User grid track acquisition method and device, equipment, medium and product

Abstract

The invention discloses a user grid track acquisition method and device, equipment, a medium and a product, and the method comprises the steps: carrying out the rasterization of an area where a to-be-processed user is located, and obtaining a plurality of grids; obtaining historical MDT data of the area and historical user track data of the area; according to the historical MDT data and the historical user track data, calculating the connection probability of historical user equipment with each base station when the historical user equipment is in each grid; and according to a base station sequence connected with the user equipment of the to-be-processed user and the connection probability, obtaining candidate grids to which the user equipment connected with each base station in the base station sequence belongs, and forming a grid track of the to-be-processed user. By adopting the embodiment of the invention, accurate acquisition of the user track can be realized.

Description

Technical Field

[0001] The present application relates to the field of positioning technology, and in particular to a method, device, equipment, medium and product for acquiring a user grid trajectory. Background Art

[0002] User location signaling data is an important part of the operator's data system and is used to determine the user's location information. At present, directly using the base station location data connected to the user device as the user's trajectory often has too large an error, so a multi-base station triangulation positioning method or a machine learning method is used.

[0003] (1) The multi-base station triangulation positioning method obtains the user trajectory by using the data of multiple base stations connected to the user device at the same time, so as to reduce the error caused by directly using the base station location data. However, the coverage range and signal strength of each base station in this method are different, resulting in large errors in the user trajectory obtained by this method.

[0004] (2) The machine learning method is to collect a large amount of historical trajectory data and its corresponding real location sequence, and train a machine learning model to obtain the user trajectory using the machine learning model. However, when the amount of data is insufficient, the machine learning model trained by this method has insufficient generalization ability, resulting in large errors in the user trajectory obtained by this method. Summary of the invention

[0005] The present application provides a method, device, equipment, medium and product for obtaining a user grid trajectory, so as to solve the problem that the user trajectory obtained in the prior art still has a large error.

[0006] To achieve the above purpose, the present application provides a method for obtaining a user grid trajectory, comprising:

[0007] Perform rasterization processing on the area where the user to be processed is located to obtain a number of grids;

[0008] Acquire historical MDT data of the area and historical user trajectory data of the area;

[0009] Calculating the connection probability between the historical user equipment and each base station at each grid according to the historical MDT data and the historical user trajectory data;

[0010] According to the base station sequence to which the user equipment of the to-be-processed user is connected and the connection probability, the candidate grid to which the user equipment connected to each base station in the base station sequence belongs is obtained to form a grid track of the to-be-processed user.

[0011] As an improvement of the above solution, the step of obtaining, according to the base station sequence to which the user equipment of the to-be-processed user is connected and the connection probability, a candidate grid to which the user equipment connected to each base station in the base station sequence belongs, and forming a grid track of the to-be-processed user includes:

[0012] Obtaining a base station sequence to which the device of the user to be processed is connected;

[0013] According to the connection probability, obtaining a candidate grid to which a user equipment connected to each base station in the base station sequence belongs;

[0014] According to the adjacent relationship between the candidate grids, a plurality of candidate grid trajectories are formed;

[0015] Based on the connection probability, the occurrence probability of each of the candidate grid trajectories is calculated, and the candidate grid trajectory with the largest occurrence probability is used as the grid trajectory of the user to be processed.

[0016] As an improvement of the above solution, the calculation of the connection probability between the historical user equipment and each base station at each grid according to the historical MDT data and the historical user trajectory data includes:

[0017] According to the historical MDT data, confirm the grid to which each MDT sampling point belongs;

[0018] Matching the historical MDT data and historical user trajectory data of the same historical user equipment at the same time to obtain a set of base stations to which the historical user equipment was connected when the grid to which each of the MDT sampling points belonged;

[0019] Collecting statistics on historical user trajectory data of each base station in the base station set to obtain statistical data;

[0020] The connection probability between the historical user equipment and each base station in the base station set when each of the MDT sampling points belongs to the grid is calculated according to the statistical data.

[0021] As an improvement of the above solution, the step of confirming the grid to which each MDT sampling point belongs based on the historical MDT data includes:

[0022] Based on the historical MDT data, confirm each MDT sampling point;

[0023] For each of the MDT sampling points, the grid to which the MDT sampling point belongs is determined according to the number of intersections between a number of rays starting from the MDT sampling point and the boundary of the grid.

[0024] As an improvement of the above solution, for each of the MDT sampling points, according to the number of intersections between a number of rays starting from the MDT sampling point and the boundary of the grid, determining the grid to which the MDT sampling point belongs includes:

[0025] For each of the MDT sampling points, N rays in multiple different directions starting from the MDT sampling point are taken, the number of boundary intersections between the rays starting from the MDT sampling point and any grid is calculated, and a first attribution probability that the MDT sampling point belongs to any grid is calculated according to the number of boundary intersections, and if the difference between the first attribution probability and 1 is within a preset range, it is confirmed that the grid to which the MDT sampling point belongs is the grid corresponding to the first attribution probability;

[0026] The first attribution probability is calculated according to the following formula:

[0027]

[0028] Where N is the number of rays starting from the MDT sampling point, I inside (i) is the intersection judgment result of the i-th ray. If the number of intersections between the ray and the boundary of the grid is an odd number, then I inside (i) = 1, if the number of intersections between the ray and the grid boundary is odd or even, then I inside (i) = 0, if there is no intersection, the ray is ignored; n is the number of rays that are not ignored.

[0029] As an improvement of the above solution, the step of making the historical MDT data of the same historical user equipment at the same time correspond to the historical user trajectory data to obtain the set of base stations to which the historical user equipment was connected when the grid to which each of the MDT sampling points belongs includes:

[0030] The historical MDT data and historical user trajectory data of the same historical user equipment at the same time are matched to obtain the base stations to which the historical user equipment is connected in the same grid:

[0031]

[0032] Wherein, i represents a grid index, m represents a user equipment, and {si} represents a set of base stations to which the mth user equipment is connected in the i-th grid;

[0033] Summarize all historical user MDT data and obtain historical user equipment in grid x i The set of base stations connected in:

[0034] x i ={Si}

[0035] Among them, {Si} represents all the iThe set of base stations to which the user equipment having historical MDT data is connected.

