WO2024103770A1 - 空间划分方法、装置及存储介质 - Google Patents

空间划分方法、装置及存储介质 Download PDF

Info

Publication number
WO2024103770A1
WO2024103770A1 PCT/CN2023/104273 CN2023104273W WO2024103770A1 WO 2024103770 A1 WO2024103770 A1 WO 2024103770A1 CN 2023104273 W CN2023104273 W CN 2023104273W WO 2024103770 A1 WO2024103770 A1 WO 2024103770A1
Authority
WO
WIPO (PCT)
Prior art keywords
tazs
atomic
taz
data
atom
Prior art date
Application number
PCT/CN2023/104273
Other languages
English (en)
French (fr)
Inventor
周银生
黄骞
沈仲明
原朝
王昊
许立言
于洪斌
唐金潼
姜河之是
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2024103770A1 publication Critical patent/WO2024103770A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services

Definitions

  • the present application relates to the field of urban planning, and in particular to a space division method, device and storage medium.
  • the urban area division method based on trajectory data is used for spatial division. This method is based on human activity data from taxis, and uses trajectory extraction, data cleaning, data filtering and interpolation, coordinate transformation, etc. to pre-process the data to obtain a trajectory data set after plane coordinate transformation. Then, the trajectory data set is used for grid division; after grid division, the binary matrix obtained by grid division is divided into urban areas using morphological methods.
  • the urban sub-areas obtained by this method are divided based on the standard grid (grid) as the smallest unit. Since the grid is square and the edges are not smooth, the boundary expression is poor. On the other hand, since the above human activity data comes from taxis and is not representative enough, the division results are biased.
  • the present application discloses a space division method, device and storage medium, which can achieve a division result that better meets the needs of the real world.
  • an embodiment of the present application provides a spatial division method.
  • the method may include: obtaining attribute data and/or interaction data of a preset area. Then, according to the attribute data of the preset area, a set of attribute data corresponding to multiple atomic flow autonomous domains TAZ is obtained, and/or according to the interaction data of the preset area, a set of interaction data corresponding to multiple atomic flow autonomous domains TAZ is obtained, and according to the multiple atomic TAZs, a set of spatial neighboring data corresponding to the multiple atomic TAZs is obtained.
  • any attribute data in the attribute data set represents the attribute of the corresponding atomic TAZ in the multiple atomic TAZs
  • any interaction data in the interaction data set represents the interaction feature between two atomic TAZs in the multiple atomic TAZs
  • any spatial neighboring data in the spatial neighboring data set represents the proximity relationship between two atomic TAZs in the multiple atomic TAZs.
  • the multiple atomic TAZs are obtained by dividing the preset area.
  • the spatial division result of the preset area is obtained according to the attribute data set and/or interaction data set corresponding to the multiple atomic TAZs, and the set of spatial neighboring data corresponding to the multiple atomic TAZs.
  • the spatial division result of the preset area can be obtained based on the attribute data set and the spatial neighboring data set.
  • the spatial division result of the preset area can also be obtained based on the interaction data set and the spatial neighboring data set.
  • the spatial division result of the preset area can also be obtained based on the interaction data set, the attribute data set and the spatial neighboring data set.
  • the spatial division result of the preset area is obtained by acquiring the attribute data and/or interaction data of the preset area, and obtaining the attribute data set of multiple atomic TAZs according to the attribute data, and/or obtaining the interaction data set of multiple TAZs according to the interaction data, and obtaining the spatial proximity data set of multiple atomic TAZs according to the multiple atomic TAZs.
  • spatial division is realized based on the attribute data and/or interaction data, which is convenient for introducing various types of data for AtomTAZ in different scenarios, and the division is based on the AtomTAZ unit, so that the division result is more in line with the needs of the real world.
  • This example can input non-interactive static data (such as semantic attributes) of node (atomic TAZ) attributes, and also considers interactive dynamic data (such as travel flow), so that the basic static environmental elements of the city and human dynamic activities can affect the division results at the same time, and it is scalable to face more scenarios.
  • non-interactive static data such as semantic attributes
  • node (atomic TAZ) attributes such as node (atomic TAZ) attributes
  • interactive dynamic data such as travel flow
  • this solution can also achieve a trade-off between different constraints by adjusting parameters, and adapt to the demand priorities of different goals, so that the characteristics of communication activities can be transformed from the operator's vague experience into an executable TAZ division scheme, thereby reducing waste and simplifying the operator's Process and the demand for improving efficiency.
  • the preset area is triangulated based on the multiple atomic TAZs, with the land boundary of the preset area as a constraint, to obtain a triangle set between any two atomic TAZs in the multiple atomic TAZs. Then, the triangle set between any two atomic TAZs in the multiple atomic TAZs is processed to obtain spatial proximity data between any two atomic TAZs in the multiple atomic TAZs.
  • the spatial proximity data set corresponding to the multiple atomic TAZs includes the spatial proximity data between the any two atomic TAZs.
  • This example uses the constrained Delaunay triangulation scheme to determine the spacing between AtomTAZs, and uses this value to control the morphological regularity of the partitions. This can effectively constrain the regional division results and achieve more regular and easy-to-manage TAZ partitions.
  • the triangles whose height-to-base ratio is greater than a first value and whose longest side-to-base ratio is greater than a second value are eliminated from the triangle set between any two atomic TAZs, thereby obtaining a processed triangle set between any two atomic TAZs in the plurality of atomic TAZs. Then, the median of the height of the triangles in the triangle set between any two atomic TAZs in the plurality of atomic TAZs is determined as the spatial proximity data between any two atomic TAZs in the plurality of atomic TAZs.
  • the attribute data of the preset area are respectively gathered into the multiple atomic TAZs to obtain the attribute data of each atomic TAZ in the multiple atomic TAZs.
  • the attribute data set corresponding to the multiple atomic TAZs includes the attribute data of each atomic TAZ.
  • non-interactive static data (attribute data) of node attributes can be input, so that basic static environmental elements of the city can affect the division results.
  • the interaction data of the preset area are respectively gathered into the multiple atomic TAZs to obtain the interaction data between any two atomic TAZs in the multiple atomic TAZs.
  • the interaction data set corresponding to the multiple atomic TAZs includes the interaction data between the any two atomic TAZs.
  • dynamic data of node attributes in interactive form (such as travel flow, etc.) can be input, so that the dynamic activities of urban humans affect the division results.
  • the degree of belonging of each atom TAZ in the multiple atom TAZs to each community in the preset area is obtained based on the attribute data set corresponding to the multiple atom TAZs and/or the interaction data set corresponding to the multiple atom TAZs, and the spatial neighboring data set corresponding to the multiple atom TAZs. Then, according to the degree of belonging of each atom TAZ in the multiple atom TAZs to each community in the preset area, the edge atom TAZ, the core atom TAZ of each community, and multiple core groups are determined from the multiple atom TAZs.
  • the edge atom TAZ is an atom TAZ whose degree of belonging to each community is not greater than a first degree of belonging threshold
  • the core atom TAZ of any community in the various communities is an atom TAZ whose degree of belonging to the community is greater than the first degree of belonging threshold
  • the core group is composed of core atom TAZs belonging to the same community and whose distance is less than a distance threshold.
  • the edge atom TAZ with the largest degree of belonging to the first community corresponding to the i-th core group among the M edge atom TAZs is merged into the i-th core group to obtain a first TAZ, wherein the spatial division result includes the first TAZ, M is an integer not less than 1, and i is a positive integer.
  • the core AtomTAZ, edge AtomTAZ and core group in the preset area are identified by using the community's attribution results.
  • the relatively balanced size of AtomTAZ and the relatively uniform distribution of core AtomTAZ ensure a relatively balanced partition size during the regional aggregation process, solve the problem of attribution of boundary areas within a certain range, and thus achieve effective division of large communities at an appropriate scale.
  • the method when there is a first edge atom TAZ whose distance from any core group in the core groups of the respective communities is greater than the preset distance, the method further includes: updating the first attribution threshold to obtain a second attribution threshold, wherein the second attribution threshold is less than the first attribution threshold. Then, according to the attribution of the first edge atom TAZ to the respective communities in the preset area and the second attribution threshold, the core group to which the first edge atom TAZ belongs is determined.
  • This scheme can realize that all edge atom TAZs can be aggregated into the core atom TAZ, and then multiple TAZs can be obtained, that is, the spatial division result can be obtained.
  • a first energy-saving control is performed on the equipment in the area corresponding to the first TAZ.
  • a first traffic planning is performed on the vehicles and traffic lights in the area corresponding to the first TAZ.
  • an embodiment of the present application further provides a space division device, including:
  • An acquisition module used to acquire attribute data and/or interaction data of a preset area
  • a processing module used for obtaining an attribute data set corresponding to a plurality of atomic flow autonomous domains TAZ according to the attribute data of the preset area, and/or obtaining an interaction data set corresponding to a plurality of atomic flow autonomous domains TAZ according to the interaction data of the preset area, and obtaining a spatial proximity data set corresponding to the plurality of atomic TAZs according to the plurality of atomic TAZs, wherein any attribute data in the attribute data set represents an attribute of a corresponding atomic TAZ in the plurality of atomic TAZs, any interaction data in the interaction data set represents an interaction feature between two atomic TAZs in the plurality of atomic TAZs, and any spatial proximity data in the spatial proximity data set represents a proximity relationship between two atomic TAZs in the plurality of atomic TAZs, wherein the plurality of atomic TAZs are obtained by dividing the preset area;
  • the partitioning module is used to obtain the spatial partitioning result of the preset area according to the attribute data set and/or interaction data set corresponding to the multiple atomic TAZs and the spatial neighboring data set corresponding to the multiple atomic TAZs.
  • the spatial division result of the preset area is obtained by acquiring the attribute data and/or interaction data of the preset area, and obtaining the attribute data set of multiple atomic TAZs according to the attribute data, and/or obtaining the interaction data set of multiple TAZs according to the interaction data, and obtaining the spatial proximity data set of multiple atomic TAZs according to the multiple atomic TAZs.
  • spatial division is realized based on the attribute data and/or interaction data, which is convenient for introducing various types of data for AtomTAZ in different scenarios, and the division is based on the AtomTAZ unit, so that the division result is more in line with the needs of the real world.
  • the processing module is used to:
  • the spatial proximity data between any two atomic TAZs in the multiple atomic TAZs are obtained by processing the triangle set between any two atomic TAZs in the multiple atomic TAZs, wherein the spatial proximity data set corresponding to the multiple atomic TAZs includes the spatial proximity data between the any two atomic TAZs.
  • processing module is further configured to:
  • the median of the heights of triangles in the set of triangles between any two atomic TAZs in the multiple atomic TAZs after the processing is determined as the spatial proximity data between any two atomic TAZs in the multiple atomic TAZs.
  • processing module is further configured to:
  • the attribute data of the preset area are respectively gathered into the multiple atomic TAZs to obtain the attribute data of each atomic TAZ in the multiple atomic TAZs; wherein the attribute data set corresponding to the multiple atomic TAZs includes the attribute data of each atomic TAZ.
  • processing module is further configured to:
  • the interaction data of the preset area are respectively gathered into the multiple atomic TAZs to obtain the interaction data between any two atomic TAZs in the multiple atomic TAZs; wherein the interaction data set corresponding to the multiple atomic TAZs includes the interaction data between the any two atomic TAZs.
  • the partitioning module is used to:
  • edge atom TAZs, core atom TAZs of each community, and multiple core groups are determined from the multiple atom TAZs; wherein the edge atom TAZs are atom TAZs whose degrees of belonging to each community are not greater than a first degree of belonging threshold, the core atom TAZs of any community in the multiple communities are atom TAZs whose degrees of belonging to the community are greater than the first degree of belonging threshold, and the core group is composed of core atom TAZs belonging to the same community and whose distance is less than a distance threshold;
  • the edge atom TAZ with the largest degree of belonging to the first community corresponding to the i-th core group among the M edge atom TAZs is merged into the i-th core group to obtain a first TAZ, wherein the spatial division result includes the first TAZ, M is an integer not less than 1, and i is a positive integer.
  • the partitioning module is further configured to:
  • the core group to which the first edge atom TAZ belongs is determined.
  • the device further includes a control module, which is used to:
  • the interactive data is human traffic data and/or telecommunication traffic data, performing first energy-saving control on equipment in the area corresponding to the first TAZ; and/or,
  • a first traffic planning is performed on the vehicles and traffic lights in the area corresponding to the first TAZ.
  • the present application provides a space division device, comprising a processor and a communication interface, the communication interface being used to receive and/or send data, and/or the communication interface being used to provide output and/or output to the processor, the processor being used to call computer instructions to implement a method provided in any possible implementation manner of the first aspect.
  • the present application provides a computer storage medium comprising computer instructions, which, when executed on an electronic device, enables the electronic device to execute a method provided in any possible implementation of the first aspect.
  • an embodiment of the present application provides a computer program product.
  • the computer program product runs on a computer, it enables the computer to execute a method provided in any possible implementation manner of the first aspect.
  • the device described in the second aspect, the device described in the third aspect, the computer-readable storage medium described in the fourth aspect, or the computer program product described in the fifth aspect provided above are all used to execute any method provided in the first aspect. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here.
  • FIG1 is a schematic diagram of the architecture of a space division system provided in an embodiment of the present application.
  • FIG2 is a schematic diagram of a flow chart of a space division method provided in an embodiment of the present application.
  • FIG3 is a schematic diagram of a space division method provided in an embodiment of the present application.
  • FIG4 is a schematic diagram of a flow chart of a space division method provided in an embodiment of the present application.
  • FIG5 is a schematic diagram of a division result provided in an embodiment of the present application.
  • FIG6 is a schematic diagram of the structure of a space division device provided in an embodiment of the present application.
  • FIG. 7 is a schematic diagram of the structure of another space dividing device provided in an embodiment of the present application.
  • Traffic Autonomous Zone is a spatial partitioning method based on road network, points of interest (POI) and the interaction intensity between various spatial locations.
  • Atom TAZ is the basic spatial unit used for data gridding and TAZ partitioning.
  • Geographic data can be understood as data describing the geographical shape characteristics of the preset area, such as roads, administrative divisions, etc.
  • Attribute data describes a location and the scalar attribute v it carries.
  • the scalar attribute v can be at least one of a point of interest POI, an area of interest (AOI), population heat, flow, channel distribution, age distribution, housing price, etc.
  • Interaction data describes the interaction traffic from one location to another.
  • the interaction traffic can be, for example, at least one of pedestrian traffic, vehicle traffic, trajectory, mainstream, drive test, Minimization of Drive-Test (MDT), Global Positioning System (GPS), etc.
  • MDT Minimization of Drive-Test
  • GPS Global Positioning System
  • Edge weight tensor Each type of interaction data is a layer, and each layer records the interaction values between each AtomTAZ to form a tensor.
  • the city sub-areas obtained by the existing technology are divided based on the standard grid (grid) as the smallest unit, and the boundary expression is poor.
  • the human activity data comes from taxis, it is not representative enough, so the division results are biased.
