Method, device and computer equipment for detecting entrance and exit

Abstract

The embodiments of the present specification provide a method, apparatus and computer equipment for detecting entrances and exits, the method for detecting entrances and exits comprising: obtaining historical distribution trajectory data of an area of ​​entrances and exits to be detected; obtaining first road network data of passable roads in the area based on the historical distribution trajectory data, and then obtaining second road network data from the first road network data to the upper-level roads; wherein the first road network data comprises a plurality of first nodes and paths between each first node; the second road network data comprises a plurality of second nodes and paths between each second node to each first node; after generating a topological map using the first road network data and the second road network data, determining the entrance and exit locations of the area based on the connectivity between nodes in the topological map after one or more of the first nodes are deleted.

Description

Technical Field

[0001] The embodiments of this specification relate to the field of computer technology, and more particularly to methods, devices, and computer equipment for detecting entrances and exits. Background Art

[0002] At present, the delivery business has brought many conveniences to people's lives. Among them, the accuracy of the geographical location has a great impact on the delivery business. For example, whether the entrance and exit locations of areas of interest (AOI) such as residential areas or hospitals are accurate will have a great impact on the delivery efficiency of the delivery capacity. Based on this, it is necessary to provide a solution for detecting entrances and exits to accurately obtain the entrance and exit locations of AOI. Summary of the invention

[0003] To overcome the problems existing in the related art, the embodiments of this specification provide a method, an apparatus and a computer device for detecting an entrance and an exit.

[0004] According to a first aspect of an embodiment of this specification, a method for detecting an entrance and exit is provided, comprising:

[0005] Obtain historical delivery trajectory data for the area of ​​the entrance and exit to be detected;

[0006] After obtaining first road network data of drivable roads in the area according to the historical delivery trajectory data, obtaining second road network data from the first road network data to the upper level road; wherein the first road network data includes a plurality of first nodes and paths between each first node; the second road network data includes a plurality of second nodes and paths from each second node to each first node;

[0007] After a topological map is generated using the first road network data and the second road network data, the entrance and exit locations of the area are determined based on connectivity between nodes in the topological map after one or more of the first nodes are deleted.

[0008] In some examples, determining the entrance and exit locations of the area according to the connectivity between nodes in the topology graph after one or more of the first nodes are deleted includes any of the following:

[0009] If, after deleting one or more first nodes, the remaining first nodes in the first road network data cannot be connected to any second node in the second road network data, determining the positions of the deleted one or more first nodes as the entrance and exit positions of the area; and / or,

[0010] The entrance and exit positions of the area are determined based on the change in distance of the path from the remaining first nodes in the first road network data to the second nodes in the second road network data before and after one or more of the first nodes are deleted in the topological graph.

[0011] In some examples, the remaining first nodes in the first road network data are unable to connect with any second node in the second road network data, including:

[0012] The remaining first nodes in the first road network data constitute one or more connected subgraphs of the topological graph, and all the second nodes in the second road network data constitute another connected subgraph of the topological graph.

[0013] In some examples, the deletion method of the one or more first nodes includes:

[0014] For each first node, obtain a first path distance parameter from the first node to each second node, and obtain a second path distance parameter from the first node to each second node after deleting an edge between the first node and its adjacent nodes;

[0015] According to the difference between the second path distance parameter and the first path distance parameter of each of the first nodes in the first road network data, the first nodes are deleted in descending order.

[0016] In some examples, the first path distance parameter includes: an average value of the sum of the shortest path distances from the first node to each second node; and / or,

[0017] The method for obtaining the second path distance parameter includes:

[0018] Calculating a target parameter corresponding to any edge of the first node, where the target parameter refers to an average value of the sum of the shortest path distances between the first node and each second node after the edge is deleted;

[0019] The target parameters corresponding to the edges are compared, and the maximum target parameter is used as the second path distance parameter.

[0020] In some examples, the method of obtaining the area of ​​the entrance and exit to be detected includes:

[0021] Acquire road network data, wherein the road network data includes data of a plurality of roads;

[0022] Determining a closed area surrounded by a plurality of roads according to the road network data;

[0023] The closed area is used to determine the area of ​​the entrance and exit to be detected.

