Positioning fingerprint leak repairing method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a positioning fingerprint leak repairing method and device, computer equipment, a readable storage medium and a program product. The method comprises the following steps: acquiring fingerprint information of each grid of a positioning area, acquiring all emission main bodies corresponding to the fingerprint information, clustering effective grids corresponding to the current emission main body, and on a plane corresponding to the positioning area, taking a grid center of a missing grid as an original point, and performing data processing on the missing grid; acquiring an adjacent cluster center of an adjacent cluster closest to the missing grids in the target radius range, acquiring adjacent grids which have intersection points with connecting lines between the grid centers of the missing grids and the adjacent cluster center on the plane, acquiring missing signal intensity of the missing grids according to the number of the adjacent grids and signal intensity corresponding to the adjacent grids, and sending the missing signal intensity of the missing grids to the target radius range. And according to the missing signal intensity, complementing the fingerprint information of the missing grid. By adopting the method, the comprehensiveness of the fingerprint information can be improved, so that the positioning accuracy is improved.

Description

Technical Field

[0001] This application relates to the field of wireless communication technology, and in particular to a method, apparatus, computer equipment, readable storage medium, and program product for fingerprint location and error correction. Background Technology

[0002] Fingerprint positioning technology typically uses wireless signals such as mobile networks, WiFi, Bluetooth, and UWB as the fingerprint medium, and uses features such as the cell / AP and signal strength as characteristics, i.e., a location fingerprint. Fingerprint acquisition, which involves collecting wireless signal information at various locations within the positioning area, is a crucial step in fingerprint positioning. Fingerprint acquisition generally employs fixed-point acquisition, where receivers, smart terminals, and other acquisition devices are used at fixed locations to receive and record downlink cell / AP information, signal strength, and other information, and then correlate this information with the location to form a positioning fingerprint.

[0003] Due to performance issues with the data collection equipment, especially when using smart terminals instead of professional receivers, the equipment often misses signals emitted by a certain MAC address of a 4G / 5G cell (neighboring cell), WiFi, or Bluetooth access point that actually has coverage at various locations. This results in information omissions during fingerprint construction, leading to significant positioning errors. Summary of the Invention

[0004] Therefore, it is necessary to provide a positioning fingerprint replacement method, device, computer equipment, readable storage medium, and program product that can improve positioning accuracy in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a method for identifying missing fingerprints, including:

[0006] The fingerprint information of each grid in the positioning area is obtained, and all transmitting entities corresponding to the fingerprint information are obtained; the fingerprint information includes the signal strength of the wireless signal received within the grid.

[0007] Cluster the valid grids corresponding to the current transmitting entity; valid grids are those located within the target area and whose corresponding fingerprint information contains the signal strength corresponding to the current transmitting entity.

[0008] On the plane corresponding to the positioning area, with the center of the missing grid as the origin, obtain the center of the nearest neighbor cluster to the missing grid within the target radius; the missing grid is the grid located within the target area and whose fingerprint information does not contain the signal strength corresponding to the current transmitting subject;

[0009] Find the adjacent rasters on the plane that have an intersection point between the line connecting the center of the missing raster and the center of the nearest cluster; the adjacent rasters are those that are adjacent to the missing raster on the plane.

[0010] Based on the number of adjacent grids and the signal strength corresponding to the adjacent grids, the missing signal strength of the missing grid is obtained, and the fingerprint information of the missing grid is completed based on the missing signal strength.

[0011] In one embodiment, the step of clustering the valid grids corresponding to the current transmitting entity includes:

[0012] Obtain the area of ​​the target region, and based on the area, determine the number of antenna points of the current transmitting entity within the target region;

[0013] Cluster the effective grids corresponding to the current transmitting entity to obtain multiple clusters corresponding to the current transmitting entity; the number of clusters corresponding to the current transmitting entity is the same as the number of antenna points.

[0014] In one embodiment, the step of obtaining the missing signal intensity of a missing grid based on the number of adjacent grids and the signal intensity corresponding to the adjacent grids includes:

[0015] If at least two adjacent grids are valid grids, the average signal strength of the adjacent grids is taken as the missing signal strength of the missing grid.

[0016] When only one adjacent grid is a valid grid, the missing signal intensity of the missing grid is obtained based on the distance between the adjacent grid and the center of the neighboring cluster and the signal intensity corresponding to the adjacent grid.

[0017] In the absence of adjacent grids, the missing signal intensity of the missing grid is obtained based on the signal intensity corresponding to the candidate grid. The candidate grid is the effective grid that intersects with the line connecting the grid center and the neighboring cluster center and is closest to the neighboring cluster center.

[0018] In one embodiment, the step of obtaining the missing signal intensity of a missing grid based on the distance between adjacent grids and the centers of neighboring clusters and the signal intensity corresponding to the adjacent grids includes:

[0019] Obtain the first distance between the center of an adjacent raster and the center of a neighboring cluster, and the second distance between the center of a missing raster and the center of a neighboring cluster, respectively.

[0020] Based on the difference between the first distance and the second distance, a first adjustment value is obtained. The signal strength of the adjacent grid is adjusted according to the first adjustment value to obtain the missing signal strength of the missing grid.

[0021] In one embodiment, the step of obtaining the missing signal intensity of the missing grid based on the signal intensity corresponding to the candidate grid includes:

[0022] Obtain the number of interval grid cells between the missing grid cells and the candidate grid cells, and obtain the second adjustment value based on the number of interval grid cells;

[0023] Adjust the signal strength corresponding to the candidate grid according to the second adjustment value to obtain the missing signal strength of the missing grid.

[0024] In one embodiment, the method further includes:

[0025] In the case of at least two neighboring clusters, obtain the reference missing signal intensity based on the center of the neighboring cluster for each neighboring cluster;

[0026] The maximum value among the reference missing signal intensities or the average value of all reference missing signal intensities is taken as the missing signal intensity of the missing grid.

[0027] Secondly, this application also provides a fingerprint positioning and replacement device, comprising:

[0028] The fingerprint acquisition module is used to acquire fingerprint information of each grid in the positioning area and to acquire all transmitting entities corresponding to the fingerprint information; the fingerprint information includes the signal strength of the wireless signal received within the grid.

