CN105101408A - Indoor positioning method based on distributed AP selection strategy - Google Patents

Abstract

The invention discloses an indoor positioning method based on a distributed AP selection strategy. The method comprises the following steps of using mobile equipment to collect k times of signal intensities of AP nodes on each reference point and processing data; equally dividing a target area into m subareas, classifying fingerprint information of the different subareas, using a fingerprint information base to train a subarea module and selecting the corresponding subarea according to RSS fingerprint information; calculating a correlation of each AP node and each subarea, sorting correlation coefficients, selecting the AP node whose correlation coefficient is greater than Ptau as a positioning node of the subarea; in each subarea, taking the selected positioning node as input of a DBN model and a corresponding position point as output of the DBN model, training the DBN model and constructing a positioning prediction model. By using the method, big noise and the AP node with a weak position distinguishing capability can be effectively removed; positioning precision of an overall WIFI indoor positioning system is increased and algorithm operation time is shortened.

Description

Based on the indoor orientation method of distributed AP selection strategy

Technical field

The present invention relates to a kind of indoor orientation method, relate to the indoor orientation method of a kind of WIFI based on distributed AP selection strategy particularly.

Background technology

Indoor positioning is a kind of technology for obtaining indoor objects object location information, is with a wide range of applications in civil and military field.Common location algorithm is mainly based on received signal strength indicator (ReceivedSignalStrengthIndication, RSSI), the time of advent (TimeofArrival, TOA), the time of advent poor (TimeDifferenceofArrival, TDOA), the technology such as angle of arrival (AngleofArrival, AOA).Wherein, the location algorithm based on RSSI has low-power consumption, low cost and the advantage easily realized, and is widely used in wireless indoor location.

The location algorithm of RSSI is used usually to be divided into: the location algorithm based on signal propagation model and the location algorithm based on Fingerprint Model.Traditional location algorithm based on signal propagation model is mainly through obtaining a large amount of sample datas, utilize legacy paths loss model to set up the functional relation of received signal strength indicator (RSSI) and euclidean distance between node pair, then estimate the positional information of target.Because wireless signal is comparatively subject to the impact of indoor environment change in communication process, RSSI value is caused to have obvious fluctuation, in legacy paths loss model, path damped expoential and envirment factor are difficult to determine simultaneously, these factors will affect the range accuracy of model, and then cause position error to increase.

Location algorithm based on Fingerprint Model sets up location model according to statistical analysis technique on the basis of a large amount of actual sample data, wherein learning model is widely used in training location prediction model as the one of statistical analysis technique, finally predicts target location with this location prediction model.The essence of the method is that one group of wireless signal strength and target location are set up mapping relations.The people such as Zhou adopt artificial neural net (ArtificialNeuralNetwork, ANN) as study forecasting tool, and integration region partitioning technology is predicted target location, achieves preferably location prediction effect.RSSI and positional information are set up non-linear relation by the people such as Sang Nan, utilize SVMs (SupportVectorMachine, SVM) to learn and predicted position information, effectively reduce position error.

Wherein based on the location algorithm of Fingerprint Model, there is positioning precision high, make full use of existing utility, upgrading and maintenance are to advantages such as customer impact are little, and be widely applied, location fingerprint location algorithm is mainly divided into off-line measurement stage and tuning on-line stage two steps.

In the wireless network with a large amount of AP node deployment, in order to obtain target location, the data handled by said method are all high dimension vector (numbers of AP node).Simultaneously, due to blocking and the factor such as node failure of object, causing might not be optimum as the locating effect that feature inputs using all AP nodes, and the AP node of redundancy adds the difficulty of location estimation, easily cause the problem of overfitting, and add the complexity of Time and place.For this problem, adopt suitable selection mechanism screening AP node, obtain preferably AP node and input as feature, both reached the effect of dimensionality reduction, turn improved positioning precision.Conventional method judges the stationkeeping ability of AP usually according to the average signal strength of a certain AP received, signal strength signal intensity average is larger, then think that the stationkeeping ability of this AP is stronger.Find in reality, this AP system of selection is incorrect, as less in AP signal strength signal intensity its fluctuation all larger everywhere in locating area, although this AP signal strength signal intensity mean value is very large, but stationkeeping ability is more weak.Conventional method does not consider that certain AP has different location contributions for positions different in localizing environment simultaneously, and such as an AP may be fine to a certain zone location ability, but poor to other zone location abilities.

