Geographic information processing method and device

Abstract

The embodiment of the invention discloses a geographic information processing method and device.According to the method and device, grids are clustered according to the position information of the grids and historical service data, the grids which are close in position and similar in historical service data attribute are clustered into grid clusters, and then the shape of the grid clusters is optimized, so that the geographic information is obtained. The method comprises the following steps of: dividing a plurality of fencing areas according to the selected fencing areas, each fencing area has a convex polygonal outer boundary relatively suitable for scheduling and has similar attributes, providing an interactive interface to display the initial attributes and detailed data of different fencing areas to operators, and generating an aggregation fencing according to at least one selected fencing area. Therefore, an operator can adjust the fence areas and generate a plurality of aggregated fence areas to generate an aggregated fence for applying a scheduling strategy.

Description

Technical Field

[0001] The present invention relates to the field of geographic information processing, and in particular to a geographic information processing method and device. Background Art

[0002] In the current online-to-offline (O2O) business, the business platform uses the mobile Internet infrastructure and the positioning function of mobile terminals to dispatch different service resources, and forms service orders between users and service resources through online demand release, so that offline service resources can effectively provide services to users. For example, in the online car-hailing business, based on the ride request posted by the passenger, the online car-hailing platform matches the online car-hailing near the passenger's location, undertakes the relevant ride task, and thus provides online car-hailing services.

[0003] In this type of business, the scheduling of service resources is closely related to the geographical location. In some operational scenarios, there may be a lack of service resources in a specific area, and it is necessary to use scheduling strategies to guide service resources to flow to resource-scarce areas during periods of resource shortage. In the prior art, the above scheduling strategies are usually implemented only according to administrative divisions. This approach cannot accurately solve the problem of spatial and temporal imbalance in the supply and demand of service resources, and does not provide tools that are convenient for operators to view and operate. Operators have difficulty in handling different types of services for different geographical areas. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides a geographic information processing method and device, hoping to provide tools so that operators can more accurately understand the distribution of business data in different geographical areas, and obtain fence areas with similar business data attributes, so that operators can adjust the fence areas and generate aggregated fences that aggregate multiple fence areas to apply scheduling strategies.

[0005] In a first aspect, an embodiment of the present invention provides a geographic information processing method, wherein the method comprises:

[0006] Acquire historical business data, wherein the historical business data includes business data of different grids in different unit time periods;

[0007] For each grid in the selected map area, clustering the grids according to the location information of the grids and the historical business data of the selected time period to determine a plurality of grid clusters, wherein the grid cluster includes at least one grid, and the selected time period includes at least one unit time period;

[0008] Performing shape optimization on each mesh cluster to determine a plurality of fenced areas, wherein the fenced areas are mesh clusters having convex polygonal outer boundaries;

[0009] Receiving filtering conditions through an interactive interface;

[0010] The fenced areas meeting the filtering conditions are displayed in a highlighted manner in the map interface, wherein fenced areas with different business data levels have different colors;

[0011] receiving a selection instruction to determine at least one fence area selected;

[0012] An aggregate fence is generated according to the selected at least one fence area.

[0013] In a second aspect, a geographic information processing device is provided, wherein the device comprises:

[0014] A historical data acquisition unit, used to acquire historical business data, wherein the historical business data includes business data of different grids in different unit time periods;

[0015] A clustering unit, configured to cluster grids for each grid in the selected map area according to the location information of the grids and the historical business data of the selected time period, and determine a plurality of grid clusters, wherein the grid cluster includes at least one grid, and the selected time period includes at least one unit time period;

[0016] An optimization unit, configured to perform shape optimization on each mesh cluster and determine a plurality of fence regions, wherein the fence regions are mesh clusters having convex polygonal outer boundaries;

[0017] An interaction unit, used for receiving screening conditions through an interaction interface;

[0018] A display unit, used for displaying fenced areas meeting the screening conditions in a highlighted manner in a map interface, wherein fenced areas with different business data levels have different color depths;

[0019] A selection unit, configured to receive a selection instruction and determine at least one fence area to be selected;

[0020] The aggregation unit is used to generate an aggregate fence according to the at least one selected fence area.

[0021] According to a third aspect, an electronic device is provided, wherein the controller comprises a memory and a processor, the memory being used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method described in the first aspect.

[0022] According to a fourth aspect, a computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method according to the first aspect is implemented.

