Information point updating method and device, and storage medium

Abstract

The application discloses an information point updating method and device and a storage medium, which can be applied to various scenes such as cloud technology, artificial intelligence, intelligent transportation and Internet of Vehicles, and the method comprises the steps of acquiring a second image corresponding to a target region at a second time; constructing a second information point relationship graph based on the second image; the second information point relationship graph represents the positional relationship between each second information point in the second image; determining a first information point relationship graph based on the target region; the first information point relationship graph is constructed based on the positional relationship between each first information point in a first image; determining an information point to be updated based on the first information point relationship graph and the second information point relationship graph; and updating the first information point relationship graph based on the information point to be updated. The application realizes quick and accurate updating of information points according to the association relationship between the information points.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus and storage medium for updating information points. Background Technology

[0002] Currently, POIs are stored statically on a per-POI basis. Each POI contains information such as its name, coordinates, address, category, and details. However, there are no relationships between POIs, and POI maintenance can only be done in isolation based on a single POI.

[0003] Existing methods for updating POI status and coordinates typically include: on-site data collection, ecosystem mining, user reporting, news scraping, and integration with partner sources. However, these methods only address single POIs or batch processing of single POIs. This results in slow update speed, low update efficiency, and high maintenance costs. Summary of the Invention

[0004] This application provides an information point updating method, apparatus, and storage medium, which can improve the updating efficiency of information points.

[0005] On the one hand, this application provides an information point updating method, the method comprising:

[0006] Obtain the second image of the target region at the second time point;

[0007] Based on the second image, a second information point relationship diagram is constructed; the second information point relationship diagram represents the positional relationship between each second information point in the second image;

[0008] Based on the target region, a first information point relationship diagram is determined; the first information point relationship diagram is constructed based on the positional relationship between each first information point in the first image, the first image being the image corresponding to the target region at a first time; the first time is earlier than the second time.

[0009] Based on the first information point relationship diagram and the second information point relationship diagram, the information points to be updated are determined;

[0010] Based on the information points to be updated, update the relationship graph of the first information points.

[0011] On the other hand, an information point updating device is provided, the device comprising:

[0012] The second image acquisition module is used to acquire the second image of the target area at the second time.

[0013] The second relationship graph construction module is used to construct a second information point relationship graph based on the second image; the second information point relationship graph represents the positional relationship between each second information point in the second image;

[0014] The first relationship graph determination module is used to determine a first information point relationship graph based on the target region; the first information point relationship graph is constructed based on the positional relationship between each first information point in a first image, the first image being the image corresponding to the target region at a first time; the first time is earlier than the second time;

[0015] The module for determining information points to be updated is used to determine information points to be updated based on the first information point relationship diagram and the second information point relationship diagram.

[0016] The information point update module is used to update the first information point relationship diagram based on the information points to be updated.

[0017] On the other hand, an information point update device is provided, the device including a processor and a memory, the memory storing at least one instruction or at least one program, the at least one instruction or the at least one program being loaded and executed by the processor to implement the information point update method as described above.

[0018] On the other hand, a computer storage medium is provided that stores at least one instruction or at least one program, which is loaded and executed by a processor to implement the information point update method as described above.

[0019] On the other hand, a computer program product or computer program is provided, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, executes the computer instructions, and causes the computer device to perform the information point update method as described above.

[0020] The information point updating method, apparatus, and storage medium provided in this application have the following technical advantages:

[0021] This application acquires a second image corresponding to a target region at a second time; constructs a second information point relationship graph based on the second image; the second information point relationship graph represents the positional relationship between each second information point in the second image; determines a first information point relationship graph based on the target region; the first information point relationship graph is constructed based on the positional relationship between each first information point in a first image, where the first image is the image corresponding to the target region at the first time; the first time is earlier than the second time; determines information points to be updated based on the first and second information point relationship graphs; and updates the first information point relationship graph based on the information points to be updated. This application constructs information point relationship graphs at different times and determines information points to be updated based on the relationship graphs at two times, thereby quickly identifying new and expired information points, and obtaining an updated information point relationship graph based on the information points to be updated, achieving rapid and accurate updating of information points based on the correlation between them. Attached Figure Description

[0022] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a schematic diagram of an information point update system provided in an embodiment of this application;

[0024] Figure 2 This is a flowchart illustrating an information point update method provided in an embodiment of this application;

[0025] Figure 3 This is a flowchart illustrating a method for constructing a second information point relationship graph based on the second image, provided in an embodiment of this application.

[0026] Figure 4 This is a flowchart illustrating a method for determining information points to be updated based on the first information point relationship diagram and the second information point relationship diagram, provided in an embodiment of this application.

[0027] Figure 5 This is a flowchart illustrating a method for updating the relationship graph of the first information point based on the information point to be updated, according to an embodiment of this application.

[0028] Figure 6 This is a schematic flowchart of a coordinate update method provided in an embodiment of this application;

[0029] Figure 7This is a flowchart of a three-dimensional reconstruction method for a first image provided in an embodiment of this application;

[0030] Figure 8 This is a flowchart illustrating the method for creating a relationship diagram of the first information points at time T1, as provided in an embodiment of this application.

[0031] Figure 9 This is a flowchart illustrating a method for recognizing a first preset text result corresponding to a first image, as provided in an embodiment of this application.

[0032] Figure 10 This is a flowchart illustrating the method for representing a first preset object corresponding to a first image provided in an embodiment of this application.

[0033] Figure 11 This is a flowchart illustrating the method for representing a first preset text image corresponding to a first image, as provided in an embodiment of this application.

[0034] Figure 12 This is a flowchart illustrating the method for extracting images based on POI crowdsourced data provided in an embodiment of this application;

[0035] Figure 13 This is a flowchart illustrating a method for recognizing a second preset target text result in a second image, as provided in an embodiment of this application.

[0036] Figure 14 This is a schematic diagram of the first image provided in the embodiments of this application;

[0037] Figure 15 This is a schematic diagram of the second image provided in the embodiments of this application;

[0038] Figure 16 This is a flowchart illustrating a method for capturing images from a first angle, as provided in an embodiment of this application.

[0039] Figure 17 This is a flowchart illustrating the method for capturing images from a second angle according to an embodiment of this application;

[0040] Figure 18 This is a flowchart illustrating a method for a second preset object based on a second image recognition, as provided in an embodiment of this application.

[0041] Figure 19 This is a flowchart illustrating a method for recognizing a second preset object based on another second image, as provided in an embodiment of this application.

