Method and apparatus for determining spatiotemporal association

Abstract

This invention provides a method and apparatus for determining spatiotemporal companion relationships, relating to the field of big data processing technology. The method includes: acquiring spatiotemporal companion serialized data of the target area based on regional communication data and regional environmental data of the target area within a preset period; acquiring at least one spatiotemporal companion derivation coefficient and a set of accompanying personnel corresponding to the at least one associated raster area within the target area and the spatiotemporal companion serialized data and the target path within the preset period; and determining personnel with association values ​​greater than a spatiotemporal companion threshold as spatiotemporal accompanying personnel in the target area. Therefore, this invention can solve the problems of inaccurate and inefficient spatiotemporal companion analysis in existing technologies due to complex analysis scenarios and large data volumes.

Description

Technical Field

[0001] This invention relates to the field of big data processing technology, and in particular to a method and apparatus for determining spatiotemporal co-occurrence relationships. Background Technology

[0002] Spatiotemporal accompaniment refers to being in the same area as a specific object within the same time period. Accompaniment relationship refers to the distance between two or more moving targets not exceeding a certain threshold within a certain period of movement. It can well explain the internal connections of groups and accurately identify personnel movement phenomena. Currently, when conducting spatiotemporal accompaniment relationship analysis, data is first collected and uploaded manually. However, the uploaded data is incomplete. Due to the huge amount of data required for spatiotemporal accompaniment analysis, manual data upload and analysis is inefficient. In addition, registering personnel at locations alleviates the difficulty of finding spatiotemporally accompanied individuals to some extent, but in relevant locations, it is generally necessary to arrange personnel to supervise and guide the scanning of QR codes. Finally, exposure interaction is determined by Bluetooth interaction of personnel's mobile terminals. Not everyone's mobile terminals have Bluetooth turned on, and this method also poses a certain degree of privacy exposure risk.

[0003] In spatiotemporal adjoint analysis, existing technologies suffer from inaccuracies and low efficiency due to the complexity of the scenarios and the large volume of data involved. Summary of the Invention

[0004] This invention provides a method and apparatus for determining spatiotemporal association relationships, in order to solve the problems of inaccurate and inefficient spatiotemporal association analysis caused by the complexity of the analysis scenario and the large amount of data in the prior art.

[0005] To solve the above-mentioned technical problems, the present invention is implemented as follows:

[0006] In a first aspect, embodiments of the present invention provide a method for determining spatiotemporal association relationships. The method includes: acquiring spatiotemporal association serialized data of the target area based on regional communication data and regional environmental data of the target area within a preset period, wherein the spatiotemporal association serialized data includes multiple raster data corresponding to multiple raster regions in the target area, the raster data includes regional personnel flow data corresponding to the raster regions within the preset period, and spatiotemporal association derivation coefficients corresponding to the raster regions; and determining at least one associated raster corresponding to a target path in the target area within the preset period based on the spatiotemporal association serialized data. The target region is defined as follows: At least one spatiotemporal accompanying derivative coefficient and a set of accompanying personnel corresponding to the at least one associated raster region are obtained, wherein the set of accompanying personnel includes the association value corresponding to each person; Persons whose association value is greater than a spatiotemporal accompanying threshold value are determined as spatiotemporal accompanying personnel in the target region, wherein the spatiotemporal accompanying threshold value is determined by a spatiotemporal accompanying prediction model based on the association value of the person within the preset period, the at least one spatiotemporal accompanying derivative coefficient corresponding to the at least one associated raster region, and the set of accompanying personnel. The spatiotemporal accompanying prediction model is trained based on actual accompanying data and sample data corresponding to the set of accompanying personnel.

[0007] Furthermore, the step of obtaining the spatiotemporal associated serialized data of the target area based on the regional communication data and regional environmental data of the target area within a preset period includes: determining the regional personnel flow data corresponding to each of the grid areas based on the location registration data of each location in the target area and the regional communication data; and determining multiple spatiotemporal associated derivative coefficients corresponding to the multiple grid areas based on the base station data in the regional communication data and the regional environmental data.

[0008] Furthermore, the regional communication data includes operator call data, wireless measurement report (MR) data, and WiFi access data of designated locations in the target area. The step of determining the corresponding regional population flow data within each of the grid areas in the preset period based on the location registration data of each location in the target area and the regional communication data includes: cleaning the data according to a preset format based on the operator call data, the MR data, the WiFi access data, and the location registration data to obtain the regional population flow data.

[0009] Further, determining multiple spatiotemporal associated derivative coefficients corresponding to the multiple grid regions based on base station data in the regional communication data and the regional environmental data includes: determining multiple base station correlation degrees for multiple grid regions based on base station distribution in the base station data and location information of the multiple grid regions; and determining the multiple spatiotemporal associated derivative coefficients based on the multiple base station correlation degrees and the regional environmental data.

