CN111263295A - WLAN indoor positioning method and device - Google Patents

Abstract

The application discloses a WLAN indoor positioning method and a device, which are used for carrying out principal component analysis on acquired first environmental information data in a target room and selecting the first environmental information data corresponding to the accumulated contribution rate meeting preset conditions as second environmental information data; constructing a target indoor model based on the second environmental information data; arranging APs and setting reference points in the target indoor model, and acquiring a signal strength RSSI value of each reference point; based on the signal strength RSSI value of each reference point, carrying out region division on the environment in the target room according to a fuzzy clustering algorithm to obtain a plurality of sub-regions; the obtained signal strength RSSI value of the test point in the subregion is input into a preset convolutional neural network model corresponding to the subregion, and the positioning result of the test point is output, so that the technical problems of low positioning speed and low positioning precision existing in the existing indoor positioning method for searching and positioning by adopting Euclidean distance are solved.

Description

A WLAN indoor positioning method and device

technical field

The present application relates to the technical field of indoor positioning, and in particular, to a WLAN indoor positioning method and device.

Background technique

With the popularization of wireless networks, location-based services have attracted more and more attention. At present, the existing global satellite positioning system estimates the position by measuring the time difference of arrival from a satellite signal by the receiver, and can analyze the position information with higher precision. However, due to the serious multipath and non-line-of-sight interference of satellite signals in indoor and high-rise cities, it is difficult to achieve positioning function indoors.

At present, Wireless Local Area Network (WLAN) has been widely distributed in domestic airports, railway stations, libraries, government office buildings and large shopping malls. ) of the signal strength value RSSI (Received Signal Strength Indicator, signal strength indicator) to obtain the corresponding position information. However, the existing indoor positioning methods mostly use the Euclidean distance for search and positioning, which has the problems of slow speed and low positioning accuracy.

SUMMARY OF THE INVENTION

The present application provides a WLAN indoor positioning method and device, which are used to solve the technical problems of slow positioning speed and low positioning accuracy existing in the existing indoor positioning method using Euclidean distance for search and positioning.

In view of this, a first aspect of the present application provides a WLAN indoor positioning method, including:

acquiring first environment information data in the target room, where the first environment information data includes spatial three-dimensional point cloud data, the position coordinates of the target object, the azimuth angle and the pitch angle of the target object;

Perform principal component analysis on the first environmental information data, and select the first environmental information data corresponding to the cumulative contribution rate that satisfies the preset condition as the second environmental information data;

Constructing the target indoor environment based on the second environment information data to obtain a target indoor model;

Arranging APs and setting reference points in the target indoor model, and acquiring the signal strength RSSI value of each of the reference points in the target indoor model;

Based on the RSSI value of the signal strength of each of the reference points, according to the fuzzy clustering algorithm, the environment in the target room is divided into regions to obtain several sub-regions;

The acquired signal strength RSSI value of the test point in the sub-area is input into the preset convolutional neural network model corresponding to the sub-area, and the positioning result of the test point is output.

Preferably, the performing principal component analysis on the first environmental information data, and selecting the first environmental information data corresponding to the cumulative contribution rate satisfying a preset condition as the second environmental information data, including:

Calculate a correlation coefficient based on the first environmental information data, and generate a correlation coefficient matrix;

Solving the characteristic equation constructed based on the correlation coefficient matrix to obtain the characteristic value;

calculating a contribution rate based on the eigenvalue;

The first environmental information data corresponding to the minimum number of characteristic values corresponding to the cumulative contribution rate greater than 85% is selected as the second environmental information data.

Preferably, before arranging APs and setting reference points in the target indoor model, and acquiring the RSSI value of the signal strength of each of the reference points in the target indoor model, the method further includes:

The coordinate processing is performed on the target indoor model.

Preferably, arranging APs and setting reference points in the target indoor model, and acquiring the signal strength RSSI value of each of the reference points in the target indoor model, includes:

Arrange a number of APs and set a number of reference points in the target indoor model, and the reference points are evenly distributed according to a preset distance;

The signal strength RSSI value from each of the APs for each of the reference points is collected.

Preferably, the arrangement of several APs and the setting of several reference points in the target indoor model further includes:

A target reference point is selected from several of the reference points, a three-dimensional coordinate system is established with the target reference point as an origin, and the position coordinates of each of the reference points are obtained based on the three-dimensional coordinate system.