[0024] According to a second aspect of an embodiment of this specification, there is provided a device for detecting an entrance and an exit, comprising:

[0025] The trajectory acquisition module is used to: obtain the historical delivery trajectory data of the area of ​​the entrance and exit to be detected;

[0026] A road network acquisition module, used to: after acquiring first road network data of passable roads in the area according to the historical delivery trajectory data, acquire second road network data from the first road network data to the upper level road; wherein the first road network data includes a plurality of first nodes and paths between each first node; the second road network data includes a plurality of second nodes and paths between each second node to each first node;

[0027] The location determination module is used to: after generating a topology map using the first road network data and the second road network data, determine the entrance and exit locations of the area according to the connectivity between the nodes in the topology map after one or more of the first nodes are deleted.

[0028] In some examples, the location determination module is further configured to:

[0029] If, after deleting one or more first nodes, the remaining first nodes in the first road network data cannot be connected to any second node in the second road network data, determining the positions of the deleted one or more first nodes as the entrance and exit positions of the area; and / or,

[0030] The entrance and exit positions of the area are determined based on the change in distance of the path from the remaining first nodes in the first road network data to the second nodes in the second road network data before and after one or more of the first nodes are deleted in the topological graph.

[0031] In some examples, the remaining first nodes in the first road network data are unable to connect with any second node in the second road network data, including:

[0032] The remaining first nodes in the first road network data constitute one or more connected subgraphs of the topological graph, and all the second nodes in the second road network data constitute another connected subgraph of the topological graph.

[0033] In some examples, the location determination module is further configured to:

[0034] For each first node, obtain a first path distance parameter from the first node to each second node, and obtain a second path distance parameter from the first node to each second node after deleting an edge between the first node and its adjacent nodes;

[0035] According to the difference between the second path distance parameter and the first path distance parameter of each of the first nodes in the first road network data, the first nodes are deleted in descending order.

[0036] In some examples, the first path distance parameter includes: an average value of the sum of the shortest path distances from the first node to each second node; and / or,

[0037] The method for obtaining the second path distance parameter includes:

[0038] Calculating a target parameter corresponding to any edge of the first node, where the target parameter refers to an average value of the sum of the shortest path distances between the first node and each second node after the edge is deleted;

[0039] The target parameters corresponding to the edges are compared, and the maximum target parameter is used as the second path distance parameter.

[0040] In some examples, the trajectory acquisition module includes:

[0041] Acquire road network data, wherein the road network data includes data of a plurality of roads;

[0042] Determining a closed area surrounded by a plurality of roads according to the road network data;

[0043] The closed area is used to determine the area of ​​the entrance and exit to be detected.

[0044] According to a third aspect of the embodiments of this specification, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, an embodiment of the method described in the first aspect is implemented.

[0045] The technical solutions provided by the embodiments of this specification may have the following beneficial effects:

[0046] In an embodiment of the present specification, for an area where entrances and exits are to be detected, historical delivery trajectory data is used to obtain first road network data of accessible roads in the area, and then second road network data of roads of the previous level from the first road network data is obtained. A topological map can be generated by connecting the nodes and paths in the first road network data and the nodes and paths in the second road network data. Since the entrance and exit locations of the area connect the outer roads of the area to the inner roads of the area, the connectivity between the nodes in the topological map after one or more of the first nodes are deleted can be used to quickly and accurately determine the entrance and exit locations of the area.

[0047] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present specification. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the specification and, together with the description, serve to explain the principles of the specification.

[0049] Figure 1 It is a flow chart of a method for detecting an entrance and exit according to an exemplary embodiment of the present specification.

[0050] Figure 2 It is a schematic diagram of a topology diagram shown in this specification according to an exemplary embodiment.

[0051] Figure 3 It is a block diagram of a computer device where an apparatus for detecting an entrance and exit is located according to an exemplary embodiment of the present specification.

[0052] Figure 4 It is a block diagram of a device for detecting an entrance and exit according to an exemplary embodiment of the present specification. DETAILED DESCRIPTION

[0053] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with this specification. Instead, they are merely examples of devices and methods consistent with some aspects of this specification as detailed in the appended claims.

[0054] The terms used in this specification are for the purpose of describing specific embodiments only and are not intended to limit this specification. The singular forms "a", "the" and "the" used in this specification and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0055] It should be understood that although the terms first, second, third, etc. may be used in this specification to describe various information, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this specification, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0056] AOI's entrance and exit data is an important underlying data for distribution business, which can be used for the site selection of food delivery points, the identification of difficult-to-pick-up and difficult-to-deliver areas, and the design of navigation path planning strategies. At present, AOI's entrance and exit data mainly rely on map data, but the accuracy of map data is usually limited and cannot cover a smaller area. There are a lot of missing AOI entrance and exit data. Some processing ideas are to manually check the map data for annotation, which requires a lot of manpower and material resources.