[0042] Figure 20 This is an example 1 of the information point relationship diagram corresponding to different times provided in the embodiments of this application;

[0043] Figure 21This is Example 2 of the information point relationship diagram corresponding to different times provided in the embodiments of this application;

[0044] Figure 22 This is a flowchart of an information point updating method provided in an embodiment of this application;

[0045] Figure 23 This is a schematic diagram of the structure of an information point updating device provided in an embodiment of this application;

[0046] Figure 24 This is a schematic diagram of the structure of a server provided in an embodiment of this application. Detailed Implementation

[0047] The technical solutions of the embodiments of this application 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 application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0048] First, some of the nouns or terms that appear in the description of the embodiments of this application are explained as follows:

[0049] POI: POI is an abbreviation for "Point of Information." In a geographic information system, a POI can be a building, a shop, a mailbox, a bus stop, etc.

[0050] Shop sign: Specifically refers to the POI sign, which usually includes information such as name, address, telephone number, business scope, branch name, and logo, but does not include the main entrance.

[0051] OCR: Optical Character Recognition, is the process of detecting text areas in a photograph and recognizing the corresponding text using algorithms.

[0052] Linking: The POI in the data identified by OCR is compared with the data in the database based on name, coordinates, and photo similarity (pointing to the same POI). If the data is consistent, the linking is successful. If the consistency is determined by text similarity, it is called text linking. If the consistency is determined by comparison between images, it is called image-to-image linking.

[0053] POI Expiration: In the real world, if a POI no longer exists due to relocation, renaming, closure, or other reasons, then the POI in the map data will be in an expired state.

[0054] Entity: refers to a data entity in the database. Any object in the real world can be mapped to a data entity. An entity can be a POI, a billboard, a tree, or an object without any actual meaning. In this article, the entity specifically refers to the identified shop sign. A shop sign is an entity.

[0055] Entity Relationship History: Data describing the spatial and temporal relationships between entities. Spatial relationships refer to which entities are above, below, left, and right of a given entity. Temporal relationships refer to the entities corresponding to the same location at a certain time or several times.

[0056] Intelligent transportation fully utilizes next-generation information technologies such as the Internet of Things, spatial sensing, cloud computing, and mobile internet across the entire transportation sector. It comprehensively applies theories and tools from transportation science, systems methods, artificial intelligence, and knowledge mining. With the goals of comprehensive perception, deep integration, proactive service, and scientific decision-making, it builds a real-time dynamic information service system, deeply mines transportation-related data, forms problem analysis models, and enhances the industry's ability to optimize resource allocation, improve public decision-making capabilities, enhance industry management capabilities, and improve public service capabilities. This promotes safer, more efficient, more convenient, more economical, more environmentally friendly, and more comfortable operation and development of transportation, and drives the transformation and upgrading of transportation-related industries.

[0057] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0058] Please see Figure 1 , Figure 1 This is a schematic diagram of an information point update system provided in an embodiment of this application, such as... Figure 1 As shown, the information point update system may include at least server 01 and client 02.

[0059] Specifically, in this embodiment, the server 01 may include a standalone server, a distributed server, or a server cluster composed of multiple servers. It may also be a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Server 01 may include a network communication unit, a processor, and a memory, etc. Specifically, server 01 can be used to construct a first information point relationship graph, a second information point relationship graph, determine information points to be updated, and update the first information point relationship graph.

[0060] Specifically, in this embodiment, the client 02 may include physical devices such as smartphones, desktop computers, tablets, laptops, digital assistants, smart wearable devices, smart speakers, in-vehicle terminals, and smart TVs. It may also include software running on these physical devices, such as web pages provided to users by service providers, or applications provided to users by those service providers. Specifically, the client 02 can be used to display a first information point relationship diagram, a second information point relationship diagram, and an updated first information point relationship diagram.

[0061] The following describes one method for updating information points according to this application. Figure 2 This is a flowchart illustrating an information point update method provided in an embodiment of this application. This specification provides the operational steps of the method described in the embodiments or flowcharts, but based on conventional or non-inventive methods, more or fewer operational steps may be included. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only possible execution order. In actual system or server product execution, the methods shown in the embodiments or drawings can be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment). Specifically, as shown in the flowchart... Figure 2 As shown, the method may include:

[0062] S201: Obtain the second image of the target region at the second time.

[0063] In this embodiment, the target area can be set according to actual needs, and the second image corresponding to the target area can be one or more. The second image carries coordinate information.

[0064] Specifically, in this embodiment of the application, the second image can be obtained through preset data, which includes:

[0065] POI crowdsourced data: Images of the actual entities captured;

[0066] Equipment crowdsourcing materials: Road images (including roadside entities) captured by dashcams;

[0067] Road crowdsourcing data: Install a mobile phone on a vehicle to capture images of the road (including roadside entities);

[0068] High-precision data: physical images captured by high-precision vehicles (specialized equipment, using radar, 360-degree panoramic shooting equipment, etc.);

[0069] Other materials: Images of the entity obtained from partners or other channels.

[0070] S203: Based on the second image, construct a second information point relationship diagram; the second information point relationship diagram represents the positional relationship between each second information point in the second image.

[0071] Specifically, in this embodiment, the coordinate information of each second information point can be determined based on the coordinate information of the second image. Entities in the second image can be identified first, and then information points can be selected from these entities.

[0072] In the embodiments of this application, such as Figure 3 As shown, constructing a second information point relationship graph based on the second image includes:

[0073] S2031: Perform three-dimensional reconstruction on the second image to construct a second point cloud dataset;

[0074] In the embodiments of this application, 3D reconstruction refers to establishing a mathematical model of a 3D object that is suitable for computer representation and processing. It is the basis for processing, manipulating and analyzing the properties of the object in a computer environment, and it is also a key technology for establishing virtual reality that expresses the objective world in a computer.

[0075] S2033: Based on the second point cloud dataset, determine each second information point in the second image;

[0076] In this embodiment, a point cloud is a dataset where each point represents a set of X, Y, and Z geometric coordinates and an intensity value. This intensity value records the strength of the returned signal based on the reflectivity of the object's surface. When these points are combined, they form a point cloud, which is a collection of data points representing 3D shapes or objects in space. Point clouds can also be automatically colored for more realistic visualization.

[0077] S2035: Determine the positional relationship between the second information points based on the second point cloud data corresponding to each second information point;

[0078] In this embodiment of the application, the distance between any two second information points can be determined by the second point cloud data corresponding to each second information point.

[0079] S2037: Based on the positional relationship between the various second information points, construct the second information point relationship diagram.

[0080] In this embodiment of the application, the second information point relationship diagram can also represent the distance between different second information points.

[0081] S205: Based on the target region, determine a first information point relationship diagram; the first information point relationship diagram is constructed based on the positional relationship between each first information point in the first image, the first image being the image corresponding to the target region at the first time; the first time is earlier than the second time.

[0082] In this embodiment of the application, the first image may carry coordinate information, and the coordinate information of each first information point can be determined based on the coordinate information of the first image.

[0083] In this embodiment of the application, the method for constructing the first information point relationship graph includes:

[0084] Obtain the first image corresponding to the target region at the first time.

