity weight model to obtain the similarity between the target platform user trajectory and other candidate trajectories. The trajectory similarity weight model is constructed using grid contribution and motion sequence similarity. The grid contribution is used to characterize the amount of user trajectory feature information in each grid in the grid trajectory and is obtained using grid trajectory entropy. The motion sequence similarity is obtained based on the motion state trajectory sequence and combined with the spatiotemporal co-occurrence between trajectories.

[0141] The cross-platform user linking module is used to select the candidate trajectory with the maximum similarity between trajectories as the matching trajectory of the target platform user trajectory based on the similarity between the target platform user trajectory and other candidate trajectories, and link the cross-instant messaging platform users corresponding to the trajectory.

[0142] In order to verify the effectiveness of this solution, the following is a further explanation based on experimental data:

[0143] We conduct an experiment on instant messaging user linking on 7 datasets, including 6 public datasets and 1 self-built dataset, and compare them with three existing typical cross-platform user linking methods. R Conduct experimental verification.

[0144] Since it is difficult to obtain real cross-platform instant messaging user trajectories, the experiment first uses the Geolife public dataset of Microsoft Research Asia for verification. The dataset consists of 17,621 trajectories, each of which consists of a series of location points with timestamps, recording the daily real-life trajectories of users in different traffic modes. Most trajectories are composed of several trajectory segments of varying lengths, and the time intervals between segments are not fixed, ranging from more than ten minutes to several hours. In order to fully verify the performance of the algorithm, Geolife is split in turn to form the dataset sets Sub-Geolife and Mix-Sub-Geolife.

[0145] (1) Dataset Sub-Geolife

[0146] Randomly select a track T from Geolife i , put T i The position points on the trajectories are arranged in time sequence and numbered. Then, according to the operations shown in Table 4, the trajectories are split into two parts, which are regarded as two cross-platform trajectory sets, and the datasets G are generated in turn. 1 , G 2 and G 3 .

[0147] Table 4 Dataset generation

[0148]

[0149] In the process of splitting the data set, the time and space spans of adjacent position points on the trajectory are gradually enlarged, and the sparsity of the position data is gradually increased, so as to compare and analyze the performance of the algorithm under different data sparsity levels.

[0150] (2) Mix-Sub-Geolife dataset

[0151] To further verify the performance of the algorithm when there are errors in the data, while continuing to reduce the data sampling rate, random errors are added to each location data to form the data set Mix-Sub-Geolife, which includes G 4 , G 5 and G 6 The operation process is shown in Table 4. The average positioning errors of WeChat and Momo users are 56.6 meters and 15.3 meters respectively. The experiment selects 80 meters and 20 meters as the position error range of the two platforms, thus generating the data set G 4 .

[0152] During the experiment, 10,500 trajectories were randomly selected from the Geolife dataset, and 10,500 sets of cross-platform trajectory pairs (T A ,TB ). Then, we randomly select 10,000 trajectory pairs as positive samples, that is, trajectory pairs containing matching trajectories. Among the remaining 500 trajectory pairs, we remove the trajectory T from platform A. A , keep the trajectory T of platform B B As negative samples, they are used to interfere with trajectory matching and test the performance of the user linking method. The data set is shown in Table 5.

[0153] Table 5 Description of the dataset

[0154]

[0155] In Table 5, in order to highlight the sparsity of the position data, the average number of position points in the trajectory is used to describe the sparsity of the data on each data set and its changes. In order to prevent the data from being too sparse and causing the trajectory to remain unchanged before and after the split, the original trajectory T i All of them consist of more than 10 locations. However, the dataset G 1 ~G 5 We do not remove any sparse trajectories, i.e., trajectories containing only 1-2 position data.

[0156] In the self-built data set, 30 volunteers were recruited to complete the collection of the real data set. The currently popular WeChat and Momo were selected as two different instant messaging platforms, and the TrigLBSD.APP application was developed and installed on the experimental mobile phone. The function of the TrigLBSD application is to randomly refresh the current location and start a round of WeChat or Momo LBSD service. In the experiment, volunteers carried the experimental mobile phone in the urban area of ​​Zhengzhou (about 1200km 2 ) activities, daily life activities, such as walking, running, riding, staying, etc. At the same time, an Android simulator was run on the computer, and virtual probes were deployed using virtual location software to locate and track the volunteers. From September to November 2021, a total of 2,679 sets of cross-platform trajectory pairs (T W ,T M ). Among them, T W and T M They represent the WeChat and Momo user trajectories of the same target user on the same day. In the collected data, 2400 sets of trajectory pairs are randomly selected as positive samples, and the WeChat user trajectories in the trajectory pairs are extracted to form a trajectory library. Momo user trajectory composition Next, randomly select 120 pairs of the remaining trajectory pairs and put the Momo user trajectories into the trajectory library. As negative samples. S In the figure, each trajectory contains 86.84 position points on average.