[0057] Based on this, an embodiment of the present specification provides a method for detecting an entrance and exit, which can automatically and quickly detect the entrance and exit positions of the AOI. The embodiment of the present specification is described in detail below.

[0058] like Figure 1 As shown, Figure 1 This is a flow chart of a method for detecting an entrance and exit according to an exemplary embodiment of the present specification, comprising the following steps:

[0059] In step 102, historical delivery trajectory data of the area of ​​the entrance and exit to be detected is obtained.

[0060] In step 104, after obtaining the first road network data of the area according to the historical delivery trajectory data, the second road network data of the upper level road network from the first road network data is obtained.

[0061] Among them, the first road network data refers to the data of the passable roads located in the area, and the first road network data includes multiple first nodes and the paths between each first node; the second road network data includes multiple second nodes and the paths between each second node to each first node.

[0062] In step 106, after a topology map is generated using the first road network data and the second road network data, the entrance and exit locations of the area are determined based on the connectivity between nodes in the topology map after one or more of the first nodes are deleted.

[0063] In some examples, the area where the entrance is to be detected may include areas such as residential areas, industrial parks, hospitals or schools. These areas do not have accurate entrance and exit locations. The solution of this embodiment can detect accurate entrance and exit location information.

[0064] Optionally, the area of ​​the entrance to be detected may be specified by the user, for example, information of the area of ​​the unknown entrance and exit location input by the user, such as the name, geographical location information, etc. may be received.

[0065] Optionally, the region of the entrance to be detected may also be a region where unknown entrances and exits are automatically found in a variety of ways. For example, the region where no entrances and exits are recorded may be found through existing map data, or it may be found in combination with user demand information, such as finding it from map data according to the region type specified by the user.

[0066] Optionally, the map data has a large amount of information. In order to improve the efficiency of obtaining the area of ​​the entrance to be detected, the present embodiment can also obtain it through road network data. The road network data refers to the data used to describe the road in the map data, that is, the road network data includes data of multiple roads; in practical applications, according to the existing road grade classification standards and combined with business needs, the road network data of the present embodiment may include trunk road network data. Taking common residential areas, parks or schools as examples, the periphery of these areas is the trunk road. Therefore, the present embodiment can determine the area of ​​the entrance to be detected by using the closed area surrounded by each trunk road through each trunk road recorded in the trunk road network data. For example, each trunk road cuts each other, and the map can be divided into non-overlapping areas, and the area of ​​the entrance to be detected exists in these areas. For example, according to the road network data, a closed area surrounded by multiple roads is determined; the closed area is used to determine the area of ​​the entrance to be detected.

[0067] In actual applications, existing map data does not cover the geographic information within some areas, such as missing road data within the area, so it is impossible to obtain accurate entrance and exit location information through existing map data. In this embodiment, the first road network data of the accessible roads in the area can be obtained through the historical delivery trajectory data of the delivery capacity in the delivery scenario.

[0068] In this embodiment, the delivery capacity delivers items according to the delivery address, which includes the delivery process of the delivery capacity in the area, that is, in the process of the delivery capacity executing the delivery order, the activity trajectory of the delivery capacity includes the activity trajectory in the area, and these activity trajectories can cover the passable roads in the area. Therefore, the historical delivery trajectory data of the delivery capacity is used to obtain the first road network data of the passable roads in the area.

[0069] In some examples, the historical delivery trajectory data refers to the activity trajectory data of the delivery capacity during the delivery process. The delivery capacity here may include delivery personnel, delivery robots, drones, unmanned vehicles and other units with certain transportation and carrying capacity. The historical delivery trajectory data of the area of ​​the entrance and exit to be detected in this embodiment refers to the activity trajectory of the delivery capacity in this area. The acquisition process of the historical delivery trajectory data can be obtained after the authorization and consent of the delivery capacity. As an example, it can be obtained by using the collected data of the electronic device carried by the delivery capacity. The electronic device carried by the delivery party in this embodiment may include one or more of the following combinations: handheld portable devices such as smart phones, or wearable portable devices such as smart bracelets or smart watches, and may also include other electronic devices such as those configured on takeaway boxes or mobile tools (such as electric vehicles). A data acquisition unit for collecting data can be configured in the electronic device to collect the mobile state data of the electronic device, and these mobile state data characterize the activity state of the delivery capacity. In some examples, the electronic device is equipped with a positioning unit for collecting positioning information of the device; as an example, the positioning unit here may include a satellite-based positioning unit, such as a GPS (Global Positioning System) positioning unit or a Beidou satellite positioning unit, or a GLONASS or Galileo satellite positioning unit, etc., and the positioning information may include longitude, latitude and altitude. In other examples, the electronic device is equipped with a communication unit, and the communication unit can obtain positioning information including longitude and latitude by communicating with a base station.

