A method and device for determining region boundaries

Abstract

The present invention discloses a method and device for determining regional boundaries, and relates to the field of smart city technology. A specific implementation of the method includes: performing residence point detection based on trajectory data to obtain a residence sequence of a target object, wherein the residence sequence includes a residence point position and a residence time; selecting a residence sequence within a specified time period from the residence sequence based on the residence time; determining a gathering area of ​​the target object based on the residence point position included in the selected residence sequence, and generating a boundary of the gathering area; based on the boundary of the gathering area, merging the boundaries of the gathering area to obtain a regional boundary. This implementation not only realizes the accurate determination of regional boundaries, but is also not limited to the type and scale of points of interest (POIs), and can be more widely applied to the boundary determination of various functional areas.

Description

Technical Field

[0001] The present invention relates to the field of smart city technology, in particular to the field of urban governance technology, and specifically to a method and device for determining regional boundaries. Background Art

[0002] Urbanization is one of the driving forces for social progress and economic development. With the refined development of cities, using points of interest (POI) on maps to mark urban functional areas can provide better decision-making analysis for future urban planning and facilitate the guidance and management of residents' daily travel. Although POI is marked as a point in the city, it does not exist in the objective world in the form of a point. The geometric boundary information of POI is the area of ​​interest (AOI), which is a polygonal closed area surrounded by GPS longitude and latitude points. Existing methods for determining urban area boundary AOI usually determine the area boundary by clustering or semantic segmentation of vehicle check-in, traffic road network, and remote sensing data.

[0003] In the process of implementing the present invention, the inventors found that the prior art has the following problems:

[0004] It is impossible to obtain the spatial scope of fine-grained urban functional areas. The spatial scope detection error of densely distributed POIs is large, and the granularity of urban functional areas is too large. It cannot accurately describe the interaction between functional areas, which is not conducive to the application of urban functional areas. For POIs with large differences in type and scale, the urban functional areas cannot be determined well. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a method and device for determining area boundaries, which obtains a residence point sequence based on trajectory data, obtains the boundary of a gathering area of ​​a target object through the position information of the residence point sequence within a period of time, and merges the boundaries of the gathering areas to obtain area boundaries. This method not only realizes the accurate determination of area boundaries, but also is not limited to the type and scale of POIs, and can be more widely applicable to the boundary determination of various functional areas in a city.

[0006] To achieve the above object, according to one aspect of an embodiment of the present invention, a method for determining a region boundary is provided, comprising:

[0007] Performing dwell point detection according to the trajectory data to obtain a dwell sequence of the target object, wherein the dwell sequence includes a dwell point position and a dwell time;

[0008] Selecting a dwell sequence within a specified time period from the dwell sequence according to the dwell time;

[0009] Determine a gathering area of ​​the target object according to the positions of the dwell points included in the selected dwell sequence, and generate a boundary of the gathering area;

[0010] According to the boundaries of the clustered areas, the boundaries of the clustered areas are merged to obtain area boundaries.

[0011] Optionally, before performing the residence point detection according to the trajectory data, the method further includes: performing a smoothing and denoising process on the trajectory data, and updating the trajectory data according to the processed trajectory data.

[0012] Optionally, performing residence point detection based on trajectory data to obtain the residence sequence of the target object includes: obtaining a set area radius; taking trajectory points whose stay time within the area radius exceeds a set time threshold as residence points, and obtaining the residence sequence of the target object based on the trajectory data of the target object residing at the residence point.

[0013] Optionally, the resident sequence further includes: a resident target object identifier and a resident point identifier corresponding to the resident target object identifier, wherein the resident point identifier is used to uniquely identify a resident point; determining a gathering area of ​​the target object according to the resident point positions included in the selected resident sequence, and generating a boundary of the gathering area, including:

[0014] Step 1: taking out a first resident point from the selected resident sequence and adding it to a first resident point set, and obtaining a first resident target object identifier corresponding to the first resident point;

[0015] Step 2: Draw a circle with the first resident point as the center and the set area radius as the radius, obtain a second resident point corresponding to the first resident target object identifier included in the circle, and add the second resident point to the first resident point set;

[0016] Step 3: for each second resident point in the first resident point set, iteratively execute the above step 2 until the obtained circle does not include the resident point corresponding to the first resident target object identifier;

[0017] Step 4: construct a first circumscribed polygon according to the first resident point set, and add resident points corresponding to second resident target object identifiers other than the first resident target object identifiers included in the first circumscribed polygon to the second resident point set;

[0018] Step 5: taking the second set of resident points as the selected resident sequence, executing the above steps 1 to 4 on the second set of resident points, and merging the obtained second circumscribed polygon with the first circumscribed polygon to obtain a merged circumscribed polygon;

[0019] Step 6: Update the selected resident sequence, repeat the above steps 1 to 5 until the resident sequence is empty, and use each obtained merged circumscribed polygon as the boundary of the aggregation area corresponding to the merged circumscribed polygon.

