Indoor wireless positioning method and device

Abstract

The embodiment of the invention provides an indoor wireless positioning method and device, and relates to the technical field of data processing, and the method comprises the steps: obtaining the CSI data of Wi-Fi at all indoor fingerprint reference points with known coordinates and at a to-be-positioned fingerprint point, and enabling different fingerprint reference points to correspond to different indoor positions, the distance between any two fingerprint reference points is greater than a preset distance; calculating first similarities among the CSI data, and calculating similarity distribution characteristics among the CSI data based on the first similarities and the CSI data; calculating second similarities among the similarity distribution characteristics, and updating the CSI data based on the second similarities; calculating a matching probability between the fingerprint point to be positioned and each fingerprint reference point; and based on the matching probability, selecting a fingerprint reference point matched with the to-be-positioned fingerprint point, and determining the coordinate of the to-be-positioned fingerprint point. By applying the scheme provided by the embodiment of the invention, the deployment time of the indoor wireless positioning system can be reduced.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of data processing technology, and in particular to an indoor wireless positioning method and device. Background Art

[0002] With the widespread deployment of wireless sensor devices in indoor environments, wireless sensor networks have made up for the defect that global navigation and positioning systems are difficult to achieve high-precision positioning indoors, providing a strong prerequisite for indoor location services. Wi-Fi, Bluetooth, RFID (Radio Frequency Identification) and UWB (Ultra Wideband) are commonly used sensors and signal sources in wireless sensor networks and are widely used in indoor wireless positioning. Among them, the Wi-Fi-based positioning method has the characteristics of high positioning accuracy and low equipment cost. The CSI (Channel State Information) of the wireless signal from the Wi-Fi device contains multi-channel subcarrier phase and amplitude data, which can describe the indoor location-related information in detail, and has become the most commonly used wireless signal feature for constructing indoor fingerprint coordinates.

[0003] In the related art, the indoor wireless positioning method based on Wi-Fi includes an offline stage and an online stage. In the offline stage, CSI data is collected at multiple fingerprint reference points indoors to build a fingerprint reference database to train the wireless positioning model; in the online stage, CSI data of the fingerprint point to be located is collected in real time, and the fingerprint reference database is compared with the wireless positioning model to obtain the predicted coordinates of the fingerprint point to be located, thereby achieving positioning. In the related art, the effect of coordinate positioning of the fingerprint point to be located depends on the degree of matching between the CSI data of the fingerprint point to be located collected in real time and the CSI data in the fingerprint reference database. The number of fingerprint reference points and the amount of CSI data collected in the offline stage will significantly affect the positioning accuracy of the fingerprint point to be located. Therefore, the number of fingerprint reference points and the amount of CSI data collected in the related art are often large.

[0004] When the old indoor scene is replaced by the new indoor scene, the size of the indoor space, the types of obstacles, the location of Wi-Fi devices, and the distribution of fingerprints will all change completely, and the new and old indoor scenes will have no correlation. Due to the environmental dependence of Wi-Fi signals, the fingerprint reference points and CSI data in the old indoor scene are no longer available in the new indoor scene. In order to use the Wi-Fi-based indoor wireless positioning method in the new indoor scene, the relevant technology requires a lot of manpower and time costs to re-collect a large number of fingerprint reference points and CSI data in the new indoor scene, and the deployment period of the new indoor wireless positioning system is relatively long. Summary of the invention

[0005] The purpose of the embodiment of the present invention is to provide an indoor wireless positioning method and device to reduce the deployment time of the indoor wireless positioning system. The specific technical solution is as follows:

[0006] In a first aspect, an embodiment of the present invention provides an indoor wireless positioning method, the method comprising:

[0007] Acquire channel state information CSI data of wireless network communication technology Wi-Fi at each fingerprint reference point with known indoor coordinates and at the fingerprint point to be located, where different fingerprint reference points correspond to different positions indoors, and the distance between any two fingerprint reference points is greater than a preset distance;

[0008] Calculating first similarities between the CSI data, and calculating similarity distribution characteristics between the CSI data based on the first similarities and the CSI data;

[0009] Calculating second similarities between the similarity distribution features, and updating the CSI data based on the second similarities;

[0010] Calculate the matching probability between the fingerprint point to be located and each fingerprint reference point based on the similarity between the finally updated CSI data of the fingerprint point to be located and other CSI data and the other CSI data;

[0011] Based on the matching probability, a fingerprint reference point matching the fingerprint point to be located is selected, and based on the coordinates of the selected fingerprint reference point, the coordinates of the fingerprint point to be located are determined.

[0012] In one embodiment of the present invention, before calculating the matching probability between the fingerprint point to be located and each fingerprint reference point based on the similarity between the CSI data of the fingerprint point to be located and other CSI data obtained by the final update and the other CSI data, the method further includes:

[0013] Return to repeatedly executing the steps of calculating the first similarities between the CSI data, calculating the similarity distribution features between the CSI data based on the first similarities and the CSI data, calculating the second similarities between the similarity distribution features, and updating the CSI data based on the second similarities, until the number of repetitions reaches a preset number.

[0014] In one embodiment of the present invention, the calculating of the first similarities between the CSI data and the calculating of the similarity distribution characteristics between the CSI data based on the first similarities and the CSI data include:

[0015] Calculate the first similarity between each CSI data, and construct a fingerprint feature fully connected graph, wherein the features of each node in the fingerprint feature fully connected graph are each CSI data, and the features of each edge in the fingerprint feature fully connected graph are the first similarity between the features of the connected nodes;

[0016] The similarity distribution characteristics between the CSI data are calculated based on the characteristics of each node and the characteristics of each edge in the fingerprint feature fully connected graph.

[0017] In one embodiment of the present invention, the calculating the second similarities between the similarity distribution features and updating the CSI data based on the second similarities includes:

[0018] Calculating the second similarity between the similarity distribution features, and constructing a similarity distribution fully connected graph, wherein the features of each node in the similarity distribution fully connected graph are the similarity distribution features, and the features of each edge in the similarity distribution fully connected graph are the second similarities between the features of the connected nodes;

[0019] Each CSI data is updated based on the features of each edge in the similarity distribution fully connected graph.

[0020] In one embodiment of the present invention, the step of selecting a fingerprint reference point that matches the fingerprint point to be located includes:

[0021] A preset proportion of fingerprint reference points having the highest probability of matching the fingerprint to be located are selected.

[0022] In one embodiment of the present invention, the steps of calculating the first similarities between the CSI data, calculating the similarity distribution characteristics between the CSI data based on the first similarities and the CSI data, selecting a fingerprint reference point matching the fingerprint point to be located based on the matching probability, and determining the coordinates of the fingerprint point to be located based on the coordinates of the selected fingerprint reference point include:

[0023] Input each CSI data into a pre-trained indoor wireless positioning model to obtain the coordinates of the fingerprint point to be located output by the indoor wireless positioning model;

[0024] The indoor wireless positioning model is used to: calculate the first similarity between each CSI data, and calculate the similarity distribution characteristics between each CSI data based on each first similarity and each CSI data; calculate the second similarity between each similarity distribution feature, and update each CSI data based on each second similarity; calculate the matching probability between the fingerprint point to be located and each fingerprint reference point based on the similarity between the CSI data of the fingerprint point to be located and other CSI data obtained by the final update and the other CSI data; based on the matching probability, select a fingerprint reference point that matches the fingerprint point to be located, and determine the coordinates of the fingerprint point to be located based on the coordinates of the selected fingerprint reference point.

