A method and device for detecting abnormal points of indoor positioning Bluetooth beacons

Abstract

The present invention provides a method and device for detecting abnormal points of indoor positioning Bluetooth beacons, which relates to the field of indoor positioning. In this method, a first neighborhood and a second neighborhood of a first beacon point are obtained from a set of beacon points; a first average value of the coordinates of the beacon points in the first neighborhood is calculated, and a second average value of the coordinates of the beacon points in the second neighborhood is calculated, and an offset score of the first beacon point is calculated according to the first average value and the second average value; an average offset score of all the beacon points in the set of beacon points is calculated, and the offset score is compared with the average offset score; a weighted distance is calculated according to the comparison result, a subspace offset factor is calculated according to the weighted distance, and the beacon points with the subspace offset factor greater than a threshold are marked as abnormal points. Implementing the technical solution provided by this application can effectively identify the abnormal points of Bluetooth beacons indoors and improve the stability and accuracy of the indoor positioning system.

Description

Technical Field

[0001] The present application relates to the technical field of indoor positioning, and in particular to a method and device for detecting abnormal points of indoor positioning Bluetooth beacons. Background Art

[0002] With the rapid development of the Internet of Things technology, Bluetooth indoor positioning systems are increasingly widely used in fields such as logistics, retail, and smart homes. Traditional GPS (Global Positioning System) cannot work effectively in indoor environments due to limitations such as signal attenuation and multipath effects. In contrast, indoor positioning systems based on Bluetooth technology have become an ideal solution due to their low power consumption, low cost, and high device penetration rate.

[0003] In complex environments such as large factories, the layout of Bluetooth beacons may be misaligned. In addition, due to the dynamic and changing nature of the factory environment, some originally correctly placed Bluetooth beacons may deviate from their original positions due to environmental interference or device movement. Considering the vast factory space and a large number of beacons, relying on manual inspection of the placement of each beacon is not only time-consuming and labor-intensive but also cannot fully guarantee accuracy.

[0004] Therefore, a detection method capable of accurately locating abnormal points of Bluetooth beacons is needed. Summary of the Invention

[0005] The present application provides a method and device for detecting abnormal points of indoor positioning Bluetooth beacons. By accurately identifying and processing abnormal beacon points, the accuracy of indoor positioning and the robustness of the system can be significantly improved, the layout and maintenance of beacon points can be optimized, and thus more accurate and reliable positioning services can be provided to users.

[0006] In a first aspect of the present application, a method for detecting abnormal points of indoor positioning Bluetooth beacons is provided, which is applied to an indoor positioning platform. The method includes:

[0007] Obtain a first neighborhood and a second neighborhood of a first beacon point from a set of beacon points. The first neighborhood is a set of the first number of nearest neighbor beacon points of the first beacon point in a preset scenario, and the second neighborhood is a set of the first number of nearest neighbor beacon points of the first beacon point in the current scenario. The first beacon point is any one of the set of beacon points;

[0008] Calculate a first average value of the coordinates of the beacon points in the first neighborhood, and calculate a second average value of the coordinates of the beacon points in the second neighborhood. Calculate an offset score of the first beacon point according to the first average value and the second average value;

[0009] Calculate the average offset score of all fiducial points in the set of fiducial points, and compare the offset score with the average offset score;

[0010] Calculate the weighted distance according to the comparison result, calculate the subspace offset factor according to the weighted distance, and mark the fiducial points with the subspace offset factor greater than the threshold as outliers.

[0011] The calculating the weighted distance according to the comparison result and calculating the subspace offset factor according to the weighted distance includes:

[0012] When the offset score is greater than the average offset score, determine the second fiducial point that is the second closest to the first fiducial point, and calculate the target distance between the first fiducial point and the second fiducial point;

[0013] Calculate the weighted distance of the first fiducial point according to the target distance and the preset weight value, and calculate the local density of the first fiducial point according to the weighted distance;

[0014] Calculate the mean of the local densities of all fiducial points in the first neighborhood to obtain the subspace density, and calculate the subspace offset factor according to the subspace density and the local density of the first fiducial point.

[0015] Optionally, the calculating the first average value of the coordinates of the fiducial points in the first neighborhood and calculating the second average value of the coordinates of the fiducial points in the second neighborhood includes:

[0016] Calculate the first average value and the second average value through the following formula:

[0017] ;

[0018] ;

[0019] Wherein, is the average value of the x axis coordinates in the first average value, is the average value of the y axis coordinates in the first average value, P xi is the i th fiducial point in the first neighborhood, x axis coordinate value, P yi is the i th fiducial point in the first neighborhood, y axis coordinate value, is the average value of the x axis coordinates in the second average value, is the average value of the y axis coordinates in the second average value, Pxj is the j axis coordinate value of the x th signal punctuation point in the second neighborhood, P yj is the y-axis coordinate value of the j th signal punctuation point in the second neighborhood, and K is the first quantity.

[0020] Optionally, calculating the offset score of the first signal punctuation point according to the first average value and the second average value includes:

[0021] Calculating the offset score of the first signal punctuation point through the following formula:

[0022] ;

[0023] where D is the offset score between the first neighborhood and the second neighborhood, is the x axis coordinate average value in the first average value, is the y axis coordinate average value in the first average value, is the x axis coordinate average value in the second average value, is the y axis coordinate average value in the second average value.

[0024] Optionally, obtaining the first neighborhood and the second neighborhood of the first signal punctuation point from the set of signal punctuation points includes:

[0025] Calculating the Euclidean distance between other signal punctuation points and the first signal punctuation point according to the preset coordinates of the signal punctuation points, and selecting the first quantity of signal punctuation points closest to the first signal punctuation point according to the Euclidean distance to form the first neighborhood, where the other signal punctuation points are the signal punctuation points in the set of signal punctuation points except the first signal punctuation point;

[0026] Determining the actual distance between other signal punctuation points and the first signal punctuation point according to the actually measured signal strength value, and selecting the first quantity of signal punctuation points closest to the first signal punctuation point according to the actual distance to form the second neighborhood, where the other signal punctuation points are the signal punctuation points in the set of signal punctuation points except the first signal punctuation point.