Preferably, inputting the acquired signal strength RSSI value of the test point in the sub-area into a preset convolutional neural network model corresponding to the sub-area, and outputting the positioning result of the test point, further comprising:

Taking the position coordinates of the reference point of each of the sub-regions and the RSSI value of the signal strength of the reference point as a training set;

Each of the training sets trains a convolutional neural network model, and when the convolutional neural network model reaches the convergence condition, several trained convolutional neural network models are obtained, and the trained convolutional neural network models are The network model is used as the preset convolutional neural network model.

A second aspect of the present application provides a WLAN indoor positioning device, including:

a first acquisition module, configured to acquire first environmental information data in the target room, where the first environmental information data includes spatial three-dimensional point cloud data, the position coordinates of the target object, the azimuth angle and the pitch angle of the target object;

a principal component analysis module, configured to perform principal component analysis on the first environmental information data, and select the first environmental information data corresponding to the cumulative contribution rate satisfying a preset condition as the second environmental information data;

a building module for constructing the target indoor environment based on the second environment information data to obtain a target indoor model;

a second acquisition module, configured to arrange APs and set reference points in the target indoor model, and acquire the RSSI value of the signal strength of each of the reference points in the target indoor model;

a division module, configured to divide the environment in the target room according to the fuzzy clustering algorithm based on the RSSI value of the signal strength of each of the reference points to obtain several sub-areas;

The positioning module is configured to input the acquired signal strength RSSI value of the test point in the sub-region into the preset convolutional neural network model corresponding to the sub-region, and output the positioning result of the test point.

Preferably, it also includes:

The preprocessing module is used for coordinate processing on the target indoor model.

Preferably, the second acquisition module includes:

an arrangement sub-module for arranging a number of APs and setting a number of reference points in the target indoor model, and the reference points are evenly distributed according to a preset distance;

A collection submodule, configured to collect the RSSI value of the signal strength from each of the APs of each of the reference points.

Preferably, the second acquisition module further includes:

The selection sub-module is used for selecting a target reference point from several of the reference points, establishing a three-dimensional coordinate system with the target reference point as an origin, and obtaining the position coordinates of each of the reference points based on the three-dimensional coordinate system.

As can be seen from the above technical solutions, the present application has the following advantages:

The present application provides a WLAN indoor positioning method, including: acquiring first environment information data in a target room, where the first environment information data includes spatial three-dimensional point cloud data, position coordinates of a target object, and azimuth and elevation angles of the target object; Perform principal component analysis on the first environmental information data, and select the first environmental information data corresponding to the cumulative contribution rate that satisfies the preset conditions as the second environmental information data; build the target indoor environment based on the second environmental information data, and obtain the target indoor model ; Arrange APs and set reference points in the target indoor model, and obtain the signal strength RSSI value of each reference point in the target indoor model; The area is divided to obtain several sub-areas; the obtained signal strength RSSI value of the test point in the sub-area is input into the preset convolutional neural network model corresponding to the sub-area, and the positioning result of the test point is output.

The WLAN indoor positioning method in the present application performs principal component analysis on the acquired first environment information data in the target room, selects the first environment information data corresponding to the cumulative contribution rate satisfying the preset condition as the second environment information data, and retains The first environmental information data that has a great influence on the construction of the target indoor model is removed, and the first environmental information data that has little influence on the target indoor model is removed, which achieves a certain data dimensionality reduction effect and improves the positioning speed to a certain extent; Build a target indoor model based on the second environmental information data, arrange APs and set reference points reasonably in the target indoor model, obtain the RSSI value of the signal strength from each AP at the reference point, and divide the target indoor environment through a clustering algorithm. , to obtain multiple sub-regions, by inputting the RSSI value of the signal strength of the test point in the sub-region into the preset convolutional neural network model corresponding to the sub-region, the positioning result of the test point is obtained, and the small region is divided on the basis of the sub-region. The precise positioning improves the indoor positioning accuracy as well as the positioning speed, and solves the technical problems of slow positioning speed and low positioning accuracy existing in the existing indoor positioning method using Euclidean distance for search and positioning.