[0157] Experiments were conducted on the above-mentioned public datasets and self-built datasets, and the relevant experimental parameter settings are shown in Table 6.

[0158] Table 6 Experimental parameter setting description

[0159]

[0160] In Table 6, the grid side length d determines the grid trajectory, the coarse-grained motion state of the trajectory, and the generated motion state trajectory. As mentioned above, in the filtering stage, d is taken as 330 meters, and when calculating the weight, d is taken as 220 to extract user features from different granularities. In formula (3), μ is used to refine the influence of the distance value on the similarity. β and γ appear in formula (10), and θ appears in formula (11). Since the number of occurrences in a certain location area on the trajectory of an instant messaging user cannot fully reflect the user's actual activity status, these three parameters are used to adjust the influence of the number of spatiotemporal co-occurrence windows between two trajectories on the similarity calculation. In the experiment, the parameters are set based on experience.

[0161] The accuracy rate is used as the evaluation index of the effectiveness of the solution in this case, and the filtering efficiency is used to evaluate the effectiveness of the algorithm filtering stage.

[0162] (1) Accuracy: Since the thresholds of different methods are different, similar to the user link article, the first n values ​​of the similarity calculation results (n≤|D|) are taken as the algorithm result, and the user link accuracy is recorded as Acc@n:

[0163]

[0164] Where D represents the target trajectory library, Indicates whether the matching trajectory exists in the top-n (n≤|D|) list.

[0165] (2) Filtering efficiency: Some existing works usually use hit rate as an indicator to evaluate the effectiveness of filtering algorithms. However, the hit rate only considers whether the candidate subset of the filtered trajectory contains matching trajectories, ignoring the impact of the candidate subset size on the subsequent similarity calculation overhead. Although a larger trajectory candidate subset improves the hit rate, it also causes more trajectories to participate in the subsequent similarity calculation, thereby increasing the computational and time costs. Therefore, in order to balance the hit rate and the candidate subset size, in order to achieve a balance between the accuracy of user links and computational efficiency, the hit rate is improved and the filtering efficiency is proposed, as shown in Equation (15).

[0166]

[0167] Among them, D A represents the target trajectory library, H represents D AThe number of trajectories hit in the A | is the hit rate. Two proportionality coefficients need to be satisfied: λ 1 >0,λ 2 >0, and λ 1 +λ 2 =1.

[0168] The experimental results and analysis are as follows:

[0169] 1. Selection of sub-scale parameters

[0170] After filtering, the original candidate trajectory library D B will retain α|D B | tracks, generate candidate subset D′ B The candidate subset size α determines the number of trajectories involved in trajectory similarity calculation, which directly affects the performance of the user linking method. In order to select a suitable subset size parameter α, experiments were conducted on 7 datasets. The results are shown in Figure 4 and 5 shown.

[0171] Figure 4 and Figure 5 The changes in filtering efficiency and hit rate are shown respectively when the subset size α changes from 0 to 1 with a span of 0.1. Figure 4 It shows that as the subset size α increases, the filtering efficiency decreases on most data sets. Figure 5 It can be seen that as α increases, the hit rate gradually increases, but the candidate subset D′ B The number of trajectories in also increases, which increases the cost of subsequent calculations. Figure 4 and Figure 5 It can be seen that on most data sets, the filtering efficiency when α is 0.1 is higher than that when it is other values, and the hit rate when α is 0.1 and 0.2 is not much lower than when it is 1.0. Therefore, it is recommended to set α to 0.1-0.2.

[0172] The experiment also analyzes the impact of different subset sizes α on the user link results of the proposed method. The experimental results are as follows: Figure 6 As shown in the figure, when the subset size α changes from 0 to 1 with a span of 0.1, as α increases, the accuracy of user links first decreases and then stabilizes. On most data sets, the accuracy is highest when α is 0.1, so α is set to 0.1 in the experiment.

