Indoor positioning method, apparatus, computer device, and storage medium
By combining Bluetooth signals and light intensity, and utilizing the combination of light intensity points and the difference in time vectors, the problem of low indoor positioning accuracy was solved, and higher precision indoor positioning was achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHANGHAI PUDONG DEVELOPMENT BANK
- Filing Date
- 2022-12-16
- Publication Date
- 2026-06-02
AI Technical Summary
In indoor environments, positioning accuracy is low when based on a single signal, making it difficult to accurately pinpoint the user's location.
By combining Bluetooth signals and light intensity, the initial positioning coordinates and area are determined through Bluetooth signals. The final location of the device is accurately located by utilizing the combination of light intensity points and the difference in time vectors.
It improves the accuracy of indoor positioning by combining Bluetooth signals and light intensity to more accurately determine the device's final location.
Smart Images
Figure CN116008908B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of indoor positioning technology, and in particular to an indoor positioning method, apparatus, computer equipment, and storage medium. Background Technology
[0002] Indoors, users may not be able to accurately locate their position due to floor obstruction or weak GPS signal, making indoor positioning difficult.
[0003] Currently, most methods for indoor positioning rely on a single signal. This signal is processed to obtain the user's location coordinates, thus achieving indoor positioning. However, methods based on a single signal suffer from low accuracy. Summary of the Invention
[0004] Therefore, it is necessary to provide an indoor positioning method, device, computer equipment, and storage medium that can improve the accuracy of indoor positioning in response to the above-mentioned technical problems.
[0005] Firstly, this application provides an indoor positioning method for locating target devices within a target area. The target area contains Bluetooth devices and light source devices. The target area is defined with multiple light intensity points, each corresponding to a light intensity value collected at its location from the light source device. The method includes:
[0006] Based on the Bluetooth signal emitted by the Bluetooth device collected by the target device, the initial positioning coordinates of the target device are obtained, and an initial positioning area containing the initial positioning coordinates is determined according to the Bluetooth positioning error.
[0007] Determine the target light intensity points that fall within the initial positioning area, and obtain multiple light intensity space vectors by combining different target light intensity points, which are composed of the light intensity corresponding to each of the different target light intensity points.
[0008] Multiple light intensities collected by the target device at multiple time points are obtained to form a light intensity time-series vector;
[0009] Based on the difference between the light intensity temporal vector and the light intensity spatial vector, the target light intensity point is determined, and based on the position coordinates of the target light intensity point, the final positioning coordinates of the target device are determined.
[0010] In one embodiment, the step of combining different target light intensity points to obtain multiple light intensity space vectors, which are combinations of the light intensity corresponding to each of the different target light intensity points, includes:
[0011] Determine the target light intensity point pairs whose line distance between them is a preset distance within the initial positioning area;
[0012] Determine the target light intensity points that the line connecting the target light intensity point pairs passes through in the initial positioning area, and construct a corresponding light intensity space vector based on the target light intensity points passed through and the target light intensity point pairs.
[0013] In one embodiment, determining the target light intensity point based on the difference between the light intensity temporal vector and the light intensity spatial vector, and determining the final positioning coordinates of the target device based on the position coordinates of the target light intensity point, includes:
[0014] Calculate the similarity between the light intensity temporal vector and each light intensity spatial vector;
[0015] If there are similarities not exceeding a preset threshold, sort them according to similarity and select a preset number of light intensity space vectors;
[0016] Cluster the preset number of light intensity spatial vectors to obtain multiple clusters;
[0017] Calculate the average similarity of all light intensity spatial vectors in each cluster, and determine the target cluster with the smallest average similarity.
[0018] The final positioning coordinates of the target device are determined based on the position coordinates of the target light intensity points corresponding to each light intensity spatial vector in the target cluster.
[0019] In one embodiment, the method further includes:
[0020] If all similarity values are greater than a preset threshold, the initial positioning coordinates will be used as the final positioning coordinates of the target device.
[0021] In one embodiment, the process of determining the preset quantity includes:
[0022] Obtain the expected value corresponding to all similarities;
[0023] Based on the expected value and the reference coefficient, determine the reference value;
[0024] Calculate the difference between each similarity and the reference value, count the total number of similarities with negative differences, and use the total number as a preset number.
[0025] In one embodiment, the process of determining the reference coefficient includes:
[0026] Determine multiple sample location coordinates, and obtain the sample light intensity temporal vector and the corresponding multiple sample light intensity spatial vectors formed by the sample device at the sample location coordinates;
[0027] Calculate the sample similarity between the sample light intensity time-series vector and the corresponding sample light intensity space vector, and obtain the expected value of the sample corresponding to all sample similarities;
[0028] Obtain the intermediate value of the reference coefficient, and determine the sample reference value based on the expected value of the sample and the intermediate value;
[0029] Calculate the difference between the similarity of each sample and the reference value of the sample, count the total number of samples with negative differences, and use the total number of samples as the reference number.
[0030] Sort the samples according to their similarity and select the reference number of sample light intensity space vectors;
[0031] Cluster the light intensity space vectors of the reference number of samples to obtain multiple sample clusters;
[0032] Calculate the average similarity of the light intensity space vectors of all samples in each sample cluster, and determine the target cluster of the sample with the smallest average similarity.
[0033] The predicted positioning coordinates of the sample device are determined based on the position coordinates of the target light intensity points corresponding to the light intensity space vectors of each sample in the target cluster.
[0034] The positioning error between the predicted positioning coordinates and the sample position coordinates is obtained and used as the positioning error corresponding to the sample position coordinates at the intermediate value.