[0027] Optionally, determining the actual distance between other signal punctuation points and the first signal punctuation point according to the actually measured signal strength value includes:

[0028] Determining the actual distance between other signal punctuation points and the first signal punctuation point through the following formula:

[0029] RSSI = RSSI 0 -10nlog 10(d) + Xs ;

[0030] Among them, RSSI is the signal strength value received by the first beacon point, RSSI 0 is the signal strength value emitted by the other beacon points, n is the path loss exponent, d is the actual distance between the other beacon points and the first beacon point, Xs is the shadow attenuation, which is a random variable following a Gaussian distribution.

[0031] Optionally, calculating the weighted distance according to the comparison result and calculating the subspace offset factor according to the weighted distance includes:

[0032] Calculating the weighted distance through the following formula:

[0033] SWD ( q ) = ω·SD ( q );

[0034] Among them, SWD ( q ) is the weighted distance of the first beacon point q ω is the weight value, SD ( q ) is the target distance from the first beacon point to the second beacon point,

[0035] Calculating the local density of the first beacon point through the following formula:

[0036] ;

[0037] Among them, ρ ( q ) is the local density of the first beacon point q

[0038] Calculating the subspace offset factor of the first beacon point through the following formula:

[0039] ;

[0040] Among them, is the subspace offset factor of the first beacon point q is the subspace density of the first beacon point.

[0041] ​​​In the second aspect of the present application, a detection system for abnormal points of indoor positioning Bluetooth beacons is provided, which is used to implement the detection method for abnormal points of indoor positioning Bluetooth beacons as described in any one of the above, and includes a neighborhood module, a calculation module, a comparison module, and an execution module, where:

[0042] The neighborhood module is configured to obtain the first neighborhood and the second neighborhood of the first beacon point from the set of beacon points. The first neighborhood is a set of the first number of nearest neighbor beacon points of the first beacon point in a preset scenario, and the second neighborhood is a set of the first number of nearest neighbor beacon points of the first beacon point in the current scenario. The first beacon point is any one of the set of beacon points;

[0043] The calculation module is configured to calculate the first average value of the coordinates of the beacon points in the first neighborhood, and calculate the second average value of the coordinates of the beacon points in the second neighborhood, and calculate the offset score of the first beacon point according to the first average value and the second average value;

[0044] The comparison module is configured to calculate the average offset score of all the beacon points in the set of beacon points, and compare the offset score with the average offset score;

[0045] The execution module is configured to calculate the weighted distance according to the comparison result, calculate the subspace offset factor according to the weighted distance, and mark the beacon points with the subspace offset factor greater than the threshold as abnormal points,

[0046] The calculating the weighted distance according to the comparison result and calculating the subspace offset factor according to the weighted distance includes:

[0047] When the offset score is greater than the average offset score, determine the second beacon point that is the second closest to the first beacon point, and calculate the target distance between the first beacon point and the second beacon point;

[0048] Calculate the weighted distance of the first beacon point according to the target distance and the preset weight value, and calculate the local density of the first beacon point according to the weighted distance;

[0049] Calculate the mean value of the local densities of all the beacon points in the first neighborhood to obtain the subspace density, and calculate the subspace offset factor according to the subspace density and the local density of the first beacon point.

[0050] In the third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method as described in any one of the above.

[0051] In the fourth aspect of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores instructions that, when executed, perform the method described in any one of the above.

[0052] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0053] 1. By calculating the first neighborhood and the second neighborhood of the fiducial points in the preset scenario and the current scenario, and combining indicators such as the offset score, weighted distance, and subspace offset factor, it is possible to accurately identify the fiducial points whose positions are offset or abnormal in the actual scenario. After excluding these fiducial points, the accuracy of indoor positioning can be significantly improved;

[0054] 2. The indoor environment is often relatively complex, and the layout of fiducial points may be affected by various factors and change, such as furniture placement, personnel movement, etc. By comparing the neighborhood information of fiducial points in the preset scenario and the current scenario in the embodiments of the present application, it is possible to flexibly respond to these environmental changes. Even when the positions of fiducial points are offset, abnormal points can be accurately detected to ensure the stable operation of the positioning system;

[0055] 3. In practical applications, fiducial points may be affected by factors such as electromagnetic interference and signal attenuation, resulting in abnormal signal strength or position information. By comprehensively considering indicators such as the offset score and weighted distance of fiducial points in the embodiments of the present application, the influence brought by these interference factors can be effectively filtered out, and the anti-interference ability of the positioning system in a complex environment can be improved;

[0056] 4. By detecting abnormal fiducial points, a basis can be provided for optimizing the layout of fiducial points. For those fiducial points whose positions are offset or abnormal, their layouts can be readjusted to better meet the requirements of the actual application scenario, thereby improving the layout rationality of the entire fiducial point network and further enhancing the performance of indoor positioning;

[0057] 5. For users, the accuracy of indoor positioning directly affects their usage experience. The embodiments of the present application can effectively improve the accuracy of indoor positioning and provide users with more accurate positioning services, such as quickly finding a target store in a shopping mall, accurately navigating in an airport, etc., thereby enhancing user satisfaction and usage experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 is a schematic flowchart of a method for detecting abnormal points of indoor positioning Bluetooth beacons disclosed in an embodiment of the present application;

[0059] Figure 2 is a schematic diagram of the simulation experiment effect of a method for detecting abnormal points of indoor positioning Bluetooth beacons disclosed in an embodiment of the present application;

[0060] Figure 3 It is another schematic flow chart of the method for detecting abnormal points of indoor positioning Bluetooth beacons disclosed in the embodiments of the present application;

[0061] Figure 4 It is a schematic diagram of modules of the system for detecting abnormal points of indoor positioning Bluetooth beacons disclosed in the embodiments of the present application;

[0062] Figure 5 It is a schematic structural diagram of an electronic device disclosed in the embodiments of the present application.

[0063] Explanation of reference numerals: 401, neighborhood module; 402, calculation module; 403, comparison module; 404, execution module; 501, processor; 502, communication bus; 503, user interface; 504, network interface; 505, memory. Detailed implementation manners

[0064] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments.