[0173] 2. Comparison results of user link experiments

[0174] In the dataset G 1 ~G 6 And the self-built G SThe cross-platform user link experiments were carried out on 7 datasets. The experimental results of the algorithm in this case were compared with three existing typical methods such as k-BCT, GS, and TF-IWF. The results are as follows Figure 7 , as shown in Table 7 and Table 8.

[0175] Table 7 Acc@1 comparison results of this algorithm and three baseline methods (%)

[0176]

[0177] Table 8 Acc@3 comparison results of this algorithm and three baseline methods (%)

[0178]

[0179] The bold part in the table is the highest value in the comparison results. Figure 7 As can be seen from Tables 7 and 6, the performance of the proposed algorithm on the seven data sets is better than the three existing baseline methods. On the seven data sets, the accuracy Acc@1 is 32.86%, 44.8%, and 14.4% higher than the three baseline methods on average, and the accuracy Acc@3 is 30.52%, 34.67%, and 13.19% higher than the three baseline methods on average.

[0180] The improvement in user link accuracy is mainly due to the fact that the algorithm in this case selects both spatial and temporal features of the trajectory, which is more user-specific than the baseline method. The baseline method extracts trajectory features through the shortest distance between locations, the number of co-occurrences of locations, etc., and only focuses on the role of certain specific location areas on the trajectory, ignoring other locations in the trajectory and the connection between locations, and does not use the temporal features of the trajectory, thus affecting the accuracy of user links across instant messaging platforms. The algorithm in this case extracts trajectory location area features based on grid contribution, and also extracts the motion state sequence features of the trajectory in time through changes between locations, so that the location and movement mode features obtained when there are errors in the location data are more user-specific.

[0181] 3. Analysis of the impact of data sparsity and error on experimental results

[0182] Further observation of Tables 7 and 8 shows that in the dataset G with errors in the position data 4 , G 5 and G 6 The accuracy of each method is significantly lower than that of the dataset G consisting of accurate location data. 1 , G 2 and G 3 , and each method has 5 For example, in G 5The accuracy rates Acc@1 of k-BCT, GS, TF-IWF and the algorithm in this case are respectively higher than those in G 1 The accuracy of user links is 61.64%, 41.58%, 53.7% and 32.6% lower than that of Acc@3, and 55.84%, 46.68%, 43.36% and 18.34% lower than that of Acc@4. The analysis shows that the sharp decline in the accuracy of user links is mainly due to the fact that the accuracy of data set G 5 The position data itself has errors, and the data sparsity is the highest. It can be seen that the error and sparsity of the data have a great impact on the user link performance.

[0183] In order to analyze the impact of data sparsity on the performance of the method, the sparsity of the trajectory data in the dataset is calculated according to the following formula:

[0184]

[0185] Among them, N t It indicates the number of trajectories with a specific number of position points in the dataset D. The sparsity of the dataset is shown in Table 9.

[0186] Table 9 Trajectory sparsity of the dataset (%)

[0187]

[0188]

[0189] As can be seen from Table 9, from the data set G 1 To G 5 , the sparsity of trajectory data gradually increases. 5 For example, in G 5 Among them, trajectories containing 5 or fewer points account for 34.56%, which is G 4 5.86 times of G; the trajectories with less than 10 points account for 54.8%, which is 4 Combining Tables 6 and 5, we can see that as the sparsity of the dataset increases, the performance of each method decreases, and in the dataset G 5 The method k-BCT achieves the lowest value in the dataset G 1 The performance is better than that of G 2 and G 3 The difference is due to the fact that in the data set G 1 In the case of G, the activity area overlaps highly and the position data on the trajectory is dense, which is prone to misjudgment for methods such as k-BCT that only rely on distance factors. 5 The accuracy is also significantly higher than that of the other three baseline methods, indicating that the proposed solution has good resistance to data sparsity and interference.

[0190] The above data show that this solution adopts multi-granularity spatiotemporal grid to organize data, dynamically adjusts the sliding step of the time window, and extracts the characteristics of trajectory users in location area and temporal movement mode based on the distance between cluster centers under the time window through grid contribution and motion sequence similarity, thereby improving the accuracy of cross-platform user links. The filtering algorithm based on the coarse-grained motion state of the trajectory not only improves the accuracy of user links, but also reduces the calculation and time overhead of comparing the similarity with candidate trajectories, and has good application prospects in the field of cross-platform user links.