[0070] Among them, the historical delivery trajectory data includes positioning information of multiple sampling moments, and the positioning information includes geographic coordinate information, that is, the historical delivery trajectory data includes multiple data points distributed in different geographical locations. In practical applications, for the area of ​​the entrance and exit to be detected, the business party may have a large amount of delivery trajectory data in the area. For example, there are some delivery orders corresponding to the area, and these delivery orders correspond to delivery trajectory data. Due to the differences in the actual activity trajectories of the delivery capacity between the delivery orders, the delivery trajectory data also have certain differences. The historical delivery trajectory data of the area of ​​this embodiment can be the delivery trajectory data that can represent the area determined by using the existing delivery trajectory data, such as the delivery trajectory data selected from the existing delivery trajectory data, or the delivery trajectory data obtained after processing the existing delivery trajectory data. For example, for a large amount of delivery trajectory data, it can be compressed by a trajectory data compression algorithm, such as the Douglas-Peucker algorithm and the Visvalingam-Whyatt algorithm. Alternatively, similar delivery trajectory data may be clustered as needed, and clustering algorithms may include clustering algorithms such as k-means. Based on the clustering results, trajectories of the same type may be merged as needed to ultimately obtain historical delivery trajectory data that can represent the area. In actual applications, the historical delivery trajectory data is not limited to whether it is vector trajectory data.

[0071] Therefore, in this embodiment, the first road network data of the passable roads in the area is obtained according to the historical delivery trajectory data, and the first road network data includes multiple first nodes and paths between the first nodes; wherein the first node can be determined by the data points included in the historical delivery trajectory data, and the path of each first node can be determined by the timing relationship between the data points, and each data point is connected according to the sampling time of each data point to form a path between the data points, so that the path between the first nodes can be obtained.

[0072] The first road network data is obtained through historical distribution trajectory data, which characterizes the activities of distribution capacity within the region; and during the distribution process, the distribution capacity enters the region from the outside of the region and then leaves the region from the inside of the region to the outside of the region. In order to determine the entrance and exit positions of the region, this embodiment further uses the first road network data to obtain the second road network data from the first road network data to the upper level road, and the second road network data refers to the data of the roads surrounding the region. Among them, the second road network data includes multiple second nodes and the paths between each second node and each first node, and the paths between each second node and each first node can include the paths between each second node.

[0073] In some examples, the second road network data can be obtained through historical distribution trajectory data, and the second nodes in the second road network data and the paths between each second node to each first node can be implemented with reference to the aforementioned implementation example of the first road network data. In other examples, it can also be obtained through the road network data of existing map data, and the road data in the existing road network data includes multiple nodes, geographic location information of the nodes, and paths between the nodes. Multiple second nodes and the paths between each second node can be obtained through the road network data, and then the paths between each second node to each first node can be obtained in combination with the paths between each first node in the first road network data. In other examples, the road network data can also be obtained in combination with the above-mentioned historical distribution trajectory data and the existing map data. As an example, when obtaining the second node in the second road network data, a k-step breadth-first search can be used, where k can be flexibly set according to needs.

[0074] After obtaining the first road network data and the second road network data, it can be determined that the first road network data and the second road network data contain the entrances and exits of the area. However, the first road network data and the second road network data include many nodes. This embodiment uses a topological map to quickly and accurately find the entrance and exit locations. Among them, a topological map including each first node, each second node, the path between each first node, and the path between each second node to each first node can be generated. In the specific implementation, in the data structure of the topological map, the path between the node and the adjacent node is expressed as the edge between the node and the adjacent node in the topological map. Since the entrance and exit locations of the area connect the peripheral roads of the area to the internal roads of the area, the entrance and exit locations of the area are the locations that must be passed from the peripheral roads of the area to the internal roads of the area. The topological map is analyzed, and the entrance and exit locations of the area can be determined through the connectivity between the nodes in the topological map after one or more of the first nodes are deleted.

[0075] For example, Figure 2 , which is a schematic diagram of a topology diagram according to an exemplary embodiment of the present specification. Figure 2 , there are shown a plurality of first nodes A1, A2, A3, A4 and A5, and a plurality of second nodes B1, B2, B3 and B4; wherein, Figure 2 For the sake of convenience, not all nodes are numbered, and the numbers of some nodes are shown. Through the topological map, this embodiment obtains the entrance and exit positions of the area by analyzing the topological map. The entrance and exit positions of the area can connect the inside and outside of the area. Therefore, this embodiment can determine the entrance and exit positions of the area based on the connectivity between the nodes in the topological map after one or more of the first nodes are deleted.