[0035] Based on the positioning error corresponding to the location coordinates of each sample, the average positioning error corresponding to the intermediate value is determined;
[0036] By adjusting the intermediate values multiple times, and determining the average positioning error corresponding to each intermediate value according to the above process;
[0037] Based on the average positioning error corresponding to each intermediate value, the actual value of the reference coefficient is determined from all intermediate values.
[0038] Secondly, this application also provides an indoor positioning device for locating target devices within a target area. The target area contains Bluetooth devices and light source devices, and the target area defines multiple light intensity points, each corresponding to a light intensity value collected at its location by the light source device. The device includes:
[0039] An initial positioning module is used to locate the target device based on the Bluetooth signal emitted by the Bluetooth device collected by the target device, obtain the initial positioning coordinates of the target device, and determine an initial positioning area containing the initial positioning coordinates based on the Bluetooth positioning error.
[0040] The spatial combination module is used to determine the target light intensity points falling into the initial positioning area. By combining different target light intensity points, multiple light intensity spatial vectors are obtained by combining the light intensity corresponding to each of the different target light intensity points.
[0041] The timing composition module is used to acquire multiple light intensities collected by the target device at multiple time points to form a light intensity timing vector;
[0042] The final positioning module is used to determine the target light intensity point based on the difference between the light intensity temporal vector and the light intensity spatial vector, and to determine the final positioning coordinates of the target device based on the position coordinates of the target light intensity point.
[0043] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the methods in any of the above embodiments.
[0044] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the methods in any of the above embodiments.
[0045] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the methods in any of the above embodiments.
[0046] The aforementioned indoor positioning method, device, computer equipment, and storage medium locate the target device by collecting Bluetooth signals, obtaining the initial positioning coordinates of the target device, determining the initial positioning area based on the Bluetooth positioning error and the initial positioning coordinates, combining the light intensity corresponding to the target light intensity point falling within the initial positioning area to obtain multiple light intensity spatial vectors, and acquiring a light intensity temporal vector composed of multiple light intensity samples collected by the target device at multiple time points. Based on the difference between the light intensity temporal vector and the light intensity spatial vector, the target light intensity point is determined, and the final positioning coordinates of the target device are determined based on the position coordinates of the target light intensity point. Compared to the traditional technology that relies on a single signal for indoor positioning, which has low accuracy, this application determines the initial positioning coordinates and initial positioning area through Bluetooth signals, identifies the target light intensity point within the initial positioning area based on light intensity, and determines the final positioning coordinates of the target device based on the position coordinates of the target light intensity point. By using a combination of Bluetooth signals and light intensity for indoor positioning, the final positioning coordinates of the target device can be obtained more accurately, improving the accuracy of indoor positioning. Attached Figure Description
[0047] Figure 1 This is a flowchart illustrating the indoor positioning method provided in the embodiments of this application;
[0048] Figure 2 This is a schematic diagram of the process for obtaining the light intensity spatial vector in one embodiment;
[0049] Figure 3 This is a flowchart illustrating the process of determining the final positioning coordinates of a target device in one embodiment;
[0050] Figure 4 This is a flowchart illustrating the process of determining a preset quantity in one embodiment;
[0051] Figure 5 This is a structural block diagram of an indoor positioning device provided in an embodiment of this application;
[0052] Figure 6 This is an internal structural diagram of a computer device provided in an embodiment of this application. Detailed Implementation
[0053] 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.
[0054] The indoor positioning method provided in this application is applied to locate a target device within a target area. The target area contains Bluetooth devices and light source devices. Multiple light intensity points are defined within the target area, each corresponding to a light intensity value generated by the light source device at its location. The target area is the area to be located indoors, including underground shopping streets, underground parking lots, or other semi-enclosed indoor areas unaffected by external light; the specific location is not limited. The Bluetooth device is a device capable of transmitting Bluetooth signals, and the light source device is a device capable of providing indoor lighting. The target device is a device capable of collecting the Bluetooth signals emitted by the Bluetooth device and the light intensity value generated by the light source device.
[0055] The specific distribution of Bluetooth devices and light sources within the target area can be as follows: the light sources are placed at equal intervals within the target area, and the Bluetooth devices are placed inside the light sources. For example, the light source is an E27 model light bulb, and the Bluetooth device is a low-power Bluetooth chip, with the low-power Bluetooth chip installed inside the E27 model light bulb. Alternatively, the distribution of Bluetooth devices and light sources within the target area can also be as follows: the light sources and Bluetooth devices are placed at equal intervals within the target area, or they are evenly distributed within the target area. The specific distribution of Bluetooth devices and light sources within the target area is not limited without affecting the implementation of the indoor positioning method provided in this embodiment.
[0056] The target area is defined by multiple light intensity points, which are the locations of the light source devices within the target area. Each light source device within the target area has a corresponding light intensity point.
[0057] Figure 1 This is a flowchart illustrating the indoor positioning method provided in this application embodiment. Taking the application of this method to a computer device as an example, it includes the following steps:
[0058] S101, based on the Bluetooth signal emitted by the Bluetooth device collected by the target device, the initial positioning coordinates of the target device are obtained, and the initial positioning area containing the initial positioning coordinates is determined according to the Bluetooth positioning error.
[0059] In this embodiment, the target device has a pre-trained Bluetooth positioning model. The Bluetooth signal is input into the trained Bluetooth positioning model, and the initial positioning coordinates of the target device are output. The Bluetooth positioning model is not limited here. In some embodiments, the Bluetooth positioning model is used as an example to train a machine learning decision tree model. During model training, the RSS (Reduced Simplified Information Settlement) value of the Bluetooth signal is used as a feature, and the corresponding location coordinates of the Bluetooth signal are used as labels. The features and labels are input into the decision tree model for training, resulting in a trained Bluetooth positioning model. The spatial Euclidean distance between the predicted location coordinates and the actual location coordinates is used as the Bluetooth positioning error.