[0010] Further, the step of obtaining at least one spatiotemporal associated derivative coefficient and a set of associated personnel corresponding to the at least one associated raster region within the target region in the preset period based on the spatiotemporal associated serialized data and the at least one associated raster region in the target region includes: obtaining the correction coefficient corresponding to the target path and the set of personnel corresponding to the at least one associated raster region; determining the association value of each person in the set of personnel based on the correction coefficient and the at least one spatiotemporal associated derivative coefficient corresponding to the at least one associated raster region, and generating the set of associated personnel.

[0011] Secondly, embodiments of the present invention further provide a spatiotemporal association determination device, the device comprising: a first acquisition module, configured to acquire spatiotemporal association serialized data of the target area based on regional communication data and regional environmental data of the target area within a preset period, wherein the spatiotemporal association serialized data includes multiple grid data corresponding to multiple grid areas in the target area, the grid data includes regional personnel flow data corresponding to the grid areas within the preset period, and spatiotemporal association derivation coefficients corresponding to the grid areas; a second acquisition module, configured to acquire spatiotemporal association serialized data and the target path corresponding to the target area within the preset period. If one associated raster region is missing, at least one spatiotemporal accompanying derivative coefficient and a set of accompanying personnel corresponding to the at least one associated raster region are obtained, wherein the set of accompanying personnel includes the association value corresponding to each person; a determination module is used to determine that the person whose association value is greater than the spatiotemporal accompanying threshold value is the spatiotemporal accompanying person in the target region, wherein the spatiotemporal accompanying threshold value is determined by a spatiotemporal accompanying prediction model based on the association value of the person in the preset period and at least one spatiotemporal accompanying derivative coefficient and the set of accompanying personnel corresponding to the at least one associated raster region, and the spatiotemporal accompanying prediction model is trained based on actual accompanying data and sample data corresponding to the set of accompanying personnel.

[0012] Further, the first acquisition module includes: a first determination submodule, used to determine the corresponding regional personnel flow data within each of the grid areas based on the location registration data of each location in the target area and the regional communication data; and a second determination submodule, used to determine multiple spatiotemporal associated derivative coefficients corresponding to the multiple grid areas based on the base station data in the regional communication data and the regional environmental data.

[0013] Furthermore, the regional communication data includes operator call data, wireless measurement report (MR) data, and WiFi access data of designated locations in the target area. The first determining submodule includes a data cleaning unit, used to clean the data according to a preset format based on the operator call data, the MR data, the WiFi access data, and the location registration data to obtain the regional personnel flow data.

[0014] Furthermore, the second determining submodule includes: a first determining unit, configured to determine the correlation degree of multiple base stations in multiple grid regions based on the base station distribution in the base station data and the location information of the multiple grid regions; and a second determining unit, configured to determine the multiple spatiotemporal associated derivative coefficients based on the correlation degree of the multiple base stations and the regional environmental data.

[0015] Further, the second acquisition module includes: a first acquisition submodule, used to acquire the correction coefficient corresponding to the target path and the personnel set corresponding to the at least one associated grid region; and a third determination submodule, used to determine the association value of each person in the personnel set based on the correction coefficient and at least one spatiotemporal associated derivative coefficient corresponding to the at least one associated grid region, and generate the accompanying personnel set.

[0016] Thirdly, embodiments of the present invention also provide an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the spatiotemporal association determination method as described in the first aspect.

[0017] Fourthly, embodiments of the present invention further provide a readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the spatiotemporal association determination method as described in the first aspect.

[0018] In this embodiment of the invention, spatiotemporal accompanying serialized data of the target area is obtained based on regional communication data and regional environmental data of the target area within a preset period. The spatiotemporal accompanying serialized data includes multiple grid data corresponding to multiple grid areas in the target area. The grid data includes regional personnel flow data corresponding to the grid areas within the preset period, and spatiotemporal accompanying derivation coefficients corresponding to the grid areas. Based on the spatiotemporal accompanying serialized data and at least one associated grid area corresponding to the target path within the preset period in the target area, at least one spatiotemporal accompanying derivation coefficient and a set of accompanying personnel corresponding to at least one associated grid area are obtained. The set of accompanying personnel includes the association value corresponding to each person. Persons with association values ​​greater than a spatiotemporal accompanying threshold are determined as spatiotemporally accompanying personnel in the target area. The spatiotemporal accompanying threshold is determined by a spatiotemporal accompanying prediction model based on the association value of the personnel within the preset period, at least one spatiotemporal accompanying derivation coefficient corresponding to at least one associated grid area, and the set of accompanying personnel. The spatiotemporal accompanying prediction model is trained based on actual accompanying data and sample data corresponding to the set of accompanying personnel.