[0023] The method and device of the embodiment of the present invention clusters grids according to the location information and historical business data of the grids, clusters grids with close locations and similar historical business data attributes into grid clusters, and then optimizes the shape of the grid clusters to obtain multiple fence areas, each fence area has a convex polygonal outer boundary that is relatively suitable for scheduling and has similar attributes. At the same time, an interactive interface is provided to display the preliminary attributes of different fence areas to operators, and an aggregate fence can be generated according to at least one selected fence area. Thus, operators can adjust the fence area and generate an aggregate fence that aggregates multiple fence areas to apply a scheduling strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The above and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

[0025] Figure 1 is a flow chart of a geographic information processing method according to an embodiment of the present invention;

[0026] Figure 2 is a flow chart of grid clustering according to an embodiment of the present invention;

[0027] Figure 3 is a schematic diagram of a mesh cluster that needs to be shape optimized in an embodiment of the present invention;

[0028] Figure 4 is a flow chart of adding an empty grid during shape optimization of a grid cluster according to an embodiment of the present invention;

[0029] Figure 5 is a schematic diagram of determining a boundary grid during shape optimization of a grid cluster according to an embodiment of the present invention;

[0030] Figure 6 is a schematic diagram of merging empty mesh clusters during shape optimization of mesh clusters according to an embodiment of the present invention;

[0031] Figure 7 Another schematic diagram of merging empty mesh clusters during shape optimization of mesh clusters according to an embodiment of the present invention

[0032] Figure 8 is a schematic diagram of an interactive interface of an embodiment of the present invention;

[0033] Fig. 9 is a schematic diagram of a geographic information processing device according to an embodiment of the present invention;

[0034] Fig.10 is a schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0035] The present application is described below based on embodiments, but the present application is not limited to these embodiments. In the detailed description of the present application below, some specific details are described in detail. It is possible for those skilled in the art to fully understand the present application without the description of these details. In order to avoid confusing the essence of the present application, known methods, processes, flows, components and circuits are not described in detail.

[0036] In addition, persons of ordinary skill in the art will appreciate that the drawings provided herein are for illustration purposes and are not necessarily drawn to scale.

[0037] Unless the context clearly requires otherwise, the words "include", "comprising" and similar words throughout the application should be interpreted as including rather than exclusive or exhaustive; that is, the meaning is "including but not limited to".

[0038] In the description of this application, it should be understood that the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of this application, unless otherwise specified, the meaning of "plurality" is two or more.

[0039] The solutions described in this specification and in the examples, if they involve the processing of personal information, will be processed on the premise of having a legal basis (such as obtaining the consent of the subject of personal information, or being necessary for the performance of a contract, etc.), and will only be processed within the scope of regulations or agreements. If a user refuses to process personal information other than the necessary information for basic functions, it will not affect the user's use of basic functions.

[0040] In the following description, the relevant services of the online car-hailing platform are used as an example. It should be understood that the method and device of this embodiment are not limited to the online car-hailing service, and any online-to-offline mobile Internet service that needs to dispatch service resources based on geographic location (including but not limited to online shopping, express delivery, takeout, errands, etc.) can apply the geographic information processing method and device of this embodiment.

[0041] In the online car-hailing business, the location where the passenger sends a ride request can be called the order-issuing location, and the location where the driver is assigned a corresponding ride task by the platform, or the location where the driver actively sends a response message to the ride request, can be called the order-receiving location. According to the order-issuing location and the order-receiving location, as well as the triggering time of the corresponding event (issuing a ride request or accepting a ride task), a large amount of business data representing the number of businesses can be recorded in the actual operation process, such as the number of orders issued (that is, the number of tasks issued) and the number of responses (that is, the number of tasks accepted). These business data can be divided into time and space according to the grid to which the location belongs and the unit time period to which the trigger time belongs, so as to obtain business data of different grids in different unit time periods. For example, the number of orders issued or the number of responses in different grids in different time periods.

[0042] In the actual operation process, since the location distribution of online ride-hailing vehicles may not be able to fully match the actual demand, for different geographical areas, after passengers in some places place orders, due to the large number of ride requests and the small number of online ride-hailing vehicles around the area, the ride requests cannot be answered by the driver in time, or there is no way to allocate drivers in time, which will lead to a decrease in the efficiency of the entire platform. Usually, the online ride-hailing platform needs to perform resource scheduling to guide online ride-hailing drivers to move to locations that need more orders. However, for operators, current tools cannot visualize the situation in different geographical areas, nor can they distinguish the business data situation in different areas with a higher granularity, which leads to a lack of data basis and means for effective service resource scheduling. In order to solve this problem, an embodiment of the present invention proposes a geographic information processing method, which is expected to parse and obtain subdivided fence areas suitable for the subsequent implementation of various service resource scheduling strategies based on historical business data. These fence areas have consistent business data attributes and are presented in a shape that is convenient for online ride-hailing vehicles to enter. At the same time, the data of different fence areas can be viewed in a visual way, and manual selection and adjustment can be performed to improve the accuracy and convenience of service resource scheduling.