[0065] In the description of the embodiments of the present application, words such as "for example" or "for illustration" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "for example" or "for illustration" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, the use of words such as "for example" or "for illustration" is intended to present relevant concepts in a specific manner.

[0066] In the description of the embodiments of the present application, the meaning of the term "a plurality" refers to two or more. For example, a plurality of systems refers to two or more systems, and a plurality of screen terminals refers to two or more screen terminals. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly indicating the technical features indicated. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The terms "include", "comprise", "have" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0067] This embodiment discloses a method for detecting abnormal points of indoor positioning Bluetooth beacons, which is applied to an indoor positioning platform, Figure 1 It is a schematic flow chart of the method for detecting abnormal points of indoor positioning Bluetooth beacons disclosed in the embodiments of the present application, as Figure 1 shown, the method includes the following steps:

[0068] S101. Obtain the first neighborhood and the second neighborhood of a first beacon point from the beacon point set. The first neighborhood is a set of the first number of nearest neighbor beacon points of the first beacon point under a preset scenario, and the second neighborhood is a set of the first number of nearest neighbor beacon points of the first beacon point under the current scenario. The first beacon point is any one in the beacon point set.

[0069] S102. Calculate the first average value of the coordinates of the beacon points in the first neighborhood, and calculate the second average value of the coordinates of the beacon points in the second neighborhood. Calculate the offset score of the first beacon point according to the first average value and the second average value.

[0070] S103. Calculate the average offset score of all the beacon points in the beacon point set, and compare the offset score with the average offset score.

[0071] S104. Calculate the weighted distance according to the comparison result, calculate the subspace offset factor according to the weighted distance, and mark the beacon points with the subspace offset factor greater than the threshold as abnormal points.

[0072] Figure 2 It is a schematic diagram of the simulation experiment effect of the detection method for abnormal points of indoor positioning Bluetooth beacons disclosed in the embodiments of the present application. The experimental map of the present invention is a 120-meter * 100-meter plane. Beacons are arranged on both sides of a U-shaped corridor passage with a length of 90 meters and a width of 70 meters. The corridor width is 5 meters. The preset scenario is to place 14 Bluetooth beacons on the west side of the west corridor and the east side of the east corridor respectively, place 12 Bluetooth beacons on the east side of the west corridor and the west side of the east corridor respectively, place 12 Bluetooth beacons on the south side of the south corridor, and place 9 Bluetooth beacons on the north side of the south corridor. Each beacon takes itself as the origin and emits its own number (ID) information and a signal related to the position that can be used to calculate the received signal strength value (RSSI) to the surroundings. All the above beacon points form a beacon point set.

[0073] The first neighborhood refers to a set of a certain number (the first number) of fiducial points that are closest to the first fiducial point in a preset scenario. Based on the fixed layout and known coordinates of the fiducial points in the preset scenario, the distances between the first fiducial point and other fiducial points are calculated, and then the first number of fiducial points with the closest distances are selected as the first neighborhood. For example, if the first number is 4, then the 4 fiducial points closest to the first fiducial point are selected as the first neighborhood. The first neighborhood reflects the local environment and relative position relationship of the fiducial points in the ideal state, providing a benchmark for subsequent offset score calculation. The second neighborhood refers to a set of a certain number (the first number) of fiducial points that are closest to the first fiducial point in the current scenario (i.e., the actual scenario). Based on the actually measured signal strength (such as RSSI value) or the real-time coordinates of the fiducial points, the distances between the first fiducial point and other fiducial points are calculated, and then the first number of fiducial points with the closest distances are selected as the second neighborhood. For example, in the actual scenario, due to environmental changes or fiducial point position offsets, the fiducial points closest to the first fiducial point may be different from those in the preset scenario. The second neighborhood reflects the local environment and relative position relationship of the fiducial points in the actual scenario. Comparing it with the first neighborhood can reveal the position deviation of the fiducial points. Calculate the first average value of the coordinates of the fiducial points in the first neighborhood, including the average values of the x-axis and y-axis coordinates. This can be obtained by adding up the x-axis coordinates of all fiducial points in the first neighborhood and dividing by the first number, and adding up the y-axis coordinates of all fiducial points and dividing by the first number. Similarly, calculate the second average value of the coordinates of the fiducial points in the second neighborhood, including the average values of the x-axis and y-axis coordinates, using the same method as the calculation of the first average value. The offset score is used to measure the degree of position deviation of the first fiducial point in the preset scenario and the current scenario. The offset score is calculated based on the difference between the first average value and the second average value. For example, the Euclidean distance between the two average values can be calculated. The larger the Euclidean distance, the greater the position deviation of the first fiducial point and the higher the offset score. The average offset score refers to the average value of the offset scores of all fiducial points in the fiducial point set. Add up the offset scores of all fiducial points and divide by the total number of fiducial points, and the result obtained is the average offset score. By comparing the offset score of the first fiducial point with the average offset score, it can be judged whether the position deviation of the first fiducial point is significantly higher than the overall average level. If the offset score of the first fiducial point is greater than the average offset score, it indicates that the fiducial point may have a large position deviation or anomaly and needs to be weighted; if the offset score is less than or equal to the average offset score, it is considered that the position deviation of the fiducial point is within the normal range. The weighted distance is obtained by weighting the K-nearest neighbor distance considering the offset score of the fiducial point. Take all the neighboring points of each target fiducial point as the subspace of that fiducial point. The local density is the reciprocal of the weighted distance of the fiducial point, and the subspace density is the average value of the local densities of all points in the first neighborhood of the fiducial point. The subspace offset factor is the ratio of the subspace density to the local density of the fiducial point.Set a threshold for the subspace offset factor to determine whether a beacon point is an abnormal point. When the subspace offset factor of a beacon point is greater than the threshold, the beacon point is considered an abnormal point and is marked. These abnormal points may be caused by position offset, signal interference, or other reasons, and need to be processed or excluded in the subsequent positioning process to improve the accuracy and reliability of positioning.