[0019] In this embodiment, the spatiotemporal accompanying serialized data is used to determine the regional personnel flow data and spatiotemporal accompanying derivation coefficients in each grid area, making the location of personnel flow in the grid area more accurate. Then, based on the position of the associated grid area in the target area, the corresponding spatiotemporal accompanying derivation coefficients and the set of accompanying personnel are obtained. The spatiotemporal accompanying personnel are then filtered out using the spatiotemporal accompanying threshold value obtained through data iteration, improving the analysis accuracy of spatiotemporal accompanying correlation. This embodiment of the invention solves the problem of inaccurate and inefficient spatiotemporal accompanying analysis in the prior art due to the complexity of the analysis scenario and the large amount of data.

[0020] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0021] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart illustrating a method for determining spatiotemporal accompaniment relationships in an embodiment of the present invention;

[0023] Figure 2This is a schematic diagram of a spatiotemporal association determination device according to an embodiment of the present invention. Detailed Implementation

[0024] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] Example 1

[0026] According to embodiments of the present invention, a method for determining spatiotemporal adjoint relationships is provided, such as... Figure 1 As shown, the method may specifically include the following steps:

[0027] S102, based on the regional communication data and regional environmental data of the target area within a preset period, obtain the spatiotemporal sequential data of the target area.

[0028] Among them, the spatiotemporal accompanying serialized data includes multiple raster data corresponding to multiple raster regions in the target area. The raster data includes the regional personnel flow data corresponding to the raster regions within a preset period, as well as the spatiotemporal accompanying derivative coefficients corresponding to the raster regions.

[0029] In this embodiment, regional communication data includes, but is not limited to, base station data, operator call data, and wireless WiFi access data in the target area. Examples include base station cell access data and wireless MR (Measurement Report).

[0030] In one example, the data collected involves spatiotemporal correlation analysis of raw data, including: 2G / 3G / 4G / 5G base station data / operator call data, wireless MR data, registration by scanning a specific QR code (registration QR code scanning), wireless WiFi access data, building surface data, etc.

[0031] In practical applications, each person arriving in the target area is considered to have one or more terminal devices. The data generated by these terminal devices includes, but is not limited to, call data, MR (Mobile Location Services), and WiFi access data. In this embodiment, by acquiring regional communication data of the target area within a preset period, it is possible to obtain information on people who have visited or passed through the target area within that preset period, thereby enabling the statistical analysis of personnel in the target area within that preset period.

[0032] In this embodiment, the regional environmental data includes, but is not limited to, environmental information such as buildings, roads, and terrain of the target area.

[0033] In this embodiment, the target area is divided according to a pre-set grid area to obtain multiple grid areas. In this embodiment, the grid areas include, but are not limited to, square areas or pentagonal areas.

[0034] In one example, a 25m x 25m grid is constructed across the target area, with the grid covering 100% of the entire area, forming grid regions Grid1, Grid2, Grid3...Gridn.

[0035] The spatiotemporal association derivative coefficient for each grid area is determined by acquiring base station distribution and regional environmental data within the target area. This coefficient is used to identify the population correlation within that grid area. For example, the spatiotemporal association derivative coefficient is lower in areas with low population density and higher in areas with high population density.

[0036] S104. Based on the spatiotemporal accompanying serialized data and at least one associated grid region corresponding to the target path in the target region within a preset period, obtain at least one spatiotemporal accompanying derivative coefficient and a set of accompanying personnel corresponding to at least one associated grid region, wherein the set of accompanying personnel includes the association value corresponding to each person.

[0037] In this embodiment, the target path is the movement path or dwelling path of a specific object. The grid area through which the specific object passes or dwells is the associated grid area.

[0038] In specific application scenarios, the target path of a specific object is obtained by using the device communication data of that object and the registration information at a fixed position in the grid area.

[0039] In this embodiment, at least one spatiotemporal associated derivative coefficient and regional personnel flow data corresponding to at least one associated raster region of the target path are obtained in the spatiotemporal associated serialized data. Obtaining regional personnel flow data in the associated raster region through the spatiotemporal associated serialized data includes, but is not limited to, determining the personnel set based on the communication data of the terminal device.

[0040] Next, based on the spatiotemporal associated derivative coefficients corresponding to all associated raster regions, the associated values ​​corresponding to each person in the personnel set are obtained, thereby constructing the associated personnel set.

[0041] S106, determine the personnel whose correlation value is greater than the spatiotemporal accompaniment threshold as the spatiotemporal accompaniment personnel in the target area. The spatiotemporal accompaniment threshold is determined by the spatiotemporal accompaniment prediction model based on the correlation value of the personnel within a preset period, at least one spatiotemporal accompaniment derivative coefficient corresponding to at least one correlation grid area, and the set of accompaniment personnel. The spatiotemporal accompaniment prediction model is iteratively completed based on the actual accompaniment data and the sample data corresponding to the set of accompaniment personnel.

