A space division method, apparatus, device, and medium

Abstract

Embodiments of the present application disclose a space division method, comprising: obtaining a first space division of a target area, the first space division dividing the target area into a plurality of sub-areas; obtaining at least one user attribute data in the target area, the user attribute data being used for recording movement of a user in the target area; and adjusting the sub-areas divided by the first space division according to the user attribute data to obtain a second space division. The present application also provides a device, a terminal and a medium, which can input user attribute data based on the first space division of the target area, adjust the first space division of the target area according to the user attribute data, and finally form a space division result superimposed with space and crowd migration attributes. Compared with a traditional single-dimensional space division mode, the present application comprehensively considers both space and crowd migration, thereby realizing a more scientific space division result.

Description

TECHNICAL FIELD

[0001] The present application relates to the electronic field, and particularly to a space division method, device, equipment and medium. BACKGROUND

[0002] When performing network planning optimization, an operator needs to divide a city into a plurality of grid units (i.e., micro grids) according to certain rules, perform grid management, realize accurate planning optimization, and thus improve revenue and reduce cost. The micro grid is the smallest block unit of the basic network planning of the whole business of the telecom, and is also the source of user business demand. It is the basis for network basic resource demand calculation, and generally has a coverage radius of 100-500 m, and has different shapes and sizes, which can be a school, a central business district (CBD), or a residential area, etc.

[0003] In the prior art, the division of space is only based on objective static properties of geographical space, such as road network, rivers, buildings, and population, etc. However, these are based on spatial dimension data that does not change, and cannot adapt to the dynamic migration of the active population, and thus the current space division method cannot meet the ideal requirements.

[0004] Therefore, the above problems in the prior art still need to be solved. SUMMARY

[0005] The embodiments of the present application provide a space division method, device, equipment and medium, which can adjust the space division according to the dynamic migration information of the population.

[0006] The first aspect of the embodiments of the present application provides a space division method, comprising: obtaining a first space division of a target area, the first space division dividing the target area into a plurality of sub-regions; obtaining at least one user attribute data in the target area, the user attribute data being used to record the movement of the user in the target area; adjusting the sub-regions divided by the first space division according to the user attribute data, to obtain a second space division.

[0007] In the embodiments, based on the first space division of the target area, the user attribute data is input, the first space division of the target area is adjusted according to the user attribute data, and finally the space division result superimposed with the space and the population migration attribute is formed. Compared with the traditional single dimension space division method, the space and the population migration are comprehensively considered, and thus a more scientific division result is realized.

[0008] Optionally, the obtaining the first spatial division of the target region comprises: dividing the target region to obtain a plurality of sub-regions; constructing an adjacency matrix according to the adjacency relationship of the sub-regions, the adjacency matrix being used to record the adjacency of each sub-region in the target region; and the adjusting the sub-regions divided by the first spatial division according to the user attribute data to obtain a second spatial division comprises: merging at least two adjacent sub-regions in the adjacency matrix according to the user attribute data, merging a part of a sub-region into an adjacent sub-region, or splitting at least one sub-region, or deleting a part of the sub-region.

[0009] In this embodiment, the adjacency matrix relationship is constructed, and then the adjacency matrix relationship is adjusted based on the user attribute data, so that the spatial division result superimposed with the space and the crowd migration attribute is realized.

[0010] Optionally, the obtaining the at least one user attribute data in the target region comprises: obtaining the moving trajectories of each user in a first sub-region and a second sub-region, the first sub-region and the second sub-region being adjacent sub-regions; and the merging the at least two adjacent sub-regions in the adjacency matrix according to the user attribute data comprises: obtaining the total length of all user moving trajectories in the first sub-region and the second sub-region; obtaining the first user trajectory length that crosses the first sub-region and the second sub-region; and merging the first sub-region and the second sub-region when the proportion of the first user trajectory length in the total length is greater than or equal to a preset value.

[0011] In this embodiment, when the proportion of the first user trajectory length in the total length is greater than or equal to the preset value, it indicates that there are more users between the first sub-region and the second sub-region. According to the crowd migration situation, the first sub-region and the second sub-region should be a continuous region, so the first sub-region and the second sub-region can be merged into one sub-region, thereby realizing the adjustment of the first spatial division. On the basis of the division based on the space, the target region is divided more in line with the actual situation by considering the trajectory of the user flow between adjacent sub-regions.

[0012] Optionally, the obtaining the at least one user attribute data in the target region comprises: obtaining the residence time of each user in a first sub-region and a second sub-region, the first sub-region and the second sub-region being adjacent sub-regions; and the merging the at least two adjacent sub-regions in the adjacency matrix according to the user attribute data comprises: obtaining the total time of all user residence times in the first sub-region and the second sub-region; obtaining a target total time of users who have resided in the first sub-region and the second sub-region respectively; and merging the first sub-region and the second sub-region when the proportion of the target total time in the total time is greater than or equal to a preset value.

[0013] In this embodiment, when the proportion of the target total time length in the total time length is greater than or equal to the preset value, it indicates that there is more frequent user traffic between the first sub-region and the second sub-region. According to the crowd migration situation, the first sub-region and the second sub-region should be a continuous region, and therefore the first sub-region and the second sub-region can be merged into one sub-region, so as to realize the adjustment of the division of the first space. On the basis of the division based on the space, considering the user residence time length between adjacent sub-regions, the target region is divided more in line with the actual situation.

[0014] Optionally, the dividing the target region to obtain a plurality of sub-regions comprises: dividing the target region in the geographical space and the time space respectively to obtain a space-time network diagram, a vertical coordinate of the space-time network diagram is used to represent geographical position information of the sub-region, and a horizontal coordinate of the space-time network diagram is used to represent different time periods; after the obtaining the at least one user attribute data in the target region, the method further comprises: matching the at least one user attribute data in the target region to the space-time network diagram to obtain a space-time moving track of each user, and one point in the space-time moving track represents a geographical position where the user is located at a current time point; and the merging, according to the user attribute data, of at least two adjacent sub-regions in the adjacent matrix comprises: obtaining a target space-time moving track that crosses a first sub-region and a second sub-region in the space-time moving track, the first sub-region and the second sub-region being adjacent regions; and when the target space-time moving track that meets the preset condition reaches a target quantity, the first sub-region and the second region are merged.

[0015] In this embodiment, the space-time grid data based on part of the time dimension is used to evaluate the satisfaction degree of the crowd time-varying space distribution function. In the space-time grid network, when the target space-time moving track that meets the preset condition reaches a target quantity, the first sub-region and the second region are merged, which can accurately compare the correlation between adjacent sub-regions at different time points and space points, so as to more accurately adjust the merging between sub-regions. More scientific space division is realized.

[0016] Optionally, when the target spatio-temporal moving track meets the preset condition, the first sub-region and the second sub-region are merged, including: predicting the latter half track according to the former half track of the target spatio-temporal moving track in the first sub-region or the second sub-region to obtain a first prediction value, the first prediction value being a coincidence degree between a predicted value of the latter half track of the first sub-region or the second sub-region and an actual value of the latter half track of the first sub-region or the second sub-region; predicting the latter half track according to the former half track of the target spatio-temporal moving track to obtain a second prediction value, the second prediction value being a coincidence degree between a predicted value of the latter half track of the target spatio-temporal moving track and an actual value of the latter half track of the target spatio-temporal moving track; and when a ratio of the second prediction value to the first prediction value meets a preset value, the first sub-region and the second sub-region are merged.

