Information processing method and device, equipment and storage medium

Abstract

The invention provides an information processing method and device, equipment and a storage medium, and relates to the technical field of computers, in particular to the technical fields of artificial intelligence, intelligent driving, intelligent transportation, high-precision maps and the like. According to the specific implementation scheme, the method comprises the steps of obtaining a POI data sub-packet of a first point of interest (POI); obtaining a name, an address and a coordinate of the first POI from a POI data sub-packet of the first POI; acquiring peripheral position information of the first POI according to the coordinates; and generating a cue word based on the name, the address and the peripheral position information of the first POI.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to technical fields such as artificial intelligence, intelligent driving, intelligent transportation, and high-precision maps. Background Art

[0002] Currently, navigation maps have become an indispensable auxiliary tool for people to travel, and their core value lies in providing people with accurate and rich destination information. In navigation maps, Points of Interest (POI) are the basic units for expressing various destinations, covering a wide range of entities such as hotels, restaurants, shopping malls, etc., providing great convenience for users' travel.

[0003] Regional POI refers to data with a certain range and multiple sub-point POIs within the range. The accurate mining and effective production of regional POIs are crucial to improving the service quality of navigation maps. Summary of the invention

[0004] The present disclosure provides an information processing method, apparatus, device and storage medium.

[0005] According to one aspect of the present disclosure, there is provided an information processing method, comprising:

[0006] Obtaining a first point of interest (POI) data sub-package;

[0007] Obtaining the name, address and coordinates of the first POI from the POI data sub-packet of the first POI;

[0008] According to the coordinates, obtain the surrounding location information of the first POI;

[0009] A prompt word is generated based on the name, address and surrounding location information of the first POI.

[0010] According to another aspect of the present disclosure, there is provided an information processing device, comprising:

[0011] An acquisition module is used to acquire a POI data sub-package of a first POI; acquire the name, address and coordinates of the first POI from the POI data sub-package of the first POI; and acquire the surrounding location information of the first POI according to the coordinates;

[0012] The generating module is used to generate a prompt word based on the name, address and surrounding location information of the first POI.

[0013] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute any method in the embodiments of the present disclosure.

[0017] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any method according to the embodiments of the present disclosure.

[0018] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, which implements any method according to the embodiments of the present disclosure when executed by a processor.

[0019] The present invention obtains the name, address and surrounding location information of the first POI to generate prompt words, and uses the prompt words and a pre-trained large language model to determine multiple regional POIs in the map area, thereby realizing automatic recognition and production of regional POIs, and providing strong support for the production and updating of navigation maps.

[0020] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0022] Figure 1 is a flowchart of an implementation of an information processing method 100 according to an embodiment of the present disclosure;

[0023] Figure 2 is a schematic diagram of determining parent point information of a first POI according to an embodiment of the present disclosure;

[0024] Figure 3 A flowchart of an implementation method for determining a parent point area in a preset area based on information of multiple parent points in the preset area;

[0025] Figure 4 is a schematic diagram of determining a parent point area according to an embodiment of the present disclosure;

[0026] Figure 5 This is a flow chart of an implementation method for verifying POI;

[0027] Figure 6is a schematic diagram of determining a similar parent point area list (i.e., similar POI List) according to an embodiment of the present disclosure;

[0028] Figure 7 is a schematic diagram of verifying and adjusting the position of a POI to be verified according to an embodiment of the present disclosure;

[0029] Figure 8 is a schematic structural diagram of an information processing device 800 according to an embodiment of the present disclosure;

[0030] Fig. 9 is a schematic structural diagram of an information processing device 900 according to an embodiment of the present disclosure;

[0031] Fig.10 A schematic block diagram of an example electronic device 1000 is shown that can be used to implement embodiments of the present disclosure. DETAILED DESCRIPTION

[0032] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0033] The “and / or” in the embodiments of the present disclosure indicates that three relationships may exist. For example, A and / or B may indicate the following three situations: A exists alone, A and B exist at the same time, and B exists alone. The term “at least one” herein indicates any combination of at least two of any one or more of a plurality of types. For example, at least one of A, B, and C may indicate any one or more elements selected from the set consisting of A, B, and C. The terms “first” and “second” herein refer to and distinguish between multiple similar technical terms, and do not mean to limit the order or to limit the meaning to only two. For example, the first feature and the second feature refer to two types / two features. The first feature may be one or more, and the second feature may also be one or more.

[0034] At present, navigation maps have become an indispensable auxiliary tool for people to travel, and their core value lies in providing people with accurate and rich destination information. In navigation maps, POI, as the basic unit for expressing various destinations, covers a wide range of entities, such as hotels, restaurants, shopping malls, etc., providing great convenience for users' travel.

[0035] Regional POI refers to data with a certain range and multiple sub-point POIs within the range, such as large scenic spots (including multiple ticket offices, parking lots, sub-attractions), residential areas (including multiple residential buildings, entrances and exits), etc. The accurate mining and effective production of these regional POIs are crucial to improving the service quality of navigation maps.

