CN115272025A

CN115272025A - Method, device and storage medium for determining population distribution thermodynamic data

Info

Publication number: CN115272025A
Application number: CN202110482704.7A
Authority: CN
Inventors: 周银生; 黄骞; 莫君贤; 许立言; 尹航
Original assignee: Peking University; Huawei Technologies Co Ltd
Current assignee: Peking University; Huawei Technologies Co Ltd
Priority date: 2021-04-30
Filing date: 2021-04-30
Publication date: 2022-11-01
Also published as: WO2022228320A1

Abstract

The embodiment of the application discloses a method, a device and a storage medium for determining population distribution thermodynamic data, and belongs to the technical field of computers. The method comprises the following steps: acquiring region attribute data of a target region; determining primary population weight data of the target area based on the region attribute data of the target area; determining second population distribution thermodynamic data of the target area based on the first population distribution thermodynamic data of the target area and the primary population weight data of the target area. By the method and the device, the accuracy of population distribution thermodynamic data can be improved.

Description

Method, device and storage medium for determining population distribution thermodynamic data

Technical Field

The present application relates to the field of computer technologies, and in particular, to a method, an apparatus, and a storage medium for determining population distribution thermal data.

Background

Population distribution thermodynamic data is data that describes the distribution of a population in a geographic area. Generally, a grid can be drawn in a geographic area, the geographic area is divided into a plurality of unit areas (generally square) with equal areas, and population distribution thermodynamic data is composed of the number of people corresponding to each unit area in the geographic area. With the development of informatization, the application of population distribution thermodynamic data is more and more extensive, for example, the population distribution thermodynamic data can be used for guiding the infrastructure construction and operation of a communication network, store site selection, advertisement placement and the like.

The manner of acquiring population distribution thermodynamic data in the related art is generally as follows: a server on the network side collects position data of a Global Positioning System (GPS) of each terminal, and statistical calculation is carried out on a large amount of collected position data to obtain population distribution thermodynamic data.

In the course of implementing the present application, the inventors found that the related art has at least the following problems:

the population distribution thermal data collected in the manner described above has a lower resolution because of the lower accuracy of the GPS location data. The resolution of the population distribution thermodynamic data is represented by the size of the unit area, and the larger the unit area is, the lower the resolution is, and the smaller the unit area is, the higher the resolution is. The resolution of the population distribution thermal data obtained by GPS location data statistics is typically 200m x 200m. The population distribution thermodynamic data with the resolution ratio cannot meet the requirements of practical application, and a method capable of improving the accuracy of the population distribution thermodynamic data is urgently needed.

Disclosure of Invention

The embodiment of the application provides a method for determining population distribution thermodynamic data, and can solve the problem that population distribution thermodynamic data are low in precision and cannot meet the requirements of practical application. The technical scheme is as follows:

in a first aspect, there is provided a method of determining population distribution thermodynamic data, the method comprising: the method comprises the steps of obtaining region attribute data of a target region, determining first-class population weight data of the target region based on the region attribute data of the target region, and determining second population distribution thermal data of the target region based on first population distribution thermal data of the target region and the first-class population weight data of the target region.

Population distribution thermodynamic data is data describing the population distribution of different locations in a geographic area. Zone attribute data is data that describes the attributes of a zone at different locations in a geographic area. Population weight data is data that describes the high and low likelihood of population distributions at different locations in a geographic area.

The region attribute data includes an attribute value of at least one region attribute corresponding to each unit region in the target region. The unit area is determined according to the target resolution. The region attribute is a region attribute having an influence on human mouth. The primary population weight data includes a population weight value corresponding to each unit area in the target area. The first population distribution thermodynamic data includes a number of people corresponding to each initial unit area in the target area. The second population distribution thermodynamic data includes the number of people corresponding to each unit area in the target area. The initial unit area is determined according to the initial resolution. The target resolution is greater than the initial resolution. The initial resolution is the resolution of the initial population distribution thermal data, which is a lower resolution, and the target resolution is the desired resolution, which is a higher resolution.

The region attribute data, population weight data and second population distribution thermodynamic data are corresponding to a target resolution, and the first population distribution thermodynamic data is corresponding to an initial resolution.

According to the scheme shown in the embodiment of the application, the region attribute data can be obtained from the map database, if the attribute value of each region attribute obtained from the map database is vector data, the vector data is converted into raster data, and if the attribute value of each region attribute obtained from the map database is raster data, the raster data can be directly used.

When the second population distribution thermodynamic data is determined based on the first population distribution thermodynamic data and the first-level population weight data, the first population distribution thermodynamic data can be interpolated, then the interpolation result is filtered based on the first-level population weight data, and the filtering result can be further used as the second population distribution thermodynamic data, or the filtering result is further processed to obtain the second population distribution thermodynamic data. Or the first population distribution thermodynamic data can be directly interpolated based on the first-level population weight data to obtain an interpolation result which is used as the second population distribution thermodynamic data, or the interpolation result is further processed to obtain the second population distribution thermodynamic data.

In one possible implementation, the at least one regional attribute having an influence on the human mouth includes: zone type and/or number of building floors. The two region attributes more easily influence the number of people in the region, so the population weight value determined by using the attribute values of the two region attributes is more accurate.

In one possible implementation manner, the population weight value corresponding to each unit area in the target area is determined based on the attribute value of at least one region attribute corresponding to each unit area in the target area and the corresponding relationship between the attribute value of the region attribute and the population weight value. And for each initial unit area in the target area, performing normalization processing on the population weight values corresponding to all the unit areas in the initial unit area to obtain a normalized population weight value corresponding to each unit area. And determining the normalized population weight values corresponding to all unit areas in the target area as the primary population weight data of the target area.

The corresponding relationship between the attribute value of the region attribute and the population weight value may be a corresponding relationship table, and after obtaining the region attribute data, for each unit region, the corresponding population weight value is searched in the corresponding relationship table based on the attribute value of at least one region attribute corresponding to the unit region, so as to obtain the population weight value corresponding to the unit region. Or, the corresponding relationship between the attribute value of the region attribute and the population weight value may adopt a calculation relational expression, and after obtaining the region attribute data, for each unit region, the attribute value of at least one region attribute corresponding to the unit region is input into the calculation relational expression, so as to obtain the population weight value corresponding to the unit region.

The normalization processing is further carried out on the obtained population weight value by taking the initial unit area as a unit, so that the number of people in the same initial unit area of the second population distribution thermodynamic data and the first population distribution thermodynamic data obtained by filtering can be the same as much as possible, and the output population distribution thermodynamic data with high resolution can be faithful to the input population distribution thermodynamic data with low resolution as much as possible.

In one possible implementation manner, the corresponding relationship between the attribute value of the region attribute and the population weight value is a calculation relationship between the attribute value of the region attribute and the population weight value, and the calculation relationship is:

z_i＝p₁×x_i1+p₂×x_i2+......+p_N×x_iN+ θ; wherein x is_i1、x_i2、……x_iNRespectively, an attribute value, z, of each of the territorial attributes in the unit area i in the target area_iIs the population weight, p, of the unit area i₁、p₂、……p_NAnd θ is a constant.

p₁、p₂、……p_NThe value of θ can be set by a technician based on empirical values, or can be learned based on accurately detected sample population distribution thermodynamic data. And the calculation relational expression is adopted, and each constant in the calculation relational expression is determined in a learning mode, so that the population weight value can be calculated more accurately, and the accuracy of the second population distribution thermodynamic data is improved.

In a possible implementation manner, interpolation processing is performed on the first population distribution thermodynamic data of the target area to obtain third population distribution thermodynamic data of the target area, and second population distribution thermodynamic data of the target area is determined based on the third population distribution thermodynamic data of the target area and the first-level population weight data of the target area.

And the third population distribution thermodynamic data comprises the number of people corresponding to each unit area in the target area.

The interpolation processing is carried out on the first human mouth distribution thermodynamic data, and cubic spline interpolation can be adopted, or interpolation processing modes such as average interpolation can also be adopted. When the third population distribution thermodynamic data is determined, the first-level population weight data can be used for filtering the third population distribution thermodynamic data to obtain second population distribution thermodynamic data, and the first-level population weight data and the third population distribution thermodynamic data can also be subjected to counterpoint multiplication to obtain the second population distribution thermodynamic data.

The edge transition between adjacent initial unit areas can be better reflected by adopting cubic spline interpolation, and the edge transition has higher matching degree with the actual population distribution.

In a possible implementation manner, filtering processing is performed on third population distribution thermodynamic data of the target area based on first-level population weight data, a target filtering window size and a target window sliding step size of the target area, so as to obtain a first filtering result. Based on the first filtering result, second population distribution thermodynamic data of the target area is determined.

The side length of the target filter window may be a ratio of the side length of the initial unit region to the side length of the unit region. The target window sliding step may be 1.