[0020] Optionally, the step 5 includes: taking the second residence point set as the selected residence sequence, executing the above steps 1 to 4 on the second residence point set, and updating the second residence point set; merging the updated second residence point set with the first residence point set to obtain a merged residence point set; constructing a circumscribed polygon based on the merged residence point set to obtain a merged circumscribed polygon.

[0021] Optionally, the boundaries of the clustered areas are merged according to the boundaries of the clustered areas, including: calculating the distances between the clustered areas respectively according to the boundaries of the clustered areas; and merging the boundaries of the clustered areas whose distances are less than a set merging distance threshold.

[0022] Optionally, based on the boundaries of the clustering areas, the boundaries of the clustering areas are merged, including: taking each of the clustering areas as a node to construct an unweighted undirected graph; calculating the distance between each pair of nodes; in the unweighted undirected graph, adding an edge between two nodes whose distance is less than a set merging distance threshold to construct a connected subgraph; and performing boundary merging on the nodes corresponding to the connected subgraph.

[0023] Optionally, determining the clustering area of ​​the target object according to the dwell point positions included in the selected dwell sequence includes: converting the dwell point positions into spatial indexes, and determining the clustering area of ​​the target object according to the spatial index included in the selected dwell sequence.

[0024] According to a second aspect of an embodiment of the present invention, there is provided a device for determining a region boundary, comprising:

[0025] A dwell sequence acquisition module, used to perform dwell point detection according to trajectory data to obtain a dwell sequence of the target object, wherein the dwell sequence includes a dwell point position and a dwell time;

[0026] A resident sequence screening module, used for selecting a resident sequence within a specified time period from the resident sequence according to the resident time;

[0027] A gathering area acquisition module, used to determine the gathering area of ​​the target object according to the positions of the dwell points included in the selected dwell sequence, and generate the boundary of the gathering area;

[0028] The region boundary acquisition module is used to merge the boundaries of the clustered regions according to the boundaries of the clustered regions to obtain region boundaries.

[0029] According to a third aspect of an embodiment of the present invention, there is provided an electronic device for determining a region boundary, characterized by comprising:

[0030] one or more processors;

[0031] a storage device for storing one or more programs,

[0032] When the one or more programs are executed by the one or more processors, the one or more processors implement the method provided in the first aspect of the embodiment of the present invention.

[0033] According to a fourth aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method provided by the first aspect of the embodiment of the present invention is implemented.

[0034] An embodiment of the invention has the following advantages or beneficial effects: by performing residence point detection based on trajectory data, a residence sequence of the target object is obtained, the residence sequence includes residence point positions and residence time; a residence sequence within a specified time period is selected from the residence sequence according to the residence time; a gathering area of ​​the target object is determined according to the residence point positions included in the selected residence sequence, and a boundary of the gathering area is generated; according to the boundary of the gathering area, the boundaries of the gathering area are merged to obtain a technical solution of the area boundary, which realizes obtaining a residence point sequence based on trajectory data, obtaining the boundary of the gathering area of ​​the target object through the position information of the residence point sequence within a period of time, and merging the boundaries of the gathering area to obtain the area boundary, which not only accurately determines the area boundary, but is also not limited to the type and scale of POI, and can be more widely applicable to the boundary determination of various functional areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0036] Figure 1 is a schematic diagram of the main process of the method for determining the region boundary according to an embodiment of the present invention;

[0037] Figure 2 is a schematic diagram of selecting a first dwell point according to an embodiment of the present invention;

[0038] Figure 3 is a schematic diagram of obtaining a second resident point according to an embodiment of the present invention;

[0039] Figure 4 1 is a schematic diagram of selecting a station point for a vehicle identification A according to an embodiment of the present invention;

[0040] Figure 5 is a schematic diagram of a first circumscribed polygon according to an embodiment of the present invention;

[0041] Figure 6 is a schematic diagram of selecting a dwell point by taking the second dwell point set as the selected dwell sequence in an embodiment of the present invention;

[0042] Figure 7 is a schematic diagram of the result of merging circumscribed polygons according to an embodiment of the present invention;

[0043] Figure 8 is a schematic diagram of main modules of a device for determining a region boundary according to an embodiment of the present invention;

[0044] Fig. 9 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0045] Fig.10 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0047] At present, the method for determining regional boundaries cannot obtain the spatial scope of fine-grained urban functional areas. The spatial scope detection error of densely distributed POIs is large, and the granularity of the obtained urban functional areas is too large. It cannot accurately describe the interaction between functional areas, which is not conducive to the application of urban functional areas. For POIs with large differences in type and scale, urban functional areas cannot be determined well, which cannot meet practical applications well.

[0048] In order to solve the above problems existing in the prior art, the present invention proposes a method for determining regional boundaries, which obtains a residence point sequence based on trajectory data, obtains the boundary of the gathering area of ​​the target object through the position information of the residence point sequence within a period of time, and merges the boundaries of the gathering area to obtain the regional boundary. This method not only realizes the accurate determination of the regional boundary, but also is not limited to the type and scale of POI, and can be more widely applicable to the boundary determination of various functional areas in the city.