[0085] Determine the positional relationship between each first information point in the first image;

[0086] In this embodiment of the application, determining the positional relationship between each first information point in the first image includes:

[0087] Perform 3D reconstruction on the first image to construct a first point cloud dataset;

[0088] Based on the first point cloud dataset, determine each first information point in the first image;

[0089] Based on the first point cloud data corresponding to each first information point, the positional relationship between each first information point is determined.

[0090] In the embodiments of this application, such as Figure 7 As shown, Figure 7 A flowchart of a 3D reconstruction method for the first image, including:

[0091] S701: Acquire the first image;

[0092] The first image can be multiple, for example, it can include image 1, 2, and 3;

[0093] S703: Perform 3D reconstruction on the first image to construct a 3D spatial point cloud image;

[0094] S705: Generates 3D reconstructed visualization images.

[0095] The positional relationship between each first information point can be determined through visual images.

[0096] Based on the positional relationships between the various first information points, a relationship diagram of the first information points is constructed.

[0097] In the embodiments of this application, such as Figure 8 As shown, Figure 8 This is the relationship diagram of the first information point at time T1. At time T1, there are four entities, A, B, C, and D. Through the 3D reconstruction, we know that the relationship between the four entities is as follows: A is to the left of B, m units away; C is to the right of B, adjacent to B; and D is to the right of C, adjacent to C. Saving the relationship between A, B, C, and D is the spatial relationship.

[0098] In this embodiment of the application, determining the first information point relationship graph based on the target region includes:

[0099] Obtain a preset information point relationship diagram corresponding to a preset region at a first time, wherein the preset region includes the target region;

[0100] The first information point relationship diagram corresponding to the target area is determined from the preset information point relationship diagram; the preset information point relationship diagram is the relationship diagram of information points within the preset area at the first time.

[0101] In this embodiment, a first information point relationship graph can be extracted from a pre-constructed, large-scale preset information point relationship graph, thereby updating that portion and achieving real-time updates to the preset information point relationship graph. Furthermore, the map data corresponding to the preset information point relationship graph can be updated in real-time, improving the accuracy of the map data.

[0102] S207: Based on the first information point relationship diagram and the second information point relationship diagram, determine the information points to be updated.

[0103] In this embodiment of the application, the second information point relationship diagram may include some or all of the first information points in the first information point relationship diagram; the information points to be updated may be newly added information points or isolated information points that already exist in the first image.

[0104] In the embodiments of this application, such as Figure 4 As shown, determining the information point to be updated based on the first information point relationship diagram and the second information point relationship diagram includes:

[0105] S2071: Acquire second preset information corresponding to each second information point in the second information point relation graph; the second preset information includes at least one of a second preset text and a second preset object;

[0106] In the embodiments of the present application, the second preset text may be text extracted from a second image based on OCR technology, and the second preset object may include a store sign image extracted based on the second image. Each store sign may correspond to one information point.

[0107] In the embodiments of the present application, each second information point may correspond to one or more second preset texts, and each second information point may correspond to one or more second preset objects.

[0108] In some embodiments, all texts in the second image may be extracted, then the text corresponding to the store sign is extracted from all the extracted texts according to the extracted store sign, to serve as the second preset text; wherein the extraction of the store sign and the extraction of all the texts may be performed synchronously.

[0109] S2073: Determine a matching result between second preset target information and first preset information in a preset information point database; the second preset target information is any second preset information, and the preset information point database is generated based on the correspondence between first information points and first preset information in the first information point relation graph; the first preset information includes at least one of a first preset text and a first preset object corresponding to the first image;

[0110] In the embodiments of the present application, the first preset text and the first preset object in the first image may be extracted; wherein the first preset object may be a store sign image, and the first preset text is the text corresponding to the first preset object; the store sign text may be split into: a proper name, a general name (business scope), a branch store name, etc., then all split texts within the same store sign frame are randomly permuted and combined, so as to construct a plurality of first preset texts. In a specific embodiment, for example Figure 9 as shown in Figure 9 it is a first preset text recognition result corresponding to a first image, the text in the store sign is "Chenji Salt Baked Store (Bao'an Store)", which is split into a plurality of texts "Chenji", "Salt Baked", "Store" and "Bao'an Store", then permutation and combination are performed on the split texts to construct the first preset text. In the matching process, for the store sign "Chenji Salt Cave Store" in the second image, it can be considered that "Salt Cave Store" is a misrecognition caused by recognition error. At this time, it is determined that the store sign "Chenji Salt Cave Store" in the second image and the "Chenji Salt Baked Store (Bao'an Store)" in the first image are the same store sign, that is, the information points corresponding to the two are successfully connected.

[0111] In this embodiment of the application, the first preset information includes the first preset text and the first preset object; the method for constructing the preset information point database includes:

[0112] Based on the correspondence between each first information point and the first preset text in the first information point relationship diagram, a first database is constructed;

[0113] In the embodiments of this application, each first information point may correspond to one or more first preset texts.

[0114] Based on the correspondence between each first information point and the first preset object, a second database is constructed;

[0115] In the embodiments of this application, each first information point may correspond to one or more first preset objects.

[0116] Based on the first database and the second database, the preset information point database is constructed.

[0117] In this embodiment of the application, the first preset text and the first preset object corresponding to each first information point in the first information point relationship graph can be determined; and the first database corresponding to the text and the second database corresponding to the object can be constructed according to the corresponding relationship, thereby facilitating text splicing and graph splicing.

[0118] In the embodiments of this application, such as Figure 10-11 As shown, Figure 10-11 Images extracted from crowdsourced device data, including road information; Figure 10 This is a schematic diagram of the first preset object corresponding to the first image; where rectangles 03 are all shop signs; Figure 11 This is a schematic diagram of the first preset text corresponding to the first image; where rectangles 04 are text extraction boxes extracted from the store sign, and the text includes "AB, CBE, XXNNZZ"; for example Figure 12 As shown, Figure 12 As shown, Figure 12 The image is extracted based on POI crowdsourced data. Rectangle 05 is the store sign, and rectangle 06 is the text extraction box corresponding to the store sign.

[0119] In this embodiment of the application, the second preset target information is a second preset target text, and determining the matching result between the second preset target information and the first preset information in the preset information point database includes:

[0120] Based on the first database, a first preset text that matches the second preset target text is determined, and a first matching success result is obtained.

[0121] In this embodiment of the application, the step of determining a first preset text that matches the second preset target text based on the first database, and obtaining a first successful matching result, includes:

[0122] Determine the first coordinates of the second preset information point corresponding to the second preset target text;

[0123] Specifically, in the embodiments of this application, the second preset target text can be one or more, and corresponds to the same information point.

[0124] Based on the first coordinates and the second coordinates corresponding to each first information point in the first database, first information points whose distance from the second preset information point is less than a preset distance are determined, and candidate information points are obtained.