[0060] Based on the Bluetooth positioning error, an initial positioning area containing the initial positioning coordinates is determined. The initial positioning area can be determined by using the initial positioning coordinates as the center and the Bluetooth positioning error as the radius; or by using the initial positioning coordinates as the center of a square and twice the Bluetooth positioning error as the side length of the square.
[0061] S102, determine the target light intensity points that fall into the initial positioning area, and obtain multiple light intensity space vectors by combining different target light intensity points.
[0062] The target light intensity point includes the coordinates of the light intensity point's location and the light intensity corresponding to that location.
[0063] In this embodiment, there are several ways to combine different target light intensity points. One of them is to combine different target light intensity points into line segments according to a preset length. Another way is to select a set number of adjacent target light intensity points and combine them together.
[0064] In one embodiment, by combining different target light intensity points, multiple light intensity space vectors are obtained, which are combinations of the light intensity corresponding to each of the different target light intensity points. A flowchart illustrating the process of obtaining the light intensity space vectors is shown below. Figure 2 As shown, it includes the following:
[0065] S201, determine the target light intensity point pair with a line distance of preset distance in the initial positioning area.
[0066] The line distance represents the straight-line distance between two target light intensity points within the initial positioning area. The preset distance is manually set, and the specific value is not limited. It can be understood that the number of identified target light intensity point pairs is at least one.
[0067] S202, determine the target light intensity points that the line formed by the target light intensity point pairs passes through in the initial positioning area, and construct the corresponding light intensity space vector based on the target light intensity points and target light intensity point pairs that have passed through.
[0068] The identified target light intensity point pairs, along with the target light intensity points that pass through the initial positioning area, form the corresponding light intensity space vector.
[0069] Taking (x1, y1, q1) and (x3, y3, q3) as a pair of target light intensity points, where (x1, y1) is the position coordinate of the first target light intensity point and q1 is the light intensity at the position of the first target light intensity point, (x3, y3) is the position coordinate of the third target light intensity point and q3 is the light intensity at the position of the third target light intensity point, and passing through the second target light intensity point (x2, y2, q2) in the initial positioning area, where (x2, y2) is the position coordinate of the second target light intensity point and q2 is the light intensity at the position of the second target light intensity point, the resulting light intensity space vector is N = (q1, q2, q3).
[0070] S103, acquire multiple light intensities collected by the target device at multiple time points to form a light intensity time sequence vector.
[0071] The target device can be mobile or stationary. The light intensity data collected by the target device at multiple time points may be different or the same. These multiple time points are manually set. For example, if we collect light intensity data at 0.2-second intervals within a 1-second timeframe, the light intensity time sequence vector would be M = (q4, q5, q6, q7, q8).
[0072] S104. Based on the difference between the light intensity time vector and the light intensity space vector, determine the target light intensity point, and based on the position coordinates of the target light intensity point, determine the final positioning coordinates of the target device.
[0073] In one embodiment, a flowchart illustrating the process of determining a target light intensity point based on the difference between the light intensity temporal vector and the light intensity spatial vector, and determining the final positioning coordinates of the target device based on the position coordinates of the target light intensity point, is shown below. Figure 3 As shown, it includes the following steps:
[0074] S301, calculate the similarity between the temporal vector of light intensity and each spatial vector of light intensity.
[0075] The DTW (Dynamic Time Warping) algorithm is used to calculate the similarity between the light intensity temporal vector and each light intensity spatial vector. This method can calculate the similarity between the light intensity temporal vector and each light intensity spatial vector even when the light intensity temporal vector and the light intensity spatial vector are of unequal length.
[0076] S302, if there are similarities not greater than a preset threshold, sort them according to similarity and select a preset number of light intensity space vectors.
[0077] In this embodiment, the similarity between the light intensity temporal vector and each light intensity spatial vector is sorted from smallest to largest. A preset number of light intensity spatial vectors with the highest similarity are selected. The final positioning coordinates of the target device are determined based on the preset number of light intensity spatial vectors with low similarity, which can improve the accuracy of the final positioning coordinates of the target device.
[0078] In one embodiment, a flowchart illustrating the process of determining the preset quantity is shown below. Figure 4 As shown, the process of determining the preset quantity can be performed before step S302 or after sorting by similarity, and includes the following:
[0079] S401, obtain the expected value corresponding to all similarities.
[0080] Where E(D) = c, D is all similarities, and c is the expected value corresponding to all similarities.
[0081] S402, determine the reference value based on the expected value and the reference coefficient.
[0082] Where b = (1 + a) × c, a > 0, b is a reference value, and a is a reference coefficient. Specifically, the reference coefficient is determined through training.
[0083] S403, calculate the difference between each similarity and the reference value, count the total number of similarities with negative differences, and use the total number as the preset number.
[0084] Where Di-b<0, Di is the i-th similarity, and the total number of Di is used as the preset number.
[0085] S303, clusters a preset number of light intensity spatial vectors to obtain multiple clusters.
[0086] Using a clustering algorithm, based on the Euclidean distance between the position coordinates corresponding to a predetermined number of light intensity spatial vectors, multiple clusters are obtained. The clustering algorithm can be KNN (K-Nearest Neighbors), W-KNN (Weighted K-Nearest Neighbors), or other implementable clustering algorithms, which are not limited here.
[0087] S304 Calculate the average similarity of all light intensity spatial vectors in each cluster, and determine the target cluster with the smallest average similarity.
[0088] For example, in a cluster, there are three light intensity spatial vectors N1, N2, and N3, with corresponding similarities D1, D2, and D3, respectively. Here, D1 is the similarity between the light intensity temporal vector M and the light intensity spatial vector N1, D2 is the similarity between the light intensity temporal vector M and the light intensity spatial vector N2, and D3 is the similarity between the light intensity temporal vector M and the light intensity spatial vector N3. The average of D1, D2, and D3 is calculated as the average similarity of this cluster.