[0036] However, in the current process of making and updating navigation maps, the mining and production of regional POIs face many challenges. On the one hand, due to the complexity and diversity of regional POIs, traditional data collection and processing methods often have difficulty in accurately identifying their boundaries; on the other hand, with the rapid development of cities, regional POIs change frequently, which puts higher requirements on the real-time and accuracy of data.

[0037] Based on the above problems, the present invention aims to solve the problem of mining and producing regional POIs. Through innovative technical means, the automatic identification and production of regional POIs are realized, providing strong support for the production and update of navigation maps.

[0038] Furthermore, the disclosed embodiments can also implement verification and error correction of POI coordinates based on regional POIs. POI coordinates are one of the most critical attributes of POI. If the POI coordinates are wrong, it will directly cause the user to be unable to reach the destination; especially indoor POIs, which are difficult to collect due to their strong concealment, and the collected coordinates are affected by factors such as indoor positioning, so the accuracy of the coordinates is difficult to guarantee. This solution uses the parent point information described in the address of the indoor POI to discover the situation of POI coordinate errors, and automatically corrects the POI coordinates to the range of the building where it is located. The problem of indoor POI coordinate errors can be solved on a large scale.

[0039] The disclosed embodiment provides an information processing method, which can be applied to a navigation map generating device or server, and the device or server may include an electronic device or server with data processing and computing functions.

[0040] Figure 1 is a flowchart of an implementation of an information processing method 100 according to an embodiment of the present disclosure, comprising:

[0041] S110, obtaining a POI data sub-package of a first POI;

[0042] S120, acquiring the name, address and coordinates of the first POI from the POI data sub-packet of the first POI;

[0043] S130, acquiring peripheral location information of the first POI according to the coordinates;

[0044] S140: Generate a prompt word based on the name, address and surrounding location information of the first POI.

[0045] The prompt words generated by the above method can be input into a pre-trained large language model (LLM), which outputs the parent point name and address of the first POI. Based on the prompt words generated by multiple first POIs in a region, multiple parent point information can be obtained, thereby realizing the automatic identification and production of regional POIs, providing strong support for the production and update of navigation maps.

[0046] In the disclosed embodiments, the "first POI" may include POIs included in map information such as navigation maps, high-precision maps, and intelligent driving high-precision maps. The "first" in the name is only used to distinguish it from other POIs in subsequent content, and is not used to limit information such as the priority or order of the POI. In some examples, the database of map elements of the intelligent driving high-precision map includes multiple packages (packet, abbreviated as Pkg). A package is equivalent to a container for organizing and managing classes and interfaces, and may contain multiple subpackages (subpackage, abbreviated as SubPkg) and feature classes. Among them, a subpackage is a container, which is a package nested in a package, and may contain multiple subpackages and feature classes; a feature class is an abstract representation of a group of objects with the same properties, methods, and relationships.

[0047] The core of the high-precision map model includes multiple packages such as the road static data package. The road static data package contains multiple sub-packages, including the POI data sub-package.

[0048] In some implementations, the POI data subpackage includes multiple feature classes, each feature class having corresponding attributes.

[0049] For example, the multiple feature classes of the POI data subpackage include at least one of a shopping mall, a restaurant, a square, a bank, a hotel, a hospital, an airport, a railway station, a subway station, a bus station, a toll station, a gas station, a charging or battery replacement station, an emergency telephone booth, a parking lot, a service area, a tourist attraction, and a public rest area;

[0050] The attributes corresponding to each feature class include at least one of location and geometry.

[0051] In some examples, the map may be divided into a certain grid to obtain multiple areas, each area has a range of 1km*1km, and each area includes multiple first POIs. In the following content, each area obtained by division is referred to as a preset area.

[0052] In some embodiments, for any preset area, each first POI in the preset area is Figure 1 The method shown performs information processing to obtain prompt words corresponding to each first POI;

[0053] For each first POI, perform the following operations:

[0054] Inputting the prompt word corresponding to the first POI into a pre-trained large language model;

[0055] Based on the output result of the pre-trained large language model and the coordinates of the first POI, the parent point information of the first POI is determined, where the parent point information of the first POI includes the parent point name and parent point coordinates of the first POI.

[0056] Figure 2 FIG. 1 is a schematic diagram of determining the parent point information of the first POI according to an embodiment of the present disclosure. Figure 2 As shown, it includes the following stages:

[0057] (1) Phase I:

[0058] Obtain POI information of the first POI, the POI information including the name, address and coordinates of the first POI; Figure 2 In the example, the name of the first POI is obtained as "Home Appliances After-Sales Service Center", the address of the first POI is "No. 1, ZZ Road, YY District, XX City", and the coordinates of the first POI include "1xx.45463 (longitude), xx.97683 (latitude)".