[0125] In this embodiment of the application, the preset distance can be set according to the actual situation, for example, it can be set to 30 meters.

[0126] If there are at least two candidate information points, obtain the first preset text corresponding to each candidate information point to obtain the text to be matched;

[0127] The second preset target text is matched with each text to be matched to obtain the matching result.

[0128] In this embodiment, the matching result can be determined based on the text similarity between two texts. For a text to be matched, a similarity threshold can be set. When the text similarity is greater than or equal to the similarity threshold, the two texts are determined to match; when the text similarity is less than the similarity threshold, the two texts are determined not to match. For multiple texts to be matched, the text with the highest similarity can be determined first as the target text to be matched, and then the matching result is determined based on the comparison between the similarity of the target text and the similarity threshold.

[0129] In this embodiment of the application, the first information point that is closer to the second preset information point can be filtered out based on the coordinate information corresponding to the information point, so as to quickly determine the matching result of the information point.

[0130] In a specific embodiment, such as Figure 13 As shown, Figure 13 The second preset target text recognition result for a second image includes "AB, CDE, XXMZZ". Due to the low clarity of the second image, the recognition results of the last two characters "CDE, XXMZZ" are not completely correct; their corresponding real text is "CBE, XXNNZZ". If the corresponding first preset text "AB, CBE, XXNNZZ" exists in the first image, then it can be determined that the text in the two images is successfully matched.

[0131] In some instances, text matching failures may be due to the inability to accurately identify the text in the image. In such cases, it is impossible to obtain accurate information point matching results based on the text matching results. Further matching is required using preset objects in the image to improve the accuracy of the matching results between the first and second information points.

[0132] In this embodiment of the application, the second preset target information includes a second preset target text and a second preset target object; determining the matching result between the second preset target information and the first preset information in the preset information point database includes:

[0133] If there is no first preset text in the first database that matches the second preset target text;

[0134] Based on the second database, a first preset object that matches the second preset target object is determined, and a second matching success result is obtained.

[0135] In this embodiment of the application, the matching result can also be determined directly based on the second preset target object, thereby further determining the matching result of the information point.

[0136] In this embodiment of the application, the second preset target information includes a second preset target object; determining the matching result between the second preset target information and the first preset information in the preset information point database includes:

[0137] Based on the second database, a first preset object that matches the second preset target object is determined, and a second matching success result is obtained.

[0138] In this embodiment of the application, multimodal features (e.g., images, text, etc.) of the second preset target object and the first preset object can be extracted to determine the matching result.

[0139] In the embodiments of this application, such as Figure 14-15 As shown, Figure 14-15 For the images corresponding to two preset objects to be matched, Figure 14 This is a schematic diagram of the first image. Figure 15 This is a schematic diagram of the second image. Both images include the store sign "CBE". The matching result between the two can be determined based on the comparison of the store sign images.

[0140] In this embodiment of the application, the data from the device crowdsourcing may be captured in both directions, such as... Figure 16-17 As shown, Figure 16 The image was taken from a first-person perspective. Figure 17 For images taken from a second angle, multimodal features can improve matching accuracy for photos taken from another angle.

[0141] In this embodiment, an information point matching model can be trained based on a sample database. Multimodal features of two objects to be matched can be extracted based on the model and compared to obtain a matching result. Furthermore, multiple second information points in multiple second images with similarity greater than a preset value can be recalled, and multiple second information points can be identified as the same information point.

[0142] In a specific embodiment, such as Figure 18-19 As shown, Figure 18 This is a second preset object based on a second image recognition; 07 in the figure is the second preset object corresponding to an extracted information point; Figure 19 The second preset object is based on another second image recognition; 08 in the figure is another second preset object corresponding to an extracted information point; it can be seen that the second preset objects (shop signs) in the two figures actually correspond to the same information point. These two second preset objects are objects with high similarity and can be recalled through the model.

[0143] In this embodiment of the application, the training method of the information point matching model may include:

[0144] Obtain a sample database; the sample database includes sample objects corresponding to sample information points.

[0145] Based on the sample database, positive sample pairs and negative sample pairs are constructed; wherein, the similarity between the two sample objects in a positive sample pair is greater than a preset similarity threshold; and the similarity between the two sample objects in a negative sample pair is less than or equal to a preset similarity threshold.

[0146] In this embodiment of the application, the similarity of the sample information points corresponding to the two sample objects in a positive sample pair is greater than a preset similarity threshold; the similarity of the sample information points corresponding to the two sample objects in a negative sample pair is less than or equal to the preset similarity threshold.

[0147] Extract the multimodal features corresponding to each sample object in the positive and negative sample pairs;

[0148] Among them, multimodal features may include, but are not limited to, image features corresponding to the sample object and text features in the image.

[0149] The information point matching model is obtained by training a preset model based on the extracted multimodal features.

[0150] In this embodiment of the application, the similarity between any two preset objects can be quickly determined by the information point matching model, thereby determining the matching result of the preset objects.

[0151] S2075: If the second preset target information does not have matching first preset information, the second information point corresponding to the second preset target information is determined as the information point to be updated.

[0152] In this embodiment of the application, the information points to be updated may include newly added information points in the second image, or isolated information points in the first image whose positional relationship cannot be determined. Since the positional relationship of isolated information points cannot be determined, this type of information point does not exist in the first information point relationship diagram.

[0153] In a specific embodiment, such as Figure 20 As shown, Figure 20 Example 1: Information point relationship diagram corresponding to different times; where T1, T2, and T3 are three different times, with T1 being the earliest time and T3 being the latest time; at time T1, there are four entities A, B, C, and D, and the relationship between the four entities is as follows: A is to the left of B, m units away; C is to the right of B, adjacent to B; D is to the right of C, adjacent to C; saving the relationship between A, B, C, and D is the spatial relationship.

[0154] At time T2, entities A, B, and D remain unchanged, but a new entity X is created between B and D, with X to the right of B and to the left of D. At time T1, C is to the right of B and to the left of D. Compared to time T2, entity C becomes entity X, indicating that C no longer exists, and a new point of interest (POI) is created at the location of C. Entity X, in addition to updating the spatial relationship between ABXD, can also establish the temporal relationship between AA, BB, CX, and DD. That is, the information point relationship graph at time T1 includes entities A, B, C, and D; the information point relationship graph at time T2 includes entities A, B, X, and D, and also includes an isolated entity E whose positional relationship cannot be identified; at time T3, the relationship between isolated entity E and entity D can be determined, therefore, the information point relationship graph at time T3 includes entities A, B, X, D, and E.

[0155] In a specific embodiment, such as Figure 21 As shown, Figure 21 Example 2 shows the relationship diagram of information points at different times; where, at time T2, entities E and F are isolated information points and do not belong to the relationship diagram of information points at time T2; at time T3, the positional relationship between entities E and F and entities D and E can be determined, so that an information point relationship diagram including entities E and F can be constructed.