[0017] In the embodiment, when the second prediction value is greater than the first prediction value, it is indicated that, in the same target spatio-temporal moving track, after merging, the prediction accuracy of the distribution function for the track meets the requirement. It can be judged that the activity habit of a user corresponding to the target spatio-temporal moving track across the first sub-region and the second sub-region meets the expectation of the distribution function, and the crossing activity of the user between the first sub-region and the second sub-region belongs to the normalized activity. Therefore, it can be judged that the first sub-region and the second sub-region should be merged into the same sub-region.

[0018] Optionally, the at least one user attribute data in the target region is obtained, including: obtaining a line graph of cell switching of a user in the target region, each line in the line graph representing a cell switched out and a cell switched in at two ends of the line, and a switching frequency between the cell switched out and the cell switched in being greater than or equal to a preset value; and the merging of a part of one sub-region into an adjacent sub-region includes: when a first line crossing two adjacent sub-regions appears in the line graph, merging the cells at two ends of the first line into the same sub-region.

[0019] In the embodiment, the switching conditions between each cell in the sub-region are accurately obtained through the line graph of cell switching, so that the detailed population migration conditions are understood, and the fine adjustment between the sub-regions is realized. More accurate regional division adjustment can be realized for the sub-regions.

[0020] Optionally, the deleting of part of the region in the sub-region according to the user attribute data includes: when a target cell in a first sub-region has no line between the target cell and other cells in the line graph, deleting the region where the target cell is located from the first sub-region, the first sub-region being one of the sub-regions in the target region.

[0021] In the embodiment, the switching conditions between each cell in the sub-region are accurately obtained through the line graph of cell switching, so that the detailed population migration conditions are understood, and the fine adjustment between the sub-regions is realized.

[0022] Optionally, after constructing the adjacency matrix according to the adjacency relationship of the sub-regions, the method further comprises: obtaining POI data of a first sub-region and a second sub-region, the first sub-region and the second sub-region being adjacent regions, the POI data being used to record geographical information of the first sub-region and the second sub-region; and merging the first sub-region and the second sub-region when a component similarity of the POI data of the first sub-region and the second sub-region is greater than or equal to a preset value.

[0023] In this embodiment, whether to merge the sub-regions is determined according to the POI data component similarity between adjacent sub-regions, so that adjustment of the spatial division is realized.

[0024] Optionally, the dividing the target region into a plurality of sub-regions comprises: dividing the target region into a plurality of sub-regions according to road network data.

[0025] In this embodiment, the geographical space of the target region can be divided by using the road network data.

[0026] The second aspect of the embodiments of the present application provides a spatial division device, comprising:

[0027] an obtaining unit, configured to obtain a first spatial division of a target region, the first spatial division dividing the target region into a plurality of sub-regions;

[0028] The obtaining unit is further configured to obtain at least one user attribute data in the target region, the user attribute data being used to record a movement of a user in the target region.

[0029] an executing unit, configured to adjust the sub-regions divided by the first spatial division according to the user attribute data, to obtain a second spatial division.

[0030] Optionally, the executing unit is further configured to:

[0031] divide the target region into a plurality of sub-regions;

[0032] construct an adjacency matrix according to an adjacency relationship of the sub-regions, the adjacency matrix being used to record an adjacency of each sub-region in the target region;

[0033] The adjusting the sub-regions divided by the first spatial division according to the user attribute data, to obtain a second spatial division, comprises:

[0034] merging at least two adjacent sub-regions in the adjacency matrix according to the user attribute data, merging a part of a sub-region into an adjacent sub-region, or splitting at least one sub-region, or deleting a part of the sub-region.

[0035] Optionally, the acquisition unit is further configured to:

[0036] acquire a moving trajectory of each user in the first sub-region and the second sub-region, the first sub-region and the second sub-region being adjacent sub-regions;

[0037] the execution unit is further configured to:

[0038] acquire a total length of moving trajectories of all users in the first sub-region and the second sub-region;

[0039] acquire a first user trajectory length spanning the first sub-region and the second sub-region;

[0040] merge the first sub-region and the second sub-region when the first user trajectory length accounts for a proportion of the total length greater than or equal to a preset value.

[0041] Optionally, the acquisition unit is further configured to:

[0042] acquire a residence duration of each user in the first sub-region and the second sub-region, the first sub-region and the second sub-region being adjacent sub-regions;

[0043] the execution unit is further configured to:

[0044] acquire a total duration of residence times of all users in the first sub-region and the second sub-region;

[0045] acquire a target total duration of users who have resided in the first sub-region and the second sub-region respectively;

[0046] merge the first sub-region and the second sub-region when the target total duration accounts for a proportion of the total duration greater than or equal to a preset value.

[0047] Optionally, the execution unit is further configured to:

[0048] divide the target region in geographical space and time space respectively to obtain a space-time network diagram, a vertical coordinate of the space-time network diagram being used to represent geographical position information of the sub-region, and a horizontal coordinate of the space-time network diagram being used to represent different time periods;

[0049] match at least one user attribute data in the target region to the space-time network diagram to obtain a space-time moving trajectory of each user, one point in the space-time moving trajectory representing a geographical position of the user at a current time point;

[0050] acquire a target space-time moving trajectory spanning the first sub-region and the second sub-region in the space-time moving trajectory, the first sub-region and the second sub-region being adjacent regions;

[0051] merge the first sub-region and the second region when the target spatio-temporal moving track meets a preset condition.

[0052] Optionally, the execution unit is further configured to:

[0053] predict the second half track of the target spatio-temporal moving track according to the first half track of the target spatio-temporal moving track, to obtain a second prediction value, the second prediction value being a coincidence degree between a prediction value of the second half track of the target spatio-temporal moving track and an actual value of the second half track of the target spatio-temporal moving track.

[0054] predict the second half track of the target spatio-temporal moving track according to the first half track of the target spatio-temporal moving track, to obtain a second prediction value, the second prediction value being a coincidence degree between a prediction value of the second half track of the target spatio-temporal moving track and an actual value of the second half track of the target spatio-temporal moving track.

[0055] merge the first sub-region and the second region when a ratio of the second prediction value to the first prediction value meets a preset value.

[0056] Optionally, the acquisition unit is further configured to:

[0057] acquire a connection diagram of cell handover of a user in a target region, each connection in the connection diagram representing a cell handover between a cell out and a cell in, and a handover frequency between the cell out and the cell in being greater than or equal to a preset value.

[0058] The execution unit is further configured to:

[0059] merge the first sub-region and the second region when a ratio of the second prediction value to the first prediction value meets a preset value.

[0060] Optionally, the execution unit is further configured to:

[0061] remove a region where a target cell in a first sub-region is located from the first sub-region when there is no connection between the target cell and other cells in the connection diagram, the first sub-region being one of the sub-regions in the target region.

[0062] Optionally, the execution unit is further configured to:

[0063] acquire POI data of a first sub-region and a second sub-region, the first sub-region and the second sub-region being adjacent regions, the POI data being used to record geographical information of the first sub-region and the second sub-region.

[0064] merge the first sub-region and the second region when a composition similarity of the POI data of the first sub-region and the second sub-region is greater than or equal to a preset value.

[0065] Optionally, the execution unit is further configured to:

[0066] According to the road network data, the target region is divided into a plurality of sub-regions.