[0025] In a second aspect, an embodiment of the present invention provides an indoor wireless positioning device, the device comprising:

[0026] An acquisition module is used to acquire channel state information CSI data of the wireless network communication technology Wi-Fi at each fingerprint reference point with known indoor coordinates and at the fingerprint point to be located, wherein different fingerprint reference points correspond to different positions indoors, and the distance between any two fingerprint reference points is greater than a preset distance;

[0027] A first calculation module, configured to calculate first similarities between each CSI data, and calculate similarity distribution characteristics between each CSI data based on each first similarity and each CSI data;

[0028] A second calculation module, configured to calculate a second similarity between the similarity distribution features, and update each CSI data based on the second similarity;

[0029] A third calculation module, configured to calculate a matching probability between the fingerprint point to be located and each fingerprint reference point based on the similarity between the finally updated CSI data of the fingerprint point to be located and other CSI data and the other CSI data;

[0030] The determination module is used to select a fingerprint reference point matching the fingerprint point to be located based on the matching probability, and determine the coordinates of the fingerprint point to be located based on the coordinates of the selected fingerprint reference point.

[0031] In one embodiment of the present invention, the device further comprises:

[0032] The return execution module is used to return to repeatedly execute the steps of calculating the first similarities between the CSI data, calculating the similarity distribution characteristics between the CSI data based on the first similarities and the CSI data, calculating the second similarities between the similarity distribution characteristics, and updating the CSI data based on the second similarities, until the number of repeated executions reaches a preset number of times.

[0033] In one embodiment of the present invention, the first calculation module is specifically used to:

[0034] Calculate the first similarity between each CSI data, and construct a fingerprint feature fully connected graph, wherein the features of each node in the fingerprint feature fully connected graph are each CSI data, and the features of each edge in the fingerprint feature fully connected graph are the first similarity between the features of the connected nodes;

[0035] The similarity distribution characteristics between the CSI data are calculated based on the characteristics of each node and the characteristics of each edge in the fingerprint feature fully connected graph.

[0036] In one embodiment of the present invention, the second calculation module is specifically used to:

[0037] Calculating the second similarity between the similarity distribution features, and constructing a similarity distribution fully connected graph, wherein the features of each node in the similarity distribution fully connected graph are the similarity distribution features, and the features of each edge in the similarity distribution fully connected graph are the second similarities between the features of the connected nodes;

[0038] Each CSI data is updated based on the features of each edge in the similarity distribution fully connected graph.

[0039] In one embodiment of the present invention, the determining module is specifically used to:

[0040] Based on the matching probability, a preset proportion of fingerprint reference points having the highest matching probability with the fingerprint to be located are selected, and based on the coordinates of the selected fingerprint reference points, the coordinates of the fingerprint point to be located are determined.

[0041] In one embodiment of the present invention, the first calculation module, the second calculation module, the third calculation module and the determination module are specifically used to:

[0042] Input each CSI data into a pre-trained indoor wireless positioning model to obtain the coordinates of the fingerprint point to be located output by the indoor wireless positioning model;

[0043] The indoor wireless positioning model is used to: calculate the first similarity between each CSI data, and calculate the similarity distribution characteristics between each CSI data based on each first similarity and each CSI data; calculate the second similarity between each similarity distribution feature, and update each CSI data based on each second similarity; calculate the matching probability between the fingerprint point to be located and each fingerprint reference point based on the similarity between the CSI data of the fingerprint point to be located and other CSI data obtained by the final update and the other CSI data; based on the matching probability, select a fingerprint reference point that matches the fingerprint point to be located, and determine the coordinates of the fingerprint point to be located based on the coordinates of the selected fingerprint reference point.

[0044] In a third aspect, an embodiment of the present invention provides an electronic device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0045] Memory, used to store computer programs;

[0046] The processor is used to implement any method step described in the first aspect when executing a program stored in the memory.

[0047] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, any method step described in the first aspect is implemented.

[0048] Beneficial effects of the embodiments of the present invention:

[0049] The embodiment of the present invention provides an indoor wireless positioning method, which first obtains the CSI data of each fingerprint reference point and the fingerprint point to be located in the room, then calculates the first similarity between each CSI data, and then obtains the similarity distribution characteristics between each CSI data; calculates the second similarity between each similarity distribution feature, and then updates each CSI data according to the second similarity, and the similarity between each updated CSI data obtained can describe the distribution relationship of the similarity between the CSI data of each fingerprint reference point and the CSI data of the fingerprint point to be located. Based on the similarity between the CSI data of the fingerprint point to be located obtained by the final update and the CSI data of each fingerprint reference point, the matching probability between the fingerprint point to be located and each fingerprint reference point can be obtained, and then the coordinates of the fingerprint point to be located are determined according to the matching probability.

[0050] Moreover, the scheme provided by the embodiment of the present invention requires that the spacing between each fingerprint reference point is greater than the preset spacing, so as to ensure that the CSI data of each fingerprint reference point has obvious characteristic differences, thereby ensuring that the similarity between each updated CSI data finally obtained can better describe the distribution relationship between the CSI data of each fingerprint reference point and the CSI data of the fingerprint point to be located, so that the matching probability between the obtained fingerprint point to be located and each fingerprint reference point can better conform to the actual situation. Therefore, when the scheme provided by the embodiment of the present invention is used for indoor wireless positioning, the spacing between the fingerprint reference points for collecting CSI data is larger, so when the indoor size is fixed, the number of fingerprint reference points will not be too large. Compared with the related technology, it can reduce the manpower and time cost required for collecting CSI data of fingerprint reference points, thereby reducing the deployment time of the indoor wireless positioning system. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other embodiments can also be obtained based on these drawings.

[0052] Figure 1 A schematic diagram of a flow chart of a first indoor wireless positioning method provided by an embodiment of the present invention;

[0053] Figure 2 A schematic diagram of the structure of a convolutional neural network for extracting a representation vector provided by an embodiment of the present invention;

[0054] Figure 3 A schematic diagram of the structure of a fully connected graph of fingerprint features provided by an embodiment of the present invention;

[0055] Figure 4 A schematic diagram of calculating similarity distribution characteristics between CSI data provided by an embodiment of the present invention;

[0056] Figure 5 A schematic diagram of the structure of a similarity distribution fully connected graph provided by an embodiment of the present invention;

[0057] Figure 6 A schematic diagram of updating various CSI data provided by an embodiment of the present invention;

[0058] Figure 7 A schematic diagram of a flow chart of a second indoor wireless positioning method provided by an embodiment of the present invention;

[0059] Figure 8 A schematic diagram of a flow chart of a third indoor wireless positioning method provided by an embodiment of the present invention;

[0060] Fig. 9 A schematic diagram of a fourth indoor wireless positioning method provided by an embodiment of the present invention;

[0061] Fig.10 A schematic diagram of the structure of the calculation process of the fingerprint feature fully connected graph and the similarity distribution fully connected graph provided by the embodiment of the present invention;

[0062] Fig.11 A schematic diagram of the structure of the calculation process of the indoor wireless positioning method provided by an embodiment of the present invention;

[0063] Fig.12 A schematic diagram of the structure of an indoor wireless positioning device provided by an embodiment of the present invention;

[0064] Fig.13 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0065] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field based on the present invention belong to the scope of protection of the present invention.

[0066] In order to use Wi-Fi-based indoor wireless positioning methods in new indoor scenarios, related technologies require a lot of manpower and time costs to re-collect a large number of fingerprint reference points and CSI data in new indoor scenarios, and the deployment cycle of new indoor wireless positioning systems is long.