[0043] Figure 1 FIG. 1 is a flow chart of a geographic information processing method according to an embodiment of the present invention. Figure 1 As shown, the geographic information processing method of this embodiment includes the following steps:

[0044] Step S100, obtaining historical business data, wherein the historical business data includes business data of different grids in different unit time periods.

[0045] Step S200: for each grid in the selected map area, cluster the grids according to the location information of the grids and the historical business data of the selected time period to determine a plurality of grid clusters, wherein the grid cluster includes at least one grid, and the selected time period includes at least one unit time period.

[0046] Step S300 , performing shape optimization on each mesh cluster to determine a plurality of fenced areas, wherein the fenced areas are mesh clusters having convex polygonal outer boundaries.

[0047] Step S400, receiving screening conditions through an interactive interface.

[0048] Step S500: Displaying fenced areas that meet the screening conditions in a highlighted manner in a map interface, wherein fenced areas with different business data levels have different colors.

[0049] Step S600: receiving a selection instruction to determine at least one selected fence area.

[0050] Step S700: generating an aggregate fence according to the at least one selected fence area.

[0051] In an embodiment of the present invention, a grid, which may also be referred to as a geographic grid, refers to a geographic data unit that covers a fixed geographic area in map data and has a boundary of a regular shape. A grid may be used as a basic unit for geographic data processing to process geographic information. A grid is usually set as a polygon, such as a hexagon or a quadrilateral. Each grid may have its own identifier (also referred to as a grid ID) and corresponding location information. The location information may be the geographic coordinates of a vertex of the grid, or the geographic coordinates of a specific location within the area covered by the grid, such as the center position of the grid. In the following description, a grid that is a regular hexagon is used as an example for illustration.

[0052] In the embodiment of the present invention, the unit time period refers to a time unit used for collecting statistics on business data, which may be 1 minute, half an hour, 1 hour, 1 day or 1 week. In different scenarios, it can be set according to the needs of the application scenario.

[0053] In step S100, historical business data can be obtained by reading business data of different grids in different unit time periods recorded in the server database. Alternatively, the historical business data can also be obtained by a user manually uploading a business data record electronic form.

[0054] In step S200, all grids in the selected map area are clustered according to historical business data, in order to obtain grid clusters with similar business data attributes and close locations. These grid clusters form the basis for the subsequent construction of fenced areas.

[0055] In an optional implementation, the map area may be a city or district specified by the administrative division, for example, Shanghai or Wuhan. At the same time, the map area may be selected through the interactive interface. Moreover, the selected time period includes multiple continuous unit time periods, or a specific unit time period. For example, the unit time period may be 1 hour, and the selected time period may be 0:00 on November 1, 2024 to 12:00 on November 15, 2024. Alternatively, the selected time period may also be the 1-hour time period from 14:00 to 15:00 on November 1, 2024. The selected time period may be selected and specified through the selection control in the interactive interface.

[0056] In an optional implementation, if Figure 2 As shown, step S200 may include the following steps:

[0057] Step S201: determining a selected time period and data items of historical business data through the interactive interface.

[0058] The data items of the business data that need to be clustered can also be selected and determined. For example, you can choose to cluster only the task release volume or the task acceptance volume, or you can cluster both at the same time. In the case that there are more data items in the business data, you can also select all or a subset of these data items as the basis for clustering.

[0059] Step S202: determining a feature vector of a grid according to the selected data items of the selected time period and the position information of the grid.

[0060] Specifically, selected data items of all grids in a predetermined map area are extracted from the historical business data according to the selected time period. Then, the location information of the grids and the selected data items are combined into a feature vector for clustering. If the predetermined time period includes multiple unit time periods, since the business data is distributed according to time, the feature vector can use the sum of the business data of the selected time period as the element of the feature vector. In an alternative implementation, the sequence of the business data of multiple unit time periods in the selected time period can also be used as the element of the feature vector. For example, if the unit time period is 1 hour, and the selected time period is 3 hours from 14:00 to 17:00 on November 1, 2024, then the feature vector can be constructed as {[location information], [A1, A2, A3]}, where A1, A2 and A3 are the business data of the three unit time periods of 14:00-15:00, 15:00-16:00, and 16:00-17:00 respectively (such as the number of orders issued, or a tensor including the number of orders issued and the number of responses), and [A1, A2, A3] is a sequence containing the business data of the above unit time periods. Using sequences for clustering can obtain grid clusters with closer spatiotemporal distribution of attributes.

[0061] Step S203: clustering the feature vectors to determine a plurality of grid clusters.