[0067] The third aspect of the embodiments of the present application provides an electronic device, comprising: a processor and a memory, the memory is used for storing instructions; the processor is used for executing the steps of each implementation of the first aspect of the embodiments of the present application according to the instructions.

[0068] The fourth aspect of the embodiments of the present application provides a computer readable storage medium, comprising instructions, when the instructions run on the computer, make the computer execute the steps of each implementation of the first aspect of the embodiments of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0069] Figure 1 The schematic diagram of one embodiment of the space division method provided by the embodiments of the present application;

[0070] Figure 2 The schematic diagram of the first space division in the space division method provided by the embodiments of the present application;

[0071] Figure 3 The schematic diagram of another embodiment of the space division method provided by the embodiments of the present application;

[0072] Figure 4 The schematic diagram of another embodiment of the space division method provided by the embodiments of the present application;

[0073] Figure 5 The schematic diagram of another embodiment of the space division method provided by the embodiments of the present application;

[0074] Figure 6 The schematic diagram of another embodiment of the space division method provided by the embodiments of the present application;

[0075] Figure 7 The schematic diagram of another embodiment of the space division method provided by the embodiments of the present application;

[0076] Figure 8 The schematic diagram of another embodiment of the space division method provided by the embodiments of the present application;

[0077] Figure 9 The schematic diagram of another embodiment of the space division method provided by the embodiments of the present application;

[0078] Figure 10a The schematic diagram of another embodiment of the space division method provided by the embodiments of the present application;

[0079] Figure 10bFIG. 2 is a schematic diagram of another embodiment of the space division method provided by the embodiments of the present application;

[0080] Figure 11 FIG. 3 is a schematic diagram of an electronic device provided by the embodiments of the present application;

[0081] Figure 12 FIG. 4 is a schematic diagram of a space division device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0082] The embodiments of the present application provide a space division method, device, equipment and medium, which can adjust the space division according to the crowd dynamic migration information.

[0083] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application.

[0084] The terms "first", "second", and the like in the specification and claims of the present application and the above drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0085] When performing network planning optimization, an operator needs to divide a city into a plurality of grid units (i.e., micro grids) according to certain rules, perform grid management, realize accurate planning optimization, and thus improve the income and reduce the cost. Meanwhile, when performing commercial site selection, a retailer needs to consider the commercial value of a site, which includes but is not limited to the people flow rule of the site, commercial format, rent cost, etc. The method of space grid division can identify a high-value area in a city, so as to find a high-quality site selection area in the city. These needs require the division of a land plot.

[0086] Currently, there are two main ways to divide a region. One is to divide the region according to administrative regions, natural regions, road network structures, and customer distribution, etc. For example, a city area, a suburban county, a developed town, and other business-intensive areas are divided into multiple regions according to road networks, water flows, and other obstacles. Each region completes the aggregation and convergence of all services within the region, and realizes efficient and low-cost fusion bearing of services. The other is to divide a city region into multiple grids, calculate the people flow density of each grid, determine a core grid from the grids, the average people flow density of all grids in the density range of the core grid exceeds a predetermined density threshold, take one of the core grids as a starting point, and take all grids in the density range of the core grid as an initial grid cluster to obtain a final grid cluster, and take each final obtained grid cluster as a business district.

[0087] The first scheme only considers the objective geographical distribution, and the second scheme only considers the distribution of people flow density. Both only consider one dimension of information and cannot perform more dimensional analysis, resulting in an inability to achieve a more scientific and accurate spatial division method.

[0088] To solve the above problems, the embodiments of the present application provide a spatial division method which can consider geographical factors and people flow migration factors at the same time, and realize more scientific and reasonable spatial division. For ease of understanding, the method provided by the embodiments of the present application is described in detail below with reference to the drawings.

[0089] Please refer to Figure 1 As shown in the figure, one embodiment of the spatial division method provided by the embodiments of the present application includes the following steps. Figure 1

[0090] 101、Obtain a first spatial division of a target region.

[0091] In this embodiment, the target region is divided into multiple sub-regions to obtain the first spatial division. Specifically, the target region can be divided into multiple sub-regions through road network data. In a geographic information system, road network data includes administrative regions, natural regions, road network structures, and customer distribution, etc. A POI can be a house, a shop, a mailbox, a bus stop, etc. Thus, the division of the target region is realized according to geographical information.

[0092] Optionally, in order to realize the merging and splitting of the sub-regions in the subsequent work process, the adjacent relationship of the multiple sub-regions in the first spatial division needs to be recorded. The specific implementation is as follows: an adjacent matrix is constructed according to the adjacent relationship of the sub-regions, and the adjacent matrix is used to record the adjacent relationship of the sub-regions in the target region. For example, as shown in the figure, the target region is divided into nine sub-regions of ABCDEFGHI, and the adjacent matrix of the target region is shown in Table 1. Figure 2 ​​

[0093]

[0094] Table 1

[0095] As shown in the adjacent matrix of Table 1, the number 1 represents that the corresponding two sub-regions are adjacent regions, and the number 0 represents that the two sub-regions are not adjacent sub-regions. In this way, in the subsequent working process, the system can obtain the adjacent conditions of each sub-region in the target region through the adjacent matrix.

[0096] 102, Obtain at least one user attribute data in the target region.

[0097] In this embodiment, the user attribute data is used to record the movement of the user in the target region, so that the crowd migration in the target region can be known according to the user attribute data. Optionally, the user attribute data can be one or more of the following: 1, the movement trajectory of the user; 2, the residence time of the user in each sub-region; 3, the trajectory of the user in the space-time network of the target region; or 4, the connection diagram of the user in the target region.

[0098] 103, Adjust the sub-regions divided by the first space division according to the user attribute data to obtain a second space division.

[0099] In this embodiment, based on the first space division of the target region, the user attribute data is input, and the first space division of the target region is adjusted according to the user attribute data, and finally a space division result superimposed with space and crowd migration attributes is formed. Compared with the traditional single-dimensional space division method, the space and the crowd migration are considered comprehensively, so that a more scientific division result is realized.

[0100] Further, the specific implementation manner of the above step 103 is: merging at least two adjacent sub-regions in the adjacent matrix according to the user attribute data, or splitting at least one sub-region, or deleting part of the regions in the sub-region. In the specific working process, according to the different types of user attribute data, different ways are used to realize the second space division. For the convenience of understanding, the specific processing method under different user attribute data types is described in detail below in combination with the drawings.

[0101] I. The user attribute data is the movement trajectory of the user.

[0102] In this embodiment, please refer to Figure 3 and Figure 4 , which specifically include the following steps.

[0103] 301, Obtain the movement trajectory of each user in the first sub-region and the second sub-region.

[0104] In this embodiment, the first sub-region and the second sub-region are adjacent sub-regions, that is, in the above Table 1, the first sub-region and the second sub-region are any two adjacent sub-regions with a value of 1. The first sub-region and the second sub-region are two-dimensional plane graphs, each user is a point on the two-dimensional plane graph, and the path of movement forms the movement trajectory of each user. Alternatively, the movement trajectory data of each user includes user identification, time and location data, so that the movement trajectories of each user in the first sub-region and the second sub-region can be quantified by the three sets of data.