[0059] According to the coordinates of the first POI, the surrounding location information of the first POI is searched in the map; for example, a circular area with the address of the first POI as the center and a preset length as the radius is used as the surrounding range of the first POI; the area divisions within the surrounding range, the surrounding road names and / or the surrounding landmarks (such as buildings, subway stations, etc.) are used as the surrounding location information of the first POI. Figure 2 In the example shown, the surrounding location information of the first POI obtained includes the area, surrounding roads and surrounding landmarks.

[0060] (2) Second stage:

[0061] A prompt is generated based on the name, address and surrounding location information of the first POI acquired in the first stage.

[0062] like Figure 2 As shown, in Figure 2 In the example shown, the generated prompt content is as follows:

[0063] “

[0064] According to the POI's own information and surrounding conditions, extract the name and address of the parent point:

[0065] Name: Home appliance after-sales repair center;

[0066] Address: 7th Floor, AA Building, No. 1 ZZ Road, YY District, XX City;

[0067] Region: XXX;

[0068] Surrounding roads: XXX

[0069] Surrounding landmarks: XXX.

[0070] ”

[0071] (3) The third stage:

[0072] The prompt generated in the second stage is input into the pre-trained LLM, which outputs the parent point name and parent point address of the first POI.

[0073] like Figure 2 As shown, in Figure 2 In the example shown, the parent point information of the POI output by LLM is as follows:

[0074] “

[0075] Parent point name: AA Building;

[0076] Parent site address: No. 1, ZZ Road, YY District, XX City

[0077] ”

[0078] In addition, the coordinates of the first POI may be used as the parent point coordinates of the first POI.

[0079] Through the above process, multiple parent point information can be determined in each preset area. For example, each parent point information may include a parent point name, a parent point address, and a parent point coordinate. The above content contained in the parent point information can provide a basis for subsequently determining the parent point area of ​​the first POI.

[0080] Furthermore, based on the information of multiple parent points in each preset area, multiple parent point areas in the preset area can be determined respectively, and the multiple parent point areas can provide strong support for the production and update of the navigation map.

[0081] The parent point area belongs to the regional POI and occupies a certain range on the map. In one example, the parent point area coordinates include multiple coordinates, which can define the range occupied by the parent point area on the map; the range can be a polygon (such as a convex polygon), each coordinate is located at the boundary of the polygon, and adjacent coordinates are connected according to certain rules to form the polygon.

[0082] Figure 3 The flowchart is a method for determining a parent point area in a preset area based on information of multiple parent points in the preset area. As shown in 3, the example includes the following steps:

[0083] S310, clustering multiple parent point information in a preset area according to the parent point name to obtain multiple first-type clusters, where multiple parent point information in each first-type cluster corresponds to one parent point name;

[0084] S320, for each first cluster, clustering the parent point information contained in the first cluster according to the parent point coordinates to obtain a second cluster, wherein the second cluster contains a plurality of parent point information whose distances between the parent point coordinates are less than or equal to a first threshold;

[0085] S330: Determine the parent point area corresponding to each second-type cluster.

[0086] In some examples, the clustering in step S310 can be implemented by a text matching algorithm such as the longest common subsequence (LCS), and multiple parent point information with the same or similar parent point names are placed in a cluster. For example, the parent point names contained in three parent point information are "AA Building", "AA Building East Gate", and "AA Building Parking Lot". Using the text matching algorithm, it is determined that the three parent point names are similar names, and then the three parent point information can be placed in a cluster, and one of the parent point names (such as "AA Building") is taken as the parent point name corresponding to the cluster.

[0087] In some examples, the clustering process in step S320 includes: using a density-based spatial clustering of applications with noise (DBSCAN) algorithm to cluster the parent point information contained in the first type of cluster according to the parent point coordinates to obtain a second type of cluster. The DBSCAN algorithm does not require the number of clusters to be specified in advance, and it can automatically discover the number of clusters based on the characteristics of the data itself; more importantly, the DBSCAN algorithm can recognize clusters of any shape and identify points that do not belong to any cluster as noise.

[0088] Generally speaking, clustering the parent point information in a first cluster can obtain a second cluster, which includes multiple parent point information, and the distance between the parent point coordinates of each parent point information is less than or equal to a first threshold. The first threshold can be a distance parameter (such as radius ε) set when clustering using the DBSCAN algorithm.

[0089] In some examples, step S330 includes:

[0090] Determine the parent point area name based on the parent point names of the plurality of parent point information included in the second type of cluster; and determine the parent point area coordinates based on the parent point coordinates of the plurality of parent point information included in the second type of cluster;

[0091] The parent point area name and parent point area coordinates constitute the information of the parent point area.

[0092] For example, the convex hull algorithm can be used to determine the coordinates of the parent point area, specifically:

[0093] Using the convex hull algorithm, determine the smallest convex polygon that contains the coordinates of multiple parent points;

[0094] The minimum convex polygon is determined as a parent point region, and the parent point region coordinates include a plurality of parent point coordinates used to define the minimum convex polygon.

[0095] The convex hull algorithm is a geometric algorithm that can determine the convex hull of a point set, that is, a minimum convex polygon that can contain all given points. The parent point area determined by the convex hull algorithm can cover all parent point coordinates, thereby improving the accuracy of the parent point area coordinates.

