CN108540926B - Wireless signal fingerprint construction method and device - Google Patents
Wireless signal fingerprint construction method and device Download PDFInfo
- Publication number
- CN108540926B CN108540926B CN201710121339.0A CN201710121339A CN108540926B CN 108540926 B CN108540926 B CN 108540926B CN 201710121339 A CN201710121339 A CN 201710121339A CN 108540926 B CN108540926 B CN 108540926B
- Authority
- CN
- China
- Prior art keywords
- wireless signal
- information
- sample points
- cell
- measurement sample
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
- H04W64/006—Locating users or terminals or network equipment for network management purposes, e.g. mobility management with additional information processing, e.g. for direction or speed determination
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses a method for constructing a wireless signal fingerprint, which comprises the following steps: acquiring at least one wireless signal measurement sample point sampled at a preset reference point, wherein the measurement sample point at least comprises measurement position information, serving cell signal strength information and neighbor cell signal strength information of a serving cell; clustering the measurement sample points according to the measurement position information, the signal intensity information of the serving cell and the signal intensity information of the adjacent cell of the serving cell to form at least one wireless signal cluster; a wireless signal fingerprint corresponding to the wireless signal cluster is generated in units of the wireless signal cluster. The invention also discloses a device for constructing the wireless signal fingerprint.
Description
Technical Field
The present invention relates to wireless signal processing technologies, and in particular, to a method and an apparatus for constructing a wireless signal fingerprint.
Background
Currently, the positioning technology based on wireless signal fingerprint is the key point of the current positioning technology research, because the position information is one of the basic elements of mobile intelligent group sensing and internet of things application, and has a wide range of application scenarios in indoor and outdoor environments, such as personnel navigation in airports, railway stations, large markets, tracking of special valuables, location-based service push, security and intrusion detection and prevention. Compared with the positioning technology based on the distance measurement and the proximity, the positioning technology based on the wireless signal fingerprint has the advantages that no special equipment needs to be added and designed to be realized on the base station side and the mobile terminal side, the cost can be saved, and the positioning precision is higher.
At present, wireless signal fingerprint positioning needs to be performed by constructing a wireless signal fingerprint database in advance, and a common scheme comprises the following steps:
1. storing all wireless signal test data according to a self-defined format;
2. classifying and storing the user-defined stored wireless signal test data according to the service cells;
3. storing the wireless signal test data which are classified and stored according to the service cell according to grids;
4. weighting and averaging the wireless signal test data in each grid into fingerprint data;
5. storing the fingerprint data and generating a wireless signal fingerprint database.
In the above scheme, when a wireless signal fingerprint is constructed, all wireless signal test data are added into the fingerprint library, and many test data are measured for many times in a short time, so that the sample points have strong time correlation and have the characteristics of close time, close position and close measured signal strength. When positioning is performed, the test data with strong time correlation is very close to the vector of the predicted point, and the actual geographic position is very far, so that the position of the predicted point is biased to be close to the points according to the positioning principle of weighted average of the scheme, and the positioning accuracy is further influenced. On the other hand, in the above scheme, all the radio signal measurement data are used as the radio signal fingerprint database, the data size is too large, and even if only the measurement data with the same serving cell is matched and selected as the search space in the positioning process, it is still necessary to calculate distances and sort many times and obtain a large amount of test data, so the accuracy and efficiency of positioning using the above scheme are not high.
Disclosure of Invention
In order to solve the existing technical problem, embodiments of the present invention provide a method and an apparatus for constructing a wireless signal fingerprint.
The technical scheme of the embodiment of the invention is realized as follows:
the embodiment of the invention provides a method for constructing a wireless signal fingerprint, which comprises the following steps:
acquiring at least one wireless signal measurement sample point sampled at a preset reference point, wherein the measurement sample point at least comprises measurement position information, serving cell signal strength information and neighbor cell signal strength information of a serving cell;
clustering the measurement sample points according to the measurement position information, the signal intensity information of the serving cell and the signal intensity information of the adjacent cell of the serving cell to form at least one wireless signal cluster;
a wireless signal fingerprint corresponding to the wireless signal cluster is generated in units of the wireless signal cluster.
In the above method, the clustering the measurement sample points to form at least one wireless signal cluster includes:
respectively comparing the measurement position information of any two measurement sample points, the signal intensity information of a service cell and the signal intensity information of an adjacent cell of the service cell to generate a first comparison result, dividing the two measurement sample points of which the first comparison result meets a first preset condition into a wireless signal cluster, and then measuring the measurement position information of any one of the rest measurement sample points, and respectively comparing the signal intensity information of the serving cell and the signal intensity information of the adjacent cell of the serving cell with the measurement position information of the measurement sample points in the wireless signal cluster, the signal intensity information of the serving cell and the signal intensity information of the adjacent cell of the serving cell to generate a second comparison result, and adding the measurement sample points of which the second comparison result meets a second preset condition into the wireless signal cluster until all the measurement sample points are clustered.
In the above method, the method further comprises:
and comparing the measurement position information, the serving cell signal strength information and the neighbor cell signal strength information of the individual measurement sample points which are not divided into the wireless signal clusters with the measurement position information, the serving cell signal strength information and the neighbor cell signal strength information of the measurement sample points in each wireless signal cluster respectively to generate a third comparison result, and forming the wireless signal clusters by the measurement sample points of which the third comparison result meets a third preset condition individually.