[0029] The grid clustering module is used to cluster the valid grids corresponding to the current transmitting subject; the valid grids are those located within the target area and whose corresponding fingerprint information contains the signal strength corresponding to the current transmitting subject;

[0030] The cluster center acquisition module is used to acquire the nearest cluster center of the nearest neighboring cluster within the target radius of the plane corresponding to the positioning area, with the center of the missing grid as the origin; the missing grid is a grid located within the target area and whose fingerprint information does not contain the signal strength corresponding to the current transmitting subject;

[0031] The adjacent acquisition module is used to acquire adjacent rasters on the plane that have an intersection point between the line connecting the center of the missing raster and the center of the neighboring cluster; an adjacent raster is a raster that is adjacent to the missing raster on the plane;

[0032] The fingerprint completion module is used to obtain the missing signal intensity of the missing grid based on the number of adjacent grids and the signal intensity corresponding to the adjacent grids, and to complete the fingerprint information of the missing grid based on the missing signal intensity.

[0033] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement any of the method steps in the first aspect.

[0034] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any one of the method steps in the first aspect.

[0035] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements any of the method steps in the first aspect.

[0036] The aforementioned fingerprinting method, apparatus, computer equipment, readable storage medium, and program product acquire fingerprint information of each grid in the positioning area and all transmitting entities corresponding to the fingerprint information. They then cluster the valid grids corresponding to the current transmitting entity. On the plane corresponding to the positioning area, with the center of the missing grid as the origin, they acquire the nearest neighbor cluster center within the target radius that is closest to the missing grid. They also acquire adjacent grids on the plane that intersect the lines connecting the center of the missing grid and the nearest neighbor cluster center. Based on the number of adjacent grids and the signal strength corresponding to the adjacent grids, they acquire the missing signal strength of the missing grid and, based on the missing signal strength, complete the fingerprint information of the missing grid. This effectively supplements the location point fingerprint information for each position, constructing a complete fingerprint database, thereby improving positioning accuracy. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is a diagram illustrating the application environment of a fingerprint identification and leak repair method in one embodiment.

[0039] Figure 2 This is a flowchart illustrating a fingerprint identification and patching method in one embodiment;

[0040] Figure 3 This is a schematic diagram of the grid distribution of the positioning area in one embodiment;

[0041] Figure 4 This is a flowchart illustrating the fingerprint identification and repair method in another embodiment;

[0042] Figure 5 This is a structural block diagram of a fingerprint identification and repair device in one embodiment;

[0043] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0044] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0045] The fingerprint localization and gap filling method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or placed in the cloud or on another network server. Terminal 102 is used to acquire fingerprint information of each grid in the positioning area, acquire all transmitting entities corresponding to the fingerprint information, cluster the valid grids corresponding to the current transmitting entity, and, on the plane corresponding to the positioning area, with the center of the missing grid as the origin, acquire the nearest neighbor cluster center of the nearest neighbor cluster within the target radius that is closest to the missing grid. It also acquires adjacent grids on the plane that intersect the lines connecting the center of the missing grid and the nearest neighbor cluster center. Based on the number of adjacent grids and the signal strength corresponding to the adjacent grids, it acquires the missing signal strength of the missing grid and completes the fingerprint information of the missing grid based on the missing signal strength. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, drones, low-altitude aircraft, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, and projection equipment. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted displays. Head-mounted displays can be virtual reality (VR) devices, augmented reality (AR) devices, and smart glasses. Server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0046] To facilitate understanding, before introducing specific embodiments of the present invention, the technical terms involved in the present invention will be explained:

[0047] AP: Access Point; the core transmitting entity under the WiFi technology standard, uniquely identified by its MAC address, and the strength of its emitted wireless signal is a key feature of WiFi-based location fingerprinting.

[0048] RSRP: Reference Signal Receiving Power; a signal strength indicator used in 5G / 4G cellular cells.

[0049] RSSI: Received Signal Strength Indicator, the physical channel between the device and the reader; a signal strength indicator used for WiFi and Bluetooth devices, and a core feature of WiFi / Bluetooth location fingerprinting.

[0050] SINR: Signal to Interference plus Noise Ratio, the physical channel between the reader and the device; an indicator reflecting the signal quality of 5G / 4G cellular cells (the ratio of signal strength to interference and noise), which, together with RSRP, constitutes the key parameters of cellular fingerprints;

[0051] MAC: Media Access Control Address; a hardware address used to uniquely identify WiFi APs (wireless access points) and Bluetooth beacons, and is the core identifier that distinguishes different WiFi / Bluetooth transmitters.

[0052] ARFCN: Absolute Radio Frequency Channel Number; used to identify the operating frequency of 5G / 4G cells, and together with CI and PCI, it forms the unique identifier of a 5G / 4G cell;

[0053] CI: Cell Identity; a unique identifier for 5G / 4G cellular cells (within a specific network range), which, in conjunction with ARFCN and PCI, enables precise differentiation of individual 5G / 4G transmitters.

[0054] PCI: Physical Cell Identity; the physical layer identifier of 5G / 4G cellular cells, used by terminals to identify reference signals of different cells, and together with ARFCN and CI, constitutes the unique identifier of a cell.

[0055] K-means: K-means Clustering Algorithm; used for clustering signal data (such as RSRP, RSSI) in valid grids, the number of clusters K needs to be specified in advance;

[0056] DBSCAN: Density-Based Spatial Clustering of Applications with Noise; a clustering algorithm that does not require pre-specifying the number of clusters, can automatically identify clusters of arbitrary shapes and noise points (invalid grids), and is suitable for scenarios with irregular signal distribution;

[0057] Mean Shift: Mean Shift Clustering Algorithm; it does not require specifying the number of clusters, finds the cluster center through density peaks, can identify clusters of arbitrary shapes, and has a certain degree of robustness to noise.

[0058] In one exemplary embodiment, such as Figure 2 As shown, a method for fingerprint localization and gap filling is provided, which can be applied to... Figure 1 Taking terminal 102 as an example, the explanation includes the following steps 202 to 210. Wherein:

[0059] S202: Obtain fingerprint information of each grid in the positioning area, and obtain all transmitting entities corresponding to the fingerprint information; the fingerprint information includes the signal strength of the wireless signal received within the grid.