[0067] In order to solve the above problems, the embodiments of the present invention provide an indoor wireless positioning method and device, which are described in detail below.

[0068] First, an indoor wireless positioning method provided by an embodiment of the present invention is described.

[0069] See also Figure 1 , which is a flow chart of a first indoor wireless positioning method provided in an embodiment of the present invention. The method is applied to an electronic device with computing capabilities. Exemplarily, the method is applied to a computer. The method includes the following steps S101 to S105.

[0070] Step S101: Acquire CSI data of Wi-Fi at each fingerprint reference point with known indoor coordinates and at the fingerprint point to be located.

[0071] Different fingerprint reference points correspond to different positions in the room, and the distance between any two fingerprint reference points is greater than a preset distance.

[0072] In the process of indoor wireless positioning, multiple fingerprint reference points with known coordinates are first determined indoors. In the embodiment of the present invention, the distance between any two fingerprint reference points is required to be greater than the preset distance to ensure that the CSI data obtained at each fingerprint reference point has obvious characteristic differences.

[0073] Exemplarily, the amount of CSI data obtained at each fingerprint reference point is KN, where KN represents the product of K and N, N is the number of fingerprint reference points, and K is the amount of CSI data obtained at each fingerprint reference point. In the embodiment of the present invention, the value of K does not need to be very large, and the value of K is generally 5 or 10. Of course, the value of K can also be set to other values ​​according to actual needs.

[0074] Step S102: Calculate the first similarities between the CSI data, and calculate the similarity distribution characteristics between the CSI data based on the first similarities and the CSI data.

[0075] The above-mentioned CSI data include CSI data at each fingerprint reference point and the fingerprint point to be located, and the similarity between each CSI data is called the above-mentioned first similarity. Since the similarity distribution characteristics between the above-mentioned CSI data are calculated by each first similarity and each CSI data, the CSI data at the fingerprint point to be located in the above-mentioned CSI data will affect the similarity distribution characteristics between the above-mentioned CSI data. The more CSI data at the fingerprint point to be located that participates in the calculation, the greater the impact on the similarity distribution characteristics between the above-mentioned CSI data, which will reduce the subsequent positioning accuracy of the fingerprint point to be located. In practical applications, the amount of CSI data at the fingerprint point to be located that participates in the calculation is generally set to 1.

[0076] For example, as described in step S101, the amount of CSI data obtained at each fingerprint reference point is KN; in addition, the amount of CSI data obtained at the fingerprint point to be located is 1, and there are KN+1 CSI data participating in the calculation of the first similarity between the CSI data. In the process of calculating the above first similarity, x i Represents CSI data, where i = 1, 2, ..., KN + 1. For each CSI data, the label y of each CSI data can be represented by a one-hot code i , the labels of the CSI data belonging to the same fingerprint reference point are the same. For example, the labels of the K CSI data at one fingerprint reference point are all [1,0,…,0] T , the labels of the K CSI data at another fingerprint reference point are all [0,1,…,0] T , and so on. In each fingerprint reference point, the labels of the K CSI data at one fingerprint reference point are different from the labels of the K CSI data at another fingerprint reference point. For the CSI data at the fingerprint point to be located, assuming that the probability that the fingerprint point to be located belongs to each fingerprint reference point is the same, the label of the CSI data at the fingerprint point to be located can be set to To represent the uniform distribution of the CSI data at the fingerprint point to be located in the label space.

[0077] In the above description, x is used i represents CSI data, then x i ∈R W×H×M , where R W×H×Mrepresents a W×H×M dimensional real number space, where W is the number of subcarriers contained in the CSI data, H is the number of CSI data packets that make up the CSI data, and M is the number of wireless signal transmission links. In order to calculate the first similarity between each CSI data, it is necessary to extract the representation vector of each CSI data. Specifically, a convolutional neural network f can be designed. emb Extract the characterization vector of each CSI data, see Figure 2 , which is a structural diagram of a convolutional neural network for extracting representation vectors provided in an embodiment of the present invention.

[0078] from Figure 2 As can be seen from the figure, taking 30 continuously collected CSI data packets as an example, by obtaining the amplitude, data with a dimension of 3×30×30 is obtained, and the data is input into the convolutional neural network f emb In the end, a 64-dimensional column vector is output. Among them, the convolutional neural network f emb The input data is processed using a 32×15×15 convolution kernel, a 64×7×7 convolution kernel, and a 128×3×3 convolution kernel in turn. Figure 2 In the example, dim is the abbreviation of dimension; Figure 2 The operations indicated by the slightly lighter grey arrows are: Conv (Convolution) 3*3, BatchNorm (batch normalization), Maxpool (maximum pooling), and LeakyReLU (Leaky Linear rectification function, a rectified linear unit function) operations on the data; the operations indicated by the slightly darker grey arrows are: Conv3*3, BatchNorm, and LeakyReLU operations. Among them, Conv3*3 represents a 3×3 dimensional convolution layer.

[0079] Specifically, Figure 2 This is just an example and can be adjusted as needed in actual applications. Figure 2 Related parameters involved in. Figure 2 Each CSI data is processed in the manner shown, and the obtained column vector is used as the characterization vector of each CSI data. Based on the characterization vector of each CSI data, the first similarity between each CSI data can be calculated by the embodiment shown below, and then the similarity distribution characteristics between each CSI data are calculated.

[0080] In one embodiment of the present invention, the first similarities between the CSI data are calculated through the following steps A and B, and the similarity distribution characteristics between the CSI data are calculated based on the first similarities and the CSI data.

[0081] Step A: Calculate the first similarity between each CSI data and construct a fingerprint feature fully connected graph.

[0082] Among them, the characteristics of each node in the above-mentioned fingerprint feature fully connected graph are respectively various CSI data, and the characteristics of each edge in the above-mentioned fingerprint feature fully connected graph are respectively the first similarity between the characteristics of the connected nodes.

[0083] Specifically, the representation vector of each CSI data is used as the feature of each node in the fingerprint feature fully connected graph. Figure 3 , which is a schematic diagram of the structure of the fingerprint feature fully connected graph provided in an embodiment of the present invention. Figure 3 Three node features are shown in Connect node features The characteristics of the edges of the corresponding nodes, Connect node features The edge features and node features of the corresponding nodes The corresponding node is Query Fingerprint, which is the CSI data at the fingerprint point to be located in this article. Figure 3 Here, dim=64+N indicates that the dimension of the node feature is 64+N, and dim=1 indicates that the dimension of the edge feature is 1. Figure 3 In the example, the parameter F indicates that the calculation is performed on the fully connected graph of the fingerprint feature, and the parameter l indicates the number of times the node feature or edge feature is calculated. l is 0, which means that the node feature or edge feature is calculated once, l is 2, which means that the node feature or edge feature is calculated three times, and so on. The corresponding node is called node i, then In the calculation related to the fully connected graph of fingerprint features, the node feature is calculated once for node i; the edge feature This means that in the calculation related to the fully connected graph of fingerprint features, the edge feature connecting node i and node 1 is calculated once.

[0084] Specifically, the edge feature of the edge connecting node i and node j is calculated for the first time, which can be shown in the following formula (1):

[0085]

[0086] In formula (1), |·| represents the absolute value, It is an encoding network that converts the first similarity between node features into features of a certain dimension. Including multiple fully connected layers and parameter settings and a sigmoid (a mathematical function with an S-shaped curve) layer.