[0105] For example Figure 4 As shown, the first sub-region 401 and the second sub-region 402 are adjacent sub-regions, and the first sub-region 401 and the second sub-region 402 include three movement trajectories of A 41, B 42 and C 43. Then, the user identification, time and location data corresponding to A, B and C are obtained, respectively, so as to record the movement trajectories of each user in the first sub-region 401 and the second sub-region 402.

[0106] 302, obtain the total length of all user movement trajectories in the first sub-region and the second sub-region.

[0107] In this embodiment, the total length of all user movement trajectories in the first sub-region and the second sub-region is the sum of the lengths of each user moving in the first sub-region and the second sub-region, for example Figure 4 As shown, the sum of the lengths of the three movement trajectories of A 41, B 42 and C 43 is the total length of all user movement trajectories in the first sub-region 401 and the second sub-region 402.

[0108] 303, the first user trajectory length across the first sub-region and the second sub-region.

[0109] In this embodiment, the first sub-region and the second sub-region include a plurality of different movement trajectories, some of which only move in the first sub-region or the second sub-region, and some of which cross the first sub-region and the second sub-region. The first user trajectory length across the first sub-region and the second sub-region constitutes the migration between the two sub-regions, and these trajectories across the first sub-region and the second sub-region may affect the division of the sub-regions.

[0110] 304, calculate the proportion of the first user trajectory length to the total length.

[0111] In this embodiment, the first user trajectory length is the length of the user trajectory across the first sub-region and the second sub-region, and the total length is the sum of the lengths of all trajectories in the first sub-region and the second sub-region. By calculating this proportion, the proportion of users across the two regions in the first sub-region and the second sub-region can be known. For example Figure 4As shown, the sum of the lengths of the three moving tracks, i.e., the total length of all user moving tracks in the first sub-region 401 and the second sub-region 402, is the length of the track A 41 crossing the first sub-region 401 and the second sub-region 402, and the calculation of the proportion is as follows: (the length of the track A 41 / the total length of the three tracks A 41, B 42 and C 43).

[0112] 305、When the proportion of the length of the first user track to the total length is greater than or equal to a preset value, the first sub-region and the second sub-region are merged.

[0113] In this embodiment, when the proportion of the length of the first user track to the total length is greater than or equal to a preset value, it indicates that there are more users between the first sub-region and the second sub-region. According to the crowd migration situation, the first sub-region and the second sub-region should be a continuous region, and thus the first sub-region and the second sub-region can be merged into one sub-region, thereby realizing the adjustment of the division of the first space. On the basis of the division based on the space, the target region is divided in a manner more in line with the actual situation by considering the track situation of the user flow between adjacent sub-regions.

[0114] II. The user attribute data is the length of time that a user stays in each sub-region.

[0115] In this embodiment, please refer to Figure 5 As shown, the method specifically comprises the following steps.

[0116] 501. Obtain the length of time that each user in the first sub-region and the second sub-region stays.

[0117] In this embodiment, the first sub-region and the second sub-region are adjacent sub-regions. That is, in the above Table 1, the first sub-region and the second sub-region are any two adjacent sub-regions with a value of 1. The first sub-region and the second sub-region include multiple users, and each of these users stays in the first sub-region and the second sub-region for a period of time. The length of time that these users stay is obtained. Specifically, the user attribute data includes a user identifier and the length of time that each user identifier corresponds to a user stays.

[0118] 502. Obtain the total length of time that all users in the first sub-region and the second sub-region stay.

[0119] In this embodiment, the users in the first sub-region and the second sub-region include first-type users who only stay in the first sub-region, second-type users who only stay in the second sub-region, and third-type users who stay in both the first sub-region and the second sub-region for a long time. The total length of time T1 that the above three types of users stay is obtained.

[0120] 503、acquire the total time length of the target that has stayed in the first sub-region and the second sub-region respectively.

[0121] In this embodiment, the total time length of the target that has stayed in the first sub-region and the second sub-region respectively is the total time length t1 of the third type of user.

[0122] 504、calculate the proportion of the total time length of the target in the total time length.

[0123] In this embodiment, the total time length of the target is the total time length t1 of the third type of user, and the total time length is the total time length T1 of the three types of users. The t1 / T1 is calculated, and the proportion of the first sub-region and the second sub-region across the two regions is known.

[0124] 505、when the proportion of the total time length of the target in the total time length is greater than or equal to a preset value, merge the first sub-region and the second sub-region.

[0125] In this embodiment, when the proportion of the total time length of the target in the total time length is greater than or equal to a preset value, it indicates that there is frequent user traffic between the first sub-region and the second sub-region. According to the population migration situation, the first sub-region and the second sub-region should be a continuous region, so the first sub-region and the second sub-region can be merged into one sub-region, thereby realizing the adjustment of the division of the first space. Based on the division based on space, considering the user staying time length between adjacent sub-regions, the target region is divided more in line with the actual situation.

[0126] III. The user attribute data is the trajectory of the user in the spatio-temporal network of the target region.

[0127] In this embodiment, please refer to Figure 6 to Figure 8 as shown, specifically comprising the following steps.

[0128] Firstly, the acquisition method of the spatio-temporal network is introduced, and the construction method of the spatio-temporal network includes the following steps.

[0129] 601、divide the target region in geographical space and time space respectively to obtain a spatio-temporal network diagram.

[0130] In this embodiment, the ordinate of the spatio-temporal network diagram is used to represent the geographical position information of the sub-region, and the abscissa of the spatio-temporal network diagram is used to represent different time periods.

[0131] In the specific working process, firstly, the geographical space of the space place is discretized and processed, such as being evenly divided into 20m square grids (it can also be evenly divided into hexagonal shapes, etc.), which realizes the division of the target region in geographical space. Then, the grid discretization processing is performed in the time dimension, such as being evenly divided into 5-minute lengths. Thus, a spatio-temporal network diagram as shown inFigure 7 the space-time network diagram, Figure 7 In the space-time network diagram, the ordinate of each point is used to represent the geographical position information S of the sub-region, specifically including the coordinate information of the user in the target region, and the abscissa is used to represent different time points T, thereby forming a space-time grid of the target region in the space-time dimension.

[0132] 602. Match the at least one user attribute data in the target region to the space-time network diagram to obtain the space-time moving track of each user.

[0133] In this embodiment, the user attribute data is matched to the space-time network diagram to obtain coordinate points as shown in Figure 7 These coordinate points are connected together to form the space-time moving track of the user in the first sub-region 701 and the second sub-region 701. Each user in the target region corresponds to a space-time moving track of his own, and one point in the space-time moving track represents the geographical position of the user at the current time point.

[0134] Based on the steps shown in steps 601 to 602, the space-time network diagram obtained records the space-time moving tracks of all users in the target region, thereby obtaining the user attribute data. Based on these space-time moving tracks, the following steps are further performed to realize the adjustment of the sub-region division.

[0135] 603. Obtain target space-time moving tracks that cross the first sub-region and the second sub-region in the space-time moving tracks.

[0136] In this embodiment, the first sub-region and the second sub-region are adjacent regions, that is, in the above Table 1, the first sub-region and the second sub-region are any two adjacent sub-regions with a value of 1. In the first sub-region and the second sub-region, there are some target space-time moving tracks that cross the first sub-region and the second sub-region, and the tracks that meet the preset conditions are obtained from these target space-time moving tracks. The following steps are then performed.

[0137] 604. When the target space-time moving track meets the preset condition, merge the first sub-region and the second region.