[0191] Unless otherwise specifically stated, the relative steps, numerical expressions and values ​​of the components and steps set forth in these embodiments do not limit the scope of the present invention.

[0192] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0193] The units and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A person of ordinary skill in the art may use different methods to implement the described functions for each specific application, but such implementation is not considered to be beyond the scope of the present invention.

[0194] Those skilled in the art will appreciate that all or part of the steps in the above method can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, such as a read-only memory, a disk or an optical disk. Optionally, all or part of the steps in the above embodiment can also be implemented using one or more integrated circuits, and accordingly, each module / unit in the above embodiment can be implemented in the form of hardware or in the form of software function modules. The present invention is not limited to any specific form of combination of hardware and software.

[0195] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for accurately linking users across instant messaging platforms to combat location errors, characterized in that: Include: Acquire cross-instant messaging platform user data in a specified area, wherein the cross-instant messaging platform user data includes user sets and user trajectory sets in both a target platform and a platform to be linked; and perform grid transformation processing on the cross-instant messaging platform user data to obtain grid trajectories and motion state trajectories of users in each user set; Under the time window control, the motion state distance between the target platform user trajectory and the to-be-linked platform user trajectory is obtained, so as to obtain a candidate trajectory corresponding to the target platform user trajectory according to the motion state distance; Clustering the location points on the user trajectory according to the time window to obtain the cluster center distance between the target platform user trajectory and the candidate trajectory, wherein the time window adopts a rolling time window with adjustable step size; The cluster center distances between trajectories are weighted according to the trajectory similarity weight model to obtain the similarity between the target platform user trajectory and other candidate trajectories. The trajectory similarity weight model is constructed using grid contribution and motion sequence similarity. The grid contribution is used to characterize the amount of user trajectory feature information in each grid in the grid trajectory and is obtained using grid trajectory entropy. The motion sequence similarity is obtained based on the motion state trajectory sequence and combined with the spatiotemporal co-occurrence between trajectories. According to the similarity between the target platform user trajectory and other candidate trajectories, the candidate trajectory with the maximum similarity between trajectories is selected as the matching trajectory of the target platform user trajectory, and the cross-instant messaging platform users corresponding to the trajectory are linked.

2. The method for accurate user linking across instant messaging platforms for combating location errors according to claim 1, characterized in that: Perform grid transformation on user data across instant messaging platforms, including: Setting the spatiotemporal granularity for describing the size of the spatiotemporal grid, wherein the spatiotemporal granularity includes the side length of the grid area and the width of the time window; Divide the specified area into grids and obtain the grid numbers corresponding to each position point on the user's trajectory; Sort the grids according to the time sequence to generate grid tracks; Slide the time window and traverse the grid trajectory, record the number of grid changes of the user trajectory in each time window, and combine the motion state in the previous time window to determine the motion state of the trajectory in the current time window to generate the motion state trajectory.

3. The method for accurate user linking across instant messaging platforms for combating location errors according to claim 1, characterized in that: Under the time window control, the motion state distance between the target platform user trajectory and the to-be-linked platform user trajectory is obtained, including: Compare the trajectory of each target user in the target platform with the trajectory of the user in the platform to be linked, and obtain the trajectory motion state distance between the trajectory of each target user in the target platform and the trajectory of the user in the platform to be linked; Obtaining a trajectory filtering score based on the trajectory motion state distance and the set and number of position co-occurrence time windows in the trajectory, wherein the trajectory filtering score is used to describe the mean difference in motion state of the trajectory to be compared and matched during the spatiotemporal co-occurrence of the position points; According to the trajectory filtering score, the user trajectories in the platform to be linked that do not match the target user trajectory are deleted to obtain the candidate trajectories corresponding to the target user trajectories of the target platform.

4. The method for accurate user linking across instant messaging platforms for combating location errors according to claim 1, characterized in that: Clustering of location points on user trajectories based on time windows, including: Constructing a perception time window with a dynamically adjustable step size, and determining the time window width according to the distribution of the perception position data, wherein the time window width includes the time granularity of the spatiotemporal grid and the rolling step size; The rolling step of the time window is dynamically adjusted according to the time interval between the trajectory segments of the target platform user trajectory, and the cluster center distance between the location points between the target platform user trajectory and the to-be-linked platform user trajectory in the corresponding time window is obtained.

