A method and device for processing AOI data

Abstract

Embodiments of the present invention provide a method and apparatus for processing AOI data. The method comprises: obtaining candidate AOI data corresponding to target POI data from multiple sources; extracting feature data from each of the candidate AOI data; sorting the candidate AOI data based on the feature data, selecting target AOI data from the sorted results; and using the target AOI data as the final AOI data for the target POI data. Embodiments of the present invention avoid manually selecting the final AOI data from multiple candidate AOI data, saving labor costs and improving the efficiency of selecting the final AOI data for the target POI data.

Description

Technical Field

[0001] The present invention relates to the field of Internet technology, and in particular to a method and device for processing AOI data. Background Art

[0002] Point of Information (POI) data in map data represents a real entity in the physical world, such as a house, a restaurant, a building, a bus stop, and so on. For some special POI data, corresponding fence information exists in the physical world. For example, a residential community has a corresponding fenced area. Fenced areas are called Areas of Interest (AOIs). AOIs are regional geographic entities in map data, such as a residential community, a university, an office building, an industrial park, a shopping mall, a hospital, a scenic spot, or a stadium.

[0003] Currently, AOI data for a single POI often comes from multiple sources, and the quality of these data varies greatly, making it impossible to directly select the optimal AOI data from multiple sources. To select the optimal AOI data from multiple sources, manual verification is required, which is inefficient and requires significant labor costs. Summary of the Invention

[0004] In view of the above problems, embodiments of the present invention are proposed to provide a method and apparatus for processing AOI data that overcomes the above problems or at least partially solves the above problems.

[0005] In order to solve the above problems, according to a first aspect of an embodiment of the present invention, a method for processing AOI data is disclosed, comprising: obtaining candidate AOI data from multiple sources corresponding to target POI data; extracting feature data of each candidate AOI data; sorting the candidate AOI data according to the feature data, and selecting target AOI data from the sorting results; and using the target AOI data as the final AOI data of the target POI data.

[0006] Optionally, extracting the feature data of the candidate AOI data respectively includes calculating one or more of area features, distance features and quantity features of the candidate AOI data.

[0007] Optionally, the calculating of the area feature of the candidate AOI data includes: calculating the contour area of ​​the candidate AOI data, and / or calculating the contour area of ​​the largest sub-candidate AOI data obtained by dividing the candidate AOI data by a preset first-level road; the calculating of the distance feature of the candidate AOI data includes: calculating the mileage of the first-level road contained in the candidate AOI data, and / or calculating the mileage of the preset second-level road contained in the candidate AOI data, and / or calculating the distance between the candidate AOI data and a preset representative point; the calculating of the quantity feature of the candidate AOI data includes: calculating the number of vertices of the candidate AOI data, and / or calculating the number of contour data contained in the candidate AOI data, and / or calculating the number of contour data intersecting with the candidate AOI data, and / or calculating the number of boundaries in the candidate AOI data that are parallel to a preset movement trajectory.

[0008] Optionally, before sorting the candidate AOI data according to the feature data, the method further comprises: merging the feature data according to a preset merging function.

[0009] Optionally, sorting the candidate AOI data according to the feature data and selecting the target AOI data from the sorting results includes: inputting the merged feature data into a preset machine learning model, and outputting the source number of the target AOI data, wherein the machine learning model is used to sort the candidate AOI data.

[0010] According to a second aspect of an embodiment of the present invention, a device for processing AOI data is further disclosed, including: an acquisition module for acquiring candidate AOI data from multiple sources corresponding to target POI data; an extraction module for respectively extracting feature data of the candidate AOI data; a sorting module for sorting the candidate AOI data according to the feature data and selecting target AOI data from the sorting results; and a determination module for using the target AOI data as the final AOI data of the target POI data.

[0011] Optionally, the extraction module is used to calculate one or more of the area feature, distance feature and quantity feature of the candidate AOI data.

[0012] Optionally, the extraction module is used to calculate the contour area of ​​the candidate AOI data, and / or calculate the contour area of ​​the largest sub-candidate AOI data obtained by dividing the candidate AOI data by a preset first-level road; the extraction module is also used to calculate the mileage of the first-level road contained in the candidate AOI data, and / or calculate the mileage of the preset second-level road contained in the candidate AOI data, and / or calculate the distance between the candidate AOI data and a preset representative point; the extraction module is also used to calculate the number of vertices of the candidate AOI data, and / or calculate the number of contour data contained in the candidate AOI data, and / or calculate the number of contour data intersecting with the candidate AOI data, and / or calculate the number of boundaries in the candidate AOI data that are parallel to the preset movement trajectory.

