CN103200676B - The method for building up of fingerprint base and device - Google Patents

Abstract

The invention discloses a method and device for establishing a fingerprint library, which can reduce the number of noise points in the fingerprint library. The method includes: determining whether the target collection point is a noise point according to the signal strength of the target collection point and the signal strength of at least one collection point adjacent to the target collection point; if the target collection point is a noise point, then according to the at least one The signal strength of the collection point is determined to determine the signal strength of the target collection point; the signal strength of the target collection point is correspondingly stored with the pre-stored position information of the target collection point, and a fingerprint library is established. In this way, the number of noise points in the fingerprint database can be reduced by selecting the collection points according to the signal strength to filter out the noise points. The embodiment of the present invention is mainly applied to establishing a fingerprint database, which can reduce the number of noise points in the fingerprint database.

Description

Method and device for establishing fingerprint library

technical field

The invention relates to the field of positioning technology, in particular to a method and device for establishing a fingerprint library.

Background technique

The positioning technology of fingerprint matching is a technology for realizing indoor positioning. The positioning technology of fingerprint matching can be divided into two stages, namely offline stage (Offlinestage) and online stage (Onlinestage). The offline stage refers to the establishment of a fingerprint library based on the signal strength of APs (access points, English full name AccessPoint) around each fingerprint point after selecting fingerprint points (fingerprint points can also be called fingerprint collection points or reference points). The online phase means that after the fingerprint library is established, the mobile terminal receives the signal strength of the surrounding APs, and performs matching calculations on the signal strength received by the mobile terminal and the database to determine the location of the mobile terminal.

Due to the mutual interference between the signals of different APs and other signals, the signal strength of the same AP collected by a certain fingerprint point and its surrounding fingerprint points may be quite different. Such fingerprint points are called noise points. The signal strength collected by the noise point is quite different from the signal strength collected by the surrounding fingerprint points, which leads to irregular signal strength distribution of the fingerprint library that introduces the noise point. Applying the fingerprint library with the noise point to carry out the matching operation in the online stage will affect the accuracy of the positioning results. Accuracy.

Therefore, how to reduce the number of noise points in the fingerprint library to improve the positioning accuracy is a problem that needs to be solved at present.

Contents of the invention

The embodiment of the present invention provides a method and device for establishing a fingerprint library, which can reduce the number of noise points in the fingerprint library.

The embodiment of the present invention adopts following technical scheme:

In the first aspect, a method for establishing a fingerprint library is provided, including:

According to the signal strength of the target collection point and the signal strength of at least one collection point adjacent to the target collection point, determine whether the target collection point is a noise point; if the target collection point is a noise point, according to the at least one The signal strength of the collection point is determined to determine the signal strength of the target collection point; the signal strength of the target collection point is correspondingly stored with the pre-stored position information of the target collection point, and a fingerprint library is established.

Optionally, before determining whether the target collection point is a noise point according to the signal strength of the target collection point and the signal strength of at least one collection point adjacent to the target collection point, the method further includes:

A neighborhood of the target collection point is determined according to a preset condition, and the neighborhood is composed of the target collection point and the at least one collection point.

Optionally, the determining whether the target collection point is a noise point according to the signal strength of the target collection point and the signal strengths of collection points adjacent to the target collection point includes:

According to the signal strength of the target collection point and the signal strength of the at least one collection point, determine the first similarity mean value of the target collection point; according to the signal strength of the target collection point and the signal strength of the at least one collection point Signal strength, determining a second similarity average of the at least one collection point; comparing the first similarity average with the second similarity average, if the first similarity average is greater than the second similarity average , then the target collection point is a noise point.

Optionally, the determining the signal strength of the target collection point according to the signal strength of the at least one collection point includes:

Taking the mean value of the signal strength of the at least one collection point as the signal strength of the target collection point; or, filtering out noise points from the at least one collection point, and taking the mean value of the signal strength of the remaining collection points as the target The signal strength of the collection point.

Optionally, the determining the first similarity mean value of the target collection point according to the signal strength of the target collection point and the signal strength of the at least one collection point includes:

According to the signal strength of the target collection point and the signal strength of the at least one collection point, determine the similarity between the target collection point and the at least one collection point, and compare the target collection point and the at least one collection point The average value of the similarity of the target collection point is used as the first similarity average value of the target collection point; the signal strength of the at least one collection point is determined according to the signal strength of the target collection point and the signal strength of the at least one collection point The second similarity mean value includes: according to the signal strength of the target collection point and the signal strength of the at least one collection point, determining the similarity between each collection point in the at least one collection point and its respective adjacent collection points, according to The average value of the similarity between each collection point and its respective adjacent collection points is used to determine the second average similarity of the at least one collection point.

In a second aspect, a device for establishing a fingerprint library is provided, including:

The first determination unit is used to determine whether the target collection point is a noise point according to the signal strength of the target collection point and the signal strength of at least one collection point adjacent to the target collection point; the second determination unit is used to determine if the target collection point is a noise point. If the target collection point is a noise point, then determine the signal strength of the target collection point according to the signal strength of the at least one collection point; the storage unit is used to combine the signal strength of the target collection point with the prestored The location information of the target collection point is correspondingly stored, and a fingerprint database is established.