[0036] As an improvement of the above solution, the statistical data includes: total stay time and total number of connected user devices;

[0037] The calculating, according to the statistical data, the connection probability between the historical user equipment and each base station in the base station set when each of the MDT sampling points belongs to the grid includes:

[0038] The connection probability between the historical user equipment and the lth base station in the base station set {Si} at the i-th grid is calculated according to the following formula:

[0039]

[0040] In the formula, represents the total length of stay of historical user equipment under the l-th base station in the base station set {Si} of the i-th grid, represents the total number of connected user equipments connected to the lth base station in the base station set {Si} of the i-th grid, represents the distance between the lth base station in the base station set {Si} of the i-th grid and the center of the i-th grid, {dur i} represents the total residence time of historical user equipment under each base station in the base station set {Si} of the i-th grid, represents the total number of connected user equipment connected to the kth base station in the base station set {Si} of the i-th grid, {dis i} represents the set of distances between each base station in the base station set {Si} of the i-th grid and the center of the i-th grid.

[0041] As an improvement to the above solution, the area where the user to be processed is located is subjected to rasterization processing to obtain a plurality of grids, including:

[0042] Obtaining the base station information of the area where the user to be processed is located;

[0043] Calculating the base station density in the area according to the base station situation in the area;

[0044] Determining a grid size of the area according to a base station density of the area;

[0045] Based on the grid size, the region is subjected to a gridding process to obtain a plurality of grids.

[0046] As an improvement of the above solution, the step of calculating the base station density in the area according to the base station situation in the area includes:

[0047] The base station density in the area is calculated according to the following formula:

[0048]

[0049] Among them, ρ 区域 Indicates the base station density of the area, N point Indicates the number of boundary points of the collected area, S boundary represents the area of ​​the polygon formed by the boundary points of the collected area, C represents the compactness of base stations in the area, M represents the number of base stations in the area, and d ij represents the distance between the i-th base station and the j-th base station.

[0050] As an improvement of the above solution, determining the grid size of the area according to the base station density of the area includes:

[0051] Determine the grid side length of the area according to the following formula:

[0052]

[0053] Among them, Grid EdgeLength Represents the grid side length of the region, ρ low =μ ρ -σ ρ , ρ high =μ ρ +σ ρ , μ ρ represents the mean value of base station density in all regions, σ ρ Indicates the standard deviation of base station density in all regions.

[0054] As an improvement of the above solution, after the area where the user to be processed is located is gridded to obtain a plurality of grids, the method for obtaining the user grid trajectory further includes:

[0055] Confirming a boundary grid within the region; wherein the boundary of the boundary grid is composed of a region boundary and a grid boundary;

[0056] Taking the boundary grid that meets the preset size condition as a candidate boundary grid;

[0057] Calculating a second belonging probability that the candidate boundary grid belongs to each adjacent grid;

[0058] The candidate boundary grid is integrated into the grid with the second highest belonging probability.

[0059] As an improvement of the above solution, the second belonging probability that the candidate boundary grid belongs to each adjacent grid is calculated:

[0060] According to the first probability Second probability and the third probability One or more of the above, obtaining a second belonging probability that the candidate boundary grid belongs to each adjacent grid;

[0061] Among them, L i is the overlapping boundary length of the candidate boundary grid and the adjacent i-th grid, L is the total overlapping boundary length of the candidate boundary grid and all adjacent grids; n is the number of adjacent grids of the candidate boundary grid, d i is the average distance between the base station in the candidate boundary grid and the center of the adjacent i-th grid, ρ is the base station density in the candidate boundary grid, and ρ i is the density of base stations in the ith grid adjacent to the candidate boundary grid, σ is the Gaussian kernel parameter; cnt i It means that there are cnt base stations in the base station set A in its adjacent i-th grid, card(A) represents the number of elements in the base station set A, and the base station set A is obtained by counting the N base stations before and after the base station in the candidate boundary grid passing through several historical user trajectory sequences.

[0062] To achieve the above purpose, the embodiment of the present application further provides a user grid trajectory acquisition device, comprising:

[0063] A grid division module is used to perform grid processing on the area where the user to be processed is located to obtain a number of grids;

[0064] A historical data acquisition module, used to acquire historical MDT data of the area and historical user trajectory data of the area;

[0065] A connection probability calculation module, used to calculate the connection probability of the historical user equipment with each base station at each grid according to the historical MDT data and the historical user trajectory data;

[0066] The grid track acquisition module is used to obtain the candidate grid to which the user equipment connected to each base station in the base station sequence belongs according to the base station sequence to which the user equipment of the user to be processed is connected and the connection probability, so as to form the grid track of the user to be processed.

[0067] To achieve the above-mentioned purpose, an embodiment of the present application also provides a user grid trajectory acquisition device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor implements the user grid trajectory acquisition method as described above when executing the computer program.

[0068] To achieve the above-mentioned purpose, an embodiment of the present application also provides a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program is running, it controls the device where the computer-readable storage medium is located to execute the user grid trajectory acquisition method as described above.

[0069] To achieve the above-mentioned purpose, an embodiment of the present application further provides a computer program product, including a computer program / instruction, which implements the above-mentioned user grid trajectory acquisition method when executed by a processor.