[0096] In this way, through the above process, multiple parent point areas are determined, and the information of each parent point area includes the parent point area name and parent point area coordinates; wherein the parent point area coordinates include multiple coordinates, and the multiple coordinates are used to define the range of the parent point area. The parent point area belongs to the regional POI. Through the above process, multiple regional POIs in the map are determined, which can realize the automatic identification and production of regional POIs, and provide strong support for the production and update of navigation maps.

[0097] Figure 4 FIG. 1 is a schematic diagram of determining a parent point area according to an embodiment of the present disclosure. Figure 4 The example shown is for a preset area. Figure 4 As shown, it includes the following stages:

[0098] (1) Phase I:

[0099] Based on the information of each first POI in the preset area, the parent point information of each first POI is determined. Figure 4 In the example shown, the parent point information of each first POI includes the parent point name, the parent point address and the parent point coordinates.

[0100] (2) Second stage:

[0101] The parent point information of the multiple first POIs in the preset area is clustered. The clustering process includes two steps. The first step is to perform clustering based on name matching (hereinafter referred to as the first clustering) to obtain multiple clusters (hereinafter referred to as the first clusters), each of which contains multiple parent point information with the same or similar names; the second step is to cluster the parent point information in each first cluster based on coordinates (hereinafter referred to as the second clustering) to obtain multiple clusters (hereinafter referred to as the second clusters). The multiple parent point information in each second cluster has the same or similar parent point name, and the distance between the parent point coordinates in the multiple parent point information in each second cluster is relatively close.

[0102] (3) The third stage:

[0103] For each second cluster, the parent point coordinates of multiple parent point information contained in the second cluster are used to generate a parent point area corresponding to the second cluster using a convex hull algorithm. The parent point area coordinates of the parent point area may include multiple coordinates.

[0104] like Figure 4 In the example, Figure 4 The convex polygon in represents a finally generated parent point region, which is obtained by clustering a first-class cluster. Specifically, after the second clustering of the parent point information in the first-class cluster, a second-class cluster is obtained; the convex hull algorithm is used to calculate the parent point coordinates of multiple parent point information in the second-class cluster (such as Figure 4 In the example, the star marks inside and on the border of the convex polygon are used to obtain a convex polygon, which represents the parent point area. The coordinates of the convex polygon border constitute the regional coordinates of the parent point area. The parent point information outside the convex polygon is the parent point information that has not been aggregated into the second cluster after the second clustering, that is, noise information.

[0105] By adopting the above method, multiple parent point areas in the map can be generated, which can provide strong support for the production and update of navigation maps. For example, the parent point information can be used to verify the POI in the map to find out whether there is an error in the coordinates of the POI and correct the error if there is an error.

[0106] The following describes the verification and error correction process of the POI in the embodiment of the present disclosure; for the sake of distinction, the POI to be verified and / or error-corrected is referred to as a POI to be verified.

[0107] Figure 5 The flowchart is a method for implementing POI verification, including some or all of the following steps:

[0108] S510, determining the parent point information of the POI to be verified, where the parent point information of the POI to be verified includes the parent point name and parent point coordinates of the POI to be verified;

[0109] S520, determining a surrounding area, wherein the distance between any position in the surrounding area and the coordinates of the parent point is less than or equal to a preset second threshold;

[0110] S530, determining a parent point region matching the POI to be verified in the surrounding area, wherein the similarity between the parent point region name of the parent point region and the name of the POI to be verified is greater than or equal to a similarity threshold;

[0111] S540: When the coordinates of the POI to be checked are outside the parent point area, adjust the coordinates of the POI to be checked so that the adjusted coordinates are within the parent point area.

[0112] In some implementations, the method of determining the parent point information of the POI to be verified in step S510 is similar to the method of determining the parent point information of the first POI in the foregoing content, for example, including the following steps:

[0113] Get the POI data sub-package of the POI to be verified;

[0114] Obtain the name, address and coordinates of the POI to be verified from the POI data sub-package of the POI to be verified;

[0115] According to the coordinates, obtain the surrounding location information of the POI to be verified;

[0116] Generate a prompt word based on the name, address and surrounding location information of the POI to be verified;

[0117] Input the prompt word corresponding to the POI to be verified into the pre-trained large language model;

[0118] Based on the output result of the pre-trained large language model and the coordinates of the POI to be verified, the parent point information of the POI to be verified is determined, and the parent point information of the POI to be verified includes the parent point name and parent point coordinates of the POI to be verified.

[0119] For other specific details, reference may be made to the specific implementation method of determining the parent point information of the first POI in the above content, which will not be repeated here.

[0120] In some embodiments, the surrounding area determined in step S520 may include an area within a predetermined range around the parent point coordinates of the POI to be verified (that is, the coordinates of the POI to be verified); for example, a circular area in the map with the parent point coordinates of the POI to be verified as the center and a predetermined length (such as 1 km) as the radius is taken as the "surrounding area".

