Method, device, equipment and medium for excavating data relationship of interest point

Abstract

The application discloses a method and device for mining data relationship of a point of interest, an equipment and a medium, and relates to the technical field of geographic information. The method comprises the following steps: acquiring position information of a point of interest; determining a road loop matched with the point of interest based on the position information; the road loop is a closed loop surrounded by external roads in road network data, and there is no road chain in the internal part of the road loop to divide the road loop into two parts; the road chain is composed of one external road or connected by two or more external roads; the external road is a road located outside the point of interest; determining a search range of the point of interest based on the road loop; and mining data relationship of the point of interest based on the search range. The application has high efficiency and recall rate when performing data mining on the point of interest.

Description

Technical Field

[0001] This application relates to the field of geographic information technology, and in particular to a method, apparatus, device, and medium for mining data relationships of points of interest. Background Technology

[0002] Point of Interest (POI) is a term in Geographic Information Systems (GIS) that broadly refers to any geographic object that can be abstracted as a point. A POI can be a tourist attraction, a shopping mall, a parking lot, a school, etc. It can be used in map search technology. When building map data, it's necessary to mine the data relationships between POIs, including associating POIs with actual connections. For example, associating Peking University with its parking lot. When users use map navigation and search for Peking University as their destination, the system will recommend parking lots associated with Peking University.

[0003] When performing data relationship mining on a point of interest, a search scope is first determined. Within this scope, candidate points of interest are retrieved from numerous uploaded point of interest data. Then, from these candidate points of interest, further filtering is performed using methods such as text relevance judgment to identify candidate points of interest that are related to the point of interest. Finally, a relationship is established between these candidate points of interest and the point of interest.

[0004] The existing method for determining the search scope is to pre-define the search scope based on the developers' prior experience and historical statistical information, using the classification of points of interest (POIs) and keywords in their names. POIs are categorized into areas such as residential communities, scenic spots, and schools. When performing data mining on POIs, keywords in the POI names, such as "primary school," "university," "hospital," and "clinic," can be used to determine which category the POI belongs to, and the search scope corresponding to that category can be used as the search scope for that POI.

[0005] However, for a certain type of point of interest, the actual area occupied by each specific point of interest in that type of point of interest is not the same. The area occupied by some points of interest may be much smaller than the preset search range of that type of point of interest. In this case, searching based on the search range will retrieve a large number of useless candidate points of interest, and the filtering efficiency of these candidate points of interest will be low. On the other hand, the area occupied by some points of interest may be larger than the preset search range of that type of point of interest. In this case, searching based on the search range may miss some candidate points of interest.

[0006] Therefore, determining a reasonable search scope when mining data relationships for points of interest has become a technical problem that urgently needs to be solved in this field. Summary of the Invention

[0007] To address the aforementioned technical problems, embodiments of this specification propose a method, apparatus, device, medium, and product for mining data relationships of points of interest. This method can determine a reasonable search range, resulting in a small amount of data retrieved when searching for candidate points of interest within that range, and reducing the likelihood of missed detections, thereby improving the efficiency and recall rate of mining data relationships of points of interest.

[0008] This specification provides an embodiment of a method for mining data relationships of points of interest, including:

[0009] Obtain the location information of points of interest;

[0010] Based on the location information, a road loop matching the point of interest is determined; the road loop is a closed loop formed by external roads in the road network data, and there is no road chain inside that divides the road loop into two parts; the road chain is composed of one external road or is formed by connecting two or more external roads; the external road is a road located outside the point of interest.

[0011] Based on the road loop, the retrieval range of the points of interest is determined;

[0012] Based on the search scope, the data relationships of the points of interest are mined.

[0013] This specification provides an embodiment of a computer device, comprising:

[0014] The acquisition module is used to acquire the location information of points of interest;

[0015] The processing module is configured to determine, based on the location information, a road loop matching the point of interest; the road loop is a closed loop formed by external roads in the road network data, and there is no internal road chain that divides the road loop into two parts, wherein the road chain is composed of one external road or is formed by connecting two or more external roads; the external road is a road located outside the point of interest; and the module is configured to determine the retrieval range of the point of interest based on the road loop, and mine the data relationships of the point of interest based on the retrieval range.

[0016] This specification provides an embodiment of a computer device, including a processor and a memory communicatively connected to the processor, characterized in that the memory stores computer-executed instructions;

[0017] The processor executes the computer execution instructions to implement the steps of the method described above.