Optionally, also include:

The third determining unit is configured to determine a neighborhood of the target collection point according to preset conditions, the neighborhood is composed of the target collection point and the at least one collection point.

Optionally, the first determination unit includes:

The first determination subunit is configured to determine the first similarity mean value of the target collection point according to the signal strength of the target collection point and the signal strength of the at least one collection point; the second determination subunit is used to determine the first similarity value of the target collection point according to The signal strength of the target collection point and the signal strength of the at least one collection point are used to determine a second average similarity value of the at least one collection point; a third determination subunit is configured to combine the first similarity average value with the The second similarity average is compared, and if the first similarity average is greater than the second similarity average, the target collection point is a noise point.

Optionally, the second determining unit is specifically configured to use the mean value of the signal strength of the at least one collection point as the signal strength of the target collection point; or, the second determining unit is specifically configured to obtain from the Noise points are filtered out of the at least one collection point, and the average signal strength of the remaining collection points is used as the signal strength of the target collection point.

Optionally, the first determining subunit is specifically configured to, according to the signal strength of the target collection point and the signal strength of the at least one collection point, determine that the target collection point is similar to the at least one collection point degree, using the average value of the similarity between the target collection point and the at least one collection point as the first similarity average value of the target collection point; the second determination subunit is specifically configured to, according to the target The signal strength of the collection point and the signal strength of the at least one collection point, determine the similarity between each collection point in the at least one collection point and the respective adjacent collection points, and determine the similarity between each collection point and the respective adjacent collection points according to the The average value of the similarity of the points is determined to determine the second average similarity of the at least one collection point.

Based on the above technical solution, the method and device for establishing a fingerprint library provided by the embodiments of the present invention, after determining that the target collection point is a noise point according to the signal strength of the target collection point and the signal strength of the collection points adjacent to the target collection point, according to the target The signal strength of the collection point adjacent to the collection point is determined to determine the signal strength of the target collection point, and the signal strength of the target collection point is correspondingly stored with the pre-stored location information of the target collection point to establish a fingerprint library. In this way, the number of noise points in the fingerprint database can be reduced by selecting the collection points according to the signal strength to filter out the noise points.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings that need to be used in the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those skilled in the art, other drawings can also be obtained based on these drawings without creative effort.

Fig. 1 is a flowchart of a method for establishing a fingerprint library provided by an embodiment of the present invention;

Fig. 2 is a flow chart of another method for establishing a fingerprint library provided by an embodiment of the present invention;

Fig. 3a is a schematic diagram of a neighborhood provided by an embodiment of the present invention;

FIG. 3b is another schematic diagram of a neighborhood provided by an embodiment of the present invention;

Fig. 3c is another schematic diagram of a neighborhood provided by an embodiment of the present invention;

Fig. 4a is a schematic diagram of a signal strength distribution provided by an embodiment of the present invention;

FIG. 4b is a schematic diagram of neighborhood division provided by an embodiment of the present invention;

Fig. 5 is a flow chart of another method for establishing a fingerprint library provided by an embodiment of the present invention;

FIG. 6 is a schematic structural diagram of an apparatus for establishing a fingerprint library provided by an embodiment of the present invention;

7 is a schematic structural diagram of another device for establishing a fingerprint library provided by an embodiment of the present invention;

FIG. 8 is a schematic structural diagram of another device for creating a fingerprint library provided by an embodiment of the present invention.

detailed description

In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are the Some, but not all, embodiments are invented. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

The embodiments of the present invention can be applied to various communication systems, such as WCDMA (Wideband Code Division Multiple Access, wideband code division multiple access) system, LTE (Long Term Evolution, long term evolution) system, and the like. The signal strength in this embodiment of the present invention may be RSSI (Received Signal Strength Indication, the full English name is ReceivedSignalStrengthIndication).

Referring to Fig. 1, a method for establishing a fingerprint library provided by an embodiment of the present invention, the method may include:

101. Determine whether the target collection point is a noise point according to the signal strength of the target collection point and the signal strength of at least one collection point adjacent to the target collection point.

Wherein, at least one collection point adjacent to the target collection point is a collection point located in the same neighborhood as the target collection point. For the determination method of the neighborhood, please refer to the subsequent section.

102. If the target collection point is a noise point, determine the signal strength of the target collection point according to the signal strength of the at least one collection point.

103. Store the signal strength of the target collection point corresponding to the pre-stored location information of the target collection point, and establish a fingerprint database.

The method for establishing the fingerprint library in the embodiment of the present invention can be realized by the device for establishing the fingerprint library. The device for establishing the fingerprint library can be a computer system or other equipment, which is not limited in the embodiment of the present invention.

The method for establishing the fingerprint library in the embodiment of the present invention, after determining that the target collection point is a noise point according to the signal strength of the target collection point and the signal strength of the collection points adjacent to the target collection point, according to the signal strength of the collection points adjacent to the target collection point Intensity, to determine the signal strength of the target collection point, store the signal strength of the target collection point and the pre-stored location information of the target collection point correspondingly, and establish a fingerprint library. In this way, the number of noise points in the fingerprint database can be reduced by selecting the collection points according to the signal strength to filter out the noise points.