[0138] In this embodiment, the method for judging whether the target space-time moving track meets the preset condition specifically includes the following steps.

[0139] 1. Predict the second half of the track according to the first half of the track of the target space-time moving track in the first sub-region or the second sub-region to obtain a first prediction value.

[0140] In this embodiment, the first prediction value is the coincidence degree of the predicted value of the second half of the track of the first sub-region or the second sub-region and the actual value of the second half of the track of the first sub-region or the second sub-region. For example, Figure 7As shown, for a target space-time moving track, the part of the target space-time moving track located in the first sub-region 701 is a first sub-track, and the part of the target space-time moving track located in the second sub-region 702 is a second sub-track. In a specific working process, the first sub-track can be taken to perform the above step 1, or the second sub-track can be taken to perform the above step 1. The embodiments of the present application do not limit this, and for the convenience of understanding, the first sub-track is taken to perform the above step 1 as an example for description.

[0141] It should be noted that the "first half" and "second half" in the step 1 and the following step 2 are not limited to 50%, and a person skilled in the art can arbitrarily allocate the proportion of the first half and the second half according to the needs, for example, the first half accounts for 80% of the total length, and the second half accounts for 20% of the total length. The specific implementation process is as follows Figure 8 As shown, the length of the first 80% of the first sub-track 81 is taken as the first half track 811. Based on the first half track, the prediction second half track 812 of the last 20% length of the first sub-track 81 is predicted by a distribution function. Then, in the Figure 8 The coincidence degree between the prediction second half track 812 and the actual second half track 813 is compared, and it is assumed that half of the coordinate points of the prediction second half track 812 coincide with the actual second half track 813. Then, the coincidence degree between the predicted value of the second half track of the first sub-track and the actual value is 50%, that is, the first predicted value is equal to 50%.

[0142] It should be noted that the above distribution function is any function in the prior art that can predict a track, and a person skilled in the art can select a suitable algorithm according to the actual needs, and the embodiments of the present application do not limit this.

[0143] Optionally, after the above step 1 is completed, the first sub-region and the second sub-region need to be merged first, and then the target space-time moving track crossing the first sub-region and the second sub-region in the merged sub-region is obtained to perform the following step 2. So as to determine whether the first sub-region and the second sub-region are really suitable for merging.

[0144] 2. The second predicted value is obtained by predicting the second half track of the target space-time moving track according to the first half track of the target space-time moving track.

[0145] In the embodiment, the second predicted value is the coincidence degree between the predicted value of the second half track of the target space-time moving track and the actual value of the second half track of the target space-time moving track. The target space-time moving track is a track crossing the first sub-region 801 and the second sub-region 802. As shown in Figure 8As shown, the first half of the target spatio-temporal moving track 82 is obtained as the first half track 821 with the length of 80% of the target spatio-temporal moving track 82. Based on the first half track 821, the second half track 822 is predicted with the length of 20% of the target spatio-temporal moving track 82 by the distribution function. Then, the coincidence degree between the second half track 822 and the actual second half track 823 is compared in the step 3. Figure 8 The coincidence degree between the predicted second half track 822 and the actual second half track 823 is 60% if there are 60% coordinate points coinciding between the predicted second half track 822 and the actual second half track 823, and the coincidence degree between the predicted second half track and the actual second half track is 60%, i.e., the second prediction value is equal to 60%.

[0146] It should be noted that the distribution function used in the step 1 and the step 2 is the same function.

[0147] 3. When the ratio of the second prediction value to the first prediction value is greater than a preset value, the first sub-region and the second sub-region are merged.

[0148] In the embodiment, when the ratio of the second prediction value to the first prediction value is greater than the preset value, for example, the second prediction value is greater than the first prediction value, and the ratio of the second prediction value to the first prediction value is greater than 100%, or the second prediction value is equal to 90% of the first prediction value, it is determined that the ratio of the second prediction value to the first prediction value is greater than the preset value. The specific ratio of the preset value can be set by those skilled in the art according to actual needs, and the embodiment of the present application is not limited thereto.

[0149] When the ratio of the second prediction value to the first prediction value is greater than the preset value, it is indicated that the prediction accuracy of the distribution function for the track meets the requirements in the same target spatio-temporal moving track. It can be determined that the activity habit of the user corresponding to the target spatio-temporal moving track across the first sub-region and the second sub-region meets the expectation of the distribution function, and the crossing activity of the user between the first sub-region and the second sub-region belongs to the normalized activity. Therefore, it can be determined that the first sub-region and the second sub-region should be merged into the same sub-region.

[0150] It should be noted that the target space-time movement trajectory involved in the above steps 1 to 3 can be a trajectory of a user in the space-time network. That is, there are multiple target space-time movement trajectories between the first sub-region and the second sub-region. Repeat the above steps 1 to 3 to calculate all target space-time movement trajectories in the first sub-region and the second sub-region that meet the preset condition. When the proportion of the target space-time movement trajectories that meet the preset condition to all space-time movement trajectories reaches a preset value, it is determined that the first sub-region and the second sub-region are merged. Alternatively, the target space-time movement trajectory involved in the above steps 1 to 3 can also be a trajectory in the space-time network obtained by fitting function according to all user movement data in the first sub-region and the second sub-region. That is, there is only one target space-time movement trajectory between the first sub-region and the second sub-region. The above steps 1 to 3 are performed on the target space-time movement trajectory to determine whether the first sub-region and the second sub-region need to be merged.

[0151] In this embodiment, the space-time grid data based on part of the time dimension is used to evaluate the satisfaction degree of the crowd time-varying space distribution function. In the space-time grid network, when the target space-time movement trajectory that meets the preset condition reaches the target number, the first sub-region and the second region are merged. The correlation between adjacent sub-regions at different time points and space points can be accurately compared, so that the merging between sub-regions can be more accurately adjusted. More scientific spatial division is achieved.

[0152] Four, the user attribute data is a connection diagram of cell switching of a user in a target region.

[0153] In this embodiment, please refer to Figure 9 and Figure 10a as shown, specifically comprising the following steps.

[0154] 901, obtaining a connection diagram of cell switching of a user in a target region.

[0155] In this embodiment, the cell can be a cell concept of a wireless cellular network, corresponding to Cell in English. The two ends of each connection in the connection diagram represent the cell switching out and the cell switching in, and the number of switching between the cell switching in and the cell switching in is greater than or equal to a preset value. The specific method is: according to the switching signaling data, find all wireless cells inside the space site which have a switching frequency greater than a certain threshold (for example, the threshold is 10 times of switching per hour) with the cell, establish the connection relationship of these cells in the wireless small area, that is, the above connection diagram. If the switching frequency between two cells is less than the threshold, no connection relationship is established. Alternatively, the switching signaling data can also be sorted according to the frequency, and the connection relationship diagram of the cells can be established according to the sorting, such as the top three cells in the sorting.

[0156] 902、When a first link across two adjacent sub-regions appears in the link graph, the cells at both ends of the first link are merged into the same sub-region.

[0157] In this embodiment, as shown in the figure, Figure 10a The target region is divided into four sub-regions, i.e., a first sub-region 1001, a second sub-region 1002, a third sub-region 1003, and a fourth sub-region 1004, based on the road network information. The first sub-region 1001 and the second sub-region 1002 are adjacent sub-regions. In the first sub-region 1001, a link graph is constructed in the above manner. It can be seen that one end of the link is connected to a first building 10011 in the first sub-region 1001 and the other end is connected to a second building 10021 in the second sub-region 1002. It can be known that the flow between the first building 10011 and the second building 10021 is frequently switched, which indicates that there is a large amount of population migration between the two buildings. Therefore, the cell where the second building 10021 is located is included in the range of the first sub-region 1001.