[0013] Optionally, the device further includes: a merging module, configured to merge the feature data according to a preset merging function before the sorting module sorts the candidate AOI data according to the feature data.

[0014] Optionally, the sorting module is used to input the merged feature data into a preset machine learning model and output the source number of the target AOI data, wherein the machine learning model is used to sort the candidate AOI data.

[0015] The embodiments of the present invention include the following advantages:

[0016] An embodiment of the present invention provides an AOI data processing solution, which obtains candidate AOI data from multiple sources corresponding to target POI data, extracts feature data of each candidate AOI data, sorts the candidate AOI data according to the feature data of the candidate AOI data, selects the target AOI data from the sorting results, and then uses the target AOI data as the final AOI data of the target POI data.

[0017] This embodiment of the present invention can extract feature data from multiple candidate AOI data, then sort the multiple candidate AOI data based on the feature data, and then select a target AOI from the sorted results, using the target AOI data as the final AOI data for the target POI data. This embodiment of the present invention avoids the need for manual screening of the final AOI data from multiple candidate AOI data, saving labor costs and improving the efficiency of selecting the final AOI data for the target POI data. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a flowchart of an embodiment of a method for processing AOI data of the present invention;

[0019] Figure 2 It is a flowchart of a multi-source AOI data screening method of the present invention;

[0020] Figure 3 It is a structural block diagram of an embodiment of an AOI data processing device of the present invention. DETAILED DESCRIPTION

[0021] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0022] Reference Figure 1 , shows a flowchart of an embodiment of a method for processing AOI data of the present invention. The method for processing AOI data can be used to filter out final AOI data for target POI data from multiple candidate AOI data. The method for processing AOI data can specifically include the following steps:

[0023] Step 101: Acquire candidate AOI data from multiple sources corresponding to target POI data.

[0024] In embodiments of the present invention, candidate AOI data may exist from multiple sources for a single target POI. These candidate AOI data can be understood as AOI data provided by various service providers for the target POI data. For example, if the target POI data is cell m, the candidate AOI data for cell m may include, but is not limited to, candidate AOI data n1 provided by the cell developer and candidate AOI data n2 provided by the courier. It should be noted that embodiments of the present invention do not impose specific restrictions on the number and type of sources for the candidate AOI data.

[0025] Step 102: extract feature data of candidate AOI data respectively.

[0026] In an embodiment of the present invention, feature data can be extracted for each candidate AOI data. Furthermore, the feature data for each candidate AOI data can include one or more types. In practical applications, regardless of whether the feature data is one or more types, the types corresponding to the feature data for each candidate AOI data can be the same. For example, if the extracted feature data for candidate AOI data n1 are of types T1, T2, and T3, then the extracted feature data for candidate AOI data n2 are also of types T1, T2, and T3.

[0027] Step 103: sort the candidate AOI data according to the feature data, and select the target AOI data from the sorting results.

[0028] In an embodiment of the present invention, each candidate AOI data item can be sorted based on its feature data. In practical applications, a corresponding numerical value can be output for each candidate AOI data item based on its feature data. Candidate AOIs with higher numerical values ​​can be ranked first during the sorting process, while those with lower numerical values ​​can be ranked last during the sorting process. It should be noted that the aforementioned high and low numerical values ​​are only relative, and ranking first and ranking last are also relative. In the embodiments of the present invention, the aforementioned high, low, front, and back should not be understood as absolute high, low, front, and back.

[0029] Step 104 : Using the target AOI data as the final AOI data of the target POI data.

[0030] In this embodiment of the present invention, the target AOI data selected from the sorting results can generally be the candidate AOI data with the highest value. That is, the candidate AOI data with the highest value is used as the final AOI data for the target POI data. Thus, this embodiment of the present invention achieves the effect of selecting the final AOI data for the target POI data from multiple candidate AOI data.

[0031] An embodiment of the present invention provides an AOI data processing solution, which obtains candidate AOI data from multiple sources corresponding to target POI data, extracts feature data of each candidate AOI data, sorts the candidate AOI data according to the feature data of the candidate AOI data, selects the target AOI data from the sorting results, and then uses the target AOI data as the final AOI data of the target POI data.

[0032] This embodiment of the present invention can extract feature data from multiple candidate AOI data, then sort the multiple candidate AOI data based on the feature data, and then select a target AOI from the sorted results, using the target AOI data as the final AOI data for the target POI data. This embodiment of the present invention avoids the need for manual screening of the final AOI data from multiple candidate AOI data, saving labor costs and improving the efficiency of selecting the final AOI data for the target POI data.