After the first filtering result is obtained, the first filtering result may be used as the second population distribution thermal data of the target area, or the first filtering result may be further processed to obtain the second population distribution thermal data of the target area.

The filtering processing mode can better reflect the mutual influence of the number of people in the unit area, and has higher matching degree with the actual population distribution.

In one possible implementation, region subdivision type data of a target sub-region in a target region is obtained. And determining second population distribution thermodynamic data of the target area based on the first filtering result and the second population weight data of the target sub-area.

The region subdivision type data comprises a type value of the region subdivision type corresponding to each unit region in the target sub-region. The secondary population weight data includes a population weight value corresponding to each unit area in the target sub-area.

The corresponding population weight value of each unit area is searched for the type value of the region subdivision type of each unit area by using a corresponding relation table of the type value of the region subdivision type and the population weight value, the population weight value of each unit area is obtained, and then population weight data is determined based on the population weight value of each unit area. Or a calculation relation between the type value of the region subdivision type and the population weight value can be used, the corresponding population weight value is calculated for the type value of the region subdivision type of each unit area, the population weight value of each unit area is obtained, and then secondary population weight data is determined based on the population weight value of each unit area.

Further, the first filtering result is processed by using the second-level population weight data, and specifically, the first filtering result may be filtered again by using the second-level population weight data, and the second filtering result is used as the second population distribution thermal data of the target area, or the second filtering result is further processed to obtain the second population distribution thermal data of the target area. Or, the second-level population weight data and the first filtering result may be subjected to counterpoint multiplication to obtain a counterpoint multiplication result, and the counterpoint multiplication result is used as the second population distribution thermodynamic data of the target area, or the counterpoint multiplication result is further processed to obtain the second population distribution thermodynamic data of the target area.

And determining secondary population weight data by adopting the region subdivision type data, and further processing the first filtering result, so that the population distribution condition in a specific region (target sub-region) can be calculated more accurately, and the calculated second population distribution thermodynamic data has higher matching degree with the actual population distribution.

In one possible implementation manner, the population weight value corresponding to each unit area in the target sub-area is determined based on the type value corresponding to each unit area in the target sub-area and the corresponding relationship between the type value and the population weight value. For each unit area in the target sub-area, determining population weight influence values of the plurality of other unit areas on the unit area based on population weight values corresponding to the plurality of other unit areas except the unit area in the target sub-area and distances between the unit area and the plurality of other unit areas, respectively, and adjusting the population weight values corresponding to the unit area based on the population weight influence values of the plurality of other unit areas on the unit area, respectively, to obtain an adjusted population weight value of the unit area. And for each initial unit area in the target sub-area, performing normalization processing on the adjusted population weight values corresponding to all the unit areas in the initial unit area to obtain a normalized population weight value corresponding to each unit area. And determining the normalized population weight values corresponding to all unit areas in the target sub-area as the secondary population weight data of the target sub-area.

The corresponding relation may be a corresponding relation table or a calculation relation.

In the above processing, the population weight value of each unit area is adjusted first, and in the normalization processing, the following describes an adjustment process of the population weight value of one unit area:

the unit area may be any one of the target sub-areas, and may be referred to as a unit area to be adjusted. And determining other unit areas except the unit area to be adjusted in the target sub-area as reference unit areas. At this time, all other unit areas than the unit area to be adjusted in the target sub-area may be selected as the reference unit area. Alternatively, a unit area satisfying a specified condition may be selected as the reference unit area in the unit areas other than the unit area to be adjusted in the target sub-area. The specified condition may be arbitrarily set according to actual requirements, for example, the specified condition is that the distance between the reference unit area and the unit area to be adjusted is less than or equal to a distance threshold value, and the distance threshold value may be set in advance based on an empirical value.

Further, a distance between each reference unit region and the unit region to be adjusted, respectively, may be determined, and the distance may be a straight line distance or include a longitude direction distance and a latitude direction distance. And then respectively determining the population weight influence value of each reference unit area on the unit area to be adjusted based on the distance between each reference unit area and the unit area to be adjusted and the population weight value corresponding to each reference unit area. The specific processing manner for determining the weight influence value may be various, for example, based on the lookup of the corresponding relationship table or based on formula calculation. One useful formula form is given below:

wherein, the distance between the reference unit area and the unit area to be adjusted may include a longitude direction distance and a latitude direction distance, d_xIs the longitudinal distance, d_yThe distance in the latitudinal direction, H is the population weight value of the reference unit area, and W is the population weight influence value of the reference unit area on the unit area to be adjusted. The formula is obtained based on a Gaussian function, wherein the standard deviation sigma corresponding to the longitude direction_xStandard deviation sigma corresponding to latitude direction_yThe determination may be based on a first width in a longitudinal direction and a second width in a latitudinal direction of the target subregion. Specifically, the value of the standard deviation corresponding to the larger value of the first width and the second width may be determined to be 1, and then σ may be calculated_xAnd σ_yIs equal to the ratio of the first width to the second width to calculate another standard deviation.

After determining the population weight influence value of each reference unit area to the unit area to be adjusted, the population weight value of the unit area to be adjusted may be added to the population weight influence values to obtain an adjusted population weight value of the unit area to be adjusted.

Because the number of people at any position has radiation influence on surrounding areas in practice, the mutual influence of the population weight values among the unit areas is calculated by adopting the method, and the actual population distribution situation can be better restored.

In a possible implementation manner, based on the second-level population weight data of the target sub-region, the size of the target filtering window, and the sliding step length of the target window, the second filtering result is obtained by performing filtering processing again on the part, corresponding to the target sub-region, in the first filtering result. And determining the second filtering result and the part of the first filtering result, which does not correspond to the target subarea, as second population distribution thermodynamic data of the target subarea.

The sizes of the filtering windows of the secondary filtering and the filtering windows of the primary filtering can be the same or different, and the sliding step lengths can be the same or different. The second filtering is performed on the part of the first filtering result corresponding to the target subregion. After the second filtering result is obtained by performing the second filtering, the second filtering result and the part of the first filtering result which does not correspond to the target sub-area may be combined to obtain the second population distribution thermodynamic data of the target area.

The mutual influence of the number of people in the unit areas can be better reflected by adopting a filtering processing mode, and the calculated second population distribution data has higher matching degree with the actual situation.

In one possible implementation, the target sub-area is a multi-story building area. The region subdivision type data comprises sub-region subdivision type data corresponding to each layer, and the sub-region subdivision type data corresponding to each layer comprises a type value of the region subdivision type corresponding to each unit region in the target sub-region in the layer. The secondary population weight data comprises sub population weight data corresponding to each layer, and the sub population weight data corresponding to each layer comprises population weight values corresponding to each unit area in the target sub-area. Accordingly, the process of the second filtering may be as follows: and for each layer, performing secondary filtering processing on the part corresponding to the target subarea in the first filtering result based on the sub-human mouth weight data, the target filtering window size and the target window sliding step length of the layer to obtain the filtering result corresponding to the layer. And combining the filtering results corresponding to each layer to determine a second filtering result.

And respectively filtering the multiple layers, and simply combining the filtering results of the multiple layers to obtain a second filtering result, wherein the second filtering result is the three-dimensional population distribution thermodynamic data of the target subarea. Through the processing mode, more accurate three-dimensional population distribution thermodynamic data can be obtained.

In a second aspect, there is provided an apparatus for determining population distribution thermodynamic data, the apparatus comprising one or more modules for implementing the method of the first aspect and possible implementations thereof.

In a third aspect, a computer device is provided, the computer device comprising a memory for storing computer instructions and a processor; the processor executes computer instructions stored by the memory to cause the computer device to perform the method of the first aspect and possible implementations thereof.

In a fourth aspect, a computer-readable storage medium is provided, which stores computer program code, which, when executed by a computer device, performs the method of the first aspect and its possible implementations.

In a fifth aspect, a computer program product is provided, the computer program product comprising computer program code which, when executed by a computer device, causes the computer device to perform the method of the first aspect and possible implementations thereof.

The technical scheme provided by the embodiment of the application has the following beneficial effects:

in the embodiment of the application, the population weight data with high resolution is determined by using the region attribute data with high resolution, and then the population distribution thermal data with low resolution is processed based on the population weight data with high resolution to obtain the population distribution thermal data with high resolution, so that the accuracy of the population distribution thermal data can be improved.

Drawings

FIG. 1 is a schematic structural diagram of a computer device according to an embodiment of the present application;

FIG. 2 is a schematic diagram of population distribution thermodynamic data provided by an embodiment of the present application;

FIG. 3 is a schematic diagram of domain attribute data provided in an embodiment of the present application;

FIG. 4 is a graphical illustration of population weight data provided by an embodiment of the present application;

FIG. 5 is a schematic diagram of a region subdivision type data provided by an embodiment of the present application;

FIG. 6 is a schematic flow chart diagram of a method for determining population distribution thermodynamic data provided by an embodiment of the present application;

FIG. 7 is a schematic diagram of an interpolation process provided in an embodiment of the present application;

FIG. 8 is a schematic diagram of a filtering process provided in an embodiment of the present application;

FIG. 9 is a schematic flow chart diagram illustrating a method for determining population distribution thermodynamic data according to an embodiment of the present disclosure;

FIG. 10 is a schematic diagram illustrating a relationship between a target sub-region and a target region according to an embodiment of the present disclosure;

FIG. 11 is a schematic flow chart diagram illustrating a method for determining population distribution thermodynamic data provided by an embodiment of the present application;

fig. 12 is a schematic structural diagram of an apparatus for determining population distribution thermodynamic data according to an embodiment of the present application.