Description of drawings

FIG. 1 is a schematic flowchart of a WLAN indoor positioning method provided by an embodiment of the present application;

FIG. 2 is another schematic flowchart of a WLAN indoor positioning method provided by an embodiment of the present application;

FIG. 3 is a schematic structural diagram of a WLAN indoor positioning apparatus according to an embodiment of the present application.

Detailed ways

In order to make those skilled in the art better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only It is a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

For ease of understanding, please refer to FIG. 1 , an embodiment of a WLAN indoor positioning method provided by the present application includes:

Step 101: Acquire first environment information data in the target room.

It should be noted that the first environment information data includes spatial three-dimensional point cloud data, the position coordinates of the target object, the azimuth angle and the elevation angle of the target object. In this embodiment of the present application, multiple cameras and multiple radars may be used to obtain the first environment information data in the target room, and the cameras may collect environment images in the target room, and the collected images may demarcate target objects such as tables and chairs in the target room. , the time difference between the transmitted pulse and the echo pulse is measured by radar. Since the electromagnetic wave propagates at the speed of light, it can be converted into the precise distance of the target object. In addition, the azimuth of the target object is measured through the sharp azimuth beam of the antenna The elevation angle beam measures the elevation angle, and then the height of the target object can be calculated according to the elevation angle and distance of the target object.

Step 102: Perform principal component analysis on the first environmental information data, and select the first environmental information data corresponding to the cumulative contribution rate satisfying the preset condition as the second environmental information data.

It should be noted that principal component analysis is performed on the first environmental information data, and the contribution rate corresponding to each first environmental information data is calculated, and the contribution rate represents the impact of each first environmental information data on the target indoor environment modeling, and the contribution rate The larger the value, the greater the impact of the corresponding first environmental information data on the target indoor environment modeling. The first environmental information data with greater influence is obtained through the contribution rate screening as the second environmental information data used to construct the target indoor model. It achieves a certain degree of dimensionality reduction for the data and avoids the influence of redundant data on modeling.

Step 103 , constructing a target indoor environment based on the second environment information data, and obtaining a target indoor model.

It should be noted that the process of constructing the target indoor environment based on the second environment information data and obtaining the target indoor model belongs to the prior art, and the specific process of the modeling will not be repeated here.

Step 104: Arrange APs and set reference points in the target indoor model, and obtain the RSSI value of the signal strength of each reference point in the target indoor model.

It should be noted that after arranging APs and setting reference points in the target indoor model, a signal receiver can be set at each reference point, and the signal strength RSSI value sent by each AP can be recorded by the signal receiver, so as to obtain each signal strength RSSI value. Signal strength RSSI value of the reference point.

Step 105 , based on the RSSI value of the signal strength of each reference point, according to the fuzzy clustering algorithm, divide the environment of the target room into regions, and obtain several sub-regions.

It should be noted that some reference points are marked as the known category information of fuzzy clustering, and the target indoor environment is divided into multiple sub-regions through the fuzzy clustering algorithm, and the category information of the sub-region to which each reference point belongs is marked, thereby realizing Division of areas.

Step 106: Input the acquired signal strength RSSI value of the test point in the sub-area into the preset convolutional neural network model corresponding to the sub-area, and output the location result of the test point.

It should be noted that each sub-area corresponds to a preset convolutional neural network model. The preset convolutional neural network model can be a trained BP neural network model, or other trained convolutional neural network models. When a test point needs to be located, a signal receiver can be arranged at the test point to record the signal strength RSSI value sent by each AP, and input the acquired signal strength RSSI values from different APs to the test point. In the preset convolutional neural network model corresponding to the sub-region of , the positioning information of the test point is output.

In the WLAN indoor positioning method in the embodiment of the present application, by performing principal component analysis on the acquired first environment information data in the target room, the first environment information data corresponding to the cumulative contribution rate satisfying the preset condition is selected as the second environment information data , the first environmental information data that has a great influence on the construction of the target indoor model is retained, and the first environmental information data that has little influence on the target indoor model is removed, which achieves a certain effect of data dimensionality reduction and improves positioning to a certain extent. Speed; build a target indoor model based on the second environmental information data, reasonably arrange APs and set reference points in the target indoor model, obtain the RSSI value of the signal strength from each AP at the reference point, and perform a clustering algorithm on the target indoor environment. The area is divided to obtain multiple sub-areas. By inputting the RSSI value of the signal strength of the test point in the sub-area into the preset convolutional neural network model corresponding to the sub-area, the positioning result of the test point is obtained. Precise positioning in small areas not only improves indoor positioning accuracy, but also improves positioning speed, and solves the technical problems of slow positioning speed and low positioning accuracy in existing indoor positioning methods using Euclidean distance for search and positioning.