[0049] In the introduction to the embodiments of the present invention, the terms and their meanings are as follows:

[0050] POI: Point of Interest, refers to any non-geographical point on an electronic map. It can be a house, a shop, a community entrance or a bus stop, etc.

[0051] AOI: Area of ​​Interest, refers to the interest surface in the electronic map, which is used to express regional geographic entities in the map.

[0052] Figure 1 is a schematic diagram of the main process of the method for determining the region boundary according to an embodiment of the present invention, such as Figure 1 As shown, the method for determining the region boundary of the embodiment of the present invention includes the following steps S101 to S104.

[0053] Step S101: Perform residence point detection according to trajectory data to obtain a residence sequence of the target object, wherein the residence sequence includes residence point positions and residence times.

[0054] Specifically, in the scenario of determining the boundaries of urban functional areas, the determination of regional boundaries can obtain the original data source through the running trajectories of certain target objects with functional purposes. For example, for mobile phones with special application functions, the distribution of a special functional area in the city can be characterized based on the action trajectory data of mobile phone users; for hazardous chemical vehicles used to transport hazardous chemicals, the running vehicle trajectory data can characterize the distribution of functional areas related to hazardous chemicals in the city. Using trajectory data as the data source of regional boundaries, through the detection of residence points, the sequence of residence points that are valuable for determining the boundaries of functional areas can be obtained, including the latitude and longitude position information of the residence points and the start and departure time of the residence points.

[0055] According to an embodiment of the present invention, before performing residence point detection according to the trajectory data, the method further includes: performing smoothing and denoising processing on the trajectory data, and updating the trajectory data according to the processed trajectory data.

[0056] Specifically, in the process of collecting trajectory data, due to equipment anomalies and information loss during transmission, data deviations and anomalies will occur. In order to make the trajectory data smoother and more in line with the current state distribution, it is necessary to combine the spatiotemporal attributes of the trajectory data with objective laws, remove and correct the noise points in the trajectory data, perform smoothing and denoising processing, and update the initial trajectory data based on the processed trajectory data.

[0057] According to another embodiment of the present invention, performing residence point detection based on trajectory data to obtain a residence sequence of a target object includes: acquiring a set area radius; taking trajectory points whose stay time within the area radius exceeds a set time threshold as residence points, and obtaining the residence sequence of the target object based on the trajectory data of the target object residing at the residence point.

[0058] Specifically, the target object here can be an entity object with mobile attributes, such as the mobile phone and hazardous chemical vehicle mentioned above. In this embodiment, the vehicle transporting hazardous chemicals is mainly used as an example for explanation. When the vehicle stays in the specified area for a period of time greater than a preset threshold, the vehicle is defined as staying in this area. In a complete transportation process, the vehicle includes at least one shipping place and a receiving place. In the embodiment of the present invention, the area radius is usually set to 20 meters, and the time threshold can be a value between 20 and 30 minutes. The above-mentioned trajectory data usually includes information such as vehicle ID, sampling time, and the latitude and longitude position of the vehicle at the time of sampling. Based on this, the area radius is set to R; according to the data information of the vehicle trajectory, within the area of ​​radius R, the trajectory point whose stay time exceeds the set time threshold is used as the residence point, and the trajectory data is converted into structured data including vehicle ID, latitude and longitude position of the residence point, residence start time, residence end time, etc., to obtain the vehicle residence sequence.

[0059] By detecting the dwelling points that meet the dwelling requirements from the trajectory data based on the above-mentioned purpose-based stopping of the vehicle, an effective data source representing the geographic functional area related to the vehicle can be obtained.

[0060] Step S102: selecting a dwell sequence within a specified time period from the dwell sequences according to the dwell time.

[0061] Specifically, the trajectory data is continuously updated. Based on the above-mentioned residence sequence, the vehicle residence information within a period of time is selected to determine the regional boundary. According to the residence time of the vehicle in the residence sequence, the residence sequence within the specified time period is selected. The residence sequence containing the residence points within the specified time period and the corresponding spatial distribution is used as the direct data source for determining the regional boundary.

[0062] Step S103: determining a gathering area of ​​the target object according to the positions of the dwell points included in the selected dwell sequence, and generating a boundary of the gathering area.