[0033] In an exemplary embodiment of the present invention, the feature data of the candidate AOI data can be divided into area features, distance features, and quantity features according to feature type. Therefore, when extracting the feature data of the candidate AOI data, one or more of the area features, distance features, and quantity features of the candidate AOI data can be calculated.

[0034] When calculating the area feature of the candidate AOI data, the contour area of ​​the candidate AOI data may be calculated, and / or the contour area of ​​the largest sub-candidate AOI data obtained by dividing the candidate AOI data by the preset first-level road may be calculated.

[0035] In practical applications, the preset first-class roads can be understood as high-class roads such as urban branch roads, main roads, expressways, highways, and bus-only roads. If the first-class road passes through the contour area corresponding to the candidate AOI data, the first-class road can split the candidate AOI data into at least two sub-candidate AOI data.

[0036] When calculating the distance features of the candidate AOI data, the mileage of the first-level roads contained in the candidate AOI data can be calculated, and / or the mileage of the preset second-level roads contained in the candidate AOI data can be calculated, and / or the distance between the candidate AOI data and the preset representative point can be calculated.

[0037] In practical applications, the preset second-level roads can be understood as low-level roads such as pedestrian paths. For each candidate AOI data, there is an abstract POI point corresponding to it, which is the representative point. When the candidate AOI data represents a contour area, the representative point represents a point. Moreover, the representative point does not necessarily lie within the contour area corresponding to the candidate AOI data. That is, the representative point can lie within the contour area corresponding to the candidate AOI data, or it can lie outside the contour area corresponding to the candidate AOI data.

[0038] When calculating the quantitative characteristics of the candidate AOI data, the number of vertices of the candidate AOI data can be calculated, and / or the number of contour data contained in the candidate AOI data can be calculated, and / or the number of contour data intersecting with the candidate AOI data can be calculated, and / or the number of boundaries in the candidate AOI data that are parallel to the preset movement trajectory can be calculated.

[0039] In practical applications, contour data can be understood as surface contour data, and the spatial relationship between contour data and candidate AOI data can be a containment relationship, an intersection relationship, or a separation relationship. For example, if the contour area corresponding to candidate AOI data n1 is a residential area, which contains Building 1 and Building 2, then the contour data corresponding to Building 1 and Building 2 respectively belong to the contour data contained in candidate AOI data n1. For another example, if the contour area corresponding to candidate AOI data n2 is a shopping mall, which shares a parking lot with the residential area corresponding to candidate AOI data n1, that is, part of the parking lot is located in the residential area corresponding to candidate AOI data n1, and another part of the parking lot is located in the shopping mall corresponding to candidate AOI data n2, then the contour data corresponding to the parking lot belongs to the contour data that intersects with candidate AOI data n1 and n2.

[0040] The preset movement trajectory can be understood as the movement trajectory provided by the business party, including but not limited to: express delivery trajectory, takeaway delivery trajectory, etc.

[0041] In an exemplary embodiment of the present invention, after extracting the feature data of the candidate AOI data, the feature data can be merged according to a preset merge function. In practical applications, the merge function can use connat(). concat() is used to connect two or more arrays. Moreover, concat() does not change the existing arrays but only returns a copy of the connected arrays. Each feature data can be used as an array connected by concat(). For each candidate AOI data, concat() can be used to merge each feature data into an array set. The array set can contain feature data arranged in a fixed order. Moreover, the arrangement order of the feature data of each candidate AOI data in the array set can be the same.

[0042] When the candidate AOI data are sorted according to the feature data and the target AOI data are selected from the sorting results, the above-mentioned array set, i.e., the merged feature data, can be input into a preset machine learning model to output the source number of the target AOI data. For example, the feature data of three candidate AOI data are all input into the machine learning model in the form of an array set, and the machine learning model can be used to sort the candidate AOI data. The machine learning model can output the identification information of the candidate AOI data with the highest value after sorting, i.e., the identification information of the target AOI data. In actual applications, the identification information is used to uniquely represent the target AOI data, and can be the source number of the target AOI data, etc. The embodiments of the present invention do not impose specific restrictions on the content, format, etc. of the identification information.

[0043] Based on the above description of an embodiment of a method for processing AOI data, a method for screening AOI data from multiple sources is introduced below. Figure 2 FIG. 1 is a flow chart of a method for screening multi-source AOI data. The AOI data in the embodiment of the present invention may also be referred to as AOI contour data.