[0060] Optionally, a grid refers to the smallest unit of location that divides the positioning area into fixed-size units. The fingerprint information of each grid represents the signal strength of the transmitting entity received at that location, such as the RSRP of a 5G cell or the RSSI of WiFi. All transmitting entities in the positioning area are obtained based on the fingerprint information. Here, a transmitting entity refers to the source emitting these wireless signals. Transmitting entities are categorized according to the wireless communication technology standard to which the wireless signal belongs. Transmitting entities of different technology standards have different signal characteristics and identification rules. After classification by technology standard, the corresponding signal data can be accurately extracted from the grid fingerprint for each type of transmitting entity, avoiding signal confusion between different standards. For example, 5G and 4G cells are typically defined by frequency (ARFCN), CI, PCI, etc. WiFi or Bluetooth beacons are generally defined by the MAC address of the access point or beacon.

[0061] S204: Cluster the valid grids corresponding to the current transmitting entity; the valid grids are those located within the target area and whose corresponding fingerprint information contains the signal strength corresponding to the current transmitting entity.

[0062] Optionally, clustering is performed on the effective grids of the current transmitting entity, such as a 5G cell or the MAC address of a WiFi network. An effective grid refers to a grid within the location area whose fingerprint information contains the signal strength of the current transmitting entity, i.e., a grid whose signal was successfully acquired by the acquisition device. The signal strength of these effective grids is processed using clustering algorithms (such as K-means or DBSCAN) to obtain multiple clusters (i.e., groups of grids with similar signal strength and spatially concentrated areas), with the center of each cluster called the cluster center. The number of clusters matches the number of antenna points of the current transmitting entity. For example, for a 5G / 4G cell, if the number of antennas is unknown, it is estimated using the layer area / (3.14 × 15²) × 110%, and then fine-tuned based on the clustering results. For a WiFi / Bluetooth transmitting entity, the number of antenna points is fixed at 1 (single antenna per device), so only one cluster is formed. The cluster center represents the area where the signal of the current transmitting entity is strongest and most concentrated.

[0063] S206: On the plane corresponding to the positioning area, with the center of the missing grid as the origin, obtain the center of the nearest neighboring cluster within the target radius that is closest to the missing grid; the missing grid is a grid located within the target area and whose fingerprint information does not contain the signal strength corresponding to the current transmitting subject.

[0064] Optionally, a missing grid refers to a grid within the positioning area where the fingerprint information does not contain the signal strength of the current transmitting subject, i.e., a grid whose signal was missed by the acquisition device. The target radius is determined by the 5G / 4G antenna power, wireless propagation model, or actual measurement. Using the center of the missing grid as the origin, draw a circle with a radius equal to the target radius on the plane of the positioning area. Find the cluster center closest to the missing grid within this circle, i.e., the neighboring cluster center. Since the signal attenuates outward from the cluster center (approximately the antenna), the signal from the missing grid should have a distance-attenuation correlation with the signal from the neighboring cluster center.

[0065] S208: Obtain the adjacent rasters on the plane that have an intersection point between the line connecting the center of the missing raster and the center of the neighboring cluster; the adjacent rasters are the rasters that are adjacent to the missing raster on the plane.

[0066] Optionally, adjacent graticles refer to graticles that are physically adjacent to the missing graticle. The intersection of the lines is the line connecting the center of the missing graticle and the center of the neighboring cluster (or). If a line passes through the region of an adjacent graticle, then that adjacent graticle is considered an adjacent graticle with an intersection point. Among all the adjacent graticles of the missing graticle, graticles that are passed through by the line connecting the missing graticle and the center of the neighboring cluster are selected. The signals of these graticles have similar propagation paths to the signals of the missing graticle, have the strongest signal correlation, and best reflect the signal characteristics of the missing graticle, thus avoiding interference from unrelated graticles in the calculation results.

[0067] S210: Based on the number of adjacent grids and the signal strength corresponding to the adjacent grids, obtain the missing signal strength of the missing grid, and complete the fingerprint information of the missing grid based on the missing signal strength.

[0068] Optionally, since the physical distance between adjacent grids is extremely short, the wireless signal will not change abruptly over a short distance (in unobstructed conditions, the signal strength difference between adjacent locations is typically only 1-2 dB). Therefore, the signal strength of adjacent grids can be used as a direct reference for the signal of the missing grid. As the signal propagates outward from the cluster center (approximately the antenna position of the transmitting main body), it attenuates with increasing distance. Therefore, the missing signal strength of the missing grid can be estimated based on the number of adjacent grids and their signal strengths. For example, when two adjacent grids have values, the two grids are located on either side of the signal propagation path of the missing grid. Taking the average value can compensate for the random error of a single grid, more closely approximating the true signal of the missing grid.

[0069] In the aforementioned fingerprint gap filling method, fingerprint information of each grid in the positioning area is obtained, along with all transmitting entities corresponding to the fingerprint information. The effective grids corresponding to the current transmitting entity are clustered. On the plane corresponding to the positioning area, with the center of the missing grid as the origin, the nearest neighbor cluster center within the target radius is obtained. Adjacent grids on the plane that intersect the lines connecting the center of the missing grid and the nearest neighbor cluster center are also obtained. Based on the number of adjacent grids and the signal strength corresponding to the adjacent grids, the missing signal strength of the missing grid is obtained. Based on the missing signal strength, the fingerprint information of the missing grid is filled in. This effectively supplements the location point fingerprint information for each position, constructing a complete fingerprint database, thereby improving positioning accuracy.

[0070] In an exemplary embodiment, the step of clustering the effective grid corresponding to the current transmitting entity includes: obtaining the area of ​​the target region, obtaining the number of antenna points of the current transmitting entity in the target region based on the area; clustering the effective grid corresponding to the current transmitting entity to obtain multiple clusters corresponding to the current transmitting entity; the number of clusters corresponding to the current transmitting entity is the same as the number of antenna points.

[0071] Optionally, the area of ​​the target region is determined, for example, the area of ​​a certain layer of the location area. Based on the technology of the transmitting entity, the number of antenna points within the target region is calculated, i.e., the number of hardware antennas deployed for transmitting signals. If the current transmitting entity is a 5G / 4G cell, and the actual number of antenna points is unknown, it is estimated based on the layer area, and can be fine-tuned later based on the actual clustering results. If it is a WiFi / Bluetooth device, the number of antenna points is fixed at 1, and no additional calculation is needed. Here, an effective grid refers to a grid in the fingerprint information of the target region that contains the signal strength of the current transmitting entity. Clustering algorithms, such as K-means, DBSCAN, and MeanShift, are used to cluster the signal strength data (such as RSRP and RSSI) and spatial location of the effective grids. Effective grids with similar signal strength and concentrated spatial distribution are grouped into a cluster, i.e., the core area of ​​signal coverage. The clustering parameters are adjusted so that the final number of clusters perfectly matches the number of antenna points. For example, if the estimated number of antenna points for a 5G cell is 3, then 3 clusters are needed after clustering; if the number of antenna points for a WiFi device is 1, then only 1 cluster is needed after clustering.