[0063] According to an embodiment of the present invention, the resident sequence further includes: a resident target object identifier and a resident point identifier corresponding to the resident target object identifier, wherein the resident point identifier is used to uniquely identify a resident point; determining a gathering area of ​​the target object according to the resident point positions included in the selected resident sequence, and generating a boundary of the gathering area, including:

[0064] Step 1: taking out a first resident point from the selected resident sequence and adding it to a first resident point set, and obtaining a first resident target object identifier corresponding to the first resident point;

[0065] Step 2: Draw a circle with the first resident point as the center and the set area radius as the radius, obtain a second resident point corresponding to the first resident target object identifier included in the circle, and add the second resident point to the first resident point set;

[0066] Step 3: for each second resident point in the first resident point set, iteratively execute the above step 2 until the obtained circle does not include the resident point corresponding to the first resident target object identifier;

[0067] Step 4: construct a first circumscribed polygon according to the first resident point set, and add resident points corresponding to second resident target object identifiers other than the first resident target object identifiers included in the first circumscribed polygon to the second resident point set;

[0068] Step 5: taking the second set of resident points as the selected resident sequence, executing the above steps 1 to 4 on the second set of resident points, and merging the obtained second circumscribed polygon with the first circumscribed polygon to obtain a merged circumscribed polygon;

[0069] Step 6: Update the selected resident sequence, repeat the above steps 1 to 5 until the resident sequence is empty, and use each obtained merged circumscribed polygon as the boundary of the aggregation area corresponding to the merged circumscribed polygon.

[0070] Specifically, in the scenario where the target object is a hazardous chemical vehicle, the resident target object is identified as a vehicle identification, the selected resident sequence includes resident point information of multiple vehicles, a resident point in the resident sequence is randomly selected to obtain the corresponding vehicle identification, the vehicle gathering area with the same vehicle identification is determined, and the boundary B of the area with this vehicle identification A is generated; the resident points of other vehicles other than A in B are traversed in a similar way to generate the boundary Br of the area with the relevant vehicle identification, Br and B are merged to obtain the boundary Bp of the complete area of ​​A; other resident points in the resident sequence that have not been visited are traversed in a similar way to obtain Bp, and the boundary set of all functional areas of the resident sequence is obtained.

[0071] For example, taking the residence sequence D of three vehicles with vehicle identifications A, B, and C as an example, the method for determining the boundary AOI of a specific area is as follows:

[0072] Step 1: For the dwell sequence D, randomly select the first dwell point from D, and the dwell point is identified as PA 1 , will PA 1 Add to the first set of residence points Z1, that is, Z1 = {PA 1}, record the first resident vehicle identifier as A.

[0073] Figure 21 is a schematic diagram of selecting the first dwell point in an embodiment of the present invention, in which PA 1 To PA 9 PB 1 To PB 3 and PC 1 To PC 3 They represent the dwelling points of vehicle identifications A, B and C in the dwelling sequence D, and PA is selected 1 The first stop point.

[0074] Step 2: PA 1 Draw a circle with the radius R as the center, and mark all the parking points marked as A in the circular area as the second parking points, and add the second parking points to the first parking point set Z1. 1 It has already been added in step 1, so there is no need to add the center PA again. 1 .

[0075] Figure 3 1 is a schematic diagram of obtaining a second dwell point according to an embodiment of the present invention, in which PA 1 Draw a circle with R as the center and R as the radius. The vehicle in the circular area is marked as A, which is the second stationary point. The second stationary point in the figure is PA. 2 and PA 4 .

[0076] Step 3: According to step 2, Figure 3 For example, at this time, the first resident point set Z1 = {PA 1 ;PA 2 ;PA 4}, for the second residence point PA newly added to the first residence point set 2 and PA 4 Step 2 is iterated until there is no more stationary point with vehicle identification A in the circular area.

[0077] Figure 4 is a schematic diagram of the station point selection of the vehicle identification A according to an embodiment of the present invention, in which PA 2 and PA 4 Take R as the radius and find the station point of vehicle identification A in the circular area to get the second station point PA 8 ,PA 3 ,PA 5 ,PA 6 ,PA 7 .

[0078] Step 4: Combine according to step 3 Figure 4 It can be seen that the first set of residence points Z1 = {PA 1 ;PA 2 ;PA 4;PA 8 ;PA 3 ;PA 5 ;PA 6 ;PA 7}, construct the first circumscribed polygon according to the first set of resident points, Figure 5 is a schematic diagram of a first circumscribed polygon according to an embodiment of the present invention. Figure 5 It can be seen that the circumscribed polygon includes the station point PB of vehicle identification B and vehicle identification C. 1 PB 2 and PC 2 , add the resident points corresponding to the second resident vehicle identification included in the first circumscribed polygon and not the first resident vehicle identification to the second resident point set, and obtain the second resident point set Z2 = {PB 1 PB 2 ; PC 2}.

[0079] Step 5: With the second resident point set Z2 as the selected resident sequence, repeat the above steps 1 to 4 to obtain a second circumscribed polygon, and merge the second circumscribed polygon with the above first circumscribed polygon to obtain a merged circumscribed polygon, i.e., a complete functional area boundary AOI.

[0080] Figure 6 1 is a schematic diagram of selecting a dwell point by taking the second dwell point set as the selected dwell sequence according to an embodiment of the present invention. After repeatedly executing steps 1 to 3 above, Z2={PB 1 PB 2 ; PC 2 ; PC 1 PB 3}.

[0081] It should be noted that when there are unvisited dwelling points in the polygon, it is necessary to follow step 5, take the unvisited dwelling points as the selected dwelling sequence, repeat the above steps 1 to 4, and merge the polygons until there are no unvisited dwelling points in the polygon.