[0076] In some examples, the determination of the entrance and exit positions of the area according to the connectivity between the nodes after one or more of the first nodes are deleted in the topological graph includes: if after deleting one or more first nodes, the remaining first nodes in the first road network data cannot be connected to any second node in the second road network data, determining the positions of the one or more deleted first nodes as the entrance and exit positions of the area. In this embodiment, there are one or more entrance and exit positions of the area, so there may also be one or more first nodes representing the entrance and exit positions of the area in the topological graph. Therefore, if there is one first node representing the entrance and exit positions of the area, after deletion, the remaining first nodes in the first road network data cannot be connected to any second node in the second road network data; if there is more than one first node representing the entrance and exit positions of the area, all the first nodes representing the entrance and exit positions of the area can be deleted, and the remaining first nodes in the first road network data cannot be connected to any second node in the second road network data.

[0077] In this embodiment, nodes are connected by paths. After a node is deleted, the edges between the deleted node and the adjacent nodes are also deleted accordingly, and the adjacent nodes lose the paths leading to the deleted node. Therefore, after one or more of the first nodes are deleted, whether the remaining first nodes in the first road network data are connected to any second node in the second road network data can be determined by the paths between the nodes in the topology graph.

[0078] As an example, the remaining first nodes in the first road network data cannot be connected to any second node in the second road network data, including: the remaining first nodes in the first road network data constitute one or more connected subgraphs of the topological graph, and all second nodes of the second road network data constitute another connected subgraph of the topological graph. Figure 2 As shown, Figure 2 Take the A5 node as the entrance and exit position in the topology graph as an example. If the first node A5 is deleted, among the remaining nodes in the topology graph, the first node from A1 through A2, A3 and A4 to A1 forms a connected subgraph, and the second node from B1 through B2, B3 and B4 to B1 forms another connected subgraph. In practical applications, if there are multiple nodes that serve as entrances and exits of a region in the topology graph, after these nodes are deleted, multiple first nodes within the region may form multiple connected subgraphs.

[0079] In other examples, the deletion of the first node will also cause a change in the path distance in the topological map. Deleting the first node as the entrance and exit of the area and deleting the first node that is not the entrance and exit of the area will have different effects on the change in the distance of the path from the first node to the second node in the topological map. Therefore, the entrance and exit locations of the area can also be determined by the change in the distance of the path from the remaining first node in the first road network data to the second node in the second road network data before and after one or more of the first nodes are deleted in the topological map. Figure 2 For example, assuming that the A2 node is deleted, the path distance from the other remaining first nodes to the second node in the topology map remains unchanged before and after the deletion, and A5 is the entrance and exit location of the area. Before and after the deletion, the other remaining first nodes cannot lead to the second node. It can also be considered that the path distance from the other remaining first nodes to the second node becomes infinite. Therefore, the entrance and exit location of the area can also be determined by the change in path distance. In practical applications, according to needs, the above-mentioned embodiment of determining the inability to connect, or the embodiment of determining the change in path distance, or a combination of the two can be used to achieve the determination of the entrance and exit location of the area.

[0080] In practical applications, when deleting the first node in a topological map, there are multiple implementation methods as needed. For example, it can be deleted randomly; or, after selecting one of the first nodes to start deletion, the other first nodes can be deleted in a certain order. The order can be set as needed, such as the order of the first node number, or the order of the distance from the deleted first node, etc. Alternatively, the probability that the first node is the first node at the entrance and exit position can be predicted by combining the geographical location of the first node, the regional location, or the path distance between the first node and the second node, and the first nodes with a high probability are deleted first to improve the efficiency of determining the entrance and exit positions of the area.

[0081] In the case where only one first node in the topology map is the entrance and exit location of the area, when deleting a node in the topology map, after deleting a first node, the connectivity of the remaining nodes in the topology map after deletion can be analyzed to determine whether the point is the entrance and exit location of the area. If the first node is not, the first node can be restored in the topology map, and other first nodes can be deleted to determine whether the other first nodes are the entrance and exit locations of the area.