[0089] The cluster with the lowest average similarity among all clusters is selected as the target cluster.
[0090] S305, determine the final positioning coordinates of the target device based on the position coordinates of the target light intensity points corresponding to each light intensity spatial vector in the target cluster.
[0091] In some embodiments, the average value of the position coordinates of the target light intensity points corresponding to each light intensity spatial vector in the target cluster is calculated as the final positioning coordinates of the target device.
[0092] In other embodiments, the position coordinates of the target light intensity points corresponding to each light intensity spatial vector in the target cluster are weighted and averaged to obtain the final positioning coordinates of the target device.
[0093] The indoor positioning method provided in this embodiment uses Bluetooth signals collected by the target device for positioning to obtain the initial positioning coordinates of the target device. Based on the Bluetooth positioning error and the initial positioning coordinates, an initial positioning area is determined. The light intensity corresponding to the target light intensity point falling within the initial positioning area is combined to obtain multiple light intensity spatial vectors. A light intensity temporal vector composed of multiple light intensity data collected by the target device at multiple time points is also obtained. Based on the difference between the light intensity temporal vector and the light intensity spatial vector, the target light intensity point is determined. The final positioning coordinates of the target device are determined based on the position coordinates of the target light intensity point. Compared to traditional technologies that rely on a single signal for indoor positioning, which have low accuracy, this application uses Bluetooth signals to determine the initial positioning coordinates and initial positioning area, identifies the target light intensity point within the initial positioning area based on light intensity, and determines the final positioning coordinates of the target device based on the position coordinates of the target light intensity point. By combining Bluetooth signals and light intensity for indoor positioning, the final positioning coordinates of the target device can be obtained more accurately, improving the accuracy of indoor positioning.
[0094] In one embodiment, the similarity between the light intensity temporal vector and each light intensity spatial vector is calculated, and if all similarities are greater than a preset threshold, the initial positioning coordinates are used as the final positioning coordinates of the target device.
[0095] In this embodiment, if the similarity between the light intensity temporal vector and each light intensity spatial vector is greater than a preset threshold, it means that the light intensity temporal vector and each light intensity spatial vector are not similar. At this time, using light intensity to locate the final positioning coordinates of the target device will cause a large error. Using the initial positioning coordinates as the final positioning coordinates of the target device can ensure the accuracy of the final positioning coordinates of the target device.
[0096] In some embodiments, the process of determining reference coefficients through training involves determining multiple sample position coordinates and obtaining the sample light intensity temporal vector and corresponding multiple sample light intensity spatial vectors formed by the sample device at the sample position coordinates. Here, the sample position coordinates are determined based on the position coordinates of Bluetooth devices and light source devices distributed within the target area; the sample device is a device capable of collecting Bluetooth signals emitted by the Bluetooth device and light intensity generated by the light source device; the sample light intensity temporal vector is composed of multiple light intensity intensities collected by the sample device at multiple time points; and the sample light intensity spatial vector is obtained by combining the light intensity intensities corresponding to the target light intensity points within the initial positioning area containing the sample position coordinates. A time period contains multiple time points corresponding to one sample light intensity temporal vector, and one sample light intensity temporal vector corresponds to at least one sample light intensity spatial vector; there can be multiple time periods.
[0097] Calculate the sample similarity between the temporal vector of sample light intensity and the corresponding spatial vector of each sample light intensity, and obtain the expected value of the sample corresponding to all sample similarities; obtain the intermediate value of the reference coefficient, and determine the sample reference value based on the sample expected value and the intermediate value; calculate the difference between each sample similarity and the sample reference value, count the total number of samples with negative differences, and use the total number of samples as the reference number.
[0098] The samples are sorted according to similarity, and a reference number of sample light intensity space vectors are selected. These reference number of sample light intensity space vectors are then clustered to obtain multiple sample clusters. The average similarity of all sample light intensity space vectors in each sample cluster is calculated, and the sample target cluster with the smallest average similarity is determined. Based on the position coordinates of the target light intensity points corresponding to the sample light intensity space vectors in each sample target cluster, the predicted positioning coordinates of the sample device are determined.
[0099] Obtain the positioning error between the predicted positioning coordinates and the sample position coordinates, and use it as the positioning error corresponding to the sample position coordinates at the intermediate value; determine the average positioning error corresponding to the intermediate value based on the positioning error corresponding to each sample position coordinate.
[0100] By adjusting the intermediate values multiple times, and following the above process, the average positioning error corresponding to each intermediate value is determined.
[0101] Based on the average positioning error corresponding to each intermediate value, determine the actual value of the reference coefficient from all intermediate values; select the intermediate value corresponding to the smallest average positioning error among all intermediate values as the actual value of the reference coefficient.
[0102] In this embodiment, by obtaining the actual values of the reference coefficients through training, it is possible to ensure that the positioning error between the predicted positioning coordinates and the sample position coordinates is small. In practical applications, this ensures the accuracy of the final positioning coordinates of the target device.
[0103] It should be understood that although the steps in the flowcharts of the embodiments described above 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 embodiments described above 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 of other steps.
[0104] Based on the same inventive concept, this application also provides an indoor positioning device for implementing the indoor positioning method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more indoor positioning device embodiments provided below can be found in the limitations of the indoor positioning method described above, and will not be repeated here.