[0074] By comparing the first neighborhood and the second neighborhood of a beacon point in a preset scenario and the current scenario, the calculated offset score can effectively reflect the change of the position of the beacon point. It can accurately identify those beacon points whose positions are offset or abnormal in the actual scenario, avoid large errors in the positioning result caused by these abnormal points, and thus significantly improve the accuracy of indoor positioning. The indoor environment is often complex and changeable, and the layout of beacon points may be affected by various factors and change, such as furniture placement, personnel movement, etc. In the embodiment of the present application, by comparing the neighborhood information of beacon points in different scenarios, it can flexibly cope with these environmental changes. Even when the position of the beacon point is offset, it can accurately detect abnormal points and ensure the stable operation of the positioning system. In practical applications, beacon points may be affected by factors such as electromagnetic interference and signal attenuation, resulting in abnormal signal strength or position information. In the embodiment of the present application, by comprehensively considering indicators such as the offset score and weighted distance of beacon points, it can effectively filter out the influence brought by these interference factors and improve the anti-interference ability of the positioning system in a complex environment. By detecting abnormal beacon points, it can provide a basis for optimizing the layout of beacon points. For those beacon points whose positions are offset or abnormal, their layouts can be readjusted to make them more in line with the requirements of the actual application scenario, thereby improving the layout rationality of the entire beacon point network and further enhancing the performance of indoor positioning.

[0075] Optionally, obtaining the first neighborhood and the second neighborhood of the first beacon point from the beacon point set includes:

[0076] According to the preset coordinates of the beacon point, calculate the Euclidean distance between other beacon points and the first beacon point, and select the first number of beacon points closest to the first beacon point according to the Euclidean distance to form the first neighborhood, where the other beacon points are the beacon points in the beacon point set except the first beacon point;

[0077] Determine the actual distance between other beacon points and the first beacon point according to the actually measured signal strength value, and select the first number of beacon points closest to the first beacon point according to the actual distance to form the second neighborhood, where the other beacon points are the beacon points in the beacon point set except the first beacon point.

[0078] According to the coordinate positions of the reference punctuation points in the preset scenario, calculate the Euclidean distances between other reference punctuation points and the first reference punctuation point. The Euclidean distance is a commonly used method to measure the straight-line distance between two points. Among the calculated Euclidean distances, select the first number of reference punctuation points that are closest to the first reference punctuation point. These reference punctuation points together constitute the first neighborhood of the first reference punctuation point. The first neighborhood reflects the distribution of the reference punctuation points around the first reference punctuation point in the preset scenario and is the neighborhood in the ideal state. In the actual scenario, by measuring the signal strength values between the reference punctuation points, the actual distances between the reference punctuation points can be estimated. There is usually a certain relationship between the signal strength and the distance, and the signal strength can be converted into a distance through a signal propagation model. According to the estimated actual distances, select the first number of reference punctuation points that are closest to the first reference punctuation point. These reference punctuation points together constitute the second neighborhood of the first reference punctuation point. The second neighborhood reflects the distribution of the reference punctuation points around the first reference punctuation point in the current actual scenario and is the neighborhood in the real environment. The first neighborhood is calculated based on the preset coordinates of the reference punctuation points and represents the neighborhood in the ideal state; while the second neighborhood is estimated based on the actually measured signal strength values and represents the neighborhood in the actual scenario. By comparing these two neighborhoods, the position change of the reference punctuation point in the actual scenario relative to the preset scenario can be found. The first number is preset and represents the number of the closest reference punctuation points to be selected when calculating the neighborhood. For example, if the first number is set to 4, then in both the first neighborhood and the second neighborhood, 4 reference punctuation points that are closest to the first reference punctuation point will be selected. Other reference punctuation points refer to all reference punctuation points in the set of reference punctuation points except the first reference punctuation point, and they all participate in the calculation of the Euclidean distance and the actual distance with the first reference punctuation point to determine whether they are selected into the neighborhood.

[0079] Calculating the Euclidean distance using the preset coordinates of the beacon points can accurately reflect the spatial position relationship of the beacon points in the ideal layout. By selecting the first number of beacon points closest to the first beacon point to form the first neighborhood, the proximity of the beacon points within the first neighborhood to the first beacon point in the preset scenario is ensured, providing a reliable basis for the subsequent calculation of the offset score. The actually measured signal strength values contain the environmental information of the beacon points in the current scenario, such as signal propagation loss, reflection, refraction, etc. The actual distances between the beacon points determined based on these actual signal strength values can more accurately reflect the relative position relationship of the beacon points in the actual environment. Selecting the first number of beacon points closest to the first beacon point to form the second neighborhood ensures the proximity of the beacon points within the second neighborhood to the first beacon point in the current scenario, providing a key basis for detecting the position offset of the beacon points. Obtaining the neighborhood information of the first beacon point from two dimensions of the preset scenario and the current scenario can effectively cope with the changes in the indoor environment. Even when the layout of the beacon points changes or the signal propagation characteristics change due to environmental factors, by comparing the differences between the first neighborhood and the second neighborhood, the abnormal conditions of the beacon points can still be accurately detected, improving the robustness of the algorithm in different scenarios. By comprehensively considering the preset coordinates and the actual signal strength values of the beacon points and selecting the neighborhood from two perspectives, the position status of the beacon points can be evaluated more comprehensively. This multi-dimensional analysis method helps to reduce misjudgments and missed detections caused by single factors and improves the accuracy of detecting abnormal beacon points.

[0080] Optionally, determining the actual distance between other beacon points and the first beacon point according to the actually measured signal strength values includes:

[0081] Determining the actual distance between other beacon points and the first beacon point through the following formula:

[0082] RSSI = RSSI 0 -10nlog 10 (d) + Xs ;

[0083] Wherein, RSSI is the signal strength value received by the first beacon point, RSSI 0 is the signal strength value emitted by the other beacon point, n is the path loss exponent, d is the actual distance between the other beacon point and the first beacon point, Xs is the shadow fading, which is a random variable following a Gaussian distribution.