[0070] Compared with the prior art, the user grid trajectory acquisition method, device, equipment, medium and product provided in the embodiment of the present application make full use of the existing accurate data, combine the historical MDT data and the historical user trajectory data to calculate the connection probability between the grid and the base station, and obtain the user trajectory. It can avoid the problem that the obtained user trajectory still has large errors due to the different coverage ranges and signal strengths of each base station, thereby improving the accuracy of the user trajectory. Moreover, compared with the machine learning method, the embodiment of the present application does not need to collect a large amount of historical trajectory data and its corresponding real position sequence, which not only reduces the difficulty of collection, but also can avoid the phenomenon of insufficient generalization ability of the machine learning model trained in the case of insufficient data, so that the accurate acquisition of user trajectory is achieved by combining sparse and accurate historical MDT data. In addition, the embodiment of the present application grids the user trajectory to achieve a better presentation effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 is a flow chart of a method for obtaining a user grid trajectory provided by an embodiment of the present application;

[0072] Figure 2 It is a structural block diagram of a user grid trajectory acquisition device provided in an embodiment of the present application;

[0073] Figure 3 It is a structural block diagram of a user grid trajectory acquisition device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0074] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0075] See also Figure 1 , Figure 1 : is a flowchart of a method for obtaining a user grid trajectory provided by an embodiment of the present application, wherein the method for obtaining a user grid trajectory comprises:

[0076] S1, rasterizing the area where the user to be processed is located to obtain a number of grids;

[0077] S2. Acquire historical MDT data of the area and historical user trajectory data of the area;

[0078] S3. Calculate the connection probability between the historical user equipment and each base station at each grid according to the historical MDT data and the historical user trajectory data;

[0079] S4. According to the base station sequence to which the user equipment of the to-be-processed user is connected and the connection probability, a candidate grid to which the user equipment connected to each base station in the base station sequence belongs is obtained to form a grid track of the to-be-processed user.

[0080] In the embodiment of the present application, the area where the user to be processed is located can be any area or any region, and is not specifically limited here. For example, the area is an irregular ecological red line area.

[0081] Historical MDT (Minimization Drive Test) data includes but is not limited to: user identification (such as user number), MDT sampling point longitude, MDT sampling point latitude and MDT sampling time; MDT sampling time includes at least two of the start time, stay duration and end time;

[0082] The historical user trajectory data includes, but is not limited to: user identification (e.g., user number), base station identification (e.g., consisting of location area code and cell identification code), base station longitude, base station latitude, and base station connection time. The base station connection time includes at least two of the start time, stay duration, and end time.

[0083] The embodiment of the present application makes full use of the existing accurate data, combines the historical MDT data and the historical user trajectory data to calculate the connection probability between the grid and the base station, and obtains the user trajectory. This can avoid the problem that the obtained user trajectory still has large errors due to the different coverage ranges and signal strengths of each base station, thereby improving the accuracy of the user trajectory. Moreover, compared with the machine learning method, the embodiment of the present application does not need to collect a large amount of historical trajectory data and its corresponding real position sequence, which not only reduces the difficulty of collection, but also can avoid the phenomenon of insufficient generalization ability of the machine learning model trained in the case of insufficient data, so that the user trajectory can be accurately obtained by combining sparse and accurate historical MDT data. In addition, the embodiment of the present application grids the user trajectory to achieve a better presentation effect.

[0084] In an optional embodiment, the area where the user to be processed is located is subjected to rasterization processing to obtain a plurality of grids, including:

[0085] Obtaining the base station information of the area where the user to be processed is located;

[0086] Calculating the base station density in the area according to the base station situation in the area;

[0087] Determining a grid size of the area according to a base station density of the area;

[0088] Based on the grid size, the region is subjected to a gridding process to obtain a plurality of grids.

[0089] In an embodiment of the present application, in order to improve the accuracy of application to different areas, an adaptive grid division method is proposed, which dynamically adjusts the size of the grid according to the base station conditions in the area to achieve reasonable grid division in different areas.

[0090] First, the base station situation of the area where the user to be processed is located is obtained, and the base station density of the area is calculated according to the base station situation of the area. The base station situation of the area includes the number of base stations in the area. For example, the number of base stations in the area is divided by the area of ​​the area to obtain the base station density of the area. In order to make the grid division more reasonable, the base station density of the area can also be calculated in combination with the boundary point situation of the area;

[0091] Specifically, the boundary points of the area are collected at a preset distance to obtain the boundary point situation. Preferably, the preset distance is 5 meters. The base station density ρ of the area is calculated according to the following formula: 区域 :

[0092]

[0093] Among them, N point Indicates the number of boundary points of the collected area, S boundary represents the area of ​​the polygon formed by the boundary points of the collected area, C represents the compactness of the base stations in the area, the smaller C is, the denser the base stations in the area are, M represents the number of base stations in the area, d ij represents the distance between the i-th base station and the j-th base station; of course, the base station density of the area can be calculated by other methods, not limited to this formula.

[0094] Next, the grid size of the area is determined according to the base station density of the area, wherein the greater the base station density of the area, the smaller the grid size of the area.

[0095] In a specific example, the grid side length Grid of the region is determined according to the following formula: EdgeLength :

[0096]

[0097] Among them, ρ low =μ ρ -σ ρ , ρ high =μρ +σ ρ , μ ρ represents the mean value of base station density in all regions, σ ρ Indicates the standard deviation of the base station density of all regions. Of course, the grid side length of the region can be determined by other methods, not limited to this formula.

[0098] Then, the grid size of the area is Grid EdgeLength *Grid EdgeLength Finally, based on the grid size, the region is gridded to obtain a plurality of grids.

[0099] In an optional embodiment, after the area where the user to be processed is located is rasterized to obtain a plurality of grids, the method for obtaining the user grid trajectory further includes:

[0100] Confirming a boundary grid within the region; wherein the boundary of the boundary grid is composed of a region boundary and a grid boundary;

[0101] Taking the boundary grid that meets the preset size condition as a candidate boundary grid;

[0102] Calculating a second belonging probability that the candidate boundary grid belongs to each adjacent grid;

[0103] The candidate boundary grid is integrated into the grid with the second highest belonging probability.

[0104] It can be understood that the grid is a regular shape, generally a square, but in actual situations the boundaries of the region may be irregular, so some boundary grids in the region (the boundary grid is composed of the boundary of the region and the boundary of the grid) have only a small area. By fusing the boundary grids with smaller areas, the influence of the boundary grid on the user grid trajectory is reduced, thereby improving the accuracy of the user grid trajectory.