[0105] See Figure 5 , Figure 5 This is a structural block diagram of an indoor positioning device provided in an embodiment of this application. The device 500 is used to locate target devices within a target area. Bluetooth devices and light source devices are distributed within the target area. Multiple light intensity points are defined within the target area, each corresponding to a light intensity value collected from the light source device at its location. The device 500 includes: an initial positioning module 501, a spatial combination module 502, a timing composition module 503, and a final positioning module 504, wherein:
[0106] The initial positioning module 501 is used to locate the target device based on the Bluetooth signal emitted by the Bluetooth device collected by the target device, obtain the initial positioning coordinates of the target device, and determine the initial positioning area containing the initial positioning coordinates according to the Bluetooth positioning error.
[0107] The spatial combination module 502 is used to determine the target light intensity points falling into the initial positioning area. By combining different target light intensity points, multiple light intensity spatial vectors are obtained by combining the light intensity corresponding to each of the different target light intensity points.
[0108] The timing composition module 503 is used to acquire multiple light intensity values collected by the target device at multiple time points to form a light intensity timing vector.
[0109] The final positioning module 504 is used to determine the target light intensity point based on the difference between the light intensity time vector and the light intensity space vector, and to determine the final positioning coordinates of the target device based on the position coordinates of the target light intensity point.
[0110] The indoor positioning device provided in this embodiment locates the target device by collecting Bluetooth signals, obtaining the initial positioning coordinates of the target device. Based on the Bluetooth positioning error and the initial positioning coordinates, an initial positioning area is determined. The light intensity corresponding to the target light intensity point falling within the initial positioning area is combined to obtain multiple light intensity spatial vectors. A light intensity temporal vector composed of multiple light intensity data collected by the target device at multiple time points is also obtained. Based on the difference between the light intensity temporal vector and the light intensity spatial vector, the target light intensity point is determined. The final positioning coordinates of the target device are determined based on the position coordinates of the target light intensity point. Compared to traditional technologies that rely on a single signal for indoor positioning, which have low accuracy, this application determines the initial positioning coordinates and initial positioning area using Bluetooth signals, identifies the target light intensity point within the initial positioning area based on light intensity, and determines the final positioning coordinates of the target device based on the position coordinates of the target light intensity point. By combining Bluetooth signals and light intensity for indoor positioning, the final positioning coordinates of the target device can be obtained more accurately, improving the accuracy of indoor positioning.
[0111] Optionally, the space combination module 502 includes:
[0112] The light intensity point pair determination unit is used to determine the target light intensity point pairs connected by a preset distance in the initial positioning area;
[0113] The spatial vector constructing unit is used to determine the target light intensity points that the line formed by the target light intensity point pair passes through in the initial positioning area, and to construct the corresponding light intensity spatial vector based on the target light intensity points and the target light intensity point pair that it passes through.
[0114] Optionally, the final positioning module 504 includes:
[0115] The similarity calculation unit is used to calculate the similarity between the light intensity temporal vector and each light intensity spatial vector.
[0116] The spatial vector selection unit is used to sort and select a preset number of light intensity spatial vectors according to their similarity when there is a similarity not greater than a preset threshold.
[0117] Clustering unit, used to cluster a preset number of light intensity spatial vectors to obtain multiple clusters;
[0118] The target cluster determination unit is used to calculate the average similarity of all light intensity spatial vectors in each cluster and determine the target cluster with the smallest average similarity.
[0119] The first final positioning unit is used to determine the final positioning coordinates of the target device based on the position coordinates of the target light intensity points corresponding to each light intensity spatial vector in the target cluster.
[0120] Optionally, the final positioning module 504 also includes:
[0121] The second final positioning unit is used to take the initial positioning coordinates as the final positioning coordinates of the target device when all similarities are greater than a preset threshold.
[0122] Optionally, the final positioning module 504 further includes a preset quantity determination unit, which is used to obtain the expected value corresponding to all similarities; determine the reference value according to the expected value and the reference coefficient; calculate the difference between each similarity and the reference value; count the total number of similarities with negative differences; and use the total number as the preset quantity.
[0123] Optionally, the device 500 further includes a reference coefficient determination module, which is used to determine multiple sample position coordinates and obtain the sample light intensity time-series vector and the corresponding multiple sample light intensity spatial vectors formed by the sample device at the sample position coordinates.
[0124] Calculate the sample similarity between the temporal vector of sample light intensity and the corresponding spatial vector of each sample light intensity, and obtain the expected value of the sample corresponding to all sample similarities;
[0125] Obtain the intermediate value of the reference coefficient, and determine the sample reference value based on the expected value and the intermediate value;
[0126] Calculate the difference between the similarity of each sample and the sample reference value, count the total number of samples with negative differences, and use the total number of samples as the reference number.
[0127] Sort the samples according to their similarity and select a reference number of sample light intensity space vectors;
[0128] Clustering is performed on the light intensity spatial vectors of a reference number of samples to obtain multiple sample clusters;
[0129] Calculate the average similarity of the light intensity space vectors of all samples in each sample cluster, and determine the target cluster of the sample with the smallest average similarity.
[0130] Based on the position coordinates of the target light intensity points corresponding to the light intensity space vectors of each sample in the sample target cluster, the predicted positioning coordinates of the sample device are determined.
[0131] Obtain the positioning error between the predicted positioning coordinates and the sample position coordinates, and use it as the positioning error corresponding to the sample position coordinates at the intermediate value.
[0132] Based on the positioning error corresponding to the location coordinates of each sample, determine the average positioning error corresponding to the intermediate value;
[0133] By adjusting the intermediate values multiple times, and following the above process, the average positioning error corresponding to each intermediate value is determined.
[0134] Based on the average positioning error corresponding to each intermediate value, the actual value of the reference coefficient is determined from all intermediate values.
[0135] Each module in the aforementioned indoor positioning 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 a computer device in software form, so that the processor can call and execute the corresponding operations of each module.