In the above method, the generating a wireless signal fingerprint corresponding to a wireless signal cluster in units of the wireless signal cluster includes:
and respectively averaging the measurement position information, the signal intensity information of the serving cell and the signal intensity information of the adjacent cell of the serving cell of the measurement sample points in the wireless signal cluster, and taking the averaged measurement position information, the signal intensity information of the serving cell and the signal intensity information of the adjacent cell of the serving cell as wireless signal fingerprints.
In the above method, the measurement sample point further includes measurement time information;
correspondingly, the clustering the measurement sample points to form at least one wireless signal cluster includes:
respectively comparing the measurement time information, the measurement position information, the signal intensity information of a service cell and the signal intensity information of a neighboring cell of a service cell of any two measurement sample points to generate a fourth comparison result, dividing the two measurement sample points of which the fourth comparison result meets a fourth preset condition into a wireless signal cluster, respectively comparing the measurement time information, the measurement position information, the signal intensity information of the service cell and the signal intensity information of the neighboring cell of any one of the remaining measurement sample points with the measurement time information, the measurement position information, the signal intensity information of the service cell and the signal intensity information of the neighboring cell of the measurement sample points in the wireless signal cluster to generate a fifth comparison result, and adding the measurement sample point of which the fifth comparison result meets a fifth preset condition into the wireless signal cluster, until clustering is completed for all measurement sample points.
In the above method, after the generating a wireless signal fingerprint corresponding to a wireless signal cluster by taking the wireless signal cluster as a unit, the method further includes:
determining a weight value for the wireless signal fingerprint, and generating a weighted wireless signal fingerprint according to the wireless signal fingerprint and the weight value thereof; the weight value is related to the number of wireless signal sample points in a wireless signal cluster corresponding to the wireless signal fingerprint.
In the above method, the step of correlating the weight value with the number of wireless signal sample points in a wireless signal cluster corresponding to the wireless signal fingerprint includes:
when the weighted values are characterized by f (x) functions, f (x) is not derivable only in a real number set with a measure of zero, and the rest are all derivable, and satisfy:
for any x1< x2 ∈ [0, + ∞), there is f (x1) ≦ f (x 2);
for any x1< x2 ∈ [0, + ∞), there is f '(x1) ≧ f' (x2) ≧ 0;
wherein x represents the number of wireless signal sample points in a wireless signal cluster, x1 and x2 represent the number of wireless signal sample points in two different wireless signal clusters, respectively, and f' (x) represents the derivative of f (x); [0, + ∞) represents a range of 0 or more up to infinity; e denotes belonging.
The embodiment of the invention also provides a device for constructing the wireless signal fingerprint, which comprises the following components:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring at least one wireless signal measurement sample point sampled at a preset reference point, and the measurement sample point at least comprises measurement position information, serving cell signal strength information and neighbor cell signal strength information of a serving cell;
the clustering module is used for clustering the measurement sample points according to the measurement position information of the measurement sample points, the signal intensity information of the serving cell and the signal intensity information of the adjacent cells of the serving cell to form at least one wireless signal cluster;
and the generating module is used for generating the wireless signal fingerprint corresponding to the wireless signal cluster by taking the wireless signal cluster as a unit.
In the above apparatus, the clustering module is specifically configured to:
respectively comparing the measurement position information, the signal intensity information of a service cell and the signal intensity information of a neighboring cell of any two measurement sample points to generate a first comparison result, dividing the two measurement sample points of which the first comparison result meets a first preset condition into a wireless signal cluster, respectively comparing the measurement position information, the signal intensity information of the service cell and the signal intensity information of the neighboring cell of any one of the rest measurement sample points with the measurement position information, the signal intensity information of the service cell and the signal intensity information of the neighboring cell of the service cell in the wireless signal cluster to generate a second comparison result, adding the measurement sample points of which the second comparison result meets a second preset condition into the wireless signal cluster until all the measurement sample points are clustered, wherein, and comparing the measurement position information, the serving cell signal strength information and the neighbor cell signal strength information of the individual measurement sample points which are not divided into the wireless signal clusters with the measurement position information, the serving cell signal strength information and the neighbor cell signal strength information of the measurement sample points in each wireless signal cluster respectively to generate a third comparison result, and forming the wireless signal clusters by the measurement sample points of which the third comparison result meets a third preset condition individually.
In the above apparatus, the generating module is specifically configured to:
and respectively averaging the measurement position information, the signal intensity information of the serving cell and the signal intensity information of the adjacent cell of the serving cell of the measurement sample points in the wireless signal cluster, and taking the averaged measurement position information, the signal intensity information of the serving cell and the signal intensity information of the adjacent cell of the serving cell as wireless signal fingerprints.
In the above apparatus, the apparatus further comprises:
the weight value module is used for determining a weight value for the wireless signal fingerprint and generating a weighted wireless signal fingerprint according to the wireless signal fingerprint and the weight value thereof; the weight value is related to the number of wireless signal sample points in a wireless signal cluster corresponding to the wireless signal fingerprint.
In the above apparatus, the clustering module is further specifically configured to:
when the measurement sample points also contain measurement time information, respectively comparing the measurement time information, the measurement position information, the signal strength information of a service cell and the signal strength information of the adjacent cell of the service cell of any two measurement sample points to generate a fourth comparison result, dividing the two measurement sample points of which the fourth comparison result meets a fourth preset condition into a wireless signal cluster, respectively comparing the measurement time information, the measurement position information, the signal strength information of the service cell and the signal strength information of the adjacent cell of any one of the rest measurement sample points with the measurement time information, the measurement position information, the signal strength information of the service cell and the signal strength information of the adjacent cell of the service cell in the wireless signal cluster to generate a fifth comparison result, and adding the measurement sample point of which the fifth comparison result meets a fifth preset condition into the wireless signal cluster, until clustering is completed for all measurement sample points.