Detailed Description

Embodiments of the present application provide a method for determining population distribution thermodynamic data, which may be implemented by a computer device. The computer device may be a device for statistical population distribution thermodynamic data. The computer device may be a device used by an entity having demographic requirements, such as a subway company, who needs to perform statistical analysis on urban demographics for subway line planning, or a chain company, which needs to perform statistical analysis on urban demographics for shop location decision-making. The computer device may also be a device used by an entity that provides third party demographic services. The computer device may be a terminal, a server group, or the like provided in a machine room or an office of the above-mentioned units.

As shown in fig. 1, the computer apparatus may include a processor 1, a memory 2, a communication section 3, and the like.

The processor may be a Central Processing Unit (CPU), and the processor may be configured to obtain region attribute data of the target area, determine population weight number based on the region attribute data, perform filtering processing on population thermal data based on the population weight data, and the like.

The memory may be various volatile memories or nonvolatile memories, such as a Solid State Disk (SSD), a Dynamic Random Access Memory (DRAM), and the like. The memory may be used to store pre-stored data, intermediate data, and result data, such as demographic thermodynamic data, geographic attribute data, demographic weighting data, and the like, in the process of determining demographic distribution thermodynamic data.

The communication means may be a wired network connector, a wireless fidelity (WiFi) module, a bluetooth module, a cellular network communication module, etc. The communication component may be configured to perform data transmission with other devices, for example, the communication component may be configured to receive first demographic distribution thermal data and geographic attribute data sent by other devices, and may also be configured to send calculated second demographic distribution thermal data to a specific device, and the like.

The method for determining population distribution thermodynamic data provided by the embodiment of the application can be used for determining high-resolution population distribution thermodynamic data based on low-resolution population distribution thermodynamic data. The embodiment of the application mainly improves the resolution of population distribution thermodynamic data in a spatial domain, and does not limit the processing in a time domain.

Some important terms in the process are explained below:

population distribution thermodynamic data

Population distribution thermodynamic data is data that describes the population distribution at different locations in a geographic area.

The population distribution thermodynamic data for the target area is described below in conjunction with fig. 2. The target area is divided into a plurality of grids, each grid is equal in size and same in shape, the shape can be a square, and each grid can be called a unit area. The number of persons per unit area corresponds to 11, for example, in fig. 2, the number of persons per unit area A1 corresponds to 11. The number of people corresponding to all unit areas in the target area constitutes population distribution thermodynamic data of the target area. From the viewpoint of image, the population distribution thermodynamic data is data in a grid form, which can be referred to as grid data for short. Population distribution thermodynamic data is of a resolution, expressed as the size of a unit area, which may be the side length of a square unit area, for example, a resolution of 10m x 10m. Since the size of the unit area is directly related to the number and density of the unit areas included in the target area, the resolution is expressed in terms of the size of the unit area.

The demographic thermal data may be stored as an array including one or more values, each value representing a number of people for a unit area in the target area.

Region attribute data

The region attribute data is data describing region attributes at different positions in a geographic region, and may correspond to at least one region attribute having an influence on human mouth, such as a region type, a number of building floors, and the like. The zone type may be a coarser grained type such as an intersection, a road, a park, a mall, a residential building, a theater, etc. For the number of building layers, if it is a non-layered area, such as a park, a road, etc., it can be considered as 1 layer. It can be seen that different terrain types have different degrees of influence on the population, for example, intersections are generally denser than roads, and malls are generally denser than parks. Different building floors have different influence degrees on population, and the population with the largest floor can be more.

The region attribute data of the target region will be described below with reference to fig. 3. The target area is divided into a plurality of grids, each grid is equal in size and same in shape, the shape can be a square, and each grid can be called a unit area. Each unit area corresponds to an attribute value of a region attribute, for example, the region type corresponding to the unit area A1 in fig. 3 is a shopping mall, and the number of building floors is 5. The attribute values of the region attributes corresponding to all the unit areas in the target area constitute region attribute data of the target area. From the viewpoint of image, the region attribute data is data in a grid form, which may be referred to as grid data for short. The region attribute data has a resolution, which is expressed as a size of a unit area, and may be a side length of a square unit area, and for example, the resolution may be 10m × 10m.

The region attribute data may be an array in a data storage form, where the array includes one or more values, each value represents an attribute value of a region attribute corresponding to one unit region in the target region, and if there are multiple region attributes, each value may be a vector, and each element of the vector is an attribute value of one region attribute.

Population weight data

Population weight data is data that describes the high and low likelihood of population distributions at different locations in a geographic area. The likelihood is influenced by the geographical property data, e.g. a mall is weighted higher than a park.

Population weight data for the target area is described below in conjunction with fig. 4. The target area is divided into a plurality of grids, each grid is equal in size and same in shape, the shape can be a square, and each grid can be called a unit area. Each unit area corresponds to a population weight value, which is a factor indicating the high and low probability of the population in the unit area, and the population weight value corresponding to the unit area A1 in fig. 4 is 0.8. The population weight values corresponding to all unit areas in the target area constitute population weight data of the target area. From the perspective of image, the population weight data is data in a grid form, which may be referred to as grid data for short. The population weight data has a resolution, which is expressed as the size of a unit area, and may be a side length of a square unit area, and for example, the resolution may be 10m × 10m.

The population weight data may be stored in an array, where the array includes one or more values, and each value represents a population weight value corresponding to one unit area in the target area.

Region subdivision type data

The region segment type data is data describing region segment types at different positions in a geographic region, and is data representing region classification with finer granularity. The region subdivision type is generally used for performing further type subdivision for the interior of a sub-region of a certain region type in a target region, for example, a park can subdivide a grassland, a road, a pavilion, a pond and the like, and a mall can subdivide a shop, a corridor, a toilet, an elevator room and the like.

The zone subdivision type data of the target sub-zone in the target zone will be described with reference to fig. 5. The target sub-area continues to be a grid for dividing the target area, so that the target sub-area includes a plurality of unit areas, each unit area corresponds to a region subdivision type, and the region subdivision type corresponding to the unit area A1 in fig. 5 is a corridor. The region subdivision types corresponding to all unit areas in the target sub-area form region subdivision type data of the target sub-area. From the viewpoint of image, the region subdivision type data is data in a grid form, which may be referred to as grid data for short. The region subdivision type data has a resolution, which is expressed as a size of a unit area, and may be a side length of a square unit area, and for example, the resolution may be 10m × 10m.

The region subdivision type data may be an array in a storage form, where the array includes one or more values, and each value represents a region subdivision type corresponding to one unit area in the target sub-area.

Initial resolution

The processing of the embodiments of the present application calculates the high resolution second population distribution thermodynamic data based on the low resolution first population distribution thermodynamic data. The low resolution may be referred to as an initial resolution, which is the resolution of the first population distribution thermodynamic data input by the method of the embodiment of the present application. The first demographic thermodynamic data may be obtained through general channels, for example, demographic thermodynamic data obtained through GPS data statistics, with a resolution of 200m x 200m.

Target resolution

The high resolution described above may be referred to as a target resolution, which is the resolution of the second population distribution thermodynamic data output by the method of embodiments of the present application. The target resolution may be set based on application requirements of population thermal data, or may be determined based on the resolution of the geographic attribute data that can be obtained. For example, the target resolution may be 10m × 10m, 5m × 5m, or the like.

The process flow shown in fig. 6 will be described in detail below with reference to specific embodiments, and the contents may be as follows:

601, obtaining region attribute data of the target region.

The target area is any geographical area, such as a city, a country, a government area, or an area defined in a map by a person. The region attribute data obtained in this step may be: and the attribute value of at least one territorial attribute corresponding to each unit area in the target area. The unit area is determined according to a target resolution, for example, the target resolution is 10m × 10m, and the unit area is a square of 10m × 10m. The target resolution, i.e., the resolution of the desired population thermodynamic data, may be preset by the technician.

A map database is generally established in a background server of a map application, and data of various regional attributes (such as regional types, building floor numbers, and the like) corresponding to a geographic area related to a map are stored in the map database, and the data may be raster data or vector data. If the raster data is the raster data and the resolution is equal to the target resolution, the computer device may directly acquire the raster data and perform resolution reduction processing on the raster data if the resolution is higher than the target resolution. If it is vector data, it needs to be converted into raster data.