As shown in Figure 2, in this embodiment of the present invention, optionally, before the above 101, it also includes:

100. Determine a neighborhood of the target collection point according to preset conditions, where the neighborhood consists of the target collection point and the at least one collection point.

In this embodiment of the present invention, the neighborhood of the target collection point can be determined according to a preset rule (such as shape). For example,

The target collection point p(i ₁ , j ₁ ) determines a collection point set U according to a certain rule or shape f, and p(i ₁ , j ₁ ) is related to a certain collection point q(i ₂ , j ₂ ) in U. Then the neighborhood of p(i ₁ ,j ₁ ) is defined as follows:

$\left\{\begin{array}{c}\mathrm{<span\; class="notranslate">\; u</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; f</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; p</span>}<span\; class="notranslate">\; )</span>\\ {\mathrm{<span\; class="notranslate">\; N</span>}}_{\mathrm{<span\; class="notranslate">\; p</span>}}^{\mathrm{<span\; class="notranslate">\; o</span>}}<span\; class="notranslate">\; =</span><span\; class="notranslate">\; \{</span>{\mathrm{<span\; class="notranslate">\; N</span>}}_{\mathrm{<span\; class="notranslate">\; q</span>}}<span\; class="notranslate">\; |</span><span\; class="notranslate">\; \&ForAll;</span>\mathrm{<span\; class="notranslate">\; q</span>}<span\; class="notranslate">\; \&Element;</span>\mathrm{<span\; class="notranslate">\; u</span>}<span\; class="notranslate">\; \}</span>\end{array}\right.<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; )</span>$

From (1-1) we know the neighborhood of p(i ₁ ,j ₁ ) does not contain p(i ₁ ,j ₁ ), it can be called a hollow neighborhood; if the neighborhood of p(i ₁ ,j ₁ ) Contains p(i ₁ ,j ₁ ), which can be expressed as N _p or N. In the neighborhood of choosing p(i ₁ ,j ₁ ) When collecting points in , you can select them according to the rules whose shape is square, rectangle or cross. Common neighborhoods include 4-domain, 8-domain, and 12-domain. As shown in Figure 3a, 3b, and 3c, the solid point is the center, and the neighborhoods contained in the dotted box with small dots are 4-domain, 8-domain, respectively. domain, l2-domain.

In the embodiment of the present invention, based on the fingerprint matching algorithm, when establishing the fingerprint library, after obtaining the signal strength (such as the RSS signal vector) of the target collection point, record the location information of the target collection point (such as the coordinates of the target collection point), and convert the The location information and the signal strength of the collection point (such as the RSS signal vector) are entered into the fingerprint database as a fingerprint, and the collection points in the fingerprint database have a certain spatial relationship.

In the embodiment of the present invention, optionally, when determining whether the target collection point is a noise point according to the signal strength of the target collection point and the signal strength of the collection points adjacent to the target collection point in the above 101, the target collection point can be According to the signal strength of the target collection point and the signal strength of the at least one collection point, determine the first similarity mean value of the target collection point; according to the signal strength of the target collection point and the signal strength of the at least one collection point, determine the at least one collection point. second similarity average: comparing the first similarity average with the second similarity average, if the first similarity average is greater than the second similarity average, then the target collection point is a noise point.

Wherein, when determining the first similarity average value of the target collection point according to the signal strength of the target collection point and the signal strength of the at least one collection point, the signal strength of the target collection point and the signal strength of the at least one collection point can be determined. Signal strength, determining the similarity between the target collection point and the at least one collection point, and using the average value of the similarity between the target collection point and the at least one collection point as the first similarity average value of the target collection point; the above-mentioned basis The signal strength of the target collection point and the signal strength of the at least one collection point, when determining the second similarity mean value of the at least one collection point, can be based on the signal strength of the target collection point and the signal strength of the at least one collection point, Determine the similarity between each collection point of the at least one collection point and the respective adjacent collection points, and determine the second similarity of the at least one collection point according to the average value of the similarity between each collection point and the respective adjacent collection points degree mean.

In the embodiment of the present invention, the noise points in the fingerprint database are distinguished according to the distribution of AP signal strength. Figure 4a is a distribution diagram of the signal strength of the AP in free space provided by the embodiment of the present invention. As shown in Figure 4, the signal of the AP covers the collection points of the area. Due to the different distances from the AP, the signal strength received by different APs is different. may be different. The different reference numbers in Figure 4a distinguish the range of signal strength values.

When judging whether the collection point C (target collection point) in Figure 4b is a noise point, the 8-neighborhood of the collection point C can be established, according to the signal strength of the collection point C and other collections of the 8-neighborhood of the collection point C in 4b The signal strength of the point can be used to judge whether the collection point C is a noise point. The signal strengths of two adjacent collection points have a certain similarity. In the embodiment of the present invention, the similarity value of two adjacent collection points is determined. When the similarity value is less than the preset threshold, the two adjacent collection points Contains noise points.

In the embodiment of the present invention, (1-2) can be used to determine the similarity between two adjacent collection points. In (1-2), L(a, b) represents the similarity between two adjacent collection points a and b, and R _a Indicates the RSSI value of the AP at collection point a, and R _b represents the RSSI value of the AP at collection point b.