[0044] First, feature extraction is performed on the AOI contour data from each source to complete the portrait of each AOI contour data. The portrait refers to describing the AOI contour data by extracting features. In practical applications, the following nine features can be extracted:

[0045] 1) Area feature: calculate the area of ​​each AOI contour data;

[0046] 2) Vertex features: Calculate the number of vertices of each AOI contour data;

[0047] 3) Cross-high-level road features: Calculate the mileage of each AOI contour data across high-level roads such as urban branch roads, main roads, expressways, highways, and bus-only roads;

[0048] 4) Shaping feature: By recalling the data of each AOI contour data across high-level roads, and climbing the road to shape the AOI contour data, the area size of the largest sub-AOI contour data is obtained;

[0049] 5) Source characteristics: Encode the AOI contour data from each source;

[0050] 6) Representative point feature: Calculate the distance from each AOI contour data to the representative point;

[0051] 7) Contour feature: Calculate the number of contour data contained in each AOI contour data, and the number of contour data intersecting with each AOI contour data;

[0052] 8) Trajectory features: Calculate the number of parallels between the boundary and trajectory of each AOI contour data;

[0053] 9) Cross-low-level road features: Calculate the mileage of low-level roads such as pedestrian roads contained in each AOI contour data.

[0054] Then, each AOI outline data is sorted according to the above characteristics of each AOI outline data.

[0055] In practical applications, each AOI contour data can be sorted by Rank(). Rank() is used to return the ranking of the value of the specified field within the result set partition. The ranking of the value of the specified field is the ranking of the previous related row plus one. Moreover, the specific implementation of Rank() can be to abstract the sorting process into an algorithm model. For example, the above features of each AOI contour data are merged, and the merged features are input into the XGBoost model. XGBoost is extreme gradient boosting. XGBoost is derived from the gradient boosting framework, but is more efficient. XGBoost can perform parallel calculations, approximate tree construction, effectively process sparse data, and optimize memory usage. The XGBoost model is then used to perform multi-classification processing and output the source features of the optimal AOI contour data, that is, output the source number of the optimal AOI contour data. For example, the features of AOI contour data from 10 sources are merged together through concat(), and then the merged features are input into the XGBoost model. The XGBoost model outputs 10 classification values, each of which corresponds to AOI contour data from 10 sources. The AOI contour data corresponding to the largest classification value among the 10 classification values ​​is the optimal AOI contour data.

[0056] Finally, the fusion operation of multi-source AOI contour data is performed according to the source number of the optimal AOI contour data obtained after sorting.

[0057] After sorting, the source number of the optimal AOI contour data is obtained, that is, the optimal AOI contour data is determined, and the optimal AOI contour data is used as the surface contour of the target POI data.

[0058] The AOI contour data in the embodiment of the present invention can be derived from the log data of each business party, and there is no need to specifically generate the AOI contour data, thereby reducing the cost of obtaining the AOI contour data.

[0059] The embodiments of the present invention can automatically extract the features of AOI contour data, automatically sort them using the features, and automatically output the source number of the optimal AOI contour data, thereby realizing an automated execution process of selecting the optimal AOI contour data for target POI data and improving the efficiency of screening the optimal AOI contour data.

[0060] Compared with manual screening of optimal AOI contour data, the embodiment of the present invention avoids the problem of screening errors caused by manual subjective judgment and improves the screening accuracy of optimal AOI contour data.

[0061] When the embodiments of the present invention are applied to scheduling scenarios, for example, online car-hailing boarding point recommendations, food delivery point recommendations, etc., more accurate online car-hailing boarding points or food delivery points can be recommended, thereby improving the accuracy of scheduling.

[0062] It should be noted that for the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0063] Reference Figure 3 , shows a structural block diagram of an embodiment of an AOI data processing device of the present invention, the AOI data processing device may specifically include the following modules:

[0064] An acquisition module 31 is configured to acquire candidate AOI data from multiple sources corresponding to target POI data;

[0065] An extraction module 32 is used to extract feature data of the candidate AOI data respectively;

[0066] A sorting module 33 is used to sort the candidate AOI data according to the feature data and select target AOI data from the sorting results;

[0067] The determination module 34 is configured to use the target AOI data as the final AOI data of the target POI data.

[0068] In an exemplary embodiment of the present invention, the extraction module 32 is configured to calculate one or more of the area feature, distance feature, and quantity feature of the candidate AOI data.