[0121] In some embodiments, in step S530, in the surrounding area, the names of the parent point areas similar to the name of the POI to be verified are determined to obtain a similar parent point area list (which may be referred to as a similar POI List); then, the names of the parent point areas in the similar POI List are matched with the name of the POI to be verified, for example, by using a text matching algorithm such as LCS to extract the parent point areas that are greater than or equal to the similarity threshold; if there are multiple parent point areas that are greater than or equal to the similarity threshold, the parent point area with the highest similarity is extracted. Then, a parent-child relationship is established between the POI to be verified and the extracted parent point areas, where the "POI to be verified" is the "child" and the "parent point area" is the "parent"; the location of the POI to be verified is displayed as a point on the map, represented by a coordinate; the location of the parent point area pair is displayed as a range on the map, represented by multiple coordinates.

[0122] In some examples, in step S540, based on the above-mentioned parent-child relationship, it can be determined whether the POI to be verified is within the region of its matching parent point; if the POI to be verified is not within the region of its matching parent point, the coordinates of the POI to be verified can be adjusted so that its coordinates are at any position within the region of its matching parent point, thereby achieving automatic verification and modification of the POI position and improving the accuracy of map data. For example, the ray method is used for judgment, a scan line is drawn from the coordinate position of the POI to be verified, and the number of intersections between the line and the boundary of the parent point region it matches is calculated; if the number of intersections is an odd number, it means that the POI to be verified is within the region of the parent point; if the number of intersections is an even number, it means that the POI to be verified is outside the region of the parent point. If the POI to be verified is outside the region of the parent point, the coordinates of the POI to be verified are adjusted so that the adjusted coordinates are within the region of the parent point (it can be adjusted to any position within the region of the parent point).

[0123] Figure 6 It is a schematic diagram of determining a similar parent point area list (ie, similar POI List) according to an embodiment of the present disclosure.

[0124] like Figure 6 As shown, the parent point area name of the POI to be verified is "AA Building". In the surrounding area of ​​the POI to be verified, the surrounding search function provided by the map service is used to determine the parent point area name similar to the parent point area name of the POI to be verified, that is, to determine multiple parent point areas that match the POI to be verified. The parent point area names of the multiple matching parent point areas are "AA Building A", "AA Building East Gate", "AA Building West Gate", "AA Building Underground Parking Lot", and "AA Building North Gate". These parent point area names can be combined into a similar parent point area list (i.e., Similar POI List).

[0125] Figure 7FIG. 1 is a schematic diagram of verifying and adjusting the position of a POI to be verified according to an embodiment of the present disclosure. Figure 7 As shown, it includes the following stages:

[0126] (1) Phase I:

[0127] Get the parent point name, parent point address and parent point coordinates of the POI to be verified, use the surrounding search function provided by the map service to determine the parent point area names similar to the parent point name of the POI to be verified, and combine these similar parent point area names into a similar parent point area list (i.e., similar POI List).

[0128] At this stage, it is necessary to limit the surrounding search range of the map service, that is, the distance between any location in the surrounding area and the parent point coordinates is less than or equal to the preset second threshold. This restriction is to ensure that the search results only contain areas that are closely related to the geographical location of the parent point area, thereby improving the accuracy and relevance of the search. The second threshold can be directly set to a fixed value according to business needs, for example, the second threshold is set to a fixed distance of 500 meters, 1 kilometer or 2 kilometers; it can also be dynamically adjusted according to the actual needs of the user, for example, by narrowing the search range to provide more accurate search results.

[0129] (2) Second stage:

[0130] The parent point area name in the similar POI List is matched with the parent point area name of the POI to be verified. In this stage, the LCS algorithm can be used to calculate the similarity between the parent point area name of the POI to be verified and the parent point area name in the POI List. The LCS algorithm is a string matching algorithm that calculates the similarity between two strings by finding the longest common subsequence between them.

[0131] In this stage, by setting the similarity threshold, it is possible to determine which parent point area names in the similar POI List have sufficient similarity with the parent point area name of the POI to be verified. If there are multiple parent point area names in the POI List whose similarity with the parent point area name of the POI to be verified is greater than or equal to the similarity threshold, the parent point area name with the highest similarity is selected as the final result.

[0132] (3) The third stage:

[0133] A parent-child relationship is established between the POI to be verified and the parent point area corresponding to the parent point area name obtained by matching the name similarity, and the positional relationship between the POI to be verified and the parent point area is determined.

[0134] In this stage, it is necessary to obtain the coordinate information of the POI to be verified and the border information of the parent point area. The border information of the parent point area includes the coordinate set of all vertices of the parent point area boundary. For polygons, these vertices are connected in sequence to form a closed boundary. After obtaining this information, the ray method can be used to determine whether the POI to be verified is within the parent point area.