[0082] Figure 7 is a schematic diagram of the result of merging circumscribed polygons according to an embodiment of the present invention. Figure 5 The first circumscribed polygon and Figure 6 The second circumscribed polygon obtained by the second resident point set Z2 is merged.

[0083] Step 6. According to the visited residence points of the selected residence sequence D, for the residence points of other vehicle identifications that have not been visited, repeat steps 1 to 5 above until all residence points in the residence sequence D are traversed, and the merged circumscribed polygons related to the other vehicle identifications are used as the boundaries of the gathering areas of the corresponding vehicles, thereby obtaining a set of boundaries of the gathering areas of all vehicles in the selected residence sequence D.

[0084] According to one embodiment of the present invention, step 5 includes: taking the second residence point set as the selected residence sequence, executing the above steps 1 to 4 on the second residence point set, and updating the second residence point set; merging the updated second residence point set with the first residence point set to obtain a merged residence point set; constructing a circumscribed polygon based on the merged residence point set to obtain a merged circumscribed polygon.

[0085] Specifically, the second circumscribed polygon obtained by executing steps 1 to 4 above usually overlaps with the first circumscribed polygon. The polygons can be merged by using the resident point set merging method. The second resident point set is updated according to steps 1 to 4; a merged resident point set is established to merge the updated second resident point set and the first resident point set; a circumscribed polygon is constructed according to the resident point distribution in the merged resident point set to obtain a merged circumscribed polygon.

[0086] The above-mentioned method for determining the boundary of the gathering area can effectively solve the situation where POIs of the same type are densely distributed. For example, there are a large number of chemical-related enterprises distributed in a chemical park. Through the stay points of the same vehicle in different time dimensions, all the stay points in a certain range are grouped together to obtain a polygonal area; all the stay points in this area can be considered to belong to the same POI range, and related polygons are constructed and merged; in addition, the newly added stay points can expand the original polygon, and through continuous iteration until stability, the polygonal area is obtained as part of the spatial range of the current POI.

[0087] Through the above-mentioned method for determining the boundary of the gathering area of ​​the target object, the appropriate area radius and merging distance threshold can be set according to POIs of different types and sizes, so as to achieve the determination of the boundary of the urban functional area suitable for POIs of different types and sizes.

[0088] According to another embodiment of the present invention, determining the clustering area of ​​the target object according to the dwell point positions included in the selected dwell sequence includes: converting the dwell point positions into spatial indexes, and determining the clustering area of ​​the target object according to the spatial index included in the selected dwell sequence.

[0089] Specifically, in view of the frequent spatial relationship calculations between the above-mentioned multiple residence points, in order to reduce the calculation complexity and shorten the running time, a rectangular spatial index can be established according to the residence point position information, and after completing the preliminary selection according to the spatial index included in the selected residence sequence in combination with the above-mentioned radius R, an accurate calculation is performed to determine the clustering area of ​​the target object; or a spatial index with sufficient data can be established according to the residence point position, and the residence point position is converted into a spatial index, and the clustering area of ​​the target object is determined according to the spatial index included in the selected residence sequence, so as to obtain the vehicle clustering area within the tolerance accuracy range.

[0090] The above-mentioned spatial index can effectively reduce the computational complexity and improve the efficiency of determining the clustered area.

[0091] Step S104: According to the boundaries of the clustered areas, the boundaries of the clustered areas are merged to obtain region boundaries.

[0092] Specifically, the POI area can be preliminarily obtained by acquiring the above-mentioned clustering areas. Due to the differences in the scale and spatial shape of POIs and the possibility of different functional areas within the POI space, it is necessary to perform distance judgment and merge the above-mentioned multiple clustering areas to finally obtain the regional boundaries.

[0093] According to one embodiment of the present invention, the boundaries of the clustering areas are merged according to the boundaries of the clustering areas, including: calculating the distances between the clustering areas respectively according to the boundaries of the clustering areas; and merging the boundaries of the clustering areas whose distances are less than a set merging distance threshold.

[0094] Specifically, according to the actual distribution of urban functional areas, when the minimum distance between the clustering areas of the target object is less than the merge distance threshold, they can be considered to belong to the same urban functional area and can be merged. Therefore, based on the boundaries of the clustering areas, the shortest distance between the boundaries is judged. When the distance is less than the set merge distance threshold, the boundaries of the clustering areas at close distances are merged to obtain the area boundary.

[0095] According to another embodiment of the present invention, the boundaries of the clustering areas are merged according to the boundaries of the clustering areas, including: taking each of the clustering areas as a node to construct an unweighted undirected graph; calculating the distance between each pair of nodes; in the unweighted undirected graph, adding an edge between two nodes whose distance is less than a set merging distance threshold to construct a connected subgraph; and merging the boundaries of the nodes corresponding to the connected subgraph.