For ease of understanding, please refer to FIG. 2 , another embodiment of a WLAN indoor positioning method provided by the present application includes:

Step 201: Acquire first environment information data in the target room.

It should be noted that the first environment information data includes spatial three-dimensional point cloud data, the position coordinates of the target object, the azimuth angle and the elevation angle of the target object. In this embodiment of the present application, multiple cameras and multiple radars may be used to obtain the first environment information data in the target room, and the cameras may collect environment images in the target room, and the collected images may demarcate target objects such as tables and chairs in the target room. , the time difference between the transmitted pulse and the echo pulse is measured by radar. Since the electromagnetic wave propagates at the speed of light, it can be converted into the precise distance of the target object. In addition, the azimuth of the target object is measured through the sharp azimuth beam of the antenna The elevation angle beam measures the elevation angle, and then the height of the target object can be calculated according to the elevation angle and distance of the target object.

Step 202: Perform principal component analysis on the first environmental information data, and select the first environmental information data corresponding to the cumulative contribution rate satisfying the preset condition as the second environmental information data.

It should be noted that the first environmental information data obtained by different cameras and radars are respectively recorded as O ₁ , O ₂ ,...O _i ,...,O _j ,...,On , and _n is an integer greater than 0 , calculate the correlation coefficient r _ij based on the first environmental information data, and generate the correlation coefficient matrix R, namely:

分别为O_i和O_j的平均值，当所有相关系数计算完后，生成的相关系数矩阵为Wherein, r _ij is the correlation coefficient between the first environmental information data O _i and the first environmental information data O _j , r _ij =r _ji ,

are the average of O _i and O _j respectively. After all correlation coefficients are calculated, the generated correlation coefficient matrix is

Solve the characteristic equation |λI-R|=0 constructed based on the correlation coefficient matrix, and obtain the characteristic values λ _l , l=1,2,...,n, which can be calculated by tools such as MATLAB.

The contribution rate is calculated based on the eigenvalues, and the calculation formula of the contribution rate is:

Select the first environmental information data corresponding to the minimum number of eigenvalues when the cumulative contribution rate is greater than 85% as the second environmental information data, and the calculation formula of the cumulative contribution rate is:

The contribution rate represents the impact of each first environmental information data on the target indoor environment modeling. The greater the contribution rate, the greater the impact of the corresponding first environmental information data on the target indoor environment modeling. The affected first environment information data is used as the second environment information data for constructing the target indoor model, which achieves a certain degree of dimensionality reduction effect on the data and avoids the influence of redundant data on modeling.

Step 203 , constructing a target indoor environment based on the second environment information data to obtain a target indoor model.

It should be noted that the process of constructing the target indoor environment based on the second environment information data and obtaining the target indoor model belongs to the prior art, and the specific process of the modeling will not be repeated here.

Step 204 , performing coordinate processing on the target indoor model.

It should be noted that the coordinate processing of the target indoor model is to simulate the target indoor environment into a three-dimensional coordinate system in space. If the origin is set in the coordinate system, a complete three-dimensional coordinate system that can obtain coordinate values is formed. Subsequent acquisition of the position coordinates of the reference point provides a basis, and the coordinate processing of the model belongs to the prior art, and the specific process of the coordinate processing of the model will not be repeated here. Wherein, the coordinate-processed target indoor model can be stored in the memory.

Step 205: Arrange APs and set reference points in the target indoor model, and obtain the position coordinates of each reference point in the target indoor model and the RSSI value of the signal strength of each reference point.

It should be noted that, arrange several APs in the target indoor model. When arranging APs, ensure that any point in the target room is covered by the signals sent by two or more APs, and set several reference points in the target indoor model. Each reference point is evenly arranged according to the preset distance, and the specific value of the preset distance can be selected according to the actual situation. Select a reference point from all reference points as the target reference point, establish a three-dimensional coordinate system with the target reference point as the origin, and based on the three-dimensional coordinate system, the position coordinates of each reference point can be obtained; it can be set at the position of each reference point The signal receiver records the signal strength RSSI value sent by each AP through the signal receiver, so as to obtain the signal strength RSSI value of each reference point.