The method and the device for constructing the wireless signal fingerprint provided by the embodiment of the invention are used for acquiring at least one wireless signal measurement sample point sampled at a preset reference point, wherein the measurement sample point at least comprises measurement position information, service cell signal strength information and adjacent cell signal strength information of a service cell; clustering the measurement sample points according to the measurement position information, the signal intensity information of the serving cell and the signal intensity information of the adjacent cell of the serving cell to form at least one wireless signal cluster; generating a wireless signal fingerprint corresponding to a wireless signal cluster by taking the wireless signal cluster as a unit, and giving a weight value to the wireless signal fingerprint; therefore, the influence of time correlation on the positioning precision is reduced, the number of sample points of a wireless signal fingerprint library is reduced under the condition that the positioning precision is not reduced, and the matching efficiency in the positioning process is improved.
Drawings
In the drawings, which are not necessarily drawn to scale, like reference numerals may describe similar components in different views. Like reference numerals having different letter suffixes may represent different examples of similar components. The drawings illustrate generally, by way of example, but not by way of limitation, various embodiments discussed herein.
FIG. 1 is a flowchart illustrating a method for constructing a wireless signal fingerprint according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a method for constructing weighted wireless signal fingerprints according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a flow chart of an actual application of a method for constructing a wireless signal fingerprint with reduced time correlation according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of an actual application flow of a method for constructing a wireless signal fingerprint with reduced data size in a fingerprint database according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a device for constructing a wireless signal fingerprint according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples.
As shown in fig. 1, the method for constructing a wireless signal fingerprint provided in an embodiment of the present invention includes:
step 101: acquiring at least one wireless signal measurement sample point sampled at a preset reference point, wherein the measurement sample point at least comprises measurement position information, serving cell signal strength information and neighbor cell signal strength information of a serving cell;
the signal strength of the wireless signal is weakened along with the increase of the propagation distance in the spatial propagation process, the closer the receiving end equipment is to the signal source, the stronger the signal strength of the signal source is, and the farther the receiving end equipment is from the signal source, the weaker the signal strength of the signal source is. The distance between the receiving end equipment and the signal source can be estimated according to the established wireless signal fingerprint database, and the position of the receiving end equipment can be obtained according to the estimated distance between the receiving end equipment and the plurality of signal sources, wherein the offline database is established according to sample points obtained by measuring the strength of the wireless signals at a plurality of preset positions.
In practical applications, measuring the wireless signal strength requires that related personnel carry a mobile terminal with a wireless communication function to measure signal strength information from different base stations in a target area, specifically, in the target area, some specific geographic positions (generally referred to as reference points) are calibrated, and geographic position coordinate information of each reference point is recorded. On each reference point, the mobile terminal collects the signal intensity from a plurality of nearby base stations within a period of time to generate a one-dimensional vector, and associates the vector with the geographic position coordinates of the reference point to generate a measurement sample point.
Step 102: clustering the measurement sample points according to the measurement position information, the signal intensity information of the serving cell and the signal intensity information of the adjacent cell of the serving cell to form at least one wireless signal cluster;
respectively comparing the measurement position information, the signal intensity information of a service cell and the signal intensity information of a neighboring cell of any two measurement sample points to generate a first comparison result, dividing the two measurement sample points of which the first comparison result meets a first preset condition into a wireless signal cluster, respectively comparing the measurement position information, the signal intensity information of the service cell and the signal intensity information of the neighboring cell of any one of the rest measurement sample points with the measurement position information, the signal intensity information of the service cell and the signal intensity information of the neighboring cell of the service cell in the wireless signal cluster to generate a second comparison result, adding the measurement sample points of which the second comparison result meets a second preset condition into the wireless signal cluster until all the measurement sample points are clustered, wherein, comparing the measurement position information, the serving cell signal strength information and the neighbor cell signal strength information of the individual measurement sample points which are not divided into the wireless signal clusters with the measurement position information, the serving cell signal strength information and the neighbor cell signal strength information of the measurement sample points in each wireless signal cluster respectively to generate a third comparison result, and forming the wireless signal clusters by the measurement sample points of which the third comparison result meets a third preset condition;
in practical applications, the method can be specifically realized by the following embodiments:
when the measurement sample points also contain measurement time information, respectively subtracting or dividing the measurement time information, the measurement position information, the serving cell signal strength information and the neighbor cell signal strength information of any two measurement sample points, dividing two measurement sample points which simultaneously meet the condition that the measurement time difference is less than or equal to a preset time threshold, the measurement position difference is less than or equal to a measurement position threshold, the serving cell signal strength difference is less than or equal to a serving cell signal strength threshold and the neighbor cell signal strength difference or the ratio is less than or equal to a neighbor cell signal strength threshold into a wireless signal cluster, and respectively comparing the measurement time information, the measurement position information, the serving cell signal strength information and the neighbor cell signal strength information of any one of the remaining measurement sample points with the measurement time information of two measurement sample points in the wireless signal cluster, Respectively subtracting or dividing the measurement position information, the signal intensity information of the service cell and the signal intensity information of the adjacent cell of the service cell, adding the measurement sample points which simultaneously satisfy the measurement time difference or the ratio of the two measurement sample points in the wireless signal cluster and are less than or equal to a preset time threshold, the measurement position difference of the two measurement sample points in the wireless signal cluster, the signal intensity difference of the service cell is less than or equal to a measurement position threshold, the signal intensity difference of the service cell is less than or equal to a measurement time threshold and the signal intensity difference of the adjacent cell or the ratio of the two measurement sample points is less than or equal to the signal intensity threshold of the adjacent cell of the service cell into the wireless signal cluster until all the measurement sample points are clustered, wherein the measurement time information, the measurement position information, the signal intensity information of the service cell and the signal intensity information of the adjacent cell of the single measurement sample point which is not divided into the wireless signal cluster are respectively combined, Measuring the difference between the position information, the signal strength information of the service cell and the signal strength information of the adjacent cell of the service cell, and independently forming a wireless signal cluster by using measurement sample points of which the measurement time difference or the ratio is greater than a preset time threshold, or the measurement position difference or the ratio is greater than a measurement position threshold, or the signal strength difference or the ratio of the service cell is greater than a signal strength threshold of the service cell, or the signal strength difference or the ratio of the adjacent cell is greater than a signal strength threshold of the adjacent cell;
in the above embodiment, since the measurement sample point is obtained by performing a plurality of wireless signal strength measurements over a period of time, therefore, the strong time correlation between the measurement sample points can lead to the similarity of the vector characteristics of the predicted points when the distance is calculated by positioning, but the actual geographical position deviation with the prediction point is very large, so that the position of the prediction point is biased to be near the wireless signal sample points with strong time correlation, the positioning accuracy is influenced, therefore, the wireless signal sample points with strong time correlation are clustered to generate a wireless signal cluster, wherein each wireless signal cluster comprises wireless signal sample points with similar time, position and signal strength, the representation bit is divided into one point by means of arithmetic averaging, so that the influence of the wireless signal sample point with strong timeliness on positioning accuracy can be effectively reduced.