Summary of the invention

In order to solve the problems of the technologies described above, the present invention seeks to: a kind of indoor orientation method based on distributed AP selection strategy is provided, the impact of larger noise and the weak AP node of position resolution can be avoided, also improve positioning precision the operation time simultaneously reduced needed for location.

Technical scheme of the present invention is:

Based on an indoor orientation method for distributed AP selection strategy, comprise the following steps:

S01: arrange D AP node in indoor environment, ensure the quorum sensing inhibitor that optional position in indoor environment o'clock is sent by the AP node of more than three or three, this target area is divided into N number of zonule simultaneously, with center, zonule for signal strength signal intensity collection point, N number of reference point altogether, for off-line phase collecting sample data;

S02: set up two-dimensional direct angle coordinate system to target area, obtains the coordinate position of N number of reference point, and in each reference point, utilize mobile device to gather the signal strength signal intensity of k AP node, and processes data;

S03: utilized target area the method for homalographic to be divided into m sub regions, classified by the finger print information of different subregion, utilizes training subregion, finger print information storehouse module, selects corresponding subregion according to RSS finger print information;

S04: the correlation calculating each AP node and each sub regions, and relative coefficient is sorted, select relative coefficient to be greater than P _τaP node, as the location node of this subregion, wherein, P _τrepresent the threshold value of relative coefficient;

S05: in every sub regions, utilizes the location node chosen as the input of DBN model, and corresponding location point is as the output of DBN model, and training DBN model, builds location prediction model;

S06: on-line prediction stage, obtains RSS finger print information that mobile device receives and as the input vector of subregion module, the subregion of output vector belonging to this RSS finger print information of subregion module;

S07: the signal strength signal intensity of the AP node utilizing the subregion that obtains in step S06 corresponding, as the input vector of DBN model, utilizes the DBN model of having trained to obtain the position of target.

Preferably, described step S02 specifically comprises the steps:

S21: the signal strength signal intensity RSS value receiving each AP node in each reference point, forms D dimensional signal vector RSS ^d; Each reference point gathers k signal strength values, constitutes the signal strength signal intensity matrix of k*D, and the signal strength signal intensity RSS value receiving a jth AP node in i-th collection is shown in the i-th row jth list of its matrix; I is the positive integer being less than or equal to k; J is the positive integer being less than or equal to D;

RSS ^D＝(rss ₁,rss ₂,rss ₃,…,rss _j,…,rss _D)(1)

In formula: rss _j∈ [-100,0] represents that reference point place receives the signal strength signal intensity of a jth AP node.

S22: build fingerprint database, training data is concentrated and is comprised N bar record, and every bar record is expressed as vectorial r, comprises the available signal strength signal intensity of AP node and the position of sampled point in vector:

r＝(RSS ⁱ,L ⁱ)＝(rss ₁,rss ₂,rss ₃,… _,rss _D,L ⁱ)(2)

In formula: RSS ⁱrepresent the RSS set received in gathering for i-th time, D represents the number of AP node, L ⁱrepresent and correspond to RSS ^dthe location tags of vector.

Preferably, described step S03 specifically comprises the following steps:

S31: locating area S is divided into m sub regions, shown in subregion is defined as follows:

$\begin{array}{cccc}{R}_c=\{L_1^c,L_2^c,...,L_k^c\}& \∀L_k^c\∈S& and& S=\underset{c=1}{\overset{m}{\∪}}{R}_c---\end{array}\left(3\right)$

In formula: c represents c sub regions, k represents the number of location point in this subregion, R _crepresent reference position point set in c sub regions; represent the information of a kth location point in c sub regions;

S32: signal strength signal intensity in fingerprint database classified according to different subregions, sets up the record information list of subregion and signal strength signal intensity.