[0084] The above formula is based on a signal propagation model. By measuring the received signal strength (RSSI) and the known reference signal strength (RSSI0, the transmitted signal strength value should be known data), and combining the path loss exponent (n), the actual distance (d) between beacon points is estimated. This method utilizes the relationship between signal strength and distance, that is, the signal strength gradually weakens as the distance increases. The shadow fading (Xs) in the formula takes into account the influence of environmental factors on signal propagation, making the distance estimation more in line with the actual scenario. In an indoor environment, the signal is blocked and reflected by various obstacles, resulting in random fluctuations in signal strength. Introducing Xs can effectively compensate for this fluctuation and improve the accuracy of distance estimation. Through this formula, the actual distance between beacon points can be accurately determined, providing reliable data support for subsequent steps such as neighborhood selection, offset score calculation, and weighted distance calculation. This helps to improve the accuracy of indoor positioning Bluetooth beacon anomaly detection, optimize the layout and maintenance of beacon points, and enhance the overall performance of the indoor positioning system.

[0085] Optionally, calculating the first average value of the coordinates of the beacon points in the first neighborhood and calculating the second average value of the coordinates of the beacon points in the second neighborhood includes:

[0086] The first average value and the second average value are calculated by the following formula:

[0087] ;

[0088] ;

[0089] Wherein, is the average value of the x axis coordinates in the first average value, is the average value of the y axis coordinates in the first average value, P xi is the i axis coordinate value of the x th beacon point in the first neighborhood, P yi is the i axis coordinate value of the y th beacon point in the first neighborhood, is the average value of the x axis coordinates in the second average value, is the average value of the y axis coordinates in the second average value, P xj is the j axis coordinate value of the x th beacon point in the second neighborhood, P yj is the jThe y-axis coordinate value of the beacon point, and K is the first quantity.

[0090] By summing the x-axis coordinates and y-axis coordinates of all beacon points in the first neighborhood and the second neighborhood respectively, and then dividing by the number of beacon points in the corresponding neighborhood, the coordinate average value of each neighborhood can be obtained. These average values reflect the central position of the beacon points in the neighborhood and provide a basis for the subsequent calculation of the offset score. By comparing the coordinate average values of the first neighborhood and the second neighborhood, the offset score of the first beacon point can be calculated. The magnitude of the offset score reflects the position deviation of the first beacon point in the preset scenario and the current scenario, and is an important indicator for judging whether the beacon point is abnormal. Accurately calculating the first average value and the second average value is of great significance for the detection of abnormal points of indoor positioning Bluetooth beacons. By comparing the coordinate average values of the two neighborhoods, the beacon points with offset or abnormal positions can be effectively identified, providing reliable data support for the optimization and maintenance of the indoor positioning system.

[0091] Optionally, calculating the offset score of the first beacon point according to the first average value and the second average value includes:

[0092] Calculating the offset score of the first beacon point through the following formula:

[0093] ;

[0094] where D is the offset score between the first neighborhood and the second neighborhood, is the average value of the x axis coordinates in the first average value, is the average value of the y axis coordinates in the first average value, is the average value of the x axis coordinates in the second average value, is the average value of the y axis coordinates in the second average value.

[0095] By calculating the distance between the coordinate average values of the first neighborhood and the second neighborhood, the offset score of the first beacon point can be obtained. The magnitude of the offset score reflects the position deviation of the first beacon point in the preset scenario and the current scenario. If the offset score is large, it indicates that the position of the first beacon point has changed significantly in the actual scenario and may be abnormal; if the offset score is small, it indicates that the position of the first beacon point remains basically unchanged in the actual scenario and there is no obvious abnormality. By calculating the offset score, the beacon points with offset or abnormal positions can be effectively identified, providing reliable data support for the optimization and maintenance of the indoor positioning system. The offset score is an important indicator for judging whether the beacon point is abnormal and is of great significance for improving the indoor positioning accuracy and system stability.

[0096] Optionally, calculating the weighted distance according to the comparison result, and calculating the subspace offset factor according to the weighted distance includes:

[0097] When the offset score is greater than the average offset score, determine the second fiducial point that is the second closest to the first fiducial point, and calculate the target distance between the first fiducial point and the second fiducial point;

[0098] Calculate the weighted distance of the first fiducial point according to the target distance and the preset weight value, and calculate the local density of the first fiducial point according to the weighted distance;

[0099] Calculate the mean value of the local densities of all the fiducial points in the first neighborhood to obtain the subspace density, and calculate the subspace offset factor according to the subspace density and the local density of the first fiducial point.

[0100] When the offset score of the first fiducial point is greater than the average offset score of all the fiducial points, it indicates that the first fiducial point may have a position offset or anomaly. In this case, it is necessary to determine the second fiducial point that is the second closest to the first fiducial point. This can be achieved by comparing the distances between the first fiducial point and other fiducial points, and selecting the fiducial point with the second smallest distance as the second fiducial point. Calculate the target distance between the first fiducial point and the second fiducial point, that is, the actual distance between them. This distance can be determined by the signal strength value or other methods. According to the target distance and the preset weight value, calculate the weighted distance of the first fiducial point. The setting of the weight value can be based on the offset score or other relevant factors to reflect the importance or influence of the fiducial point. The local density is defined as the reciprocal of the weighted distance of the fiducial point, and the local density reflects the "crowdedness" of the fiducial point in its weighted neighborhood. Calculate the mean value of the local densities of all the fiducial points in the first neighborhood to obtain the subspace density. The subspace density represents the average value of the "crowdedness" of all the fiducial points in the first neighborhood. The subspace offset factor is the ratio of the subspace density of the first fiducial point to the local density. When the subspace offset factor is greater than the preset threshold, it indicates that the first fiducial point may have a position offset or anomaly, so it can be marked as an abnormal point. In the embodiment of the present application, the preset threshold can be 1.4.

[0101] By comparing the offset scores with the average offset score, those fiducial points with large position changes can be identified. Further, by calculating the target distances between these fiducial points and their second-nearest neighbor fiducial points, the actual position deviations of the fiducial points can be more precisely quantified. For those fiducial points with high offset scores, introducing a preset weight to calculate the weighted distance can more reasonably reflect the importance of the fiducial points and the possible impact they may have on the positioning system, thereby improving the accuracy of anomaly detection. By calculating the local density of the first fiducial point and the average local density (subspace density) of all fiducial points within the first neighborhood, the local distribution of the fiducial points can be evaluated, which is crucial for maintaining the stability of the positioning system in a complex environment. The calculation of the subspace offset factor helps to identify those fiducial points that exhibit anomalies in the local area. Even if their absolute offset scores are not particularly high, but they appear abnormal relative to the distribution of surrounding fiducial points, such fiducial points may also be marked as anomalies. By identifying the abnormal fiducial points and their position deviations, it is possible to provide guidance for the re-layout of the fiducial points, optimize the distribution of the fiducial points, and improve the coverage uniformity and positioning accuracy of the entire positioning system.