The following describes a process of converting vector data into raster data by taking vector data of a region type as an example.

For example, the vector data for a mall may include the coordinates of each vertex of the planar outline of the mall (assuming the planar outline is an arbitrary polygon) and the mall type identifier. The mall is in the target area. Based on the vertex coordinates, the corresponding polygon can be determined to be used as the plane contour line of the market, further, all unit areas within the range of the plane contour line are determined in the target area, and the region types corresponding to the unit areas are determined to be the market.

In a similar manner as described above, vector data of various region attributes may be converted into raster data.

And 602, determining a population weight value corresponding to each unit area in the target area based on the attribute value of the region attribute corresponding to each unit area in the region attribute data and the corresponding relationship between the attribute value of the region attribute and the population weight value.

The population weight value is a factor representing the high and low probability of population in the unit area.

Based on the different forms of the corresponding relations, there are a plurality of specific processing manners in this step, and several of these processing manners are described below.

In the first mode, the corresponding relation is a calculation relational expression of an attribute value of a region attribute and a population weight value.

The calculation relationship may be as follows:

z_i＝p₁×x_il+p₂Xx_i2+......+p_w×x_iN+θ

wherein x is_i1、x_i2、……x_iNRespectively, the attribute value of each territory attribute in the unit area i in the target area. z is a radical of_iIs the population weight value per unit area i. p is a radical of₁、p₂、……p_NIs a weighting coefficient corresponding to each territorial property and can be a constant. θ may also be a constant. p is a radical of₁、p₂、……p_NAnd the value of theta can be obtained by learning based on the population distribution thermodynamic data which is accurately detected, and can also be set by technicians based on experience values, and the learning mode will be described in detail in the following. i can be regarded as the number of the unit area, and for any numberThe unit area may calculate a population weight value based on the calculation relationship.

And in the second mode, the corresponding relation adopts a corresponding relation table of the attribute value of the region attribute and the population weight value.

The correspondence table may be set by a skilled person based on empirical values. After the region attribute data is obtained, for each unit region, the corresponding population weight value is searched in the corresponding relation table based on the attribute value of at least one region attribute corresponding to the unit region, and the population weight value corresponding to the unit region is obtained.

603, for each initial unit area in the target area, performing normalization processing on the population weight values corresponding to all the unit areas in the initial unit area to obtain a normalized population weight value corresponding to each unit area.

The target region may be divided into several unit regions based on the target resolution, and the target region may be divided into several initial unit regions based on the initial resolution, each of which may include a plurality of unit regions. For example, if the initial resolution is 200m × 200m and the target resolution is 10m × 10m, the size of each initial unit area is 200m × 200m and the size of each unit area is 10m × 10m, and thus each initial unit area includes 400 unit areas.

Based on the above characteristics, the population weight values of the unit areas in the initial unit area can be normalized by taking the initial unit area as a range. For any initial unit area, a plurality of unit areas in the initial unit area are determined, and the population weight values of the plurality of unit areas are obtained. And further carrying out normalization processing on the population weight values of the plurality of unit areas to obtain a normalized population weight value corresponding to each unit area in the plurality of unit areas. The processing is performed for each initial unit area, so that a normalized population weight value corresponding to each unit area in the target area can be obtained.

And 604, determining the normalized population weight values corresponding to all the unit areas in the target area as population weight data of the target area.

605, performing interpolation processing on the first population distribution thermodynamic data of the target area to obtain third population distribution thermodynamic data of the target area.

The first human mouth distribution thermodynamic data comprise the number of people corresponding to each initial unit area in the target area. The initial unit area is determined according to an initial resolution, for example, the initial resolution is 200m × 200m, and the initial unit area is a square of 200m × 200m. The third population distribution thermodynamic data includes a number of people corresponding to each unit area in the target area. The target resolution is greater than the initial resolution.

The interpolation processing is carried out on the first human mouth distribution thermodynamic data, and cubic spline interpolation can be adopted, or interpolation processing modes such as average interpolation can also be adopted. The process of the interpolation process can be seen in fig. 7.

And 606, filtering the third population distribution thermodynamic data of the target area based on the population weight data of the target area, the size of the target filtering window and the sliding step length of the target window to obtain second population distribution thermodynamic data of the target area.

And the second population distribution thermodynamic data comprises the number of people corresponding to each unit area in the target area. The second population distribution thermal data is a result of filtering the third population distribution thermal data. The target filter window size may be set according to actual requirements, for example, the ratio of the side length of the initial unit region to the side length of the unit region may be set as the filter window side length, where the initial unit region is a square of 200m × 200m, the unit region side length is a square of 10m × 10m, and then the target filter window size is 20 × 20. The target window sliding step size may be set by the technician based on empirical values, such as 1, 2, etc.

The filtering process can be seen in fig. 8, where the target area is a square area, the values in the figure are indicated by X and Y, and do not represent that the values in different unit areas are the same, and the actual data may be any values. The third population distribution thermodynamic data and population weight data are both data for the target area and are both based on the target resolution so they have the same spatial distribution, as shown in the figure they can both be represented as an 8 x 8 matrix.

A filter window may be used to select a corresponding portion of the third population distribution thermodynamic data and population weight data. The target filter window size in the figure is 3 x 3. A 3 x 3 matrix may be selected at the upper left corner of the third population distribution thermodynamic data and population weight data, respectively, using a filter window, and then the inner product Y of the two matrices is calculated. In addition, a filtering result is established, which is identical in data form to the third population distribution thermodynamic data, also in an 8 × 8 matrix, whose content is temporarily empty at the beginning of the establishment, into which the inner product Y of each calculation is subsequently placed.

Next, the placement position of the current inner product Y in the filtering result is determined, and the filtering window is currently located at the upper left corner of the third population distribution thermal data, so that the filtering window can also be placed at the upper left corner of the filtering result, and then the position of the specified position in the filtering window, which corresponds to the current position in the filtering result, is determined as the result position, which is the placement position of the inner product Y in the filtering result. The designated position may be arbitrarily set, and in general, the designated position may be a center position of the filter window, the designated position may be a filter window with an even side length, and the designated position may be a position located at the upper left (or upper right, etc.) of the 4 positions of the center of the filter window. After determining the result location, the current inner product Y is placed at the result location. As shown in the figure, the 3 × 3 filtering window is located at the upper left corner of the filtering result, and the corresponding position of the center position of the filtering window in the filtering result is the position of 2 rows and 2 columns, which is the result position, and the current value of the inner product Y can be filled in the position of 2 rows and 2 columns in the filtering result.

After the above processing, the calculation of the first matrix inner product of the filtering process is completed. Further, the filtering window may be slid to the right, where the sliding distance is a target window sliding step length, and if the target window sliding step length is 1, the filtering window may be slid to the right by one grid. And then the inner product of the second matrix is calculated. And by analogy, when the filtering window moves to the rightmost side and the matrix inner product is calculated, sliding the filtering window to the leftmost side and sliding downwards, wherein the distance of the downward sliding is the sliding step length of the target window, and continuing the processing until the filtering window slides to the lower right corner and the matrix inner product is calculated.

In this case, the filtering result also lacks data in the outer circle, for example, 1 row and 1 column, 1 row and 2 column, 1 row and 3 column, and so on. The data of the outer ring can be complemented, and the complementing methods are various. For example, for each location of the outer circle of missing data, the location of this gap may be filled in using the data in the location that is closest to it and that has already been filled in. For another example, a preset value may be filled in a position of the vacant data, and the like.

After the second population distribution thermodynamic data of the target area is acquired, the second population distribution thermodynamic data of the target area can be sent to the target device to be displayed. Or, the second population distribution thermodynamic data acquired within a certain time period can be counted, and based on the statistical result, a target advertisement spot is selected from a plurality of pending advertisement spots for advertisement delivery, and based on the statistical result, a target store position is selected from a plurality of pending store positions for setting stores, and the like.

The population distribution thermodynamic data is changed with time, so the first population distribution thermodynamic data obtained in the above way is also changed with time. Thus, for the target area, the above steps 601-604 may be performed only once during a period of time, and the region attribute data of the target area may be considered as unchanged. Alternatively, steps 601-604 may be re-executed each time a change in zone attribute data of the target area is detected. Alternatively, steps 601-604 may be re-executed each time the second population distribution thermal data is calculated. After step 604 is completed, population weight data of the target area is obtained. The first demographic distribution thermal data may be periodically acquired, and each time the first demographic distribution thermal data is acquired, the population weight data for the target area may be invoked to perform steps 605-606.

In the processing process, the population distribution thermodynamic data with high resolution ratio is obtained by adopting a processing mode of firstly interpolating and then filtering. Optionally, after the population weight data is determined, interpolation processing may be performed on the population distribution thermodynamic data with the low resolution directly based on the population weight data to obtain the population distribution thermodynamic data with the high resolution.