[0156] In this embodiment of the application, the method further includes:

[0157] If the second preset target information has a matching first preset information, obtain the first information point corresponding to the matching first preset information as the first target information point;

[0158] Obtain the second information point corresponding to the second preset target information, and use it as the second target information point;

[0159] Based on the first target information point and the second target information point, an association relationship between the information points is constructed.

[0160] S209: Update the first information point relationship graph based on the information points to be updated.

[0161] In this embodiment, when there are multiple information points to be updated, the multiple information points to be updated can be updated synchronously according to the positional relationship between the multiple information points to be updated and other information points, so as to obtain the final updated information point relationship diagram at one time. This eliminates the need to update each information point sequentially, thereby improving the update efficiency of information points.

[0162] In the embodiments of this application, such as Figure 5 As shown, updating the relationship graph of the first information point based on the information point to be updated includes:

[0163] S2091: Determine the adjacent information points of the information point to be updated in the second information point relationship graph;

[0164] In this embodiment of the application, adjacent information points are those that have been successfully connected.

[0165] S2093: Based on the association relationship of the information points, determine the first target information point corresponding to the adjacent information point to obtain the adjacent target information point;

[0166] S2095: Based on the position of the adjacent target information points in the first information point relationship graph, determine the target position of the information point to be updated in the first information point relationship graph;

[0167] S2097: Update the first information point relationship graph based on the target location corresponding to the information point to be updated.

[0168] Specifically, in this embodiment of the application, updating the first information point relationship graph based on the target location corresponding to the information point to be updated includes:

[0169] Determine whether a corresponding first information point exists at the target location in the first information point relationship diagram;

[0170] If a corresponding first information point exists at the target location in the first information point relationship graph, the corresponding first information point is replaced with the information point to be updated to obtain an updated information point relationship graph.

[0171] In this embodiment of the application, if a corresponding first information point exists at the target location in the first information point relationship diagram, the first information point can be determined to be an expired information point and can be deleted.

[0172] In this embodiment of the application, the method further includes:

[0173] If there is no corresponding first information point at the target location in the first information point relationship graph, the information point to be updated is set at the target location to obtain an updated information point relationship graph.

[0174] If the target location in the first information point relationship diagram does not have a corresponding first information point, it means that the information point to be updated is an isolated information point or a non-existent information point in the first image.

[0175] In this embodiment of the application, the method further includes:

[0176] Based on the first information point relationship graph and the updated information point relationship graph, an information point location mapping relationship is constructed; the information point location mapping relationship represents the information points corresponding to the same location at the first time and the second time respectively;

[0177] Based on the information point location mapping relationship, new information points and information points to be removed are determined.

[0178] In this embodiment of the application, the information points to be filtered out are expired information points (expired POIs).

[0179] In this embodiment of the application, if the information points corresponding to the same location at the first time and the second time are different, the information points at the first time at the same location are determined as filtered information points, and the information points at the second time at the same location are determined as newly added information points;

[0180] If the information points corresponding to the same location are the same in the first time and the second time, it is determined that the information points corresponding to the same location are neither newly added information points nor filtered information points.

[0181] In the embodiments of this application, such as Figure 6 As shown, the method further includes:

[0182] S601: Based on the map data corresponding to the second image, determine the initial coordinate information of any second information point;

[0183] S603: Based on the updated information point relationship graph, determine the first positional relationship between any second information point and adjacent updated information points; the adjacent updated information points are the adjacent information points of any second information point in the updated information point relationship graph;

[0184] S605: Based on preset coordinate information, determine the second positional relationship between any second information point and the adjacent updated information point; the preset coordinate information includes the initial coordinate information and the coordinate information corresponding to the adjacent updated information point.

[0185] In this embodiment of the application, the coordinate information corresponding to the adjacent updated information points is information with a high degree of accuracy that has been confirmed, so that the coordinates of the second information point can be checked based on this information.

[0186] S607: If the first positional relationship does not match the second positional relationship, update the initial coordinate information of any second information point based on the coordinate information corresponding to the adjacent updated information points.

[0187] In the embodiments of this application, such as Figure 21 As shown, Figure 21 In the middle, entity F' is the coordinate point determined at time T2. At time T3, based on the positional relationships of entities D, E, and E, and entities E and F, a spatial relationship is established between entities D, E, and F, indicating that D, E, and F are adjacent in sequence. However, judging from the coordinates of entity F', the relationship between F and D and E conflicts, suggesting that the coordinates of F are incorrect. Therefore, entity F is moved to the right of entity E to correct its coordinates. This application can batch correct the coordinate offsets of POIs in the library, improving the coordinate accuracy.

[0188] In this embodiment of the application, the method further includes:

[0189] Based on the updated first information point relationship graph, the preset information point relationship graph is updated.

[0190] In this embodiment of the application, an updated preset information point relationship diagram can be obtained based on the updated diagram corresponding to the first information point relationship diagram in the preset information point relationship diagram.

[0191] Specifically, in the embodiments of this application, such as Figure 22 As shown, Figure 22 A flowchart of an information point update method, including:

[0192] (1) Determine the second image using preset data and perform store sign recognition to obtain the store sign entity;

[0193] (2) Based on the image corresponding to the store sign, perform OCR recognition and extract text features;

[0194] (3) Perform three-dimensional reconstruction on the second image to obtain the second information point relationship diagram;

[0195] (4) Based on the second information point relationship diagram and the corresponding first information point relationship diagram, perform text attachment;

[0196] (5) If the text is successfully attached, update the resume database according to the attachment result; the resume database stores the first information point relationship diagram.

[0197] (6) If text attachment fails, perform image attachment;

[0198] (7) If the connection is successful, update the resume database according to the connection result;

[0199] (8) If the connection fails, determine the adjacent information points corresponding to the information points that cannot be connected, and thus determine their corresponding spatial relationships;

[0200] (9) If all adjacent information points have accurate coordinate information, it can be determined that the information point has a reliable spatial relationship and the location information of the information point can be determined.

[0201] (10) Update the resume database based on the location information of the information point.

[0202] As can be seen from the technical solutions provided by the embodiments of this application above, the embodiments of this application obtain a second image corresponding to a target region at a second time; construct a second information point relationship graph based on the second image; the second information point relationship graph represents the positional relationship between each second information point in the second image; determine a first information point relationship graph based on the target region; the first information point relationship graph is constructed based on the positional relationship between each first information point in the first image, the first image being the image corresponding to the target region at a first time; the first time is earlier than the second time; determine the information points to be updated based on the first information point relationship graph and the second information point relationship graph; update the first information point relationship graph based on the information points to be updated. This application constructs information point relationship graphs at different times and determines the information points to be updated based on the relationship graphs at two times, thereby quickly identifying new and expired information points, and obtaining an updated information point relationship graph based on the information points to be updated, realizing fast and accurate updating of information points based on the correlation between information points.