Step 103: a wireless signal fingerprint corresponding to the wireless signal cluster is generated in units of the wireless signal cluster.
Respectively averaging measurement position information, serving cell signal strength information and neighbor cell signal strength information of a serving cell of a measurement sample point in a wireless signal cluster, and taking the averaged measurement position information, serving cell signal strength information and neighbor cell signal strength information of the serving cell as wireless signal fingerprints;
in practical application, the wireless signal fingerprint can establish index information according to information such as time, geographic position, signal strength and the like, and the index information is stored to generate a wireless signal fingerprint database, so that the efficiency of matching relevant information in the positioning process can be improved.
The embodiment of the invention also provides a method for constructing the weighted wireless signal fingerprint, which can reduce the number of wireless signal sample points and improve the positioning efficiency on the premise of not influencing the positioning accuracy, and as shown in fig. 2, the method specifically comprises the following steps:
step 201: acquiring at least one wireless signal measurement sample point sampled at a preset reference point, wherein the measurement sample point at least comprises measurement position information, serving cell signal strength information and neighbor cell signal strength information of a serving cell;
step 202: clustering the measurement sample points according to the measurement position information, the signal intensity information of the serving cell and the signal intensity information of the adjacent cell of the serving cell to form at least one wireless signal cluster;
respectively comparing the measurement time information, the measurement position information, the signal intensity information of a service cell and the signal intensity information of a neighboring cell of a service cell of any two measurement sample points to generate a fourth comparison result, dividing the two measurement sample points of which the fourth comparison result meets a fourth preset condition into a wireless signal cluster, respectively comparing the measurement time information, the measurement position information, the signal intensity information of the service cell and the signal intensity information of the neighboring cell of any one of the remaining measurement sample points with the measurement time information, the measurement position information, the signal intensity information of the service cell and the signal intensity information of the neighboring cell of the measurement sample points in the wireless signal cluster to generate a fifth comparison result, and adding the measurement sample point of which the fifth comparison result meets a fifth preset condition into the wireless signal cluster, until all the measurement sample points are clustered;
in practical applications, the method can be specifically realized by the following embodiments:
respectively subtracting or dividing the measurement position information, the service cell signal strength information and the neighbor cell signal strength information of the service cell of any two measurement sample points, dividing the two measurement sample points which simultaneously satisfy the condition that the difference or ratio of the measurement positions is less than or equal to the measurement position threshold, the difference or ratio of the service cell signal strength is less than or equal to the service cell signal strength threshold and the neighbor cell signal strength difference or ratio of the service cell is less than or equal to the neighbor cell signal strength threshold into a wireless signal cluster, respectively subtracting the measurement position information, the service cell signal strength information and the neighbor cell signal strength information of any one measurement sample point in the rest measurement sample points from the measurement position information, the service cell signal strength information and the neighbor cell signal strength information of the service cell of two measurement sample points in the wireless signal cluster, adding the measurement sample points which simultaneously satisfy the measurement position difference or the ratio of the two measurement sample points in the wireless signal cluster and the measurement position difference or the ratio of the two measurement sample points in the wireless signal cluster is less than or equal to the measurement position threshold, the service cell signal strength difference or the ratio of the two measurement sample points in the wireless signal cluster is less than or equal to the service cell signal strength threshold and the adjacent cell signal strength difference or the ratio of the two measurement sample points in the wireless signal cluster is less than or equal to the service cell signal strength threshold to the wireless signal cluster until all the measurement sample points are clustered, wherein the measurement position information, the service cell signal strength information and the adjacent cell signal strength information of the single measurement sample points which are not divided into the wireless signal cluster are respectively differed with the measurement position information, the service cell signal strength information and the adjacent cell signal strength information of the service cell in each wireless signal cluster, and the measurement position difference or the ratio is, Or the measurement sample points of which the signal intensity difference or the ratio of the serving cell is greater than the signal intensity threshold of the serving cell, or the signal intensity difference or the ratio of the adjacent cell is greater than the signal intensity threshold of the adjacent cell form a wireless signal cluster independently.