[0102] Optionally, the calculating the weighted distance according to the comparison result and calculating the subspace offset factor according to the weighted distance includes:

[0103] The weighted distance is calculated by the following formula:

[0104] SWD ( q ) = ω·SD ( q );

[0105] Wherein, SWD ([[]] q ) is the weighted distance of the first fiducial point q , ω is the weight, SD ([[]] q ) is the target distance from the first fiducial point to the second fiducial point,

[0106] The local density of the first fiducial point is calculated by the following formula:

[0107] ;

[0108] Wherein, ρ ([[]] q ) is the local density of the first fiducial point q ,

[0109] The subspace offset factor of the first fiducial point is calculated by the following formula:

[0110] ;

[0111] Wherein, is the subspace offset factor of the first beacon point q , and is the subspace density of the first beacon point.

[0112] By introducing weights ω , the importance of the actual distance between beacon points in anomaly detection can be more reasonably reflected. In the embodiments of the present application ω is 1.2. For those beacon points with larger offset scores, the weights can be adjusted to increase their influence in the weighted distance calculation, thereby improving the accuracy of anomaly detection. The calculation of local density and subspace density provides a basis for the calculation of the subspace offset factor. All the neighbor points of the first number of neighbor points of the first beacon point are used as the subspace of the first beacon point. The subspace density reflects the overall situation of the relative position relationship of beacon points within the entire first neighborhood. The subspace offset factor is a key indicator for determining whether a beacon point is abnormal. When the subspace offset factor is greater than a preset threshold, it indicates that the relative "crowdedness" of the beacon point within its subspace is much higher than that of other points, and there may be a position offset or anomaly. Therefore, it can be marked as an abnormal point. As Figure 2 shown, the points with boxes around the periphery are abnormal points, where the hollow ones are the points with displacements, and the solid ones are the points with exchanges.

[0113] Figure 3 is another schematic flowchart of the method for detecting abnormal points of indoor positioning Bluetooth beacons disclosed in the embodiments of the present application. As Figure 3 shown, the method for detecting abnormal points of indoor positioning Bluetooth beacons includes the following steps: S301, calculate the distance between Bluetooth beacons by measuring RSSI values; S302, find the target number of nearest neighbor beacon points of the target beacon point in the ideal beacon layout scenario, and calculate the first average value of the target number of nearest neighbor beacon points; S303, find the target number of nearest neighbor beacon points of the target beacon point in the actual beacon layout scenario, and calculate the second average value of the target number of nearest neighbor beacon points; S304, determine the offset score according to the first average value and the second average value; S305, judge whether the offset score exceeds the average value; if so, execute S306, calculate the weighted distance, otherwise execute S307, calculate the unweighted distance; S308, calculate the subspace offset factor according to the distance; S309, judge whether the subspace offset factor exceeds the threshold; if so, execute S310, mark it as an abnormal point, otherwise execute S311, mark it as a normal point.

[0114] This embodiment also discloses a system for detecting abnormal points of indoor positioning Bluetooth beacons Figure 4 is a schematic diagram of the modules of the system for detecting abnormal points of indoor positioning Bluetooth beacons disclosed in the embodiments of the present application. As Figure 4As shown in the figure, the system includes a neighborhood module 401, a calculation module 402, a comparison module 403, and an execution module 404, where:

[0115] The neighborhood module 401 is configured to obtain the first neighborhood and the second neighborhood of the first fiducial point from the set of fiducial points. The first neighborhood is a set of the first number of nearest neighbor fiducial points of the first fiducial point in a preset scenario, and the second neighborhood is a set of the first number of nearest neighbor fiducial points of the first fiducial point in the current scenario. The first fiducial point is any one in the set of fiducial points.

[0116] The calculation module 402 is configured to calculate the first average value of the coordinates of the fiducial points in the first neighborhood, calculate the second average value of the coordinates of the fiducial points in the second neighborhood, and calculate the offset score of the first fiducial point according to the first average value and the second average value.

[0117] The comparison module 403 is configured to calculate the average offset score of all the fiducial points in the set of fiducial points and compare the offset score with the average offset score.

[0118] The execution module 404 is configured to calculate a weighted distance according to the comparison result, calculate a subspace offset factor according to the weighted distance, and mark the fiducial points with the subspace offset factor greater than the threshold as outlier points.

[0119] The calculating the weighted distance according to the comparison result and calculating the subspace offset factor according to the weighted distance includes:

[0120] When the offset score is greater than the average offset score, determine the second fiducial point that is the second closest to the first fiducial point, and calculate the target distance between the first fiducial point and the second fiducial point.

[0121] Calculate the weighted distance of the first fiducial point according to the target distance and the preset weight value, and calculate the local density of the first fiducial point according to the weighted distance.

[0122] Calculate the mean value of the local densities of all the fiducial points in the first neighborhood to obtain the subspace density, and calculate the subspace offset factor according to the subspace density and the local density of the first fiducial point.

[0123] Optionally, the calculation module 402 is configured to:

[0124] Calculate the first average value and the second average value through the following formula:

[0125] ;

[0126] ;

[0127] Among them, is the x average value of the axis coordinates in the first average value, is the y average value of the axis coordinates in the first average value, P xi is the i axis coordinate value of the x n-th fiducial point in the first neighborhood, P yi is the i axis coordinate value of the y n-th fiducial point in the first neighborhood, is the x average value of the axis coordinates in the second average value, is the y average value of the axis coordinates in the second average value, P xj is the j axis coordinate value of the x n-th fiducial point in the second neighborhood, P yj is the j y-axis coordinate value of the n-th fiducial point in the second neighborhood, and K is the first quantity.