The specific treatment may be as follows:

for each initial unit area, determining the number of people in the initial unit area in the first population distribution thermodynamic data, determining the population weight value of each unit area contained in the initial unit area in the population weight data, determining the sum of the population weight values, for each unit area in the initial unit area, determining the ratio of the population weight value of the unit area to the sum, and further determining the product of the ratio and the number of people in the initial unit area to obtain the number of people corresponding to the unit area. By adopting the method, the number of people in all unit areas in the target area can be obtained, namely, interpolation is completed, and the population distribution thermodynamic data with high resolution is obtained.

In the processing process, filtering processing is carried out on the third population distribution thermodynamic data by using population weight data. Optionally, the population weight data and the third population thermal distribution data may be directly multiplied by each other in a bit-by-bit manner without using a filtering processing manner, so as to obtain the second population distribution thermal data. The specific treatment may be as follows:

and for each unit area, acquiring the number of people in the unit area in the third population thermal distribution data, acquiring the population weight value of the unit area in the population weight data, calculating the product of the hot number of people and the population weight value, and determining the updated number of people in the unit area. And determining the updated number of people in all unit areas in the target area as the finally output high-resolution population distribution thermodynamic data.

In the above processing process, step 603 performs normalization processing on the population weight value, so that the number of people in the same initial unit area of the second population distribution thermodynamic data obtained by filtering and the first population distribution thermodynamic data can be the same as much as possible, and the output population distribution thermodynamic data with high resolution can be faithful to the input population distribution thermodynamic data with low resolution as much as possible. Optionally, the normalization processing in step 603 may not be performed, and the population weight values of all the unit areas output in step 602 are directly determined as the population weight data of the target area, and then the filtering result is scaled after filtering, so that the number of people in the same initial unit area in the second population distribution thermodynamic data that is finally output is the same as the number of people in the first population distribution thermodynamic data. The specific treatment may be as follows:

for each initial unit area, acquiring the number of people corresponding to the initial unit area (which can be called as initial number of people) in the first human mouth distribution thermodynamic data, determining the sum of the number of people corresponding to all the unit areas included in the initial unit area in the filtering result, namely the total number of people of the initial unit area, determining the ratio of the initial number of people to the total number of people, and multiplying the number of people corresponding to each unit area included in the initial unit area by the ratio in the filtering result to obtain the adjusted number of people. And determining the adjusted number of people corresponding to all unit areas in the target area as second population distribution thermodynamic data of the target area.

In the above process, p₁、p₂、……p_NAnd theta values can be obtained by learning based on the population distribution thermodynamic data which is accurately detected, and the corresponding learning method can be as follows:

first, sample population distribution thermodynamic data of a precisely detected sample area is obtained, the sample population distribution thermodynamic data including the number of people per unit area in the sample area, the unit area being determined according to a target resolution, such as 10m × 10m. The precise detection mode can be various, for example, the precise detection mode is obtained by analyzing monitoring video images, or the precise detection mode is obtained by detecting the position of the terminal through a base station, and the like. And then, performing resolution reduction processing on the sample population distribution thermodynamic data, specifically, for each initial unit area in the sample area, adding the number of people in all unit areas included in the initial unit area to obtain the number of people in the initial unit area, wherein the number of people in all the initial unit areas in the sample area constitutes the population distribution thermodynamic data after resolution reduction. The initial unit area is determined according to an initial resolution, such as 200m × 200m. Then, the population is decreased in resolutionThe distribution thermodynamic data is the first population distribution thermodynamic data, and the first population distribution thermodynamic data is processed by the process to obtain the second population distribution thermodynamic data. During processing, step 602 uses the calculation formula for p₁、p₂、……p_NAnd θ is unknown, then the second population distribution thermodynamic data obtained at this time is an expression represented by these unknowns, and the correct value of the second population distribution thermodynamic data should be the sample population distribution thermodynamic data, so the expression should be equal to the sample population distribution thermodynamic data, and thus p is established₁、

p₂、……p_NAnd theta. By means of a large number of samples, a large number of p can be established₁、p₂、……p_NAnd theta, and regression analysis processing is performed on these relational expressions to obtain p₁、p₂、……p_NAnd the value of θ.

In the above process, the first filtering is used to obtain population distribution thermodynamic data with high resolution, and in the processing process described below, the region subdivision type data in the target sub-region included in the target region is obtained, and the first filtering result is further filtered for the second time to obtain population distribution thermodynamic data with high resolution. The corresponding processing flow can be seen in fig. 9, which includes the following steps:

901, obtaining region attribute data of the target region.

And 902, determining a population weight value corresponding to each unit area in the target area based on the attribute value of the region attribute corresponding to each unit area in the region attribute data and the corresponding relationship between the attribute value of the region attribute and the population weight value.

And 903, for each initial unit area in the target area, performing normalization processing on the population weight values corresponding to all the unit areas in the initial unit area to obtain a normalized population weight value corresponding to each unit area.

And 904, determining the normalized population weight values corresponding to all unit areas in the target area as the primary population weight data of the target area.

The first-level population weight data and the second-level population weight data in the later steps are population weight data determined based on different parameters, and are respectively used for the first filtering and the second filtering, and the values of the first-level population weight data and the second-level population weight data may be different, but the essential meanings of the first-level population weight data and the second-level population weight data are the same, and are data describing the high and low probability of population distribution at different positions in a geographic area. Accordingly, the population weight value may also be referred to herein as a primary population weight value.

905, performing interpolation processing on the first population distribution thermodynamic data of the target area to obtain third population distribution thermodynamic data of the target area.

And 906, filtering the third population distribution thermodynamic data of the target area based on the first-level population weight data, the size of the target filtering window and the sliding step length of the target window to obtain a first filtering result.

The processing of steps 901-906 is similar to the processing of steps 601-606, and the relevant description in the above flow can be referred to. The difference is that the filtering result of step 606 is directly used as the finally outputted second population distribution thermal data, and the filtering result of step 906 is further processed to obtain the finally outputted second population distribution thermal data.

907, obtaining the region subdivision type data of the target sub-region in the target region.

Where the target sub-region is a part or all of the target region, the relationship between the target sub-region and the target region may be as shown in fig. 10. The region segment type data has already been explained in the beginning of the embodiments of the present application, and here, the region segment type data includes a type value of the region segment type corresponding to each unit region in the target sub-region.

The computer device may determine one or more target sub-regions in the target region. The manner of determining the target sub-region can vary, and several ways are listed here:

in the first mode, a target sub-region is artificially selected in the target region.

In the second method, first, a unit area of a designated area type is specified in the target area. Wherein the specified zone type may be set by a technician based on actual needs. For example, the designated zone type may be one or more of office building, park, mall, etc. types. Then, a target sub-area composed of unit areas of the designated area type is determined. Specifically, in a unit area of a designated area type, unit areas adjacent to each other and having the same area type may be determined as one target sub-area.

Optionally, for each determined target sub-region, it is determined whether the target sub-region is a rectangle placed in the forward direction, where each side of the rectangle is parallel to the longitude line or the latitude line. If the target sub-region is not a rectangle placed in the forward direction, the target sub-region may be adjusted, a minimum circumscribed rectangle placed in the forward direction of the target sub-region may be determined, and the target sub-region is adjusted to a region corresponding to the minimum circumscribed rectangle. If the target sub-region is a forward-placed rectangle, no adjustment may be made to the target sub-region. In the case that the target sub-region is not a forward placed rectangle, if the target sub-region can be divided into a plurality of forward placed rectangles, other processing methods can also be adopted, and the processing methods can be: and dividing the target sub-area into a plurality of rectangles which are placed in the forward direction, wherein each rectangle which is placed in the forward direction is used as one target sub-area.

And for each determined target sub-area, the region subdivision type data of the target sub-area can be obtained, and the subsequent steps are processed. The region subdivision type data classifies the region types more finely than the region type data, for example, a park can subdivide grasslands, roads, pavilions, ponds and the like. The geographical subdivision type data may be retrieved from a background server of the map application in a similar manner as step 601, or the records may be manually collected, i.e. viewed and recorded by a worker to the site.

And 908, determining a population weight value corresponding to each unit area in the target sub-area based on the type value of the region subdivision type corresponding to each unit area in the target sub-area and the corresponding relationship between the type value and the population weight value.

Here, the population weight value may also be referred to as a secondary population weight value.

This step is similar to the processing manner of step 602, and may also adopt a correspondence table or a calculation relation, which is referred to in the above embodiments, except that the attribute referred to for determining the population weight value is a region segment type.

And 909, for each of the target sub-areas, determining the population weight influence value of each of the plurality of other unit areas on the unit area based on the population weight values corresponding to the plurality of other unit areas other than the unit area in the target sub-area and the distances between the unit area and the plurality of other unit areas, and adjusting the population weight value corresponding to the unit area based on the population weight influence values of each of the plurality of other unit areas on the unit area to obtain the adjusted population weight value of the unit area.