  • the present application provides a spatial division method that can achieve a division result that is more in line with the needs of the real world.
  • Schematic diagram of a space partitioning system the system includes a multi-source database and a server 103.
  • the multi-source database includes an attribute database 101 and an interaction database 102.
  • the server 103 obtains multi-source data of a preset area from a multi-source database.
  • the multi-source data may be at least one of attribute data and interaction data.
  • the multi-source data may also include geographic data.
  • the server 103 may also pre-process the data, such as format alignment according to actual scene requirements, to meet actual needs.
  • the server 103 processes the data obtained from the multi-source database to obtain multiple indicators required by the community discovery algorithm.
  • the processing includes entering the attribute data and/or the interaction data into a grid. For example, multiple atomic TAZs are obtained by dividing the preset area, and then the attribute data and/or the interaction data are combined into each atomic TAZ, so that each atomic TAZ has semantic attributes and/or interaction attributes.
  • the multiple indicators required by the community discovery algorithm may include the semantic attribute data and/or interaction attribute data of each atomic TAZ.
  • the server 103 calculates the community area division of the preset area through a community discovery algorithm, and further integrates the obtained areas to obtain the final space division result.
  • spatial division is achieved based on multi-source data, which facilitates the introduction of various types of data into AtomTAZ in different scenarios. Moreover, the division is based on AtomTAZ units, so that the division results are more in line with the needs of the real world.
  • FIG. 2 it is a flow chart of a space division method provided by an embodiment of the present application.
  • the method can be applied to the aforementioned space division system, such as the space division system shown in Figure 1.
  • the space division method shown in Figure 2 may include steps 201-203. It should be understood that this application is described in the order of 201-203 for the convenience of description, and is not intended to be limited to execution in the above order.
  • the embodiment of the present application does not limit the order of execution, execution time, number of executions, etc. of the above one or more steps.
  • the following description takes the execution subject of steps 201-203 of the space division method as a server as an example, and this application is also applicable to other execution subjects. Steps 201-203 are as follows:
  • the preset area may be, for example, a city, a province, etc.
  • the attribute data describes a location and the scalar attribute v it carries.
  • the scalar attribute v can be at least one of a point of interest POI, an area of interest AOI, population heat, channel distribution, age distribution, housing price, etc.
  • the scalar attribute v of a location can be multiple.
  • the scalar attribute v can be a continuous value, a discrete value, or a factor value.
  • the interaction data describes the interaction traffic from one location to another location.
  • the interaction traffic may be, for example, at least one of pedestrian traffic, vehicle traffic, trajectory, mainstream, drive test, Minimization of Drive Test (MDT), Global Positioning System (GPS), etc.
  • MDT Minimization of Drive Test
  • GPS Global Positioning System
  • the interaction traffic from one location to another location may be of multiple different attributes.
  • any attribute data in the attribute data set represents the attribute of the corresponding atomic TAZ in the multiple atomic TAZs
  • any interaction data in the interaction data set represents the interaction feature between two atomic TAZs in the multiple atomic TAZs
  • any spatial proximity data in the spatial proximity data set represents the proximity relationship between two atomic TAZs in the multiple atomic TAZs, wherein the multiple atomic TAZs are obtained by dividing the preset area
  • Traffic Autonomous Zone is a spatial division method based on the road network, POI and the interaction intensity between various spatial places.
  • the spatial places divided based on this method can better correspond to the same type of people, and the flow of people in each place is highly consistent, so a more reasonable functional zoning can be achieved.
  • Atomic Traffic Autonomous Zone TAZ (AtomTAZ) is the basic spatial unit used for data entry and division of TAZ.
  • the atomic TAZs do not overlap with each other and are all surface vectors.
  • the atomic TAZ is a simple polygon.
  • the actual position of the road in space can be more accurately reflected, thereby more finely reflecting the functions of other areas in the city except the roads.
  • the preset urban area can be divided into N mutually non-intersecting atomic TAZs.
  • the atom TAZ is covered with geographical information.
  • TAZ code can be generated for each AtomTAZ.
  • TAZ code (TAZCode) is a set of coding schemes for spatial calculations. The code is used to conveniently refer to each AtomTAZ, which helps in the subsequent data entry, thereby improving the calculation efficiency of the algorithm.
  • the preset area can be divided to obtain a node set.
  • obtaining, according to the multiple atomic TAZs, a spatial neighboring data set corresponding to the multiple atomic TAZs includes:
  • the spatial proximity data between any two atomic TAZs in the multiple atomic TAZs are obtained by processing the triangle set between any two atomic TAZs in the multiple atomic TAZs, wherein the spatial proximity data set corresponding to the multiple atomic TAZs includes the spatial proximity data between the any two atomic TAZs.
  • triangulation is the process of generating a set of triangles for a given set of plane points.
  • Delaunay triangulation is a triangulation in which the circumscribed circles of all triangles satisfy the empty circle property, which is called a Delaunay triangulation.
  • the empty circle property means that the circumscribed circle of a triangle (or edge) does not contain any vertex in the point set (except the boundary).
  • the boundary of the land parcel of the preset area is used as a constraint, so that the segmented triangles bypass the set constraint line or surface.
  • This method can be used to find elements that are discrete in form but adjacent in space.
  • the proximity is determined by the constrained Delaunay triangulation results between the plot polygons, and the plot boundary is used as a constraint, and the triangulated triangles are not allowed to cross the plot boundary.
  • a triangle set of non-long triangles between any two polygons is taken, and the median of the height of each triangle in the triangle set of any non-long triangles is used as the spatial proximity data between the two polygons (atomic TAZs).
  • atomic TAZs the spatial proximity data between each atomic TAZ and any other atomic TAZ in all atomic TAZs.
  • a spatial proximity data set is obtained.
  • the spatial proximity data set is a spatial proximity matrix
  • the spatial proximity matrix describes the spatial proximity relationship between each atomic TAZ.
  • the spacing between AtomTAZs is determined. This value is used to control the morphological regularity of the partition, which can effectively constrain the regional division results and achieve a more regular and easy-to-manage TAZ partition.
  • the process further includes acquiring geographic data, and then directly obtaining a spatially adjacent data set based on the geographic data, which is not limited in this solution.
  • the geographic data may be understood as data describing the geographic shape characteristics of the preset area.
  • the geographic data may include at least one of a vector map, a road network, a water body, an administrative division, and a statutory plan.
  • Vector map refers to vector map data.
  • Road network refers to: road network in the field of transportation.
  • Water bodies are a general term for rivers, lakes, seas, groundwater, glaciers, etc. They are natural complexes covered by water.
  • Administrative divisions are regions divided into levels by the country for the convenience of administrative management.
  • the statutory plan is prepared annually by the urban planning authority in accordance with the requirements of the city's master plan and zoning plan, and contains detailed provisions on the land use nature, development intensity, supporting facilities, road traffic and urban design of each area within the zone.
  • obtaining attribute data sets corresponding to a plurality of atomic flow autonomous zones TAZ according to the attribute data of the preset area includes:
  • the attribute data of the preset area are respectively gathered into the multiple atomic TAZs to obtain the attribute data of each atomic TAZ in the multiple atomic TAZs; wherein the attribute data set corresponding to the multiple atomic TAZs includes the attribute data of each atomic TAZ.
  • the attribute information is aggregated into AtomTAZ according to their spatial position relationship.
  • each node Vi has z attributes Vi : (TAZCode i ; x1 , x2 , ... xZ ), and the N Vi attributes constitute the attribute data set.
  • the attribute data set is the node attribute matrix
  • obtaining the interaction data sets corresponding to the plurality of atomic flow autonomous zones TAZ according to the interaction data of the preset area includes:
  • the interaction data of the preset area are respectively gathered into the multiple atomic TAZs to obtain the interaction data between any two atomic TAZs in the multiple atomic TAZs; wherein the interaction data set corresponding to the multiple atomic TAZs includes the interaction data between any two atomic TAZs. The interaction data between them.
  • each type of interaction data based on AtomTAZ
  • the starting point O, the end point D and the flow e are aggregated into AtomTAZ according to their spatial position relationship.
  • the interaction data from one location to another has L different w attributes.
  • each pair of OD nodes (V i ,V j ) has L edge weights
  • the N ⁇ N (V i ,V j ) attributes constitute the interaction data set.
  • the interaction data set is the edge weight tensor
  • non-interactive static data of node attributes such as semantic attributes
  • interactive dynamic data such as travel flow
  • the spatial division result may be a plurality of TAZs, wherein each TAZ is obtained by aggregating a plurality of atomic TAZs.
  • the spatial division result of the preset area is obtained according to the attribute data sets corresponding to the multiple atomic TAZs and the spatial neighboring data sets corresponding to the multiple atomic TAZs.
  • the spatial division result of the preset area is obtained according to the interaction data set corresponding to the multiple atomic TAZs and the spatial neighboring data set corresponding to the multiple atomic TAZs.
  • the spatial division result of the preset area is obtained according to the attribute data set corresponding to the multiple atomic TAZs, the interaction data set corresponding to the multiple atomic TAZs, and the spatial neighboring data set corresponding to the multiple atomic TAZs.
  • the Martina Contisciani Overlapping Community Detection (MTCOV) expectation-maximization (EM) algorithm MTCOV-EM is applied to obtain the degree of attribution mv matrix of each node (atomic TAZ) belonging to each community.
  • the output result is usually a discontinuous large area, so the result needs to be processed again.
  • This example sets the first attribution threshold ⁇ n to satisfy 0.5 ⁇ n ⁇ 1 to distinguish the core AtomTAZ from the edge AtomTAZ.
  • the core AtomTAZ refers to those AtomTAZs with mv ⁇ n for any community C.
  • the core AtomTAZs belonging to the same community and having similar spatial positions are grouped into a core group according to their connectivity (spatial proximity matrix P), and then several core groups can be obtained.
  • the edge AtomTAZs refer to those AtomTAZs with mv ⁇ n for all communities C.
  • edge AtomTAZ After the above classification of core AtomTAZ and edge AtomTAZ, processing starts from any core group and an edge AtomTAZ is added to it.
  • the rule of adding the edge AtomTAZ is: the edge AtomTAZ that is closest to the core group and does not exceed d is preferentially selected for addition.
  • the edge AtomTAZ with the largest mv with the community C to which the core group belongs is selected for addition.
  • the first attribution threshold ⁇ n is gradually reduced so that each AtomTAZ is added to the core group as much as possible.
  • the first attribution threshold ⁇ n is gradually reduced to obtain a second attribution threshold, and the unadded edge AtomTAZ is re-divided, and based on the second attribution threshold, for example, it is updated to a core AtomTAZ, thereby obtaining a new core group.
  • a spatial partitioning result (fused partitioning result) is obtained.
  • This example uses the community's degree of belonging to identify the core AtomTAZ and edge AtomTAZ in the preset area.
  • the relatively balanced size of the AtomTAZ and the relatively uniform distribution of the core AtomTAZ ensure a relatively balanced partition size during the regional aggregation process, solve the problem of the belonging of the boundary area within a certain range, and thus achieve effective division of large communities at an appropriate scale.
  • the spatial division result of the preset area is obtained by acquiring the attribute data and/or interaction data of the preset area, and obtaining the attribute data set of multiple atomic TAZs according to the attribute data, and/or obtaining the interaction data set of multiple TAZs according to the interaction data, and obtaining the spatial proximity data set of multiple atomic TAZs according to the multiple atomic TAZs.
  • spatial division is realized based on the attribute data and/or interaction data, which is convenient for introducing various types of data for AtomTAZ in different scenarios, and the division is based on the AtomTAZ unit, so that the division result is more in line with the needs of the real world.
  • this solution can also achieve a trade-off between different constraints by adjusting parameters, and adapt to the demand priorities of different goals, so that the characteristics of communication activities can be transformed from the operator's vague experience into an executable TAZ division scheme, realizing the operator's demands of reducing waste, simplifying processes, and improving efficiency.
  • FIG. 4 it is a flow chart of a space division method provided by an embodiment of the present application.
  • the method can be applied to the aforementioned space division system, such as the space division system shown in Figure 1.
  • the space division method shown in Figure 4 may include steps 401-403. It should be understood that this application is described in the order of 401-403 for the convenience of description, and is not intended to be limited to execution in the above order.
  • the embodiment of the present application does not limit the order of execution, execution time, number of executions, etc. of the above one or more steps.
  • the following description takes the execution subject of steps 401-403 of the space division method as a server as an example, and this application is also applicable to other execution subjects. Steps 401-403 are as follows:
  • the multi-source data of City A in this example includes the following three aspects:
  • Baidu travel OD data (e.g. data for the entire day of December 19, 2019).
  • the multi-source data is preprocessed. Specifically, the above OSM road network data, Baidu POI, Baidu AOI, and Baidu travel OD data are all cleaned.
  • the city A is divided into multiple non-intersecting AtomTAZs.
  • a spatial proximity matrix can be generated based on the selected triangles N is the number of AtomTAZ.
  • the POI data and AOI data are gridded separately to obtain the AtomTAZ semantic attributes, which can be expressed as the attribute matrix Among them, 2 is the type of attribute data (POI, AOI).
  • spatial interactive calculation into a grid is achieved.
  • residence extraction when the same individual stays in the same AtomTAZ for more than t, the individual is considered to have a residence.
  • t is a positive number.
  • Baidu travel OD data in interactive data is in grid units, so the grid and AtomTAZ are spatially intersected, and the AtomTAZ with the largest intersection area with a grid is taken as the AtomTAZ corresponding to the grid. Based on this, the OD recorded in all grids can be converted into OD with AtomTAZ as the basic spatial unit.
  • Interaction conversion Generate an undirected graph interaction matrix based on the number of resident ODs between any two AtomTAZs Edge weight tensor Among them, 1 is the type of interactive data (Baidu travel OD data).
  • multiple indicators such as multiple AtomTAZs, the spatial proximity matrix P of the multiple AtomTAZs, the attribute matrix X, the edge weight tensor E, etc. are obtained.
  • the community area division of the preset area is calculated by a community discovery algorithm, and a fusion process is performed to obtain a final division result.
  • the community area division of the preset area is calculated by a community discovery algorithm.
  • the MTCOV-EM algorithm is applied to obtain the degree matrix and distribution map of multiple AtomTAZs.
  • the core AtomTAZ and edge AtomTAZ of each community, as well as the core group, are identified.
  • the partitioning results in this example have no significant disadvantages compared to the community discovery Louvain algorithm that only optimizes a certain attribute. This is related to the fact that the spatial distribution patterns of various physical quantities within the city are relatively similar.
  • each AtomTAZ is of similar size, and an edge AtomTAZ is added to each Core Group in turn during the regional aggregation process; in addition, the spatial proximity matrix generated by constraining the Delaunay triangulation also plays a role in limiting the AtomTAZs that are too far apart.
  • This scheme controls the discreteness of regional size at a lower level, ensuring the relative regularity of regional morphology.
  • This scheme also provides an easy-to-operate unified zoning scheme for multiple objectives (such as network planning, construction, maintenance, optimization, marketing, etc.).
  • this scheme still achieves performance comparable to that of traditional modularity optimization algorithms, and demonstrates its advantages in multi-objective trade-offs compared to the Louvain algorithm that optimizes the modularity of a single attribute.