[0135] The basic idea of ​​the ray method is to start from the POI to be checked, emit a ray in any direction, and then calculate the number of intersections between this ray and the boundary of the parent point area. If the number of intersections is an odd number, the POI to be checked is in the parent point area or at the boundary of the parent point area (if the POI to be checked is at the boundary of the parent point area, the POI to be checked is an intersection); if the number of intersections is an even number (including 0), the POI to be checked is outside the parent point area.

[0136] (4) Stage 4:

[0137] If the POI to be checked is outside the parent point area, the POI to be checked is adjusted to any position within the parent point area.

[0138] like Figure 7 As shown, the POI to be verified is "Home Appliances After-Sales Service Center". The POI to be verified is outside the parent point area "AA Building", so the POI to be verified needs to be adjusted to any position within the parent point area.

[0139] The present disclosure also provides an information processing device, Figure 8 8 is a schematic diagram of the structure of an information processing device 800 according to an embodiment of the present disclosure, including:

[0140] The acquisition module 810 is used to acquire a POI data sub-package of a first POI; acquire the name, address and coordinates of the first POI from the POI data sub-package of the first POI; and acquire the surrounding location information of the first POI according to the coordinates;

[0141] The generating module 820 is used to generate a prompt word based on the name, address and surrounding location information of the first POI.

[0142] Fig. 9 is a schematic diagram of the structure of an information processing device 900 according to an embodiment of the present disclosure, which, in some implementations, further includes:

[0143] For multiple first POIs in the preset area, perform the following operations respectively:

[0144] An input module 930, configured to input a prompt word corresponding to the first POI into a pre-trained large language model;

[0145] The determination module 940 is used to determine the parent point information of the first POI based on the output result of the pre-trained large language model and the coordinates of the first POI, where the parent point information of the first POI includes the parent point name and parent point coordinates of the first POI.

[0146] In some implementations, the information processing device 900 further includes:

[0147] The clustering module 950 is used to cluster the multiple parent point information in the preset area according to the parent point name to obtain multiple first clusters, and the multiple parent point information in each first cluster corresponds to one parent point name; and for each first cluster, clustering the parent point information contained in the first cluster according to the parent point coordinates to obtain a second cluster, wherein the second cluster contains multiple parent point information whose distance between the parent point coordinates is less than or equal to the first threshold;

[0148] The determination module 940 is used to determine the parent point area corresponding to each second type cluster.

[0149] In some implementations, the clustering module 950 is configured to use a DBSCAN clustering algorithm to cluster the parent point information contained in the first cluster according to the parent point coordinates to obtain a second cluster.

[0150] In some implementations, the determination module 940 is configured to:

[0151] Determine the parent point region name based on the parent point names of the plurality of parent point information included in the second type of cluster; and determine the parent point region coordinates based on the parent point coordinates of the plurality of parent point information included in the second type of cluster;

[0152] The parent point area name and parent point area coordinates constitute the information of the parent point area.

[0153] In some implementations, the determination module 940 is configured to:

[0154] Using the convex hull algorithm, determine the smallest convex polygon that contains the coordinates of multiple parent points;

[0155] The minimum convex polygon is determined as a parent point region, wherein the parent point region coordinates include a plurality of parent point coordinates for defining the minimum convex polygon.

[0156] In some implementations, the information processing device 900 further includes an adjustment module 960, and the determination module 940 is further configured to:

[0157] Determine the parent point information of the POI to be verified, where the parent point information of the POI to be verified includes the parent point name and parent point coordinates of the POI to be verified; determine a surrounding area, where the distance between any position in the surrounding area and the parent point coordinates is less than or equal to a preset second threshold; in the surrounding area, determine a parent point area matching the POI to be verified, where the similarity between the parent point area name of the parent point area and the name of the POI to be verified is greater than or equal to a similarity threshold;

[0158] The adjustment module 960 is used to adjust the coordinates of the POI to be checked so that the adjusted coordinates are within the parent point area when the coordinates of the POI to be checked are outside the parent point area.

[0159] In some implementations, the determination module 940 is configured to:

[0160] Get the POI data sub-package of the POI to be verified;

[0161] Obtain the name, address and coordinates of the POI to be verified from the POI data sub-package of the POI to be verified;

[0162] According to the coordinates, obtain the surrounding location information of the POI to be verified;

[0163] Generate a prompt word based on the name, address and surrounding location information of the POI to be verified;

[0164] Input the prompt word corresponding to the POI to be verified into the pre-trained large language model;

[0165] Based on the output result of the pre-trained large language model and the coordinates of the POI to be verified, the parent point information of the POI to be verified is determined, and the parent point information of the POI to be verified includes the parent point name and parent point coordinates of the POI to be verified.

[0166] In some implementations, the POI data subpackage includes multiple feature classes, each feature class having corresponding attributes.

[0167] In some embodiments, the plurality of feature classes of the POI data sub-package include at least one of a shopping mall, a restaurant, a plaza, a bank, a hotel, a hospital, an airport, a railway station, a subway station, a bus station, a toll station, a gas station, a charging or battery replacement station, an emergency telephone booth, a parking lot, a service area, a tourist attraction, and a public rest area;

[0168] The attributes corresponding to each feature class include at least one of location and geometry.