[0072] In this embodiment, by clustering the effective grids corresponding to the current transmitting subject according to the number of antenna points, the number of clusters corresponding to the current transmitting subject is the same as the number of antenna points. This ensures that the center of each cluster accurately corresponds to an actual signal source, avoiding the cluster center from deviating from the real antenna due to the deviation in the number of clusters, thereby improving the accuracy of subsequent fingerprinting.

[0073] In an exemplary embodiment, the step of obtaining the missing signal intensity of a missing grid based on the number of adjacent grids and the signal intensity corresponding to the adjacent grids includes: when there are at least two adjacent grids as valid grids, taking the average signal intensity of the adjacent grids as the missing signal intensity of the missing grid; when there is only one adjacent grid as a valid grid, obtaining the missing signal intensity of the missing grid based on the distance between the adjacent grid and the neighboring cluster center and the signal intensity corresponding to the adjacent grid; when there are no adjacent grids, obtaining the missing signal intensity of the missing grid based on the signal intensity corresponding to the candidate grid; the candidate grid is a valid grid that intersects with the line connecting the grid center and the neighboring cluster center and is closest to the neighboring cluster center.

[0074] Optionally, if the line passes through two grids adjacent to the missing grid, and at least two of the physically adjacent grids of the missing grid are valid grids (i.e., the fingerprint information contains the signal strength of the current transmitting subject), then since the adjacent grids are physically very close to the missing grid, and the two valid adjacent grids are usually located on both sides of the line connecting the missing grid and the center of the neighboring cluster, their signal strength can reflect the signal level of the missing grid. By averaging the two adjacent grids, the random error of a single valid grid can be offset, resulting in a closer approximation of the true signal of the missing grid.

[0075] When the connection passes through only one adjacent valid grid, the nearest cluster center is the core region where the current transmitting signal is strongest. The signal attenuates with distance as it propagates outward from the cluster center (default attenuation is 1dB per meter). It is necessary to first determine which is closer to the nearest cluster center, the valid adjacent grid or the missing grid, and then adjust the signal strength according to the attenuation pattern. If the valid adjacent grid is closer to the nearest cluster center than the missing grid, and the missing grid is farther from the signal source and has a weaker signal, then the missing signal strength is the valid adjacent grid signal strength - 1dB (attenuation per grid). If the valid adjacent grid is farther from the nearest cluster center than the missing grid, and the missing grid is closer to the signal source and has a stronger signal, then the missing signal strength is the valid adjacent grid signal strength + 1dB (attenuation per grid).

[0076] If no adjacent valid grids exist on the connection line, the candidate grid closest to the cluster center is selected from all neighboring grids of the missing grid. In this case, the signal attenuates along the path from the cluster center to the candidate grid to the missing grid, and the attenuation magnitude is proportional to the number of grids between the candidate grid and the missing grid. Therefore, the missing signal strength is the candidate grid signal strength minus (unit grid attenuation value × grid distance between the candidate grid and the missing grid), where the default unit attenuation is 1 dB, and the grid distance is the number of physical intervals between two grids.

[0077] For example, such as Figure 3 As shown, it is understandable that Figure 3 This is merely an example of the grid distribution of the positioning area for ease of understanding and does not represent the actual coverage area or the actual grid range of the positioning area. Figure 3 In the diagram, the positioning area is divided into multiple grids. For the current transmitting entity, the grids represented by solid lines are valid grids, and their signal strengths are shown in the data in the figure. The grids represented by dashed lines are missing grids A, B, and C. For missing grids A and B, there is a neighboring cluster center X1; for missing grid C, there is a neighboring cluster center X2.

[0078] For the missing grid A, there are no adjacent valid grids that intersect the line connecting the grid center point and the nearest cluster center X1. Therefore, the nearest valid grid on the line that is closest to the cluster center X1 is obtained as a candidate grid (i.e. -66dBm). The number of grids between the candidate grid and the missing grid is 2. Then the second adjustment value is -2dB. At this time, the calculated missing signal strength of the missing grid A is -66+(-2)=-68dBm.

[0079] For the missing grid B, the line connecting the grid center point and the adjacent cluster center X1 passes through two adjacent valid grids (i.e., -68dBm and -69dBm). Therefore, the missing signal strength of the missing grid B is (-68+-68) / 2=-68dBm.

[0080] For the missing grid C, the line connecting the grid center point and the adjacent cluster center X2 passes through one adjacent valid grid (i.e., -65dBm), and the distance between the missing grid and the adjacent valid grid is 1. Then the first adjustment amount is -1dB, and the missing signal strength of the missing grid C is -65+(-1)=-66dBm.

[0081] In this embodiment, by obtaining the signal strength of the missing grid based on the adjacent grids, the accuracy of the signal strength can be improved, and the location point fingerprint information can be effectively supplemented for each location.

[0082] In an exemplary embodiment, the step of obtaining the missing signal intensity of a missing grid based on the distance between adjacent grids and the centers of neighboring clusters and the signal intensity corresponding to adjacent grids includes: obtaining a first distance between the grid center of an adjacent grid and the center of a neighboring cluster and a second distance between the grid center of a missing grid and the center of a neighboring cluster, respectively; obtaining a first adjustment value based on the difference between the first distance and the second distance; and adjusting the signal intensity corresponding to the adjacent grids based on the first adjustment value to obtain the missing signal intensity of the missing grid.

[0083] Optionally, the neighboring cluster center is the region where the current transmitting main signal is strongest and most concentrated, approximating the signal source. The first distance refers to the straight-line distance from the center of the adjacent valid grid to the neighboring cluster center, and the second distance refers to the straight-line distance from the center of the missing grid to the neighboring cluster center. By using a rasterized map of the location area, the distances from the adjacent valid grid and the missing grid to the neighboring cluster center are obtained, resulting in the first and second distances. A corresponding fixed attenuation value is obtained based on the distance difference, and the signal strength of the adjacent valid grid is corrected to obtain the missing signal strength.