Step 206 , based on the RSSI value of the signal strength of each reference point, according to the fuzzy clustering algorithm, divide the environment of the target room into regions, and obtain several sub-regions.

It should be noted that the original data matrix A is obtained according to the RSSI value of the signal strength of each reference point:

A=(x _ij ) _n×m , j=1,2,...,m; i=1,2,...,n;

Among them, n is the number of APs, m is the number of reference points, and x _ij is the RSSI value of the signal strength sent by the i-th AP received by the j-th reference point.

The fuzzy similarity matrix is established by lattice closeness, so that:

a_j、b_j、a_i和b_i为对信号强度RSSI值的隶属度的近似值；Among them, r _ij is the similarity coefficient,

a _j , b _j , a _i and b _i are approximate values of membership to the RSSI value of the signal strength;

The fuzzy similarity matrix is:

R=(r _ij ) _m×m ;

Calculate the fuzzy equivalence matrix from the fuzzy similarity matrix:

t(R)=R ^* =R2 ^;

Assume

t(R)=(r _ij ') _m×m ;

t(R) _λ =(r _ij '(λ)) _m×m ;

Starting from the fuzzy similarity matrix R obtained above, a fuzzy equivalent matrix R ^* can be constructed by using the square method to find the transitive closure t(R) of R, and then take a set of λ∈[0 ,1], generally λ=0.998, if r _ij '(λ)=1, it is considered that the arrangement position of the ith AP and the position of the jth reference point can be regarded as a sub-area, so as to realize the target indoor environment into multiple sub-regions.

Step 207: Use the position coordinates of the reference point of each sub-region and the RSSI value of the signal strength of the reference point as a training set.

It should be noted that the position coordinates of the reference point of each sub-region and the RSSI value of the signal strength of the reference point are used as a training set, each sub-region corresponds to a training set, and there are as many training sets as there are sub-regions.

Step 208: Train a convolutional neural network model for each training set. When the convolutional neural network model reaches the convergence condition, several trained convolutional neural network models are obtained, and the trained convolutional neural network model is used as a preset. Convolutional Neural Network Model.

It should be noted that, in the embodiment of the present application, each training set trains a convolutional neural network model, and there are as many training sets as there are corresponding convolutional neural network models. The number of layer nodes h is determined by the empirical formula, namely:

Among them, o is the number of nodes in the input layer, p is the number of nodes in the output layer, and q is an adjustment constant between 1 and 10.

According to the input vector, the connection weight w _ij between the input layer and the hidden layer, and the threshold a _j , calculate the hidden layer output H:

Wherein, f(·) is an activation function, and the activation function in this embodiment of the present application is f(x)=1/(1+e ^−x ).

According to the hidden layer output H, the connection layer weight w _jk and the threshold b _k , calculate the output layer output O _k :

Among them, m is the number of output layer nodes.

According to the output value O _k of the convolutional neural network and the expected output y _k (that is, the position coordinates of the reference point), the identification error E of the model is calculated:

Update the network connection weights w _ij and w _jk according to the model identification error E:

δ _jk =(y _k -O _k )·O _k ·(1-O _k );

为学习率，根据实际情况进行设置。in,

For the learning rate, set it according to the actual situation.

According to the model identification error E, update the thresholds a _j and b _k of the network nodes:

When the recognition error of the convolutional neural network model is less than the preset threshold, the iteration ends, and the trained convolutional neural network model is obtained, and the trained convolutional neural network model is used as the preset convolutional neural network model.

Step 209: Input the acquired signal strength RSSI value of the test point in the sub-region into the preset convolutional neural network model corresponding to the sub-region, and output the positioning result of the test point.

It should be noted that each sub-region corresponds to a preset convolutional neural network model. When a test point needs to be located, a signal receiver can be arranged at the test point to record the signal strength RSSI value sent by each AP. Input the RSSI value of the obtained signal strength from different APs into the preset convolutional neural network model corresponding to the sub-region where the test point is located, so as to output the position coordinates of the test point, and obtain the positioning information of the test point, wherein , the sub-region where the test point is located can be determined by the aforementioned clustering algorithm. Comparing the errors of the WLAN indoor positioning in the embodiment of the present application with the traditional positioning method, as shown in Table 1, the WLAN indoor positioning method in the embodiment of the present application has smaller errors and higher accuracy.