Step 203: generating a wireless signal fingerprint corresponding to the wireless signal cluster by taking the wireless signal cluster as a unit;
the method comprises the steps of averaging measurement position information of measurement sample points in a wireless signal cluster, serving cell signal strength information and neighbor cell signal strength information of a serving cell respectively, and taking the averaged measurement position information, serving cell signal strength information and neighbor cell signal strength information of the serving cell as wireless signal fingerprints.
Step 204: determining a weight value for the wireless signal fingerprint, and generating a weighted wireless signal fingerprint according to the wireless signal fingerprint and the weight value thereof; the weight value is related to the number of wireless signal sample points in a wireless signal cluster corresponding to the wireless signal fingerprint.
When the weighted values are characterized by f (x) functions, f (x) is not derivable only in a real number set with a measure of zero, and the rest are all derivable, and satisfy:
for any x1< x2 ∈ [0, + ∞), there is f (x1) ≦ f (x 2);
for any x1< x2 ∈ [0, + ∞), there is f '(x1) ≧ f' (x2) ≧ 0;
wherein x represents the number of wireless signal sample points in a wireless signal cluster, x1 and x2 represent the number of wireless signal sample points in two different wireless signal clusters, respectively, and f' (x) represents the derivative of f (x); [0, + ∞) represents a range of 0 or more up to infinity; e denotes belonging. The weight value function represents a monotone non-decreasing function, and the function value increases more and more slowly, or stops increasing after reaching a certain value, for example: (x) x,
a function of this form.
In practical application, wireless signals are influenced by many situations, so that the measured signal strengths are likely to have differences at different times and in the same place, if the signal strengths are measured at different times and in the same place for a plurality of times and are close, the wireless signals of the current geographic position can be determined to be stable, when a similar signal strength signal measurement result appears at a prediction point, the prediction point can be determined to have a higher probability in the vicinity of the test geographic position, when matching and positioning, the distance of one reference point only needs to be calculated, the distance of a certain number of wireless signal sample points of one wireless signal cluster for constructing a wireless fingerprint library can be calculated, then a weight value is given to the wireless signal fingerprints, the data quantity of the wireless signal fingerprint library is reduced, and the efficiency of positioning and matching is improved.
Fig. 3 is a schematic diagram of a practical application flow of the method for reducing the construction of time-dependent wireless signal fingerprints according to the embodiment of the present invention, as shown in fig. 3, the flow includes the following steps:
step 301: clustering according to the characteristics of the wireless signal sample points to obtain a plurality of wireless signal clusters;
each wireless signal sample point in the wireless signal cluster needs to satisfy a time difference < Th1 (which may be set according to actual requirements, for example, 20 seconds), a longitude and latitude difference < Th2 (which may be set according to actual requirements, for example, 20 meters), and a signal strength difference < Th3 (which may be set according to actual requirements, for example, 1.5 decibels (dB)); the time difference, the longitude and latitude difference and the signal intensity difference are set to meet the requirement that the measurement sample points with strong timeliness are divided into a signal cluster as far as possible.
Step 302: carrying out arithmetic averaging on time information, longitude and latitude information, signal strength information and the like of wireless sample points in each cluster to generate a wireless signal fingerprint;
the wireless signal fingerprint represents the characteristics of the wireless signal cluster, such as time information, geographical location information and signal strength information.
Step 303: and storing the wireless signal fingerprint to generate a wireless signal fingerprint library.
Fig. 4 is a schematic diagram of an actual application process of the method for reducing the construction of the wireless signal fingerprint of the fingerprint database data volume according to the embodiment of the present invention, as shown in fig. 4, the process includes the following steps:
step 401: clustering according to the characteristics of the wireless signal sample points to obtain a plurality of wireless signal clusters;
each wireless signal sample point in the wireless signal cluster needs to satisfy a longitude and latitude difference < Th2 (which may be set according to actual requirements, for example, 20 meters) and a signal strength difference < Th3 (which may be set according to actual requirements, for example, 1.5 dB).
Step 402: carrying out arithmetic averaging on longitude and latitude information, signal strength information and the like of wireless sample points in each cluster to generate a wireless signal fingerprint;
the wireless signal fingerprint represents the characteristics of the wireless signal cluster, such as time information, geographical location information, signal strength information, and the like.
Step 403: assigning a weight value to each wireless signal fingerprint;
when the weighted values are characterized by f (x) functions, f (x) is only irreducible in a real number set with a measure of zero, the rest are all derivable, and the following conditions are met:
for any x1< x2 ∈ [0, + ∞), there is f (x1) ≦ f (x 2);
for any x1< x2 ∈ [0, + ∞), there is f '(x1) ≧ f' (x2) ≧ 0;
wherein x represents wirelessThe number of wireless signal sample points of the signal cluster, x1 and x2 respectively represent the number of wireless signal sample points in two different wireless signal clusters, and f' (x) represents the derivative of f (x); [0, + ∞) represents a range of 0 or more up to infinity; e represents belonging; the weight value function represents a monotone non-decreasing function, and the function value increases more and more slowly, or stops increasing after reaching a certain value, for example: (x) x,
a function of this form.
Step 404: and storing the wireless signal fingerprints endowed with the weight values to generate a wireless signal fingerprint library.