[0105] In the embodiment of the present application, the boundary grid that meets the preset size condition is used as a candidate boundary grid. Preferably, the preset size condition is that the area of ​​the boundary grid is less than a preset area threshold, and the preset area threshold is 0.25*S grid , where S grid is the area of ​​the grid.

[0106] The second belonging probability of the candidate boundary grid belonging to each of the adjacent grids is calculated, and the candidate boundary grid is integrated into the grid with the largest second belonging probability.

[0107] For example, the first probability p that the candidate boundary grid belongs to the adjacent i-th grid can be calculated based on the overlapped boundary length between the candidate boundary grid and the adjacent grid. i1 :

[0108]

[0109] Among them, L i is the overlapping boundary length of the candidate boundary grid and the adjacent i-th grid, and L is the total overlapping boundary length of the candidate boundary grid and all adjacent grids.

[0110] The second probability p that the candidate boundary grid belongs to its adjacent i-th grid can also be calculated based on the average distance between the base station in the candidate boundary grid and the center of the adjacent grid. i2 :

[0111]

[0112] Where n is the number of adjacent grids of the candidate boundary grid, d i is the average distance between the base station in the candidate boundary grid and the center of the adjacent i-th grid, ρ is the base station density in the candidate boundary grid, and ρ i is the density of base stations in the ith grid adjacent to the candidate boundary grid, σ is the Gaussian kernel parameter, which is used to control the influence of the average distance. A smaller σ value will make the average distance have a more significant impact on the weight, while a larger σ value will weaken the influence of the average distance. i Both can be obtained by dividing the number of base stations in the grid by the area of ​​the grid.

[0113] The third probability that the candidate boundary grid belongs to each adjacent grid may also be calculated according to the belonging grids of the base stations before and after the base station that passes through the candidate boundary grid in the historical user trajectory:

[0114] The base station set A is obtained by counting the N base stations before and after the base station in the candidate boundary grid in the historical user trajectory sequence; the third probability p that the candidate boundary grid belongs to its adjacent i-th grid is calculated according to the following formula: i3 :

[0115]

[0116] In the formula, cnt i It means that there are cnt base stations in the base station set A in its adjacent i-th grid, and card(A) represents the number of elements in the base station set A.

[0117] The first probability p i1 , the second probability p i2 , the third probability p i3 It can be directly used as the second belonging probability p of the candidate boundary grid belonging to each adjacent grid. i , for example, the second belonging probability p i =p i1Of course, we can also combine the probabilities calculated by the above methods (including the first probability p i1 , the second probability p i2 , the third probability p i3 ), and obtain the second belonging probability p of the candidate boundary grid belonging to its adjacent i-th grid i , for example, the second belonging probability p i =p i2 *p i3 , the second belonging probability p i =q1*p i1 +q2*p i2 +q3*p i3 ; q1, q2, q3 are the weights of the first probability, the second probability, and the third probability, respectively, and are not specifically limited here.

[0118] In an optional embodiment, the calculating, according to the historical MDT data and the historical user trajectory data, the connection probability of the historical user equipment with each base station at each grid includes:

[0119] According to the historical MDT data, confirm the grid to which each MDT sampling point belongs;

[0120] Matching the historical MDT data and historical user trajectory data of the same historical user equipment at the same time to obtain a set of base stations to which the historical user equipment was connected when the grid to which each of the MDT sampling points belonged;

[0121] Collecting statistics on historical user trajectory data of each base station in the base station set to obtain statistical data;

[0122] The connection probability between the historical user equipment and each base station in the base station set when each of the MDT sampling points belongs to the grid is calculated according to the statistical data.

[0123] In the embodiment of the present application, the grid for confirming the attribution of the MDT sampling points is defined as the positional relationship between points and polygons, which can be confirmed by various methods, such as geometric algorithms, ray methods, and the like.

[0124] The historical MDT data and historical user trajectory data of the same historical user equipment at the same time are matched to obtain the base station set to which the historical user equipment is connected when each of the grids to which the MDT sampling points belong. Specifically,

[0125] The historical MDT data and historical user trajectory data of the same historical user equipment at the same time are matched to obtain the base stations to which the historical user equipment is connected in the same grid:

[0126]

[0127] Wherein, i represents a grid index, m represents a user equipment, and {si} represents a set of base stations to which the mth user equipment is connected in the i-th grid.

[0128] Summarize all historical user MDT data and obtain historical user equipment in grid x i The set of base stations connected in .

[0129] x i ={Si}

[0130] {Si} represents all the i The set of base stations to which the user equipment having historical MDT data is connected.

[0131] The historical user trajectory data of each base station in the base station set is counted to obtain statistical data; wherein the statistical data includes: total stay time and total number of connected user devices;

[0132] The connection probability between the historical user equipment and the lth base station in the base station set {Si} at the i-th grid is calculated according to the following formula:

[0133]

[0134] In the formula, represents the total length of stay of historical user equipment under the l-th base station in the base station set {Si} of the i-th grid, represents the total number of connected user equipments connected to the lth base station in the base station set {Si} of the i-th grid, represents the distance between the lth base station in the base station set {Si} of the i-th grid and the center of the i-th grid, {dur i} represents the total residence time of historical user equipment under each base station in the base station set {Si} of the i-th grid, represents the total number of connected user equipment connected to the kth base station in the base station set {Si} of the i-th grid, {dis i} represents the set of distances between each base station in the base station set {Si} of the i-th grid and the center of the i-th grid. Of course, the connection probability can be calculated by other methods, not limited to this formula.

[0135] In an optional embodiment, the confirming, according to the historical MDT data, the grid to which each MDT sampling point belongs includes:

[0136] Based on the historical MDT data, confirm each MDT sampling point;

[0137] For each of the MDT sampling points, the grid to which the MDT sampling point belongs is determined according to the number of intersections between a number of rays starting from the MDT sampling point and the boundary of the grid.