[0018] This specification provides an embodiment of a computer-readable storage medium having a computer program or instructions stored thereon, and / or a computer program product, wherein the computer program or instructions are executed by a processor to implement the steps of the methods described above.

[0019] The at least one technical solution adopted in the embodiments of this specification can achieve the following beneficial effects: When mining data relationships for points of interest, the search scope is based on road loops. Roads have natural spatial segmentation, and points of interest are often surrounded by surrounding roads. The area surrounded by the road loop is often the same as or slightly larger than the area actually occupied by the point of interest. Data retrieval based on this search scope can reduce the recall of useless data and improve judgment efficiency, judgment accuracy, and recall rate. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A flowchart illustrating a method for mining data relationships of points of interest, provided in an embodiment of this specification;

[0022] Figure 2 A partial schematic diagram of a road network provided for an embodiment of this specification;

[0023] Figure 3 This specification provides a schematic diagram of map information for data mining of the Q scenic area, as illustrated in an embodiment of the invention.

[0024] Figure 4 This specification provides a schematic diagram of map information for data mining of a parking lot XX, as illustrated in an embodiment of the present invention.

[0025] Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of this specification;

[0026] Figure 6 This is a schematic diagram of the structure of a computer device / equipment / system provided for an embodiment of this specification. Detailed Implementation

[0027] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0028] The embodiments described below are merely preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Various modifications and improvements made by those skilled in the art to the technical solutions of the present invention without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.

[0029] To address the shortcomings of existing technologies, this solution provides the following embodiments:

[0030] Figure 1 This is a flowchart illustrating a method for mining data relationships of points of interest, provided as an embodiment of this specification.

[0031] From a hardware perspective, the entity executing this process can be a device or server; from a program perspective, it can be an application running on that device or server. (See reference...) Figure 1 The process may include the following steps:

[0032] Step 101: Obtain the location information of the point of interest.

[0033] Points of interest (POIs) data are collected through methods such as data acquisition devices or manual measurement. After collection, the data is uploaded to a server or related equipment to form a POI dataset. This POI data can include location information, as well as descriptive information such as name, address, and phone number. Each POI occupies a specific physical area. Within this area, a point is selected as a reference point, and the spatial coordinates of this reference point represent the location information of the POI. For example, taking scenic area Q as an example, the spatial coordinates of a specific location within scenic area Q can represent its location information. When performing data mining on a particular POI, for ease of description, the POI to be mined is referred to as the first POI, and its location information is obtained from the POI dataset.

[0034] Step 103: Based on the location information, determine the road loop that matches the point of interest; the road loop is a closed loop formed by external roads in the road network data, and there is no road chain inside that divides the road loop into two parts. The road chain is composed of one external road or is formed by connecting two or more external roads; the external road is a road located outside the point of interest.

[0035] A road network refers to an interconnected and interwoven road system within a defined area. In data mining of points of interest across the entire country, this road network can refer to a national-level network. In data mining of points of interest within a province, it can refer to a provincial-level road network. Roads within a road network form closed loops. A closed loop here refers to a loop formed by external roads in the road network data, where no internal road chain divides the loop into two parts. A road chain consists of one road or two or more connected roads. It's important to note that a road chain here refers to a road chain that is connected to a closed loop. If a road chain is formed by interchanges located above or below a closed loop, but does not intersect with or form a connection with the closed loop, then this road chain does not constitute a division of the closed loop into two parts. Figure 2 This is a partial schematic diagram of a road network provided as an embodiment of this specification. (Refer to...) Figure 2 The road closed loop refers to the closed loop composed of roads akih, not the closed loop composed of roads abcdefhg, because in the closed loop abcdefhg, there is a road chain formed by connecting roads i and l that divides the closed loop abcdefhg into two parts.

[0036] Based on the location information of the point of interest (POI), it can be determined that the POI is located within a certain road loop, and then that road loop is identified as the road loop that matches the POI. This approach is suitable when the location information of the POI is highly accurate.

[0037] Step 105: Based on the road loop, determine the retrieval range of the points of interest.

[0038] After identifying the road loop that matches the first point of interest (POI), the area enclosed by the road loop can be directly used as the search scope. In the POI dataset, if the location information of the POIs is highly accurate, and the POI is actually located within the road loop, then the uploaded location information will also be within the search scope. This way, by directly using the area enclosed by the road loop as the search scope, other POIs related to the first POI can be searched without missing any POIs that should actually be associated with the first POI.

[0039] Step 107: Based on the search scope, mine the data relationships of the points of interest.