Table 1 Error comparison table

test point Traditional solution positioning error Positioning error in this application test point 1 5.3% 3.2% test point 2 6.1% 4.1% Test point 3 10.4% 5.3% test point 4 7.2% 3.1%

For ease of understanding, please refer to FIG. 3 , an embodiment of a WLAN indoor positioning device provided by the present application includes:

The first obtaining module 301 is configured to obtain first environment information data in the target room, where the first environment information data includes spatial three-dimensional point cloud data, the position coordinates of the target object, the azimuth angle and the elevation angle of the target object.

The principal component analysis module 302 is configured to perform principal component analysis on the first environmental information data, and select the first environmental information data corresponding to the cumulative contribution rate satisfying the preset condition as the second environmental information data.

The construction module 303 is configured to construct the target indoor environment based on the second environment information data to obtain the target indoor model.

The second acquiring module 304 is used for arranging APs and setting reference points in the target indoor model, and acquiring the RSSI value of the signal strength of each reference point in the target indoor model.

The division module 305 is configured to divide the environment in the target indoor environment according to the fuzzy clustering algorithm based on the RSSI value of the signal strength of each reference point, and obtain several sub-areas.

The positioning module 306 is configured to input the acquired RSSI value of the signal strength of the test point in the sub-region into the preset convolutional neural network model corresponding to the sub-region, and output the positioning result of the test point.

Further, it also includes:

The preprocessing module 307 is used for coordinate processing on the target indoor model.

Further, the second obtaining module 304 includes:

The arrangement sub-module 3041 is used for arranging several APs and setting several reference points in the target indoor model, and the reference points are evenly distributed according to the preset distance.

The collection sub-module 3042 is configured to collect the RSSI value of the signal strength from each AP of each reference point.

Further, the second obtaining module 304 also includes:

The selection sub-module 3043 is used to select a target reference point among several reference points, establish a three-dimensional coordinate system with the target reference point as the origin, and obtain the position coordinates of each reference point based on the three-dimensional coordinate system.

Further, it also includes:

The training set acquisition module 308 is used to use the position coordinates of the reference point of each sub-region and the signal strength RSSI value of the reference point as a training set;

The training module 309 is used to train a convolutional neural network model for each training set. When the convolutional neural network model reaches the convergence condition, several trained convolutional neural network models are obtained, and the trained convolutional neural network models are As a preset convolutional neural network model.

Further, the principal component analysis module 302 is specifically used for:

Calculate a correlation coefficient based on the first environmental information data, and generate a correlation coefficient matrix;

Solve the characteristic equation constructed based on the correlation coefficient matrix to obtain the characteristic value;

Calculate contribution rate based on eigenvalues;

Select the first environment information data corresponding to the minimum number of characteristic values when the cumulative contribution rate is greater than 85% as the second environment information data.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

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

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.

The integrated unit, if implemented in the form of a software functional unit and sold or used as an independent product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the present application can be embodied in the form of software products in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, and the computer software products are stored in a storage medium , including several instructions for executing all or part of the steps of the methods described in the various embodiments of the present application through a computer device (which may be a personal computer, a server, or a network device, etc.). The aforementioned storage media include: U disk, mobile hard disk, read-only memory (full English name: Read-Only Memory, English abbreviation: ROM), random access memory (English full name: Random Access Memory, English abbreviation: RAM), magnetic disks Or various media such as optical discs that can store program codes.

As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand: The technical solutions described in the embodiments are modified, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions in the embodiments of the present application.