[0136] In one 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 interface, communication interface, display unit, and input device. The processor, memory, and input / output interface 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 interface. 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 interface is 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, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements an indoor positioning method. The display unit is used to form a visually visible image and can be a display screen, projection device, or 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.
[0137] Those skilled in the art will understand that Figure 6 The 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.
[0138] In one 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 implement the steps of the indoor positioning method provided in the above embodiment.
[0139] The target device is located based on the Bluetooth signal emitted by the Bluetooth device. The initial positioning coordinates of the target device are obtained. Based on the Bluetooth positioning error, the initial positioning area containing the initial positioning coordinates is determined.
[0140] Determine the target light intensity points that fall into the initial positioning area, and obtain multiple light intensity space vectors by combining different target light intensity points.
[0141] Acquire multiple light intensities collected by the target device at multiple time points to construct a light intensity time-series vector;
[0142] Based on the difference between the light intensity temporal vector and the light intensity spatial vector, the target light intensity point is determined, and based on the position coordinates of the target light intensity point, the final positioning coordinates of the target device are determined.
[0143] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0144] Identify target light intensity point pairs that are connected by a preset distance within the initial positioning area;
[0145] Determine the target light intensity points that the line connecting the target light intensity point pairs passes through in the initial positioning area, and construct the corresponding light intensity space vector based on the target light intensity points and target light intensity point pairs that have passed through.
[0146] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0147] Calculate the similarity between the temporal vector of light intensity and each spatial vector of light intensity;
[0148] If there are similarities not exceeding a preset threshold, sort them according to similarity and select a preset number of light intensity space vectors;
[0149] Clustering is performed on a preset number of light intensity spatial vectors to obtain multiple clusters;
[0150] Calculate the average similarity of all light intensity spatial vectors in each cluster, and determine the target cluster with the smallest average similarity.
[0151] The final positioning coordinates of the target device are determined based on the position coordinates of the target light intensity points corresponding to each light intensity spatial vector in the target cluster.
[0152] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0153] If all similarity scores are greater than a preset threshold, the initial positioning coordinates will be used as the final positioning coordinates of the target device.
[0154] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0155] Obtain the expected value corresponding to all similarities;
[0156] Determine the reference value based on the expected value and the reference coefficient;
[0157] Calculate the difference between each similarity value and the reference value, count the total number of similarities with negative differences, and use the total number as the preset number.
[0158] In one embodiment, the processor, when executing a computer program, also performs the following steps:
[0159] Determine multiple sample location coordinates, and obtain the sample light intensity temporal vector and the corresponding multiple sample light intensity spatial vectors formed by the sample device at the sample location coordinates;
[0160] Calculate the sample similarity between the temporal vector of sample light intensity and the corresponding spatial vector of each sample light intensity, and obtain the expected value of the sample corresponding to all sample similarities;
[0161] Obtain the intermediate value of the reference coefficient, and determine the sample reference value based on the expected value and the intermediate value;
[0162] Calculate the difference between the similarity of each sample and the sample reference value, count the total number of samples with negative differences, and use the total number of samples as the reference number.
[0163] Sort the samples according to their similarity and select a reference number of sample light intensity space vectors;
[0164] Clustering is performed on the light intensity spatial vectors of a reference number of samples to obtain multiple sample clusters;
[0165] Calculate the average similarity of the light intensity space vectors of all samples in each sample cluster, and determine the target cluster of the sample with the smallest average similarity.
[0166] Based on the position coordinates of the target light intensity points corresponding to the light intensity space vectors of each sample in the sample target cluster, the predicted positioning coordinates of the sample device are determined.
[0167] Obtain the positioning error between the predicted positioning coordinates and the sample position coordinates, and use it as the positioning error corresponding to the sample position coordinates at the intermediate value.
[0168] Based on the positioning error corresponding to the location coordinates of each sample, determine the average positioning error corresponding to the intermediate value;
[0169] By adjusting the intermediate values multiple times, and following the above process, the average positioning error corresponding to each intermediate value is determined.
[0170] Based on the average positioning error corresponding to each intermediate value, the actual value of the reference coefficient is determined from all intermediate values.
[0171] The implementation principle and technical effects of the above embodiments are similar to those of the above method embodiments, and will not be repeated here.
[0172] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the indoor positioning method provided in the above embodiment:
[0173] The target device is located based on the Bluetooth signal emitted by the Bluetooth device. The initial positioning coordinates of the target device are obtained. Based on the Bluetooth positioning error, the initial positioning area containing the initial positioning coordinates is determined.
[0174] Determine the target light intensity points that fall into the initial positioning area, and obtain multiple light intensity space vectors by combining different target light intensity points.
[0175] Acquire multiple light intensities collected by the target device at multiple time points to construct a light intensity time-series vector;
[0176] Based on the difference between the light intensity temporal vector and the light intensity spatial vector, the target light intensity point is determined, and based on the position coordinates of the target light intensity point, the final positioning coordinates of the target device are determined.
[0177] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:
[0178] Identify target light intensity point pairs that are connected by a preset distance within the initial positioning area;
[0179] Determine the target light intensity points that the line connecting the target light intensity point pairs passes through in the initial positioning area, and construct the corresponding light intensity space vector based on the target light intensity points and target light intensity point pairs that have passed through.
[0180] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:
[0181] Calculate the similarity between the temporal vector of light intensity and each spatial vector of light intensity;
[0182] If there are similarities not exceeding a preset threshold, sort them according to similarity and select a preset number of light intensity space vectors;
[0183] Clustering is performed on a preset number of light intensity spatial vectors to obtain multiple clusters;
[0184] Calculate the average similarity of all light intensity spatial vectors in each cluster, and determine the target cluster with the smallest average similarity.