[0062] Specifically, various existing unsupervised clustering methods can be used to cluster feature vectors, for example, the K-means algorithm. The main goal of the K-means algorithm is to divide the data set into k clusters, with the data points in each cluster having higher similarity, and the data points between different clusters having lower similarity. In the K-means algorithm, k initial centroids are first selected, which can be selected randomly or through a specific strategy. Each data point is then assigned to the nearest centroid to form k clusters, where "nearest" usually refers to the Euclidean distance, but other distance metrics can also be used. Next, the mean of all data points in each cluster is calculated and used as the new centroid. The process of assigning data points and updating the centroid is repeated until the centroid no longer changes or the predetermined maximum number of iterations is reached.

[0063] Thus, through step S200, the preliminary grouping of the grids can be obtained. However, clustering does not consider the final overall outer boundary shape of the grid cluster. Although the grid clusters obtained by clustering are connected in position and have similar business data performance, they may form some situations that cannot be used as an independent fence area. For example, Figure 3 As shown in FIG. 1 , the area surrounded by the clustered grid cluster 31 forms one or more rings, with a certain number of empty grids 32 or grids that are clustered into other grid clusters in the middle. If such a grid cluster is directly constructed into a fenced area and the fenced area is used as the basic geographical unit for implementing the scheduling strategy, it will cause scheduling confusion. Figure 3 The middle ring area is used as the implementation area of ​​the scheduling strategy. The relevant online car-hailing vehicles will be confused that they cannot get rewards for accepting orders in the enclosed grid 32. At the same time, such a shape is not convenient for operators to use or further construct an aggregate fence. Therefore, it is necessary to optimize the shape of the grid cluster to obtain the corresponding multiple fence areas. Since the convex polygon area is conducive to the visual observation of the operator, and from the perspective of traffic, the convex polygon area is easier to enter and exit from different directions, the goal of shape optimization is to obtain multiple grid clusters with convex polygon outer boundaries as fence areas.

[0064] Therefore, in step S300, shape optimization is performed on each grid cluster to determine multiple fence areas. Specifically, shape optimization includes merging at least one grid that does not belong to the target grid cluster into the target fence area, or dividing at least one grid that belongs to the target grid cluster into an independent fence area or merging it with other fence areas. Shape optimization can also directly merge a grid cluster containing a small number of grids (for example, the number of grids is less than or equal to 2) with an adjacent grid cluster with the highest business data similarity to form a fence area. The above-mentioned merging and division include the merging of grid clusters and grid clusters obtained by clustering business data, and also include the merging of empty grid clusters and existing area fences. At the same time, the shape optimization process can be completed through multiple iterations.

[0065] Figure 4 FIG. 1 is a flow chart of adding an empty grid in the process of shape optimization of a grid cluster according to an embodiment of the present invention. Figure 4 As shown, the shape optimization process corresponding to step S300 includes at least the following steps:

[0066] Step S401: determining a target grid cluster among multiple grid clusters.

[0067] It should be understood that before step S401, all the empty grids that have not been clustered in the map area can be determined in advance. In this embodiment, the empty grids are grids that have not been clustered due to the absence of business data.

[0068] The target mesh cluster is the mesh cluster that needs to be processed in the current iteration cycle. The target mesh cluster can be a specific mesh cluster or multiple mesh clusters. In the following description, the target mesh cluster is taken as an example for explanation.

[0069] Step S402: for a target grid cluster, determine a boundary grid cluster of an area covered by the target grid cluster.

[0070] In this embodiment, the boundary grid refers to the grid located at the edge of the grid cluster. One feature of the edge grid is that among the six grids adjacent to its six sides, at least one grid does not belong to the same grid cluster as the edge grid, that is, the number of adjacent grids of the edge grid in the grid cluster is less than 6. Therefore, by traversing each grid in the target grid cluster and counting its adjacent grids in the target grid cluster, a boundary grid set can be determined. The boundary grid set can use a data structure such as a linked list or a list to store its grid identifier.

[0071] Figure 5 FIG. 1 is a schematic diagram of determining a boundary grid during shape optimization of a grid cluster according to an embodiment of the present invention. Figure 5As shown, for the target grid cluster 5, each of its boundary grid clusters 51 has at least one adjacent grid 52 that does not belong to the target grid cluster, and all six adjacent grids of the non-boundary grid 53 belong to the target grid cluster.

[0072] Step S403, searching for empty grids starting from the boundary grids.

[0073] Similarly, an empty grid search traversal can be performed from each boundary grid along the direction of the adjacent grid belonging to the non-target grid cluster. If an empty grid is found, the empty grid is added to a list until the search ends. Searching for empty grids starting from the boundary grid can effectively obtain empty grids suitable for merging with the target grid cluster.

[0074] The end of the search includes a variety of different situations.

[0075] In step S404, it is determined whether the search reaches a predetermined stop condition or the number of empty grids is greater than a preset second threshold. If so, step S405 is executed to stop the search. If not, step S406 is executed after the search is completed.