This step adjusts the population weight value of each unit area in the target sub-area in consideration of the mutual influence of the population weight values between different unit areas. The following describes the adjustment process of the population weight value of a unit area:

The adjusted population weight value for each unit area in the target sub-area may be determined based on the above.

Optionally, the standard deviation σ is_xAnd standard deviation σ_yThe same value, such as 1, may also be used.

Alternatively, other formula forms may be used, for example, the population weight influence value is equal to the product of the straight-line distance and a fixed coefficient, and the like.

Alternatively, the population weight value corresponding to each unit area in the target sub-area output in step 908 may be directly subjected to the subsequent processing without performing the adjustment processing of the population weight value in step 909.

And 910, for each initial unit area in the target sub-area, normalizing the adjusted population weight values corresponding to all the unit areas in the initial unit area to obtain a normalized population weight value corresponding to each unit area.

This step is similar to the processing of step 603, and can be referred to in the related description.

911, determining the normalized population weight values corresponding to all the unit areas in the target sub-area as the second-level population weight data of the target sub-area.

The secondary population weight data comprises a population weight value corresponding to each unit area in the target area.

And 912, performing secondary filtering processing on the part, corresponding to the target subregion, in the first filtering result based on the secondary population weight data of the target subregion, the size of the target filtering window and the sliding step length of the target window to obtain a second filtering result.

The first filtering result is data corresponding to the whole target region, step 912 may only take the portion of the first filtering result corresponding to the target subregion for filtering, and for the portion of the first filtering result not corresponding to the target subregion, this step may not do so. The secondary population weight data is data corresponding to the target sub-region, and the secondary population weight data and the portion of the first filtered result corresponding to the target sub-region are based on the target resolution, so the two data have the same spatial distribution, e.g., they are both 6 × 6 matrices. The corresponding filtering process is similar to the filtering process of step 606, and reference may be made to the related description.

913, determining the second filtering result and the portion of the first filtering result not corresponding to the target sub-area as the second population distribution thermal data of the target area.

In the processing process, a first filtering result is obtained by adopting a processing mode of firstly interpolating and then filtering the population distribution thermodynamic data with low resolution. Optionally, after the first-level population weight data is determined, interpolation processing may be directly performed on the population distribution thermodynamic data with the low resolution based on the first-level population weight data, so as to obtain the population distribution thermodynamic data with the high resolution. The specific processing can be referred to the above related contents.

In the processing process, the first-level population weight data is used for filtering the third population distribution thermodynamic data. Optionally, a filtering processing mode may not be adopted, and the first-level population weight data and the third population thermal distribution data are directly multiplied by each other in a bit-by-bit manner to obtain first intermediate data, where the first intermediate data corresponds to the first filtering result. The specific processing can be referred to the above related contents.

In the processing process, the first filtering result is filtered by using the second-level population weight data. Optionally, the second population distribution thermodynamic data may be obtained by directly multiplying the second-level population weight data by the first filtering result in a bit-by-bit manner without using a filtering processing method. The specific processing can be seen in the above related contents.

In the above processing procedure, step 903 and step 910 perform normalization processing. Optionally, the two normalization processes may not be performed, the population weight value output in step 902 is directly determined as the first-level population weight data of the target area, the population weight value output in step 909 is determined as the second-level population weight data of the target area, then, after the second filtering, the combined data of the part of the first filtering result that does not correspond to the target sub-area and the second filtering result is determined, and the combined data is scaled to obtain the second population distribution thermodynamic data, so that the number of people in the same initial unit area of the finally output second population distribution thermodynamic data is the same as the number of people in the same initial unit area of the first population distribution thermodynamic data. The specific processing can be seen in the above related contents.

Step 902 may also involve p in the above process₁、p₂、……p_NAnd the value of theta can be learned based on the learning method described above, and the flow of fig. 6 is still used to process the population distribution thermodynamic data after resolution reduction, and finally determine p₁、p₂、……p_NAnd the value of θ. Additionally, step 908 may involve pre-learning constants in the calculation relationships if the calculation relationships are also used to calculate population weight values. Can be in determining p₁、p₂、……p_NAnd after the value of theta is taken, learning is carried out by adopting a similar learning method. Alternatively, the values of the constants involved in

steps

902 and 908 may be learned together using the learning method described above.

The following describes in detail a processing manner of the case where the target sub-area is a multi-story building area, and the corresponding processing may be as shown in fig. 11, and includes the following steps:

region attribute data of the target region is acquired 1101.

And 1102, determining a population weight value corresponding to each unit area in the target area based on the attribute value of the region attribute corresponding to each unit area in the region attribute data and the corresponding relationship between the attribute value of the region attribute and the population weight value.

1103, for each initial unit area in the target area, normalizing the population weight values corresponding to all unit areas in the initial unit area to obtain a normalized population weight value corresponding to each unit area.

And 1104, determining the normalized population weight values corresponding to all the unit areas in the target area as primary population weight data of the target area.

1105, performing interpolation processing on the first population distribution thermodynamic data of the target area to obtain third population distribution thermodynamic data of the target area.

1106, filtering the third population distribution thermodynamic data of the target area based on the first-level population weight data of the target area, the size of the target filtering window and the sliding step length of the target window to obtain a first filtering result.

The processing of steps 1101-1106 is similar to the processing of steps 601-606, and the relevant description in the above flow can be referred to. The difference is that the filtering result of step 606 is directly used as the finally outputted second population distribution thermal data, and the filtering result of step 1106 is further processed to obtain the finally outputted second population distribution thermal data.

1107, obtain the region subdivision type data of the target sub-region in the target region.

The region subdivision type data comprises sub region subdivision type data corresponding to each layer. The sub-region subdivision type data corresponding to the layer comprises a type value of the region subdivision type corresponding to each unit region in the target sub-region in the layer.

The process of determining the target sub-area and the process of acquiring the zone subdivision type data are similar to step 907, and the specific process can be referred to the related contents above.

1108, for each floor of the multi-floor building, determining a corresponding population weight value of each unit area in the target sub-area on the floor based on the type value of the area subdivision type corresponding to each unit area in the target sub-area on the floor and the corresponding relation between the type value and the population weight value.

1109, in each floor of the multi-story building, for each unit area in the target sub-area, determining a population weight influence value of each of the plurality of other unit areas on the unit area based on a population weight value corresponding to a plurality of other unit areas other than the unit area in the target sub-area and a distance between the unit area and each of the plurality of other unit areas, and adjusting the population weight value corresponding to the unit area based on the population weight influence value of each of the plurality of other unit areas on the unit area to obtain an adjusted population weight value of the unit area.

The processing performed on each layer in steps 1108-1109 is the same as steps 908-909, and the specific processing can be referred to the related contents above.

1110, for each initial unit area in the target sub-area, performing normalization processing on the adjusted population weight values of all the unit areas in the initial unit area in all the layers to obtain a normalized population weight value of each unit area in each layer.

For example, the normalization processing in this step is illustrated, where the initial unit area size is 200m × 200m, the unit area size is 10m × 10m, and there are 10 floors of the building, then 400 adjusted population weight values are corresponding to each floor of one initial unit area, and the 10 floors totally include 4000 adjusted population weight values, and for one initial unit area, the 4000 population weight values need to be normalized.

1111, respectively determining the normalized population weight values corresponding to all unit areas of the target sub-area in each layer as the sub-population weight data corresponding to each layer, and obtaining the secondary population weight data of the target sub-area.

The secondary population weight data comprises sub population weight data corresponding to each layer.

And 1112, for each layer of the multi-layer building, performing re-filtering processing on the part, corresponding to the target subregion, in the first filtering result based on the sub-human mouth weight data, the target filtering window size and the target window sliding step length of the layer to obtain the filtering result corresponding to the layer.

And performing secondary filtering processing on the first filtering result by using the sub-population weight data of each layer to obtain a filtering result corresponding to each layer, wherein the filtering processing process of each layer is similar to the filtering processing process of the step 606, and the specific processing can refer to the related contents.

1113, combining the filtering results corresponding to each layer to determine a second filtering result.

Wherein the second filtering result includes multiple layers of data.

1114, determining the second filtered result and the part of the first filtered result not corresponding to the target sub-area as the second population distribution thermal data of the target area.

And the second population distribution thermal data is multi-layer data in the part of the target subarea and single-layer data in the part outside the target subarea.

In the processing process, a first filtering result is obtained by adopting a processing mode of firstly interpolating and then filtering the population distribution thermodynamic data with low resolution. Optionally, after the first-level population weight data is determined, interpolation processing may be directly performed on the population distribution thermodynamic data with the low resolution based on the first-level population weight data, so as to obtain the population distribution thermodynamic data with the high resolution. The specific processing can be seen in the above related contents.

In the processing process, the first filtering result is filtered by using the second-level population weight data. Optionally, the sub-population weight data of each layer may be directly multiplied by the first filtering result in bit without using a filtering processing mode. The specific processing can be referred to the above related contents.