[0138] In the embodiment of the present application, for an MDT sampling point, a plurality of rays are used to confirm the ownership of the MDT sampling point, so that the grid to which the MDT sampling point belongs can be accurately confirmed. Specifically:

[0139] For each of the MDT sampling points, N rays in multiple different directions starting from the MDT sampling point are taken, the number of boundary intersections between the rays starting from the MDT sampling point and any grid is calculated, and a first attribution probability that the MDT sampling point belongs to any grid is calculated according to the number of boundary intersections, and if the difference between the first attribution probability and 1 is within a preset range, it is confirmed that the grid to which the MDT sampling point belongs is the grid corresponding to the first attribution probability;

[0140] The first attribution probability is calculated according to the following formula:

[0141]

[0142] Where N is the number of rays starting from the MDT sampling point, I inside (i) is the intersection judgment result of the i-th ray. If the number of intersections between the ray and the boundary of the grid is an odd number, then I inside (i) = 1, if the number of intersections between the ray and the grid boundary is odd or even, then I inside (i) = 0, if there is no intersection, the ray is ignored. n is the number of rays that are not ignored. When the starting point is on the grid, the point is not considered as an intersection point, that is, the number of boundary intersection points does not count the starting point.

[0143] If the first attribution probability P inside The difference from 1 is within the preset range, for example, -0.2≤P inside -1≤0.2, it can be considered that P inside is close to 1, then it is confirmed that the MDT sampling point is in the P inside In the corresponding grid, that is, the MDT sampling point belongs to the grid, otherwise the MDT sampling point is outside the grid and does not belong to the grid. Further, if the MDT sampling point has a first belonging probability P with multiple grids inside If both are close to 1, it means that the MDT sampling point falls on the boundary of the grid, and the MDT sampling point is ignored, that is, not used as a basis.

[0144] In an optional embodiment, obtaining, according to the base station sequence to which the user equipment of the to-be-processed user is connected and the connection probability, a candidate grid to which the user equipment connected to each base station in the base station sequence belongs, and forming a grid track of the to-be-processed user includes:

[0145] Obtaining a base station sequence to which the device of the user to be processed is connected;

[0146] According to the connection probability, obtaining a candidate grid to which a user equipment connected to each base station in the base station sequence belongs;

[0147] According to the adjacent relationship between the candidate grids, a plurality of candidate grid trajectories are formed;

[0148] Based on the connection probability, the occurrence probability of each of the candidate grid trajectories is calculated, and the candidate grid trajectory with the largest occurrence probability is used as the grid trajectory of the user to be processed.

[0149] In the embodiment of the present application, for each base station in the base station sequence to which the device of the user to be processed is connected, based on the connection probability, the candidate grid to which the user device connected to the base station belongs is obtained, that is, the user device to be processed is connected to the base station when it is located in the candidate grid. According to the adjacent relationship between these candidate grids, several candidate grid tracks are formed.

[0150] Exemplarily, starting from the first base station in the base station sequence, the candidate grid {X1} to which the user equipment connected to the first base station belongs and the corresponding connection probability are obtained, and then the candidate grid {X2} to which the user equipment connected to the second base station belongs and the corresponding connection probability are obtained. The grids in {X2} that are adjacent to any grid in {X1} are taken out to form a binary sequence. If there are multiple adjacent grids, all binary sequences are saved. If there are no adjacent grids, multiple nearest grids are taken to form a binary sequence, and so on, until the last base station in the base station sequence is processed, and all multi-element sequences are saved. These multi-element sequences form the candidate grid trajectory.

[0151] For example, the candidate grid {X1} contains grids A1, A2, and A3; the candidate grid {X2} contains grids B1, B2, and B3. Assuming that B1 is adjacent to A1 and A2, and B2 is adjacent to A3, the binary sequences are (A1, B1), (A2, B1), and (A3, B2). Next, the candidate grid {X3} contains grids C1 and C2. Assuming that C1 is adjacent to B1, and C2 is adjacent to B1, the ternary sequences are (A1, B1, C1), (A2, B1, C2), and so on, until the last base station in the base station sequence is processed and a multi-element sequence is formed.

[0152] Based on the connection probability, the occurrence probability of each candidate grid track is calculated, and the candidate grid track with the largest occurrence probability is used as the grid track of the user to be processed. For example, the connection probabilities corresponding to the candidate grid tracks are normalized, and the normalized connection probabilities are multiplied to obtain the occurrence probability of the candidate grid track.

[0153] Among them, the normalization formula is:

[0154]

[0155] In the formula, x ′ represents the normalized connection probability, represents the connection probability between the historical user equipment and the lth base station in the base station set {Si} at the i-th grid.

[0156] See also Figure 2 , Figure 2 : is a structural block diagram of a user grid trajectory acquisition device 10 provided in an embodiment of the present application, wherein the user grid trajectory acquisition device 10 comprises:

[0157] A grid division module 11 is used to perform grid processing on the area where the user to be processed is located to obtain a plurality of grids;

[0158] A historical data acquisition module 12, used to acquire historical MDT data of the area and historical user trajectory data of the area;

[0159] A connection probability calculation module 13, configured to calculate the connection probability of the historical user equipment with each base station at each grid according to the historical MDT data and the historical user trajectory data;

[0160] The grid track acquisition module 14 is used to obtain the candidate grid to which the user equipment connected to each base station in the base station sequence belongs according to the base station sequence to which the user equipment of the user to be processed is connected and the connection probability, so as to form the grid track of the user to be processed.

[0161] Optionally, the grid trajectory acquisition module 14 is further used for:

[0162] Obtaining a base station sequence to which the device of the user to be processed is connected;

[0163] According to the connection probability, obtaining a candidate grid to which a user equipment connected to each base station in the base station sequence belongs;

[0164] According to the adjacent relationship between the candidate grids, a plurality of candidate grid trajectories are formed;

[0165] Based on the connection probability, the occurrence probability of each of the candidate grid trajectories is calculated, and the candidate grid trajectory with the largest occurrence probability is used as the grid trajectory of the user to be processed.