[0076] In step S405, the search is stopped. After the search is stopped, the process may return to step S401 to determine a new target grid cluster for the next iteration.

[0077] The search reaches the preset condition means that the preset search amount is reached during the search process, so the search can be stopped. For example, if the search algorithm adopts the depth-first search algorithm, then when the search depth reaches the preset value, the search is not ended, which means that there are too many empty grids around the boundary grid, which is not suitable for subsequent operations, so the search is stopped.

[0078] If the number of empty grids is greater than the preset second threshold, it also indicates that the size of the empty grids around the target grid cluster is too large and needs to be segmented before processing. Therefore, the search is also stopped. Stopping the search means stopping the process of merging the empty grids into each grid cluster.

[0079] If the search is not interrupted due to the reasons in step S404, but is completed according to the preset process and the search completion conditions are met, then the process proceeds to step S406.

[0080] In step S406, it is determined whether the number of empty grids searched is zero. If yes, step S407 is executed. If no, step S408 is executed.

[0081] In step S407, if there are no empty grids around the boundary of the target grid cluster, then there is no need to merge the empty grids, so the merging operation of this round of iteration is stopped. After the merging is stopped, the process can return to step S401 to determine a new target grid cluster for the next round of iteration.

[0082] In step S408, at least one empty grid cluster is determined, wherein the empty grid cluster includes at least one empty grid connected to each other.

[0083] Specifically, different empty grid clusters may include duplicate empty grids, so multiple empty grid clusters may be deduplicated to remove duplicate empty grids from one or more empty grid clusters, thereby ensuring that there are no duplicate grids between different empty grid clusters.

[0084] In step S409 to step S411, for all empty grid clusters, according to the number of empty grids contained, they are merged with the target grid cluster or divided into adjacent fence areas / non-target grid clusters.

[0085] In step S409, it is determined whether the number of empty grids in the empty grid cluster is greater than a first threshold, if so, step S410 is executed, otherwise, step S411 is executed.

[0086] In step S410 , in response to the number of empty grids in the empty grid cluster being greater than a first threshold, the empty grid cluster and at least one connected boundary grid are divided into neighbor fence areas with the highest overlap.

[0087] In step S411 , in response to the number of empty grids in the empty grid cluster being less than or equal to a first threshold, the empty grid cluster is assigned to a fence area corresponding to the target grid cluster.

[0088] That is to say, if the number of empty grids in the empty grid cluster is small, it means that the holes between or inside the grid clusters are small. In this case, the difference between the business data of the hole area and the business data of other grids will not have a significant impact on the properties of the entire area. In this case, the empty grid cluster is directly merged into the fence area corresponding to the target grid cluster.

[0089] If there are many empty grids in the empty grid cluster, it means that there are large holes between the grid clusters. In this case, it is not determined whether it is located inside a certain grid cluster, but the overlap between the hole area (that is, the empty grid cluster) and the adjacent grid cluster is judged. Specifically, the number of grid overlapped vertices or the proportion of the number of overlapped vertices with the adjacent grid cluster can be used as the overlap to bring practicality. If the empty grid cluster is located inside the target grid cluster, then only the target grid cluster is adjacent to it, so the overlap of the target grid cluster is the highest, that is, all vertices overlap, so the empty grid cluster is directly merged into the target grid cluster. If the empty grid cluster is located between the target grid cluster and another or several other non-target grid clusters. Then determine the grid cluster with the largest number of overlapping vertices with the empty grid cluster, and merge the empty grid cluster with it. Optionally, the shared edges can also be used as the overlap.

[0090] Figure 6 Figure 2 shows a schematic diagram of merging empty grid clusters. Figure 6 , two empty grid clusters 61 and 62 are searched from the boundary grids of the target grid cluster 6. Among them, the empty grid cluster 61 is located at the edge of the target grid cluster 6, but the number of grids in the empty grid cluster 61 is 2, which is less than or equal to the preset first threshold 2. Therefore, the empty grid cluster 61 can be merged into the target grid cluster 6. The empty grid cluster 62 is located inside the target grid cluster 6, and its number is 4, which is greater than the preset first threshold 2. At this time, it is necessary to judge its overlap with the adjacent grid clusters. Since the empty grid cluster 62 is located inside the target grid cluster 6 and only overlaps with the target grid cluster 6, the empty grid cluster 62 should also be merged into the target grid cluster 6.

[0091] Figure 7 FIG. 4 shows an exemplary schematic diagram of merging empty grid clusters between grid clusters. Figure 7 In , an empty grid cluster 71 is searched from the boundary grid of the target grid cluster 7. The empty grid cluster 71 is located at the edge of the target grid cluster 7, and is adjacent to the target grid cluster 7 and the adjacent grid clusters 72 and 73. The number of empty grids in the empty grid cluster 71 is 4, which is greater than the preset first threshold 2. Therefore, it is necessary to determine the overlap between the empty grid cluster 71 and the adjacent grid clusters 7, 72, and 73. Since the empty grid cluster 71 and the grid cluster 72 have the most overlapping vertices, it is determined that the overlap between the two is the highest, and the empty grid cluster 71 is merged with the grid cluster 72.