[0096] Specifically, each clustered area obtained above is taken as a node to construct an unweighted undirected graph G; the distance d between each pair of nodes is calculated respectively; when d is less than the set merge distance threshold distance, an edge is added between the two nodes to construct a connected subgraph; the polygons corresponding to all connected subgraphs in G are merged to obtain the region boundary.

[0097] Figure 8 FIG. 2 is a schematic diagram of the main modules of the device for determining the region boundary according to an embodiment of the present invention. Figure 8 As shown, the region boundary determination device 800 mainly includes a resident sequence acquisition module 801 , a resident sequence screening module 802 , an aggregated region acquisition module 803 and a region boundary acquisition module 804 .

[0098] A dwell sequence acquisition module 801 is used to perform dwell point detection according to trajectory data to obtain a dwell sequence of the target object, wherein the dwell sequence includes a dwell point position and a dwell time;

[0099] A resident sequence screening module 802 is used to select a resident sequence within a specified time period from the resident sequence according to the resident time;

[0100] A gathering area acquisition module 803 is used to determine the gathering area of ​​the target object according to the positions of the dwell points included in the selected dwell sequence, and generate the area boundary of the gathering area;

[0101] The region boundary acquisition module 804 is used to merge the boundaries of the clustered regions according to the boundaries of the clustered regions to obtain region boundaries.

[0102] Specifically, the region boundary determination device 800 further includes a denoising module (not shown in the figure) for: performing smoothing and denoising processing on the trajectory data before performing residence point detection according to the trajectory data, and updating the trajectory data according to the processed trajectory data.

[0103] Specifically, the residence sequence acquisition module 801 can also be used to: obtain a set area radius; take a trajectory point whose stay time within the area radius exceeds a set time threshold as a residence point, and obtain the residence sequence of the target object based on the trajectory data of the target object residing at the residence point.

[0104] Specifically, the resident sequence also includes: a resident target object identifier and a resident point identifier corresponding to the resident target object identifier, wherein the resident point identifier is used to uniquely identify a resident point; the clustering area acquisition module 803 can also be used to: take out a first resident point from the selected resident sequence and add it to the first resident point set, and obtain the first resident target object identifier corresponding to the first resident point; draw a circle with the first resident point as the center and the set area radius as the radius, obtain the second resident point corresponding to the first resident target object identifier included in the circle, and add the second resident point to the first resident point set; for each second resident point in the first resident point set, iteratively execute the above step 2 until the obtained circle is The resident point corresponding to the first resident target object identifier is not included; a first resident point set is constructed according to the first resident point set, and the resident points corresponding to the second resident target object identifier that is not the first resident target object identifier and included in the first resident point set are added to the second resident point set; the second resident point set is used as the selected resident sequence, the above steps 1 to 4 are performed on the second resident point set, and the obtained second circumscribed polygon is merged with the first circumscribed polygon to obtain a merged circumscribed polygon; the selected resident sequence is updated, and the above steps 1 to 5 are repeated until the resident sequence is empty, and each merged circumscribed polygon obtained is used as the boundary of the aggregation area corresponding to the merged circumscribed polygon.

[0105] Specifically, the aggregation area acquisition module 803 is also used to: take the second residence point set as the selected residence sequence, execute the above steps 1 to 4 on the second residence point set, and update the second residence point set; merge the updated second residence point set with the first residence point set to obtain a merged residence point set; construct a circumscribed polygon based on the merged residence point set to obtain a merged circumscribed polygon.

[0106] Specifically, the region boundary acquisition module 804 may also be used to: calculate the distances between the clustered regions according to the boundaries of the clustered regions; and merge the boundaries of the clustered regions whose distances are less than a set merging distance threshold.

[0107] Specifically, the region boundary acquisition module 804 can also be used to: construct an unweighted undirected graph by taking each of the clustered regions as a node; calculate the distance between each pair of nodes; in the unweighted undirected graph, add edges between two nodes whose distance is less than a set merge distance threshold to construct a connected subgraph; and perform boundary merging on the nodes corresponding to the connected subgraph.

[0108] Specifically, the gathering area acquisition module 803 may also be used to: convert the residence point position into a spatial index, and determine the gathering area of ​​the target object according to the spatial index included in the selected residence sequence.

[0109] Fig. 9 is an exemplary system architecture diagram to which embodiments of the present invention can be applied.

[0110] like Fig. 9 As shown, system architecture 900 may include terminal devices 901, 902, 903, network 904 and server 905. Network 904 is used to provide a medium for communication links between terminal devices 901, 902, 903 and server 905. Network 904 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0111] Users can use terminal devices 901, 902, 903 to interact with server 905 through network 904 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 901, 902, 903, such as area boundary determination applications, etc. (only as an example).

[0112] The terminal devices 901 , 902 , and 903 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers, etc.