[0042] In this embodiment, a spatiotemporal association threshold value is determined by a spatiotemporal association prediction model based on the association value of personnel within a preset period, at least one spatiotemporal association derivative coefficient corresponding to at least one associated grid region, and the set of accompanying personnel.

[0043] In this embodiment, the actual accompanying data is sample data determined manually, such as sample data corresponding to confirmed spatiotemporal accompanying personnel or non-spatiotemporal accompanying personnel in the target area.

[0044] In this embodiment, while using actual accompanying data as training sample data, data from a certain number of accompanying personnel sets are selected as training sample data, and a portion of actual accompanying data is selected as validation data to train the spatiotemporal accompanying prediction model until the spatiotemporal accompanying model iterates to a preset number of times or the model converges.

[0045] After obtaining the spatiotemporal association threshold value through the spatiotemporal association prediction model, the set of accompanying personnel is filtered based on the spatiotemporal association threshold value. Specifically, personnel with association values ​​greater than the spatiotemporal association threshold value are selected as spatiotemporal accompanying personnel, who have an association relationship with the specific object corresponding to the target path.

[0046] Through the above embodiments, regional personnel flow data and spatiotemporal association derivative coefficients are determined in each grid area based on spatiotemporal associated serialized data. Then, the corresponding spatiotemporal association derivative coefficients and associated personnel sets are obtained based on the position of the associated grid area in the target area. Finally, spatiotemporal associated personnel are filtered out based on the spatiotemporal association threshold value obtained through data iteration. This invention solves the problem of inaccurate and inefficient spatiotemporal association analysis in existing technologies due to the complexity of the analysis scenario and the large amount of data.

[0047] Optionally, in this embodiment, spatiotemporal serialized data of the target area is obtained based on the regional communication data and regional environmental data of the target area within a preset period, including but not limited to: determining the regional personnel flow data corresponding to each grid area based on the location registration data and regional communication data of each location in the target area; and determining multiple spatiotemporal serialized derivative coefficients corresponding to multiple grid areas based on the base station data and regional environmental data in the regional communication data.

[0048] In this embodiment, by acquiring regional communication data of the target area within a preset period, it is possible to obtain the visitors or passersby of the target area within the preset period.

[0049] In addition, the number of people visiting a location can be obtained by acquiring the location registration data for each venue in the target area. Specific registration methods include, but are not limited to: scanning the QR code displayed by the target venue, or clicking the corresponding link to register online.

[0050] The above two methods are used to obtain the regional population flow data corresponding to each grid area within a preset period.

[0051] In practical applications, the distribution of base stations is positively correlated with population density. Therefore, in this embodiment, the population density corresponding to the grid area is determined based on base station data and regional environmental data in the regional communication data, and then the spatiotemporal associated derivative coefficient corresponding to the grid area is determined.

[0052] For example, based on the base station distribution in the base station data of the target area, the correlation between the grid area and its neighboring base stations is determined. Furthermore, the correlation is further optimized based on the regional environmental data of the target area to obtain the spatiotemporal associated derivative coefficient.

[0053] Using the above example, based on base station data and regional environmental data in the regional communication data, the spatiotemporal associated derivative coefficients corresponding to the grid region are determined, and the correlation between the grid region and spatial characteristics is determined.

[0054] Optionally, in this embodiment, the regional communication data includes operator call data, wireless measurement report (MR) data, and WiFi access data of designated locations in the target area. The regional personnel flow data corresponding to each grid area within a preset period is determined based on the location registration data of each location in the target area and the regional communication data. This includes, but is not limited to, cleaning the data according to a preset format based on the operator call data, MR data, WiFi access data, and location registration data to obtain the regional personnel flow data.

[0055] In some examples of this embodiment, registration information, operator call data, MR data, and Wi-Fi access data are normalized, and the above data are cleaned according to data type, unique personnel identifier, timestamp, longitude, latitude, IP address, MAC address, etc., to obtain regional personnel flow data of the grid area.

[0056] Optionally, in this embodiment, multiple spatiotemporal associated derivative coefficients corresponding to multiple grid regions are determined based on base station data and regional environmental data in the regional communication data, including but not limited to: determining multiple base station correlation degrees of multiple grid regions based on base station distribution in the base station data and location information of multiple grid regions; and determining multiple spatiotemporal associated derivative coefficients based on multiple base station correlation degrees and regional environmental data.

[0057] In this embodiment, the base station correlation degree between the grid area and the adjacent base stations is determined based on the base station distribution and the location information of the grid area.