[0092] In step S411, the data of the fence area is updated.

[0093] After completing the data update for the fence area, the process may return to step S401 and continue to iterate until all empty grids are merged.

[0094] Thus, it is ensured that multiple fenced areas without holes and closely adjacent to each other can be formed in the predetermined map area. Based on these fenced areas, subsequent human-computer interaction can be effectively carried out, and necessary aggregation can be performed to generate geographic fences for implementing scheduling strategies.

[0095] Figure 8 Schematic diagram of the interactive interface of an embodiment of the present invention. Figure 8 As shown, the interactive interface 8 includes an operation area 81, a map control 82 and a sidebar 83. Various selection controls or text controls are set in the operation area 81 for selecting time periods, map areas and data items. At the same time, these selection controls or text controls can also be used to input screening conditions to filter data for fence area results for selected time periods and selected data items. The map control 82 is used to display different fence areas 82a on the map background. Among them, the selected data items of the clustered business data can be divided into different levels, and each fence area 82a has a corresponding level of business data. In the map control 82, fence areas 82a with different business data levels are displayed in different colors (different colors or different grayscales), so that operators can easily view the approximate properties of different fence areas from the map control 82. The sidebar 83 can set different options for operators to select data items or other content. At the same time, the interactive interface 8 can also include a floating information display control 84. The floating information display control 84 can be located in the upper layer of the map control 82 in the form of a floating window, displaying the business data of the target fence area or the selected target fence area at the cursor position and the fence area identification. The business data displayed in the floating information display control 84 may not be limited to the data used for clustering. Taking the online car-hailing business as an example, the displayed business data includes the regional order ratio, the number of regional responses, the number of regional orders, the regional response rate, etc. At the same time, a data item selection control 85 can also be set, and the data item selection control 85 can select the major category of data items that you want the floating information display control 84 to display.

[0096] Optionally, a color scale 82b corresponding to different business data levels may also be displayed on the map control 82. This can facilitate the operator to compare and view the levels corresponding to the fenced area 82a.

[0097] In order to achieve the above interaction, the method of this embodiment may include the following steps: determining the currently selected target fence area or the target fence area where the cursor is suspended; displaying the business data of the target fence area in the interactive interface; receiving a data item selection operation for a floating information display control; and switching the business data type displayed in the floating information display control according to the data item selection operation.

[0098] Therefore, by interacting with the operator through the interactive interface 8, it is possible to obtain and display the fence area and display related business data.

[0099] Correspondingly, this embodiment completes the above functions through steps S400-S500, that is:

[0100] Step S400, receiving screening conditions through an interactive interface.

[0101] Step S500: Display the fenced areas that meet the screening conditions in a highlighted manner in the map interface, wherein fenced areas with different business data levels have different colors.

[0102] Furthermore, the method of this embodiment can further interact with the operator through an interactive interface to aggregate at least one fence area to generate an aggregate fence, so that the operator can perform further operations on the area of ​​the related aggregate fence.

[0103] In step S600, a selection instruction is received to determine at least one selected fence area.

[0104] By selecting the map control 82, one or more fenced areas can be selected, or one or more fenced areas that have been selected can be deselected. Thus, the operator can consider the need to aggregate those fenced areas to implement the same scheduling strategy based on the color of the fenced areas and the specific data displayed in the floating information display control 84.

[0105] The purpose of providing the manual selection function is that in some cases, after screening by the screening conditions, there are still some fence areas that are screened out among multiple fence areas suitable for implementing the same scheduling strategy. At this time, if these fence areas with unreasonable shapes are directly aggregated, it will cause the drivers guided by the scheduling strategy to be dissatisfied with the division of the aggregated area (or the area that can enjoy the scheduling strategy) in the future, and a lot of explanation and communication are required. In this case, you can manually select additional fence areas, or remove some fence areas, and aggregate to generate a suitable aggregate fence.

[0106] Step S700: generating an aggregate fence according to the at least one selected fence area.

[0107] In step S700, the selected fence area can be generated into an aggregate fence. The aggregate fence includes one or more fence areas where the operator believes that the scheduling strategy can be implemented. The aggregate fence can be reflected as a list of all grids in the area or relevant information about the area boundary. At the same time, a semi-transparent mask can be displayed on the interactive interface for the area corresponding to the aggregate fence to facilitate the operator to view.