S33: build subregion module, determine BP neural network model and train with the recorded information of signal strength signal intensity the BP neural net set up according to subregion mark, using signal strength signal intensity RSSI as input, corresponding subregion mark area is as output training BP neural net, and the parameter revising BP neural net in training makes it reflect the relation of RSSI-area;

S34: identify area with the actual signal strength values RSSI received with corresponding subregion and go repetition training and verify the BP neural net set up, the BP neural net of having trained is packaged into a fixing function, this function is input as received signal strength RSSI, exports and is corresponding subregion mark.

Preferably, described BP neural net is five layers of neural net, the number of plies of hidden layer is 2 layers, the interstitial content of input layer is D, and the interstitial content of output layer is 1, and the interstitial content of hidden layer is respectively 6,4, namely adopt the BP neural network structure of D:6:4:1, training function is traincgf algorithm, and frequency of training and target error are set to 100 and 0.00004 respectively.

Preferably, described step S04 specifically comprises the following steps:

S41: in this subregion, the signal of a jth AP node on k location point in scanning area, this AP node is defined as follows at the relative coefficient of this subregion:

$\begin{array}{cc}{P}_j=\frac{\left|\underset{i=1}{\overset{k}{\Σ}}(x_i-x)(y_i-y)({\mathrm{rss}}_{ji}-{\mathrm{rss}}_j)\right|}{\sqrt{\underset{i=1}{\overset{k}{\Σ}}{(x_i-x)}^2\underset{i=1}{\overset{k}{\Σ}}{(y_i-y)}^2\underset{i=1}{\overset{k}{\Σ}}{({\mathrm{rss}}_{ji}-{\mathrm{rss}}_j)}^2}}& j=1...D\end{array}---\left(4\right)$

In formula: P _jrepresent the correlation of a jth AP node and this subregion, x _irepresent the X-axis coordinate of i-th location point, x represents the average of the X-axis coordinate of k location point in this region, y _irepresent the Y-axis coordinate of i-th location point, y represents the average of the Y-axis coordinate of k location point in this region, rss _jirepresent that i-th location point receives the average of the signal strength signal intensity of a jth AP node, rss _jrepresent the signal strength signal intensity average of the jth AP node that k location point receives, k represents the number of location point in this subregion, and D represents the number of AP node in locating area;

S42: in every sub regions, the relative coefficient vector representation of D AP node is:

P(AP)＝[P ₁,P ₂,...,P _D](5)

If P _j>P _τrepresent that a jth AP node is relevant to this subregion, on the contrary then uncorrelated, P _τrepresent the threshold value of relative coefficient.

Preferably, described step S05 specifically comprises the following steps:

S51: the signal strength signal intensity obtaining the AP node of all location point information and correspondence in this subregion in fingerprint database, as the training dataset of this subregion;

S52: determine DBN model and go to train with the training dataset of this subregion and set up DBN model, using the signal strength signal intensity RSSI of the corresponding A P node received as input, corresponding location point Location goes to train the DBN model set up as exporting, and in training, revise the parameter of DBN model, make final location model correctly can reflect the relation of RSSI-Location;

S53: go repetition training also to verify the DBN model set up with signal strength values RSSI and the corresponding location point Location of the actual corresponding A P node received; Adjust the weights between neuron by the energy function between visible layer and hidden layer, carry out the weights between trim network finally by back-propagation algorithm.

Preferably, described DBN model is 5 layer networks, and wherein the number of plies of hidden layer is 3 layers, and the interstitial content of input layer is the number of the AP node chosen, and the node data of output layer is 2, and the interstitial content of hidden layer is respectively 10,6,4.