[0158] Through the above manner, although there is a certain amount of population migration between the first sub-region and the second sub-region, the migration is not large-scale and only occurs in the second building in the second sub-region. Therefore, the region where the second building is located is merged into the first sub-region, so as to realize fine adjustment of the division of the first sub-region and the second sub-region. The division of the space becomes more accurate and scientific.

[0159] Further, the step 902 describes the case of adding part of the region in the fine adjustment process. In the actual work process, part of the region can also be removed in the fine adjustment process. The specific steps include the following.

[0160] 903、When a target cell in the first sub-region has no link with other cells in the link graph, the region where the target cell is located is removed from the first sub-region.

[0161] In this embodiment, as shown in the figure, Figure 10a The first sub-region 1001 is one of the sub-regions in the target region. The target cell 10012 is one of the cells in the first sub-region 1001. It can be seen that there is a link between each of the cells in the first sub-region 1001, which indicates that there is a large amount of population migration between the buildings in the first sub-region 1001. The buildings indeed should be divided into the same sub-region. However, there is no link between the target cell 10012 and other cells in the first sub-region 1001, which indicates that there is no population migration between the target cell 10012 and other cells in the first sub-region 1001. Therefore, the region where the target cell 10012 is located is removed from the first sub-region 1001, so as to realize fine adjustment of the first sub-region 1001 and remove the part that does not belong to the first sub-region 1001.

[0162] In this embodiment, the handover details between each cell in a sub-region are accurately obtained through a cell handover diagram, thereby providing a detailed understanding of population migration and enabling fine-tuning between sub-regions. Compared to other methods provided in this application embodiment, this approach allows for more precise regional division and adjustment of sub-regions.

[0163] It should be noted that the above provides four methods for obtaining user attribute data. Based on the different types of user attribute data, the method provided in this application embodiment employs different methods to adjust the sub-regions within the target area. In the specific working process, after dividing the target area to obtain a first spatial division, the first spatial division can be further adjusted using point of information (POI) data. For ease of understanding, this method will be described in detail below with reference to the accompanying drawings.

[0164] Please see Figure 10b ,like Figure 10b As shown, another implementation method for further adjusting the first space division in this application embodiment includes the following steps.

[0165] 11. Obtain the Point of Interest (POI) data for the first and second sub-regions.

[0166] The first and second sub-regions are adjacent regions, meaning that in Table 1 above, the first and second sub-regions are any two adjacent sub-regions with a value of 1. POI data is used to record the geographic information of the first and second sub-regions. For example, a component in the POI data could be a house, a shop, a mailbox, a bus stop, or a school, etc. This step involves obtaining the POI information for the first and second sub-regions respectively.

[0167] 12. Compare the similarity between the POI data of the first sub-region and the POI data of the second sub-region.

[0168] In this embodiment, the POI data of the first sub-region and the second sub-region each have their own components. For example, the POI data of the first sub-region includes schools, stations and shops, while the POI data of the second sub-region includes schools, post offices and hospitals.

[0169] 13. When the similarity of POI data components between the first sub-region and the second sub-region is greater than or equal to a preset value, merge the first sub-region and the second sub-region.

[0170] In this embodiment, when the POI data component similarity of the first sub-region and the second sub-region is greater than or equal to a preset value, it indicates that the two sub-regions include a common part. For example, the POI data of the first sub-region includes 80 school type POIs, 10 station type POIs, and 10 shop type POIs. After theme analysis, it is determined that the region is of a school type as a main component, and the user is mainly a school activity related crowd. The second sub-region includes 90 school type POIs, 5 post office type POIs, and 5 hospital type POIs. After theme analysis, it is determined that the region is of a school type as a main component, and the user is mainly a school activity related crowd. Therefore, it can be determined that the activity related crowds between the first sub-region and the second sub-region are the same, that is, the POI data component similarity of the first sub-region and the second sub-region is greater than or equal to a preset value. The first sub-region and the second sub-region should be merged into one region.

[0171] In this embodiment, the components recorded by the POI data are used to adjust the region division, so that the adjustment of the first space division is realized according to the characteristics of the POI data.

[0172] The space division method provided in the embodiments of the present application includes: obtaining a first space division of a target region, the first space division dividing the target region into a plurality of sub-regions; obtaining at least one user attribute data in the target region, the user attribute data being used to record a movement of a user in the target region; and adjusting the sub-regions divided by the first space division according to the user attribute data to obtain a second space division. Compared with the traditional single dimension space division method, both the space and the crowd migration are considered, so that a more scientific space division is realized.

[0173] Optionally, the space division method provided in the embodiments of the present application can also be applied to the store site selection of the retail industry. The retail industry is called an "industry of site selection", and the key to success is "site selection, site selection, site selection". For an enterprise preparing to invest, the store site with the greatest investment potential can be determined through site selection analysis. For an enterprise that has already invested, the analysis result can be used to adjust the business strategy. The core of site selection is commercial district analysis. The commercial district here refers to the geographical area range of a retail store or its aggregation attracting customers. The above-mentioned space division method provided in the present application can realize more scientific division of the commercial district.

[0174] Further, the space division method provided in the embodiments of the present application can also be applied to other use scenarios that require space division, which is not limited in the embodiments of the present application.

[0175] From the hardware structure, the above-mentioned device management method can be implemented by one entity device, or can be implemented by multiple entity devices, or can be a logical functional module in one entity device, and the embodiments of the present application do not make specific limitations.

[0176] For example, the device management method described above can be implemented by an electronic device in Figure 11 . Figure 11 A hardware structure schematic diagram of an electronic device provided by an embodiment of the present application; the electronic device comprises at least one processor 1101, a communication line 1102, a memory 1103 and at least one communication interface 1104.

[0177] The processor 1101 can be a general central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of programs of the present application.

[0178] The communication line 1102 can include a path for transmitting information between the above-mentioned components.

[0179] The communication interface 1104 uses any transceiver-like device for communicating with other devices or communication networks, such as an Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc.

[0180] The memory 1103 can be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, a magnetic disk storage or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and that can be accessed by a computer, but not limited to. The memory can exist independently, and be connected to the processor through the communication line 1102. The memory can also be integrated with the processor.

[0181] The memory 1103 stores computer execution instructions for implementing the scheme of this application, and the execution is controlled by the processor 1101. The processor 1101 executes the computer execution instructions stored in the memory 1103, thereby implementing the billing management method provided in the following embodiments of this application.

[0182] Optionally, the computer execution instructions in the embodiments of this application may also be referred to as application code, and the embodiments of this application do not specifically limit this.

[0183] In a specific implementation, as one example, the processor 1101 may include one or more CPUs, for example... Figure 11 CPU0 and CPU1 in the CPU.