[0108] That is, after the aggregation fence is generated, step S800 may be further included to set a scheduling strategy for the aggregation fence. The scheduling strategy at least includes a profit adjustment strategy for undertaking tasks in the area corresponding to the aggregation fence. For example, in the online car-hailing business, the scheduling strategy may be a commission reward for orders for undertaking ride tasks in the scheduling area.

[0109] The regional information or boundary information of the aggregate fence can be downloaded by the operator and imported into the system for implementing the scheduling strategy. After the aggregate fence is generated, the operator can jump to the scheduling strategy page and enter the scheduling strategy to be implemented for the aggregate fence, thereby deploying the scheduling strategy online.

[0110] The method of the embodiment of the present invention clusters grids according to the location information and historical business data of the grids, clusters grids with close locations and similar historical business data attributes into grid clusters, and then optimizes the shape of the grid clusters to obtain multiple fence areas, each fence area has a convex polygonal outer boundary that is relatively suitable for scheduling and has similar attributes. At the same time, an interactive interface is provided to display the initial attributes and detailed data of different fence areas to operators, and an aggregate fence can be generated according to at least one selected fence area. As a result, operators can adjust the fence area and generate an aggregate fence that aggregates multiple fence areas to apply a scheduling strategy, which is convenient for the subsequent implementation of the scheduling strategy.

[0111] Fig. 9 Schematic diagram of a geographic information processing device according to an embodiment of the present invention. Fig. 9 As shown, the geographic information processing device of this embodiment includes a historical data acquisition unit 91, a clustering unit 92, an optimization unit 93, an interaction unit 94, a display unit 95, a selection unit 96 and an aggregation unit 97.

[0112] The historical data acquisition unit 91 is used to acquire historical business data, wherein the historical business data includes business data of different grids in different unit time periods; the clustering unit 92 is used to perform grid clustering for each grid in the selected map area according to the location information of the grid and the historical business data of the selected time period, and determine multiple grid clusters, wherein the grid cluster includes at least one grid, and the selected time period includes at least one unit time period; the optimization unit 93 is used to perform shape optimization for each grid cluster, and determine multiple fence areas, wherein the fence areas are grid clusters with convex polygonal outer boundaries; the interaction unit 94 is used to receive filtering conditions through the interaction interface; the display unit 95 is used to display the fence areas that meet the filtering conditions in the map interface in a highlighted manner, wherein fence areas with different business data levels have different colors; the selection unit 96 is used to receive a selection instruction to determine at least one selected fence area; the aggregation unit 97 is used to generate an aggregated fence based on the at least one selected fence area.

[0113] The device of the embodiment of the present invention clusters grids according to the location information and historical business data of the grids, clusters grids with close locations and similar historical business data attributes into grid clusters, and then optimizes the shape of the grid clusters to obtain multiple fence areas, each fence area has a convex polygonal outer boundary that is relatively suitable for scheduling and has similar attributes. At the same time, an interactive interface is provided to display the preliminary attributes and detailed data of different fence areas to operators, and an aggregate fence can be generated according to at least one selected fence area. Thus, operators can adjust the fence area and generate an aggregate fence that aggregates multiple fence areas to generate a scheduling strategy, which is convenient for the subsequent implementation of the scheduling strategy.

[0114] Fig.10 Schematic diagram of an electronic device according to an embodiment of the present invention. Fig.10 As shown, the electronic device includes a general computer hardware structure for implementing the above method of the embodiment of the present invention, which at least includes a processor 101 and a memory 102.

[0115] The processor 101 and the memory 102 are connected via a bus 103. The memory 102 is suitable for storing instructions or programs executable by the processor 101. The processor 101 may be an independent microprocessor or a collection of one or more microprocessors. Thus, the processor 101 executes the instructions stored in the memory 102, thereby executing the method flow of the embodiment of the present invention as described above to realize the processing of data and the control of other devices. The bus 103 connects the above-mentioned multiple components together, and at the same time connects the above-mentioned components to the display controller 104 and the display device and the input / output (I / O) device 105. The input / output (I / O) device 105 may be a mouse, a keyboard, a modem, a network interface, a touch input device, a somatosensory input device, a printer, and other devices known in the art. Typically, the input / output device 105 is connected to the system via an input / output (I / O) controller 106.

[0116] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, devices (equipment) or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application may adopt a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0117] The present application is described with reference to flowcharts of methods, apparatuses (devices) and computer program products according to embodiments of the present application. It should be understood that each process in the flowchart can be implemented by computer program instructions.

[0118] These computer program instructions may be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device that implements the process Figure 1 A function specified in a process or multiple processes.

[0119] These computer program instructions may also be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce the instructions for implementing the process Figure 1 A device that specifies functions in a process or multiple processes.