  • this scheme provides a method that takes into account both attribute and interaction zoning logics in the zoning method based on the community discovery algorithm; and the spatial proximity matrix reflects the road level, that is, the road width, to a certain extent. Therefore, through the spatial proximity matrix and the attribution threshold, the range of the edge atom TAZ that can be included in a core group can be controlled, thereby controlling the partition shape and size. In this way, a solution that takes into account the partition shape and size problems is provided in the zoning task based on community discovery; and a port is provided for the subsequent input of more attribute data or interaction data, and adjustable parameters are provided to ensure the flexibility of the algorithm.
  • zoning units can be assigned different types of energy-saving or experience optimization strategies to achieve differentiated regional management. This strategy is reflected in the entire planning, construction, maintenance and operation process.
  • the interactive data is human traffic data and/or telecommunication traffic data
  • different energy-saving controls are performed on the devices in the areas corresponding to the divided TAZs.
  • the area can be divided into 5 TAZs based on the above method.
  • TAZ is obtained by aggregating multiple atomic TAZs.
  • the park belongs to TAZ S1.
  • the residential area belongs to TAZ S2.
  • the school belongs to TAZ S3.
  • the general hospital belongs to TAZ S4.
  • the office building belongs to TAZ S5. Specifically, more traffic is provided to the network devices in the areas corresponding to TAZ S4 and TAZ S5 during the day, and more traffic is provided to the network devices in the area corresponding to TAZ S2 at night.
  • TAZ S5 Specifically, more traffic is provided to the network devices in the areas corresponding to TAZ S4 and TAZ S5 during the day, and more traffic is provided to the network devices in the area corresponding to TAZ S2 at night.
  • other controls are also possible, and this solution does not limit this.
  • the attribute data is GDP heat and/or housing price heat
  • different statistics and management are performed on the areas corresponding to each TAZ obtained by division.
  • national land and ecological regional planning can achieve planning guidance with different orientations by dividing space in an organized manner.
  • This scheme can provide a balanced division result based on a variety of different planning needs.
  • the attribute data is vegetation coverage data
  • different planning guidance is provided for the areas corresponding to the divided TAZs.
  • Traffic cells are artificial statistical units used to analyze the traffic between different traffic units, thereby providing planning and management assistance at different perspectives, such as macro, meso, and micro. This technical solution can provide analysis results at different scales, which is more in line with the needs.
  • the interactive data is vehicle flow
  • different traffic plans are performed for the vehicles and traffic lights in the areas corresponding to the divided TAZs.
  • the division of multiple units or modules is only a logical division according to function, and is not used as a limitation on the specific structure of the device.
  • some functional modules may be subdivided into more small functional modules, and some functional modules may also be combined into one functional module, but no matter whether these functional modules are subdivided or combined, the general process performed by the device is the same.
  • some devices contain a receiving unit and a sending unit.
  • the sending unit and the receiving unit can also be integrated into a communication unit, which can implement the functions implemented by the receiving unit and the sending unit.
  • each unit corresponds to its own program code (or program instruction), and when the program code corresponding to each of these units is run on the processor, the unit is controlled by the processing unit to execute the corresponding process to implement the corresponding function.
  • the present application also provides a device for implementing any of the above methods.
  • a space division device is provided, including a device for implementing The module (or means) of each step executed by the server in any of the above methods.
  • FIG. 6 it is a schematic diagram of the structure of a space division device provided in an embodiment of the present application.
  • the space division device is used to implement the aforementioned space division method, such as the space division method shown in Fig. 2, Fig. 3, and Fig. 4.
  • the device may include an acquisition module 601, a processing module 602 and a division module 603, which are specifically as follows:
  • An acquisition module 601 is used to acquire attribute data and/or interaction data of a preset area
  • Processing module 602 is used to obtain attribute data sets corresponding to multiple atomic flow autonomous domains TAZ according to the attribute data of the preset area, and/or obtain interaction data sets corresponding to multiple atomic flow autonomous domains TAZ according to the interaction data of the preset area, and obtain spatial proximity data sets corresponding to the multiple atomic TAZs according to the multiple atomic TAZs, wherein any attribute data in the attribute data set represents the attribute of the corresponding atomic TAZ in the multiple atomic TAZs, any interaction data in the interaction data set represents the interaction feature between two atomic TAZs in the multiple atomic TAZs, and any spatial proximity data in the spatial proximity data set represents the proximity relationship between two atomic TAZs in the multiple atomic TAZs, wherein the multiple atomic TAZs are obtained by dividing the preset area;
  • the partitioning module 603 is used to obtain the spatial partitioning result of the preset area according to the attribute data set and/or interaction data set corresponding to the multiple atomic TAZs and the spatial neighboring data set corresponding to the multiple atomic TAZs.
  • the spatial division result of the preset area is obtained by acquiring the attribute data and/or interaction data of the preset area, and obtaining the attribute data set of multiple atomic TAZs according to the attribute data, and/or obtaining the interaction data set of multiple TAZs according to the interaction data, and obtaining the spatial proximity data set of multiple atomic TAZs according to the multiple atomic TAZs.
  • spatial division is realized based on the attribute data and/or interaction data, which is convenient for introducing various types of data for AtomTAZ in different scenarios, and the division is based on the AtomTAZ unit, so that the division result is more in line with the needs of the real world.
  • the processing module 602 is configured to:
  • the spatial proximity data between any two atomic TAZs in the multiple atomic TAZs are obtained by processing the triangle set between any two atomic TAZs in the multiple atomic TAZs, wherein the spatial proximity data set corresponding to the multiple atomic TAZs includes the spatial proximity data between the any two atomic TAZs.
  • processing module 602 is further configured to:
  • the median of the heights of triangles in the set of triangles between any two atomic TAZs in the plurality of atomic TAZs after the processing is determined as the spatial proximity data between any two atomic TAZs in the plurality of atomic TAZs.
  • processing module 602 is further configured to:
  • the attribute data of the preset area are respectively gathered into the multiple atomic TAZs to obtain the attribute data of each atomic TAZ in the multiple atomic TAZs; wherein the attribute data set corresponding to the multiple atomic TAZs includes the attribute data of each atomic TAZ.
  • processing module 602 is further configured to:
  • the interaction data of the preset areas are respectively gathered into the multiple atomic TAZs to obtain the interaction data between any two atomic TAZs in the multiple atomic TAZs; wherein the interaction data set corresponding to the multiple atomic TAZs includes the interaction data between any two atomic TAZs.
  • the division module 603 is used to:
  • edge atom TAZs, core atom TAZs of the respective communities, and multiple core groups are determined from the multiple atom TAZs; wherein the edge atom TAZs are atom TAZs whose degrees of belonging to the respective communities are not greater than a first degree of belonging threshold, the core atom TAZs of any community in the multiple communities are atom TAZs whose degrees of belonging to the community are greater than the first degree of belonging threshold, and the core group is composed of core atom TAZs belonging to the same community and whose distance is less than a distance threshold;
  • the edge atom TAZ with the largest degree of belonging to the first community corresponding to the i-th core group among the M edge atom TAZs is merged into the i-th core group to obtain a first TAZ, wherein the spatial division result includes the first TAZ, M is an integer not less than 1, and i is a positive integer.
  • the partitioning module 603 is further used for:
  • the core group to which the first edge atom TAZ belongs is determined according to the degrees of belonging of the first edge atom TAZ to the communities in the preset area and the second degree of belonging threshold.
  • the device further includes a control module, configured to:
  • a first energy-saving control is performed on the equipment in the area corresponding to the first TAZ; and/or,
  • a first traffic planning is performed on vehicles and traffic lights in an area corresponding to the first TAZ.
  • each module in each of the above devices is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated.
  • the modules in the space division device can be implemented in the form of a processor calling software; for example, the space division device includes a processor, the processor is connected to a memory, and instructions are stored in the memory.
  • the processor calls the instructions stored in the memory to implement any of the above methods or realize the functions of each module of the device, wherein the processor is, for example, a general-purpose processor, such as a central processing unit (CPU) or a microprocessor, and the memory is a memory inside the device or a memory outside the device.
  • CPU central processing unit
  • microprocessor a microprocessor
  • the modules in the device may be implemented in the form of hardware circuits, and the functions of some or all units may be implemented by designing the hardware circuits, and the hardware circuits may be understood as one or more processors; for example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC), and the functions of some or all of the above units may be implemented by designing the logical relationship of the components in the circuit; for another example, in another implementation, the hardware circuit may be implemented by a programmable logic device (PLD), and a field programmable gate array (FPGA) may be used as an example, which may include a large number of logic gate circuits, and the connection relationship between the logic gate circuits may be configured by a configuration file, so as to implement the functions of some or all of the above units. All modules of the above devices may be implemented in the form of a processor calling software, or in the form of hardware circuits, or in part by a processor calling software, and the rest by hardware circuits.
  • ASIC application-specific integrated circuit
  • FPGA field programmable gate
  • FIG. 7 it is a schematic diagram of the hardware structure of another space division device provided in an embodiment of the present application.
  • the space division device 700 shown in FIG. 7 (the device 700 may be a computer device) includes a memory 701, a processor 702, a communication interface 703, and a bus 704.
  • the memory 701, the processor 702, and the communication interface 703 are connected to each other through the bus 704.
  • Memory 701 can be a read-only memory (ROM), a static storage device, a dynamic storage device or a random access memory (RAM).
  • ROM read-only memory
  • RAM random access memory
  • the memory 701 can store programs. When the program stored in the memory 701 is executed by the processor 702, the processor 702 and the communication interface 703 are used to execute the various steps of the space division method of the embodiment of the present application.
  • the processor 702 is a circuit with signal processing capability.
  • the processor 702 may be a circuit with instruction reading and running capability, such as a central processing unit CPU, a microprocessor, a graphics processing unit (GPU) (which may be understood as a microprocessor), or a digital signal processor (DSP); in another implementation, the processor 702 may implement certain functions through the logical relationship of a hardware circuit, and the logical relationship of the hardware circuit may be fixed or reconfigurable, such as the processor 702 being a hardware circuit implemented by an ASIC or a programmable logic device PLD, such as an FPGA.
  • a programmable logic device PLD such as an FPGA.
  • the process of the processor loading a configuration document to implement the hardware circuit configuration may be understood as the process of the processor loading instructions to implement the functions of some or all of the above modules.
  • it may also be a hardware circuit designed for artificial intelligence, which may be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc.
  • the processor 702 is used to execute relevant programs to implement the functions that need to be performed by the units in the space division device of the embodiment of the present application, or to execute the space division method of the method embodiment of the present application.
  • each module in the above device can be one or more processors (or processing circuits) configured to implement the above method, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.
  • the modules in the above device can be fully or partially integrated together, or can be implemented independently.
  • these modules are integrated together and implemented in the form of a system-on-a-chip (SOC).
  • SOC may include at least one processor for implementing any of the above methods or implementing the functions of the modules of the device.
  • the type of the at least one processor may be different, for example, including a CPU and an FPGA, a CPU and an artificial intelligence processor, a CPU and a GPU, etc.
  • the communication interface 703 uses a transceiver device such as, but not limited to, a transceiver to implement communication between the device 700 and other devices or a communication network. For example, data can be obtained through the communication interface 703.
  • a transceiver device such as, but not limited to, a transceiver to implement communication between the device 700 and other devices or a communication network. For example, data can be obtained through the communication interface 703.
  • the bus 704 may include a processor for transmitting information between various components of the device 700 (eg, the memory 701, the processor 702, and the communication interface 703). Pathway.
  • the device 700 shown in FIG. 7 only shows a memory, a processor, and a communication interface, in the specific implementation process, those skilled in the art should understand that the device 700 also includes other devices necessary for normal operation. At the same time, according to specific needs, those skilled in the art should understand that the device 700 may also include hardware devices for implementing other additional functions. In addition, those skilled in the art should understand that the device 700 may also only include the devices necessary for implementing the embodiments of the present application, and does not necessarily include all the devices shown in FIG. 7.
  • An embodiment of the present application also provides a computer-readable storage medium, which stores instructions.
  • the computer-readable storage medium is executed on a computer or a processor, the computer or the processor executes one or more steps in any of the above methods.
  • the embodiment of the present application further provides a computer program product including instructions.
  • the computer program product is run on a computer or a processor, the computer or the processor executes one or more steps in any of the above methods.
  • A/B can represent A or B; wherein A and B can be singular or plural.
  • multiple refers to two or more than two.
  • At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items.
  • at least one of a, b, or c can represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c can be single or multiple.
  • the words “first”, “second”, etc. are used to distinguish the same items or similar items with substantially the same functions and effects. Those skilled in the art can understand that the words “first”, “second”, etc. do not limit the quantity and execution order, and the words “first”, “second”, etc. do not limit them to be necessarily different. Meanwhile, in the embodiments of the present application, words such as “exemplary” or “for example” are used to indicate examples, illustrations or descriptions. Any embodiment or design described as “exemplary” or “for example” in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as “exemplary” or “for example” is intended to present related concepts in a concrete manner for ease of understanding.
  • the disclosed systems, devices and methods can be implemented in other ways.
  • the division of the unit is only a logical function division, and there may be other division methods in actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.
  • the mutual coupling, direct coupling, or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • the computer program product includes one or more computer instructions.
  • the computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.
  • the computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium.
  • the computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.).
  • the computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated.
  • the available medium can be a read-only memory (ROM), or a random access memory (RAM), or a magnetic medium, such as a floppy disk, a hard disk, a tape, a magnetic disk, or an optical medium, such as a digital versatile disc (DVD), or a semiconductor medium, such as a solid state disk (SSD), etc.
  • ROM read-only memory
  • RAM random access memory
  • magnetic medium such as a floppy disk, a hard disk, a tape, a magnetic disk, or an optical medium, such as a digital versatile disc (DVD), or a semiconductor medium, such as a solid state disk (SSD), etc.
  • SSD solid state disk