[0113] The server 905 may be a server that provides various services, such as a background management server that supports the determination of the regional boundaries performed by the user using the terminal devices 901, 902, and 903 (for example only). The background management server may perform residence point detection based on the trajectory data to obtain a residence sequence of the target object, wherein the residence sequence includes the residence point position and the residence time; select a residence sequence within a specified time period from the residence sequence according to the residence time; determine the gathering area of ​​the target object according to the residence point position included in the selected residence sequence, and generate the boundary of the gathering area; perform boundary merging on the gathering area according to the boundary of the gathering area to obtain the regional boundary and other processing, and feed back the processing result (such as boundary data, etc. - for example only) to the terminal device.

[0114] It should be noted that the method for determining the region boundary provided in the embodiment of the present invention is generally executed by the server 905 , and accordingly, the device for determining the region boundary is generally disposed in the server 905 .

[0115] It should be understood that Fig. 9 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0116] Reference below Fig.10 , is a schematic diagram of the structure of a computer system 1000 of a terminal device or a server suitable for implementing an embodiment of the present invention. Fig.10 The terminal device or server shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0117] like Fig.10 As shown, the computer system 1000 includes a central processing unit (CPU) 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage part 1008 into a random access memory (RAM) 1003. In the RAM 1003, various programs and data required for the operation of the system 1000 are also stored. The CPU 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0118] The following components are connected to the I / O interface 1005: an input section 1006 including a keyboard, a mouse, etc.; an output section 1007 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN card, a modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the I / O interface 1005 as needed. A removable medium 1011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1010 as needed, so that a computer program read therefrom is installed into the storage section 1008 as needed.

[0119] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 1009, and / or installed from the removable medium 1011. When the computer program is executed by the central processing unit (CPU) 1001, the above-mentioned functions defined in the system of the present invention are executed.

[0120] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination thereof.

[0121] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0122] The units involved in the embodiments of the present invention may be implemented by software or hardware. The units described may also be set in a processor, for example, it may be described as: a processor including: a resident sequence acquisition module, a resident sequence screening module, a clustering region acquisition module and a region boundary acquisition module.

[0123] Among them, the names of these modules do not constitute a limitation on the modules themselves in some cases. For example, the region boundary acquisition module can also be described as "a module used to merge the boundaries of the aggregation areas according to the boundaries of the aggregation areas to obtain region boundaries."

[0124] On the other hand, the present invention also provides a computer-readable medium, which may be included in the device described in the embodiment; or it may exist independently and not be assembled into the device. The computer-readable medium carries one or more programs, and when the one or more programs are executed by a device, the device includes: performing residence point detection according to trajectory data to obtain a residence sequence of the target object, the residence sequence including residence point positions and residence time; selecting a residence sequence within a specified time period from the residence sequence according to the residence time; determining the clustering area of ​​the target object according to the residence point positions included in the selected residence sequence, and generating the boundary of the clustering area; merging the boundaries of the clustering area according to the boundaries of the clustering area to obtain the region boundary.

[0125] The technical solution according to the embodiment of the present invention has the following advantages or beneficial effects: by performing residence point detection based on trajectory data, a residence sequence of the target object is obtained, and the residence sequence includes residence point positions and residence time; a residence sequence within a specified time period is selected from the residence sequence according to the residence time; a gathering area of ​​the target object is determined according to the residence point positions included in the selected residence sequence, and a boundary of the gathering area is generated; according to the boundary of the gathering area, the boundaries of the gathering area are merged to obtain the technical solution of the area boundary, which realizes obtaining the residence point sequence based on trajectory data, obtaining the boundary of the gathering area of ​​the target object through the position information of the residence point sequence within a period of time, and merging the boundaries of the gathering area to obtain the area boundary, which not only accurately determines the area boundary, but is also not limited to the type and scale of POI, and can be more widely applied to the boundary determination of various functional areas in the city.

[0126] The specific implementation methods described herein do not constitute limitations on the scope of protection of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention shall be included in the scope of protection of the present invention.

Claims

1. A method for determining region boundaries, It is characterized in that include: Performing residence point detection according to the trajectory data to obtain a residence sequence of the target object, the residence sequence including a residence point position, a residence time, a residence target object identifier, and a residence point identifier corresponding to the residence target object identifier, the residence point identifier being used to uniquely identify a residence point; Selecting a dwell sequence within a specified time period from the dwell sequence according to the dwell time; Determine the clustering area of ​​the target object according to the resident point positions included in the selected resident sequence, and generate the boundary of the clustering area, including: randomly select a resident point in the selected resident sequence to obtain the corresponding resident target object identifier, determine the clustering area corresponding to the resident target object identifier, and generate the boundary of the first clustering area of ​​the resident target object identifier; traverse other resident points corresponding to resident target object identifiers different from the resident target object identifier in the boundary of the clustering area of ​​the resident target object identifier, generate the boundary of the second clustering area of ​​the resident target object identifier corresponding to the other resident points, and merge the boundary of the first clustering area with the boundary of the second clustering area to obtain the boundary of the clustering area of ​​the resident target object identifier; traverse the resident points that have not been visited in the selected resident sequence in a manner of generating the boundary of the clustering area of ​​the resident target object identifier, and obtain the boundaries of all clustering areas of the selected resident sequence; According to the boundaries of the clustered areas, the boundaries of the clustered areas are merged to obtain area boundaries.