Preferably, DBN model comprises RBM1 and RBM2, RBM1 module and RBM2 module all comprise visible layer and hidden layer, when the signal strength signal intensity set of AP node is input to the visible layer of RBM1, weights by connecting are extracted the feature of input data by hidden layer, and adjust the weights between neuron by the energy function between visible layer and hidden layer; The output of RBM1 hidden layer is using the input as RBM2 visible layer, RBM2 hidden layer extracts the profound feature of grouped data further, the DBN model of having trained is packaged into a fixing function, the input of this function is received signal strength RSSI, exports the location point being target.

Advantage of the present invention is:

1, the method effectively can remove larger noise and the weak AP node of position resolution.By room area being divided into several independent subregions, and calculate the correlation of subregion and all AP nodes, choose the training node of the excellent AP node of correlation as this subregion, model training is positioned finally by degree of depth confidence network (DeepBeliefNetwork, DBN) model.Effectively improve the positioning precision of whole WIFI indoor locating system.

2, simplify algorithm and decrease Riming time of algorithm.

Accompanying drawing explanation

Below in conjunction with drawings and Examples, the invention will be further described:

Fig. 1 is the flow chart that the present invention locates realization;

Fig. 2 is the general framework figure of the indoor positioning algorithms of the distributed AP selection strategy that the present invention proposes;

Fig. 3 is indoor scene schematic diagram of the present invention;

Fig. 4 is DBN model structured flowchart.

Wherein: 1, station, 2, AP node, 3, pillar.

Embodiment

For making the object, technical solutions and advantages of the present invention clearly understand, below in conjunction with embodiment also with reference to accompanying drawing, the present invention is described in more detail.Should be appreciated that, these describe just exemplary, and do not really want to limit the scope of the invention.In addition, in the following description, the description to known features and technology is eliminated, to avoid unnecessarily obscuring concept of the present invention.

Embodiment:

As shown in Figure 1, a kind of indoor orientation method based on distributed AP selection strategy, comprises the following steps:

S01: arrange D AP node in indoor environment, ensure the quorum sensing inhibitor that optional position in indoor environment o'clock is sent by the AP node of more than three or three, this target area is divided into N number of zonule simultaneously, with center, zonule for signal strength signal intensity collection point, N number of reference point altogether, for off-line phase collecting sample data;

S02: set up two-dimensional direct angle coordinate system to target area, obtains the coordinate position of N number of reference point, and in each reference point, utilize mobile device to gather the signal strength signal intensity of k AP node, and processes data;

S03: utilized target area the method for homalographic to be divided into m sub regions, classified by the finger print information of different subregion, utilizes training subregion, finger print information storehouse module, selects corresponding subregion according to RSS finger print information;

S04: the correlation calculating each AP node and each sub regions, and relative coefficient is sorted, select relative coefficient to be greater than P _τaP node, as the location node of this subregion, P _τrepresent the threshold value of relative coefficient;

S05: in every sub regions, utilizes the location node chosen as the input of DBN model, and corresponding location point is as the output of DBN model, and training DBN model, builds location prediction model;

S06: on-line prediction stage, obtains RSS finger print information that mobile device receives and as the input vector of subregion module, the subregion of output vector belonging to this RSS finger print information of subregion module;

S07: the signal strength signal intensity of the AP node utilizing the subregion that obtains in step S06 corresponding, as the input vector of DBN model, utilizes the DBN model of having trained to obtain the position of target.

The collection experiment scene of locator data is located at Comprehensive Experiment indoor, tests in the indoor scene shown in Fig. 3, and the terminal equipment of data acquisition is a Samsung smart mobile phone (I9228), and operating system is Android4.1.2.This laboratory is about 12.8m, wide about 12.5m, height is 3m about, and indoor are furnished with station 1, the office appliancess such as computer, AP node 2 highly keeps 1.6m, the layout of AP node 2 as shown in Figure 3, in this region, the signal of 25 AP nodes 2 can be collected, wherein, the propagation path of the signal of part AP node 2 is non line of sight, there is the obstruct of pillar 3.During experiment, this target area is divided into 144 zonules, each zonule size is 1m × 1m, and with center, zonule for signal strength signal intensity collection point, totally 144 reference points, for off-line phase collecting sample data.For ensureing the accuracy of sample data, each signal acquisition point obtains the set of signals of 600 AP nodes 2, once per second.