[0082] In the case where two or more nodes in the topology graph are the entrance and exit locations of the region, if the first node deleted is not the entrance and exit location of the region, then all the first nodes and second nodes in the remaining nodes can be connected, and the path distance remains unchanged; if the first node deleted is the entrance and exit location of the region, after the first node is deleted, there are still other first nodes that are the entrance and exit locations of the region, and all the first nodes and second nodes in the remaining nodes can also be connected through the nodes at other entrance and exit locations, but the path distance changes. Other first nodes that were originally connected to the second node through the deleted first node need to be connected to the second node through other nodes at the entrance and exit locations, so the path distance becomes longer. When all nodes that are entrance and exit locations are deleted, the remaining first nodes form one or more connected subgraphs, and the distance to the second node becomes infinite.

[0083] In practical applications, the number of nodes in the topological map may be large. In the process of deleting the first node to determine the entrance and exit locations of the area, in order to improve the analysis efficiency, this embodiment provides the following deletion method, which can quickly determine the entrance and exit locations of the area. As an example, in some examples, the method of deleting one or more first nodes includes: for each first node, obtaining the first path distance parameter from the first node to each second node, and obtaining the second path distance parameter from the first node to each second node after deleting the edge of the first node with its adjacent nodes; according to the difference between the second path distance parameter and the first path distance parameter of each of the first nodes in the first road network data, the first nodes are deleted in order from large to small.

[0084] In this embodiment, the nodes at the entrance and exit positions of the area will cause the path distance from the remaining first nodes to the second nodes to become larger. Therefore, the first nodes are deleted in descending order according to the difference between the second path distance parameter and the first path distance parameter. Each time a first node is deleted, it is determined whether a connected subgraph appears in the topological graph. If not, the next first node is deleted; until a connected subgraph appears in the topological graph, all the deleted first nodes are the nodes at the entrance and exit positions of the area.

[0085] Among them, the first path distance parameter is a parameter that characterizes the distance from the first node to each second node, which can be determined using the shortest path distance from the first node to each second node. For example, it can be the sum, the average of the sum, the product, the average of the products, etc.

[0086] The second path distance parameter is the path distance from the first node to each second node after a certain edge of the first node is deleted. It can be determined by the shortest path distance from the first node to each second node after a certain edge of the first node is deleted. For example, if the first node has multiple edges, the change in path distance after each edge is deleted can be calculated respectively, and the path distance with the largest change can be selected to determine the second path distance parameter. The second path distance parameter can also be calculated by sum, average value of sum, product, average value of product, etc.

[0087] As an example, the first path distance parameter includes: the average value of the sum of the shortest path distances from the first node to each second node. The method for obtaining the second path distance parameter includes: calculating the target parameter corresponding to any edge of the first node, the target parameter refers to the average value of the sum of the shortest path distances between the first node and each second node after the edge is deleted; comparing the target parameters corresponding to each edge, and taking the largest target parameter as the second path distance parameter. Through the above embodiments, efficient calculation can be achieved.

[0088] Next, the invention will be described again by the following examples.

[0089] First, the map is cut into non-overlapping regions using the existing trunk road network topology. The boundary of each region is the trunk road, and the region contains one or more AOIs, denoted as S.

[0090] For any S, a first network G inside S is extracted, where the first network G includes a plurality of first nodes.

[0091] Perform a breadth-first search on each node of G to obtain G'. G' is the aforementioned topological graph, including G; G'-G is the new node expanded by G, which is the aforementioned second node.

[0092] For each node i in G, calculate the shortest path from it to each second node of G'-G, and take the average value as d_i, which is the first path distance parameter. For example, assuming that the second nodes in the periphery of the area are B1 to B9, d_i = ((i→B1)+(i→B2)+……)÷9.

[0093] For each node i in G, delete the edges connected to it; calculate the shortest path from it to each second node of G-G', first calculate the average, and then take the maximum value. For example, a node i has three edges, e1, e2 and e3; delete only e1 and calculate d_i'; delete only e2 and calculate d_i' again; delete only e3 and calculate d_i'; among the three d_i', take the maximum value as the second path distance parameter.

[0094] Sort the node i in G according to d_i'-d_i and delete them one by one. If two large connected subgraphs appear in G after deleting m points, then the m points are considered to be the entry and exit points of the community, and the corresponding community road network is a connected subgraph in G.

[0095] Corresponding to the above-mentioned embodiment of the entrance and exit detection method, this specification also provides an embodiment of the entrance and exit detection device and the computer equipment used therein.