[0040] Within the retrieval scope, points of interest are searched from the point of interest dataset. The found points of interest are then compared with the primary point of interest using either a common relationship mining or a principal-subsidiary relationship mining. Common relationship mining addresses the issue that since point of interest data may originate from multiple sources, different sources may generate duplicate point of interest data for the same point. If this duplicate data is directly provided to the map engine, it will cause confusion during the search. Therefore, this duplicate data needs to be merged or cleaned. Principal-subsidiary relationship mining, for example, involves establishing a principal relationship between a residential community as the primary point of interest and the individual buildings within that community as sub-points of interest.

[0041] Figure 1 The method described above, when mining data relationships for points of interest, uses a search scope based on road loops. Roads have natural spatial segmentation; points of interest are often surrounded by surrounding roads. The area enclosed by these road loops is often the same as, or slightly larger than, the area actually occupied by the point of interest. Searching based on this scope reduces the recall of useless data and improves both efficiency and accuracy in decision-making.

[0042] For example, refer to Figure 3 When performing data mining on the point of interest Q, if the search scope is determined using current technology, the radius of the search scope would be several kilometers, given that Q is classified as a 5A-level scenic area. However, the actual area occupied by Q is a rectangular region with sides of approximately 1 kilometer. Setting the search radius to several kilometers would obviously retrieve many point of interest data located outside of Q, which are clearly unrelated to Q and need to be excluded. However, using a road loop matching Q as the search scope, where the area enclosed by this loop is the same as or only slightly larger than the actual area occupied by Q, results in a much smaller search scope with a radius of several kilometers. This leads to a smaller amount of irrelevant point of interest data and significantly improves the efficiency of further determining whether there is a connection between the point of interest and Q.

[0043] For example, some 5A-level scenic spots actually occupy a very large area, exceeding the search radius of several kilometers. When performing data mining on such a 5A-level scenic spot, using existing techniques for data retrieval might miss points of interest that should be associated with it, resulting in a low recall rate. However, if the area occupied by the 5A-level scenic spot is also surrounded by a road loop, using that road loop as the search scope will prevent missed searches, leading to a higher recall rate.

[0044] Optionally, determining the road loop matching the point of interest based on the location information specifically includes:

[0045] Based on the location information, a first region is constructed that includes the point of interest.

[0046] If the second region enclosed by the road loop overlaps with the first region, then the road loop is determined to be a road loop that matches the point of interest.

[0047] After obtaining the location information of the point of interest, a first region is constructed based on this location information, that is, based on the spatial coordinates of the reference point. This first region encloses the reference point. The shape of the first region can be a polygon or other shapes, without specific limitations. The size of the first region is also set appropriately as needed. A preferred approach is to set the first region as a square region centered on the reference point. The side length of the square region can be set to 10m. (Refer to...) Figure 2 Describe, Figure 2 This is a schematic diagram of a portion of the road network. Point M is the reference point for the first point of interest (POI), and the area enclosed by the dashed box represents the actual area occupied by the POI. A square is created centered on point M as the first region of the POI.

[0048] If the first region corresponding to a point of interest overlaps with the second region enclosed by a road loop, then the point of interest matches the road loop. The determination of whether the first and second regions overlap can be made using existing methods based on reference points and related geometric algorithms.

[0049] This method for determining road loops that match points of interest (POIs) is applicable not only to cases where the location information of the POI and / or road loops is highly accurate, but also to cases where the location information is less accurate. For example, suppose a POI is located inside a road loop, but near its edge. In this case, the POI should actually match the road loop. However, if the location information of the POI is not highly accurate during location data acquisition, the POI may drift during localization, moving outside the road loop. This would cause the POI to be considered outside the road loop and thus not be matched, resulting in missed road loops. However, this method first constructs a first region based on the POI, and then matches this first region with the road loop. Even if the POI's location information drifts, the constructed first region will still overlap with the road loop, ensuring that the POI is still matched with the road loop and no road loop is missed.

[0050] A spatial index can be built for road loops based on data structures such as R-trees or quadtrees. When determining road loops that match the first region, a query matching of road loops can be performed based on the spatial index.

[0051] Optionally, the method for generating the road closed loop specifically includes:

[0052] Retrieve external roads from road network data;

[0053] Starting from the first connection point of the external road and taking the external road as the starting road, among the external roads connected to the second connection point of the external road, the external road with the smallest angle with the external road is selected as the next road of the external road.

[0054] Using the first connection point of the next road as a new starting point, and using the next road as a new starting road, continue to select the next road until the road loop is formed; the first connection point of the next road and the second connection point of the starting road are the same connection point.