[0184] In a specific implementation, as one example, an electronic device may include multiple processors, for example... Figure 11 Processors 1101 and 1107 are mentioned. Each of these processors can be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. A processor here can refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0185] In a specific implementation, as one embodiment, the electronic device may further include an output device 1105 and an input device 1106. The output device 1105 communicates with the processor 1101 and can display information in various ways. For example, the output device 1105 may be a liquid crystal display (LCD), a light-emitting diode (LED) display device, a cathode ray tube (CRT) display device, or a projector, etc. The input device 1106 communicates with the processor 1101 and can receive user input in various ways. For example, the input device 1106 may be a mouse, keyboard, touchscreen device, or sensing device, etc.

[0186] The aforementioned electronic device can be a general-purpose device or a special-purpose device. In specific implementations, the electronic device can be a server, a wireless terminal device, an embedded device, or something else. Figure 11 Devices with similar structures. The embodiments of this application do not limit the type of electronic device.

[0187] The embodiments of the present application can divide the functional units of the electronic device according to the above method examples. For example, each functional unit can be divided according to each function, or two or more functions can be integrated in one processing unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit. It should be noted that the division of the units in the embodiments of the present application is illustrative, and is only a logical functional division. When actually implemented, another division manner can be used.

[0188] For example, in the case of dividing each functional unit in an integrated manner, Figure 12 A structural schematic diagram of a space division apparatus provided by an embodiment of the present application is shown.

[0189] As Figure 12 shown, the space division apparatus provided by the embodiment of the present application includes:

[0190] The obtaining unit 1201 is configured to obtain a first space division of a target region, the first space division dividing the target region into a plurality of sub-regions.

[0191] The obtaining unit 1201 is further configured to obtain at least one user attribute data in the target region, the user attribute data being used to record a movement of a user in the target region.

[0192] The execution unit 1202 is configured to adjust the sub-regions divided by the first space division according to the user attribute data, to obtain a second space division.

[0193] Optionally, the execution unit 1202 is further configured to:

[0194] divide the target region to obtain a plurality of sub-regions;

[0195] construct an adjacency matrix according to an adjacency relationship of the sub-regions, the adjacency matrix being used to record an adjacency of each sub-region in the target region;

[0196] The adjustment of the sub-regions divided by the first space division according to the user attribute data to obtain the second space division includes:

[0197] merging at least two adjacent sub-regions in the adjacency matrix according to the user attribute data, merging a part of one sub-region into an adjacent sub-region, or splitting at least one sub-region, or deleting a part of the sub-region.

[0198] Optionally, the obtaining unit 1201 is further configured to:

[0199] obtain each movement track in a first sub-region and a second sub-region, the first sub-region and the second sub-region being adjacent sub-regions;

[0200] The execution unit 1202 is further configured to:

[0201] obtain a total length of all user movement trajectories in the first sub-region and the second sub-region;

[0202] obtain a first user trajectory length across the first sub-region and the second sub-region;

[0203] merge the first sub-region and the second sub-region when the proportion of the first user trajectory length in the total length is greater than or equal to a preset value.

[0204] Optionally, the obtaining unit 1201 is further configured to:

[0205] obtain a length of time for each user to stay in a first sub-region and a second sub-region, the first sub-region and the second sub-region being adjacent sub-regions;

[0206] The execution unit 1202 is further configured to:

[0207] obtain a total length of all user stay times in the first sub-region and the second sub-region;

[0208] obtain a target total length of time for each user to stay in the first sub-region and the second sub-region respectively;

[0209] merge the first sub-region and the second sub-region when the proportion of the target total length in the total length is greater than or equal to a preset value.

[0210] Optionally, the execution unit 1202 is further configured to:

[0211] divide the target region in geographical space and time space respectively to obtain a space-time network diagram, a vertical coordinate of the space-time network diagram being used to represent geographical position information of the sub-region, and a horizontal coordinate of the space-time network diagram being used to represent different time periods;

[0212] match at least one user attribute data in the target region to the space-time network diagram to obtain a space-time movement trajectory of each user, one point in the space-time movement trajectory representing a geographical position of the user at a current time point;

[0213] obtain a target space-time movement trajectory across a first sub-region and a second sub-region in the space-time movement trajectory, the first sub-region and the second sub-region being adjacent regions;

[0214] merge the first sub-region and the second region when the target space-time movement trajectory meets a preset condition.

[0215] Optionally, a part of the target spatio-temporal moving track located in the first sub-region is a first sub-track, and a part of the target spatio-temporal moving track located in the second sub-region is a second sub-track; the execution unit 1202 is further configured to:

[0216] According to the target spatio-temporal moving track, a first predicted value is obtained by predicting a second half of the track according to a first half of the track in the first sub-region or the second sub-region, the first predicted value being a coincidence degree between a predicted value of the second half of the track in the first sub-region or the second sub-region and an actual value of the second half of the track in the first sub-region or the second sub-region;

[0217] According to the target spatio-temporal moving track, a second predicted value is obtained by predicting a second half of the track according to a first half of the track, the second predicted value being a coincidence degree between a predicted value of the second half of the track and an actual value of the second half of the track;

[0218] When a ratio of the second predicted value to the first predicted value satisfies a preset value, the first sub-region and the second sub-region are merged.

[0219] Optionally, the acquisition unit 1201 is further configured to:

[0220] The acquisition unit 1201 is further configured to acquire a connection diagram of cell switching of a user in a target region, each connection in the connection diagram having two ends representing a cell switched out and a cell switched in, and a switching frequency between the cell switched out and the cell switched in being greater than or equal to a preset value.

[0221] The execution unit 1202 is further configured to:

[0222] When a first connection spanning two adjacent sub-regions appears in the connection diagram, the cells at two ends of the first connection are merged into a same sub-region.

[0223] Optionally, the execution unit 1202 is further configured to:

[0224] When a target cell in a first sub-region has no connection with other cells in the connection diagram, a region where the target cell is located is deleted from the first sub-region, the first sub-region being one of the sub-regions in the target region.

[0225] Optionally, the execution unit 1202 is further configured to:

[0226] The execution unit 1202 is further configured to acquire information point (POI) data of a first sub-region and a second sub-region, the first sub-region and the second sub-region being adjacent regions, and the POI data being used to record geographical information of the first sub-region and the second sub-region.

[0227] When a component similarity of the POI data of the first sub-region and the second sub-region is greater than or equal to a preset value, the first sub-region and the second sub-region are merged.

[0228] Optionally, the execution unit 1202 is further configured to:

[0229] According to the road network data, the target region is divided into a plurality of sub-regions.

[0230] The embodiment of the present application further provides a computer readable storage medium, which comprises instructions, when the instructions are executed on a computer, the computer executes the method in the foregoing embodiment.

[0231] The terms "first", "second", "third", "fourth" and the like in the description and claims of the present application and above drawings are used to distinguish similar objects, and do not necessarily indicate a particular order or sequence. It should be understood that the data thus used can be interchanged, where appropriate, so that the embodiments described herein can be carried out in sequences other than those illustrated or described herein. Furthermore, the terms "comprise" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, processes, methods, systems, products, or devices that comprise a list of steps or units are not necessarily limited to those clearly listed, but can include other steps or units not clearly listed or inherent to such processes, methods, products, or devices.

[0232] In the present application, "at least one" refers to one or more, and "multiple" refers to two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple. In the present application, "A and / or B" includes A alone, B alone, and A+B.

[0233] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0234] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of the units is only a logical module division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0235] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or distributed on multiple network units. Part or all of the units can be obtained to achieve the purposes of the embodiments of the present application according to actual needs.

[0236] In addition, the modules in the various embodiments of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software module unit.