Fig. 5 is a schematic structural diagram of a wireless signal fingerprint constructing apparatus according to an embodiment of the present invention, and as shown in fig. 5, the wireless signal fingerprint constructing apparatus according to the embodiment of the present invention includes:
an obtaining module 501, configured to obtain at least one wireless signal measurement sample point sampled at a preset reference point, where the measurement sample point at least includes measurement location information, serving cell signal strength information, and neighboring cell signal strength information of a serving cell;
a clustering module 502, configured to cluster the measurement sample points according to the measurement position information of the measurement sample points, the signal strength information of the serving cell, and the signal strength information of the neighboring cell of the serving cell, so as to form at least one wireless signal cluster;
a generating module 503, configured to generate a wireless signal fingerprint corresponding to a wireless signal cluster by taking the wireless signal cluster as a unit;
the clustering module 502 is specifically configured to:
respectively comparing the measurement position information, the signal intensity information of a service cell and the signal intensity information of a neighboring cell of any two measurement sample points to generate a first comparison result, dividing the two measurement sample points of which the first comparison result meets a first preset condition into a wireless signal cluster, respectively comparing the measurement position information, the signal intensity information of the service cell and the signal intensity information of the neighboring cell of any one of the rest measurement sample points with the measurement position information, the signal intensity information of the service cell and the signal intensity information of the neighboring cell of the service cell in the wireless signal cluster to generate a second comparison result, adding the measurement sample points of which the second comparison result meets a second preset condition into the wireless signal cluster until all the measurement sample points are clustered, wherein, and comparing the measurement position information, the serving cell signal strength information and the neighbor cell signal strength information of the individual measurement sample points which are not divided into the wireless signal clusters with the measurement position information, the serving cell signal strength information and the neighbor cell signal strength information of the measurement sample points in each wireless signal cluster respectively to generate a third comparison result, and forming the wireless signal clusters by the measurement sample points of which the third comparison result meets a third preset condition individually.
The generating module 503 is specifically configured to:
and respectively averaging the measurement position information, the signal intensity information of the serving cell and the signal intensity information of the adjacent cell of the serving cell of the measurement sample points in the wireless signal cluster, and taking the averaged measurement position information, the signal intensity information of the serving cell and the signal intensity information of the adjacent cell of the serving cell as wireless signal fingerprints.
The wireless signal fingerprint constructing device of the embodiment of the invention further comprises:
a weight value module 504, configured to determine a weight value for the wireless signal fingerprint, and generate a weighted wireless signal fingerprint according to the wireless signal fingerprint and the weight value thereof; the weight value is related to the number of wireless signal sample points in a wireless signal cluster corresponding to the wireless signal fingerprint.
In the above apparatus, the clustering module 502 is further specifically configured to:
when the measurement sample points also contain measurement time information, respectively comparing the measurement time information, the measurement position information, the signal strength information of a service cell and the signal strength information of the adjacent cell of the service cell of any two measurement sample points to generate a fourth comparison result, dividing the two measurement sample points of which the fourth comparison result meets a fourth preset condition into a wireless signal cluster, respectively comparing the measurement time information, the measurement position information, the signal strength information of the service cell and the signal strength information of the adjacent cell of any one of the rest measurement sample points with the measurement time information, the measurement position information, the signal strength information of the service cell and the signal strength information of the adjacent cell of the service cell in the wireless signal cluster to generate a fifth comparison result, and adding the measurement sample point of which the fifth comparison result meets a fifth preset condition into the wireless signal cluster, until clustering is completed for all measurement sample points.
It should be noted that the specific implementation functions of the obtaining module 501, the clustering module 502, the generating module 503, and the weight value module 504 can be understood according to the related descriptions of the wireless signal fingerprint construction method described in fig. 1 and fig. 2, and are not described herein again.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention.
Claims (8)
1. A method for constructing a fingerprint of a wireless signal, the method comprising:
acquiring at least one wireless signal measurement sample point sampled at a preset reference point, wherein the measurement sample point at least comprises measurement position information, serving cell signal strength information and neighbor cell signal strength information of a serving cell;
clustering the measurement sample points according to the measurement position information, the signal intensity information of the serving cell and the signal intensity information of the adjacent cell of the serving cell to form at least one wireless signal cluster;
generating a wireless signal fingerprint corresponding to the wireless signal cluster by taking the wireless signal cluster as a unit;
the generating a wireless signal fingerprint corresponding to a wireless signal cluster by taking the wireless signal cluster as a unit comprises the following steps:
respectively averaging the measurement position information, the signal intensity information of a serving cell and the signal intensity information of the adjacent cell of the serving cell of a measurement sample point in a wireless signal cluster, and taking the averaged measurement position information, the signal intensity information of the serving cell and the signal intensity information of the adjacent cell of the serving cell as wireless signal fingerprints;
after generating the wireless signal fingerprint corresponding to the wireless signal cluster by taking the wireless signal cluster as a unit, the method further comprises the following steps:
determining a weight value for the wireless signal fingerprint, and generating a weighted wireless signal fingerprint according to the wireless signal fingerprint and the weight value thereof; the weight value is related to the number of wireless signal sample points in a wireless signal cluster corresponding to the wireless signal fingerprint.
2. The method of claim 1, wherein clustering measurement sample points to form at least one wireless signal cluster comprises:
respectively comparing the measurement position information of any two measurement sample points, the signal intensity information of a service cell and the signal intensity information of an adjacent cell of the service cell to generate a first comparison result, dividing the two measurement sample points of which the first comparison result meets a first preset condition into a wireless signal cluster, and then measuring the measurement position information of any one of the rest measurement sample points, and respectively comparing the signal intensity information of the serving cell and the signal intensity information of the adjacent cell of the serving cell with the measurement position information of the measurement sample points in the wireless signal cluster, the signal intensity information of the serving cell and the signal intensity information of the adjacent cell of the serving cell to generate a second comparison result, and adding the measurement sample points of which the second comparison result meets a second preset condition into the wireless signal cluster until all the measurement sample points are clustered.