[0055] Since road network data may include internal and external roads, the terms "internal road" and "external road" are relative to a point of interest (POI). Roads located within a POI are called internal roads, and roads located outside a POI are called external roads. For example, within scenic area Q, there are roads for people or vehicles; these are internal roads. Roads surrounding scenic area Q are external roads.

[0056] In a road network, the points where external roads intersect are called connection points, which are the endpoints of the external roads. Each external road has two endpoints, or two connection points. The specific method for forming a road loop through the road network is as follows: starting from a connection point, and using the external roads connected to that connection point as the starting roads, begin searching for a road loop. Then, perform the same operation on other connection points until all external roads in the road network form a road loop, or all external roads have been traversed. The process of generating a road loop is described below.

[0057] A connection point connects to several external roads. One of these external roads is chosen as the starting road; this connection point is called the first connection point of the starting road. The other connection point of the starting road is called the second connection point. From the external roads connected to the second connection point of the starting road, the next road is selected. The road with the smallest angle to the starting road is chosen as the next road. Then, the first connection point of the next road becomes the new starting point, and the first connection point of the next road becomes the second connection point of the starting road. This process continues until a closed loop is formed. (Refer to...) Figure 2Starting from connection point A, with external road l as the initial road, and connection point B as the second connection point of the initial road, the external road connected to connection point B is denoted as ikj, and the external road with the smallest angle to external road l is external road j. It should be noted that the angle here is directional. Using the second connection point as a vertex, the angle by which the initial road is rotated counterclockwise (or clockwise) to the next road is the angle between the next road and the initial road. Using connection point B as a vertex, external road i is rotated counterclockwise; obviously, external road i coincides with external road j first, so external road j is selected as the next road. Then, using external road j as the new initial road, the search for the next road continues. At this point, connection point B is called the first connection point of external road j, and connection point C is the second connection point of external road j. Using connection point C as a vertex, external road j is rotated counterclockwise; it will first coincide with external road e, so external road e is the next road. The search for the next road continues until a closed road loop ljed is formed. Similarly, starting from connection point A, and taking the external road drc as the starting road, we can find the closed loop of the road.

[0058] Optionally, acquiring external roads from the road network data specifically includes:

[0059] Obtain road network data;

[0060] Based on the road attribute information, internal roads in the road network data are filtered out to obtain the first road;

[0061] Filter out roads with a connectivity of less than two from the first road to obtain the external roads.

[0062] Since road network data includes not only external roads but also other roads such as internal roads, it's necessary to extract the external roads to generate road loops. One method is to exclude internal roads from the road network data, leaving only the external roads. The road network data contains road attribute information describing whether a road is internal or external. After filtering out internal roads, roads with a connectivity of less than two are then filtered out from the remaining roads. Roads with a connectivity of less than two are dead-end roads, meaning they have only one connection point with another road and the other endpoint is not connected to any other road. For example... Figure 2 In the diagram, road q represents a path with a connectivity of less than two. Since paths with a connectivity of less than two cannot form closed loops, they are excluded. This reduces the traversal of these paths when generating closed loops, thus improving the efficiency of closed loop generation.

[0063] It should be noted that the external roads here can be further limited to those that are accessible to vehicles. Some external roads, although located outside the point of interest, prohibit vehicles and only allow pedestrians; these external roads also need to be filtered out based on their attribute information.

[0064] Optionally, the method further includes:

[0065] Filter out road loops whose area of ​​the second region enclosed by the road loop is less than the first threshold to obtain the first road loop;

[0066] By filtering out road loops in the first road loop that have no topological connectivity with other road loops, a second road loop is obtained.

[0067] When determining the road loop that matches the point of interest, it can be selected from the second road loop. Then, based on the second road loop that matches the point of interest, the search range of the point of interest is determined.

[0068] In road network data, road attribute information may not accurately label every road. Roads within some points of interest (POIs) may not be marked as internal roads, leading to them being treated as external roads and forming road loops. These loops will have relatively small areas, or they may be isolated loops. When the area of ​​a road loop is less than a first threshold, it indicates that the loop does not actually completely enclose a POI, but is formed by internal roads within the POI, and can be filtered out. The first threshold needs to be limited according to the actual situation. For example, the first threshold can be set to 100 square meters.