[0058] Specifically, the base station correlation between a grid area and its neighboring base stations can be obtained in the following ways:

[0059] S11, construct a full 25m*25m grid in the target area, with the grid covering 100% of the entire area, forming grid regions Grid1, Grid2, Grid3...Gridn;

[0060] S12, wireless base stations are distributed according to latitude and longitude, and the base stations form several discrete points in space. A circular area is formed by buffering outwards according to the distance t of each base station. There will be intersections of the buffer distances t of different base stations. The polygon formed by connecting the intersections is used to construct the Thiessen polygon grid of the base station.

[0061] S13, the constructed Thiessen polygon grid is superimposed on the grid to obtain the correlation relationship of the base station distribution corresponding to the grid. A threshold x is set according to the ratio of the overlapping area. If the overlapping area is greater than the threshold x, it is a high correlation with a corresponding correlation coefficient a. If the overlapping area is less than the threshold x, it is a low correlation with a correlation coefficient b. The grid data carrying base station information Grid1{cell1[a],cell2[b]}, Grid2{cell3[a],cell4[b]}, ... is output.

[0062] The correlation between multiple base stations in multiple grid areas is determined using the above method.

[0063] Then, based on the correlation between multiple base stations and regional environmental data, multiple spatiotemporal associated derivative coefficients are determined, which may include the following steps:

[0064] S21, overlay and analyze the different types of layer data such as buildings, public areas, green spaces, roads, and mountains in the map data with raster data, generate the spatiotemporal associated derivative coefficient m (0≤m≤10) based on the density of people gathering in different places, and output a list of raster areas and spatial characteristics associated with each other.

[0065] S22, Based on the list of raster regions and spatial characteristics output from the above steps, a raster is associated with multiple types of layers. At this time, the spatiotemporal co-derivative coefficient M of the raster is... ;

[0066] S23, Spatial overlay analysis is performed on the time-series data and raster data from the above steps to output spatiotemporal accompanying sequence data with raster granularity.

[0067] Optionally, in this embodiment, based on the spatiotemporal accompanying serialized data and at least one associated raster region corresponding to the target path within a preset period in the target region, at least one spatiotemporal accompanying derivative coefficient and an accompanying personnel set corresponding to at least one associated raster region are obtained, including but not limited to: obtaining the correction coefficient corresponding to the target path and the personnel set corresponding to at least one associated raster region; determining the association value of each person in the personnel set based on the correction coefficient and at least one spatiotemporal accompanying derivative coefficient corresponding to at least one associated raster region, and generating the accompanying personnel set.

[0068] In specific application scenarios, a correction coefficient is set for the specific location of a particular object on the target path within the associated grid region. Based on this correction coefficient, the spatiotemporal accompaniment value for each person in the accompanying personnel set is determined. Optionally, the specific location can be selected based on the length of time the specific object resides.

[0069] In one example of this embodiment, the process of determining the set of accompanying people in the associated grid region may specifically include the following steps:

[0070] S31, within a preset period, detect specific objects that have been identified through the spatiotemporal association of the grid. Taking a single detection as an example, it is known that the specific object passes through grids G1, G2, and G3, and its spatiotemporal association derivative coefficients are M1, M2, and M3, respectively.

[0071] S32, based on the grid-granular spatiotemporal serialized data output from the above steps, associate grids G1, G2, and G3 with the personnel sets S1, S2, and S3 within the nearest time period T; based on the carrier call data and WiFi access records of a specific object, it can be determined that the specific object is a fixed indoor person, and at this time, a correction coefficient N (0≤N≤1) is given;

[0072] S33, using the unique identifier of the personnel as the granularity, calculate the spatiotemporal association value Z of each personnel relative to the event in step 201), and the calculation method is as follows: .

[0073] Using the above method, based on the correction coefficient corresponding to a specific object and at least one spatiotemporal associated derivative coefficient corresponding to at least one associated raster region, the association value of each person in the personnel set is determined, and an accompanying personnel set is generated, which is denoted as Sm.