[0096] The embodiments of the device for detecting the entrance and exit of this specification can be applied to computer devices, such as servers or terminal devices. The device embodiments can be implemented by software, hardware, or a combination of software and hardware. Taking software implementation as an example, as a device in a logical sense, it is formed by the processor of the entrance and exit detection device reading the corresponding computer program instructions in the non-volatile memory into the memory and running it. From the hardware level, if Figure 3 The figure is a hardware structure diagram of the computer equipment where the device for detecting the entrance and exit of this manual is located, except Figure 3 In addition to the processor 310, memory 330, network interface 320, and non-volatile memory 340 shown, the computer device where the entrance and exit detection device 331 is located in the embodiment may also include other hardware according to the actual function of the computer device, which will not be described in detail.

[0097] like Figure 4 As shown, Figure 4 1 is a block diagram of a device for detecting an entrance and exit according to an exemplary embodiment of the present specification, the device comprising:

[0098] The trajectory acquisition module 41 is used to: acquire historical delivery trajectory data of the area of ​​the entrance and exit to be detected;

[0099] The road network acquisition module 42 is used to: after acquiring the first road network data of the passable roads in the area according to the historical delivery trajectory data, acquire the second road network data from the first road network data to the upper level road; wherein the first road network data includes a plurality of first nodes and the paths between the first nodes; the second road network data includes a plurality of second nodes and the paths between the second nodes to the first nodes;

[0100] The location determination module 43 is used to: after generating a topology map using the first road network data and the second road network data, determine the entrance and exit locations of the area according to the connectivity between nodes in the topology map after one or more of the first nodes are deleted.

[0101] In some examples, the location determination module is further configured to:

[0102] If, after deleting one or more first nodes, the remaining first nodes in the first road network data cannot be connected to any second node in the second road network data, determining the positions of the deleted one or more first nodes as the entrance and exit positions of the area; and / or,

[0103] The entrance and exit positions of the area are determined based on the change in distance of the path from the remaining first nodes in the first road network data to the second nodes in the second road network data before and after one or more of the first nodes are deleted in the topological graph.

[0104] In some examples, the remaining first nodes in the first road network data are unable to connect with any second node in the second road network data, including:

[0105] The remaining first nodes in the first road network data constitute one or more connected subgraphs of the topological graph, and all the second nodes in the second road network data constitute another connected subgraph of the topological graph.

[0106] In some examples, the location determination module is further configured to:

[0107] For each first node, obtain a first path distance parameter from the first node to each second node, and obtain a second path distance parameter from the first node to each second node after deleting an edge between the first node and its adjacent nodes;

[0108] According to the difference between the second path distance parameter and the first path distance parameter of each of the first nodes in the first road network data, the first nodes are deleted in descending order.

[0109] In some examples, the first path distance parameter includes: an average value of the sum of the shortest path distances from the first node to each second node; and / or,

[0110] The method for obtaining the second path distance parameter includes:

[0111] Calculating a target parameter corresponding to any edge of the first node, where the target parameter refers to an average value of the sum of the shortest path distances between the first node and each second node after the edge is deleted;

[0112] The target parameters corresponding to the edges are compared, and the maximum target parameter is used as the second path distance parameter.

[0113] In some examples, the trajectory acquisition module includes:

[0114] Acquire road network data, wherein the road network data includes data of a plurality of roads;

[0115] Determining a closed area surrounded by a plurality of roads according to the road network data;

[0116] The closed area is used to determine the area of ​​the entrance and exit to be detected.

[0117] Correspondingly, an embodiment of the present specification also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, an embodiment of the method for detecting entrances and exits described in the first aspect above is implemented.

[0118] The implementation process of the functions and effects of each module in the above-mentioned device for detecting entrances and exits is specifically described in the implementation process of the corresponding steps in the above-mentioned method for detecting entrances and exits, and will not be repeated here.

[0119] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this specification. A person of ordinary skill in the art can understand and implement it without paying creative labor.

[0120] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0121] The step division of the above methods is only for the purpose of clear description. When implemented, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this patent; adding insignificant modifications to the algorithm or process or introducing insignificant designs without changing the core design of the algorithm and process are all within the scope of protection of this patent.

[0122] The description of "specific examples" or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0123] Those skilled in the art will readily appreciate other embodiments of the specification after considering the specification and practicing the invention claimed herein. The specification is intended to cover any variations, uses or adaptations of the specification that follow the general principles of the specification and include common knowledge or customary techniques in the art that are not claimed in the specification. The specification and examples are to be considered exemplary only, and the true scope and spirit of the specification are indicated by the following claims.

[0124] It should be understood that the present description is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present description is limited only by the appended claims.

[0125] The above description is only a preferred embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this specification should be included in the scope of protection of this specification.