[0169] For the description of specific functions and examples of each module and submodule of the device in the embodiment of the present disclosure, reference can be made to the relevant description of the corresponding steps in the above method embodiment, which will not be repeated here.

[0170] In the technical solution disclosed in the present invention, the acquisition, storage and application of personal information of users involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0171] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0172] Fig.10 A schematic block diagram of an example electronic device 1000 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0173] like Fig.10 As shown, the device 1000 includes a computing unit 1001, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1002 or a computer program loaded from a storage unit 1008 into a random access memory (RAM) 1003. In the RAM 1003, various programs and data required for the operation of the device 1000 can also be stored. The computing unit 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0174] A number of components in the device 1000 are connected to the I / O interface 1005, including: an input unit 1006, such as a keyboard, a mouse, etc.; an output unit 1007, such as various types of displays, speakers, etc.; a storage unit 1008, such as a disk, an optical disk, etc.; and a communication unit 1009, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1009 allows the device 1000 to exchange data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0175] The computing unit 1001 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 1001 performs the various methods and processes described above, such as detection methods. For example, in some embodiments, the detection method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 1008. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 1000 via ROM 1002 and / or communication unit 1009. When the computer program is loaded into RAM 1003 and executed by the computing unit 1001, one or more steps of the detection method described above may be performed. Alternatively, in other embodiments, the computing unit 1001 may be configured to perform the detection method in any other appropriate manner (e.g., by means of firmware).

[0176] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0177] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0178] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0179] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0180] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0181] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0182] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0183] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. An information processing method, comprising: Obtaining a point of interest data sub-package of a first point of interest; Obtaining the name, address and coordinates of the first point of interest from the point of interest data sub-package of the first point of interest; According to the coordinates, obtaining peripheral location information of the first point of interest; Generate a prompt word based on the name, address and surrounding location information of the first point of interest.

2. The method according to claim 1, further comprising: For multiple first points of interest in the preset area, perform the following operations respectively: Inputting the prompt word corresponding to the first point of interest into a pre-trained large language model; Based on the output result of the pre-trained large language model and the coordinates of the first point of interest, the parent point information of the first point of interest is determined, where the parent point information of the first point of interest includes the parent point name and parent point coordinates of the first point of interest.

3. The method according to claim 2, further comprising: Clustering the plurality of parent point information in the preset area according to the parent point name to obtain a plurality of first clusters, wherein the plurality of parent point information in each first cluster corresponds to a parent point name; For each of the first clusters, clustering the parent point information contained in the first cluster according to the parent point coordinates to obtain a second cluster, wherein the second cluster contains a plurality of parent point information whose distances between the parent point coordinates are less than or equal to a first threshold; Determine the parent point area corresponding to each of the second-type clusters.

4. The method according to claim 3, wherein: The clustering of the parent point information contained in the first cluster according to the parent point coordinates to obtain the second cluster includes: A density-based noise application spatial clustering algorithm is used to cluster the parent point information contained in the first cluster according to the parent point coordinates to obtain a second cluster.

5. The method according to claim 3 or 4, wherein: The determining of the parent point area corresponding to each of the second-type clusters includes: Determine the parent point area name based on the parent point names of the plurality of parent point information included in the second type of cluster; and determine the parent point area coordinates based on the parent point coordinates of the plurality of parent point information included in the second type of cluster; The parent point area name and the parent point area coordinates constitute the information of the parent point area.

6. The method according to claim 5, wherein: The determining of the parent point area coordinates based on the parent point coordinates of the plurality of parent point information included in the second cluster includes: Using a convex hull algorithm, determine a minimum convex polygon containing the coordinates of the multiple parent points; The minimum convex polygon is determined as the parent point region, and the parent point region coordinates include a plurality of parent point coordinates for defining the minimum convex polygon.

7. The method according to any one of claims 3 to 6, further comprising: Determine the parent point information of the interest point to be verified, wherein the parent point information of the interest point to be verified includes the parent point name and parent point coordinates of the interest point to be verified; Determine a surrounding area, wherein the distance between any position in the surrounding area and the coordinates of the parent point is less than or equal to a preset second threshold; In the surrounding area, determining a parent point area matching the to-be-checked interest point, wherein the similarity between the parent point area name of the parent point area and the name of the to-be-checked interest point is greater than or equal to a similarity threshold; In the case where the coordinates of the interest point to be verified are outside the parent point area, the coordinates of the interest point to be verified are adjusted so that the adjusted coordinates are within the parent point area.

8. The method according to claim 7, wherein: The step of determining the parent point information of the point of interest to be verified includes: Obtaining a point of interest data sub-package of the point of interest to be verified; Obtaining the name, address and coordinates of the point of interest to be verified from the point of interest data sub-package of the point of interest to be verified; According to the coordinates, obtaining the surrounding location information of the point of interest to be verified; Generate a prompt word based on the name, address and surrounding location information of the point of interest to be verified; Inputting the prompt word corresponding to the interest point to be verified into a pre-trained large language model; Based on the output result of the pre-trained large language model and the coordinates of the interest point to be verified, the parent point information of the interest point to be verified is determined, and the parent point information of the interest point to be verified includes the parent point name and parent point coordinates of the interest point to be verified.