[0084] In this embodiment, by obtaining the missing signal intensity of the missing grid based on the distance between the adjacent grid and the center of the neighboring cluster and the signal intensity corresponding to the adjacent grid, the missing signal intensity can be accurately obtained, and the location point fingerprint information can be effectively supplemented for each location to build a complete fingerprint database, thereby improving the positioning accuracy.

[0085] In an exemplary embodiment, the step of obtaining the missing signal intensity of a missing grid based on the signal intensity corresponding to a candidate grid includes: obtaining the number of interval grids between the missing grid and the candidate grid; obtaining a second adjustment value based on the number of interval grids; and adjusting the signal intensity corresponding to the candidate grid based on the second adjustment value to obtain the missing signal intensity of the missing grid.

[0086] Optionally, in the location area grid map, along the line connecting the nearest cluster center → candidate grid → missing grid, the number of grids between the missing grid and the candidate grid is obtained, and a second adjustment value is obtained based on the number of grids. Assuming a unit grid spacing of 1 meter corresponds to 1dB attenuation, the second adjustment value = -(number of grids N × unit grid attenuation value). Here, the negative sign represents that the signal attenuates with increasing distance as it propagates from the candidate grid to the missing grid. Since the candidate grid and the missing grid are on the same signal propagation path, the signal of the missing grid is the result of the candidate grid signal attenuating after N grids; therefore, the second adjustment value is needed to correct the candidate grid signal strength.

[0087] In this embodiment, by adjusting the signal strength corresponding to the candidate grid according to the second adjustment value, the missing signal strength of the missing grid can be obtained. This allows for accurate acquisition of the missing signal strength, effective supplementation of location point fingerprint information for each location, and construction of a complete fingerprint database, thereby improving positioning accuracy.

[0088] In an exemplary embodiment, the method further includes: when there are at least two neighboring clusters, obtaining reference missing signal intensities based on the centers of neighboring clusters for each neighboring cluster; and using the maximum value of the reference missing signal intensities or the average value of all reference missing signal intensities as the missing signal intensity of the missing grid.

[0089] Optionally, when filtering neighboring clusters of a missing grid, one or two neighboring clusters can be selected based on their distance. When selecting at least two neighboring clusters, for each neighboring cluster center, a reference missing signal intensity based on the number of adjacent grids on the line connecting the missing grid center and that neighboring cluster center is obtained. For the multiple obtained reference missing signal intensities, the final missing signal intensity is obtained by taking the maximum or average value.

[0090] In this embodiment, by obtaining the reference missing signal intensity based on the neighboring cluster centers of each neighboring cluster, and using the maximum value of the reference missing signal intensity or the average value of all reference missing signal intensities as the missing signal intensity of the missing grid, the random error of estimating a single cluster center can be avoided, and the accuracy of the missing signal intensity can be improved.

[0091] In one exemplary embodiment, such as Figure 4As shown, a method for locating and filling fingerprint gaps is provided, which includes the following steps:

[0092] (1) Fingerprint information acquisition: acquire fingerprint information of each grid in the positioning area, and acquire all transmitting entities corresponding to the fingerprint information; the fingerprint information includes the signal strength of the wireless signal received in the grid.

[0093] (2) Effective grid clustering: Obtain the area of ​​the target region, and obtain the number of antenna points of the current transmitting subject within the target region based on the area; cluster the effective grids corresponding to the current transmitting subject to obtain multiple clusters corresponding to the current transmitting subject; the number of clusters corresponding to the current transmitting subject is the same as the number of antenna points. Among them, the effective grid is the grid located within the target region and the corresponding fingerprint information contains the signal strength corresponding to the current transmitting subject.

[0094] (3) Acquisition of neighboring cluster centers: On the plane corresponding to the positioning area, with the center of the missing grid as the origin, acquire the nearest neighbor cluster center of the nearest neighbor cluster within the target radius that is closest to the missing grid; the missing grid is a grid located within the target area and whose fingerprint information does not contain the signal strength corresponding to the current transmitting subject.

[0095] (4) Acquiring adjacent graticles: Acquire adjacent graticles on the plane that have an intersection point between the line connecting the center of the missing graticle and the center of the neighboring cluster; adjacent graticles are graticles that are adjacent to the missing graticle on the plane.

[0096] (5) Fingerprint information omission: When at least two adjacent grids are valid grids, the average signal strength of the adjacent grids is taken as the missing signal strength of the missing grid. When only one adjacent grid is valid, the first distance between the grid center of the adjacent grid and the center of the neighboring cluster and the second distance between the grid center of the missing grid and the center of the neighboring cluster are obtained respectively. Based on the difference between the first distance and the second distance, a first adjustment value is obtained, and the signal strength of the adjacent grid is adjusted according to the first adjustment value to obtain the missing signal strength of the missing grid. When no adjacent grids exist, the number of grids between the missing grid and the candidate grid is obtained, and a second adjustment value is obtained based on the number of grids between them. The signal strength of the candidate grid is adjusted according to the second adjustment value to obtain the missing signal strength of the missing grid. Among them, the candidate grid is the valid grid that intersects with the line connecting the grid center and the center of the neighboring cluster and is closest to the center of the neighboring cluster. When at least two neighboring clusters exist, obtain the reference missing signal intensity based on the center of each neighboring cluster. Use the maximum value of the reference missing signal intensity or the average value of all reference missing signal intensities as the missing signal intensity of the missing grid. Complete the fingerprint information of the missing grid based on the missing signal intensity.

[0097] In this embodiment, by acquiring the fingerprint information of each grid in the positioning area and all transmitting entities corresponding to the fingerprint information, the effective grids corresponding to the current transmitting entity are clustered. On the plane corresponding to the positioning area, with the grid center of the missing grid as the origin, the nearest neighbor cluster center of the nearest neighbor cluster within the target radius is acquired. The adjacent grids that intersect the lines connecting the grid center of the missing grid and the neighbor cluster center on the plane are acquired. Based on the number of adjacent grids and the signal strength corresponding to the adjacent grids, the missing signal strength of the missing grid is acquired. Based on the missing signal strength, the fingerprint information of the missing grid is completed. This can effectively supplement the location point fingerprint information at each location, construct a complete fingerprint database, and thus improve the positioning accuracy.

[0098] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0099] Based on the same inventive concept, this application also provides a fingerprint positioning and replacement device for implementing the aforementioned fingerprint positioning and replacement method. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more embodiments of the fingerprint positioning and replacement device provided below can be found in the limitations of the fingerprint positioning and replacement method described above, and will not be repeated here.