[0203] This application also provides an information point updating device, such as... Figure 23 As shown, the device includes:

[0204] The second image acquisition module 2310 is used to acquire the second image of the target area at the second time.

[0205] The second relationship graph construction module 2320 is used to construct a second information point relationship graph based on the second image; the second information point relationship graph represents the positional relationship between each second information point in the second image;

[0206] The first relationship graph determination module 2330 is used to determine a first information point relationship graph based on the target region; the first information point relationship graph is constructed based on the positional relationship between each first information point in a first image, the first image being the image corresponding to the target region at a first time; the first time is earlier than the second time;

[0207] The module 2340 for determining information points to be updated is used to determine information points to be updated based on the first information point relationship diagram and the second information point relationship diagram.

[0208] The information point update module 2350 is used to update the first information point relationship diagram based on the information points to be updated.

[0209] In some embodiments, the second relationship graph construction module may include:

[0210] The second point cloud dataset construction submodule is used to perform three-dimensional reconstruction on the second image and construct the second point cloud dataset.

[0211] The second information point determination submodule is used to determine each second information point in the second image based on the second point cloud dataset;

[0212] The positional relationship determination submodule is used to determine the positional relationship between the second information points based on the second point cloud data corresponding to each second information point;

[0213] The second relationship graph construction submodule is used to construct the second information point relationship graph based on the positional relationship between the various second information points.

[0214] In some embodiments, the module for determining the information point to be updated may include:

[0215] The second preset information acquisition submodule is used to acquire the second preset information corresponding to each second information point in the second information point relationship diagram; the second preset information includes at least one of second preset text and second preset object.

[0216] The matching result determination submodule is used to determine the matching result between the second preset target information and the first preset information in the preset information point database; the second preset target information is any second preset information, and the preset information point database is generated based on the correspondence between the first information point and the first preset information in the first information point relationship graph; the first preset information includes at least one of the first preset text and the first preset object corresponding to the first image.

[0217] The submodule for determining information points to be updated is used to determine the second information point corresponding to the second preset target information as the information point to be updated if the second preset target information does not have matching first preset information.

[0218] In some embodiments, the apparatus may further include:

[0219] The first target information point determination module is used to obtain the first information point corresponding to the matching first preset information if the second preset target information has matching first preset information, and use it as the first target information point.

[0220] The second target information point determination module is used to obtain the second information point corresponding to the second preset target information, and use it as the second target information point;

[0221] The information point association construction module is used to construct information point associations based on the first target information point and the second target information point.

[0222] In some embodiments, the information point update module may include:

[0223] The adjacent information point determination submodule is used to determine the adjacent information points of the information point to be updated in the second information point relationship graph;

[0224] The adjacent target information point determination submodule is used to determine the first target information point corresponding to the adjacent information point based on the association relationship of the information points, so as to obtain the adjacent target information points;

[0225] The target location determination submodule is used to determine the target location of the information point to be updated in the first information point relationship graph based on the position of the adjacent target information points in the first information point relationship graph;

[0226] The information point update submodule is used to update the first information point relationship graph based on the target location corresponding to the information point to be updated.

[0227] In some embodiments, the information point update submodule may include:

[0228] The first information point judgment unit is used to determine whether there is a corresponding first information point at the target location in the first information point relationship diagram.

[0229] The information point replacement unit is used to replace the corresponding first information point with the information point to be updated if there is a corresponding first information point at the target location in the first information point relationship diagram, thereby obtaining an updated information point relationship diagram.

[0230] In some embodiments, the apparatus may further include:

[0231] The location mapping relationship construction module is used to construct information point location mapping relationships based on the first information point relationship graph and the updated information point relationship graph; the information point location mapping relationship represents the information points corresponding to the same location at the first time and the second time respectively;

[0232] The information point determination module is used to determine new information points and filter out information points based on the information point location mapping relationship.

[0233] In some embodiments, the apparatus may further include:

[0234] The initial coordinate information determination module is used to determine the initial coordinate information of any second information point based on the map data corresponding to the second image;

[0235] The first positional relationship determination module is used to determine the first positional relationship between any second information point and adjacent updated information points based on the updated information point relationship graph; the adjacent updated information points are the adjacent information points of any second information point in the updated information point relationship graph.

[0236] The second positional relationship determination module is used to determine the second positional relationship between any second information point and the adjacent updated information point based on preset coordinate information; the preset coordinate information includes the initial coordinate information and the coordinate information corresponding to the adjacent updated information point.

[0237] In some embodiments, the first preset information includes the first preset text and the first preset object; the device may further include:

[0238] The first database construction module is used to construct a first database based on the correspondence between each first information point and the first preset text in the first information point relationship diagram;

[0239] The second database construction module is used to construct a second database based on the correspondence between each first information point and the first preset object;

[0240] The preset information point database construction module is used to construct the preset information point database based on the first database and the second database.

[0241] In some embodiments, the second preset target information is a second preset target text, and the matching result determination submodule includes:

[0242] The first matching result determination unit is used to determine, based on the first database, a first preset text that matches the second preset target text, and obtain a first matching success result.

[0243] In some embodiments, the second preset target information includes a second preset target text and a second preset target object; the matching result determination submodule may include:

[0244] The second matching result determination unit is used to determine the first preset object that matches the second preset target object based on the second database if there is no first preset text that matches the second preset target text in the first database, and obtain the second matching success result.

[0245] In some embodiments, the apparatus further includes:

[0246] The first image acquisition module is used to acquire the first image corresponding to the target region at the first time.

[0247] The positional relationship determination module is used to determine the positional relationship between each first information point in the first image;

[0248] The first information point relationship graph construction module is used to construct the first information point relationship graph based on the positional relationship between the various first information points.

[0249] In some embodiments, the positional relationship determination module includes:

[0250] The first point cloud dataset construction submodule is used to perform three-dimensional reconstruction on the first image and construct the first point cloud dataset.

[0251] The first information point determination submodule is used to determine each first information point in the first image based on the first point cloud dataset;

[0252] The information point location relationship determination submodule is used to determine the location relationship between the first information points based on the first point cloud data corresponding to each first information point.

[0253] The apparatus and method embodiments described herein are based on the same inventive concept.

[0254] This application provides an information point update device, which includes a processor and a memory. The memory stores at least one instruction or at least one program, which is loaded and executed by the processor to implement the information point update method provided in the above method embodiments.

[0255] The embodiments of this application also provide a computer storage medium, which can be disposed in a terminal to store at least one instruction or at least one program related to implementing an information point update method in the method embodiments. The at least one instruction or at least one program is loaded and executed by the processor to implement the information point update method provided in the above method embodiments.

[0256] Embodiments of this application also provide a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the information point update method provided in the above-described method embodiments.