3. The method of claim 2, further comprising:
and comparing the measurement position information, the serving cell signal strength information and the neighbor cell signal strength information of the individual measurement sample points which are not divided into the wireless signal clusters with the measurement position information, the serving cell signal strength information and the neighbor cell signal strength information of the measurement sample points in each wireless signal cluster respectively to generate a third comparison result, and forming the wireless signal clusters by the measurement sample points of which the third comparison result meets a third preset condition individually.
4. The method of claim 1, wherein the measurement sample points further include measurement time information;
correspondingly, the clustering the measurement sample points to form at least one wireless signal cluster includes:
respectively comparing the measurement time information, the measurement position information, the signal intensity information of a service cell and the signal intensity information of a neighboring cell of a service cell of any two measurement sample points to generate a fourth comparison result, dividing the two measurement sample points of which the fourth comparison result meets a fourth preset condition into a wireless signal cluster, respectively comparing the measurement time information, the measurement position information, the signal intensity information of the service cell and the signal intensity information of the neighboring cell of any one of the remaining measurement sample points with the measurement time information, the measurement position information, the signal intensity information of the service cell and the signal intensity information of the neighboring cell of the measurement sample points in the wireless signal cluster to generate a fifth comparison result, and adding the measurement sample point of which the fifth comparison result meets a fifth preset condition into the wireless signal cluster, until clustering is completed for all measurement sample points.
5. The method of claim 1, wherein the weighting value is related to a number of wireless signal sample points in a wireless signal cluster corresponding to a wireless signal fingerprint, and comprises:
when the weighted values are characterized by f (x) functions, f (x) is not derivable only in a real number set with a measure of zero, and the rest are all derivable, and satisfy:
for any x1< x2 ∈ [0, + ∞), there is f (x1) ≦ f (x 2);
for any x1< x2 ∈ [0, + ∞), there is f '(x1) ≧ f' (x2) ≧ 0;
wherein x represents the number of wireless signal sample points in a wireless signal cluster, x1 and x2 represent the number of wireless signal sample points in two different wireless signal clusters, respectively, and f' (x) represents the derivative of f (x); [0, + ∞) represents a range of 0 or more up to infinity; e denotes belonging.
6. An apparatus for constructing a fingerprint of a wireless signal, the apparatus comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring at least one wireless signal measurement sample point sampled at a preset reference point, and the measurement sample point at least comprises measurement position information, serving cell signal strength information and neighbor cell signal strength information of a serving cell;
the clustering module is used for clustering the measurement sample points according to the measurement position information of the measurement sample points, the signal intensity information of the serving cell and the signal intensity information of the adjacent cells of the serving cell to form at least one wireless signal cluster;
the generating module is used for generating wireless signal fingerprints corresponding to the wireless signal clusters by taking the wireless signal clusters as units;
the generation module is specifically configured to:
respectively averaging the measurement position information, the signal intensity information of a serving cell and the signal intensity information of the adjacent cell of the serving cell of a measurement sample point in a wireless signal cluster, and taking the averaged measurement position information, the signal intensity information of the serving cell and the signal intensity information of the adjacent cell of the serving cell as wireless signal fingerprints;
the weight value module is used for determining a weight value for the wireless signal fingerprint and generating a weighted wireless signal fingerprint according to the wireless signal fingerprint and the weight value thereof; the weight value is related to the number of wireless signal sample points in a wireless signal cluster corresponding to the wireless signal fingerprint.
7. The apparatus of claim 6, wherein the clustering module is specifically configured to:
respectively comparing the measurement position information, the signal intensity information of a service cell and the signal intensity information of a neighboring cell of any two measurement sample points to generate a first comparison result, dividing the two measurement sample points of which the first comparison result meets a first preset condition into a wireless signal cluster, respectively comparing the measurement position information, the signal intensity information of the service cell and the signal intensity information of the neighboring cell of any one of the rest measurement sample points with the measurement position information, the signal intensity information of the service cell and the signal intensity information of the neighboring cell of the service cell in the wireless signal cluster to generate a second comparison result, adding the measurement sample points of which the second comparison result meets a second preset condition into the wireless signal cluster until all the measurement sample points are clustered, wherein, and comparing the measurement position information, the serving cell signal strength information and the neighbor cell signal strength information of the individual measurement sample points which are not divided into the wireless signal clusters with the measurement position information, the serving cell signal strength information and the neighbor cell signal strength information of the measurement sample points in each wireless signal cluster respectively to generate a third comparison result, and forming the wireless signal clusters by the measurement sample points of which the third comparison result meets a third preset condition individually.