[0100] In one exemplary embodiment, such as Figure 5 As shown, a fingerprint positioning and gap-filling device is provided, comprising: a fingerprint acquisition module 10, a grid clustering module 20, a cluster center acquisition module 30, an adjacent acquisition module 40, and a fingerprint completion module 50, wherein:

[0101] The fingerprint acquisition module 10 is used to acquire fingerprint information of each grid in the positioning area and acquire all transmitting entities corresponding to the fingerprint information; the fingerprint information includes the signal strength of the wireless signal received in the grid.

[0102] The grid clustering module 20 is used to cluster the valid grids corresponding to the current transmitting subject; the valid grids are grids located within the target area and whose corresponding fingerprint information contains the signal strength corresponding to the current transmitting subject.

[0103] The cluster center acquisition module 30 is used to acquire the nearest neighbor cluster center of the nearest neighbor cluster within the target radius of the plane corresponding to the positioning area, with the center of the missing grid as the origin; the missing grid is a grid located within the target area and whose fingerprint information does not contain the signal strength corresponding to the current transmitting subject.

[0104] The adjacent acquisition module 40 is used to acquire adjacent graticles that intersect with the line connecting the center of the missing graticle and the center of the neighboring cluster on the plane; the adjacent graticles are graticles that are adjacent to the missing graticle on the plane.

[0105] The fingerprint completion module 50 is used to obtain the missing signal intensity of the missing grid based on the number of adjacent grids and the signal intensity corresponding to the adjacent grids, and to complete the fingerprint information of the missing grid based on the missing signal intensity.

[0106] In an exemplary embodiment, the grid clustering module 20 is further configured to obtain the area of ​​the target region, obtain the number of antenna points of the current transmitting subject in the target region based on the area; cluster the effective grids corresponding to the current transmitting subject to obtain multiple clusters corresponding to the current transmitting subject; the number of clusters corresponding to the current transmitting subject is the same as the number of antenna points.

[0107] In an exemplary embodiment, the fingerprint completion module 50 is further configured to: when at least two adjacent grids are valid grids, use the average signal intensity of the adjacent grids as the missing signal intensity of the missing grid; when only one adjacent grid is valid grid, obtain the missing signal intensity of the missing grid based on the distance between the adjacent grid and the neighboring cluster center and the signal intensity corresponding to the adjacent grid; when no adjacent grid exists, obtain the missing signal intensity of the missing grid based on the signal intensity corresponding to the candidate grid; the candidate grid is a valid grid that intersects with the line connecting the grid center and the neighboring cluster center and is closest to the neighboring cluster center.

[0108] In an exemplary embodiment, the fingerprint completion module 50 is further configured to obtain a first distance between the center of an adjacent grid and the center of a neighboring cluster, and a second distance between the center of a missing grid and the center of a neighboring cluster; obtain a first adjustment value based on the difference between the first distance and the second distance; adjust the signal strength corresponding to the adjacent grid based on the first adjustment value; and obtain the missing signal strength of the missing grid.

[0109] In an exemplary embodiment, the fingerprint completion module 50 is further configured to obtain the number of interval grids between the missing grid and the candidate grid, obtain a second adjustment value based on the number of interval grids, and adjust the signal strength corresponding to the candidate grid based on the second adjustment value to obtain the missing signal strength of the missing grid.

[0110] In an exemplary embodiment, the fingerprint completion module 50 is further configured to, when there are at least two neighboring clusters, obtain the reference missing signal intensity based on the center of the neighboring cluster of each neighboring cluster; and use the maximum value of the reference missing signal intensity or the average value of all reference missing signal intensities as the missing signal intensity of the missing grid.

[0111] Each module in the aforementioned fingerprint identification and repair device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0112] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 6 As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When executed by the processor, the computer program implements a fingerprint identification and repair method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0113] Those skilled in the art will understand that Figure 6The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0114] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps: acquiring fingerprint information of each grid in a positioning area, and acquiring all transmitting entities corresponding to the fingerprint information; the fingerprint information includes the signal strength of the wireless signal received within the grid; clustering the valid grids corresponding to the current transmitting entity; the valid grids are those located within the target area and whose corresponding fingerprint information contains the signal strength corresponding to the current transmitting entity; on the plane corresponding to the positioning area, with the center of the missing grid as the origin, acquiring the nearest neighbor cluster center of the nearest neighbor cluster within the target radius that is closest to the missing grid; the missing grid is a grid located within the target area and whose fingerprint information does not contain the signal strength corresponding to the current transmitting entity; acquiring adjacent grids on the plane that intersect the line connecting the center of the missing grid and the center of the nearest neighbor cluster; the adjacent grids are those adjacent to the missing grid on the plane; acquiring the missing signal strength of the missing grid based on the number of adjacent grids and the signal strength corresponding to the adjacent grids, and completing the fingerprint information of the missing grid based on the missing signal strength.

[0115] In one embodiment, the clustering of the effective grid corresponding to the current transmitting entity when the processor executes the computer program includes: obtaining the area of ​​the target region, obtaining the number of antenna points of the current transmitting entity in the target region based on the area; clustering the effective grid corresponding to the current transmitting entity to obtain multiple clusters corresponding to the current transmitting entity; the number of clusters corresponding to the current transmitting entity is the same as the number of antenna points.

[0116] In one embodiment, the processor executing a computer program to obtain the missing signal intensity of a missing grid based on the number of adjacent grids and the signal intensity corresponding to the adjacent grids includes: when at least two adjacent grids are valid grids, taking the average signal intensity of the adjacent grids as the missing signal intensity of the missing grid; when only one adjacent grid is valid grid, obtaining the missing signal intensity of the missing grid based on the distance between the adjacent grid and the nearest cluster center and the signal intensity corresponding to the adjacent grid; when no adjacent grids exist, obtaining the missing signal intensity of the missing grid based on the signal intensity corresponding to a candidate grid; the candidate grid is a valid grid that intersects with the line connecting the grid center and the nearest cluster center and is closest to the nearest cluster center.

[0117] In one embodiment, the processor executing a computer program to obtain the missing signal intensity of a missing grid based on the distance between adjacent grids and the centers of neighboring clusters and the signal intensity corresponding to the adjacent grids includes: obtaining a first distance between the grid center of an adjacent grid and the center of a neighboring cluster and a second distance between the grid center of the missing grid and the center of a neighboring cluster, respectively; obtaining a first adjustment value based on the difference between the first distance and the second distance; adjusting the signal intensity corresponding to the adjacent grids based on the first adjustment value to obtain the missing signal intensity of the missing grid.