[0166] Optionally, the connection probability calculation module 13 is further used for:

[0167] According to the historical MDT data, confirm the grid to which each MDT sampling point belongs;

[0168] Matching the historical MDT data and historical user trajectory data of the same historical user equipment at the same time to obtain a set of base stations to which the historical user equipment was connected when the grid to which each of the MDT sampling points belonged;

[0169] Collecting statistics on historical user trajectory data of each base station in the base station set to obtain statistical data;

[0170] The connection probability between the historical user equipment and each base station in the base station set when each of the MDT sampling points belongs to the grid is calculated according to the statistical data.

[0171] Optionally, the connection probability calculation module 13 is further used for:

[0172] Based on the historical MDT data, confirm each MDT sampling point;

[0173] For each of the MDT sampling points, the grid to which the MDT sampling point belongs is determined according to the number of intersections between a number of rays starting from the MDT sampling point and the boundary of the grid.

[0174] Optionally, the connection probability calculation module 13 is further used for:

[0175] For each of the MDT sampling points, N rays in multiple different directions starting from the MDT sampling point are taken, the number of boundary intersections between the rays starting from the MDT sampling point and any grid is calculated, and a first attribution probability that the MDT sampling point belongs to any grid is calculated according to the number of boundary intersections, and if the difference between the first attribution probability and 1 is within a preset range, it is confirmed that the grid to which the MDT sampling point belongs is the grid corresponding to the first attribution probability;

[0176] The first attribution probability is calculated according to the following formula:

[0177]

[0178] Where N is the number of rays starting from the MDT sampling point, I inside (i) is the intersection judgment result of the i-th ray. If the number of intersections between the ray and the boundary of the grid is an odd number, then I inside (i) = 1, if the number of intersections between the ray and the grid boundary is odd or even, then I inside (i) = 0, if there is no intersection, the ray is ignored; n is the number of rays that are not ignored.

[0179] Optionally, the connection probability calculation module 13 is further used for:

[0180] The historical MDT data and historical user trajectory data of the same historical user equipment at the same time are matched to obtain the base stations to which the historical user equipment is connected in the same grid:

[0181]

[0182] Wherein, i represents a grid index, m represents a user equipment, and {si} represents a set of base stations to which the mth user equipment is connected in the i-th grid;

[0183] Summarize all historical user MDT data and obtain historical user equipment in grid x i The set of base stations connected in:

[0184] x i ={Si}

[0185] Among them, {Si} represents all the i The set of base stations to which the user equipment having historical MDT data is connected.

[0186] Optionally, the statistical data includes: total stay time and total number of connected user devices;

[0187] The connection probability calculation module 13 is also used for:

[0188] The connection probability between the historical user equipment and the lth base station in the base station set {Si} at the i-th grid is calculated according to the following formula:

[0189]

[0190] In the formula, represents the total length of stay of historical user equipment under the l-th base station in the base station set {Si} of the i-th grid, represents the total number of connected user equipments connected to the lth base station in the base station set {Si} of the i-th grid, represents the distance between the lth base station in the base station set {Si} of the i-th grid and the center of the i-th grid, {dur i} represents the total residence time of historical user equipment under each base station in the base station set {Si} of the i-th grid, represents the total number of connected user equipment connected to the kth base station in the base station set {Si} of the i-th grid, {dis i} represents the set of distances between each base station in the base station set {Si} of the i-th grid and the center of the i-th grid.

[0191] Optionally, the grid division module 11 is further used for:

[0192] Obtaining the base station information of the area where the user to be processed is located;

[0193] Calculating the base station density in the area according to the base station situation in the area;

[0194] Determining a grid size of the area according to a base station density of the area;

[0195] Based on the grid size, the region is subjected to a gridding process to obtain a plurality of grids.

[0196] Optionally, the grid division module 11 is further used for:

[0197] The base station density in the area is calculated according to the following formula:

[0198]

[0199] Among them, ρ 区域 Indicates the base station density of the area, N point Indicates the number of boundary points of the collected area, S boundary represents the area of ​​the polygon formed by the boundary points of the collected area, C represents the compactness of base stations in the area, M represents the number of base stations in the area, and d ij represents the distance between the i-th base station and the j-th base station.

[0200] Optionally, the grid division module 11 is further used for:

[0201] Determine the grid side length of the area according to the following formula:

[0202]

[0203] Among them, Grid EdgeLength Represents the grid side length of the region, ρ low =μ ρ -σ ρ , ρ high =μ ρ +σ ρ , μ ρ represents the mean value of base station density in all regions, σ ρ Indicates the standard deviation of base station density in all regions.

[0204] Optionally, the user grid trajectory acquisition device 10 further includes:

[0205] The boundary grid fusion module is used to confirm the boundary grids in the area; use the boundary grids that meet the preset size conditions as candidate boundary grids; calculate the second belonging probability of the candidate boundary grid belonging to each adjacent grid; and integrate the candidate boundary grid into the grid with the largest second belonging probability; wherein the boundary of the boundary grid is composed of the area boundary and the grid boundary.

[0206] Optionally, the boundary grid fusion module is further used for:

[0207] According to the first probability Second probability and the third probability One or more of the above, obtaining a second belonging probability that the candidate boundary grid belongs to each adjacent grid;

[0208] Among them, L i is the overlapping boundary length of the candidate boundary grid and the adjacent i-th grid, L is the total overlapping boundary length of the candidate boundary grid and all adjacent grids; n is the number of adjacent grids of the candidate boundary grid, d i is the average distance between the base station in the candidate boundary grid and the center of the adjacent i-th grid, ρ is the base station density in the candidate boundary grid, and ρ i is the density of base stations in the ith grid adjacent to the candidate boundary grid, σ is the Gaussian kernel parameter; cnt i It means that there are cnt base stations in the base station set A in its adjacent i-th grid, card(A) represents the number of elements in the base station set A, and the base station set A is obtained by counting the N base stations before and after the base station in the candidate boundary grid passing through several historical user trajectory sequences.

[0209] It is worth noting that the working process of each module in the user grid trajectory acquisition device 10 described in the embodiment of the present application can refer to the working process of the user grid trajectory acquisition method described in the above embodiment, and will not be repeated here.