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Tourism & Hospitality (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Health & Medical Sciences (AREA)
  • Educational Administration (AREA)
  • Remote Sensing (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种空间划分方法、装置及存储介质，该方法包括：获取预设区域的属性数据和/或交互数据；根据所述预设区域的属性数据得到多个原子TAZ对应的属性数据集合，和/或根据所述预设区域的交互数据得到多个原子TAZ对应的交互数据集合，以及根据所述多个原子TAZ得到空间邻近数据集合；根据所述多个原子TAZ对应的属性数据集合和/或交互数据集合，以及所述多个原子TAZ对应的空间邻近数据集合得到所述预设区域的空间划分结果。基于多源数据来实现空间划分，便于在不同场景中为AtomTAZ引入各类数据，且，该划分基于AtomTAZ单位进行划分，使得划分结果更加符合真实世界的需求。

Description

空间划分方法、装置及存储介质
本申请要求于2022年11月14日提交中国专利局、申请号为202211422419.7、申请名称为“空间划分方法、装置及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及城市规划领域，尤其涉及一种空间划分方法、装置及存储介质。
背景技术
城市是承载人类活动的场所，城市空间的划分是很多地理和人类活动分析的基础工作，因此区域划分在很多地理空间相关应用中显得愈发重要。不合理的城市基本单元划分不仅将衍生低效的市民生活问题，同时也将影响城市功能分析和规划的有效性。
以电信运营场景为例，由于城市不同区域的人群具有不同的活动特点，例如居民小区在夜间通讯需求高、商务区在日间活动频繁等，运营商要根据区域特性采用不同的组网策略以适应不同的通信活动特点。因此，运营商希望通过对城市进行分区，以掌握不同区域的通信规律。类似地，运营商可能希望在其业务全流程中均应用分区，包括网络规划、建设、维护、优化、营销等。因此，准确灵活地对城市空间进行划分和认识，已成为当代城市管理水平提升或者电信细分场景识别的核心技术。
当前采用基于轨迹数据的城市区域划分方法进行空间划分。该方法基于源自出租车的人类活动数据，采用轨迹提取、数据清洗、数据过滤与插值、坐标转换等对数据进行预处理，得到经过平面坐标转换后的轨迹数据集，然后，利用轨迹数据集进行网格划分；在网格划分之后，利用形态学方法对网格划分得到的二值矩阵进行城市区域划分。
通过该方式划分得到的城市子区域由于是基于标准网格(栅格)作为最小单元进行划分的，由于栅格是正方形，边缘不光滑，因此边界表达性较差。另一方面，由于上述人类活动数据来源于出租车，代表性不足，因此划分结果有偏差。
发明内容
本申请公开了一种空间划分方法、装置及存储介质，可以实现划分结果更加符合真实世界的需求。
第一方面，本申请实施例提供一种空间划分方法。该方法可包括：获取预设区域的属性数据和/或交互数据。然后，根据该预设区域的属性数据得到多个原子流量自治域TAZ对应的属性数据集合，和/或根据该预设区域的交互数据得到多个原子流量自治域TAZ对应的交互数据集合，以及根据该多个原子TAZ得到该多个原子TAZ对应的空间邻近数据集合。其中，该属性数据集合中的任一属性数据表征该多个原子TAZ中对应原子TAZ的属性，该交互数据集合中的任一交互数据表征该多个原子TAZ中两个原子TAZ之间的交互特征，该空间邻近数据集合中的任一空间邻近数据表征该多个原子TAZ中两个原子TAZ之间的邻近关系。其中，该多个原子TAZ是将该预设区域进行划分得到的。最后，根据该多个原子TAZ对应的属性数据集合和/或交互数据集合，以及该多个原子TAZ对应的空间邻近数据集合得到该预设区域的空间划分结果。
也就是说，可以基于属性数据集合和空间邻近数据集合得到该预设区域的空间划分结果。也可以基于交互数据集合和空间邻近数据集合得到该预设区域的空间划分结果。还可以是基于交互数据集合、属性数据集合和空间邻近数据集合得到该预设区域的空间划分结果等。
本申请实施例，通过获取预设区域的属性数据和/或交互数据，并根据属性数据得到多个原子TAZ的属性数据集合，和/或根据交互数据得到多个TAZ的交互数据集合，以及根据多个原子TAZ得到多个原子TAZ的空间邻近数据集合，进而得到预设区域的空间划分结果。采用该手段，基于属性数据和/或交互数据来实现空间划分，便于在不同场景中为AtomTAZ引入各类数据，且，该划分基于AtomTAZ单位进行划分，使得划分结果更加符合真实世界的需求。
该示例，既可以输入节点(原子TAZ)属性的非交互的静态数据(如语义属性)，也考虑了交互形式的动态数据(如出行人流)，使得城市基本静态环境要素和人类动态活动同时影响划分结果，并具备可扩展性以面向更多场景。
另一方面，本方案还可以通过调节参数实现不同约束之间的权衡，自适应不同目标的需求优先级，使得通信活动的特征能从运营商的模糊的经验变成可执行的TAZ划分方案，实现运营商的减少浪费、简化 流程、提高效率的诉求。
在一种可能的实现方式中，以该预设区域的地块边界为约束，基于该多个原子TAZ对该预设区域进行三角剖分，得到该多个原子TAZ中任意两个原子TAZ之间的三角形集合。然后，根据该多个原子TAZ中任意两个原子TAZ之间的三角形集合进行处理，得到该多个原子TAZ中任意两个原子TAZ之间的空间邻近数据。其中，该多个原子TAZ对应的空间邻近数据集合包含该任意两个原子TAZ之间的空间邻近数据。
该示例通过利用约束Delaunay三角剖分方案，确定了AtomTAZ间的间距，以该值控制分区的形态规整性，可以对区域划分结果进行有效的约束，实现较为规整、易于管理的TAZ分区。
在一种可能的实现方式中，剔除该任意两个原子TAZ之间的三角形集合中高与底之比大于第一数值且最长边与该底之比大于第二数值的三角形，得到处理后的该多个原子TAZ中任意两个原子TAZ之间的三角形集合。然后，将该处理后的多个原子TAZ中任意两个原子TAZ之间的三角形集合中的三角形的高的中位数确定为该多个原子TAZ中任意两个原子TAZ之间的空间邻近数据。
基于上述处理得到的任意两个原子TAZ之间的空间邻近数据，可以实现对区域划分结果进行有效的约束。
在一种可能的实现方式中，将该预设区域的属性数据分别汇聚至该多个原子TAZ中，以得到该多个原子TAZ中每个原子TAZ的属性数据。其中，该多个原子TAZ对应的属性数据集合包含该每个原子TAZ的属性数据。
采用该示例，可以输入节点属性的非交互的静态数据(属性数据)，使得城市基本静态环境要素可以影响划分结果。
在一种可能的实现方式中，将该预设区域的交互数据分别汇聚至该多个原子TAZ中，以得到该多个原子TAZ中任意两个原子TAZ之间的交互数据。其中，该多个原子TAZ对应的交互数据集合包含该任意两个原子TAZ之间的交互数据。
采用该示例，可以输入节点属性的交互形式的动态数据(如出行人流等)，使得城市人类动态活动影响划分结果。
在一种可能的实现方式中，根据该多个原子TAZ对应的属性数据集合和/或该多个原子TAZ对应的交互数据集合，及该多个原子TAZ对应的空间邻近数据集合得到该多个原子TAZ中每个原子TAZ分别归属于该预设区域的各个社区的归属度。然后，根据该多个原子TAZ中每个原子TAZ分别归属于该预设区域的各个社区的归属度从该多个原子TAZ中确定边缘原子TAZ、该各个社区的核心原子TAZ以及多个核心组。其中，该边缘原子TAZ为归属于各个社区的归属度均不大于第一归属度阈值的原子TAZ，该各个社区中任一社区的核心原子TAZ为归属于该社区的归属度大于该第一归属度阈值的原子TAZ，该核心组由属于同一社区且距离小于距离阈值的核心原子TAZ组成。当与该预设区域的第i个核心组的距离不大于预设距离的边缘原子TAZ有M个时，将该M个边缘原子TAZ中归属于该第i个核心组对应的第一社区的归属度最大的边缘原子TAZ合并至该第i个核心组，以得到第一TAZ，其中，该空间划分结果包含该第一TAZ，M为不小于1的整数，i为正整数。
该示例，利用社区的归属度结果识别了预设区域中的核心AtomTAZ、边缘AtomTAZ以及核心组，以AtomTAZ较为均衡的大小和核心AtomTAZ的较为均匀的分布保证了区域聚合过程中较为均衡的分区大小，解决了一定范围内的边界区域归属问题，从而实现了大社区在适宜尺度上的有效划分。
在一种可能的实现方式中，当存在与该各个社区的核心组中的任意核心组的距离均大于该预设距离的第一边缘原子TAZ时，该方法还包括：更新该第一归属度阈值，得到第二归属度阈值，该第二归属度阈值小于该第一归属度阈值。然后，根据该第一边缘原子TAZ分别归属于该预设区域的各个社区的归属度和该第二归属度阈值，确定该第一边缘原子TAZ归属于的核心组。
该方案可以实现所有的边缘原子TAZ都可以被聚合到核心原子TAZ中，进而可得到多个TAZ，即得到空间划分结果。
在一种可能的实现方式中，当该交互数据为人流数据和/或电信流量数据时，对该第一TAZ对应的区域的设备进行第一节能控制。和/或，
当该交互数据为车流数据时，对该第一TAZ对应的区域的车辆和信号灯进行第一交通规划。
基于该方案的划分方法，可以实现基于不同的交互数据和/或属性数据，对预设区域进行不同的划分，进而实现不同的控制等。
第二方面，本申请实施例还提供一种空间划分装置，包括：
获取模块，用于获取预设区域的属性数据和/或交互数据；
处理模块，用于根据该预设区域的属性数据得到多个原子流量自治域TAZ对应的属性数据集合，和/或根据该预设区域的交互数据得到多个原子流量自治域TAZ对应的交互数据集合，以及根据该多个原子TAZ得到该多个原子TAZ对应的空间邻近数据集合，其中，该属性数据集合中的任一属性数据表征该多个原子TAZ中对应原子TAZ的属性，该交互数据集合中的任一交互数据表征该多个原子TAZ中两个原子TAZ之间的交互特征，该空间邻近数据集合中的任一空间邻近数据表征该多个原子TAZ中两个原子TAZ之间的邻近关系，其中，该多个原子TAZ是将该预设区域进行划分得到的；
划分模块，用于根据该多个原子TAZ对应的属性数据集合和/或交互数据集合，以及该多个原子TAZ对应的空间邻近数据集合得到该预设区域的空间划分结果。
本申请实施例，通过获取预设区域的属性数据和/或交互数据，并根据属性数据得到多个原子TAZ的属性数据集合，和/或根据交互数据得到多个TAZ的交互数据集合，以及根据多个原子TAZ得到多个原子TAZ的空间邻近数据集合，进而得到预设区域的空间划分结果。采用该手段，基于属性数据和/或交互数据来实现空间划分，便于在不同场景中为AtomTAZ引入各类数据，且，该划分基于AtomTAZ单位进行划分，使得划分结果更加符合真实世界的需求。
在一种可能的实现方式中，该处理模块，用于：
以该预设区域的地块边界为约束，基于该多个原子TAZ对该预设区域进行三角剖分，得到该多个原子TAZ中任意两个原子TAZ之间的三角形集合；
根据该多个原子TAZ中任意两个原子TAZ之间的三角形集合进行处理，得到该多个原子TAZ中任意两个原子TAZ之间的空间邻近数据，其中，该多个原子TAZ对应的空间邻近数据集合包含该任意两个原子TAZ之间的空间邻近数据。
在一种可能的实现方式中，该处理模块，还用于：
剔除该任意两个原子TAZ之间的三角形集合中高与底之比大于第一数值且最长边与该底之比大于第二数值的三角形，得到处理后的该多个原子TAZ中任意两个原子TAZ之间的三角形集合；
将该处理后的该多个原子TAZ中任意两个原子TAZ之间的三角形集合中的三角形的高的中位数确定为该多个原子TAZ中任意两个原子TAZ之间的空间邻近数据。
在一种可能的实现方式中，该处理模块，还用于：
将该预设区域的属性数据分别汇聚至该多个原子TAZ中，以得到该多个原子TAZ中每个原子TAZ的属性数据；其中，该多个原子TAZ对应的属性数据集合包含该每个原子TAZ的属性数据。
在一种可能的实现方式中，该处理模块，还用于：
将该预设区域的交互数据分别汇聚至该多个原子TAZ中，以得到该多个原子TAZ中任意两个原子TAZ之间的交互数据；其中，该多个原子TAZ对应的交互数据集合包含该任意两个原子TAZ之间的交互数据。
在一种可能的实现方式中，该划分模块，用于：
根据该多个原子TAZ对应的属性数据集合和/或该多个原子TAZ对应的交互数据集合，及该多个原子TAZ对应的空间邻近数据集合得到该多个原子TAZ中每个原子TAZ分别归属于该预设区域的各个社区的归属度；
根据该多个原子TAZ中每个原子TAZ分别归属于该预设区域的各个社区的归属度从该多个原子TAZ中确定边缘原子TAZ、该各个社区的核心原子TAZ以及多个核心组；其中，该边缘原子TAZ为归属于各个社区的归属度均不大于第一归属度阈值的原子TAZ，该各个社区中任一社区的核心原子TAZ为归属于该社区的归属度大于该第一归属度阈值的原子TAZ，该核心组由属于同一社区且距离小于距离阈值的核心原子TAZ组成；