[0118] In one embodiment, the processor executing a computer program to obtain the missing signal intensity of a missing grid based on the signal intensity corresponding to a candidate grid includes: obtaining the number of interval grids between the missing grid and the candidate grid; obtaining a second adjustment value based on the number of interval grids; and adjusting the signal intensity corresponding to the candidate grid based on the second adjustment value to obtain the missing signal intensity of the missing grid.

[0119] In one embodiment, when the processor executes the computer program, it further performs the following steps: in the presence of at least two neighboring clusters, obtaining the reference missing signal intensity based on the center of the neighboring cluster for each neighboring cluster; and taking the maximum value of the reference missing signal intensity or the average value of all reference missing signal intensities as the missing signal intensity of the missing grid.

[0120] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When executed by a processor, the computer program performs the following steps: acquiring fingerprint information of each grid in a positioning area and acquiring all transmitting entities corresponding to the fingerprint information; the fingerprint information includes the signal strength of the wireless signal received within the grid; clustering the valid grids corresponding to the current transmitting entity; the valid grids are those located within the target area and whose corresponding fingerprint information contains the signal strength corresponding to the current transmitting entity; on the plane corresponding to the positioning area, with the grid center of the missing grid as the origin, acquiring the nearest neighbor cluster center of the nearest neighbor cluster within the target radius that is closest to the missing grid; the missing grid is a grid located within the target area and whose fingerprint information does not contain the signal strength corresponding to the current transmitting entity; acquiring adjacent grids on the plane that intersect the line connecting the grid center of the missing grid and the neighbor cluster center; the adjacent grids are those adjacent to the missing grid on the plane; acquiring the missing signal strength of the missing grid based on the number of adjacent grids and the signal strength corresponding to the adjacent grids, and completing the fingerprint information of the missing grid based on the missing signal strength.

[0121] In one embodiment, when the computer program is executed by the processor, the clustering of the effective grid corresponding to the current transmitting entity includes: obtaining the area of ​​the target region; obtaining the number of antenna points of the current transmitting entity within the target region based on the area; clustering the effective grid corresponding to the current transmitting entity to obtain multiple clusters corresponding to the current transmitting entity; the number of clusters corresponding to the current transmitting entity is the same as the number of antenna points.

[0122] In one embodiment, when a computer program is executed by a processor, obtaining the missing signal intensity of a missing grid based on the number of adjacent grids and the signal intensity corresponding to the adjacent grids includes: if at least two adjacent grids are valid grids, taking the average signal intensity of the adjacent grids as the missing signal intensity of the missing grid; if only one adjacent grid is valid grid, obtaining the missing signal intensity of the missing grid based on the distance between the adjacent grid and the nearest cluster center and the signal intensity corresponding to the adjacent grid; if no adjacent grids exist, obtaining the missing signal intensity of the missing grid based on the signal intensity corresponding to a candidate grid; the candidate grid is a valid grid that intersects with the line connecting the grid center and the nearest cluster center and is closest to the nearest cluster center.

[0123] In one embodiment, when a computer program is executed by a processor, obtaining the missing signal intensity of a missing grid based on the distance between adjacent grids and the centers of neighboring clusters and the signal intensity corresponding to the adjacent grids includes: obtaining a first distance between the grid center of an adjacent grid and the center of a neighboring cluster and a second distance between the grid center of the missing grid and the center of a neighboring cluster, respectively; obtaining a first adjustment value based on the difference between the first distance and the second distance; adjusting the signal intensity corresponding to the adjacent grids based on the first adjustment value to obtain the missing signal intensity of the missing grid.

[0124] In one embodiment, when a computer program is executed by a processor, obtaining the missing signal intensity of a missing grid based on the signal intensity corresponding to a candidate grid includes: obtaining the number of interleaved grids between the missing grid and the candidate grid; obtaining a second adjustment value based on the number of interleaved grids; and adjusting the signal intensity corresponding to the candidate grid based on the second adjustment value to obtain the missing signal intensity of the missing grid.

[0125] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: in the presence of at least two neighboring clusters, obtaining the reference missing signal intensity based on the center of the neighboring cluster for each neighboring cluster; and taking the maximum value of the reference missing signal intensity or the average value of all reference missing signal intensities as the missing signal intensity of the missing grid.

[0126] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps: acquiring fingerprint information of each grid in a positioning area and acquiring all transmitting entities corresponding to the fingerprint information; the fingerprint information includes the signal strength of the wireless signal received within the grid; clustering the valid grids corresponding to the current transmitting entity; the valid grids are those located within the target area and whose corresponding fingerprint information contains the signal strength corresponding to the current transmitting entity; on the plane corresponding to the positioning area, with the grid center of the missing grid as the origin, acquiring the nearest neighbor cluster center of the nearest neighbor cluster within the target radius that is closest to the missing grid; the missing grid is a grid located within the target area and whose fingerprint information does not contain the signal strength corresponding to the current transmitting entity; acquiring adjacent grids on the plane that intersect the line connecting the grid center of the missing grid and the neighbor cluster center; the adjacent grids are those adjacent to the missing grid on the plane; acquiring the missing signal strength of the missing grid based on the number of adjacent grids and the signal strength corresponding to the adjacent grids, and completing the fingerprint information of the missing grid based on the missing signal strength.

[0127] In one embodiment, when the computer program is executed by the processor, the clustering of the effective grid corresponding to the current transmitting entity includes: obtaining the area of ​​the target region; obtaining the number of antenna points of the current transmitting entity within the target region based on the area; clustering the effective grid corresponding to the current transmitting entity to obtain multiple clusters corresponding to the current transmitting entity; the number of clusters corresponding to the current transmitting entity is the same as the number of antenna points.

[0128] In one embodiment, when a computer program is executed by a processor, obtaining the missing signal intensity of a missing grid based on the number of adjacent grids and the signal intensity corresponding to the adjacent grids includes: if at least two adjacent grids are valid grids, taking the average signal intensity of the adjacent grids as the missing signal intensity of the missing grid; if only one adjacent grid is valid grid, obtaining the missing signal intensity of the missing grid based on the distance between the adjacent grid and the nearest cluster center and the signal intensity corresponding to the adjacent grid; if no adjacent grids exist, obtaining the missing signal intensity of the missing grid based on the signal intensity corresponding to a candidate grid; the candidate grid is a valid grid that intersects with the line connecting the grid center and the nearest cluster center and is closest to the nearest cluster center.