Receive the signal strength signal intensity RSS value of each AP node in each reference point, form 25 dimensional signal vector RSS ^d; Each reference point gathers 600 signal strength values, constitutes the signal strength signal intensity matrix of 600*25, and the signal strength signal intensity RSS value receiving a jth AP node in i-th collection is shown in the i-th row jth list of its matrix; I is the positive integer being less than or equal to k; J is the positive integer being less than or equal to D;

RSS ²⁵＝(rss ₁,rss ₂,rss ₃,…,rss ₂₅)(1)

In formula: rss _j∈ [-100,0] represents that reference point place receives the signal strength signal intensity of a jth AP node.

Build fingerprint database, training data is concentrated and is comprised N bar record, and every bar record can be expressed as vectorial r, comprises the available signal strength signal intensity of AP node and the position of sampled point in vector:

$r=({\mathrm{RSS}}^i,L^i)=({\mathrm{rss}}_1,{\mathrm{rss}}_2,{\mathrm{rss}}_3,...,,)---\left(2\right)$

In formula: D represents the number of AP node, L ⁱrepresent and correspond to RSS ^dthe location tags of vector.If mobile device does not receive the signal of certain AP node, acquiescence uses-100 to fill this AP node signal strength value.The reason that mobile device does not receive certain AP node signal has following 2 points: one is this AP one malfunctions; Two is that this AP node is subject to blocking of barrier.

It is as shown in the table for the fingerprint database set up:

L 1	X 1	Y 1	rss 1	……	rss 25
						……	……	……	……	……	……
L N	X N	Y N	rss 1	……	rss 25

Wherein, L ₁to L _nbe the N number of reference point chosen, the information of each reference point comprises the RSS value of positional information and D AP.

Suppose Region dividing to be 4 sub regions, subregion defines as shown in Equation 3:

$\begin{array}{cccc}{R}_c=\{L_1^c,L_2^c,...,L_k^c\}& \∀L_i^c\∈S& and& S=\underset{c=1}{\overset{4}{\∪}}{R}_c\end{array}---\left(3\right)$

In formula: c represents c sub regions, k represents the number of location point in this subregion, and S represents locating area (target area), R _crepresent reference position point set in c sub regions; represent the information of a kth location point in c sub regions.

The subregion different according to each, classifies signal strength signal intensity in fingerprint database according to different subregions, and the recorded information of subregion and signal strength signal intensity represents and is:

area 1

rss 1

……

rss 25

area 1	rss 1	……	rss 25
				……	……	……	……
area 4	rss 1	……	rss 25

Area ₁represent the 1st sub regions, rss ₁represent the signal strength signal intensity of the 1st AP node.

Build subregion module, determine BP neural network model and train with the recorded information of signal strength signal intensity the BP neural net set up according to subregion mark, using signal strength signal intensity RSSI as input, corresponding subregion mark area is as output training BP neural net, and each parameter revising BP neural net in training is can reflect the relation of RSSI-area; The BP neural net adopted is five layers of neural net; In the five layers of neural net adopted, the number of plies of hidden layer is 2 layers, the interstitial content of input layer is 25, the interstitial content of output layer is 1, and the interstitial content of hidden layer is respectively 6,4, namely the BP neural network structure of 25:6:4:1 is adopted, training function be traincgf algorithm, frequency of training and target error be set to respectively 100 and territory, 0.00004, BP network partition module as shown in Figure 2.

The signal strength values RSSI received by reality and corresponding subregion identify area and go repetition training and verify the BP neural net set up, the BP neural net of having trained is packaged into a fixing function, this function is input as received signal strength RSSI, exports and is corresponding subregion mark.