[0087] In addition, in order to integrate the edge features in the fully connected graph of fingerprint features from a global perspective, after calculating the first similarity between the features of each node, all Normalize it, It is the feature of the edge connecting node i and node j in the fully connected graph of fingerprint features.

[0088] Step B: Calculate the similarity distribution characteristics between the CSI data based on the characteristics of each node and the characteristics of each edge in the fingerprint feature fully connected graph.

[0089] After obtaining the features of each node and each edge in the fully connected graph of fingerprint features, the similarity distribution features are further calculated to increase the distinguishability of the features of each node and improve the subsequent positioning capability of the fingerprint points to be located. In the embodiment of the present invention, the N*K dimensional vector representing the similarity distribution features is To indicate. In the above example, parameter D indicates the calculation related to the similarity distribution characteristics, l indicates the number of calculations, such as l is 0 means it is calculated once, l is 2 means it is calculated three times, i indicates With CSI data x i For the N*K dimensional vector representing the above similarity distribution characteristics, the jth item of the vector represents the CSI data x i and CSI data x j The degree of similarity between them.

[0090] Specifically, when l is 0, if x i is the CSI data at the fingerprint reference point, then It can be shown as the following formula (2):

[0091]

[0092] If x i is the CSI data at the fingerprint point to be located, then It can be shown as the following formula (3):

[0093]

[0094] In formula (2) and formula (3), || is a concatenation operator, which means concatenating multiple α(i,j) results to form an N*K array. For α(i,j), it can be defined as follows:

[0095] If the CSI data x i 、x j If the labels of CSI data x are the same, then α(i,j)=1; i 、x jIf the labels of are different, then α(i,j)=0; where i,j=1,…,NK.

[0096] See also Figure 4 , is a schematic diagram of calculating the similarity distribution characteristics between CSI data provided by an embodiment of the present invention. Figure 4 It can be seen that based on the node features and edge features with dimensions of N*K in the fully connected graph of fingerprint features, after generating features with dimensions of 2*N*K, the network f is aggregated through the fingerprint similarity distribution relationship F2D :R 2NK →R NK Implement feature conversion, convert the generated features with dimension 2*N*K into similarity distribution features with dimension N*K. F2D It consists of multiple fully connected layers and an activation function ReLU, with the parameter set to θ F2D .

[0097] Step S103: Calculate the second similarities between the similarity distribution features, and update the CSI data based on the second similarities.

[0098] After calculating the similarity distribution features between the CSI data, the similarity between the similarity distribution features is calculated, and the result obtained is called the second similarity. Using the above second similarity, each similarity distribution feature is transmitted back to each CSI data, thereby updating each CSI data and improving the distinction between each CSI data. In one embodiment of the present invention, the second similarity between each similarity distribution feature is calculated by following steps C and D, and each CSI data is updated based on each second similarity.

[0099] Step C: Calculate the second similarity between the similarity distribution features and construct a similarity distribution fully connected graph.

[0100] The features of each node in the similarity distribution fully connected graph are respectively the features of the similarity distribution, and the features of each edge in the similarity distribution fully connected graph are respectively the second similarities between the features of the connected nodes.

[0101] See also Figure 5 , which is a structural schematic diagram of a similarity distribution fully connected graph provided in an embodiment of the present invention. Figure 5 Three node features are shown in Connect node features The characteristics of the edges of the corresponding nodes, Connect node features The edge features of the corresponding nodes. The l represents the connection node feature The number of times the edge feature of the corresponding node is calculated. In the embodiment of the present invention, l is 0, which means it is calculated once, l is 1, which means it is calculated twice, and so on.

[0102] Specifically, for the connection node features The edge features of the corresponding node are calculated for the first time, which can be shown as the following formula (4):

[0103]

[0104] In formula (4), Fingerprint Similarity Distribution Relational Encoding Network It consists of multiple fully connected layers and a sigmoid layer, with parameters set to After calculating the features of each edge in the similarity distribution fully connected graph, regularization operations can be performed on each edge feature to integrate the edge features in the similarity distribution fully connected graph.

[0105] Step D: Update each CSI data based on the features of each edge in the similarity distribution fully connected graph.

[0106] After calculating the edge features in the similarity distribution fully connected graph, the CSI data can be updated using the following formula (5):

[0107]

[0108] In formula (5), It is a fingerprint feature aggregation network, which consists of multiple fully connected layers and the parameters are set to θ D2F .

[0109] For details, see Figure 6 , is a schematic diagram of updating various CSI data provided by an embodiment of the present invention. Figure 6 As can be seen from the figure, the features of each edge in the similarity distribution fully connected graph are applied to the representation vector of the calculated CSI data to generate a vector with a dimension of (64+N)*N*K. D2F Processing is performed, that is, the representation vector of the CSI data is calculated again, thereby realizing the update of the CSI data.

[0110] Step S104: Calculate the matching probability between the fingerprint point to be located and each fingerprint reference point based on the similarity between the finally updated CSI data of the fingerprint point to be located and other CSI data and the other CSI data.

[0111] Specifically, the vector representing the similarity distribution relationship between the finally updated CSI data of the fingerprint point to be located and other CSI data, as well as the data representing the coordinates of the other CSI data, are uniformly processed using the relevant classification function to calculate the matching probability between the fingerprint point to be located and each fingerprint reference point.

[0112] In the embodiment of the present invention, the matching probability between the fingerprint point to be located and each fingerprint reference point can be calculated in the following manner, as shown in the following formula (6):

[0113]

[0114] In formula (6), the normalized exponential function Softmax is used. is the CSI data x i The matching probability between the corresponding fingerprint point to be located and the fingerprint reference point, is the prediction result of the fingerprint point label to be located, y j is the unique-hot code label of the fingerprint reference point to which the j-th CSI data in the CSI data at each fingerprint reference point belongs.

[0115] Step S105: Based on the matching probability, a fingerprint reference point matching the fingerprint point to be located is selected, and based on the coordinates of the selected fingerprint reference point, the coordinates of the fingerprint point to be located are determined.

[0116] After obtaining the matching probability between the fingerprint point to be located and each fingerprint reference point, the fingerprint reference point with the highest matching probability with the fingerprint point to be located can be selected, and the coordinates of the fingerprint reference point can be used as the coordinates of the fingerprint point to be located; or several fingerprint reference points with a higher matching probability with the fingerprint point to be located and ranked in the front preset position can be selected, and the average value of the coordinates of these fingerprint reference points can be calculated as the coordinates of the fingerprint point to be located. Of course, there are other ways to determine the fingerprint reference point to be located, as long as the fingerprint reference point is selected according to the matching probability, and then the coordinates of the fingerprint point to be located are determined, and the method is in line with the actual situation.

[0117] As can be seen from the above, in the solution provided by the embodiment of the present invention, firstly, the CSI data of each fingerprint reference point in the room and the fingerprint point to be located are obtained, and then the first similarity between each CSI data is calculated, and then the similarity distribution characteristics between each CSI data are obtained; the second similarity between each similarity distribution feature is calculated, and then each CSI data is updated according to the second similarity, and the similarity between each updated CSI data obtained in this way can describe the distribution relationship of the similarity between the CSI data of each fingerprint reference point and the CSI data of the fingerprint point to be located. Based on the similarity between the CSI data of the fingerprint point to be located obtained by the final update and the CSI data of each fingerprint reference point, the matching probability between the fingerprint point to be located and each fingerprint reference point can be obtained, and then the coordinates of the fingerprint point to be located can be determined according to the matching probability.