In the above processing procedure, step 1103 and step 1110 perform normalization processing. Optionally, the two-step normalization processing may not be performed, the population weight value output in step 1102 is directly determined as the first-level population weight data of the target area, the population weight value output in step 1109 is determined as the second-level population weight data of the target area, then, after the second filtering, the combined data of the second filtering result and the part of the first filtering result that does not correspond to the target sub-area is determined, scaling adjustment is performed on the combined data, so as to obtain the second population distribution thermodynamic data, and the number of people in the same initial unit area of the finally output second population distribution thermodynamic data is the same as the number of people in the same initial unit area of the first population distribution thermodynamic data. The specific processing can be referred to the above related contents.

Step 1102 may also involve p in the above process₁、p₂、……p_NAnd the learning of the value of theta can be based on the learning method described above, still with the help of the flow chart of fig. 6 for resolution reductionProcessing the population distribution thermodynamic data after rate to finally determine p₁、p₂、……p_NAnd the value of θ. Step 1108 also involves pre-learning constants in the computational relationships, if the computational relationships are also used to calculate population weight values. Can be in determining p₁、p₂、……p_NAnd after the value of theta is taken, learning is carried out by adopting a similar learning method. Alternatively, the values of the constants involved in

steps

1102 and 1108 may be learned together using the learning method described above.

Based on the same technical concept, the present application further provides an apparatus for determining population distribution thermodynamic data, which can be applied to the computer device provided in the above embodiment, as shown in fig. 12, and the apparatus includes:

an obtaining module 1210, configured to obtain region attribute data of a target area, where the region attribute data includes an attribute value of at least one region attribute corresponding to each unit area in the target area, and the unit area is determined according to a target resolution, and the region attribute is a region attribute that has an effect on human mouth. The acquiring function in the

above steps

601, 901, and 1101, and other implicit steps may be implemented specifically.

The weight determining module 1220 is configured to determine, based on the region attribute data of the target region, primary population weight data of the target region, where the primary population weight data includes a population weight value corresponding to each unit region in the target region. The weight determination functions in the above-described steps 602-604, 902-904, 1102-1104, as well as other implicit steps, may be implemented in particular.

A resolution increasing module 1230, configured to determine second population distribution thermodynamic data of the target area based on first population distribution thermodynamic data of the target area and first-level population weight data of the target area, where the first population distribution thermodynamic data includes a number of people corresponding to each initial unit area in the target area, the initial unit area is determined according to an initial resolution, the second population distribution thermodynamic data includes a number of people corresponding to each unit area in the target area, and the target resolution is greater than the initial resolution. The resolution enhancement functions in steps 605-606, 905-913, 1105-1114, and other implicit steps described above may be implemented in particular.

In one possible implementation, the at least one geographic attribute having an impact on human mouth includes: type of territory and/or number of building floors.

In a possible implementation manner, the weight determining module is configured to: determining a population weight value corresponding to each unit area in the target area based on the attribute value of at least one region attribute corresponding to each unit area in the target area and the corresponding relationship between the attribute value of the region attribute and the population weight value; for each initial unit area in the target area, performing normalization processing on the population weight values corresponding to all the unit areas in the initial unit area to obtain a normalized population weight value corresponding to each unit area; and determining the normalized population weight values corresponding to all unit areas in the target area as primary population weight data of the target area.

In a possible implementation manner, the correspondence between the attribute value of the region attribute and the population weight value is a calculation relation between the attribute value of the region attribute and the population weight value, where the calculation relation is:

In one possible implementation manner, the resolution increasing module 1230 is configured to: performing interpolation processing on the first population distribution thermodynamic data of the target area to obtain third population distribution thermodynamic data of the target area, wherein the third population distribution thermodynamic data comprises the number of people corresponding to each unit area in the target area; determining second population distribution thermodynamic data of the target area based on the third population distribution thermodynamic data of the target area and the primary population weight data of the target area.

In a possible implementation manner, the resolution increasing module 1230 is configured to: filtering third population distribution thermodynamic data of the target area based on the first-level population weight data, the size of a target filtering window and the sliding step length of the target window of the target area to obtain a first filtering result; determining second population distribution thermodynamic data for the target region based on the first filtering result.

In a possible implementation manner, the resolution increasing module 1230 is configured to: obtaining region subdivision type data of a target sub-region in a target region, wherein the region subdivision type data comprise a type value of a region subdivision type corresponding to each unit region in the target sub-region; determining secondary population weight data of the target sub-region based on the region subdivision type data of the target sub-region, wherein the secondary population weight data comprise a population weight value corresponding to each unit region in the target sub-region; determining second population distribution thermodynamic data of the target region based on the first filtering result and secondary population weight data of the target sub-region.

In one possible implementation manner, the resolution increasing module 1230 is configured to: determining a population weight value corresponding to each unit area in the target sub-area based on the type value corresponding to each unit area in the target sub-area and the corresponding relationship between the type value and the population weight value; for each unit area in the target sub-area, determining population weight influence values of the plurality of other unit areas on the unit area based on population weight values corresponding to a plurality of other unit areas except the unit area in the target sub-area and distances between the unit area and the plurality of other unit areas, respectively, and adjusting the population weight values corresponding to the unit area based on the population weight influence values of the plurality of other unit areas on the unit area, respectively, to obtain an adjusted population weight value of the unit area; for each initial unit area in the target sub-area, performing normalization processing on the adjusted population weight values corresponding to all unit areas in the initial unit area to obtain a normalized population weight value corresponding to each unit area; and determining the normalized population weight values corresponding to all unit areas in the target sub-area as the secondary population weight data of the target sub-area.

In one possible implementation manner, the resolution increasing module 1230 is configured to: performing secondary filtering processing on the part, corresponding to the target subarea, in the first filtering result based on the secondary population weight data of the target subarea, the size of a target filtering window and the sliding step length of the target window to obtain a second filtering result; and determining the second filtering result and the part of the first filtering result, which does not correspond to the target subarea, as second population distribution thermodynamic data of the target subarea.

In one possible implementation, the target sub-area is a multi-story building area. The region subdivision type data comprises sub region subdivision type data corresponding to each layer, and the sub region subdivision type data corresponding to each layer comprises a type value of the region subdivision type corresponding to each unit area in the target sub region. The secondary population weight data comprises sub population weight data corresponding to each layer, and the sub population weight data corresponding to each layer comprises a population weight value corresponding to each unit area in the target sub-area on the layer.

The resolution increasing module 1230 is configured to: for each layer, based on the sub-population weight data, the size of a target filtering window and the sliding step length of the target window of the layer, performing secondary filtering processing on the part, corresponding to the target sub-region, in the first filtering result to obtain a filtering result corresponding to the layer; and combining the filtering results corresponding to each layer to determine a second filtering result.

It should be noted that the obtaining module 1210, the weight determining module 1220 and the resolution increasing module 1230 may be implemented by a processor, or implemented by a processor and a memory.

It should be noted that: the above embodiment provides an apparatus for determining population distribution thermodynamic data, which is only illustrated by the above division of the functional modules when performing the process of determining population distribution thermodynamic data, and in practical applications, the above function distribution may be completed by different functional modules according to needs, that is, the internal structure of the apparatus is divided into different functional modules, so as to complete all or part of the above described functions. In addition, the apparatus for determining population distribution thermodynamic data and the method for determining population distribution thermodynamic data provided in the foregoing embodiments belong to the same concept, and specific implementation processes thereof are detailed in the method embodiments, and are not described herein again.

In the above embodiments, all or part of the implementation may be realized by software, hardware, firmware or any combination thereof, and when the implementation is realized by software, all or part of the implementation may be realized in the form of a computer program product. The computer program product comprises one or more computer program instructions which, when loaded and executed on a device, cause a process or function according to an embodiment of the application to be performed, in whole or in part. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (e.g., coaxial cable, fiber optic, digital subscriber line) or wirelessly (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by the device or a data storage device, such as a server, a data center, etc., that is integrated into one or more available media. The usable medium may be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape, etc.), an optical medium (such as a Digital Video Disk (DVD), etc.), or a semiconductor medium (such as a solid state disk, etc.).

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the storage medium may be a read-only memory, a magnetic disk or an optical disk.

The above description is intended to be illustrative only, and should not be taken as limiting the scope of the present application, in which any modifications, equivalents, improvements and the like that fall within the spirit of the present application are intended to be included within the scope of the present application.

Claims

1. A method of determining population distribution thermodynamic data, the method comprising:

acquiring region attribute data of a target region, wherein the region attribute data comprises an attribute value of at least one region attribute corresponding to each unit region in the target region, the unit region is determined according to a target resolution, and the region attribute is a region attribute having an influence on human mouth;

determining primary population weight data of the target area based on the region attribute data of the target area, wherein the primary population weight data comprises a population weight value corresponding to each unit area in the target area;

determining second population distribution thermodynamic data of the target area based on first population distribution thermodynamic data of the target area and first-level population weight data of the target area, wherein the first population distribution thermodynamic data comprises the number of people corresponding to each initial unit area in the target area, the initial unit area is determined according to an initial resolution, the second population distribution thermodynamic data comprises the number of people corresponding to each unit area in the target area, and the target resolution is greater than the initial resolution.