[0257] Optionally, in this embodiment, the storage medium may be located at at least one of the multiple network servers in a computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0258] The memory described in this application embodiment can be used to store software programs and modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, applications required for the functions, etc.; the data storage area may store data created according to the use of the device, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory may also include a memory controller to provide the processor with access to the memory.

[0259] The information point update method embodiments provided in this application can be executed on a mobile terminal, computer terminal, server, or similar computing device. Taking running on a server as an example, Figure 24 This is a hardware structure block diagram of a server for an information point update method provided in an embodiment of this application. For example... Figure 24As shown, the server 2400 can vary significantly due to different configurations or performance. It may include one or more Central Processing Units (CPUs) 2410 (CPUs 2410 may include, but are not limited to, microprocessors (MCUs) or programmable logic devices (FPGAs), a memory 2430 for storing data, and one or more storage media 2420 (e.g., one or more mass storage devices) for storing application programs 2423 or data 2422. The memory 2430 and storage media 2420 may be temporary or persistent storage. The program stored in the storage media 2420 may include one or more modules, each module may include a series of instruction operations on the server. Furthermore, the CPU 2410 may be configured to communicate with the storage media 2420 and execute the series of instruction operations stored in the storage media 2420 on the server 2400. Server 2400 may also include one or more power supplies 2460, one or more wired or wireless network interfaces 2450, one or more input / output interfaces 2440, and / or one or more operating systems 2421, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0260] The input / output interface 2440 can be used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of server 2400. In one example, the input / output interface 2440 includes a network interface controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the input / output interface 2440 may be a radio frequency (RF) module for wireless communication with the Internet.

[0261] Those skilled in the art will understand that Figure 24 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, server 2400 may also include... Figure 24 The more or fewer components shown, or having the same Figure 24 The different configurations shown.

[0262] As can be seen from the embodiments of the information point updating method, apparatus, device, or storage medium provided in this application, this application obtains a second image corresponding to a target region at a second time; constructs a second information point relationship diagram based on the second image; the second information point relationship diagram represents the positional relationship between each second information point in the second image; determines a first information point relationship diagram based on the target region; the first information point relationship diagram is constructed based on the positional relationship between each first information point in a first image, where the first image is the image corresponding to the target region at a first time; the first time is earlier than the second time; determines information points to be updated based on the first and second information point relationship diagrams; and updates the first information point relationship diagram based on the information points to be updated. This application constructs information point relationship diagrams at different times and determines information points to be updated based on the relationship diagrams at two times, thereby quickly identifying new and expired information points and obtaining an updated information point relationship diagram based on the information points to be updated, thus realizing fast and accurate updating of information points based on the correlation between information points.

[0263] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0264] 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 describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0265] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer storage medium, such as a read-only memory, a disk, or an optical disk.

[0266] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for updating information points, characterized in that, The method includes: Acquire a second image of the target area at the second time point; the second image is an entity image collected along the road. Perform 3D reconstruction on the second image to construct a second point cloud dataset; Based on the second point cloud dataset, determine each second information point in the second image; Based on the second point cloud data corresponding to each of the second information points, the positional relationship between the second information points is determined; Based on the positional relationships between the various second information points, a second information point relationship diagram is constructed; Based on the target region, a first information point relationship diagram is determined; the first information point relationship diagram is constructed based on the positional relationship between each first information point in the first image, the first image being the image corresponding to the target region at a first time; the first time is earlier than the second time. Obtain the second preset information corresponding to each second information point in the second information point relationship diagram; the second preset information includes second preset text and second preset object, the second preset object including a store sign image; Determine the matching result between the second preset target information and the first preset information in the preset information point database; the second preset target information is any second preset information, and the preset information point database is generated based on the correspondence between the first information point and the first preset information in the first information point relationship diagram; the first preset information includes the first preset text corresponding to the first image and the first preset object; If the second preset target information does not match the first preset information, the second information point corresponding to the second preset target information is determined as the information point to be updated; Based on the information points to be updated, update the relationship graph of the first information points.

2. The method according to claim 1, characterized in that, The method further includes: If the second preset target information has a matching first preset information, obtain the first information point corresponding to the matching first preset information as the first target information point; Obtain the second information point corresponding to the second preset target information, and use it as the second target information point; Based on the first target information point and the second target information point, an association relationship between the information points is constructed.

3. The method according to claim 2, characterized in that, The step of updating the first information point relationship graph based on the information point to be updated includes: Determine the adjacent information points of the information point to be updated in the second information point relationship graph; Based on the association relationship of the information points, the first target information point corresponding to the adjacent information point is determined, and the adjacent target information points are obtained; Based on the position of the adjacent target information points in the first information point relationship graph, determine the target position of the information point to be updated in the first information point relationship graph; The relationship graph of the first information point is updated based on the target location corresponding to the information point to be updated.

4. The method according to claim 3, characterized in that, The step of updating the first information point relationship graph based on the target location corresponding to the information point to be updated includes: Determine whether a corresponding first information point exists at the target location in the first information point relationship diagram; If a corresponding first information point exists at the target location in the first information point relationship graph, the corresponding first information point is replaced with the information point to be updated to obtain an updated information point relationship graph.

5. The method according to claim 4, characterized in that, The method further includes: Based on the first information point relationship graph and the updated information point relationship graph, an information point location mapping relationship is constructed; the information point location mapping relationship represents the information points corresponding to the same location at the first time and the second time respectively; Based on the information point location mapping relationship, new information points and information points to be removed are determined.

6. The method according to claim 4 or 5, characterized in that, The method further includes: Based on the map data corresponding to the second image, determine the initial coordinate information of any second information point; Based on the updated information point relationship graph, a first positional relationship between any second information point and an adjacent updated information point is determined; the adjacent updated information point is the information point adjacent to any second information point in the updated information point relationship graph. Based on preset coordinate information, a second positional relationship between any second information point and the adjacent updated information point is determined; the preset coordinate information includes the initial coordinate information and the coordinate information corresponding to the adjacent updated information point.

7. The method according to claim 1, characterized in that, The first preset information includes the first preset text and the first preset object; The method for constructing the preset information point database includes: Based on the correspondence between each first information point and the first preset text in the first information point relationship diagram, a first database is constructed; Based on the correspondence between each first information point and the first preset object, a second database is constructed; Based on the first database and the second database, the preset information point database is constructed.

8. The method according to claim 7, characterized in that, The second preset target information is the second preset target text. Determining the matching result between the second preset target information and the first preset information in the preset information point database includes: Based on the first database, a first preset text that matches the second preset target text is determined, and a first matching success result is obtained.

9. The method according to claim 7, characterized in that, The second preset target information includes the second preset target text and the second preset target object; The determination of the matching result between the second preset target information and the first preset information in the preset information point database includes: If there is no first preset text in the first database that matches the second preset target text, then based on the second database, a first preset object that matches the second preset target object is determined, and a second matching success result is obtained.