[0118] Moreover, the scheme provided by the embodiment of the present invention requires that the spacing between each fingerprint reference point is greater than the preset spacing, so as to ensure that the CSI data of each fingerprint reference point has obvious characteristic differences, thereby ensuring that the similarity between each updated CSI data finally obtained can better describe the distribution relationship between the CSI data of each fingerprint reference point and the CSI data of the fingerprint point to be located, so that the matching probability between the obtained fingerprint point to be located and each fingerprint reference point can better conform to the actual situation. Therefore, when the scheme provided by the embodiment of the present invention is used for indoor wireless positioning, the spacing between the fingerprint reference points for collecting CSI data is larger, so when the indoor size is fixed, the number of fingerprint reference points will not be too large. Compared with the related technology, it can reduce the manpower and time cost required for collecting CSI data of fingerprint reference points, thereby reducing the deployment time of the indoor wireless positioning system.

[0119] In the process of locating the fingerprint point to be located, if the similarity distribution characteristics between each CSI data are calculated only once, and each CSI data is updated only once based on the second similarity, due to the small number of times of feature information propagation and aggregation between each CSI data, the coordinates of the fingerprint point to be located that are finally determined may differ greatly from the actual situation, that is, the calculation accuracy of the coordinates of the fingerprint point to be located is not high. Therefore, the embodiment of the present invention provides the following Figure 7 The embodiment shown.

[0120] See also Figure 7 , is a flow chart of a second indoor wireless positioning method provided by an embodiment of the present invention, and Figure 1 Compared with the embodiment shown, before the step S104, the step S102 is returned to be repeatedly executed until the number of repetitions reaches a preset number.

[0121] Specifically, in the description of step A above, formula (1) describes the first calculation of the first similarity. Correspondingly, in formula (1), Where l is 0. For the case where the first similarity is calculated multiple times, that is, l>0, in this case, the following formula (7) can be used to describe the similarity obtained in each calculation:

[0122]

[0123] By using formula (7), the first similarity can be continuously calculated and updated.

[0124] In the description of step B above, equations (2) and (3) describe the first calculation of the similarity distribution characteristics between the CSI data. For the case where the similarity distribution characteristics between the CSI data are calculated multiple times, that is, In this case, the following formula (8) can be used to describe the

[0125]

[0126] By using formula (8), the similarity distribution characteristics between each CSI data can be continuously calculated and updated.

[0127] In the description of step C above, formula (4) describes the first calculation of the second similarity. For the case where the second similarity is calculated multiple times, that is, In this case, the following formula (9) can be used to describe the

[0128]

[0129] By using formula (9), the second similarity can be continuously calculated and updated, and then each CSI data is updated based on the updated second similarity.

[0130] It can be seen from the above that in the solution provided by the embodiment of the present invention, by repeated calculations, each CSI data is continuously updated, so that the characteristic information between each CSI data is propagated and aggregated multiple times, which can improve the calculation accuracy of the coordinates of the fingerprint point to be located.

[0131] See also Figure 8 , is a flow chart of a third indoor wireless positioning method provided by an embodiment of the present invention, and Figure 1 Compared with the embodiment shown, the above step S105 can be implemented by the following step S105A.

[0132] Step S105A: Based on the matching probability, select a preset ratio of fingerprint reference points with the highest matching probability with the fingerprint to be located, and determine the coordinates of the fingerprint point to be located based on the coordinates of the selected fingerprint reference points.

[0133] After selecting the fingerprint reference points with the highest pre-set ratio of matching probability with the above-mentioned fingerprint to be located, the coordinates of the selected fingerprint reference points are processed to obtain the coordinates of the fingerprint point to be located. Exemplarily, the number of selected fingerprint reference points that meet the pre-set ratio is 3, that is, the three fingerprint reference points with the top three matching probabilities are selected from the front to the back according to the size of the matching probability. For these three fingerprint reference points, the coordinates of the fingerprint point to be located are obtained based on the weighted calculation of the matching probability, as shown in the following formula (10):

[0134]

[0135] In formula (10), L is the coordinate of the predicted fingerprint point to be located, L i , P i They correspond to the coordinates of the three selected fingerprint reference points and the corresponding matching probabilities.

[0136] As can be seen from the above, in the solution provided by the embodiment of the present invention, a preset proportion of fingerprint reference points with the highest probability of matching the above-mentioned fingerprint to be located are selected, that is, the coordinates of the above-mentioned fingerprint point to be located are comprehensively determined based on multiple fingerprint reference points with higher matching probabilities, so that the determined coordinates of the fingerprint point to be located are more in line with the actual situation.

[0137] See also Fig. 9 , is a flow chart of a fourth indoor wireless positioning method provided by an embodiment of the present invention, and Figure 1 Compared with the embodiment shown, the above steps S102 to S105 can be implemented by the following step S106.

[0138] Step S106: input each CSI data into a pre-trained indoor wireless positioning model to obtain the coordinates of the fingerprint point to be located output by the indoor wireless positioning model.

[0139] Among them, the above-mentioned indoor wireless positioning model is used to: calculate the first similarity between each CSI data, and calculate the similarity distribution characteristics between each CSI data based on each first similarity and each CSI data; calculate the second similarity between each similarity distribution feature, and update each CSI data based on each second similarity; based on the similarity between the CSI data of the above-mentioned fingerprint point to be located and other CSI data obtained by the final update and the above-mentioned other CSI data, calculate the matching probability between the above-mentioned fingerprint point to be located and each fingerprint reference point; based on the above-mentioned matching probability, select the fingerprint reference point matching the above-mentioned fingerprint point to be located, and determine the coordinates of the above-mentioned fingerprint point to be located based on the coordinates of the selected fingerprint reference point.

[0140] Specifically, the process of the indoor wireless positioning model processing CSI data and determining the coordinates of the fingerprint point to be located can be referred to the description of the indoor wireless positioning method in the previous text, which will not be repeated here.

[0141] The training process of the indoor wireless positioning model can be briefly described as follows: for a large amount of fingerprint data obtained in other indoor scenes, determine N sample fingerprint reference points, obtain K sample CSI data at each sample fingerprint reference point, and obtain KN sample CSI data; then, randomly obtain a sample CSI data to be located from the data other than the KN sample CSI data in the large amount of fingerprint data, so that KN+1 sample CSI data are obtained. Among them, the coordinates and labels of the fingerprint points corresponding to the CSI data in the large amount of fingerprint data are known quantities.

[0142] After obtaining the above KN+1 sample CSI data, the labels of the above sample CSI data to be located are artificially masked and treated as unknown quantities. Afterwards, the above KN+1 sample CSI data are processed according to the processing method of CSI data in the indoor wireless positioning method described above to obtain the predicted coordinates of the fingerprint points corresponding to the above sample CSI data to be located, which is the training output result of the above indoor wireless positioning model.

[0143] In the training of the indoor wireless positioning model, the sample loss of the model is calculated based on the training output of the model, and then the parameters of the model are adjusted based on the sample loss. Specifically, in the embodiment of the present invention, the sample loss includes the fingerprint sample matching loss and the fingerprint sample similarity distribution loss, wherein the fingerprint sample matching loss function can be shown as the following formula (11):

[0144]

[0145] Among them, y i and They are the sample CSI data x to be located respectively i The true labels and predicted labels.

[0146] The fingerprint sample similarity distribution loss function can be expressed as follows:

[0147]

[0148] Finally, the sample loss function of the above indoor wireless positioning model can be expressed as follows:

[0149]

[0150] in, represents the number of calculations of the second similarity in one training of the above indoor wireless positioning model, and γ is the fingerprint sample matching loss function The weight of λ is the fingerprint sample similarity distribution loss function The weights γ and λ are used to balance the importance of the fingerprint sample matching loss function and the fingerprint sample similarity distribution loss function. The values ​​can be determined according to the needs. For example, γ can be taken as 0.9 and λ can be taken as 0.1.