Claims (10)

1. a WLAN indoor positioning method, is characterized in that, comprises: acquiring first environment information data in the target room, where the first environment information data includes spatial three-dimensional point cloud data, the position coordinates of the target object, the azimuth angle and the pitch angle of the target object; Perform principal component analysis on the first environmental information data, and select the first environmental information data corresponding to the cumulative contribution rate that satisfies the preset condition as the second environmental information data; Constructing the target indoor environment based on the second environment information data to obtain a target indoor model; Arranging APs and setting reference points in the target indoor model, and acquiring the signal strength RSSI value of each of the reference points in the target indoor model; Based on the RSSI value of the signal strength of each of the reference points, according to the fuzzy clustering algorithm, the environment in the target room is divided into regions to obtain several sub-regions; The acquired signal strength RSSI value of the test point in the sub-area is input into the preset convolutional neural network model corresponding to the sub-area, and the positioning result of the test point is output. 2 . The WLAN indoor positioning method according to claim 1 , wherein the principal component analysis is performed on the first environmental information data, and the first environmental information corresponding to the cumulative contribution rate satisfying a preset condition is selected. 3 . The data is the second environmental information data, including: Calculate a correlation coefficient based on the first environmental information data, and generate a correlation coefficient matrix; Solving the characteristic equation constructed based on the correlation coefficient matrix to obtain the characteristic value; calculating a contribution rate based on the eigenvalue; The first environmental information data corresponding to the minimum number of characteristic values corresponding to the cumulative contribution rate greater than 85% is selected as the second environmental information data. 3 . The WLAN indoor positioning method according to claim 1 , wherein the AP and reference points are arranged in the target indoor model, and the signal strength of each reference point in the target indoor model is obtained. 4 . RSSI values, which previously included: The coordinate processing is performed on the target indoor model. 4 . The WLAN indoor positioning method according to claim 3 , wherein the AP and reference points are arranged in the target indoor model, and the signal strength of each reference point in the target indoor model is obtained. 5 . RSSI values, including: Arrange a number of APs and set a number of reference points in the target indoor model, and the reference points are evenly distributed according to a preset distance; The signal strength RSSI value from each of the APs for each of the reference points is collected. 5. The WLAN indoor positioning method according to claim 4, characterized in that, arranging several APs and setting several reference points in the target indoor model, further comprising: A target reference point is selected from several of the reference points, a three-dimensional coordinate system is established with the target reference point as an origin, and the position coordinates of each of the reference points are obtained based on the three-dimensional coordinate system. 6 . The WLAN indoor positioning method according to claim 5 , wherein the acquired signal strength RSSI value of the test point in the sub-area is input into a preset convolutional neural network corresponding to the sub-area. 7 . The model, which outputs the positioning results of the test points, also includes: Taking the position coordinates of the reference point of each of the sub-regions and the RSSI value of the signal strength of the reference point as a training set; Each of the training sets trains a convolutional neural network model, and when the convolutional neural network model reaches the convergence condition, several trained convolutional neural network models are obtained, and the trained convolutional neural network models are The network model is used as the preset convolutional neural network model. 7. A WLAN indoor positioning device, comprising: a first acquisition module, configured to acquire first environmental information data in the target room, where the first environmental information data includes spatial three-dimensional point cloud data, the position coordinates of the target object, the azimuth angle and the pitch angle of the target object; a principal component analysis module, configured to perform principal component analysis on the first environmental information data, and select the first environmental information data corresponding to the cumulative contribution rate satisfying a preset condition as the second environmental information data; a building module for constructing the target indoor environment based on the second environment information data to obtain a target indoor model; a second acquisition module, configured to arrange APs and set reference points in the target indoor model, and acquire the RSSI value of the signal strength of each of the reference points in the target indoor model; a division module, configured to divide the environment in the target room according to the fuzzy clustering algorithm based on the RSSI value of the signal strength of each of the reference points to obtain several sub-areas; The positioning module is configured to input the acquired signal strength RSSI value of the test point in the sub-region into the preset convolutional neural network model corresponding to the sub-region, and output the positioning result of the test point. 8. The WLAN indoor positioning device according to claim 7, further comprising: The preprocessing module is used for coordinate processing on the target indoor model. 9. The WLAN indoor positioning device according to claim 8, wherein the second acquisition module comprises: an arrangement sub-module for arranging a number of APs and setting a number of reference points in the target indoor model, and the reference points are evenly distributed according to a preset distance; A collection submodule, configured to collect the RSSI value of the signal strength from each of the APs of each of the reference points. 10. The WLAN indoor positioning device according to claim 9, wherein the second acquisition module further comprises: The selection sub-module is used for selecting a target reference point from several of the reference points, establishing a three-dimensional coordinate system with the target reference point as an origin, and obtaining the position coordinates of each of the reference points based on the three-dimensional coordinate system.

Images