当与该预设区域的第i个核心组的距离不大于预设距离的边缘原子TAZ有M个时，将该M个边缘原子TAZ中归属于该第i个核心组对应的第一社区的归属度最大的边缘原子TAZ合并至该第i个核心组，以得到第一TAZ，其中，该空间划分结果包含该第一TAZ，M为不小于1的整数，i为正整数。
在一种可能的实现方式中，当存在与该各个社区的核心组中的任意核心组的距离均大于该预设距离的第一边缘原子TAZ时，该划分模块，还用于：
更新该第一归属度阈值，得到第二归属度阈值，该第二归属度阈值小于该第一归属度阈值；
根据该第一边缘原子TAZ分别归属于该预设区域的各个社区的归属度和该第二归属度阈值，确定该第一边缘原子TAZ归属于的核心组。
在一种可能的实现方式中，该装置还包括控制模块，用于：
当该交互数据为人流数据和/或电信流量数据时，对该第一TAZ对应的区域的设备进行第一节能控制；和/或，
当该交互数据为车流数据时，对该第一TAZ对应的区域的车辆和信号灯进行第一交通规划。
第三方面，本申请提供了一种空间划分装置，包括处理器和通信接口，该通信接口用于接收和/或发送数据，和/或，该通信接口用于为该处理器提供输出和/或输出，该处理器用于调用计算机指令，以实现如第一方面任一种可能的实施方式提供的方法。
第四方面，本申请提供了一种计算机存储介质，包括计算机指令，当该计算机指令在电子设备上运行时，使得该电子设备执行如第一方面任一种可能的实施方式提供的方法。
第五方面，本申请实施例提供一种计算机程序产品，当计算机程序产品在计算机上运行时，使得计算机执行如第一方面任一种可能的实施方式提供的方法。
可以理解地，上述提供的第二方面所述的装置、第三方面所述的装置、第四方面所述的计算机可读存储介质或者第五方面所述的计算机程序产品均用于执行第一方面中任一所提供的方法。因此，其所能达到的有益效果可参考对应方法中的有益效果，此处不再赘述。
附图说明
下面对本申请实施例用到的附图进行介绍。
图1是本申请实施例提供的一种空间划分系统的架构示意图；
图2是本申请实施例提供的一种空间划分方法的流程示意图；
图3是本申请实施例提供的一种空间划分方法的示意图；
图4是本申请实施例提供的一种空间划分方法的流程示意图；
图5是本申请实施例提供的一种划分结果示意图；
图6是本申请实施例提供的一种空间划分装置的结构示意图；
图7是本申请实施例提供的另一种空间划分装置的结构示意图。
具体实施方式
下面结合本申请实施例中的附图对本申请实施例进行描述。本申请实施例的实施方式部分使用的术语仅用于对本申请的具体实施例进行解释，而非旨在限定本申请。
为了便于理解，以下示例地给出了部分与本申请实施例相关概念的说明以供参考。如下所述：
1.流量自治域(Traffic Autonomous Zone，TAZ)，是一种基于路网，兴趣点(Points of Interest，POI)和各空间场所之间的交互强度的空间划分方法。原子流量自治域TAZ(AtomTAZ)，是用于数据入格与划分TAZ的基本空间单位。
2.地理数据，可以理解为，描述了该预设区域的地理形状特征的数据。如道路、行政区划等。
3.属性数据描述了一个位置location和其承载的标量属性v。例如，该标量属性v可以是兴趣点POI，兴趣区域(Areas of Interest，AOI)，人口热力，流量，渠道分布，年龄分布，房价等中的至少一项。
4.交互数据描述了从一个位置到另一个位置的交互流量。该交互流量例如可以是人流，车流，轨迹，主流，路测，最小化路测(Minimization of Drive-Test，MDT)，全球定位系统(Global Positioning System，GPS)等中的至少一项。
5.边权重张量：每种交互数据为一层，每层记录各个AtomTAZ之间的交互数值，以此构成的张量。
上述对概念的示例性说明可以应用在下文的实施例中。
现有技术划分得到的城市子区域由于是基于标准网格(栅格)作为最小单元进行划分的，边界表达性较差。且，由于人类活动数据来源于出租车，代表性不足，因此划分结果有偏差。有鉴于此，本申请提供一种空间划分方法，能够实现划分结果更加符合真实世界的需求。
以下将结合附图，来详细介绍本申请实施例的系统架构。请参见图1，图1是本申请实施例适用的一 种空间划分系统的示意图，该系统包括多源数据库和服务器103。该多源数据库包括属性数据库101以及交互数据库102。
其中，服务器103从多源数据库中获取预设区域的多源数据。该多源数据例如可以是属性数据和交互数据中的至少一种。在一种可能的实现方式中，该多源数据还可以包括地理数据。
可选的，服务器103获取到数据后，还可以对数据进行预处理。该处理可以是根据实际场景需要进行格式对齐等处理，以满足实际需求。
服务器103基于从多源数据库中获取的数据进行处理，得到社区发现算法所需的多项指标。该处理包括将属性数据和/或交互数据入格。例如通过对预设区域进行划分得到多个原子TAZ，然后将属性数据和/或交互数据结合到各个原子TAZ中，使得各个原子TAZ具备语义属性和/或交互属性。该社区发现算法所需的多项指标可包括该各个原子TAZ的语义属性数据和/或交互属性数据。
然后，服务器103基于上述多项指标，通过社区发现算法计算得到该预设区域的社区区域划分，并对得到的区域进行进一步融合处理得到最终的空间划分结果。
本申请实施例中，基于多源数据来实现空间划分，便于在不同场景中为AtomTAZ引入各类数据，且，该划分基于AtomTAZ单位进行划分，使得划分结果更加符合真实世界的需求。
上面说明了本申请实施例的架构，下面对本申请实施例的方法进行详细介绍。
参照图2所示，是本申请实施例提供的一种空间划分方法的流程示意图。可选的，该方法可以应用于前述的空间划分系统，例如图1所示的空间划分系统。如图2所示的空间划分方法可以包括步骤201-203。应理解，本申请为了方便描述，故通过201-203这一顺序进行描述，并不旨在限定一定通过上述顺序进行执行。本申请实施例对于上述一个或多个步骤的执行的先后顺序、执行的时间、执行的次数等不做限定。下文以空间划分方法的步骤201-203的执行主体为服务器为例进行描述，对于其他执行主体本申请同样也适用。步骤201-203具体如下：
201、获取预设区域的属性数据和/或交互数据；
该预设区域例如可以是某个城市、某个省份等。
属性数据描述了一个位置location和其承载的标量属性v。例如，该标量属性v可以是兴趣点POI，兴趣区域AOI，人口热力，渠道分布，年龄分布，房价等中的至少一项。其中，一个位置的标量属性v可以是多种。标量属性v既可以是连续值、离散值，也可以是因子值等。
交互数据描述了从一个位置到另一个位置的交互流量。该交互流量例如可以是人流，车流，轨迹，主流，路测，最小化路测MDT，全球定位系统GPS等中的至少一项。其中，从一个位置到另一个位置的交互流量可以是多种不同的属性。
202、根据所述预设区域的属性数据得到多个原子流量自治域TAZ对应的属性数据集合，和/或根据所述预设区域的交互数据得到多个原子流量自治域TAZ对应的交互数据集合，以及根据所述多个原子TAZ得到所述多个原子TAZ对应的空间邻近数据集合，其中，所述属性数据集合中的任一属性数据表征所述多个原子TAZ中对应原子TAZ的属性，所述交互数据集合中的任一交互数据表征所述多个原子TAZ中两个原子TAZ之间的交互特征，所述空间邻近数据集合中的任一空间邻近数据表征所述多个原子TAZ中两个原子TAZ之间的邻近关系，其中，所述多个原子TAZ是将所述预设区域进行划分得到的；
其中，运营商在进行网络规划优化时，需要将城市按照一定规则划分成若干网格单元，进行网格化管理。
流量自治域(Traffic Autonomous Zone，TAZ)，是一种基于路网，POI和各空间场所之间的交互强度的空间划分方法，基于该方法划分的空间场所能更好的对应相同类型的人群，每个场所内部的人流活动规律是高度一致的，因此可以实现更加合理的功能分区。
原子流量自治域TAZ(AtomTAZ)，是用于数据入格与划分TAZ的基本空间单位。
在一种可能的实现方式中，该原子TAZ之间是互相不重叠的，且均为面矢量。
进一步可选的，该原子TAZ之间可以存在间隙。
进一步可选的，该原子TAZ为简单多边形。
可选的，通过将道路面矢量去除可更准确地反映道路在空间中占据的实际位置，从而更精细地反映城市中除道路外的其它区域的功能。
其中，通过上述划分，可将预设的城市区域切分为N个互不相交的原子TAZ。
可选的，原子TAZ涵盖有地理信息。
进一步地，还可以为每一个AtomTAZ生成TAZ编码。TAZ编码(TAZCode)，是一套用于空间计算的编码方案。通过编码方便指代各AtomTAZ，有助于后续数据入格等，进而提高算法的计算效率。
基于每一个AtomTAZ节点，则可以将预设区域划分后得到节点集合。该节点集合V可以表示为V＝{AtomTAZ with TAZCodei},1≤i≤N。N为原子TAZ的个数。
在一种可能的实现方式中，根据所述多个原子TAZ得到所述多个原子TAZ对应的空间邻近数据集合，包括：
以所述预设区域的地块边界为约束，基于所述多个原子TAZ对所述预设区域进行三角剖分，得到所述多个原子TAZ中任意两个原子TAZ之间的三角形集合；
根据所述多个原子TAZ中任意两个原子TAZ之间的三角形集合进行处理，得到所述多个原子TAZ中任意两个原子TAZ之间的空间邻近数据，其中，所述多个原子TAZ对应的空间邻近数据集合包含所述任意两个原子TAZ之间的空间邻近数据。
其中，三角剖分就是对给定的平面点集，生成三角形集合的过程。德劳内Delaunay三角剖分是所有三角形的外接圆均满足空圆性质的三角剖分，称为一个Delaunay三角剖分。空圆性质即一个三角形(或边)的外接圆范围内(边界除外)，不包含点集中的任何顶点。
具体地，通过设定剖分的边界，以所述预设区域的地块边界为约束，使得剖分出的三角形绕开了设置的约束线或面。采用该手段可以找到形态离散但空间相邻的元素。
其中，邻近性由地块多边形之间的约束Delaunay三角剖分结果决定，并以地块边界为约束，不允许划分得到的剖分三角穿过地块边界。
可选的，通过剔除其中的长三角形(例如高与底边之比大于2，且最长边与底边之比大于3的三角形)，取任意两个多边形(原子TAZ)之间的非长三角形的三角形集合，该任意非长三角形的三角形集合中各三角形的高的中位数作为该两个多边形(原子TAZ)之间的空间邻近数据。通过获取到所有原子TAZ中每个原子TAZ与其他任意原子TAZ之间的空间邻近数据，即得到空间邻近数据集合。例如该空间邻近数据集合为空间邻近矩阵该空间邻近矩阵描述了各个原子TAZ之间的空间邻近关系。
通过利用约束Delaunay三角剖分方案，确定了AtomTAZ间的间距，以该值控制分区的形态规整性，可以对区域划分结果进行有效的约束，实现较为规整、易于管理的TAZ分区。
在一种可能的实现方式中，还包括获取地理数据。然后，根据地理数据直接得到空间邻近数据集合，本方案对此不作限制。
该地理数据，可以理解为，描述了该预设区域的地理形状特征的数据。例如，该地理数据可包括矢量地图，路网，水体，行政区划，法定图则等至少一项。
矢量地图，是指矢量型的地图数据。
路网，是指：交通领域的道路网络。
水体，是江、河、湖、海、地下水、冰川等的总称。是被水覆盖地段的自然综合体。
行政区划，是国家为便于行政管理而分级划分的区域。
法定图则，是由城市规划主管部门每年根据城市总体规划、分区规划的要求编制，对分区内各片区的土地利用性质、开发强度、配套设施、道路交通和城市设计等方面作出的详细规定。
在一种可能的实现方式中，所述根据所述预设区域的属性数据得到多个原子流量自治域TAZ对应的属性数据集合，包括：
将所述预设区域的属性数据分别汇聚至所述多个原子TAZ中，以得到所述多个原子TAZ中每个原子TAZ的属性数据；其中，所述多个原子TAZ对应的属性数据集合包含所述每个原子TAZ的属性数据。
可选的，对每一种属性数据，基于AtomTAZ和TAZCode，按照其空间位置关系将属性信息汇聚到AtomTAZ中。
由于数据多源性，必然涉及到跨系统查询交换。通过基于TAZCode的数据入格，会加快入格的效率。
通过设定每个位置的标量属性均为z种，则将属性信息汇聚到AtomTAZ中后，每个节点Vi都具备了z种属性Vi:(TAZCodei；x1,x2,…xZ)，N个Vi属性构成了属性数据集合。例如该属性数据集合为节点属性矩阵
在一种可能的实现方式中，所述根据所述预设区域的交互数据得到多个原子流量自治域TAZ对应的交互数据集合，包括：
将所述预设区域的交互数据分别汇聚至所述多个原子TAZ中，以得到所述多个原子TAZ中任意两个原子TAZ之间的交互数据；其中，所述多个原子TAZ对应的交互数据集合包含所述任意两个原子TAZ之 间的交互数据。