[0151] After the sample loss of the indoor wireless positioning model is obtained in the manner shown in formula (13), the parameters of the indoor wireless positioning model are adjusted based on the sample loss, and the indoor wireless positioning model is continuously trained until a preset training termination condition is reached. Specifically, the preset training termination condition may be a preset number of training times. When the preset training termination condition is reached, it is considered that the indoor wireless positioning model has been trained.

[0152] It can be seen from the above that in the solution provided by the embodiment of the present invention, the coordinates of the fingerprint point to be located can be obtained by processing each CSI data using the trained indoor wireless positioning model.

[0153] See also Fig.10 , is a schematic diagram of the structure of the calculation process of the fingerprint feature full connection graph and the similarity distribution full connection graph provided by the embodiment of the present invention. Fig.10 It can be seen that after calculating the first similarity between each CSI data and constructing the fingerprint feature fully connected graph, the similarity distribution features between each CSI data are calculated as nodes in the similarity distribution fully connected graph, and the second similarity between each similarity distribution feature is calculated, thereby constructing the similarity distribution fully connected graph; then, each CSI data is updated based on the features of each edge in the similarity distribution fully connected graph, and the calculation is repeated in this way.

[0154] See also Fig.11 , is a schematic diagram of the structure of the calculation process of the indoor wireless positioning method provided by the embodiment of the present invention. Fig.11 It can be seen that first, the features of the CSI data at each fingerprint reference point and the fingerprint point to be located are extracted to generate a representation vector of each CSI data, and then a fingerprint feature fully connected graph is constructed, and the node features and edge features of the fingerprint feature fully connected graph are calculated to construct a similarity distribution fully connected graph. After that, the fingerprint feature fully connected graph and the similarity distribution fully connected graph can be calculated and updated multiple times. Based on the edge features related to the CSI data at the fingerprint point to be located in the final updated fingerprint feature fully connected graph, as well as the data of each fingerprint reference point, the matching probability between the fingerprint point to be located and each fingerprint reference point is obtained, and finally the coordinates of the fingerprint point to be located are determined based on the matching probability.

[0155] Corresponding to the aforementioned indoor wireless positioning method, an embodiment of the present invention further provides an indoor wireless positioning device.

[0156] See also Fig.12 , is a schematic diagram of the structure of an indoor wireless positioning device provided by an embodiment of the present invention, the device is applied to an electronic device with computing capability, and the device includes:

[0157] The acquisition module 1201 is used to obtain channel state information CSI data of the wireless network communication technology Wi-Fi at each fingerprint reference point with known indoor coordinates and at the fingerprint point to be located, wherein different fingerprint reference points correspond to different positions indoors, and the distance between any two fingerprint reference points is greater than a preset distance.

[0158] The first calculation module 1202 is used to calculate the first similarities between the CSI data, and calculate the similarity distribution characteristics between the CSI data based on the first similarities and the CSI data.

[0159] The second calculation module 1203 is used to calculate the second similarities between the similarity distribution features, and update the CSI data based on the second similarities.

[0160] The third calculation module 1204 is used to calculate the matching probability between the fingerprint point to be located and each fingerprint reference point based on the similarity between the finally updated CSI data of the fingerprint point to be located and other CSI data and the other CSI data.

[0161] The determination module 1205 is used to select a fingerprint reference point that matches the fingerprint point to be located based on the matching probability, and determine the coordinates of the fingerprint point to be located based on the coordinates of the selected fingerprint reference point.

[0162] In one embodiment of the present invention, the first calculation module 1202 is specifically used for:

[0163] Calculate the first similarity between each CSI data, and construct a fingerprint feature fully connected graph, wherein the features of each node in the fingerprint feature fully connected graph are the CSI data, and the features of each edge in the fingerprint feature fully connected graph are the first similarity between the features of the connected nodes;

[0164] Based on the features of each node and each edge in the fingerprint feature fully connected graph, the similarity distribution features between the CSI data are calculated.

[0165] In one embodiment of the present invention, the second calculation module 1203 is specifically used for:

[0166] Calculate the second similarity between the similarity distribution features, and construct a similarity distribution fully connected graph, wherein the features of each node in the similarity distribution fully connected graph are the similarity distribution features, and the features of each edge in the similarity distribution fully connected graph are the second similarities between the features of the connected nodes;

[0167] Each CSI data is updated based on the features of each edge in the similarity distribution fully connected graph.

[0168] As can be seen from the above, in the solution provided by the embodiment of the present invention, firstly, the CSI data of each fingerprint reference point in the room and the fingerprint point to be located are obtained, and then the first similarity between each CSI data is calculated, and then the similarity distribution characteristics between each CSI data are obtained; the second similarity between each similarity distribution feature is calculated, and then each CSI data is updated according to the second similarity, and the similarity between each updated CSI data obtained in this way can describe the distribution relationship of the similarity between the CSI data of each fingerprint reference point and the CSI data of the fingerprint point to be located. Based on the similarity between the CSI data of the fingerprint point to be located obtained by the final update and the CSI data of each fingerprint reference point, the matching probability between the fingerprint point to be located and each fingerprint reference point can be obtained, and then the coordinates of the fingerprint point to be located can be determined according to the matching probability.

[0169] Moreover, the scheme provided by the embodiment of the present invention requires that the spacing between each fingerprint reference point is greater than the preset spacing, so as to ensure that the CSI data of each fingerprint reference point has obvious characteristic differences, thereby ensuring that the similarity between each updated CSI data finally obtained can better describe the distribution relationship between the CSI data of each fingerprint reference point and the CSI data of the fingerprint point to be located, so that the matching probability between the obtained fingerprint point to be located and each fingerprint reference point can better conform to the actual situation. Therefore, when the scheme provided by the embodiment of the present invention is used for indoor wireless positioning, the spacing between the fingerprint reference points for collecting CSI data is larger, so when the indoor size is fixed, the number of fingerprint reference points will not be too large. Compared with the related technology, it can reduce the manpower and time cost required for collecting CSI data of fingerprint reference points, thereby reducing the deployment time of the indoor wireless positioning system.

[0170] In one embodiment of the present invention, the above device further includes:

[0171] Return to execution module 1206, used to return to repeatedly execute the above steps of calculating the first similarities between each CSI data, calculating the similarity distribution characteristics between each CSI data based on each first similarity and each CSI data, calculating the second similarity between each similarity distribution feature, and updating each CSI data based on each second similarity, until the number of repeated executions reaches a preset number of times.

[0172] It can be seen from the above description that the function of the return execution module 1206 is to make the first calculation module 1202 and the second calculation module 1203 repeatedly execute their corresponding operations until the number of repeated executions reaches a preset number.

[0173] It can be seen from the above that in the solution provided by the embodiment of the present invention, by repeated calculations, each CSI data is continuously updated, so that the characteristic information between each CSI data is propagated and aggregated multiple times, which can improve the calculation accuracy of the coordinates of the fingerprint point to be located.

[0174] In one embodiment of the present invention, the determination module 1205 is specifically used to:

[0175] Based on the matching probability, a preset proportion of fingerprint reference points with the highest matching probability with the fingerprint to be located are selected, and based on the coordinates of the selected fingerprint reference points, the coordinates of the fingerprint point to be located are determined.