[0069] An isolated loop refers to a closed loop that has no topological connectivity with other road closed loops. For example, Figure 2 The road loop mnop in the context of interest is not connected to other road loops and is called an island loop. This type of road loop is formed by roads within the points of interest that have not been accurately filtered out, and these road loops need to be filtered out.

[0070] After filtering out these closed-loop roads, new roads with a connectivity of less than two may be formed, and these roads can be further filtered out.

[0071] Optionally, determining the retrieval range of the point of interest based on the road loop closure specifically includes:

[0072] The second region enclosed by the road loop is expanded according to the first preset condition to obtain a third region, which is the search range; the first preset condition is set based on the collection accuracy of the location information of the point of interest.

[0073] When determining the search scope, to ensure compatibility with information uploaded by data acquisition devices with varying acquisition precision and to prevent overlooking points of interest during retrieval, the second region can be expanded according to a first preset condition to obtain a third region, which will then be used as the search scope. For example, a point of interest located inside a road loop but near its edge may experience location drift due to inaccurate location information during data acquisition. For instance, the point of interest might actually be inside the road loop, but the acquired location information might be inaccurate, leading to an incorrect judgment that the point of interest is outside the road loop. This would result in missed detections during data retrieval. Assuming a location information acquisition precision of 50m, each road forming the road loop can be extended by 50m, thus expanding the search scope. Then, the third region enclosed by the expanded road loop can be used as the search scope, reducing the possibility of missed detections.

[0074] Optionally, before determining the retrieval range of the point of interest based on the road loop closure, the method further includes:

[0075] Determine whether the point of interest is an underground location to obtain a first determination result;

[0076] The determination of the retrieval range of the point of interest based on the road loop specifically includes:

[0077] If the first determination result indicates that the point of interest is an underground location, then a first preset area is constructed based on the location information and the category of the point of interest;

[0078] The area formed by merging the third region and the first preset region is determined as the search range.

[0079] When a point of interest (POI) is an underground location, it may cross roads, such as an underground parking lot where part is on the right side of the road and part is on the left. In this case, using the road loop as the search scope may result in a search scope smaller than the actual area occupied by the POI, leading to missed detections. To address this, a first preset region can be used to determine the search scope. The first preset region can be a range determined using existing technologies based on the classification of POIs. The search scope is determined by merging the first preset region and a third region. This reduces the possibility of missing POIs.

[0080] Optionally, when there are two or more matching road loops for the point of interest, determining the search range for the point of interest based on the road loops specifically includes:

[0081] Each of the second regions enclosed by the road loops is expanded according to a first preset condition to obtain several third regions; the first preset condition is set based on the acquisition accuracy of the location information of the points of interest.

[0082] The area formed by merging the aforementioned third regions is defined as the search range.

[0083] For a point of interest located at the edge of a road loop, the first region, pre-defined based on location information, may overlap with a second region surrounded by multiple road loops. Alternatively, the point of interest may be located within multiple road loops simultaneously. In both cases, the point of interest will have more than one matching road loop. Therefore, the second region surrounded by each road loop needs to be expanded according to the first pre-defined condition to obtain a third region. The region formed by merging these third regions is then determined as the search range.

[0084] Optionally, mining the data relationships of the points of interest based on the search scope specifically includes:

[0085] Retrieve candidate points of interest within the search scope;

[0086] Candidate interest points that are irrelevant to the stated interest points are filtered out based on text relevance to obtain the first candidate interest point;

[0087] If the number of the first candidate points of interest is not less than the preset number of candidates, then the location information of the first candidate points of interest is obtained;

[0088] Based on the location information of the first candidate point of interest and the location information of the point of interest, the first candidate point of interest located in the same road loop as the point of interest is selected as the point of interest to be associated.

[0089] Establish the association relationship between the points of interest to be associated and the points of interest.

[0090] The preset number of candidates can be set to two. (See reference...) Figure 4 In the Figure 4 When performing data mining on a parking lot, assuming the parking lot is named "XX University Parking Lot," and the search scope involves two closed road loops (left and right), after filtering out candidate points of interest (POIs) based on text relevance, two candidate POIs remain, named "XX University West Campus" and "XX University East Campus." One more POI needs to be eliminated, and the remaining candidate POI needs to be associated with the "XX University Parking Lot." In existing technologies, the elimination process involves calculating the distance between the candidate POI and the first POI based on their location information, and selecting the closer candidate POI as the one to be associated. Figure 4It is known that the parking lot is 279 meters away from the West Campus of XX University, which is closer than 289 meters. Current technology would establish a connection between the parking lot and the West Campus. However, it is clearly impractical to walk to the West Campus after parking in this parking lot, requiring crossing the North Third Ring Road. This method, based on the location information of candidate points of interest, determines which candidate point of interest is located within the same road loop as the first point of interest. The East Campus of XX University and the parking lot are located within the same road loop. Establishing a connection between the East Campus and the parking lot is more accurate.