2. The method of claim 1, wherein the at least one regional attribute having an effect on human mouth comprises: zone type and/or number of building floors.

3. The method of claim 1 or 2, wherein determining primary demographic weight data for the target zone based on the zone attribute data for the target zone comprises:

determining a population weight value corresponding to each unit area in the target area based on the attribute value of at least one region attribute corresponding to each unit area in the target area and the corresponding relationship between the attribute value of the region attribute and the population weight value;

for each initial unit area in the target area, performing normalization processing on the population weight values corresponding to all the unit areas in the initial unit area to obtain a normalized population weight value corresponding to each unit area;

and determining the normalized population weight values corresponding to all unit areas in the target area as the primary population weight data of the target area.

4. The method according to claim 3, wherein the correspondence between the attribute value of the region attribute and the population weight value is a calculation relationship between the attribute value of the region attribute and the population weight value, and the calculation relationship is:

z_i＝p₁×x_i1+p₂×x_i2+......+p_N×x_iN+θ；

wherein x is_i1、x_i2、……x_iNRespectively, an attribute value, z, of each of the territorial attributes in the unit area i in the target area_iIs the population weight, p, of the unit area i₁、p₂、……p_NAnd θ is a constant.

5. A method according to any of claims 1-4, wherein determining second population distribution thermodynamic data for the target area based on the first population distribution thermodynamic data for the target area and the primary population weight data for the target area comprises:

performing interpolation processing on the first population distribution thermodynamic data of the target area to obtain third population distribution thermodynamic data of the target area, wherein the third population distribution thermodynamic data comprises the number of people corresponding to each unit area in the target area;

determining second population distribution thermodynamic data of the target area based on the third population distribution thermodynamic data of the target area and the primary population weight data of the target area.

6. The method of claim 5, wherein determining second population distribution thermal data for the target area based on the third population distribution thermal data for the target area and the primary population weight data for the target area comprises:

filtering third population distribution thermodynamic data of the target area based on the first-level population weight data, the size of a target filtering window and the sliding step length of the target window of the target area to obtain a first filtering result;

determining second population distribution thermodynamic data for the target region based on the first filtering result.

7. The method of claim 6, wherein determining second population distribution thermodynamic data for the target area based on the first filtered result comprises:

obtaining region subdivision type data of a target sub-region in a target region, wherein the region subdivision type data comprise a type value of a region subdivision type corresponding to each unit region in the target sub-region;

determining secondary population weight data of the target sub-area based on the region subdivision type data of the target sub-area, wherein the secondary population weight data comprise population weight values corresponding to each unit area in the target sub-area;

and determining second population distribution thermodynamic data of the target region based on the first filtering result and the secondary population weight data of the target subregion.

8. The method of claim 7, wherein determining secondary population weight data for the target sub-region based on the regional subdivision type data for the target sub-region comprises:

determining a population weight value corresponding to each unit area in the target sub-area based on the type value corresponding to each unit area in the target sub-area and the corresponding relationship between the type value and the population weight value;

for each unit area in the target sub-area, determining population weight influence values of the plurality of other unit areas on the unit area based on population weight values corresponding to a plurality of other unit areas except the unit area in the target sub-area and distances between the unit area and the plurality of other unit areas, respectively, and adjusting the population weight values corresponding to the unit area based on the population weight influence values of the plurality of other unit areas on the unit area, respectively, to obtain an adjusted population weight value of the unit area;

for each initial unit area in the target sub-area, performing normalization processing on the adjusted population weight values corresponding to all unit areas in the initial unit area to obtain a normalized population weight value corresponding to each unit area;

and determining the normalized population weight values corresponding to all unit areas in the target sub-area as the secondary population weight data of the target sub-area.

9. The method of claim 7 or 8, wherein determining second population distribution thermodynamic data of the target region based on the first filtering result and secondary population weight data of the target sub-region comprises:

performing secondary filtering processing on the part, corresponding to the target subarea, in the first filtering result based on the secondary population weight data of the target subarea, the size of a target filtering window and the sliding step length of the target window to obtain a second filtering result;

and determining the second filtering result and the part of the first filtering result, which does not correspond to the target subarea, as second population distribution thermodynamic data of the target subarea.

10. The method of claim 9, wherein the target sub-area is a multi-story building area; the region subdivision type data comprises sub-region subdivision type data corresponding to each layer, and the sub-region subdivision type data corresponding to each layer comprises a type value of the region subdivision type corresponding to each unit area in the target sub-region on the layer; the secondary population weight data comprises sub population weight data corresponding to each layer, and the sub population weight data corresponding to each layer comprises a population weight value corresponding to each unit area in the target sub-area on the layer;

performing secondary filtering processing on the part, corresponding to the target subregion, in the first filtering result based on the secondary population weight data of the target subregion, the target filtering window size and the target window sliding step length to obtain a second filtering result, wherein the secondary filtering processing comprises:

for each layer, based on the sub-population weight data, the size of a target filtering window and the sliding step length of the target window of the layer, performing secondary filtering processing on the part, corresponding to the target sub-region, in the first filtering result to obtain a filtering result corresponding to the layer;

and combining the filtering results corresponding to each layer to determine a second filtering result.

11. An apparatus for determining population distribution thermodynamic data, the apparatus comprising:

the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring region attribute data of a target region, the region attribute data comprises an attribute value of at least one region attribute corresponding to each unit region in the target region, the unit region is determined according to a target resolution, and the region attribute is a region attribute having an influence on human mouth;

a weight determining module, configured to determine, based on region attribute data of the target region, primary population weight data of the target region, where the primary population weight data includes a population weight value corresponding to each unit region in the target region;

a resolution increasing module, configured to determine second population distribution thermodynamic data of the target area based on first population distribution thermodynamic data of the target area and first-level population weight data of the target area, where the first population distribution thermodynamic data includes a number of people corresponding to each initial unit area in the target area, the initial unit area is determined according to an initial resolution, the second population distribution thermodynamic data includes a number of people corresponding to each unit area in the target area, and the target resolution is greater than the initial resolution.

12. The apparatus of claim 11, wherein the at least one geographic attribute that has an effect on the mouth comprises: zone type and/or number of building floors.

13. The apparatus of claim 11 or 12, wherein the weight determining module is configured to:

14. The apparatus of claim 13, wherein the correspondence between the attribute value of the region attribute and the population weight value is a calculation relationship between the attribute value of the region attribute and the population weight value, and the calculation relationship is:

z_i＝p₁×x_i1+p₂×x_i2+......+p_N×x_iN+θ；

wherein x is_i1、x_i2、……x_iNRespectively, an attribute value, z, of each of the territorial attributes in a unit area i in the target area_iIs the population weight, p, of the unit area i₁、p₂、……p_NAnd θ is a constant.

15. The apparatus of any one of claims 11-14, wherein the resolution enhancement module is configured to:

16. The apparatus of claim 15, wherein the resolution enhancement module is configured to:

17. The apparatus of claim 16, wherein the resolution enhancement module is configured to:

determining secondary population weight data of the target sub-region based on the region subdivision type data of the target sub-region, wherein the secondary population weight data comprise a population weight value corresponding to each unit region in the target sub-region;

18. The apparatus of claim 17, wherein the resolution enhancement module is configured to:

for each unit area in the target sub-area, determining population weight influence values of a plurality of other unit areas to the unit area respectively based on population weight values corresponding to the plurality of other unit areas except the unit area in the target sub-area and distances between the unit area and the plurality of other unit areas respectively, and adjusting the population weight values corresponding to the unit area based on the population weight influence values of the plurality of other unit areas to the unit area respectively to obtain an adjusted population weight value of the unit area;

19. The apparatus of claim 17 or 18, wherein the resolution enhancement module is configured to:

20. The apparatus of claim 19, wherein the target sub-area is a multi-story building area; the region subdivision type data comprises sub-region subdivision type data corresponding to each layer, and the sub-region subdivision type data corresponding to each layer comprises a type value of the region subdivision type corresponding to each unit area in the target sub-region on the layer; the secondary population weight data comprises sub population weight data corresponding to each layer, and the sub population weight data corresponding to each layer comprises a population weight value corresponding to each unit area in the target sub-area on the layer;

the resolution raising module is configured to:

21. A computer device, comprising a memory for storing computer instructions and a processor;

the processor executes computer instructions stored by the memory to cause the computer device to perform the method of any of claims 1 to 10.

22. A computer-readable storage medium, characterized in that it stores computer program code which, when executed by a computer device, performs the method of any of the preceding claims 1 to 10.