[0074] It should be noted that, in this embodiment, spatiotemporal accompanying serialized data of the target area is obtained based on the regional communication data and regional environmental data of the target area within a preset period. This spatiotemporal accompanying serialized data includes multiple raster data corresponding to multiple raster regions in the target area. The raster data includes regional personnel flow data corresponding to the raster regions within the preset period, and spatiotemporal accompanying derivation coefficients corresponding to the raster regions. Based on the spatiotemporal accompanying serialized data and at least one associated raster region corresponding to the target path within the preset period in the target area, at least one spatiotemporal accompanying derivation coefficient and a set of accompanying personnel corresponding to at least one associated raster region are obtained. The set of accompanying personnel includes the association value corresponding to each person. Persons with association values ​​greater than a spatiotemporal accompanying threshold are determined as spatiotemporally accompanying personnel in the target area. The spatiotemporal accompanying threshold is determined by a spatiotemporal accompanying prediction model based on the association value of the personnel within the preset period, at least one spatiotemporal accompanying derivation coefficient corresponding to at least one associated raster region, and the set of accompanying personnel. The spatiotemporal accompanying prediction model is trained based on actual accompanying data and sample data corresponding to the set of accompanying personnel. In this embodiment, the regional personnel flow data and spatiotemporal association derivation coefficients are determined in each grid area based on the spatiotemporal association serialized data. Then, the corresponding spatiotemporal association derivation coefficients and accompanying personnel sets are obtained according to the position of the associated grid area in the target area. Finally, spatiotemporal association personnel are filtered out based on the spatiotemporal association threshold value obtained through data iteration. This embodiment of the invention solves the problem of inaccurate and inefficient spatiotemporal association analysis caused by complex analysis scenarios and large data volumes in the prior art.

[0075] Example 2

[0076] This invention provides a detailed description of a spatiotemporal association determination device according to an embodiment of the present invention.

[0077] Reference Figure 2 The diagram shows a schematic representation of the spatiotemporal association determination device in an embodiment of the present invention.

[0078] The spatiotemporal association determination device of this invention includes: a first acquisition module 20, a second acquisition module 22, and a determination module 24.

[0079] The functions of each module and the interaction between them are described in detail below.

[0080] The first acquisition module 20 is used to acquire spatiotemporal associated serialized data of the target area based on the regional communication data and regional environmental data of the target area within a preset period. The spatiotemporal associated serialized data includes multiple grid data corresponding to multiple grid areas in the target area. The grid data includes regional personnel flow data corresponding to the grid areas within the preset period, and spatiotemporal associated derivative coefficients corresponding to the grid areas.

[0081] The second acquisition module 22 is used to acquire at least one spatiotemporal associated derivative coefficient and a set of associated personnel corresponding to the at least one associated raster region in the target region within the preset period, based on the spatiotemporal associated serialized data and at least one associated raster region in the target region. The set of associated personnel includes the associated values ​​corresponding to each person.

[0082] The determination module 24 is used to determine that the personnel whose correlation value is greater than the spatiotemporal accompaniment threshold value are the spatiotemporal accompaniment personnel in the target area. The spatiotemporal accompaniment threshold value is determined by the spatiotemporal accompaniment prediction model based on the correlation value of the personnel in the preset period, at least one spatiotemporal accompaniment derivative coefficient corresponding to at least one correlation grid area, and the set of accompaniment personnel. The spatiotemporal accompaniment prediction model is trained based on actual accompaniment data and sample data corresponding to the set of accompaniment personnel.

[0083] Optionally, in this embodiment, the first acquisition module 20 includes:

[0084] The first determining submodule is used to determine the corresponding regional personnel flow data within each of the grid areas based on the location registration data of each location in the target area and the communication data.

[0085] The second determining submodule is used to determine multiple spatiotemporal associated derivative coefficients corresponding to the multiple grid regions based on the base station data in the communication data and the regional environment data.

[0086] Optionally, in this embodiment, the communication data includes carrier call data, wireless measurement report (MR) data, and WiFi access data of a designated location in the target area, wherein the first determining submodule includes:

[0087] The data cleaning unit is used to clean the data according to a preset format based on the operator call data, the MR data, the WiFi access data, and the location registration data to obtain the population flow data of the area.

[0088] Optionally, in this embodiment, the second determining submodule includes:

[0089] The first determining unit is used to determine the correlation degree of multiple base stations in multiple grid areas based on the base station distribution in the base station data and the location information of the multiple grid areas;

[0090] The second determining unit is used to determine the multiple spatiotemporal associated derivative coefficients based on the correlation degree of the multiple base stations and the regional environmental data.

[0091] Optionally, in this embodiment, the second acquisition module 22 includes:

[0092] The first acquisition submodule is used to acquire the correction coefficient corresponding to the target path and the personnel set corresponding to the at least one associated grid area;

[0093] The third determining submodule is used to determine the association value of each person in the personnel set based on the correction coefficient and at least one spatiotemporal associated derivative coefficient corresponding to the at least one associated raster region, and to generate the accompanying personnel set.

[0094] Furthermore, in this embodiment of the invention, the regional population flow data and spatiotemporal association derivative coefficients in each grid region are determined based on the spatiotemporal association serialized data. Then, the corresponding spatiotemporal association derivative coefficients and the set of accompanying personnel are obtained based on the position of the associated grid region in the target region. Finally, the spatiotemporal association personnel are selected based on the spatiotemporal association threshold value obtained through data iteration. This embodiment of the invention solves the problem of inaccurate and inefficient spatiotemporal association analysis in the prior art due to the complexity of the analysis scenario and the large amount of data.