Suppose in this subregion, the signal of a jth AP node on k location point in scanning area, so this AP node is defined as follows at the relative coefficient in this region:

$\begin{array}{cc}{P}_j=\frac{\left|\underset{i=1}{\overset{k}{\Σ}}(x_i-x)(y_i-y)({\mathrm{rss}}_{ji}-{\mathrm{rss}}_j)\right|}{\sqrt{\underset{i=1}{\overset{k}{\Σ}}{(x_i-x)}^2\underset{i=1}{\overset{k}{\Σ}}{(y_i-y)}^2\underset{i=1}{\overset{k}{\Σ}}{({\mathrm{rss}}_{ji}-{\mathrm{rss}}_j)}^2}}& j=\mathrm{1...25}\end{array}---\left(4\right)$

In formula: P _jrepresent the correlation in a jth AP node and this region, x _irepresent the X-axis coordinate of i-th location point, x represents the average of the X-axis coordinate of k location point in this region, y _irepresent the Y-axis coordinate of i-th location point, y represents the average of the Y-axis coordinate of k location point in this region, rss _jirepresent that i-th location point receives the average of the signal strength signal intensity of a jth AP node, rss _jrepresent the signal strength signal intensity average of a jth AP node of k location point reception in this region, k represents the number of location point in this subregion.

In every sub regions, the relative coefficient vector representation of 25 AP nodes is:

P(AP)＝[P ₁，P ₂，...，](5)

If P _j>P _τrepresent that a jth AP node is relevant to this subregion, on the contrary then uncorrelated.Choose the AP node relevant to this region to input as feature, position model training.

P _τrepresent the threshold value of relative coefficient, adopt the method for repetition test to determine.

In fingerprint database, obtain the signal strength signal intensity of the AP node of all location point information and correspondence in this subregion, it can be used as the training dataset of this subregion.

Determine DBN model and go to train with the training dataset of this subregion and set up DBN model, using the signal strength signal intensity RSSI of the corresponding A P node received as input, corresponding location point Location goes to train the DBN model set up as exporting, and in training, revise each parameter of DBN model, make final location model correctly can reflect the relation of RSSI-Location; The DBN model adopted is 5 layer networks, and wherein the number of plies of hidden layer is 3 layers, and the interstitial content of input layer is 25, and the node data of output layer is 2, and the interstitial content of hidden layer is respectively 10,6,4, and its network configuration is 25:10:6:4:2.

Signal strength values RSSI and the corresponding location point Location of the corresponding A P node received by reality go repetition training and verify the DBN model set up.

Adjust the weights between neuron by the energy function between visible layer and hidden layer, carry out the weights between trim network finally by back-propagation algorithm.DBN model as shown in Figure 4, comprises RBM1 module and RBM2 module, and RBM1 module and RBM2 module all comprise visible layer and hidden layer.Its training process is: when the signal strength signal intensity set of AP node is input to the visible layer of RBM1, and hidden layer will extract the feature of input data by the weights connected, and will adjust the weights between neuron by the energy function between visible layer and hidden layer; The output of RBM1 hidden layer is using the input as RBM2 visible layer, and new hidden layer extracts the profound feature of grouped data further.The DBN model of having trained is packaged into a fixing function, the input of this function is received signal strength RSSI, exports the location point being target.

At the RSS finger print information that test point receives, as the input vector of subregion module, the output vector of subregion module is the subregion belonging to this finger print information.

Utilize the subregion obtained in step 6, the signal strength signal intensity of the AP node utilizing this subregion corresponding, as the input vector of DBN model, utilizes the DBN model of having trained to obtain the position of final goal.

Should be understood that, above-mentioned embodiment of the present invention only for exemplary illustration or explain principle of the present invention, and is not construed as limiting the invention.Therefore, any amendment made when without departing from the spirit and scope of the present invention, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.In addition, claims of the present invention be intended to contain fall into claims scope and border or this scope and border equivalents in whole change and modification.