[0210] A user grid trajectory acquisition device 10 provided in an embodiment of the present application makes full use of existing accurate data, combines historical MDT data and historical user trajectory data to calculate the connection probability between the grid and the base station, and obtains the user trajectory. This can avoid the problem that the user trajectory obtained still has large errors due to different coverage ranges and signal strengths of each base station, thereby improving the accuracy of the user trajectory. Moreover, compared with the machine learning method, the embodiment of the present application does not need to collect a large amount of historical trajectory data and its corresponding real position sequence, which not only reduces the difficulty of collection, but also can avoid the phenomenon of insufficient generalization ability of the machine learning model trained in the case of insufficient data, so that the accurate acquisition of user trajectories is achieved by combining sparse and accurate historical MDT data. In addition, the embodiment of the present application grids the user trajectory to achieve a better presentation effect.

[0211] In addition, an embodiment of the present application further provides a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program is running, it controls the device where the computer-readable storage medium is located to execute the user grid trajectory acquisition method as described in any of the above embodiments.

[0212] In addition, an embodiment of the present application further provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the user grid trajectory acquisition method as described in any of the above embodiments.

[0213] See also Figure 3 , Figure 3 : is a structural block diagram of a user grid trajectory acquisition device 20 provided in an embodiment of the present application, and the user grid trajectory acquisition device 20 includes: a processor 21, a memory 22, and a computer program stored in the memory 22 and executable on the processor 21. When the processor 21 executes the computer program, the steps in the above-mentioned user grid trajectory acquisition method embodiment are implemented. Alternatively, when the processor 21 executes the computer program, the functions of each module / unit in the above-mentioned device embodiments are implemented.

[0214] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory 22 and executed by the processor 21 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the user grid trajectory acquisition device 20.

[0215] The user grid track acquisition device 20 may include, but is not limited to, a processor 21 and a memory 22. Those skilled in the art may understand that the schematic diagram is only an example of the user grid track acquisition device 20 and does not constitute a limitation on the user grid track acquisition device 20. The user grid track acquisition device 20 may include more or less components than shown in the figure, or combine certain components, or different components. For example, the user grid track acquisition device 20 may also include input and output devices, network access devices, buses, etc.

[0216] The processor 21 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor 21 is the control center of the user grid track acquisition device 20, and uses various interfaces and lines to connect various parts of the entire user grid track acquisition device 20.

[0217] The memory 22 can be used to store the computer program and / or module. The processor 21 realizes various functions of the user grid trajectory acquisition device 20 by running or executing the computer program and / or module stored in the memory 22 and calling the data stored in the memory 22. The memory 22 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 22 can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0218] Wherein, if the module / unit integrated in the user grid trajectory acquisition device 20 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor 21, the steps of the above-mentioned method embodiments can be implemented. Wherein, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium.

[0219] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0220] The above is a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications are also considered to be within the scope of protection of the present application.

Claims

1. A method for obtaining a user grid trajectory, characterized in that: include: Perform rasterization processing on the area where the user to be processed is located to obtain a number of grids; Acquire historical MDT data of the area and historical user trajectory data of the area; Calculating the connection probability between the historical user equipment and each base station at each grid according to the historical MDT data and the historical user trajectory data; According to the base station sequence to which the user equipment of the to-be-processed user is connected and the connection probability, the candidate grid to which the user equipment connected to each base station in the base station sequence belongs is obtained to form a grid track of the to-be-processed user.

2. The user grid trajectory acquisition method according to claim 1, characterized in that: The step of obtaining, according to the base station sequence to which the user equipment of the to-be-processed user is connected and the connection probability, a candidate grid to which the user equipment connected to each base station in the base station sequence belongs, and forming a grid track of the to-be-processed user comprises: Obtaining a base station sequence to which the device of the user to be processed is connected; According to the connection probability, obtaining a candidate grid to which a user equipment connected to each base station in the base station sequence belongs; According to the adjacent relationship between the candidate grids, a plurality of candidate grid trajectories are formed; Based on the connection probability, the occurrence probability of each of the candidate grid trajectories is calculated, and the candidate grid trajectory with the largest occurrence probability is used as the grid trajectory of the user to be processed.

3. The user grid trajectory acquisition method according to claim 1, characterized in that: The calculating, according to the historical MDT data and the historical user trajectory data, the connection probability between the historical user equipment and each base station at each grid includes: According to the historical MDT data, confirm the grid to which each MDT sampling point belongs; Matching the historical MDT data and historical user trajectory data of the same historical user equipment at the same time to obtain a set of base stations to which the historical user equipment was connected when the grid to which each of the MDT sampling points belonged; Collecting statistics on historical user trajectory data of each base station in the base station set to obtain statistical data; The connection probability between the historical user equipment and each base station in the base station set when each of the MDT sampling points belongs to the grid is calculated according to the statistical data.

4. The method for obtaining user grid trajectory according to claim 3, characterized in that: The step of confirming the grid to which each MDT sampling point belongs according to the historical MDT data includes: Based on the historical MDT data, confirm each MDT sampling point; For each of the MDT sampling points, the grid to which the MDT sampling point belongs is determined according to the number of intersections between a number of rays starting from the MDT sampling point and the boundary of the grid.

5. The method for obtaining user grid trajectory according to claim 4, characterized in that: The step of determining, for each of the MDT sampling points, the grid to which the MDT sampling point belongs according to the number of intersections between a number of rays starting from the MDT sampling point and the boundary of the grid, includes: For each of the MDT sampling points, N rays in multiple different directions starting from the MDT sampling point are taken, the number of boundary intersections between the rays starting from the MDT sampling point and any grid is calculated, and a first attribution probability that the MDT sampling point belongs to any grid is calculated according to the number of boundary intersections, and if the difference between the first attribution probability and 1 is within a preset range, it is confirmed that the grid to which the MDT sampling point belongs is the grid corresponding to the first attribution probability; The first attribution probability is calculated according to the following formula: Where N is the number of rays starting from the MDT sampling point, I inside (i) is the intersection judgment result of the i-th ray. If the number of intersections between the ray and the boundary of the grid is an odd number, then I inside (i) = 1, if the number of intersections between the ray and the grid boundary is odd or even, then I inside (i) = 0, if there is no intersection, the ray is ignored; n is the number of rays that are not ignored.