[0095] Example 3

[0096] Preferably, embodiments of the present invention also provide an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the spatiotemporal association determination method as described above.

[0097] Optionally, in this embodiment, the memory is configured to store program code for performing the following steps:

[0098] S1. Based on the regional communication data and regional environmental data of the target area within a preset period, obtain the spatiotemporal accompanying serialized data of the target area. The spatiotemporal accompanying serialized data includes multiple grid data corresponding to multiple grid areas in the target area. The grid data includes regional personnel flow data corresponding to the grid areas within the preset period, and the spatiotemporal accompanying derivative coefficients corresponding to the grid areas.

[0099] S2, based on the spatiotemporal accompanying serialized data and at least one associated grid region in the target region corresponding to the target path within the preset period, obtain at least one spatiotemporal accompanying derivative coefficient and an accompanying personnel set corresponding to the at least one associated grid region, wherein the accompanying personnel set includes the association value corresponding to each person.

[0100] S3, determine the personnel whose correlation value is greater than the spatiotemporal accompaniment threshold as spatiotemporal accompaniment personnel in the target area, wherein the spatiotemporal accompaniment threshold is determined by the spatiotemporal accompaniment prediction model based on the correlation value of the personnel in the preset period, at least one spatiotemporal accompaniment derivative coefficient corresponding to the at least one correlation grid area, and the set of accompaniment personnel. The spatiotemporal accompaniment prediction model is iteratively completed based on actual accompaniment data and sample data corresponding to the set of accompaniment personnel.

[0101] Optionally, specific examples in this embodiment can refer to the examples described in Embodiment 1 above, and will not be repeated here.

[0102] Example 4

[0103] Embodiments of the present invention also provide a readable storage medium. Optionally, in this embodiment, the readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the spatiotemporal association determination method as described in Embodiment 1.

[0104] Optionally, in this embodiment, the readable storage medium is configured to store program code for performing the following steps:

[0105] S1. Based on the regional communication data and regional environmental data of the target area within a preset period, obtain the spatiotemporal accompanying serialized data of the target area. The spatiotemporal accompanying serialized data includes multiple grid data corresponding to multiple grid areas in the target area. The grid data includes regional personnel flow data corresponding to the grid areas within the preset period, and the spatiotemporal accompanying derivative coefficients corresponding to the grid areas.

[0106] S2, based on the spatiotemporal accompanying serialized data and at least one associated grid region in the target region corresponding to the target path within the preset period, obtain at least one spatiotemporal accompanying derivative coefficient and an accompanying personnel set corresponding to the at least one associated grid region, wherein the accompanying personnel set includes the association value corresponding to each person.

[0107] S3, determine the personnel whose correlation value is greater than the spatiotemporal accompaniment threshold as spatiotemporal accompaniment personnel in the target area, wherein the spatiotemporal accompaniment threshold is determined by the spatiotemporal accompaniment prediction model based on the correlation value of the personnel in the preset period, at least one spatiotemporal accompaniment derivative coefficient corresponding to the at least one correlation grid area, and the set of accompaniment personnel. The spatiotemporal accompaniment prediction model is iteratively completed based on actual accompaniment data and sample data corresponding to the set of accompaniment personnel.

[0108] Optionally, in this embodiment, the aforementioned readable storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0109] Optionally, specific examples in this embodiment can refer to the examples described in Embodiment 1 above, and will not be repeated here.

[0110] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0111] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0112] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of the present invention.

[0113] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0114] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0115] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0116] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0117] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0118] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0119] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method of determining a spacetime relationship, characterized by, The method comprises: According to the regional communication data and the regional environment data of the target area in a preset period, obtain the space-time accompanying serialized data of the target area, wherein the space-time accompanying serialized data comprises a plurality of grid data corresponding to a plurality of grid regions in the target area, the grid data comprises corresponding regional personnel flow data in the grid region in the preset period, and the grid region corresponds to a space-time accompanying derivative coefficient; wherein the space-time accompanying derivative coefficient can identify the personnel correlation degree of the grid region; According to the space-time accompanying serialized data and at least one associated grid region corresponding to a target path in the target area in the preset period, obtain at least one space-time accompanying derivative coefficient and an accompanying personnel set corresponding to the at least one associated grid region, wherein the accompanying personnel set comprises an associated value corresponding to each personnel; Determine the personnel with an associated value greater than a space-time accompanying threshold value as a space-time accompanying personnel in the target area, wherein the space-time accompanying threshold value is determined by a space-time accompanying prediction model according to the associated value of the personnel in the preset period, at least one space-time accompanying derivative coefficient corresponding to the at least one associated grid region, and an accompanying personnel set, and the space-time accompanying prediction model is iteratively completed according to actual accompanying data and sample data corresponding to the accompanying personnel set; The method comprises: According to the regional communication data and the regional environment data of the target area in a preset period, obtain the space-time accompanying serialized data of the target area, wherein the space-time accompanying serialized data comprises a plurality of grid data corresponding to a plurality of grid regions in the target area, the grid data comprises corresponding regional personnel flow data in the grid region in the preset period, and the grid region corresponds to a space-time accompanying derivative coefficient; wherein the space-time accompanying derivative coefficient can identify the personnel correlation degree of the grid region; According to the base station data in the regional communication data and the regional environment data, determine a plurality of space-time accompanying derivative coefficients corresponding to the plurality of grid regions; The method comprises: Obtain a correction coefficient corresponding to the target path and a personnel set corresponding to the at least one associated grid region; According to the correction coefficient, at least one space-time accompanying derivative coefficient corresponding to the at least one associated grid region, determine the associated value of each personnel in the personnel set, and generate the accompanying personnel set.