Claims (8)

1. based on an indoor orientation method for distributed AP selection strategy, it is characterized in that, comprise the following steps:

S01: arrange D AP node in indoor environment, ensure the quorum sensing inhibitor that optional position in indoor environment o'clock is sent by the AP node of more than three or three, this target area is divided into N number of zonule simultaneously, with center, zonule for signal strength signal intensity collection point, N number of reference point altogether, for off-line phase collecting sample data;

S02: set up two-dimensional direct angle coordinate system to target area, obtains the coordinate position of N number of reference point, and in each reference point, utilize mobile device to gather the signal strength signal intensity of k AP node, and processes data;

S03: utilized target area the method for homalographic to be divided into m sub regions, classified by the finger print information of different subregion, utilizes training subregion, finger print information storehouse module, selects corresponding subregion according to RSS finger print information;

S04: the correlation calculating each AP node and each sub regions, and relative coefficient is sorted, select relative coefficient to be greater than P _τaP node, as the location node of this subregion, wherein, P _τrepresent the threshold value of relative coefficient;

S05: in every sub regions, utilizes the location node chosen as the input of DBN model, and corresponding location point is as the output of DBN model, and training DBN model, builds location prediction model;

S06: on-line prediction stage, obtains RSS finger print information that mobile device receives and as the input vector of subregion module, the subregion of output vector belonging to this RSS finger print information of subregion module;

S07: the signal strength signal intensity of the AP node utilizing the subregion that obtains in step S06 corresponding, as the input vector of DBN model, utilizes the DBN model of having trained to obtain the position of target.

2. the indoor orientation method based on distributed AP selection strategy according to claim 1, is characterized in that, described step S02 specifically comprises the steps:

S21: the signal strength signal intensity RSS value receiving each AP node in each reference point, forms D dimensional signal vector RSS ^d; Each reference point gathers k signal strength values, constitutes the signal strength signal intensity matrix of k*D, and the signal strength signal intensity RSS value receiving a jth AP node in i-th collection is shown in the i-th row jth list of its matrix; I is the positive integer being less than or equal to k; J is the positive integer being less than or equal to D;

RSS ^D＝(rss ₁,rss ₂,rss ₃,…,rss _j,…，rss _D)(1)

In formula: rss _j∈ [-100,0] represents that reference point place receives the signal strength signal intensity of a jth AP node.

S22: build fingerprint database, training data is concentrated and is comprised N bar record, and every bar record is expressed as vectorial r, comprises the available signal strength signal intensity of AP node and the position of sampled point in vector:

r＝(RSS ⁱ,L ⁱ)＝(rss ₁,rss ₂,rss ₃,…,rss _D,L ⁱ)(2)

In formula: RSS ⁱrepresent the RSS set received in gathering for i-th time, D represents the number of AP node, L ⁱrepresent and correspond to RSS ^dthe location tags of vector.

3. the indoor orientation method based on distributed AP selection strategy according to claim 1, is characterized in that, described step S03 specifically comprises the following steps:

S31: locating area S is divided into m sub regions, shown in subregion is defined as follows:

$\begin{array}{cccc}{R}_c=\left\{L_1^c,L_2^c,...,L_k^c\right\}& \∀L_k^c\∈S& and& S=\underset{c=1}{\overset{m}{\∪}}{R}_c\end{array}---\left(3\right)$

In formula: c represents c sub regions, k represents the number of location point in this subregion, R _crepresent reference position point set in c sub regions; represent the information of a kth location point in c sub regions;

S32: signal strength signal intensity in fingerprint database classified according to different subregions, sets up the record information list of subregion and signal strength signal intensity.

S33: build subregion module, determine BP neural network model and train with the recorded information of signal strength signal intensity the BP neural net set up according to subregion mark, using signal strength signal intensity RSSI as input, corresponding subregion mark area is as output training BP neural net, and the parameter revising BP neural net in training makes it reflect the relation of RSSI-area;

S34: identify area with the actual signal strength values RSSI received with corresponding subregion and go repetition training and verify the BP neural net set up, the BP neural net of having trained is packaged into a fixing function, this function is input as received signal strength RSSI, exports and is corresponding subregion mark.