例如，对每一种交互数据，基于AtomTAZ，按照其空间位置关系将起点O，终点D和流量e汇聚到AtomTAZ中。设定从一个位置到另一个位置的交互数据均具有L种不同的w属性。汇聚后每对OD节点(Vi,Vj)都具备了L个边权N×N个(Vi,Vj)属性构成了交互数据集合。例如，该交互数据集合为边权重张量
采用该示例，既可以输入节点属性的非交互的静态数据(如语义属性)，也考虑了交互形式的动态数据(如出行人流等)，使得城市基本静态环境要素和人类动态活动同时影响划分结果，并具备可扩展性以面向更多场景。
203、根据所述多个原子TAZ对应的属性数据集合和/或交互数据集合，以及所述多个原子TAZ对应的空间邻近数据集合得到所述预设区域的空间划分结果。
该空间划分结果可以是得到多个TAZ。其中，每个TAZ分别是由多个原子TAZ聚合得到的。
在一种可能的实现方式中，根据所述多个原子TAZ对应的属性数据集合及所述多个原子TAZ对应的空间邻近数据集合得到所述预设区域的空间划分结果。
在另一种可能的实现方式中，根据所述多个原子TAZ对应的交互数据集合及所述多个原子TAZ对应的空间邻近数据集合得到所述预设区域的空间划分结果。
在又一种可能的实现方式中，根据所述多个原子TAZ对应的属性数据集合、所述多个原子TAZ对应的交互数据集合，及所述多个原子TAZ对应的空间邻近数据集合得到所述预设区域的空间划分结果。
例如，如图3所示，基于得到的多个原子TAZ对应的属性数据集合、多个原子TAZ对应的交互数据集合，及多个原子TAZ对应的空间邻近数据集合，应用马蒂娜·康提夏妮重叠社区发现(Martina Contisciani Overlapping Community Detection，MTCOV)期望最大值(Expectation-Maximization，EM)算法MTCOV-EM，得到各个节点(原子TAZ)归属于各个社区的归属度mv矩阵。
考虑到社区发现算法并没有直接面向空间连续性优化，输出结果通常是不连续的大范围区域，因此需要对该结果再进行处理。该示例设定第一归属度阈值λn满足0.5≤λn<1，以此来区分核心AtomTAZ与边缘AtomTAZ。核心AtomTAZ指对于任意社区C的mv≥λn的那些AtomTAZ。
可选的，按照其所属社区分组，依据其连通性(空间邻近矩阵P)，将属于同一社区且空间位置相近的核心AtomTAZ形成的组划分为一个核心组，进而可得到若干个核心组。其中，边缘AtomTAZ指对于所有社区C的mv<λn的那些AtomTAZ。
基于上述核心AtomTAZ与边缘AtomTAZ分类后，从任意一个核心组开始处理，给其添加一个边缘AtomTAZ。其中，该添加的边缘AtomTAZ的规则为：优先选择与核心组距离最近，且不超过d的边缘AtomTAZ进行添加。
可选的，若有多个边缘AtomTAZ均与同一核心组距离接近，则选择与核心组所属社区C的mv最大的那个边缘AtomTAZ进行添加。
可选的，当在第n轮迭代过程中，将第一归属度阈值λn逐渐降低，使得尽可能让每个AtomTAZ都被添加到核心组内。例如，将第一归属度阈值λn逐渐降低得到第二归属度阈值，对未添加的边缘AtomTAZ进行重新划分，基于该第二归属度阈值，例如更新其为核心AtomTAZ，进而得到新的核心组。当所有的AtomTAZ都被聚合到核心组内时，即可得到多个TAZ，也即得到空间划分结果(融合划分结果)。
该示例利用社区的归属度结果识别了预设区域中的核心AtomTAZ和边缘AtomTAZ，以AtomTAZ较为均衡的大小和核心AtomTAZ的较为均匀的分布保证了区域聚合过程中较为均衡的分区大小，解决了一定范围内的边界区域归属问题，从而实现了大社区在适宜尺度上的有效划分。
上述基于核心组和边缘AtomTAZ的融合方式仅为一种可选的方式，还可以采用其他的方式进行处理，本方案对此不作严格限制。
本申请实施例，通过获取预设区域的属性数据和/或交互数据，并根据属性数据得到多个原子TAZ的属性数据集合，和/或根据交互数据得到多个TAZ的交互数据集合，以及根据多个原子TAZ得到多个原子TAZ的空间邻近数据集合，进而得到预设区域的空间划分结果。采用该手段，基于属性数据和/或交互数据来实现空间划分，便于在不同场景中为AtomTAZ引入各类数据，且，该划分基于AtomTAZ单位进行划分，使得划分结果更加符合真实世界的需求。
另一方面，本方案还可以通过调节参数实现不同约束之间的权衡，自适应不同目标的需求优先级，使得通信活动的特征能从运营商的模糊的经验变成可执行的TAZ划分方案，实现运营商的减少浪费、简化流程、提高效率的诉求。
下面以城市A的空间区域划分为例进行具体说明。
参照图4所示，是本申请实施例提供的一种空间划分方法的流程示意图。可选的，该方法可以应用于前述的空间划分系统，例如图1所示的空间划分系统。如图4所示的空间划分方法可以包括步骤401-403。应理解，本申请为了方便描述，故通过401-403这一顺序进行描述，并不旨在限定一定通过上述顺序进行执行。本申请实施例对于上述一个或多个步骤的执行的先后顺序、执行的时间、执行的次数等不做限定。下文以空间划分方法的步骤401-403的执行主体为服务器为例进行描述，对于其他执行主体本申请同样也适用。步骤401-403具体如下：
401、获取多源数据；
该示例中的A市的多源数据包括如下三方面：
(1)属性数据：百度POI、百度AOI；
(2)交互数据：百度出行OD数据(例如2019年12月19日全天的数据)。
可选的，对该多源数据进行预处理。具体地，对上述OSM路网数据、百度POI、百度AOI、百度出行OD数据均进行清洗。
402、对所述多源数据进行处理，得到社区发现算法所需的多项指标；
首先，对该A市进行划分，得到多个互不相交的AtomTAZ。
具体地，基于AtomTAZ方法，该A市可生成N＝2708个AtomTAZ，即得到节点集V。
然后，基于得到的多个AtomTAZ，进行约束Delaunay三角剖分处理。针对该部分的介绍可参阅前述图2所示实施例中步骤202的记载，在此不再赘述。基于筛选出的三角形可生成空间邻近矩阵N为AtomTAZ的个数。
且，将上述属性数据入格。
具体地，对每一个AtomTAZ，将POI数据和AOI数据分别入格，得到AtomTAZ语义属性，其可表示为属性矩阵其中，2为属性数据的种类(POI、AOI)。
还包括将空间交互数据入格。
例如，通过驻留提取，空间转化，交互转化方法，得到实现空间交互计算入格。
其中，驻留提取：当同一个体在同一AtomTAZ内逗留超过t时，认为该个体发生了一次驻留。t为正数。
空间转化：交互数据中的百度出行OD数据以栅格为单位，因此将栅格与AtomTAZ进行空间求交计算，取与一个栅格相交面积最大的AtomTAZ作为该栅格对应的AtomTAZ。基于此可得到将所有栅格记录的OD转化为AtomTAZ作为基本空间单位的OD。
交互转化：基于任何两个AtomTAZ之间的驻留OD人数，生成无向图交互矩阵边权重张量其中，1为交互数据的种类(百度出行OD数据)。
基于上述数据处理，得到多个AtomTAZ、该多个AtomTAZ的空间邻近矩阵P、属性矩阵X、边权重张量E等多项指标。
基于节点集合V、属性矩阵X、边权重张量E和空间邻近矩阵P，构建具有2708个节点、2种节点属性的2层复杂网络G。
403、基于上述多项指标，通过社区发现算法计算得到该预设区域的社区区域划分，并进行融合处理得到最终的划分结果。
首先，基于上述多项指标，通过社区发现算法计算得到该预设区域的社区区域划分。
例如，基于上述2层复杂网络G，应用MTCOV-EM算法，得到多个AtomTAZ的归属度矩阵和分布图。
然后，基于归属度矩阵识别出各个社区的核心AtomTAZ和边缘AtomTAZ，以及核心组Core Group。
根据预设的融合原则进行区域聚合，将边缘AtomTAZ合并到Core Group内。
当所有的AtomTAZ都被聚合到Core Group内时，最终可得到多个TAZ，也即得到最终的融合划分结果。针对该部分的介绍可参阅前述图2所示实施例中的步骤203，在此不再赘述。
该示例中的分区结果相比仅单独优化某一属性的社区发现Louvain算法而言无显著劣势。这与城市内部本身具有的各类物理量的空间分布规律较为相近有关。
且本方案中，各个AtomTAZ大小相近，且区域聚合过程中轮流给每个Core Group添加一个边缘AtomTAZ；此外约束Delaunay三角剖分生成的空间邻近矩阵也起到了限制相隔过远的AtomTAZ的作用， 使得该方案将区域大小的离散程度控制在了更低的水平，保证了区域形态的相对规整。本方案同时提供了针对多目标(如网络规划、建设、维护、优化、营销等)的易操作的统一区划方案。
且，本方案在不直接面向模块度优化的情况下，仍然获得了与传统优化模块度的算法相当的表现，且比起单独优化某一属性模块度的Louvain算法体现了本方案在多目标权衡方面的优势。
相较于现有技术，本方案在基于社区发现算法的区划方法中提供了一种兼顾属性与交互两类区划逻辑的方法；且空间邻近矩阵在一定程度上反映了道路等级即道路宽度，因此通过空间邻近矩阵和归属度阈值，可控制能划入某个核心组的边缘原子TAZ的范围，因而控制了分区形态与大小，这样在基于社区发现的区划任务中给出了一种兼顾分区形态与大小问题的解决方案；且为后续更多种属性数据或交互数据的输入提供了端口，且提供了可调参数，保证了算法的灵活性。
下面对本申请实施例的应用进行介绍。本申请实施例提供的空间划分方法至少可以应用于以下几个方面：
1，电信方面
在电信行业中，不同的区划单元可赋予不同类型的节能或体验优化策略，从而实现差异化的区域管理，这一策略体现在整个规建维优营过程中。
例如，当交互数据为人流数据和/或电信流量数据时，对划分得到的各个TAZ对应的区域的设备进行不同的节能控制。
参照图5所示，该区域基于前述方法可划分为5个TAZ。TAZ是由多个原子TAZ聚合而成得到的。其中，公园属于TAZ S1。住宅区属于TAZ S2。学校属于TAZ S3。综合医院属于TAZ S4。写字楼属于TAZ S5。具体地，白天对TAZ S4和TAZ S5对应的区域的网络设备提供较多的流量等，晚上对TAZ S2对应的区域的网络设备提供较多的流量等。当然还可以是其他控制，本方案对此不作限制。
2，城市规划和管理方面
城市中存在着客观的管理单元，如行政区划，本质上即是为了更好的实现城市功能区的统计和管理。本方案可以根据区域特征给出适应性更强的划分结果。
例如，当属性数据为GDP热力和/或房价热力时，对划分得到的各个TAZ对应的区域进行不同的统计和管理。
3，国土和生态研究方面
作为一种有效的空间发展管理方式，国土和生态区域规划通过将空间进行有组织的划分，实现不同取向的规划指导。本方案能够综合多种不同规划需求给出权衡后的划分结果。
例如，当属性数据为植被覆盖数据时，对划分得到的各个TAZ对应的区域进行不同的规划指导。
4，交通方面
交通小区是人为给出的统计单元，用以分析不同交通单元间的来往情况，从而在宏观、中观、微观等不同角度上给予规划管理帮助。本技术方案能够给出不同尺度下的分析结果，与需求更加契合。
例如，当交互数据为车流时，对划分得到的各个TAZ对应的区域的车辆和信号灯进行不同的交通规划。
需要说明的是，本方案还可以应用于其他方面，本方案对此不作严格限制。
需要说明的是，在本申请的各个实施例中，如果没有特殊说明以及逻辑冲突，各个实施例之间的术语和/或描述具有一致性、且可以相互引用，不同的实施例中的技术特征根据其内在的逻辑关系可以组合形成新的实施例。
上述详细阐述了本申请实施例的方法，下面提供了本申请实施例的装置。可以理解的，本申请各个装置实施例中，对多个单元或者模块的划分仅是一种根据功能进行的逻辑划分，不作为对装置具体的结构的限定。在具体实现中，其中部分功能模块可能被细分为更多细小的功能模块，部分功能模块也可能组合成一个功能模块，但无论这些功能模块是进行了细分还是组合，装置所执行的大致流程是相同的。例如，一些装置中包含接收单元和发送单元。一些设计中，发送单元和接收单元也可以集成为通信单元，该通信单元可以实现接收单元和发送单元所实现的功能。通常，每个单元都对应有各自的程序代码(或者说程序指令)，这些单元各自对应的程序代码在处理器上运行时，使得该单元受处理单元的控制而执行相应的流程从而实现相应功能。
本申请实施例还提供用于实现以上任一种方法的装置，例如，提供一种空间划分装置包括用以实现以 上任一种方法中服务器所执行的各步骤的模块(或手段)。
例如，参照图6所示，是本申请实施例提供的一种空间划分装置的结构示意图。该空间划分装置用于实现前述的空间划分方法，例如图2、图3、图4所示的空间划分方法。
如图6所示，该装置可包括获取模块601、处理模块602和划分模块603，具体如下：
获取模块601，用于获取预设区域的属性数据和/或交互数据；
处理模块602，用于根据所述预设区域的属性数据得到多个原子流量自治域TAZ对应的属性数据集合，和/或根据所述预设区域的交互数据得到多个原子流量自治域TAZ对应的交互数据集合，以及根据所述多个原子TAZ得到所述多个原子TAZ对应的空间邻近数据集合，其中，所述属性数据集合中的任一属性数据表征所述多个原子TAZ中对应原子TAZ的属性，所述交互数据集合中的任一交互数据表征所述多个原子TAZ中两个原子TAZ之间的交互特征，所述空间邻近数据集合中的任一空间邻近数据表征所述多个原子TAZ中两个原子TAZ之间的邻近关系，其中，所述多个原子TAZ是将所述预设区域进行划分得到的；