5. The method for accurate user linking across instant messaging platforms for combating location errors according to claim 1, characterized in that: The cluster center distances between trajectories are weighted according to the trajectory similarity weight model to obtain the similarity between the target platform user trajectory and other candidate trajectories, including: Obtain the basic similarity between the target platform user trajectory and the to-be-linked platform user trajectory based on the cluster center distance between the trajectories; The trajectory entropy is obtained based on the number of grid cells contained in the grid trajectory and the number of location points where the user trajectory falls into each grid, and the contribution of the grid in the grid trajectory is obtained based on the trajectory entropy; According to the motion state trajectory and combined with the spatiotemporal co-occurrence of the trajectories between the target platform and the platform to be linked, the motion sequence similarity between the target platform user trajectory and the platform to be linked user trajectory is obtained; The similarity between the user trajectory of the target platform and the user trajectory of the platform to be linked is obtained based on basic similarity, grid contribution and motion sequence similarity.

6. The method for accurate user linking across instant messaging platforms for combating location errors according to claim 5, characterized in that: The similarity calculation formula between trajectories is expressed as: Among them, T A 、T B are the target platform user trajectory and the to-be-linked platform user trajectory, μ is the adjustment parameter used to reduce the distance value, D dist (T A ,T B ) represents the distance between trajectories, W A ∩W B is the set of time windows where positions co-occur in two trajectories, f num (·) is a function that controls the influence of the number of spatiotemporal co-occurrences between two trajectories on the similarity calculation, M sim (T A ,T B ) is the function for calculating the similarity of motion sequences between trajectories.

7. The method for accurate user linking across instant messaging platforms for combating location errors according to claim 1, characterized in that: The candidate trajectory with the maximum similarity between trajectories is selected as the matching trajectory of the target platform user trajectory, including: The similarities between the trajectories of each user on the target platform and the candidate trajectories are sorted, and several user trajectories with the highest similarity rankings are selected from the candidate trajectories as the winning trajectories that match the corresponding user trajectories on the target platform.

8. A precise user linking system across instant messaging platforms for combating location errors, characterized in that: It includes: cross-platform user data acquisition module, candidate user trajectory acquisition module, trajectory location point clustering module, trajectory similarity calculation module and cross-platform user link module, among which, A cross-platform user data acquisition module is used to acquire cross-instant messaging platform user data in a specified area, wherein the cross-instant messaging platform user data includes user sets and user trajectory sets in both the target platform and the platform to be linked; and grid transformation processing is performed on the cross-instant messaging platform user data to obtain grid trajectories and motion state trajectories of users in each user set; The candidate user trajectory acquisition module is used to obtain the motion state distance between the target platform user trajectory and the to-be-linked platform user trajectory under the time window control, so as to obtain the candidate trajectory corresponding to the target platform user trajectory according to the motion state distance; The trajectory location point clustering module is used to cluster the location points on the user trajectory according to the time window, and obtain the cluster center distance between the user trajectory of the target platform and the candidate trajectory. The time window adopts a rolling time window with adjustable step size; The trajectory similarity calculation module is used to weight the cluster center distances between trajectories according to the trajectory similarity weight model to obtain the similarity between the target platform user trajectory and other candidate trajectories. The trajectory similarity weight model is constructed using grid contribution and motion sequence similarity. The grid contribution is used to characterize the amount of user trajectory feature information in each grid in the grid trajectory and is obtained using grid trajectory entropy. The motion sequence similarity is obtained based on the motion state trajectory sequence and combined with the spatiotemporal co-occurrence between trajectories. The cross-platform user linking module is used to select the candidate trajectory with the maximum similarity between trajectories as the matching trajectory of the target platform user trajectory based on the similarity between the target platform user trajectory and other candidate trajectories, and link the cross-instant messaging platform users corresponding to the trajectory.

9. An electronic device, characterized in that: include: at least one processor, and a memory coupled to the at least one processor; The memory stores a computer program, and the computer program can be executed by the at least one processor to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the method according to any one of claims 1 to 7 can be implemented.

Images