10. The method according to claim 1, characterized in that, The method for constructing the first information point relationship graph includes: Obtain the first image corresponding to the target region at the first time. Determine the positional relationship between each first information point in the first image; Based on the positional relationships between the various first information points, a relationship diagram of the first information points is constructed.

11. The method according to claim 10, characterized in that, Determining the positional relationship between each first information point in the first image includes: Perform 3D reconstruction on the first image to construct a first point cloud dataset; Based on the first point cloud dataset, determine each first information point in the first image; Based on the first point cloud data corresponding to each first information point, the positional relationship between each first information point is determined.

12. An information point updating device, characterized in that, The device includes: The second image acquisition module is used to acquire a second image of the target area at a second time; the second image is an entity image collected along the road. The second relationship graph construction module is used to perform three-dimensional reconstruction on the second image and construct a second point cloud dataset; based on the second point cloud dataset, determine each second information point in the second image; based on the second point cloud data corresponding to each second information point, determine the positional relationship between each second information point; and construct a second information point relationship graph based on the positional relationship between each second information point. The first relationship graph determination module is used to determine a first information point relationship graph based on the target region; the first information point relationship graph is constructed based on the positional relationship between each first information point in a first image, the first image being the image corresponding to the target region at a first time; the first time is earlier than the second time; The module for determining information points to be updated is used to determine information points to be updated based on the first information point relationship diagram and the second information point relationship diagram. The module includes: a second preset information acquisition submodule, used to acquire second preset information corresponding to each second information point in the second information point relationship diagram; the second preset information includes second preset text and a second preset object, the second preset object including a shop sign image; a matching result determination submodule, used to determine the matching result between the second preset target information and first preset information in the preset information point database; the second preset target information is any second preset information, the preset information point database is generated based on the correspondence between the first information point and the first preset information in the first information point relationship diagram; the first preset information includes first preset text and a first preset object corresponding to the first image; and the module for determining information points to be updated, used to determine the second information point corresponding to the second preset target information as the information point to be updated if the second preset target information does not have matching first preset information. The information point update module is used to update the first information point relationship diagram based on the information points to be updated.

13. The apparatus according to claim 12, characterized in that, The device further includes: The first target information point determination module is used to obtain the first information point corresponding to the matching first preset information if the second preset target information has matching first preset information, and use it as the first target information point. The second target information point determination module is used to obtain the second information point corresponding to the second preset target information, and use it as the second target information point; The information point association construction module is used to construct information point associations based on the first target information point and the second target information point.

14. The apparatus according to claim 13, characterized in that, The information point update module includes: The adjacent information point determination submodule is used to determine the adjacent information points of the information point to be updated in the second information point relationship graph; The adjacent target information point determination submodule is used to determine the first target information point corresponding to the adjacent information point based on the association relationship of the information points, so as to obtain the adjacent target information points; The target location determination submodule is used to determine the target location of the information point to be updated in the first information point relationship graph based on the position of the adjacent target information points in the first information point relationship graph; The information point update submodule is used to update the first information point relationship graph based on the target location corresponding to the information point to be updated.

15. The apparatus according to claim 14, characterized in that, The information point update submodule includes: The first information point judgment unit is used to determine whether there is a corresponding first information point at the target location in the first information point relationship diagram. The information point replacement unit is used to replace the corresponding first information point with the information point to be updated if there is a corresponding first information point at the target location in the first information point relationship diagram, thereby obtaining an updated information point relationship diagram.

16. The apparatus according to claim 15, characterized in that, The device further includes: The location mapping relationship construction module is used to construct information point location mapping relationships based on the first information point relationship graph and the updated information point relationship graph; the information point location mapping relationship represents the information points corresponding to the same location at the first time and the second time respectively; The information point determination module is used to determine new information points and filter out information points based on the information point location mapping relationship.

17. The apparatus according to claim 15 or 16, characterized in that, The device further includes: The initial coordinate information determination module is used to determine the initial coordinate information of any second information point based on the map data corresponding to the second image; The first positional relationship determination module is used to determine the first positional relationship between any second information point and adjacent updated information points based on the updated information point relationship graph; the adjacent updated information points are the adjacent information points of any second information point in the updated information point relationship graph. The second positional relationship determination module is used to determine the second positional relationship between any second information point and the adjacent updated information point based on preset coordinate information; the preset coordinate information includes the initial coordinate information and the coordinate information corresponding to the adjacent updated information point.

18. The apparatus according to claim 12, characterized in that, The first preset information includes the first preset text and the first preset object; the device further includes: The first database construction module is used to construct a first database based on the correspondence between each first information point and the first preset text in the first information point relationship diagram; The second database construction module is used to construct a second database based on the correspondence between each first information point and the first preset object; The preset information point database construction module is used to construct the preset information point database based on the first database and the second database.

19. The apparatus according to claim 18, characterized in that, The second preset target information is the second preset target text, and the matching result determination submodule includes: The first matching result determination unit is used to determine, based on the first database, a first preset text that matches the second preset target text, and obtain a first matching success result.

20. The apparatus according to claim 18, characterized in that, The second preset target information includes a second preset target text and a second preset target object; the matching result determination submodule includes: The second matching result determination unit is used to determine the first preset object that matches the second preset target object based on the second database if there is no first preset text that matches the second preset target text in the first database, and obtain the second matching success result.

21. The apparatus according to claim 12, characterized in that, The device further includes: The first image acquisition module is used to acquire the first image corresponding to the target region at the first time. The positional relationship determination module is used to determine the positional relationship between each first information point in the first image; The first information point relationship graph construction module is used to construct the first information point relationship graph based on the positional relationship between the various first information points.

22. The apparatus according to claim 21, characterized in that, The positional relationship determination module includes: The first point cloud dataset construction submodule is used to perform three-dimensional reconstruction on the first image and construct the first point cloud dataset. The first information point determination submodule is used to determine each first information point in the first image based on the first point cloud dataset; The information point location relationship determination submodule is used to determine the location relationship between the first information points based on the first point cloud data corresponding to each first information point.

23. An information point updating device, characterized in that, The device includes a processor and a memory, the memory storing at least one instruction or at least one program, the at least one instruction or at least one program being loaded and executed by the processor to implement the information point update method as described in any one of claims 1-11.

24. A computer program product, characterized in that, The computer program product includes computer instructions stored in a computer-readable storage medium, a processor of a computer device reading the computer instructions from the computer-readable storage medium, and the processor executing the computer instructions to cause the computer device to perform the information point update method as described in any one of claims 1-11.

25. A computer storage medium, characterized in that, The computer storage medium stores at least one instruction or at least one program, which is loaded and executed by a processor to implement the information point update method as described in any one of claims 1-11.

Images