L(a,b)=-(R _a -R _b ) ² (1-2)

The method for judging whether the target collection point is a noise point is described in detail below. If the 8-neighborhood that does not include the collection point C is The 8-neighborhood containing the collection point C is N _c , then:

N _c ={P ₁ ,P ₂ ,...,P ₈ ,C}(1-3)

If the collection point C is included in the 8-neighborhood, the sum of the similarities between the collection point P _i (P _i ≠C) and its adjacent collection points is but:

${\mathrm{<span\; class="notranslate">\; S</span>}}_{{\mathrm{<span\; class="notranslate">\; P</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}}^{{\mathrm{<span\; class="notranslate">\; N</span>}}_{\mathrm{<span\; class="notranslate">\; C</span>}}}<span\; class="notranslate">\; =</span>\underset{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; \&NotEqual;</span>\mathrm{<span\; class="notranslate">\; i</span>}}{\overset{{\mathrm{<span\; class="notranslate">\; u</span>}}_{{\mathrm{<span\; class="notranslate">\; P</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}}^{{\mathrm{<span\; class="notranslate">\; N</span>}}_{\mathrm{<span\; class="notranslate">\; C</span>}}}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}\mathrm{<span\; class="notranslate">\; L</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; P</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; ,</span>{\mathrm{<span\; class="notranslate">\; P</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; ,</span>{\mathrm{<span\; class="notranslate">\; P</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; \&Element;</span>{\mathrm{<span\; class="notranslate">\; u</span>}}_{{\mathrm{<span\; class="notranslate">\; P</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}}^{{\mathrm{<span\; class="notranslate">\; N</span>}}_{\mathrm{<span\; class="notranslate">\; C</span>}}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 4</span>}<span\; class="notranslate">\; )</span>$

in, is a collection of collection points adjacent to collection point P _i in the 8-neighborhood including collection point C, for example, collection points adjacent to collection point P1 are collection point P2, collection point P4, and collection point C. The collection points adjacent to the collection point P4 are the collection point P1, the collection point P2, the collection point P6, the collection point 7, and the collection point C.

The average similarity between the collection point P _i (P _i ≠ C) and the adjacent points for:

${\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; S</span>}}}_{{\mathrm{<span\; class="notranslate">\; P</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}}^{{\mathrm{<span\; class="notranslate">\; N</span>}}_{\mathrm{<span\; class="notranslate">\; C</span>}}}<span\; class="notranslate">\; =</span>\frac{{\mathrm{<span\; class="notranslate">\; S</span>}}_{{\mathrm{<span\; class="notranslate">\; P</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}}^{{\mathrm{<span\; class="notranslate">\; N</span>}}_{\mathrm{<span\; class="notranslate">\; C</span>}}}}{{\mathrm{<span\; class="notranslate">\; no</span>}}_{{\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 5</span>}<span\; class="notranslate">\; )</span>$

in is the number of collected points in the neighborhood of P _i (P _i ≠ C), such as

The average similarity of all collection points in N _C except collection point C for:

${\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; S</span>}}}_{{\mathrm{<span\; class="notranslate">\; N</span>}}_{\mathrm{<span\; class="notranslate">\; C</span>}}^{\mathrm{<span\; class="notranslate">\; o</span>}}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; 8</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; 8</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; S</span>}}}_{{\mathrm{<span\; class="notranslate">\; P</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}}^{{\mathrm{<span\; class="notranslate">\; N</span>}}_{\mathrm{<span\; class="notranslate">\; C</span>}}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 6</span>}<span\; class="notranslate">\; )</span>$

The sum of similarities between collection point C and adjacent collection points for:

${\mathrm{<span\; class="notranslate">\; S</span>}}_{\mathrm{<span\; class="notranslate">\; C</span>}}^{{\mathrm{<span\; class="notranslate">\; N</span>}}_{\mathrm{<span\; class="notranslate">\; C</span>}}}<span\; class="notranslate">\; =</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; 8</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}\mathrm{<span\; class="notranslate">\; L</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; C</span>}<span\; class="notranslate">\; ,</span>{\mathrm{<span\; class="notranslate">\; P</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 7</span>}<span\; class="notranslate">\; )</span>$

The average similarity between collection point C and adjacent collection points for:

${\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; S</span>}}}_{\mathrm{<span\; class="notranslate">\; C</span>}}^{{\mathrm{<span\; class="notranslate">\; N</span>}}_{\mathrm{<span\; class="notranslate">\; C</span>}}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; 8</span>}}{\mathrm{<span\; class="notranslate">\; S</span>}}_{\mathrm{<span\; class="notranslate">\; C</span>}}^{{\mathrm{<span\; class="notranslate">\; N</span>}}_{\mathrm{<span\; class="notranslate">\; C</span>}}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 8</span>}<span\; class="notranslate">\; )</span>$

when When , the collection point C is a noise point, otherwise the collection point C is a non-noise point.

In the embodiment of the present invention, optionally, when determining the signal strength of the target collection point according to the signal strength of the at least one collection point in the above step 102, the mean value of the signal strength of the at least one collection point can be used as the target collection point or, filter out noise points from the at least one collection point, and use the mean value of the signal strengths of the remaining collection points as the signal strength of the target collection point.

For example, when the collection point C in Fig. 4b is a noise point, the signal strength of the collection point C is taken as the mean value of the signal strengths of the collection points other than the collection point C in the neighborhood of the collection point C.