4. the indoor orientation method based on distributed AP selection strategy according to claim 3, it is characterized in that, described BP neural net is five layers of neural net, and the number of plies of hidden layer is 2 layers, and the interstitial content of input layer is D, the interstitial content of output layer is 1, the interstitial content of hidden layer is respectively 6,4, namely adopts the BP neural network structure of D:6:4:1, training function is traincgf algorithm, and frequency of training and target error are set to 100 and 0.00004 respectively.

5. the indoor orientation method based on distributed AP selection strategy according to claim 1, is characterized in that, described step S04 specifically comprises the following steps:

S41: in this subregion, the signal of a jth AP node on k location point in scanning area, this AP node is defined as follows at the relative coefficient of this subregion:

$\begin{array}{cc}{P}_j=\frac{\left|\underset{i=1}{\overset{k}{\Σ}}\left(x_i-x\right)\left(y_i-y\right)\left({\mathrm{rss}}_{ji}-{\mathrm{rss}}_j\right)\right|}{\sqrt{\underset{i=1}{\overset{k}{\Σ}}{\left(x_i-x\right)}^2\underset{i=1}{\overset{k}{\Σ}}{(y_i-y)}^2\underset{i=1}{\overset{k}{\Σ}}{\left({\mathrm{rss}}_{ji}-{\mathrm{rss}}_j\right)}^2}}& j=1...D\end{array}---\left(4\right)$

In formula: P _jrepresent the correlation of a jth AP node and this subregion, x _irepresent the X-axis coordinate of i-th location point, x represents the average of the X-axis coordinate of k location point in this region, y _irepresent the Y-axis coordinate of i-th location point, y represents the average of the Y-axis coordinate of k location point in this region, rss _jirepresent that i-th location point receives the average of the signal strength signal intensity of a jth AP node, rss _jrepresent the signal strength signal intensity average of the jth AP node that k location point receives, k represents the number of location point in this subregion, and D represents the number of AP node in locating area;

S42: in every sub regions, the relative coefficient vector representation of D AP node is:

P(AP)＝[P ₁,P ₂,...,P _D](5)

If P _j>P _τrepresent that a jth AP node is relevant to this subregion, on the contrary then uncorrelated, P _τrepresent the threshold value of relative coefficient.

6. the indoor orientation method based on distributed AP selection strategy according to claim 1, is characterized in that, described step S05 specifically comprises the following steps:

S51: the signal strength signal intensity obtaining the AP node of all location point information and correspondence in this subregion in fingerprint database, as the training dataset of this subregion;

S52: determine DBN model and go to train with the training dataset of this subregion and set up DBN model, using the signal strength signal intensity RSSI of the corresponding A P node received as input, corresponding location point Location goes to train the DBN model set up as exporting, and in training, revise the parameter of DBN model, make final location model correctly can reflect the relation of RSSI-Location;

S53: go repetition training also to verify the DBN model set up with signal strength values RSSI and the corresponding location point Location of the actual corresponding A P node received; Adjust the weights between neuron by the energy function between visible layer and hidden layer, carry out the weights between trim network finally by back-propagation algorithm.

7. the indoor orientation method based on distributed AP selection strategy according to claim 6, it is characterized in that, described DBN model is 5 layer networks, wherein the number of plies of hidden layer is 3 layers, the interstitial content of input layer is the number of the AP node chosen, and the node data of output layer is 2, and the interstitial content of hidden layer is respectively 10,6,4.

8. the indoor orientation method based on distributed AP selection strategy according to claim 7, it is characterized in that, DBN model comprises RBM1 and RBM2, RBM1 module and RBM2 module all comprise visible layer and hidden layer, when the signal strength signal intensity set of AP node is input to the visible layer of RBM1, weights by connecting are extracted the feature of input data by hidden layer, and adjust the weights between neuron by the energy function between visible layer and hidden layer; The output of RBM1 hidden layer is using the input as RBM2 visible layer, RBM2 hidden layer extracts the profound feature of grouped data further, the DBN model of having trained is packaged into a fixing function, the input of this function is received signal strength RSSI, exports the location point being target.