Claims

1. A method for detecting an entrance and exit, comprising: Obtain historical delivery trajectory data for the area of ​​the entrance and exit to be detected; After obtaining first road network data of drivable roads in the area according to the historical delivery trajectory data, obtaining second road network data from the first road network data to the upper-level roads; wherein the first road network data includes a plurality of first nodes and paths between the first nodes; the second road network data includes a plurality of second nodes and paths from the second nodes to the first nodes, and the second road network data refers to data of roads surrounding the area; After a topological map is generated using the first road network data and the second road network data, the entrance and exit locations of the area are determined based on connectivity between nodes in the topological map after one or more of the first nodes are deleted.

2. The method according to claim 1, wherein determining the entrance and exit locations of the area according to the connectivity between nodes in the topological graph after one or more of the first nodes are deleted comprises any of the following: If, after deleting one or more first nodes, the remaining first nodes in the first road network data cannot be connected to any second node in the second road network data, the positions of the deleted one or more first nodes are determined to be the entrance and exit positions of the area; or, The entrance and exit positions of the area are determined based on the change in distance of the path from the remaining first nodes in the first road network data to the second nodes in the second road network data before and after one or more of the first nodes are deleted in the topological graph.

3. The method according to claim 2, wherein the remaining first nodes in the first road network data cannot be connected to any second node in the second road network data, comprising: The remaining first nodes in the first road network data constitute one or more connected subgraphs of the topological graph, and all the second nodes in the second road network data constitute another connected subgraph of the topological graph.

4. According to the method of claim 1, the deletion method of the one or more first nodes comprises: For each first node, obtain a first path distance parameter from the first node to each second node, and obtain a second path distance parameter from the first node to each second node after deleting an edge between the first node and its adjacent nodes; According to the difference between the second path distance parameter and the first path distance parameter of each of the first nodes in the first road network data, the first nodes are deleted in descending order.

5. The method according to claim 4, wherein the first path distance parameter comprises: an average value of the sum of the shortest path distances from the first node to each second node; and / or, The method for obtaining the second path distance parameter includes: Calculating a target parameter corresponding to any edge of the first node, where the target parameter refers to an average value of the sum of the shortest path distances between the first node and each second node after the edge is deleted; The target parameters corresponding to the edges are compared, and the maximum target parameter is used as the second path distance parameter.

6. According to the method of claim 1, the method for obtaining the area of ​​the entrance and exit to be detected comprises: Acquire road network data, wherein the road network data includes data of a plurality of roads; Determining a closed area surrounded by a plurality of roads according to the road network data; The closed area is used to determine the area of ​​the entrance and exit to be detected.

7. A device for detecting an entrance and an exit, comprising: The trajectory acquisition module is used to: obtain the historical delivery trajectory data of the area of ​​the entrance and exit to be detected; A road network acquisition module, used to: after acquiring first road network data of passable roads in the area according to the historical delivery trajectory data, acquire second road network data from the first road network data to the upper level road; wherein the first road network data includes a plurality of first nodes and paths between each first node; the second road network data includes a plurality of second nodes and paths between each second node to each first node, and the second road network data refers to data of roads surrounding the area; The location determination module is used to: after generating a topology map using the first road network data and the second road network data, determine the entrance and exit locations of the area according to the connectivity between the nodes in the topology map after one or more of the first nodes are deleted.

8. The device according to claim 7, wherein the location determination module is further configured to: If, after deleting one or more first nodes, the remaining first nodes in the first road network data cannot be connected to any second node in the second road network data, determining the positions of the deleted one or more first nodes as the entrance and exit positions of the area; and / or, The entrance and exit positions of the area are determined based on the change in distance of the path from the remaining first nodes in the first road network data to the second nodes in the second road network data before and after one or more of the first nodes are deleted in the topological graph.

9. The device according to claim 8, wherein the remaining first nodes in the first road network data cannot be connected to any second node in the second road network data, comprising: The remaining first nodes in the first road network data constitute one or more connected subgraphs of the topological graph, and all the second nodes in the second road network data constitute another connected subgraph of the topological graph.

10. The device according to claim 7, wherein the location determination module is further configured to: For each first node, obtain a first path distance parameter from the first node to each second node, and obtain a second path distance parameter from the first node to each second node after deleting an edge between the first node and its adjacent nodes; According to the difference between the second path distance parameter and the first path distance parameter of each of the first nodes in the first road network data, the first nodes are deleted in descending order.

11. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method according to any one of claims 1 to 6 is implemented.

Images