[0185] The final positioning coordinates of the target device are determined based on the position coordinates of the target light intensity points corresponding to each light intensity spatial vector in the target cluster.
[0186] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:
[0187] If all similarity scores are greater than a preset threshold, the initial positioning coordinates will be used as the final positioning coordinates of the target device.
[0188] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:
[0189] Obtain the expected value corresponding to all similarities;
[0190] Determine the reference value based on the expected value and the reference coefficient;
[0191] Calculate the difference between each similarity value and the reference value, count the total number of similarities with negative differences, and use the total number as the preset number.
[0192] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:
[0193] Determine multiple sample location coordinates, and obtain the sample light intensity temporal vector and the corresponding multiple sample light intensity spatial vectors formed by the sample device at the sample location coordinates;
[0194] Calculate the sample similarity between the temporal vector of sample light intensity and the corresponding spatial vector of each sample light intensity, and obtain the expected value of the sample corresponding to all sample similarities;
[0195] Obtain the intermediate value of the reference coefficient, and determine the sample reference value based on the expected value and the intermediate value;
[0196] Calculate the difference between the similarity of each sample and the sample reference value, count the total number of samples with negative differences, and use the total number of samples as the reference number.
[0197] Sort the samples according to their similarity and select a reference number of sample light intensity space vectors;
[0198] Clustering is performed on the light intensity spatial vectors of a reference number of samples to obtain multiple sample clusters;
[0199] Calculate the average similarity of the light intensity space vectors of all samples in each sample cluster, and determine the target cluster of the sample with the smallest average similarity.
[0200] Based on the position coordinates of the target light intensity points corresponding to the light intensity space vectors of each sample in the sample target cluster, the predicted positioning coordinates of the sample device are determined.
[0201] Obtain the positioning error between the predicted positioning coordinates and the sample position coordinates, and use it as the positioning error corresponding to the sample position coordinates at the intermediate value.
[0202] Based on the positioning error corresponding to the location coordinates of each sample, determine the average positioning error corresponding to the intermediate value;
[0203] By adjusting the intermediate values multiple times, and following the above process, the average positioning error corresponding to each intermediate value is determined.
[0204] Based on the average positioning error corresponding to each intermediate value, the actual value of the reference coefficient is determined from all intermediate values.
[0205] The implementation principle and technical effects of the above embodiments are similar to those of the above method embodiments, and will not be repeated here.
[0206] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the indoor positioning method provided in the above embodiment:
[0207] The target device is located based on the Bluetooth signal emitted by the Bluetooth device. The initial positioning coordinates of the target device are obtained. Based on the Bluetooth positioning error, the initial positioning area containing the initial positioning coordinates is determined.
[0208] Determine the target light intensity points that fall into the initial positioning area, and obtain multiple light intensity space vectors by combining different target light intensity points.
[0209] Acquire multiple light intensities collected by the target device at multiple time points to construct a light intensity time-series vector;
[0210] Based on the difference between the light intensity temporal vector and the light intensity spatial vector, the target light intensity point is determined, and based on the position coordinates of the target light intensity point, the final positioning coordinates of the target device are determined.
[0211] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:
[0212] Identify target light intensity point pairs that are connected by a preset distance within the initial positioning area;
[0213] Determine the target light intensity points that the line connecting the target light intensity point pairs passes through in the initial positioning area, and construct the corresponding light intensity space vector based on the target light intensity points and target light intensity point pairs that have passed through.
[0214] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:
[0215] Calculate the similarity between the temporal vector of light intensity and each spatial vector of light intensity;
[0216] If there are similarities not exceeding a preset threshold, sort them according to similarity and select a preset number of light intensity space vectors;
[0217] Clustering is performed on a preset number of light intensity spatial vectors to obtain multiple clusters;
[0218] Calculate the average similarity of all light intensity spatial vectors in each cluster, and determine the target cluster with the smallest average similarity.
[0219] The final positioning coordinates of the target device are determined based on the position coordinates of the target light intensity points corresponding to each light intensity spatial vector in the target cluster.
[0220] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:
[0221] If all similarity scores are greater than a preset threshold, the initial positioning coordinates will be used as the final positioning coordinates of the target device.
[0222] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:
[0223] Obtain the expected value corresponding to all similarities;
[0224] Determine the reference value based on the expected value and the reference coefficient;
[0225] Calculate the difference between each similarity value and the reference value, count the total number of similarities with negative differences, and use the total number as the preset number.
[0226] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:
[0227] Determine multiple sample location coordinates, and obtain the sample light intensity temporal vector and the corresponding multiple sample light intensity spatial vectors formed by the sample device at the sample location coordinates;
[0228] Calculate the sample similarity between the sample light intensity time vector and the corresponding sample light intensity space vector, and obtain the expected value of the sample corresponding to the similarity of all samples.
[0229] Obtain the intermediate value of the reference coefficient, and determine the sample reference value based on the expected value and the intermediate value;
[0230] Calculate the difference between the similarity of each sample and the sample reference value, count the total number of samples with negative differences, and use the total number of samples as the reference number.
[0231] 5. Sort the samples according to their similarity and select a reference number of sample light intensity space vectors;
[0232] Clustering is performed on the light intensity spatial vectors of a reference number of samples to obtain multiple sample clusters;
[0233] Calculate the average similarity of the light intensity space vectors of all samples in each sample cluster, and determine the target cluster of the sample with the smallest average similarity.
[0234] Based on the position coordinates of the target light intensity points corresponding to the light intensity space vectors of each sample in the target cluster, the predicted positioning coordinates of the sample device are determined.
[0235] Obtain the positioning error between the predicted positioning coordinates and the sample position coordinates, and use it as the positioning error corresponding to the sample position coordinates at the intermediate value.