[0120] Another embodiment of the present invention relates to a non-volatile storage medium for storing a computer-readable program, wherein the computer-readable program is used for a computer to execute part or all of the above method embodiments.

[0121] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by specifying relevant hardware through a program, and the program is stored in a storage medium, including several instructions for a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0122] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A geographic information processing method, characterized in that: The method comprises: Acquire historical business data, wherein the historical business data includes business data of different grids in different unit time periods; For each grid in the selected map area, clustering the grids according to the location information of the grids and the historical business data of the selected time period to determine a plurality of grid clusters, wherein the grid cluster includes at least one grid, and the selected time period includes at least one unit time period; Performing shape optimization on each mesh cluster to determine a plurality of fenced areas, wherein the fenced areas are mesh clusters having convex polygonal outer boundaries; Receiving filtering conditions through an interactive interface; The fenced areas meeting the filtering conditions are displayed in a highlighted manner in the map interface, wherein fenced areas with different business data levels have different colors; receiving a selection instruction to determine at least one fence area selected; An aggregate fence is generated according to the selected at least one fence area.

2. The method according to claim 1, characterized in that The business data includes the task release volume and task acceptance volume of the grid in the corresponding unit time period.

3. The method according to claim 1, characterized in that The method further comprises: Determine the currently selected target fence area or the target fence area where the cursor is hovering; The business data of the target fence area is displayed in the interactive interface.

4. The method according to claim 3, characterized in that The business data of the target fence area is displayed in the floating information display control of the interactive interface; The method further comprises: Receive a data item selection operation for a floating information display control; The business data type displayed in the floating information display control is switched according to the data item selection operation.

5. The method according to claim 1, characterized in that The shape optimization includes merging at least one mesh that does not belong to the target mesh cluster into the target fence area, or dividing at least one mesh that belongs to the target mesh cluster into independent fence areas or merging it with a non-target fence area.

6. The method according to claim 1, characterized in that The method further comprises: A scheduling strategy is set for the aggregate fence, and the scheduling strategy at least includes a profit adjustment strategy for undertaking tasks in the area corresponding to the aggregate fence.

7. The method according to claim 1, characterized in that Grid clustering based on the location information of the grid and the historical business data of the selected time period includes: Determine the selected time period and the selected data items of the historical business data through the interactive interface; Determine a feature vector of a grid based on selected data items of a selected time period and position information of the grid; The feature vectors are clustered to determine a plurality of grid clusters.

8. The method according to claim 1, characterized in that The performing shape optimization on each grid cluster and determining a plurality of fence areas comprises: Determine an empty grid, where the empty grid is a grid that cannot be clustered due to the absence of business data; The empty grids are merged into each grid cluster to determine a plurality of fenced areas.

9. The method according to claim 8, characterized in that Merging the empty grids into each grid cluster comprises: For a target grid cluster, determining a boundary grid cluster of an area covered by the target grid cluster; Searching for empty grids from each of the boundary grid clusters to determine at least one empty grid cluster, wherein the empty grid cluster includes at least one empty grid connected to each other; In response to the number of empty grids in the empty grid cluster being less than or equal to a first threshold, assigning the empty grid cluster to a fence area corresponding to the target grid cluster; In response to the number of empty grids in the empty grid cluster being greater than a first threshold, dividing the empty grid cluster and at least one connected boundary grid into a neighbor fence area with the highest overlap; Update the data of the fence area.

10. The method according to claim 9, characterized in that Merging the empty grids into each grid cluster further includes: In response to the search reaching a predetermined stop condition, or the number of empty grids found to be greater than a second threshold, stopping the search; In response to finding that the number of empty grids is zero, merging the empty grids into each grid cluster is stopped.

11. A geographic information processing device, characterized in that: The device comprises: A historical data acquisition unit, used to acquire historical business data, wherein the historical business data includes business data of different grids in different unit time periods; A clustering unit, configured to cluster grids for each grid in the selected map area according to the location information of the grids and the historical business data of the selected time period, and determine a plurality of grid clusters, wherein the grid cluster includes at least one grid, and the selected time period includes at least one unit time period; An optimization unit, configured to perform shape optimization on each mesh cluster and determine a plurality of fence regions, wherein the fence regions are mesh clusters having convex polygonal outer boundaries; An interaction unit, used for receiving screening conditions through an interaction interface; A display unit, used to display fenced areas that meet the screening conditions in a highlighted manner in a map interface, wherein fenced areas with different business data levels have different colors; A selection unit, configured to receive a selection instruction and determine at least one fence area to be selected; The aggregation unit is used to generate an aggregate fence according to the at least one selected fence area.

12. An electronic device, characterized in that: The electronic device comprises a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method according to any one of claims 1-10.

13. A computer-readable storage medium storing computer program instructions, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 10 is implemented.

Images