[0091] For example, using existing technologies to define the search scope may retrieve a large number of useless points of interest, which often increases the difficulty of relationship mining. For instance, when mining the data relationship "XX Community - East Gate 1", many similar data entries like "XX Community Phase 1", "XX Community Phase 2", "XX Community East Zone", and "XX Community West Zone" are retrieved. Even using the spatial relative positions of "East Gate 1" and "XX Community" candidate data, effective differentiation is often impossible. In this case, using road loop closure can easily filter out some useless data such as "XX Community Phase X" and "XX Community X Zone", thereby reducing the difficulty of optimizing point of interest relationships and improving mining accuracy.

[0092] Optionally, before determining the retrieval range of the point of interest based on the road loop closure, the method further includes:

[0093] Determine whether there exists an interest surface to describe the actual area occupied by the point of interest, and obtain a second determination result;

[0094] If the second judgment result indicates the existence of the interest surface, the interest surface is expanded according to the second preset condition to obtain the search range; the second preset condition is set based on the acquisition accuracy of the location information of the interest point.

[0095] For certain points of interest (POIs), the POI data includes interest surface data. The interest surface describes the actual area occupied by the POI. For example, for some famous scenic spots, the actual area has been precisely measured and has detailed and accurate records. When performing data relationship mining, searches can be conducted based on this actual area, resulting in a more precise retrieval range. Similarly, considering the accuracy of candidate POI collection, for example, when mining data on public toilets within a famous scenic spot, if a newly built public toilet's information is collected and uploaded, the accuracy of its location information may not be precise enough. Therefore, the interest surface for that famous scenic spot needs to be appropriately expanded so that the public toilet can be retrieved during the POI data search, preventing omissions.

[0096] Based on the same idea, embodiments of this specification also provide apparatus corresponding to the above methods.

[0097] Figure 5 This is a schematic diagram of the structure of a computer device provided as an embodiment of this specification. Figure 5 As shown, it includes:

[0098] Module 501 is used to acquire the location information of points of interest;

[0099] Processing module 502 is configured to determine, based on the location information, a road loop matching the point of interest; the road loop is a closed loop formed by external roads in the road network data, and there is no internal road chain that divides the road loop into two parts, wherein the road chain is composed of one external road or is formed by connecting two or more external roads; the external road is a road located outside the point of interest; and is configured to determine the retrieval range of the point of interest based on the road loop, and mine the data relationship of the point of interest based on the retrieval range.

[0100] Optionally, the device further includes:

[0101] The first construction module is used to construct a first region that includes the point of interest based on the location information;

[0102] The first matching module is used to determine the road loop as a road loop that matches the point of interest if the second region enclosed by the road loop overlaps with the first region.

[0103] Optionally, the device further includes:

[0104] The first acquisition module is used to acquire external roads from the road network data;

[0105] The first generation module is used to select the external road with the smallest angle to the external road from among the external roads connected to the second connection point of the external road, starting from the first connection point of the external road and taking the external road as the starting road.

[0106] Using the first connection point of the next road as a new starting point, and using the next road as a new starting road, continue to select the next road until the road loop is formed; the first connection point of the next road and the second connection point of the starting road are the same connection point.

[0107] Optionally, the device further includes:

[0108] The second acquisition module is used to acquire road network data;

[0109] The first filtering module is used to filter out internal roads in the road network data based on the road attribute information to obtain the first road;

[0110] The second filtering module is used to filter out roads with a connectivity of less than two in the first road to obtain the external road.

[0111] Optionally, the device further includes:

[0112] The third filtering module is used to filter out road loops in which the area of ​​the second region enclosed by the road loop is smaller than the first threshold, so as to obtain the first road loop.

[0113] The fourth filtering module is used to filter out road loops in the first road loop that have no topological connectivity with other road loops, so as to obtain the second road loop.

[0114] Optionally, the device further includes:

[0115] The first determining module is used to expand the second area surrounded by the road loop according to the first preset conditions to obtain a third area, wherein the third area is the retrieval range; the first preset conditions are set based on the acquisition accuracy of the location information of the points of interest.