[0128] Optionally, the calculation module 402 is configured to:

[0129] Calculate the offset score of the first fiducial point through the following formula:

[0130] ;

[0131] where D is the offset score between the first neighborhood and the second neighborhood, is the x average value of the axis coordinates in the first average value, is the y average value of the axis coordinates in the first average value, is the x average value of the axis coordinates in the second average value, is the y average value of the axis coordinates in the second average value.

[0132] Optionally, the neighborhood module 401 is configured to:

[0133] Calculate the Euclidean distance between other fiducial points and the first fiducial point according to the preset coordinates of the fiducial points, and select the first quantity of fiducial points closest to the first fiducial point according to the Euclidean distance to form the first neighborhood, where the other fiducial points are the fiducial points in the fiducial point set except the first fiducial point;

[0134] Determine the actual distance between other beacon points and the first beacon point according to the actually measured signal strength value, and select the first number of beacon points closest to the first beacon point according to the actual distance to form a second neighborhood. The other beacon points are the beacon points in the beacon point set except the first beacon point.

[0135] Optionally, the neighborhood module 401 is configured to:

[0136] Determine the actual distance between other beacon points and the first beacon point through the following formula:

[0137] RSSI = RSSI 0 -10nlog 10 (d) + Xs ;

[0138] Wherein, RSSI is the signal strength value received by the first beacon point, RSSI 0 is the signal strength value emitted by the other beacon point, n is the path loss exponent, d is the actual distance between the other beacon point and the first beacon point, Xs is the shadow attenuation, which is a random variable following a Gaussian distribution.

[0139] Optionally, the execution module 404 is configured to:

[0140] Calculate the weighted distance through the following formula:

[0141] SWD ( q ) = ω·SD ([[]] q );

[0142] Wherein, SWD ([[]] q ) is the weighted distance of the first beacon point q , ω is the weight value, SD ([[]] q ) is the target distance from the first beacon point to the second beacon point,

[0143] Calculate the local density of the first beacon point through the following formula:

[0144] ;

[0145] Wherein, ρ ([[]] q ) is the local density of the first beacon point q ,

[0146] Calculate the subspace offset factor of the first signal punctuation point by the following formula:

[0147] ;

[0148] wherein, is the subspace offset factor of the first signal punctuation point q , and is the subspace density of the first signal punctuation point.

[0149] It should be noted that when the device provided in the above embodiment realizes its functions, only the division of the above function modules is used for illustration. In actual applications, the above functions can be allocated to different function modules according to needs, that is, the internal structure of the device is divided into different function modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process can be seen in the method embodiment, which will not be elaborated here.

[0150] This embodiment also discloses an electronic device. Referring to Figure 5 the electronic device may include: at least one processor 501, at least one communication bus 502, a user interface 503, a network interface 504, and at least one memory 505.

[0151] Among them, the communication bus 502 is used to realize the connection and communication between these components.

[0152] Among them, the user interface 503 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 503 may further include a standard wired interface and a wireless interface.

[0153] Among them, the network interface 504 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0154] Among them, the processor 501 may include one or more processing cores. The processor 501 connects various parts within the entire server through various interfaces and lines. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 505, and by calling the data stored in the memory 505, it executes various functions of the server and processes data. Optionally, the processor 501 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 501 may integrate a combination of one or several of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface, application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 501 and may be implemented separately through a single chip.

[0155] Among them, the memory 505 may include random access memory (RAM) and may also include read-only memory. Optionally, the memory 505 includes a non-transitory computer-readable storage medium. The memory 505 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 505 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store the data involved in the above-mentioned various method embodiments. Optionally, the memory 505 may also be at least one storage device located far from the aforementioned processor 501. As Figure 5 shown, the memory 505, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for the detection method of indoor positioning Bluetooth beacon abnormal points.

[0156] In Figure 5In the electronic device shown, the user interface 503 is mainly used to provide an interface for the user to input and obtain the data input by the user; and the processor 501 can be used to call the application program stored in the memory 505 for detecting abnormal points of the indoor positioning Bluetooth beacon. When executed by one or more processors 501, the electronic device is caused to execute the method of one or more of the above embodiments.

[0157] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0158] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0159] In the several embodiments provided by this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling, direct coupling, or communication connection can be through some service interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical or other form.

[0160] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0161] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0162] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory 505 and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of various embodiments of this application. The aforementioned memory 505 includes: various media such as USB flash drives, mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0163] The foregoing are only exemplary embodiments of the present disclosure and should not be used to limit the scope of the present disclosure. That is, all equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. Those skilled in the art will readily think of other implementation manners of the present disclosure after considering the disclosure of the specification. This application aims to cover any variations, uses, or adaptive changes of the present disclosure, and these variations, uses, or adaptive changes follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not recorded in the present disclosure. The specification and embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for detecting abnormal points of indoor positioning Bluetooth beacons, characterized in that, Applied to an indoor positioning platform, the method includes: Obtain a first neighborhood and a second neighborhood of a first beacon point from a set of beacon points. The first neighborhood is a set of the first number of nearest neighbor beacon points of the first beacon point in a preset scenario, and the second neighborhood is a set of the first number of nearest neighbor beacon points of the first beacon point in the current scenario. The first beacon point is any one of the set of beacon points; Calculate a first average value of the coordinates of the beacon points in the first neighborhood, and calculate a second average value of the coordinates of the beacon points in the second neighborhood. Calculate an offset score of the first beacon point according to the first average value and the second average value; Calculate an average offset score of all the beacon points in the set of beacon points, and compare the offset score with the average offset score; Calculate a weighted distance according to the comparison result, calculate a subspace offset factor according to the weighted distance, and mark the beacon points with the subspace offset factor greater than a threshold as abnormal points. The calculating the weighted distance according to the comparison result and calculating the subspace offset factor according to the weighted distance includes: When the offset score is greater than the average offset score, determine a second beacon point that is the second closest to the first beacon point, and calculate a target distance between the first beacon point and the second beacon point; Calculate a weighted distance of the first beacon point according to the target distance and a preset weight value, and calculate a local density of the first beacon point according to the weighted distance; Calculate an average value of the local densities of all the beacon points in the first neighborhood to obtain a subspace density, and calculate the subspace offset factor according to the subspace density and the local density of the first beacon point. The obtaining the first neighborhood and the second neighborhood of the first beacon point from the set of beacon points includes: Calculate the Euclidean distance between other beacon points and the first beacon point according to the preset coordinates of the beacon points, and select the first number of beacon points closest to the first beacon point according to the Euclidean distance to form the first neighborhood. The other beacon points are the beacon points in the set of beacon points except the first beacon point; Determine the actual distance between other beacon points and the first beacon point according to the actually measured signal strength value, and select the first number of beacon points closest to the first beacon point according to the actual distance to form the second neighborhood. The other beacon points are the beacon points in the set of beacon points except the first beacon point.