2. The method according to claim 1, It is characterized in that Before performing dwell point detection based on trajectory data, it also includes: The trajectory data is smoothed and denoised, and the trajectory data is updated according to the processed trajectory data.

3. The method according to claim 1 or 2, It is characterized in that The residence point detection is performed based on the trajectory data, and the residence sequence of the target object is obtained, including: Get the set area radius; The trajectory points whose stay time within the radius of the area exceeds a set time threshold are taken as residence points, and the residence sequence of the target object is obtained according to the trajectory data of the target object that resides at the residence point.

4. The method according to claim 1, It is characterized in that Determining a gathering area of ​​the target object according to the positions of the dwell points included in the selected dwell sequence, and generating a boundary of the gathering area, including: Step 1: taking out a first resident point from the selected resident sequence and adding it to a first resident point set, and obtaining a first resident target object identifier corresponding to the first resident point; Step 2: Draw a circle with the first resident point as the center and the set area radius as the radius, obtain a second resident point corresponding to the first resident target object identifier included in the circle, and add the second resident point to the first resident point set; Step 3: for each second resident point in the first resident point set, iteratively execute the above step 2 until the obtained circle does not include the resident point corresponding to the first resident target object identifier; Step 4: construct a first circumscribed polygon according to the first resident point set, and add resident points corresponding to second resident target object identifiers other than the first resident target object identifiers included in the first circumscribed polygon to the second resident point set; Step 5: taking the second set of resident points as the selected resident sequence, executing the above steps 1 to 4 on the second set of resident points, and merging the obtained second circumscribed polygon with the first circumscribed polygon to obtain a merged circumscribed polygon; Step 6: Update the selected resident sequence, repeat the above steps 1 to 5 until the resident sequence is empty, and use each obtained merged circumscribed polygon as the boundary of the aggregation area corresponding to the merged circumscribed polygon.

5. The method according to claim 4, It is characterized in that The step 5 comprises: Taking the second resident point set as the selected resident sequence, executing the above steps 1 to 4 on the second resident point set, and updating the second resident point set; Merging the updated second resident point set with the first resident point set to obtain a merged resident point set; A circumscribed polygon is constructed according to the merged resident point set to obtain a merged circumscribed polygon.

6. The method according to claim 1, It is characterized in that According to the boundaries of the clustered areas, merging the boundaries of the clustered areas includes: According to the boundaries of the clustering areas, respectively calculating the distances between the two clustering areas; The boundaries of the clustered areas whose distance is less than the set merge distance threshold are merged.

7. The method according to claim 1 or 6, It is characterized in that According to the boundaries of the clustered areas, merging the boundaries of the clustered areas includes: Taking each of the clustered areas as a node, constructing an unweighted undirected graph; Calculate the distance between two nodes; In the unweighted undirected graph, an edge is added between two nodes whose distance is less than a set merge distance threshold to construct a connected subgraph; The nodes corresponding to the connected subgraphs are subjected to boundary merging.

8. The method according to claim 1, It is characterized in that Determining the gathering area of ​​the target object according to the residence point positions included in the selected residence sequence includes: The residence point position is converted into a spatial index, and the gathering area of ​​the target object is determined according to the spatial index included in the selected residence sequence.

9. A device for determining a region boundary, It is characterized in that include: A dwell sequence acquisition module, used to perform dwell point detection according to the trajectory data to obtain a dwell sequence of the target object, wherein the dwell sequence includes a dwell point position, a dwell time, a dwell target object identifier and a dwell point identifier corresponding to the dwell target object identifier, wherein the dwell point identifier is used to uniquely identify a dwell point; A resident sequence screening module, used for selecting a resident sequence within a specified time period from the resident sequence according to the resident time; A gathering area acquisition module is used to determine the gathering area of ​​the target object according to the resident point positions included in the selected resident sequence, and generate the boundary of the gathering area, including: randomly selecting a resident point in the selected resident sequence to obtain the corresponding resident target object identifier, determining the gathering area corresponding to the resident target object identifier, and generating the boundary of the first gathering area of ​​the resident target object identifier; traversing other resident points different from the resident point in the boundary of the gathering area of ​​the resident target object identifier, generating the boundary of the second gathering area of ​​the resident target object identifier corresponding to the other resident points, and merging the boundary of the first gathering area and the boundary of the second gathering area to obtain the boundary of the gathering area of ​​the resident target object identifier; traversing the resident points that have not been visited in the selected resident sequence in a manner of generating the boundary of the gathering area of ​​the resident target object identifier, and obtaining the boundaries of all gathering areas of the selected resident sequence; The region boundary acquisition module is used to merge the boundaries of the clustered regions according to the boundaries of the clustered regions to obtain region boundaries.

10. A mobile electronic device terminal, It is characterized in that include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 8.

11. A computer readable medium having a computer program stored thereon, It is characterized in that When the program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images