划分模块603，用于根据所述多个原子TAZ对应的属性数据集合和/或交互数据集合，以及所述多个原子TAZ对应的空间邻近数据集合得到所述预设区域的空间划分结果。
本申请实施例，通过获取预设区域的属性数据和/或交互数据，并根据属性数据得到多个原子TAZ的属性数据集合，和/或根据交互数据得到多个TAZ的交互数据集合，以及根据多个原子TAZ得到多个原子TAZ的空间邻近数据集合，进而得到预设区域的空间划分结果。采用该手段，基于属性数据和/或交互数据来实现空间划分，便于在不同场景中为AtomTAZ引入各类数据，且，该划分基于AtomTAZ单位进行划分，使得划分结果更加符合真实世界的需求。
在一种可能的实现方式中，所述处理模块602，用于：
以所述预设区域的地块边界为约束，基于所述多个原子TAZ对所述预设区域进行三角剖分，得到所述多个原子TAZ中任意两个原子TAZ之间的三角形集合；
根据所述多个原子TAZ中任意两个原子TAZ之间的三角形集合进行处理，得到所述多个原子TAZ中任意两个原子TAZ之间的空间邻近数据，其中，所述多个原子TAZ对应的空间邻近数据集合包含所述任意两个原子TAZ之间的空间邻近数据。
在一种可能的实现方式中，所述处理模块602，还用于：
剔除所述任意两个原子TAZ之间的三角形集合中高与底之比大于第一数值且最长边与所述底之比大于第二数值的三角形，得到处理后的所述多个原子TAZ中任意两个原子TAZ之间的三角形集合；
将所述处理后的所述多个原子TAZ中任意两个原子TAZ之间的三角形集合中的三角形的高的中位数确定为所述多个原子TAZ中任意两个原子TAZ之间的空间邻近数据。
在一种可能的实现方式中，所述处理模块602，还用于：
将所述预设区域的属性数据分别汇聚至所述多个原子TAZ中，以得到所述多个原子TAZ中每个原子TAZ的属性数据；其中，所述多个原子TAZ对应的属性数据集合包含所述每个原子TAZ的属性数据。
在一种可能的实现方式中，所述处理模块602，还用于：
将所述预设区域的交互数据分别汇聚至所述多个原子TAZ中，以得到所述多个原子TAZ中任意两个原子TAZ之间的交互数据；其中，所述多个原子TAZ对应的交互数据集合包含所述任意两个原子TAZ之间的交互数据。
在一种可能的实现方式中，所述划分模块603，用于：
根据所述多个原子TAZ对应的属性数据集合和/或所述多个原子TAZ对应的交互数据集合，及所述多个原子TAZ对应的空间邻近数据集合得到所述多个原子TAZ中每个原子TAZ分别归属于所述预设区域的各个社区的归属度；
根据所述多个原子TAZ中每个原子TAZ分别归属于所述预设区域的各个社区的归属度从所述多个原子TAZ中确定边缘原子TAZ、所述各个社区的核心原子TAZ以及多个核心组；其中，所述边缘原子TAZ为归属于各个社区的归属度均不大于第一归属度阈值的原子TAZ，所述各个社区中任一社区的核心原子TAZ为归属于该社区的归属度大于所述第一归属度阈值的原子TAZ，所述核心组由属于同一社区且距离小于距离阈值的核心原子TAZ组成；
当与所述预设区域的第i个核心组的距离不大于预设距离的边缘原子TAZ有M个时，将所述M个边缘原子TAZ中归属于所述第i个核心组对应的第一社区的归属度最大的边缘原子TAZ合并至所述第i个核心组，以得到第一TAZ，其中，所述空间划分结果包含所述第一TAZ，M为不小于1的整数，i为正整数。
在一种可能的实现方式中，当存在与所述各个社区的核心组中的任意核心组的距离均大于所述预设距 离的第一边缘原子TAZ时，所述划分模块603，还用于：
更新所述第一归属度阈值，得到第二归属度阈值，所述第二归属度阈值小于所述第一归属度阈值；
根据所述第一边缘原子TAZ分别归属于所述预设区域的各个社区的归属度和所述第二归属度阈值，确定所述第一边缘原子TAZ归属于的核心组。
在一种可能的实现方式中，所述装置还包括控制模块，用于：
当所述交互数据为人流数据和/或电信流量数据时，对所述第一TAZ对应的区域的设备进行第一节能控制；和/或，
当所述交互数据为车流数据时，对所述第一TAZ对应的区域的车辆和信号灯进行第一交通规划。
针对上述各模块的具体实现可参阅前述实施例的相应记载，在此不再赘述。
应理解以上各个装置中各模块的划分仅是一种逻辑功能的划分，实际实现时可以全部或部分集成到一个物理实体上，也可以物理上分开。此外，空间划分装置中的模块可以以处理器调用软件的形式实现；例如空间划分装置包括处理器，处理器与存储器连接，存储器中存储有指令，处理器调用存储器中存储的指令，以实现以上任一种方法或实现该装置各模块的功能，其中处理器例如为通用处理器，比如中央处理单元(central processing unit，CPU)或微处理器，存储器为装置内的存储器或装置外的存储器。或者，装置中的模块可以以硬件电路的形式实现，可以通过对硬件电路的设计实现部分或全部单元的功能，该硬件电路可以理解为一个或多个处理器；例如，在一种实现中，该硬件电路为专用集成电路(application-specific integrated circuit，ASIC)，通过对电路内元件逻辑关系的设计，实现以上部分或全部单元的功能；再如，在另一种实现中，该硬件电路为可以通过可编程逻辑器件(programmable logic device，PLD)实现，以现场可编程门阵列(field programmable gate array，FPGA)为例，其可以包括大量逻辑门电路，通过配置文件来配置逻辑门电路之间的连接关系，从而实现以上部分或全部单元的功能。以上装置的所有模块可以全部通过处理器调用软件的形式实现，或全部通过硬件电路的形式实现，或部分通过处理器调用软件的形式实现，剩余部分通过硬件电路的形式实现。
参照图7所示，是本申请实施例提供的又一种空间划分装置的硬件结构示意图。如图7所示的空间划分装置700(该装置700具体可以是一种计算机设备)包括存储器701、处理器702、通信接口703以及总线704。其中，存储器701、处理器702、通信接口703通过总线704实现彼此之间的通信连接。
存储器701可以是只读存储器(read only memory，ROM)，静态存储设备，动态存储设备或者随机存取存储器(random access memory，RAM)。
存储器701可以存储程序，当存储器701中存储的程序被处理器702执行时，处理器702和通信接口703用于执行本申请实施例的空间划分方法的各个步骤。
处理器702是一种具有信号的处理能力的电路，在一种实现中，处理器702可以是具有指令读取与运行能力的电路，例如中央处理单元CPU、微处理器、图形处理器(graphics processing unit，GPU)(可以理解为一种微处理器)、或数字信号处理器(digital singnal processor，DSP)等；在另一种实现中，处理器702可以通过硬件电路的逻辑关系实现一定功能，该硬件电路的逻辑关系是固定的或可以重构的，例如处理器702为ASIC或可编程逻辑器件PLD实现的硬件电路，比如FPGA。在可重构的硬件电路中，处理器加载配置文档，实现硬件电路配置的过程，可以理解为处理器加载指令，以实现以上部分或全部模块的功能的过程。此外，还可以是针对人工智能设计的硬件电路，其可以理解为一种ASIC，例如神经网络处理单元(neural network processing unit，NPU)、张量处理单元(tensor processing unit，TPU)、深度学习处理单元(deep learning processing unit,DPU)等。处理器702用于执行相关程序，以实现本申请实施例的空间划分装置中的单元所需执行的功能，或者执行本申请方法实施例的空间划分方法。
可见，以上装置中的各模块可以是被配置成实施以上方法的一个或多个处理器(或处理电路)，例如：CPU、GPU、NPU、TPU、DPU、微处理器、DSP、ASIC、FPGA，或这些处理器形式中至少两种的组合。
此外，以上装置中的各模块可以全部或部分可以集成在一起，或者可以独立实现。在一种实现中，这些模块集成在一起，以片上系统(system-on-a-chip，SOC)的形式实现。该SOC中可以包括至少一个处理器，用于实现以上任一种方法或实现该装置各模块的功能，该至少一个处理器的种类可以不同，例如包括CPU和FPGA，CPU和人工智能处理器，CPU和GPU等。
通信接口703使用例如但不限于收发器一类的收发装置，来实现装置700与其他设备或通信网络之间的通信。例如，可以通过通信接口703获取数据。
总线704可包括在装置700各个部件(例如，存储器701、处理器702、通信接口703)之间传送信息 的通路。
应注意，尽管图7所示的装置700仅仅示出了存储器、处理器、通信接口，但是在具体实现过程中，本领域的技术人员应当理解，装置700还包括实现正常运行所必须的其他器件。同时，根据具体需要，本领域的技术人员应当理解，装置700还可包括实现其他附加功能的硬件器件。此外，本领域的技术人员应当理解，装置700也可仅仅包括实现本申请实施例所必须的器件，而不必包括图7中所示的全部器件。
本申请实施例还提供了一种计算机可读存储介质，该计算机可读存储介质中存储有指令，当其在计算机或处理器上运行时，使得计算机或处理器执行上述任一个方法中的一个或多个步骤。
本申请实施例还提供了一种包含指令的计算机程序产品。当该计算机程序产品在计算机或处理器上运行时，使得计算机或处理器执行上述任一个方法中的一个或多个步骤。
应理解，在本申请的描述中，除非另有说明，“/”表示前后关联的对象是一种“或”的关系，例如，A/B可以表示A或B；其中A，B可以是单数或者复数。并且，在本申请的描述中，除非另有说明，“多个”是指两个或多于两个。“以下至少一项(个)”或其类似表达，是指的这些项中的任意组合，包括单项(个)或复数项(个)的任意组合。例如，a，b，或c中的至少一项(个)，可以表示：a，b，c，a-b，a-c，b-c，或a-b-c，其中a，b，c可以是单个，也可以是多个。另外，为了便于清楚描述本申请实施例的技术方案，在本申请的实施例中，采用了“第一”、“第二”等字样对功能和作用基本相同的相同项或相似项进行区分。本领域技术人员可以理解“第一”、“第二”等字样并不对数量和执行次序进行限定，并且“第一”、“第二”等字样也并不限定一定不同。同时，在本申请实施例中，“示例性的”或者“例如”等词用于表示作例子、例证或说明。本申请实施例中被描述为“示例性的”或者“例如”的任何实施例或设计方案不应被解释为比其它实施例或设计方案更优选或更具优势。确切而言，使用“示例性的”或者“例如”等词旨在以具体方式呈现相关概念，便于理解。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。例如，该单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如，多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。所显示或讨论的相互之间的耦合、或直接耦合、或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。该计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行该计算机程序指令时，全部或部分地产生按照本申请实施例的流程或功能。该计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。该计算机指令可以存储在计算机可读存储介质中，或者通过该计算机可读存储介质进行传输。该计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(digital subscriber line，DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。该计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。该可用介质可以是只读存储器(read-only memory，ROM)，或随机存取存储器(random access memory，RAM)，或磁性介质，例如，软盘、硬盘、磁带、磁碟、或光介质，例如，数字通用光盘(digital versatile disc，DVD)、或者半导体介质，例如，固态硬盘(solid state disk，SSD)等。
以上所述，仅为本申请实施例的具体实施方式，但本申请实施例的保护范围并不局限于此，任何在本申请实施例揭露的技术范围内的变化或替换，都应涵盖在本申请实施例的保护范围之内。因此，本申请实施例的保护范围应以所述权利要求的保护范围为准。