2. The detection method for abnormal points of indoor positioning Bluetooth beacons according to claim 1, characterized in that The calculating the first average value of the coordinates of the beacon points in the first neighborhood and calculating the second average value of the coordinates of the beacon points in the second neighborhood includes: Calculate the first average value and the second average value by the following formula: ； ； Among them, is the average value of the x axis coordinates in the first average value, is the average value of the y axis coordinates in the first average value, P xi is the i -th fiducial point's x axis coordinate value in the first neighborhood, P yi is the i -th fiducial point's y axis coordinate value in the first neighborhood, is the average value of the x axis coordinates in the second average value, is the average value of the y axis coordinates in the second average value, P xj is the j -th fiducial point's x axis coordinate value in the second neighborhood, P yj is the j -th fiducial point's y-axis coordinate value, and K is the first quantity.

3. The detection method for abnormal points of indoor positioning Bluetooth beacons according to claim 2, characterized in that, The calculating the offset score of the first beacon point according to the first average value and the second average value includes: Calculate the offset score of the first beacon point by the following formula: ； Among them, D is the offset score of the first neighborhood and the second neighborhood, which is the x average value of the axis coordinates in the first average value, which is the y average value of the axis coordinates in the first average value, which is the x average value of the axis coordinates in the second average value, which is the y average value of the axis coordinates in the second average value.

4. The method for detecting abnormal points of indoor positioning Bluetooth beacons according to claim 1, wherein The determining the actual distance between other beacon points and the first beacon point according to the actually measured signal strength value includes: Determine the actual distance between other beacon points and the first beacon point by the following formula: ； Wherein, RSSI is the signal strength value received by the first beacon point, RSSI 0 is the signal strength value emitted by the other beacon points, n is the path loss exponent, d is the actual distance between the other beacon points and the first beacon point, Xs is the shadow fading, which is a random variable following a Gaussian distribution.

5. The detection method for abnormal points of indoor positioning Bluetooth beacons according to claim 1, characterized in that The calculating the weighted distance according to the comparison result and calculating the subspace offset factor according to the weighted distance includes: Calculate the weighted distance by the following formula: ； Among them, SWD ( q ) is the weighted distance of the first fiducial point q , ω is the weight value, SD ( q ) is the target distance from the first fiducial point to the second fiducial point Calculate the local density of the first fiducial point by the following formula: ； Among them, ρ ( q ) is the local density of the first fiducial point q and Calculate the subspace offset factor of the first fiducial point by the following formula: ； Among them, is the subspace offset factor of the first signal punctuation point q , and is the subspace density of the first signal punctuation point.

6. An indoor positioning Bluetooth beacon anomaly detection system for implementing the indoor positioning Bluetooth beacon anomaly detection method described in any one of claims 1 to 5, characterized in that, Comprising a neighborhood module, a calculation module, a comparison module and an execution module, wherein: The neighborhood module is configured to obtain a first neighborhood and a second neighborhood of a first fiducial point from a set of fiducial points, the first neighborhood being a set of the first number of nearest neighbor fiducial points of the first fiducial point in a preset scenario, the second neighborhood being a set of the first number of nearest neighbor fiducial points of the first fiducial point in the current scenario, and the first fiducial point being any one of the set of fiducial points; The calculation module is configured to calculate a first average value of the coordinates of the fiducial points in the first neighborhood, and calculate a second average value of the coordinates of the fiducial points in the second neighborhood, and calculate an offset score of the first fiducial point according to the first average value and the second average value; The comparison module is configured to calculate an average offset score of all the fiducial points in the set of fiducial points, and compare the offset score with the average offset score; The execution module is configured to calculate a weighted distance according to the comparison result, calculate a subspace offset factor according to the weighted distance, and mark the fiducial points with the subspace offset factor greater than a threshold as outliers, The calculating the weighted distance according to the comparison result and calculating the subspace offset factor according to the weighted distance includes: When the offset score is greater than the average offset score, determine a second fiducial point that is the second closest to the first fiducial point, and calculate a target distance between the first fiducial point and the second fiducial point; Calculate the weighted distance of the first fiducial point according to the target distance and a preset weight value, and calculate the local density of the first fiducial point according to the weighted distance; Calculate the mean value of the local densities of all the fiducial points in the first neighborhood to obtain a subspace density, and calculate the subspace offset factor according to the subspace density and the local density of the first fiducial point, The obtaining the first neighborhood and the second neighborhood of the first fiducial point from the set of fiducial points includes: According to the preset coordinates of the fiducial points, calculate the Euclidean distance between other fiducial points and the first fiducial point, and select the first number of fiducial points closest to the first fiducial point according to the Euclidean distance to form the first neighborhood, where the other fiducial points are the fiducial points in the set of fiducial points except the first fiducial point; Determine the actual distance between other fiducial points and the first fiducial point according to the actually measured signal strength value, and select the first number of fiducial points closest to the first fiducial point according to the actual distance to form the second neighborhood, where the other fiducial points are the fiducial points in the set of fiducial points except the first fiducial point.

7. An electronic device, characterized in that, Comprising a processor, a memory, a user interface and a network interface, the memory is used for storing instructions, the user interface and the network interface are both used for communicating with other devices, and the processor is used for executing the instructions stored in the memory, so that the electronic device executes the method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed, perform the method according to any one of claims 1-5.

Images