[0116] Optionally, the device further includes:

[0117] The first judgment module is used to determine whether the point of interest is an underground location and obtain a first judgment result;

[0118] The second construction module is used to construct a first preset area based on the location information and the category of the point of interest if the first judgment result indicates that the point of interest is an underground place;

[0119] The second determining module is used to determine the area after merging the third region and the first preset region as the search range.

[0120] Optionally, the device further includes:

[0121] The third determining module is used to expand the second region surrounded by each road loop according to a first preset condition when there are two or more matching road loops for the point of interest, to obtain several third regions; the first preset condition is set based on the acquisition accuracy of the location information of the point of interest; the region formed by merging the several third regions is determined as the search range.

[0122] Optionally, the device further includes:

[0123] The first mining module is used to retrieve candidate points of interest within the retrieval range; filter out candidate points of interest that are irrelevant to the points of interest based on text relevance to obtain a first candidate point of interest; if the number of the first candidate points of interest is not less than two, then obtain the location information of the first candidate points of interest; based on the location information of the first candidate points of interest and the location information of the points of interest, select the first candidate point of interest located in the same road loop as the points of interest as the points of interest to be associated; and establish the association relationship between the points of interest to be associated and the points of interest.

[0124] Optionally, the device further includes:

[0125] The second judgment module is used to determine whether there is an interest surface that describes the actual area occupied by the point of interest, and to obtain a second judgment result.

[0126] The fourth determining module is used to expand the interest surface according to the second preset condition to obtain the search range if the second determination result indicates that the interest surface exists; the second preset condition is set based on the acquisition accuracy of the location information of the interest point.

[0127] Based on the same idea, embodiments of this specification also provide computer devices / equipment / systems corresponding to the above methods.

[0128] Figure 6 This is a schematic diagram of the structure of a computer device provided as an embodiment of this specification. Figure 6 As shown, the computer device 600 may include a processor 610 and a memory 630 communicatively connected to the processor 610. The memory 630 stores computer execution instructions 620, which the processor executes to implement the steps of any of the methods described above.

[0129] Based on the same idea, embodiments of this specification also provide a computer-readable storage medium corresponding to the above methods, which stores a computer program or instructions thereon, and / or a computer program product, the computer product including the computer program or instructions, which can be executed by a processor to implement the steps of any of the methods described above.

[0130] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on its differences from other embodiments. In particular, for... Figure 6 As the computer device shown is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0131] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program a digital system themselves to "integrate" it onto a PLD, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Moreover, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compiler used when writing program development code. The original code before compilation must also be written in a specific programming language, which is called a Hardware Description Language (HDL). There is not just one HDL, but many, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also understand that by simply performing some logic programming on the method flow using the aforementioned hardware description languages ​​and programming it into an integrated circuit, the hardware circuit that implements the logic method flow can be easily obtained.

[0132] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, ASICs, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means that can be included within it to implement various functions can also be considered as structures within the hardware component. Alternatively, the means that can be used to implement various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0133] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0134] For ease of description, the above devices are described separately by function as various units. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware.

[0135] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (which may include, but are not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0136] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, produce a machine that can be used to implement the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0137] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture that may include instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0138] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that can be used to implement a process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0139] In a typical configuration, a computing device may include one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0140] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0141] Computer-readable media can include both permanent and non-permanent, removable and non-removable media, and information storage can be achieved by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media can include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital character versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media cannot include transient computer-readable media, such as modulated data signals and carrier waves.

[0142] It should also be noted that the terms "may include," "comprise," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that may include a list of elements may include not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "may include a…" does not exclude the presence of other identical elements in the process, method, article, or apparatus that may include said element.

[0143] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (which may include, but are not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0144] This application can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules can include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0145] The above description is merely an embodiment of this application and should not be construed as limiting the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for mining data relationships of points of interest, characterized in that, include: Obtain the location information of a single point of interest; If the location information of a single point of interest is highly accurate, and the point of interest is within any road loop, then the road loop is a road loop that matches the single point of interest. When the location information of a single point of interest (POI) is inaccurate, the POI may drift during localization, moving outside the road loop. Based on the location information, a first region is constructed that includes the POI. If the second region enclosed by the road loop overlaps with the first region, the road loop is determined to be the one matching the POI. The road loop is a closed loop formed by external roads in the road network data, without any internal road chains that divide the road loop into two parts. The road chain consists of one external road or is formed by connecting two or more external roads. The external roads are roads located outside the POI. Based on the matching road loop, the retrieval range of the individual point of interest is determined; Based on the search scope, the data relationships of the individual points of interest are mined.