[0176] As can be seen from the above, in the solution provided by the embodiment of the present invention, a preset proportion of fingerprint reference points with the highest probability of matching the above-mentioned fingerprint to be located are selected, that is, the coordinates of the above-mentioned fingerprint point to be located are comprehensively determined based on multiple fingerprint reference points with higher matching probabilities, so that the determined coordinates of the fingerprint point to be located are more in line with the actual situation.

[0177] In one embodiment of the present invention, the first calculation module 1202, the second calculation module 1203, the third calculation module 1204 and the determination module 1205 are specifically used to:

[0178] Input each CSI data into a pre-trained indoor wireless positioning model to obtain the coordinates of the fingerprint point to be located output by the indoor wireless positioning model;

[0179] Among them, the above-mentioned indoor wireless positioning model is used to: calculate the first similarity between each CSI data, and calculate the similarity distribution characteristics between each CSI data based on each first similarity and each CSI data; calculate the second similarity between each similarity distribution feature, and update each CSI data based on each second similarity; based on the similarity between the CSI data of the above-mentioned fingerprint point to be located and other CSI data obtained by the final update and the above-mentioned other CSI data, calculate the matching probability between the above-mentioned fingerprint point to be located and each fingerprint reference point; based on the above-mentioned matching probability, select the fingerprint reference point matching the above-mentioned fingerprint point to be located, and determine the coordinates of the above-mentioned fingerprint point to be located based on the coordinates of the selected fingerprint reference point.

[0180] It can be seen from the above that in the solution provided by the embodiment of the present invention, the coordinates of the fingerprint point to be located can be obtained by processing each CSI data using the trained indoor wireless positioning model.

[0181] See also Fig.13 , is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, including a processor 1301, a communication interface 1302, a memory 1303 and a communication bus 1304, wherein the processor 1301, the communication interface 1302, and the memory 1303 communicate with each other through the communication bus 1304;

[0182] Memory 1303, used for storing computer programs;

[0183] The processor 1301 is used to implement any step of the aforementioned indoor wireless positioning method when executing the program stored in the memory 1303.

[0184] As can be seen from the above, in the solution provided by the embodiment of the present invention, firstly, the CSI data of each fingerprint reference point in the room and the fingerprint point to be located are obtained, and then the first similarity between each CSI data is calculated, and then the similarity distribution characteristics between each CSI data are obtained; the second similarity between each similarity distribution feature is calculated, and then each CSI data is updated according to the second similarity, and the similarity between each updated CSI data obtained in this way can describe the distribution relationship of the similarity between the CSI data of each fingerprint reference point and the CSI data of the fingerprint point to be located. Based on the similarity between the CSI data of the fingerprint point to be located obtained by the final update and the CSI data of each fingerprint reference point, the matching probability between the fingerprint point to be located and each fingerprint reference point can be obtained, and then the coordinates of the fingerprint point to be located can be determined according to the matching probability.

[0185] Moreover, the scheme provided by the embodiment of the present invention requires that the spacing between each fingerprint reference point is greater than the preset spacing, so as to ensure that the CSI data of each fingerprint reference point has obvious characteristic differences, thereby ensuring that the similarity between each updated CSI data finally obtained can better describe the distribution relationship between the CSI data of each fingerprint reference point and the CSI data of the fingerprint point to be located, so that the matching probability between the obtained fingerprint point to be located and each fingerprint reference point can better conform to the actual situation. Therefore, when the scheme provided by the embodiment of the present invention is used for indoor wireless positioning, the spacing between the fingerprint reference points for collecting CSI data is larger, so when the indoor size is fixed, the number of fingerprint reference points will not be too large. Compared with the related technology, it can reduce the manpower and time cost required for collecting CSI data of fingerprint reference points, thereby reducing the deployment time of the indoor wireless positioning system.

[0186] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0187] The communication interface is used for communication between the above electronic device and other devices.

[0188] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0189] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0190] In another embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned indoor wireless positioning methods are implemented.

[0191] When the computer program stored in the computer-readable storage medium provided by the embodiment of the present invention is applied to perform indoor wireless positioning, first obtain the CSI data of each fingerprint reference point in the room and the fingerprint point to be located, then calculate the first similarity between each CSI data, and then obtain the similarity distribution characteristics between each CSI data; calculate the second similarity between each similarity distribution feature, and then update each CSI data according to the second similarity, so that the similarity between each updated CSI data can describe the distribution relationship of the similarity between the CSI data of each fingerprint reference point and the CSI data of the fingerprint point to be located. Based on the similarity between the CSI data of the fingerprint point to be located obtained by the final update and the CSI data of each fingerprint reference point, the matching probability between the fingerprint point to be located and each fingerprint reference point can be obtained, and then the coordinates of the fingerprint point to be located can be determined according to the matching probability.

[0192] Moreover, the scheme provided by the embodiment of the present invention requires that the spacing between each fingerprint reference point is greater than the preset spacing, so as to ensure that the CSI data of each fingerprint reference point has obvious characteristic differences, thereby ensuring that the similarity between each updated CSI data finally obtained can better describe the distribution relationship between the CSI data of each fingerprint reference point and the CSI data of the fingerprint point to be located, so that the matching probability between the obtained fingerprint point to be located and each fingerprint reference point can better conform to the actual situation. Therefore, when the scheme provided by the embodiment of the present invention is used for indoor wireless positioning, the spacing between the fingerprint reference points for collecting CSI data is larger, so when the indoor size is fixed, the number of fingerprint reference points will not be too large. Compared with the related technology, it can reduce the manpower and time cost required for collecting CSI data of fingerprint reference points, thereby reducing the deployment time of the indoor wireless positioning system.

[0193] In another embodiment of the present invention, a computer program product including instructions is provided. When the computer program product is run on a computer, the computer executes any one of the indoor wireless positioning methods in the above embodiments.

[0194] When the computer program product provided by the embodiment of the present invention is applied to indoor wireless positioning, the CSI data of each indoor fingerprint reference point and the fingerprint point to be located are first obtained, and then the first similarity between each CSI data is calculated, and then the similarity distribution characteristics between each CSI data are obtained; the second similarity between each similarity distribution feature is calculated, and then each CSI data is updated according to the second similarity, and the similarity between each updated CSI data obtained in this way can describe the distribution relationship of the similarity between the CSI data of each fingerprint reference point and the CSI data of the fingerprint point to be located. Based on the similarity between the CSI data of the fingerprint point to be located obtained by the final update and the CSI data of each fingerprint reference point, the matching probability between the fingerprint point to be located and each fingerprint reference point can be obtained, and then the coordinates of the fingerprint point to be located can be determined according to the matching probability.

[0195] Moreover, the scheme provided by the embodiment of the present invention requires that the spacing between each fingerprint reference point is greater than the preset spacing, so as to ensure that the CSI data of each fingerprint reference point has obvious characteristic differences, thereby ensuring that the similarity between each updated CSI data finally obtained can better describe the distribution relationship between the CSI data of each fingerprint reference point and the CSI data of the fingerprint point to be located, so that the matching probability between the obtained fingerprint point to be located and each fingerprint reference point can better conform to the actual situation. Therefore, when the scheme provided by the embodiment of the present invention is used for indoor wireless positioning, the spacing between the fingerprint reference points for collecting CSI data is larger, so when the indoor size is fixed, the number of fingerprint reference points will not be too large. Compared with the related technology, it can reduce the manpower and time cost required for collecting CSI data of fingerprint reference points, thereby reducing the deployment time of the indoor wireless positioning system.