[0129] In one embodiment, when a computer program is executed by a processor, obtaining the missing signal intensity of a missing grid based on the distance between adjacent grids and the centers of neighboring clusters and the signal intensity corresponding to the adjacent grids includes: obtaining a first distance between the grid center of an adjacent grid and the center of a neighboring cluster and a second distance between the grid center of the missing grid and the center of a neighboring cluster, respectively; obtaining a first adjustment value based on the difference between the first distance and the second distance; adjusting the signal intensity corresponding to the adjacent grids based on the first adjustment value to obtain the missing signal intensity of the missing grid.

[0130] In one embodiment, when a computer program is executed by a processor, obtaining the missing signal intensity of a missing grid based on the signal intensity corresponding to a candidate grid includes: obtaining the number of interleaved grids between the missing grid and the candidate grid; obtaining a second adjustment value based on the number of interleaved grids; and adjusting the signal intensity corresponding to the candidate grid based on the second adjustment value to obtain the missing signal intensity of the missing grid.

[0131] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: in the presence of at least two neighboring clusters, obtaining the reference missing signal intensity based on the center of the neighboring cluster for each neighboring cluster; and taking the maximum value of the reference missing signal intensity or the average value of all reference missing signal intensities as the missing signal intensity of the missing grid.

[0132] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0133] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0134] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for identifying and filling gaps in fingerprint positioning, characterized in that, The method includes: The fingerprint information of each grid in the positioning area is obtained, and all transmitting entities corresponding to the fingerprint information are obtained; the fingerprint information includes the signal strength of the wireless signal received within the grid. Cluster the valid grids corresponding to the current transmitting entity; the valid grids are those located within the target area and whose corresponding fingerprint information contains the signal strength corresponding to the current transmitting entity; On the plane corresponding to the positioning area, with the center of the missing grid as the origin, obtain the center of the nearest neighbor cluster within the target radius that is closest to the missing grid; the missing grid is a grid located within the target area and for which the signal strength corresponding to the current transmitting subject is not present in the fingerprint information; Obtain adjacent grid cells on the plane that intersect the line connecting the center of the missing grid cell and the center of the neighboring cluster; the adjacent grid cells are the grid cells on the plane that are adjacent to the missing grid cell. Based on the number of adjacent grids and the signal strength corresponding to the adjacent grids, the missing signal strength of the missing grid is obtained, and the fingerprint information of the missing grid is completed based on the missing signal strength.

2. The method according to claim 1, characterized in that, The clustering of the effective grid corresponding to the current transmitting entity includes: Obtain the area of ​​the target region, and based on the area, obtain the number of antenna points of the current transmitting entity within the target region; Cluster the effective grids corresponding to the current transmitting entity to obtain multiple clusters corresponding to the current transmitting entity; the number of clusters corresponding to the current transmitting entity is the same as the number of antenna points.

3. The method according to claim 1, characterized in that, The step of obtaining the missing signal intensity of the missing grid based on the number of adjacent grids and the signal intensity corresponding to the adjacent grids includes: If at least two adjacent grids are valid grids, the average signal strength of the adjacent grids is taken as the missing signal strength of the missing grid. When only one adjacent grid is a valid grid, the missing signal strength of the missing grid is obtained based on the distance between the adjacent grid and the center of the neighboring cluster and the signal strength corresponding to the adjacent grid. In the absence of adjacent grids, the missing signal intensity of the missing grid is obtained based on the signal intensity corresponding to the candidate grid; the candidate grid is a valid grid that intersects with the line connecting the grid center and the neighboring cluster center and is closest to the neighboring cluster center.

4. The method according to claim 3, characterized in that, The step of obtaining the missing signal intensity of the missing grid based on the distance between the adjacent grid and the center of the neighboring cluster and the signal intensity corresponding to the adjacent grid includes: Obtain the first distance between the center of the adjacent grid and the center of the neighboring cluster, and the second distance between the center of the missing grid and the center of the neighboring cluster, respectively. Based on the difference between the first distance and the second distance, a first adjustment value is obtained, and the signal strength corresponding to the adjacent grid is adjusted according to the first adjustment value to obtain the missing signal strength of the missing grid.

5. The method according to claim 3, characterized in that, The step of obtaining the missing signal intensity of the missing grid based on the signal intensity corresponding to the candidate grid includes: Obtain the number of interval grid cells between the missing grid cells and the candidate grid cells, and obtain a second adjustment value based on the number of interval grid cells; Adjust the signal strength corresponding to the candidate grid according to the second adjustment value to obtain the missing signal strength of the missing grid.

6. The method according to claim 1, characterized in that, The method further includes: In the case of at least two neighboring clusters, obtain the reference missing signal intensity based on the center of the neighboring cluster for each neighboring cluster; The maximum value among the reference missing signal intensities or the average value of all reference missing signal intensities is taken as the missing signal intensity of the missing grid.

7. A fingerprint positioning and leak repair device, characterized in that, The device includes: The fingerprint acquisition module is used to acquire fingerprint information of each grid in the positioning area and acquire all transmitting entities corresponding to the fingerprint information; the fingerprint information includes the signal strength of the wireless signal received in the grid. The grid clustering module is used to cluster the valid grids corresponding to the current transmitting subject; the valid grids are grids located within the target area and whose corresponding fingerprint information contains the signal strength corresponding to the current transmitting subject; The cluster center acquisition module is used to acquire the nearest cluster center of the nearest neighboring cluster to the missing grid within the target radius on the plane corresponding to the positioning area, with the grid center of the missing grid as the origin; the missing grid is a grid located within the target area and for which the signal strength corresponding to the current transmitting subject is not present in the fingerprint information; The adjacent acquisition module is used to acquire adjacent grid cells on the plane that have an intersection point between the line connecting the center of the missing grid cell and the center of the neighboring cluster; the adjacent grid cell is the grid cell that is adjacent to the missing grid cell on the plane; The fingerprint completion module is used to obtain the missing signal intensity of the missing grid based on the number of adjacent grids and the signal intensity corresponding to the adjacent grids, and to complete the fingerprint information of the missing grid based on the missing signal intensity.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images