[0069] In an exemplary embodiment of the present invention, the extraction module 32 is configured to calculate the contour area of ​​the candidate AOI data, and / or calculate the contour area of ​​the largest sub-candidate AOI data obtained by dividing the candidate AOI data by a preset first-level road;

[0070] The extraction module 32 is further configured to calculate the mileage of the first-level road included in the candidate AOI data, and / or calculate the mileage of the preset second-level road included in the candidate AOI data, and / or calculate the distance between the candidate AOI data and a preset representative point;

[0071] The extraction module 32 is further configured to calculate the number of vertices of the candidate AOI data, and / or calculate the number of contour data contained in the candidate AOI data, and / or calculate the number of contour data intersecting with the candidate AOI data, and / or calculate the number of boundaries in the candidate AOI data that are parallel to a preset movement trajectory.

[0072] In an exemplary embodiment of the present invention, the apparatus further comprises:

[0073] The merging module is configured to merge the feature data according to a preset merging function before the sorting module 33 sorts the candidate AOI data according to the feature data.

[0074] In an exemplary embodiment of the present invention, the sorting module 33 is used to input the merged feature data into a preset machine learning model and output the source number of the target AOI data, wherein the machine learning model is used to sort the candidate AOI data.

[0075] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0076] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0077] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0078] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the process in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0079] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0080] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0081] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they become aware of the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0082] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or terminal device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or terminal device that includes the element.

[0083] The above is a detailed introduction to the AOI data processing method and device provided by the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only intended to help understand the method and core concept of the present invention. At the same time, for those skilled in the art, according to the concept of the present invention, there may be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for processing AOI data, characterized in that: include: Obtain candidate AOI data from multiple sources corresponding to the target POI data; Extracting feature data of the candidate AOI data respectively; Sorting the candidate AOI data according to the feature data, and selecting target AOI data from the sorting results; Using the target AOI data as the final AOI data of the target POI data; The extracting feature data of the candidate AOI data respectively includes: Calculating one or more of the area feature, distance feature, and quantity feature of the candidate AOI data; the calculating the area feature of the candidate AOI data includes: Calculating the contour area of ​​the candidate AOI data, and / or calculating the contour area of ​​the largest sub-candidate AOI data obtained by dividing the candidate AOI data by a preset first-level road; The calculating the distance feature of the candidate AOI data includes: Calculating the mileage of the first-level road included in the candidate AOI data, and / or calculating the mileage of the preset second-level road included in the candidate AOI data, and / or calculating the distance between the candidate AOI data and a preset representative point; The calculating of the quantitative features of the candidate AOI data includes: Calculate the number of vertices of the candidate AOI data, and / or calculate the number of contour data contained in the candidate AOI data, and / or calculate the number of contour data intersecting with the candidate AOI data, and / or calculate the number of boundaries in the candidate AOI data that are parallel to a preset movement trajectory.

2. The method according to claim 1, characterized in that Before sorting the candidate AOI data according to the feature data, the method further includes: The feature data are merged according to a preset merging function.

3. The method according to claim 2, characterized in that The step of sorting the candidate AOI data according to the feature data and selecting target AOI data from the sorting results includes: The merged feature data is input into a preset machine learning model, and the source number of the target AOI data is output, wherein the machine learning model is used to sort the candidate AOI data.

4. A device for processing AOI data, characterized in that: include: An acquisition module is used to acquire candidate AOI data from multiple sources corresponding to the target POI data; An extraction module, configured to extract feature data of the candidate AOI data respectively; A sorting module, configured to sort the candidate AOI data according to the feature data, and select target AOI data from the sorting results; A determination module, configured to use the target AOI data as final AOI data of the target POI data; The extraction module is configured to calculate one or more of an area feature, a distance feature, and a quantity feature of the candidate AOI data; the extraction module is configured to calculate a contour area of ​​the candidate AOI data, and / or calculate a contour area of ​​a maximum sub-candidate AOI data obtained by dividing the candidate AOI data by a preset first-level road; The extraction module is further configured to calculate the mileage of the first-level road included in the candidate AOI data, and / or calculate the mileage of the preset second-level road included in the candidate AOI data, and / or calculate the distance between the candidate AOI data and a preset representative point; The extraction module is further used to calculate the number of vertices of the candidate AOI data, and / or calculate the number of contour data contained in the candidate AOI data, and / or calculate the number of contour data intersecting with the candidate AOI data, and / or calculate the number of boundaries in the candidate AOI data that are parallel to the preset movement trajectory.

5. The device according to claim 4, characterized in that The device further comprises: A merging module is configured to merge the feature data according to a preset merging function before the sorting module sorts the candidate AOI data according to the feature data.

6. The device according to claim 5, characterized in that The sorting module is used to input the merged feature data into a preset machine learning model and output the source number of the target AOI data, wherein the machine learning model is used to sort the candidate AOI data.

Images