Alternatively, the signal strength of the collection point C is taken as the mean value of the signal strengths of the collection points in the neighborhood of the collection point C, among the collection points other than the collection point C, and non-noise points. For example, (1-9) may be used to determine the signal strength of the acquisition point C.

${\mathrm{<span\; class="notranslate">\; R</span>}}_{\mathrm{<span\; class="notranslate">\; N</span>}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; no</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; R</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 9</span>}<span\; class="notranslate">\; )</span>$

Among them, R _N is the signal strength of the updated noise point, R _i is the signal strength of the non-noise point in the neighborhood, and n is the number of collection points of the non-noise point in the neighborhood.

It should be noted that, in the embodiment of the present invention, only a single AP is used as an example for illustration. In practice, when a collection point receives signals from multiple APs at the same time to establish a fingerprint library, the above steps of judging the noise point and replacing the signal strength of the noise point by a single AP are repeated. For the method, the method of traversing each AP and establishing the fingerprint library is sufficient, and will not be described in detail. When using multiple APs to build a fingerprint library, due to the limited signal coverage of APs, when the collection point does not receive a certain AP signal, set the AP signal strength to a value that does not affect the calculation (such as -100dBm) and add to the fingerprint library, so that after traversing all APs, each collection point of the entire fingerprint library contains all AP signal strengths.

The step numbers in the embodiment of the present invention are only for distinguishing different steps, and do not constitute a limitation to the embodiment of the present invention.

The method for establishing the fingerprint library in the embodiment of the present invention, after determining that the target collection point is a noise point according to the signal strength of the target collection point and the signal strength of the collection points adjacent to the target collection point, according to the signal strength of the collection points adjacent to the target collection point Intensity, to determine the signal strength of the target collection point, store the signal strength of the target collection point and the pre-stored location information of the target collection point correspondingly, and establish a fingerprint library. In this way, the number of noise points in the fingerprint database can be reduced by selecting the collection points according to the signal strength to filter out the noise points.

The specific implementation process of the method for establishing the fingerprint library in the embodiment of the present invention will be described in detail below.

Referring to Fig. 5, another method for establishing a fingerprint library provided by an embodiment of the present invention may include:

301. Traverse the pre-stored fingerprint database, and find a set Q of all APs in the pre-stored fingerprint database.

For example, Q={AP ₁ ,AP ₂ ,...,AP _n }.

302. Fill the signal strength of each collection point in the prestored fingerprint database in the form of a set Q.

That is, when the signal strength of the collection point (such as the RSS signal vector) does not include the signal strength of an AP in the set Q, add the received signal strength of the AP to the signal strength of the collection point, if the AP is not received Set the AP signal strength to a value that does not affect the calculation (such as -100dBm).

303. Select each AP in Q as a signal source, traverse all collection points to determine the noise point of each AP, and re-determine the signal strength of the noise point of each AP.

304. Update the signal strength of each collection point in the pre-stored fingerprint database, store correspondingly with the location information (such as coordinates) of each collection point, and establish a new fingerprint database.

Wherein, the location information of each collection point can be stored in the above-mentioned pre-stored fingerprint library.

The above 301-304 are only a brief description, and for the detailed implementation process, please refer to the method for establishing a fingerprint database in other embodiments of the present invention.

The method for establishing a fingerprint library in the embodiment of the present invention can reduce the number of noise points in the fingerprint library by selecting collection points according to signal strength and filtering out noise points.

Please refer to FIG. 6, an embodiment of the present invention provides a device for establishing a fingerprint library, including: a first determination unit 41, a second determination unit 42, and a storage unit 43, wherein:

The first determination unit 41 is configured to determine whether the target collection point is a noise point according to the signal strength of the target collection point and the signal strength of at least one collection point adjacent to the target collection point;

The second determination unit 42 is configured to determine the signal strength of the target collection point according to the signal strength of at least one collection point if the target collection point is a noise point;

The storage unit 43 is used for correspondingly storing the signal strength of the target collection point and the pre-stored location information of the target collection point to establish a fingerprint library.

As shown in Figure 7, in the embodiment of the present invention, optionally, the above device may further include:

The third determining unit 40 is configured to determine the neighborhood of the target collection point according to preset conditions, and the neighborhood is composed of the target collection point and at least one collection point.

As shown in FIG. 8, in this embodiment of the present invention, optionally, the first determining unit 41 may include:

The first determining subunit 411 is configured to determine the first similarity mean value of the target collection point according to the signal strength of the target collection point and the signal strength of at least one collection point;

The second determination subunit 412 is configured to determine a second similarity mean value of at least one collection point according to the signal strength of the target collection point and the signal strength of at least one collection point;

The third determining subunit 413 is configured to compare the first average similarity with the second average similarity, and if the first average similarity is greater than the second average similarity, then the target collection point is a noise point.

In the embodiment of the present invention, optionally, the second determining unit 42 may be specifically configured to use the mean value of the signal strength of at least one collection point as the signal strength of the target collection point;

Alternatively, the second determining unit 42 may be specifically configured to filter out noise points from at least one collection point, and use the mean value of the signal strengths of the remaining collection points as the signal strength of the target collection point.