2. The method of claim 1, wherein, The regional communication data comprises operator call data, wireless measurement report MR data, and WiFi access data of designated places in the target area, wherein, The method comprises: According to the operator call data, the MR data, the WiFi access data, and the place registration data, perform data cleaning according to a preset format to obtain the regional personnel flow data.

3. The method of claim 1, wherein, The determining the plurality of space-time accompanying derivative coefficients corresponding to the plurality of grid regions according to the base station data in the regional communication data and the regional environment data comprises: determining a plurality of base station correlation degrees of the plurality of grid regions according to base station distribution in the base station data and position information of the plurality of grid regions; determining the plurality of space-time accompanying derivative coefficients according to the plurality of base station correlation degrees and the regional environment data.

4. A spatiotemporal relationship determination apparatus characterized by comprising: The device comprises: The first obtaining module is configured to obtain space-time accompanying serialized data of a target region according to regional communication data and regional environment data of the target region in a preset period, wherein the space-time accompanying serialized data comprises a plurality of grid data corresponding to a plurality of grid regions in the target region, the grid data comprises corresponding regional personnel flow data in the grid region in the preset period, and the grid region corresponds to a space-time accompanying derivative coefficient; and the space-time accompanying derivative coefficient can identify a personnel correlation degree of the grid region. The second obtaining module is configured to obtain at least one space-time accompanying derivative coefficient corresponding to at least one associated grid region of a target path in the target region in the preset period and an accompanying personnel set according to the space-time accompanying serialized data and the at least one associated grid region. The determining module is configured to determine a personnel with an associated value greater than a space-time accompanying threshold value as a space-time accompanying personnel in the target region, wherein the space-time accompanying threshold value is determined by a space-time accompanying prediction model according to the associated value of the personnel in the preset period, the at least one space-time accompanying derivative coefficient corresponding to the at least one associated grid region, and the accompanying personnel set; and the space-time accompanying prediction model is trained according to actual accompanying data and sample data corresponding to the accompanying personnel set. The second obtaining module comprises: The first obtaining submodule is configured to obtain a correction coefficient corresponding to the target path and a personnel set corresponding to the at least one associated grid region. The third determining submodule is configured to determine an associated value of each personnel in the personnel set according to the correction coefficient and the at least one space-time accompanying derivative coefficient corresponding to the at least one associated grid region, and generate the accompanying personnel set. The first obtaining module comprises: The first determining submodule is configured to determine corresponding regional personnel flow data in each grid region according to place registration data of each place in the target region and the regional communication data. The second determining submodule is configured to determine a plurality of space-time accompanying derivative coefficients corresponding to the plurality of grid regions according to base station data in the regional communication data and the regional environment data.

5. The apparatus of claim 4, wherein, The regional communication data comprises operator call data, wireless measurement report MR data, and WiFi access data of a designated place in the target region, wherein the first determining submodule comprises: A data cleaning unit is configured to clean data according to the operator call data, the MR data, the WiFi access data and the site registration data in a preset format to obtain the regional personnel flow data.

6. The apparatus of claim 4, wherein, The second determining sub-module comprises: A first determining unit is configured to determine a plurality of base station correlation degrees of a plurality of grid regions according to base station distribution in the base station data and position information of the plurality of grid regions; A second determining unit is configured to determine the plurality of spatiotemporal concomitant derivative coefficients according to the plurality of base station correlation degrees and the regional environment data.

7. An electronic device, comprising: The application further provides a computer program product, comprising: A memory, a processor and a computer program stored in the memory and executable on the processor, wherein the computer program is executed by the processor to implement the steps of the spatiotemporal concomitant relationship determining method according to any one of claims 1 to 3.

8. A readable storage medium, characterized by, The computer program is stored in the readable storage medium and executable by the processor to implement the steps of the spatiotemporal concomitant relationship determining method according to any one of claims 1 to 3.

Images