6. The method for obtaining user grid trajectory according to claim 3, characterized in that: The step of making the historical MDT data of the same historical user equipment at the same time correspond to the historical user trajectory data to obtain a set of base stations to which the historical user equipment was connected when the grid to which each of the MDT sampling points belongs includes: The historical MDT data and historical user trajectory data of the same historical user equipment at the same time are matched to obtain the base stations to which the historical user equipment is connected in the same grid: Wherein, i represents a grid index, m represents a user equipment, and {si} represents a set of base stations to which the mth user equipment is connected in the i-th grid; Summarize all historical user MDT data and obtain historical user equipment in grid x i The set of base stations connected in: x i ={Si} Among them, {Si} represents all the i The set of base stations to which the user equipment having historical MDT data is connected.

7. The method for obtaining user grid trajectory according to claim 6, characterized in that: The statistical data include: total dwell time and total number of connected user devices; The calculating, according to the statistical data, the connection probability between the historical user equipment and each base station in the base station set when each of the MDT sampling points belongs to the grid includes: The connection probability between the historical user equipment and the lth base station in the base station set {Si} at the i-th grid is calculated according to the following formula: In the formula, represents the total length of stay of historical user equipment under the l-th base station in the base station set {Si} of the i-th grid, represents the total number of connected user equipments connected to the first base station in the base station set {Si} of the i-th grid, represents the distance between the lth base station in the base station set {Si} of the i-th grid and the center of the i-th grid, {dur i } represents the total residence time of historical user equipment under each base station in the base station set {Si} of the i-th grid, represents the total number of connected user equipment connected to the kth base station in the base station set {Si} of the i-th grid, {dis i } represents the set of distances between each base station in the base station set {Si} of the i-th grid and the center of the i-th grid.

8. The method for obtaining user grid trajectory according to claim 1, characterized in that: The area where the user to be processed is located is subjected to rasterization processing to obtain a plurality of grids, including: Obtaining the base station information of the area where the user to be processed is located; Calculating the base station density in the area according to the base station situation in the area; Determining a grid size of the area according to a base station density of the area; Based on the grid size, the region is subjected to a gridding process to obtain a plurality of grids.

9. The method for obtaining user grid trajectory according to claim 8, characterized in that: The calculating the base station density of the area according to the base station situation of the area includes: The base station density in the area is calculated according to the following formula: Among them, ρ 区域 Indicates the base station density of the area, N point Indicates the number of boundary points of the collected area, S boundary represents the area of ​​the polygon formed by the boundary points of the collected area, C represents the compactness of base stations in the area, M represents the number of base stations in the area, and d ij represents the distance between the i-th base station and the j-th base station.

10. The method for acquiring user grid trajectory according to claim 8, characterized in that: Determining the grid size of the area according to the base station density of the area includes: Determine the grid side length of the area according to the following formula: Among them, Grid EdgeLength represents the grid side length of the region, ρ low =μ ρ -σ ρ , ρ high =μ ρ +σ ρ , μ ρ represents the mean value of base station density in all regions, σ ρ Indicates the standard deviation of base station density in all regions.

11. The method for obtaining user grid trajectory according to claim 1, characterized in that: After the area where the user to be processed is located is rasterized to obtain a plurality of grids, the method for obtaining the user grid trajectory further includes: Confirming a boundary grid within the region; wherein the boundary of the boundary grid is composed of a region boundary and a grid boundary; Taking the boundary grid that meets the preset size condition as a candidate boundary grid; Calculating a second belonging probability that the candidate boundary grid belongs to each adjacent grid; The candidate boundary grid is integrated into the grid with the second highest belonging probability.

12. The method for acquiring user grid trajectory according to claim 11, characterized in that: The second belonging probability of the candidate boundary grid belonging to each adjacent grid is calculated: According to the first probability Second probability i∈[1,n] and the third probability One or more of the above, obtaining a second belonging probability that the candidate boundary grid belongs to each adjacent grid; Among them, L i is the overlapping boundary length of the candidate boundary grid and the adjacent i-th grid, L is the total overlapping boundary length of the candidate boundary grid and all adjacent grids; n is the number of adjacent grids of the candidate boundary grid, d i is the average distance between the base station in the candidate boundary grid and the center of the adjacent i-th grid, ρ is the base station density in the candidate boundary grid, and ρ i is the density of base stations in the i-th grid adjacent to the candidate boundary grid, σ is the Gaussian kernel parameter; cnt i It means that there are cnt base stations in the base station set A in its adjacent i-th grid, card(A) represents the number of elements in the base station set A, and the base station set A is obtained by counting the N base stations before and after the base station in the candidate boundary grid passing through several historical user trajectory sequences.

13. A user grid trajectory acquisition device, characterized in that: include: A grid division module is used to perform grid processing on the area where the user to be processed is located to obtain a number of grids; A historical data acquisition module, used to acquire historical MDT data of the area and historical user trajectory data of the area; A connection probability calculation module, used to calculate the connection probability of the historical user equipment with each base station at each grid according to the historical MDT data and the historical user trajectory data; The grid track acquisition module is used to obtain the candidate grid to which the user equipment connected to each base station in the base station sequence belongs according to the base station sequence to which the user equipment of the user to be processed is connected and the connection probability, so as to form the grid track of the user to be processed.

14. A user grid trajectory acquisition device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the method for acquiring a user grid trajectory according to any one of claims 1 to 12 is implemented.

15. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program; wherein, when the computer program is run, it controls the device where the computer-readable storage medium is located to execute the user grid trajectory acquisition method according to any one of claims 1 to 12.

16. A computer program product, characterized in that The method comprises a computer program / instruction, which, when executed by a processor, implements the method for acquiring user grid tracks as claimed in any one of claims 1 to 12.

Images