9. The method according to any one of claims 1 to 8, wherein: The interest point data sub-package includes a plurality of feature classes, and each feature class has corresponding attributes.

10. The method according to claim 9, wherein: The multiple element classes of the POI data sub-package include at least one of a shopping mall, a restaurant, a square, a bank, a hotel, a hospital, an airport, a railway station, a subway station, a bus station, a toll station, a gas station, a charging or battery replacement station, an emergency telephone booth, a parking lot, a service area, a tourist attraction, and a public rest area; The attributes corresponding to each feature class include at least one of position and geometry.

11. An information processing device, comprising: An acquisition module, used to acquire a point of interest data sub-package of a first point of interest; Acquire the name, address and coordinates of the first point of interest from the point of interest data sub-packet of the first point of interest; and acquire the surrounding location information of the first point of interest according to the coordinates; A generation module is used to generate a prompt word based on the name, address and surrounding location information of the first point of interest.

12. The apparatus according to claim 11, further comprising: An input module, used for inputting the prompt word corresponding to the first interest point into a pre-trained large language model; A determination module is used to determine the parent point information of the first interest point based on the output result of the pre-trained large language model and the coordinates of the first interest point, where the parent point information of the first interest point includes the parent point name and parent point coordinates of the first interest point.

13. The apparatus according to claim 12, further comprising: A clustering module, used for clustering the plurality of parent point information in the preset area according to the parent point name to obtain a plurality of first clusters, wherein the plurality of parent point information in each first cluster corresponds to a parent point name; and for clustering the parent point information contained in the first cluster according to the parent point coordinates for each of the first clusters to obtain a second cluster, wherein the second cluster contains a plurality of parent point information whose distances between the parent point coordinates are less than or equal to a first threshold; The determination module is further used to determine the parent point area corresponding to each of the second-type clusters.

14. The device according to claim 13, wherein: The clustering module is used to cluster the parent point information contained in the first cluster according to the parent point coordinates by using a density-based noise application spatial clustering algorithm to obtain a second cluster.

15. The device according to claim 13 or 14, wherein: The determination module is used for: Determine the parent point area name based on the parent point names of the plurality of parent point information included in the second type of cluster; and determine the parent point area coordinates based on the parent point coordinates of the plurality of parent point information included in the second type of cluster; The parent point area name and the parent point area coordinates constitute the information of the parent point area.

16. The device according to claim 15, wherein: The determination module is used for: Using a convex hull algorithm, determine a minimum convex polygon containing the coordinates of the multiple parent points; The minimum convex polygon is determined as the parent point region, and the parent point region coordinates include a plurality of parent point coordinates for defining the minimum convex polygon.

17. The device according to any one of claims 13 to 16, further comprising an adjustment module; The determining module is also used for: Determine the parent point information of the interest point to be verified, wherein the parent point information of the interest point to be verified includes the parent point name and parent point coordinates of the interest point to be verified; Determine a surrounding area, wherein the distance between any position in the surrounding area and the coordinates of the parent point is less than or equal to a preset second threshold; In the surrounding area, determining a parent point area matching the to-be-checked interest point, wherein the similarity between the parent point area name of the parent point area and the name of the to-be-checked interest point is greater than or equal to a similarity threshold; The adjustment module is used to adjust the coordinates of the interest point to be checked so that the adjusted coordinates are within the parent point area when the coordinates of the interest point to be checked are outside the parent point area.

18. The device according to claim 17, wherein: The determination module is used for: Obtaining a point of interest data sub-package of the point of interest to be verified; Obtaining the name, address and coordinates of the point of interest to be verified from the point of interest data sub-package of the point of interest to be verified; According to the coordinates, obtaining the surrounding location information of the point of interest to be verified; Generate a prompt word based on the name, address and surrounding location information of the point of interest to be verified; Inputting the prompt word corresponding to the interest point to be verified into a pre-trained large language model; Based on the output result of the pre-trained large language model and the coordinates of the interest point to be verified, the parent point information of the interest point to be verified is determined, and the parent point information of the interest point to be verified includes the parent point name and parent point coordinates of the interest point to be verified.

19. The device according to any one of claims 11 to 18, wherein: The interest point data sub-package includes a plurality of feature classes, and each feature class has corresponding attributes.

20. The device according to claim 19, wherein The multiple element classes of the POI data sub-package include at least one of a shopping mall, a restaurant, a square, a bank, a hotel, a hospital, an airport, a railway station, a subway station, a bus station, a toll station, a gas station, a charging or battery replacement station, an emergency telephone booth, a parking lot, a service area, a tourist attraction, and a public rest area; The attributes corresponding to each feature class include at least one of position and geometry.

21. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 10.

22. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-10.

23. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 10.

Images