2. The method as described in claim 1, characterized in that, The method for generating the road closed loop specifically includes: Retrieve external roads from road network data; Taking the first connection point of the external road as the starting point and the external road as the starting road, among the external roads connected to the second connection point of the external road, the external road with the smallest angle with the starting road is selected as the next external road; Using the first connection point of the next road as a new starting point, and using the next road as a new starting road, continue to select the next road until the road loop is formed; the first connection point of the next road and the second connection point of the starting road are the same connection point.

3. The method as described in claim 2, characterized in that, The acquisition of external roads in the road network data specifically includes: Obtain road network data; Based on the road attribute information, internal roads in the road network data are filtered out to obtain the first road; Filter out roads with a connectivity of less than two from the first road to obtain the external roads.

4. The method as described in claim 2, characterized in that, The method further includes: Filter out road loops whose area of ​​the second region enclosed by the road loop is less than the first threshold to obtain the first road loop; By filtering out road loops in the first road loop that have no topological connectivity with other road loops, a second road loop is obtained.

5. The method as described in claim 1, characterized in that, The step of determining the retrieval range of the points of interest based on the matched road loop specifically includes: The second region surrounded by the matching road loop is expanded according to the first preset condition to obtain a third region, which is the search range; the first preset condition is set based on the acquisition accuracy of the location information of the point of interest.

6. The method as described in claim 5, characterized in that, Before determining the retrieval range of the point of interest based on the matched road loop, the method further includes: Determine whether the point of interest is an underground location to obtain a first determination result; The process of determining the retrieval range of the points of interest based on the matched road loop specifically includes: If the first determination result indicates that the point of interest is an underground location, then a first preset area is constructed based on the location information and the category of the point of interest; The area formed by merging the third region and the first preset region is determined as the search range.

7. The method as described in claim 1, characterized in that, When there are two or more matching road loops for a point of interest, the search range for the point of interest is determined based on the matching road loops, specifically including: Each of the matching road loops is expanded into several third regions according to a first preset condition; the first preset condition is set based on the acquisition accuracy of the location information of the points of interest. The area formed by merging the aforementioned third regions is defined as the search range.

8. The method according to any one of claims 1-7, characterized in that, The step of mining the data relationships of the points of interest based on the search scope specifically includes: Retrieve candidate points of interest within the search scope; Candidate interest points that are irrelevant to the stated interest points are filtered out based on text relevance to obtain the first candidate interest point; If the number of the first candidate points of interest is not less than the preset number of candidates, then the location information of the first candidate points of interest is obtained; Based on the location information of the first candidate point of interest and the location information of the point of interest, the first candidate point of interest located in the same road loop as the point of interest is selected as the point of interest to be associated. Establish the association relationship between the points of interest to be associated and the points of interest.

9. The method as described in claim 1, characterized in that, Before determining the retrieval range of the point of interest based on the matched road loop, the method further includes: Determine whether there exists an interest surface to describe the actual area occupied by the point of interest, and obtain a second determination result; If the second judgment result indicates the existence of the interest surface, the interest surface is expanded according to the second preset condition to obtain the search range; the second preset condition is set based on the acquisition accuracy of the location information of the interest point.

10. A computer device, characterized in that, include: The acquisition module is used to acquire the location information of a single point of interest; The processing module is configured to, when the location information of a single point of interest is highly accurate, determine if the point of interest is within any road closed loop, and then define the road closed loop as a road closed loop that matches the single point of interest. When the location information of a single point of interest (POI) is inaccurate, the POI may drift during localization, moving outside the road loop. Based on the location information, a first region containing the POI is constructed. If the second region enclosed by the road loop overlaps with the first region, the road loop is determined to be the one matching the POI. The road loop is a closed loop formed by external roads in the road network data, without any internal road chains that divide the road loop into two parts. The road chain consists of one external road or is formed by connecting two or more external roads. The external roads are roads located outside the POI. The system also includes methods for determining the retrieval range of the POI based on the matching road loop and mining the data relationships of the POI based on the retrieval range.

11. A computer device, comprising a processor and a memory communicatively connected to said processor, characterized in that, The memory stores computer-executed instructions; The processor executes the computer execution instructions to implement the steps of the method as described in any one of claims 1 to 9.

12. A computer-readable storage medium having computer instructions stored thereon; and / or a computer program product comprising computer instructions, characterized in that, The computer instructions can be executed by a processor to implement the method for mining data relationships of points of interest as described in any one of claims 1 to 9.

Images