[0196] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk Solid State Disk (SSD)), etc.

[0197] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0198] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, electronic device, computer-readable storage medium, and computer program product embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0199] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. An indoor wireless positioning method, characterized in that: The method comprises: Acquire channel state information CSI data of wireless network communication technology Wi-Fi at each fingerprint reference point with known indoor coordinates and at the fingerprint point to be located, where different fingerprint reference points correspond to different positions indoors, and the distance between any two fingerprint reference points is greater than a preset distance; Calculating first similarities between the CSI data, and calculating similarity distribution characteristics between the CSI data based on the first similarities and the CSI data; Calculating second similarities between the similarity distribution features, and updating the CSI data based on the second similarities; Calculate the matching probability between the fingerprint point to be located and each fingerprint reference point based on the similarity between the finally updated CSI data of the fingerprint point to be located and other CSI data and the other CSI data; Based on the matching probability, a fingerprint reference point matching the fingerprint point to be located is selected, and based on the coordinates of the selected fingerprint reference point, the coordinates of the fingerprint point to be located are determined.

2. The method according to claim 1, characterized in that Before calculating the matching probability between the fingerprint point to be located and each fingerprint reference point based on the similarity between the CSI data of the fingerprint point to be located and other CSI data obtained by the final update and the other CSI data, the method further includes: Return to repeatedly executing the steps of calculating the first similarities between the CSI data, calculating the similarity distribution features between the CSI data based on the first similarities and the CSI data, calculating the second similarities between the similarity distribution features, and updating the CSI data based on the second similarities, until the number of repetitions reaches a preset number.

3. The method according to claim 1, characterized in that The calculating of the first similarities between the CSI data and calculating the similarity distribution characteristics between the CSI data based on the first similarities and the CSI data include: Calculate the first similarity between each CSI data, and construct a fingerprint feature fully connected graph, wherein the features of each node in the fingerprint feature fully connected graph are each CSI data, and the features of each edge in the fingerprint feature fully connected graph are the first similarity between the features of the connected nodes; The similarity distribution characteristics between the CSI data are calculated based on the characteristics of each node and the characteristics of each edge in the fingerprint feature fully connected graph.

4. The method according to claim 1, characterized in that: The calculating the second similarities between the similarity distribution features and updating the CSI data based on the second similarities includes: Calculating the second similarity between the similarity distribution features, and constructing a similarity distribution fully connected graph, wherein the features of each node in the similarity distribution fully connected graph are the similarity distribution features, and the features of each edge in the similarity distribution fully connected graph are the second similarities between the features of the connected nodes; Each CSI data is updated based on the features of each edge in the similarity distribution fully connected graph.

5. The method according to any one of claims 1 to 4, characterized in that The selecting a fingerprint reference point that matches the fingerprint point to be located includes: A preset proportion of fingerprint reference points having the highest probability of matching the fingerprint to be located are selected.

6. The method according to claim 1, characterized in that The step of calculating the first similarities between the CSI data, calculating the similarity distribution characteristics between the CSI data based on the first similarities and the CSI data, selecting a fingerprint reference point matching the fingerprint point to be located based on the matching probability, and determining the coordinates of the fingerprint point to be located based on the coordinates of the selected fingerprint reference point, comprises: Input each CSI data into a pre-trained indoor wireless positioning model to obtain the coordinates of the fingerprint point to be located output by the indoor wireless positioning model; The indoor wireless positioning model is used to: calculate the first similarity between each CSI data, and calculate the similarity distribution characteristics between each CSI data based on each first similarity and each CSI data; calculate the second similarity between each similarity distribution feature, and update each CSI data based on each second similarity; calculate the matching probability between the fingerprint point to be located and each fingerprint reference point based on the similarity between the CSI data of the fingerprint point to be located and other CSI data obtained by the final update and the other CSI data; based on the matching probability, select a fingerprint reference point that matches the fingerprint point to be located, and determine the coordinates of the fingerprint point to be located based on the coordinates of the selected fingerprint reference point.

7. An indoor wireless positioning device, characterized in that: The device comprises: An acquisition module is used to acquire channel state information CSI data of the wireless network communication technology Wi-Fi at each fingerprint reference point with known indoor coordinates and at the fingerprint point to be located, wherein different fingerprint reference points correspond to different positions indoors, and the distance between any two fingerprint reference points is greater than a preset distance; A first calculation module, configured to calculate first similarities between each CSI data, and calculate similarity distribution characteristics between each CSI data based on each first similarity and each CSI data; A second calculation module, configured to calculate a second similarity between the similarity distribution features, and update each CSI data based on the second similarity; A third calculation module, configured to calculate a matching probability between the fingerprint point to be located and each fingerprint reference point based on the similarity between the finally updated CSI data of the fingerprint point to be located and other CSI data and the other CSI data; The determination module is used to select a fingerprint reference point matching the fingerprint point to be located based on the matching probability, and determine the coordinates of the fingerprint point to be located based on the coordinates of the selected fingerprint reference point.

8. The device according to claim 7, characterized in that The device also includes: The return execution module is used to return to repeatedly execute the steps of calculating the first similarities between the CSI data, calculating the similarity distribution characteristics between the CSI data based on the first similarities and the CSI data, calculating the second similarities between the similarity distribution characteristics, and updating the CSI data based on the second similarities, until the number of repeated executions reaches a preset number of times.

9. The device according to claim 7, characterized in that The first calculation module is specifically used for: Calculate the first similarity between each CSI data, and construct a fingerprint feature fully connected graph, wherein the features of each node in the fingerprint feature fully connected graph are each CSI data, and the features of each edge in the fingerprint feature fully connected graph are the first similarity between the features of the connected nodes; The similarity distribution characteristics between the CSI data are calculated based on the characteristics of each node and the characteristics of each edge in the fingerprint feature fully connected graph.

10. The device according to claim 7, characterized in that The second calculation module is specifically used for: Calculating the second similarity between the similarity distribution features, and constructing a similarity distribution fully connected graph, wherein the features of each node in the similarity distribution fully connected graph are the similarity distribution features, and the features of each edge in the similarity distribution fully connected graph are the second similarities between the features of the connected nodes; Each CSI data is updated based on the features of each edge in the similarity distribution fully connected graph.

11. The device according to any one of claims 7 to 10, characterized in that The determination module is specifically used for: Based on the matching probability, a preset proportion of fingerprint reference points having the highest matching probability with the fingerprint to be located are selected, and based on the coordinates of the selected fingerprint reference points, the coordinates of the fingerprint point to be located are determined.

12. The device according to claim 7, characterized in that The first calculation module, the second calculation module, the third calculation module and the determination module are specifically used to: Input each CSI data into a pre-trained indoor wireless positioning model to obtain the coordinates of the fingerprint point to be located output by the indoor wireless positioning model; The indoor wireless positioning model is used to: calculate the first similarity between each CSI data, and calculate the similarity distribution characteristics between each CSI data based on each first similarity and each CSI data; calculate the second similarity between each similarity distribution feature, and update each CSI data based on each second similarity; calculate the matching probability between the fingerprint point to be located and each fingerprint reference point based on the similarity between the CSI data of the fingerprint point to be located and other CSI data obtained by the final update and the other CSI data; based on the matching probability, select a fingerprint reference point that matches the fingerprint point to be located, and determine the coordinates of the fingerprint point to be located based on the coordinates of the selected fingerprint reference point.

13. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, for implementing the method steps described in any one of claims 1 to 6 when executing a program stored in a memory.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps of any one of claims 1 to 6 are implemented.

Images