[0237] When the integrated unit is realized in the form of a software module unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0238] Those skilled in the art should realize that in the above one or more examples, the functions described in the present application can be realized by hardware, software, firmware or any combination thereof. When realized by software, these functions can be stored in a computer readable medium or transmitted as one or more instructions or codes on a computer readable medium. The computer readable medium includes a computer storage medium and a communication medium, wherein the communication medium includes any medium that facilitates the transmission of a computer program from one place to another. The storage medium can be any available medium that can be accessed by a general or special purpose computer.

[0239] The above specific embodiments further illustrate the purposes, technical solutions and beneficial effects of the present application. It should be understood that the above description is only a specific embodiment of the present application.

[0240] The above-described embodiments are only used to illustrate the technical solutions of the present application, but not limit the present application; although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A spatial partitioning method, characterized in that, include: Obtain a first spatial division of the target region, wherein the first spatial division divides the target region into multiple sub-regions; At least one user attribute data is obtained in the target area. The user attribute data is used to record the user's activities in the target area. The user attribute data includes one or more of the following: the user's movement trajectory, the duration of the user's stay in each sub-area, the user's trajectory in the spatiotemporal network of the target area, and the connection diagram of the user's cell handover in the target area. The sub-regions divided by the first spatial division are adjusted according to the user attribute data to obtain the second spatial division.

2. The method according to claim 1, characterized in that, The step of obtaining the first spatial division of the target region includes: The target region is divided into multiple sub-regions; An adjacency matrix is ​​constructed based on the adjacency relationships of the sub-regions, and the adjacency matrix is ​​used to record the adjacency of each sub-region in the target region. The step of adjusting the sub-regions divided by the first spatial division according to the user attribute data to obtain the second spatial division includes: Based on the user attribute data, merge at least two adjacent sub-regions in the adjacency matrix, merge a portion of a sub-region into an adjacent sub-region, or split at least one sub-region, or delete a portion of the sub-region.

3. The method according to claim 2, characterized in that, The step of obtaining at least one user attribute data in the target region includes: Obtain the movement trajectory of each user in the first sub-region and the second sub-region, wherein the first sub-region and the second sub-region are adjacent sub-regions; The step of merging at least two adjacent sub-regions in the adjacency matrix based on the user attribute data includes: Obtain the total length of all user movement trajectories in the first sub-region and the second sub-region; Obtain the length of the first user trajectory spanning the first sub-region and the second sub-region; When the proportion of the length of the first user trajectory to the total length is greater than or equal to a preset value, the first sub-region and the second sub-region are merged.

4. The method according to claim 2, characterized in that, The step of obtaining at least one user attribute data in the target region includes: Obtain the dwell time of each user in the first sub-region and the second sub-region, wherein the first sub-region and the second sub-region are adjacent sub-regions; The step of merging at least two adjacent sub-regions in the adjacency matrix based on the user attribute data includes: Obtain the total dwell time of all users in the first sub-region and the second sub-region; Obtain the target total duration of users who have resided in the first sub-region and the second sub-region respectively; When the proportion of the target total duration to the total duration is greater than or equal to a preset value, the first sub-region and the second sub-region are merged.

5. The method according to claim 2, characterized in that, The target region is divided into multiple sub-regions, including: The target area is divided into geographic space and temporal space to obtain a spatiotemporal network diagram. The vertical axis of the spatiotemporal network diagram is used to represent the geographic location information of the sub-regions, and the horizontal axis of the spatiotemporal network diagram is used to represent different time periods. After obtaining at least one user attribute data in the target region, the method further includes: At least one user attribute data in the target area is matched to the spatiotemporal network graph to obtain the spatiotemporal movement trajectory of each user. A point in the spatiotemporal movement trajectory represents the geographical location of the user at the current time point. The step of merging at least two adjacent sub-regions in the adjacency matrix based on the user attribute data includes: Obtain the target spatiotemporal movement trajectory that spans the first sub-region and the second sub-region, wherein the first sub-region and the second sub-region are adjacent regions; When the target spatiotemporal movement trajectory meets the preset conditions, the first sub-region and the second sub-region are merged.

6. The method according to claim 5, characterized in that, When the target spatiotemporal movement trajectory meets preset conditions, merging the first sub-region and the second sub-region includes: Based on the first half of the target's spatiotemporal movement trajectory in the first sub-region or the second sub-region, the second half of the trajectory is predicted to obtain a first predicted value. The first predicted value is the degree of overlap between the predicted value of the second half of the trajectory in the first sub-region or the second sub-region and the actual value of the second half of the trajectory in the first sub-region or the second sub-region. The second half of the target spatiotemporal movement trajectory is predicted based on the first half of the trajectory to obtain a second predicted value. The second predicted value is the degree of overlap between the predicted value of the second half of the target spatiotemporal movement trajectory and the actual value of the second half of the target spatiotemporal movement trajectory. When the ratio of the second predicted value to the first predicted value meets a preset value, the first sub-region and the second sub-region are merged.

7. The method according to claim 2, characterized in that, The step of obtaining at least one user attribute data in the target region includes: Obtain a connection diagram of cell handover performed by the user in the target area. The two ends of each connection diagram represent the cell leaving the cell and the cell entering the cell, respectively, and the number of handovers between the cells entering the cell is greater than or equal to a preset value. The process of merging a portion of a sub-region into an adjacent sub-region includes: When a first line spanning two adjacent sub-regions appears in the connection diagram, the cells at both ends of the first line are merged into the same sub-region.

8. The method according to claim 7, characterized in that, The step of deleting a portion of the sub-region based on the user attribute data includes: When a target cell in the first sub-region has no connection with other cells on the connection map, the region where the target cell is located is deleted from the first sub-region. The first sub-region is a sub-region of the target region, and the target cell is a cell of the first sub-region.

9. The method according to claim 2, characterized in that, The step of adjusting the sub-regions divided by the first spatial division according to the user attribute data to obtain the second spatial division includes: Acquire Point of Interest (POI) data for a first sub-region and a second sub-region, wherein the first sub-region and the second sub-region are adjacent regions, and the POI data is used to record the geographic information of the first sub-region and the second sub-region; When the similarity of POI data components between the first sub-region and the second sub-region is greater than or equal to a preset value, the first sub-region and the second sub-region are merged.

10. The method according to any one of claims 2 to 9, characterized in that, The target region is divided into multiple sub-regions, including: The target area is divided into multiple sub-areas based on road network data.

11. A spatial division device, characterized in that, include: An acquisition unit is used to acquire a first spatial division of a target region, wherein the first spatial division divides the target region into multiple sub-regions. The acquisition unit is further configured to acquire at least one user attribute data in the target area. The user attribute data is used to record the user's movement in the target area. The user attribute data includes one or more of the following: the user's movement trajectory, the duration of the user's stay in each sub-area, the user's trajectory in the spatiotemporal network of the target area, and the connection diagram of the user's cell handover in the target area. An execution unit is used to adjust the sub-regions divided by the first spatial division according to the user attribute data to obtain a second spatial division.

12. An electronic device, characterized in that, include: Processor and memory, The memory is used to store instructions; The processor is configured to execute the method as described in any one of claims 1 to 10 according to the instructions.

13. A computer-readable storage medium comprising instructions, characterized in that, When the instructions are executed on a computer, the computer performs the method as described in any one of claims 1 to 10.

Images