[0236] Based on the positioning error corresponding to the location coordinates of each sample, determine the average positioning error corresponding to the intermediate value;
[0237] 5. By adjusting the intermediate values multiple times, and following the above process, determine the average positioning error corresponding to each intermediate value;
[0238] Based on the average positioning error corresponding to each intermediate value, the actual value of the reference coefficient is determined from all intermediate values.
[0239] The implementation principle and technical effects of the above embodiments are similar to those of the above method embodiments, and will not be repeated here.
[0240] 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 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, etc., and are not limited to these.
[0241] 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 specification.
[0242] 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. An indoor positioning method, characterized in that, This method is applied to locate target devices within a target area, where Bluetooth devices and light source devices are distributed. The target area is defined with multiple light intensity points, each corresponding to a light intensity value collected at its location by the light source device. The method includes: Based on the Bluetooth signal emitted by the Bluetooth device collected by the target device, the initial positioning coordinates of the target device are obtained, and an initial positioning area containing the initial positioning coordinates is determined according to the Bluetooth positioning error. Determine the target light intensity points that fall within the initial positioning area, and obtain multiple light intensity space vectors by combining different target light intensity points, which are composed of the light intensity corresponding to each of the different target light intensity points. Multiple light intensities collected by the target device at multiple time points are obtained to form a light intensity time-series vector; Based on the difference between the light intensity temporal vector and the light intensity spatial vector, the target light intensity point is determined, and based on the position coordinates of the target light intensity point, the final positioning coordinates of the target device are determined.
2. The method according to claim 1, characterized in that, The process of combining different target light intensity points to obtain multiple light intensity space vectors, which are combinations of the light intensity corresponding to each of the different target light intensity points, includes: Determine the target light intensity point pairs whose line distance between them is a preset distance within the initial positioning area; Determine the target light intensity points that the line connecting the target light intensity point pairs passes through in the initial positioning area, and construct a corresponding light intensity space vector based on the target light intensity points passed through and the target light intensity point pairs.
3. The method according to claim 1, characterized in that, The step of determining the target light intensity point based on the difference between the light intensity temporal vector and the light intensity spatial vector, and determining the final positioning coordinates of the target device based on the position coordinates of the target light intensity point, includes: Calculate the similarity between the light intensity temporal vector and each light intensity spatial vector; If there are similarities not exceeding a preset threshold, sort them according to similarity and select a preset number of light intensity space vectors; Cluster the preset number of light intensity spatial vectors to obtain multiple clusters; Calculate the average similarity of all light intensity spatial vectors in each cluster, and determine the target cluster with the smallest average similarity. The final positioning coordinates of the target device are determined based on the position coordinates of the target light intensity points corresponding to each light intensity spatial vector in the target cluster.
4. The method according to claim 3, characterized in that, The method further includes: If all similarity values are greater than a preset threshold, the initial positioning coordinates will be used as the final positioning coordinates of the target device.
5. The method according to claim 3, characterized in that, The process of determining the preset quantity includes: Obtain the expected value corresponding to all similarities; Based on the expected value and the reference coefficient, determine the reference value; Calculate the difference between each similarity and the reference value, count the total number of similarities with negative differences, and use the total number as a preset number.
6. The method according to claim 5, characterized in that, The process of determining the reference coefficient includes: Determine multiple sample location coordinates, and obtain the sample light intensity temporal vector and the corresponding multiple sample light intensity spatial vectors formed by the sample device at the sample location coordinates; Calculate the sample similarity between the sample light intensity time-series vector and the corresponding sample light intensity space vector, and obtain the expected value of the sample corresponding to all sample similarities; Obtain the intermediate value of the reference coefficient, and determine the sample reference value based on the expected value of the sample and the intermediate value; Calculate the difference between the similarity of each sample and the reference value of the sample, count the total number of samples with negative differences, and use the total number of samples as the reference number. Sort the samples according to their similarity and select the reference number of sample light intensity space vectors; Cluster the light intensity space vectors of the reference number of samples to obtain multiple sample clusters; Calculate the average similarity of the light intensity space vectors of all samples in each sample cluster, and determine the target cluster of the sample with the smallest average similarity. The predicted positioning coordinates of the sample device are determined based on the position coordinates of the target light intensity points corresponding to the light intensity space vectors of each sample in the target cluster. The positioning error between the predicted positioning coordinates and the sample position coordinates is obtained and used as the positioning error corresponding to the sample position coordinates at the intermediate value. Based on the positioning error corresponding to the location coordinates of each sample, the average positioning error corresponding to the intermediate value is determined; By adjusting the intermediate values multiple times, and determining the average positioning error corresponding to each intermediate value according to the above process; Based on the average positioning error corresponding to each intermediate value, the actual value of the reference coefficient is determined from all intermediate values.
7. An indoor positioning device, characterized in that, This device is used to locate target devices within a target area, where Bluetooth devices and light source devices are distributed. The target area is defined with multiple light intensity points, each corresponding to a light intensity value collected at its location by the light source device. The device includes: An initial positioning module is used to locate the target device based on the Bluetooth signal emitted by the Bluetooth device collected by the target device, obtain the initial positioning coordinates of the target device, and determine an initial positioning area containing the initial positioning coordinates based on the Bluetooth positioning error. The spatial combination module is used to determine the target light intensity points falling into the initial positioning area. By combining different target light intensity points, multiple light intensity spatial vectors are obtained by combining the light intensity corresponding to each of the different target light intensity points. The timing composition module is used to acquire multiple light intensities collected by the target device at multiple time points to form a light intensity timing vector; The final positioning module is used to determine the target light intensity point based on the difference between the light intensity temporal vector and the light intensity spatial vector, and to determine the final positioning coordinates of the target device based on the position coordinates of the target light intensity point.
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.