Claims (19)

  1. 一种空间划分方法，其特征在于，包括：
    获取预设区域的属性数据和/或交互数据；
    根据所述预设区域的属性数据得到多个原子流量自治域TAZ对应的属性数据集合，和/或根据所述预设区域的交互数据得到多个原子流量自治域TAZ对应的交互数据集合，以及根据所述多个原子TAZ得到所述多个原子TAZ对应的空间邻近数据集合，其中，所述属性数据集合中的任一属性数据表征所述多个原子TAZ中对应原子TAZ的属性，所述交互数据集合中的任一交互数据表征所述多个原子TAZ中两个原子TAZ之间的交互特征，所述空间邻近数据集合中的任一空间邻近数据表征所述多个原子TAZ中两个原子TAZ之间的邻近关系，其中，所述多个原子TAZ是将所述预设区域进行划分得到的；
    根据所述多个原子TAZ对应的属性数据集合和/或交互数据集合，以及所述多个原子TAZ对应的空间邻近数据集合得到所述预设区域的空间划分结果。
  2. 根据权利要求1所述的方法，其特征在于，所述根据所述多个原子TAZ得到所述多个原子TAZ对应的空间邻近数据集合，包括：
    以所述预设区域的地块边界为约束，基于所述多个原子TAZ对所述预设区域进行三角剖分，得到所述多个原子TAZ中任意两个原子TAZ之间的三角形集合；
    根据所述多个原子TAZ中任意两个原子TAZ之间的三角形集合进行处理，得到所述多个原子TAZ中任意两个原子TAZ之间的空间邻近数据，其中，所述多个原子TAZ对应的空间邻近数据集合包含所述任意两个原子TAZ之间的空间邻近数据。
  3. 根据权利要求2所述的方法，其特征在于，所述根据所述多个原子TAZ中任意两个原子TAZ之间的三角形集合进行处理，得到所述多个原子TAZ中任意两个原子TAZ之间的空间邻近数据，包括：
    剔除所述任意两个原子TAZ之间的三角形集合中高与底之比大于第一数值且最长边与所述底之比大于第二数值的三角形，得到处理后的所述多个原子TAZ中任意两个原子TAZ之间的三角形集合；
    将所述处理后的所述多个原子TAZ中任意两个原子TAZ之间的三角形集合中的三角形的高的中位数确定为所述多个原子TAZ中任意两个原子TAZ之间的空间邻近数据。
  4. 根据权利要求1至3任一项所述的方法，其特征在于，所述根据所述预设区域的属性数据得到多个原子流量自治域TAZ对应的属性数据集合，包括：
    将所述预设区域的属性数据分别汇聚至所述多个原子TAZ中，以得到所述多个原子TAZ中每个原子TAZ的属性数据；其中，所述多个原子TAZ对应的属性数据集合包含所述每个原子TAZ的属性数据。
  5. 根据权利要求1至4任一项所述的方法，其特征在于，所述根据所述预设区域的交互数据得到多个原子流量自治域TAZ对应的交互数据集合，包括：
    将所述预设区域的交互数据分别汇聚至所述多个原子TAZ中，以得到所述多个原子TAZ中任意两个原子TAZ之间的交互数据；其中，所述多个原子TAZ对应的交互数据集合包含所述任意两个原子TAZ之间的交互数据。
  6. 根据权利要求1至5任一项所述的方法，其特征在于，所述根据所述多个原子流量自治域TAZ对应的属性数据集合和/或交互数据集合，以及所述多个原子TAZ对应的空间邻近数据集合得到所述预设区域的空间划分结果，包括：
    根据所述多个原子TAZ对应的属性数据集合和/或所述多个原子TAZ对应的交互数据集合，及所述多个原子TAZ对应的空间邻近数据集合得到所述多个原子TAZ中每个原子TAZ分别归属于所述预设区域的各个社区的归属度；
    根据所述多个原子TAZ中每个原子TAZ分别归属于所述预设区域的各个社区的归属度从所述多个原子TAZ中确定边缘原子TAZ、所述各个社区的核心原子TAZ以及多个核心组；其中，所述边缘原子TAZ为归属于各个社区的归属度均不大于第一归属度阈值的原子TAZ，所述各个社区中任一社区的核心原子 TAZ为归属于该社区的归属度大于所述第一归属度阈值的原子TAZ，所述核心组由属于同一社区且距离小于距离阈值的核心原子TAZ组成；
    当与所述预设区域的第i个核心组的距离不大于预设距离的边缘原子TAZ有M个时，将所述M个边缘原子TAZ中归属于所述第i个核心组对应的第一社区的归属度最大的边缘原子TAZ合并至所述第i个核心组，以得到第一TAZ，其中，所述空间划分结果包含所述第一TAZ，M为不小于1的整数，i为正整数。
  7. 根据权利要求6所述的方法，其特征在于，当存在与所述各个社区的核心组中的任意核心组的距离均大于所述预设距离的第一边缘原子TAZ时，所述方法还包括：
    更新所述第一归属度阈值，得到第二归属度阈值，所述第二归属度阈值小于所述第一归属度阈值；
    根据所述第一边缘原子TAZ分别归属于所述预设区域的各个社区的归属度和所述第二归属度阈值，确定所述第一边缘原子TAZ归属于的核心组。
  8. 根据权利要求6或7所述的方法，其特征在于，所述方法还包括：
    当所述交互数据为人流数据和/或电信流量数据时，对所述第一TAZ对应的区域的设备进行第一节能控制；和/或，
    当所述交互数据为车流数据时，对所述第一TAZ对应的区域的车辆和信号灯进行第一交通规划。
  9. 一种空间划分装置，其特征在于，包括：
    获取模块，用于获取预设区域的属性数据和/或交互数据；
    处理模块，用于根据所述预设区域的属性数据得到多个原子流量自治域TAZ对应的属性数据集合，和/或根据所述预设区域的交互数据得到多个原子流量自治域TAZ对应的交互数据集合，以及根据所述多个原子TAZ得到所述多个原子TAZ对应的空间邻近数据集合，其中，所述属性数据集合中的任一属性数据表征所述多个原子TAZ中对应原子TAZ的属性，所述交互数据集合中的任一交互数据表征所述多个原子TAZ中两个原子TAZ之间的交互特征，所述空间邻近数据集合中的任一空间邻近数据表征所述多个原子TAZ中两个原子TAZ之间的邻近关系，其中，所述多个原子TAZ是将所述预设区域进行划分得到的；
    划分模块，用于根据所述多个原子TAZ对应的属性数据集合和/或交互数据集合，以及所述多个原子TAZ对应的空间邻近数据集合得到所述预设区域的空间划分结果。
  10. 根据权利要求9所述的装置，其特征在于，所述处理模块，用于：
    以所述预设区域的地块边界为约束，基于所述多个原子TAZ对所述预设区域进行三角剖分，得到所述多个原子TAZ中任意两个原子TAZ之间的三角形集合；
    根据所述多个原子TAZ中任意两个原子TAZ之间的三角形集合进行处理，得到所述多个原子TAZ中任意两个原子TAZ之间的空间邻近数据，其中，所述多个原子TAZ对应的空间邻近数据集合包含所述任意两个原子TAZ之间的空间邻近数据。
  11. 根据权利要求10所述的装置，其特征在于，所述处理模块，还用于：
    剔除所述任意两个原子TAZ之间的三角形集合中高与底之比大于第一数值且最长边与所述底之比大于第二数值的三角形，得到处理后的所述多个原子TAZ中任意两个原子TAZ之间的三角形集合；
    将所述处理后的所述多个原子TAZ中任意两个原子TAZ之间的三角形集合中的三角形的高的中位数确定为所述多个原子TAZ中任意两个原子TAZ之间的空间邻近数据。
  12. 根据权利要求9至11任一项所述的装置，其特征在于，所述处理模块，还用于：
    将所述预设区域的属性数据分别汇聚至所述多个原子TAZ中，以得到所述多个原子TAZ中每个原子TAZ的属性数据；其中，所述多个原子TAZ对应的属性数据集合包含所述每个原子TAZ的属性数据。
  13. 根据权利要求9至12任一项所述的装置，其特征在于，所述处理模块，还用于：
    将所述预设区域的交互数据分别汇聚至所述多个原子TAZ中，以得到所述多个原子TAZ中任意两个原子TAZ之间的交互数据；其中，所述多个原子TAZ对应的交互数据集合包含所述任意两个原子TAZ之间的交互数据。
  14. 根据权利要求9至13任一项所述的装置，其特征在于，所述划分模块，用于：
    根据所述多个原子TAZ对应的属性数据集合和/或所述多个原子TAZ对应的交互数据集合，及所述多个原子TAZ对应的空间邻近数据集合得到所述多个原子TAZ中每个原子TAZ分别归属于所述预设区域的各个社区的归属度；
    根据所述多个原子TAZ中每个原子TAZ分别归属于所述预设区域的各个社区的归属度从所述多个原子TAZ中确定边缘原子TAZ、所述各个社区的核心原子TAZ以及多个核心组；其中，所述边缘原子TAZ为归属于各个社区的归属度均不大于第一归属度阈值的原子TAZ，所述各个社区中任一社区的核心原子TAZ为归属于该社区的归属度大于所述第一归属度阈值的原子TAZ，所述核心组由属于同一社区且距离小于距离阈值的核心原子TAZ组成；
    当与所述预设区域的第i个核心组的距离不大于预设距离的边缘原子TAZ有M个时，将所述M个边缘原子TAZ中归属于所述第i个核心组对应的第一社区的归属度最大的边缘原子TAZ合并至所述第i个核心组，以得到第一TAZ，其中，所述空间划分结果包含所述第一TAZ，M为不小于1的整数，i为正整数。
  15. 根据权利要求14所述的装置，其特征在于，当存在与所述各个社区的核心组中的任意核心组的距离均大于所述预设距离的第一边缘原子TAZ时，所述划分模块，还用于：
    更新所述第一归属度阈值，得到第二归属度阈值，所述第二归属度阈值小于所述第一归属度阈值；
    根据所述第一边缘原子TAZ分别归属于所述预设区域的各个社区的归属度和所述第二归属度阈值，确定所述第一边缘原子TAZ归属于的核心组。
  16. 根据权利要求14或15所述的装置，其特征在于，所述装置还包括控制模块，用于：
    当所述交互数据为人流数据和/或电信流量数据时，对所述第一TAZ对应的区域的设备进行第一节能控制；和/或，
    当所述交互数据为车流数据时，对所述第一TAZ对应的区域的车辆和信号灯进行第一交通规划。
  17. 一种空间划分装置，其特征在于，包括处理器和通信接口，所述通信接口用于接收和/或发送数据，和/或，所述通信接口用于为所述处理器提供输出和/或输出，所述处理器用于调用计算机指令，以实现权利要求1-8任一项所述的方法。
  18. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质中存储有计算机程序，所述计算机程序用于实现权利要求1-8任一项所述的方法。
  19. 一种计算机程序产品，其特征在于，当计算机程序产品在计算机上运行时，使得所述计算机执行如权利要求1至8任意一项所述的方法。
PCT/CN2023/104273 2022-11-14 2023-06-29 空间划分方法、装置及存储介质 WO2024103770A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211422419.7A CN115730711A (zh) 2022-11-14 2022-11-14 空间划分方法、装置及存储介质
CN202211422419.7 2022-11-14

Publications (1)

Publication Number Publication Date
WO2024103770A1 true WO2024103770A1 (zh) 2024-05-23

Family

ID=85295647

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/104273 WO2024103770A1 (zh) 2022-11-14 2023-06-29 空间划分方法、装置及存储介质

Country Status (2)

Country Link
CN (1) CN115730711A (zh)
WO (1) WO2024103770A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115730711A (zh) * 2022-11-14 2023-03-03 华为技术有限公司 空间划分方法、装置及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107818534A (zh) * 2017-10-31 2018-03-20 武汉大学 一种具有空间约束的人类活动网络区域划分方法
CN110176141A (zh) * 2019-05-09 2019-08-27 中电海康集团有限公司 一种基于poi及流量特征的交通小区划分方法和系统
CN113343565A (zh) * 2021-05-31 2021-09-03 南京图申图信息科技有限公司 顾及空间异质性的邻域效应模式构建与ca模拟方法及系统
CN114511125A (zh) * 2020-10-23 2022-05-17 华为技术有限公司 一种空间划分方法、装置、设备及介质
CN115730711A (zh) * 2022-11-14 2023-03-03 华为技术有限公司 空间划分方法、装置及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107818534A (zh) * 2017-10-31 2018-03-20 武汉大学 一种具有空间约束的人类活动网络区域划分方法
CN110176141A (zh) * 2019-05-09 2019-08-27 中电海康集团有限公司 一种基于poi及流量特征的交通小区划分方法和系统
CN114511125A (zh) * 2020-10-23 2022-05-17 华为技术有限公司 一种空间划分方法、装置、设备及介质
CN113343565A (zh) * 2021-05-31 2021-09-03 南京图申图信息科技有限公司 顾及空间异质性的邻域效应模式构建与ca模拟方法及系统
CN115730711A (zh) * 2022-11-14 2023-03-03 华为技术有限公司 空间划分方法、装置及存储介质

Also Published As

Publication number Publication date
CN115730711A (zh) 2023-03-03

Similar Documents

Publication Publication Date Title
Ali et al. Exploiting dynamic spatio-temporal graph convolutional neural networks for citywide traffic flows prediction
Peng et al. Spatial temporal incidence dynamic graph neural networks for traffic flow forecasting
Liu et al. Contextualized spatial–temporal network for taxi origin-destination demand prediction
WO2022227303A1 (zh) 信息处理方法、装置、计算机设备及存储介质
WO2024103770A1 (zh) 空间划分方法、装置及存储介质
CN110414732A (zh) 一种出行未来轨迹预测方法、装置、储存介质及电子设备
Xu et al. A graph spatial-temporal model for predicting population density of key areas
CN114386536B (zh) 区域确定方法、装置、计算设备以及存储介质
Kong et al. The method and application of big data mining for mobile trajectory of taxi based on MapReduce
Schoier et al. Spatial data mining for highlighting hotspots in personal navigation routes
Huynh et al. A comparative study of topological analysis and temporal network analysis of a public transport system
Daniel et al. GIS-based study on the association between road centrality and socio-demographic parameters: A case study
Chen et al. Reposition optimization in free-floating bike-sharing system: A case study in Shenzhen City
CN113191029B (zh) 基于集群计算的交通仿真方法、程序及介质
CN111310340B (zh) 基于人类移动的城市区域交互异常关系识别方法及设备
CN113641749A (zh) 一种基于二部图的人口流动网络估计方法及系统
CN111738527B (zh) 一种基于热点探测模型的城市交通小区划分方法
Cai et al. Data-driven traffic zone division in smart city: Framework and technology
Xing et al. Recommendation of urban vehicle driving routes under traffic congestion: A traffic congestion regulation method considering road network equilibrium
Courtat Walk on City Maps-Mathematical and Physical phenomenology of the City, a Geometrical approach
Yongdong et al. Analysis of road travel behaviour based on big trajectory data
CN115511343A (zh) 一种城市核心区域的确定方法、装置、设备以及存储介质
CN113343565B (zh) 顾及空间异质性的邻域效应模式构建与ca模拟方法及系统
CN114266317A (zh) 聚类方法、装置和服务器
Gao et al. Income estimation based on human mobility patterns and machine learning models