As shown in FIG. 8 , in this embodiment of the present invention, optionally, the first determining subunit 411 may be specifically configured to, according to the signal strength of the target collection point and the signal strength of at least one collection point, determine the relationship between the target collection point and at least one The similarity of the collection point, using the average value of the similarity between the target collection point and at least one collection point as the first similarity average of the target collection point;

The second determination subunit 412 can be specifically configured to determine the similarity between each collection point of at least one collection point and its respective adjacent collection points according to the signal strength of the target collection point and the signal strength of at least one collection point, and according to each The average value of the similarity between the collection points and respective adjacent collection points is used to determine the second average similarity of at least one collection point.

The device for establishing the fingerprint database in the embodiment of the present invention may be a computer system or other equipment, which is not limited in the embodiment of the present invention. The device for establishing a fingerprint library in the embodiment of the present invention can realize the above-mentioned method embodiment, and the specific functions of each unit in the device for establishing a fingerprint library are only briefly described. For the detailed implementation process, please refer to the corresponding steps of the above-mentioned method embodiment.

The numbering of each unit in the embodiment of the present invention is only for distinguishing different units, and does not constitute a limitation to the embodiment of the present invention.

The device for establishing the fingerprint database in the embodiment of the present invention, after determining that the target collection point is a noise point according to the signal strength of the target collection point and the signal strength of the collection points adjacent to the target collection point, according to the signal strength of the collection points adjacent to the target collection point Intensity, to determine the signal strength of the target collection point, store the signal strength of the target collection point and the pre-stored location information of the target collection point correspondingly, and establish a fingerprint library. In this way, the number of noise points in the fingerprint database can be reduced by selecting the collection points according to the signal strength to filter out the noise points.

The embodiment of the present invention is mainly applied to establishing a fingerprint database, which can reduce the number of noise points in the fingerprint database.

It should be noted that: the device provided by the above-mentioned embodiment is only illustrated by the division of the above-mentioned functional units. In practical applications, the above-mentioned function allocation can be completed by different functional units or modules according to the needs, that is, the internal structure of the device Divided into different functional units or modules to complete all or part of the functions described above. In addition, the device and the method embodiment provided by the above embodiment belong to the same idea, and the specific implementation process thereof is detailed in the method embodiment, and will not be repeated here.

The serial numbers of the above embodiments of the present invention are for description only, and do not represent the advantages and disadvantages of the embodiments.

Those of ordinary skill in the art can understand that all or part of the steps for implementing the above embodiments can be completed by hardware, and can also be completed by instructing related hardware through a program. The program can be stored in a computer-readable storage medium. The above-mentioned The storage medium mentioned may be a read-only memory, a magnetic disk or an optical disk, and the like.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection of the present invention. within range.

Claims (10)

1. A method for establishing a fingerprint database is characterized by comprising the following steps:

determining whether a target acquisition point is a noise point according to the signal intensity of the target acquisition point and the signal intensity of at least one acquisition point adjacent to the target acquisition point;

if the target acquisition point is a noise point, determining the signal intensity of the target acquisition point according to the signal intensity of the at least one acquisition point;

correspondingly storing the signal intensity of the target acquisition point and prestored position information of the target acquisition point, and establishing a fingerprint database;

wherein the determining whether the target acquisition point is a noise point according to the signal strength of the target acquisition point and the signal strength of at least one acquisition point adjacent to the target acquisition point comprises: at least one acquisition point adjacent to the target acquisition point is an acquisition point located in the same neighborhood with the target acquisition point, and the neighborhood determination rule is as follows: target acquisition Point p (i)₁,j₁) Determining a collection of acquisition points U, p (i) according to a certain rule or shape f₁,j₁) And a certain collection point q (i) in U₂,j₂) Correlation; then p (i)₁,j₁) Neighborhood of (2)Is defined as follows:

$\left\{\begin{array}{c}U=f\left(p\right)\\ N_p^o=\left\{N_q\right|\&ForAll;q\&Element;U\}\end{array}\right.---(1-1)$

wherein,is not p (i)₁,j₁) The hollow neighborhood of (a);

when whether the target acquisition point is a noise point is determined according to the signal intensity of the target acquisition point and the signal intensity of the acquisition point adjacent to the target acquisition point, determining a first similarity mean value of the target acquisition point according to the signal intensity of the target acquisition point and the signal intensity of the at least one acquisition point; determining a second similarity mean value of the at least one acquisition point according to the signal intensity of the target acquisition point and the signal intensity of the at least one acquisition point; comparing the first similarity mean value with the second similarity mean value, and if the first similarity mean value is larger than the second similarity mean value, determining that the target acquisition point is a noise point;

determining the similarity of two adjacent acquisition points by using a formula (1-2), wherein L (a, b) in the formula (1-2) represents the similarity of two adjacent acquisition points a and b, and R_aRepresents the RSSI value, R, of the AP at acquisition Point a_bRepresents the RSSI value of the AP at the acquisition point b;

L(a,b)＝-(R_a-R_b)²(1-2)

judging whether the target acquisition point is a noise point, if the 8-neighborhood not containing the acquisition point C isThe 8-neighborhood containing collection point C is N_cAnd then:

N_c＝{P₁,P₂,...,P₈,C}(1-3)

acquisition Point P if it contains in the 8-neighborhood of acquisition Point C_i(P_iNot equal to C) and the sum of the similarity of adjacent acquisition points isThen:

$S_{P_i}^{N_C}=\underset{j\&NotEqual;i}{\overset{U_{P_i}^{N_C}}{\&Sigma;}}L(P_i,P_j),P_j\&Element;U_{P_i}^{N_C}---(1-4)$

wherein,in 8-neighborhood of acquisition Point C, and acquisition Point P_iThe set of adjacent acquisition points, such as acquisition point P1, which is acquisition point P2, acquisition point P4, and acquisition point C; acquisition points adjacent to acquisition point P4 are acquisition point P1, acquisition point P2, acquisition point P6, acquisition point 7, and acquisition point C;

acquisition Point P_i(P_iNot equal to C) mean value of similarity with neighboring pointsComprises the following steps:

${\stackrel{\&OverBar;}{S}}_{P_i}^{N_C}=\frac{S_{P_i}^{N_C}}{n_{p_i}}---(1-5)$

whereinIs P_i(P_iNot equal to C), e.g. number of acquisition points in neighborhood

N_CAverage similarity of all acquisition Point points except acquisition Point CComprises the following steps:

${\stackrel{\&OverBar;}{S}}_{N_C^o}=\frac{1}{8}\underset{i=1}{\overset{8}{\&Sigma;}}{\stackrel{\&OverBar;}{S}}_{P_i}^{N_C}---(1-6)$

sum of similarity of acquisition Point C and neighboring acquisition PointComprises the following steps:

$S_C^{N_C}=\underset{i=1}{\overset{8}{\&Sigma;}}L(C,P_i)---(1-7)$

similarity mean value of acquisition point C and adjacent acquisition pointsComprises the following steps:

${\stackrel{\&OverBar;}{S}}_C^{N_C}=\frac{1}{8}{S}_C^{N_C}---(1-8)$

when in useAnd in time, the acquisition point C is a noise point, otherwise, the acquisition point C is a non-noise point.

2. The method of claim 1, wherein said determining whether a target acquisition point is a noise point based on a signal strength of said target acquisition point and a signal strength of at least one acquisition point neighboring said target acquisition point, further comprises:

and determining the neighborhood of the target acquisition point according to a preset condition, wherein the neighborhood consists of the target acquisition point and the at least one acquisition point.

3. The method of claim 1 or 2, wherein said determining whether a target acquisition point is a noise point based on signal strength of said target acquisition point and signal strength of acquisition points neighboring said target acquisition point comprises:

determining a first similarity mean value of the target acquisition point according to the signal intensity of the target acquisition point and the signal intensity of the at least one acquisition point;

determining a second similarity mean value of the at least one acquisition point according to the signal intensity of the target acquisition point and the signal intensity of the at least one acquisition point;

and comparing the first similarity mean value with a second similarity mean value, and if the first similarity mean value is larger than the second similarity mean value, determining that the target acquisition point is a noise point.

4. The method of claim 1, wherein said determining a signal strength of said target acquisition point from a signal strength of said at least one acquisition point comprises:

taking the mean value of the signal intensity of the at least one acquisition point as the signal intensity of the target acquisition point;

or filtering noise points from the at least one acquisition point, and taking the signal intensity mean value of the rest acquisition points as the signal intensity of the target acquisition point.

5. The method of claim 3, wherein said determining a first mean similarity value for said target acquisition point from said signal strength of said target acquisition point and said signal strength of said at least one acquisition point comprises:

determining the similarity between the target acquisition point and the at least one acquisition point according to the signal intensity of the target acquisition point and the signal intensity of the at least one acquisition point, and taking the average value of the similarity between the target acquisition point and the at least one acquisition point as the first similarity average value of the target acquisition point;

determining a second similarity mean for the at least one acquisition point based on the signal strength of the target acquisition point and the signal strength of the at least one acquisition point comprises:

according to the signal intensity of the target acquisition point and the signal intensity of the at least one acquisition point, determining the similarity of each acquisition point in the at least one acquisition point and respective adjacent acquisition points, and according to the average value of the similarities of each acquisition point and respective adjacent acquisition points, determining the average value of the second similarities of the at least one acquisition point.

6. An apparatus for creating a fingerprint library, comprising:

the first determining unit is used for determining whether a target acquisition point is a noise point according to the signal intensity of the target acquisition point and the signal intensity of at least one acquisition point adjacent to the target acquisition point;

a second determining unit, configured to determine, if the target acquisition point is a noise point, a signal strength of the target acquisition point according to the signal strength of the at least one acquisition point;

the storage unit is used for correspondingly storing the signal intensity of the target acquisition point and prestored position information of the target acquisition point and establishing a fingerprint database;

wherein the first determining unit is configured to: at least one acquisition point adjacent to the target acquisition point is an acquisition point located in the same neighborhood with the target acquisition point, and the neighborhood determination rule is as follows: target acquisition Point p (i)₁,j₁) Determining a collection of acquisition points U, p (i) according to a certain rule or shape f₁,j₁) And a certain collection point q (i) in U₂,j₂) Correlation; then p (i)₁,j₁) Neighborhood of (2)Is defined as follows:

$\left\{\begin{array}{c}U=f\left(p\right)\\ N_p^o=\left\{N_q\right|\&ForAll;q\&Element;U\}\end{array}\right.---(1-1)$

wherein,is not p (i)₁,j₁) The hollow neighborhood of (a);

when whether the target acquisition point is a noise point is determined according to the signal intensity of the target acquisition point and the signal intensity of the acquisition point adjacent to the target acquisition point, determining a first similarity mean value of the target acquisition point according to the signal intensity of the target acquisition point and the signal intensity of the at least one acquisition point; determining a second similarity mean value of the at least one acquisition point according to the signal intensity of the target acquisition point and the signal intensity of the at least one acquisition point; comparing the first similarity mean value with the second similarity mean value, and if the first similarity mean value is larger than the second similarity mean value, determining that the target acquisition point is a noise point;

determining the similarity of two adjacent acquisition points by using (1-2), wherein L (a, b) in (1-2) represents the similarity of two adjacent acquisition points a and b, and R_aRepresents the RSSI value, R, of the AP at acquisition Point a_bRepresents the RSSI value of the AP at the acquisition point b;

L(a,b)＝-(R_a-R_b)²(1-2)

judging whether the target acquisition point is a noise point, if the 8-neighborhood not containing the acquisition point C isThe 8-neighborhood containing collection point C is N_cAnd then:

N_c＝{P₁,P₂,...,P₈,C}(1-3)

acquisition Point P if it contains in the 8-neighborhood of acquisition Point C_i(P_iNot equal to C) and the sum of the similarity of adjacent acquisition points isThen:

$S_{P_i}^{N_C}=\underset{j\&NotEqual;i}{\overset{U_{P_i}^{N_C}}{\&Sigma;}}L(P_i,P_j),P_j\&Element;U_{P_i}^{N_C}---(1-4)$

wherein,in 8-neighborhood of acquisition Point C, and acquisition Point P_iThe set of adjacent acquisition points, such as acquisition point P1, which is acquisition point P2, acquisition point P4, and acquisition point C; acquisition points adjacent to acquisition point P4 are acquisition point P1, acquisition point P2, acquisition point P6, acquisition point 7, and acquisition point C;

acquisition Point P_i(P_iNot equal to C) mean value of similarity with neighboring pointsComprises the following steps:

${\stackrel{\&OverBar;}{S}}_{P_i}^{N_C}=\frac{S_{P_i}^{N_C}}{n_{p_i}}---(1-5)$

whereinIs P_i(P_iNot equal to C), e.g. number of acquisition points in neighborhood

N_CAverage similarity of all acquisition Point points except acquisition Point CComprises the following steps:

${\stackrel{\&OverBar;}{S}}_{N_C^o}=\frac{1}{8}\underset{i=1}{\overset{8}{\&Sigma;}}{\stackrel{\&OverBar;}{S}}_{P_i}^{N_C}---(1-6)$

sum of similarity of acquisition Point C and neighboring acquisition PointComprises the following steps:

$S_C^{N_C}=\underset{i=1}{\overset{8}{\&Sigma;}}L(C,P_i)---(1-7)$

similarity mean value of acquisition point C and adjacent acquisition pointsComprises the following steps:

${\stackrel{\&OverBar;}{S}}_C^{N_C}=\frac{1}{8}{S}_C^{N_C}---(1-8)$

when in useAnd in time, the acquisition point C is a noise point, otherwise, the acquisition point C is a non-noise point.

7. The apparatus of claim 6, further comprising:

and the third determining unit is used for determining a neighborhood of the target acquisition point according to a preset condition, wherein the neighborhood consists of the target acquisition point and the at least one acquisition point.

8. The apparatus according to claim 6 or 7, wherein the first determining unit comprises:

the first determining subunit is configured to determine a first similarity mean value of the target acquisition point according to the signal strength of the target acquisition point and the signal strength of the at least one acquisition point;

a second determining subunit, configured to determine, according to the signal strength of the target acquisition point and the signal strength of the at least one acquisition point, a second similarity mean value of the at least one acquisition point;

and the third determining subunit is configured to compare the first similarity mean with the second similarity mean, and if the first similarity mean is greater than the second similarity mean, the target acquisition point is a noise point.

9. The apparatus according to claim 6, wherein said second determining unit is specifically configured to use a mean value of signal strengths of said at least one acquisition point as the signal strength of said target acquisition point;

or, the second determining unit is specifically configured to filter noise points from the at least one acquisition point, and use a mean value of signal intensities of remaining acquisition points as the signal intensity of the target acquisition point.

10. The apparatus according to claim 8, wherein the first determining subunit is specifically configured to determine, according to the signal strength of the target acquisition point and the signal strength of the at least one acquisition point, a similarity between the target acquisition point and the at least one acquisition point, and use an average value of the similarities between the target acquisition point and the at least one acquisition point as a first similarity average value of the target acquisition point;

the second determining subunit is specifically configured to determine, according to the signal intensity of the target acquisition point and the signal intensity of the at least one acquisition point, a similarity between each acquisition point of the at least one acquisition point and a respective adjacent acquisition point, and determine, according to an average value of the similarities between each acquisition point and the respective adjacent acquisition point, a second similarity average value of the at least one acquisition point.