8. The apparatus of claim 6, wherein the clustering module is further specifically configured to:
when the measurement sample points also contain measurement time information, respectively comparing the measurement time information, the measurement position information, the signal strength information of a service cell and the signal strength information of the adjacent cell of the service cell of any two measurement sample points to generate a fourth comparison result, dividing the two measurement sample points of which the fourth comparison result meets a fourth preset condition into a wireless signal cluster, respectively comparing the measurement time information, the measurement position information, the signal strength information of the service cell and the signal strength information of the adjacent cell of any one of the rest measurement sample points with the measurement time information, the measurement position information, the signal strength information of the service cell and the signal strength information of the adjacent cell of the service cell in the wireless signal cluster to generate a fifth comparison result, and adding the measurement sample point of which the fifth comparison result meets a fifth preset condition into the wireless signal cluster, until clustering is completed for all measurement sample points.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710121339.0A CN108540926B (en) | 2017-03-02 | 2017-03-02 | Wireless signal fingerprint construction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710121339.0A CN108540926B (en) | 2017-03-02 | 2017-03-02 | Wireless signal fingerprint construction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108540926A CN108540926A (en) | 2018-09-14 |
| CN108540926B true CN108540926B (en) | 2021-01-15 |
Family
ID=63489303
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710121339.0A Active CN108540926B (en) | 2017-03-02 | 2017-03-02 | Wireless signal fingerprint construction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108540926B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110045371A (en) * | 2019-04-28 | 2019-07-23 | 软通智慧科技有限公司 | A kind of identification method, device, equipment and storage medium |
| CN115119210A (en) * | 2021-03-19 | 2022-09-27 | 华为技术有限公司 | Method for determining whether electronic equipment needs to be re-authenticated or not and electronic equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101547506A (en) * | 2009-02-17 | 2009-09-30 | 华中科技大学 | GSM network consumer positioning method based on signal receiving strength information fingerprint |
| CN102480784A (en) * | 2010-11-24 | 2012-05-30 | 中国移动通信集团公司 | Method and system for evaluating fingerprint positioning error |
| CN102480677A (en) * | 2010-11-24 | 2012-05-30 | 中国移动通信集团公司 | Determination method of fingerprint positioning error and device thereof |
| CN103987118A (en) * | 2014-05-19 | 2014-08-13 | 浙江师范大学 | Access point k-means clustering method based on received signal strength signal ZCA whitening |
| CN105120433A (en) * | 2015-08-19 | 2015-12-02 | 上海交通大学 | WLAN indoor positioning method based on continuous sampling and fuzzy clustering |
| CN105223546A (en) * | 2015-09-30 | 2016-01-06 | 西安电子科技大学 | Based on the indoor orientation method of received signal strength and reference point locations double focusing class |
| CN105704652A (en) * | 2016-02-16 | 2016-06-22 | 中国科学院光电研究院 | Method for building and optimizing fingerprint database in WLAN/Bluetooth positioning processes |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8933841B2 (en) * | 2010-12-13 | 2015-01-13 | The Governing Council Of The University Of Toronto | System and method for localization |
-
2017
- 2017-03-02 CN CN201710121339.0A patent/CN108540926B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101547506A (en) * | 2009-02-17 | 2009-09-30 | 华中科技大学 | GSM network consumer positioning method based on signal receiving strength information fingerprint |
| CN102480784A (en) * | 2010-11-24 | 2012-05-30 | 中国移动通信集团公司 | Method and system for evaluating fingerprint positioning error |
| CN102480677A (en) * | 2010-11-24 | 2012-05-30 | 中国移动通信集团公司 | Determination method of fingerprint positioning error and device thereof |
| CN103987118A (en) * | 2014-05-19 | 2014-08-13 | 浙江师范大学 | Access point k-means clustering method based on received signal strength signal ZCA whitening |
| CN105120433A (en) * | 2015-08-19 | 2015-12-02 | 上海交通大学 | WLAN indoor positioning method based on continuous sampling and fuzzy clustering |
| CN105223546A (en) * | 2015-09-30 | 2016-01-06 | 西安电子科技大学 | Based on the indoor orientation method of received signal strength and reference point locations double focusing class |
| CN105704652A (en) * | 2016-02-16 | 2016-06-22 | 中国科学院光电研究院 | Method for building and optimizing fingerprint database in WLAN/Bluetooth positioning processes |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108540926A (en) | 2018-09-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lee et al. | Random forest and WiFi fingerprint-based indoor location recognition system using smart watch | |
| Liu et al. | Improving positioning accuracy using GPS pseudorange measurements for cooperative vehicular localization | |
| Pei et al. | Using inquiry-based Bluetooth RSSI probability distributions for indoor positioning | |
| CN106793082B (en) | Mobile equipment positioning method in WLAN/Bluetooth heterogeneous network environment | |
| Xue et al. | A new weighted algorithm based on the uneven spatial resolution of RSSI for indoor localization | |
| CN112218330B (en) | Positioning method and communication device | |
| US11419088B2 (en) | Radiation source positioning method based on radio spectrum monitoring big data processing | |
| CN104038901A (en) | Indoor positioning method for reducing fingerprint data acquisition workload | |
| Ning et al. | Outdoor location estimation using received signal strength-based fingerprinting | |
| CN104540221A (en) | WLAN indoor positioning method based on semi-supervised SDE algorithm | |
| Zhang et al. | Weighted adaptive KNN algorithm with historical information fusion for fingerprint positioning | |
| CN114374449A (en) | Interference source determination method, device, equipment and medium | |
| CN102625444A (en) | Terminal positioning method and base station | |
| CN108574927B (en) | Mobile terminal positioning method and device | |
| CN108540926B (en) | Wireless signal fingerprint construction method and device | |
| Li et al. | Outdoor location estimation using received signal strength feedback | |
| Ma et al. | Subway station real-time indoor positioning system for cell phones | |
| Rodrigues et al. | Extracting 3D maps from crowdsourced GNSS skyview data | |
| Ji et al. | Accurate Long‐Term Evolution/Wi‐Fi hybrid positioning technology for emergency rescue | |
| CN114758364B (en) | Industrial Internet of things scene fusion positioning method and system based on deep learning | |
| CN111356072A (en) | Position estimation method and device for indoor positioning and readable storage medium | |
| Li et al. | A novel fingerprinting method of WiFi indoor positioning based on Weibull signal model | |
| CN109842847B (en) | Method for distinguishing indoor user terminal from outdoor user terminal and base station | |
| Huijiao et al. | Location Algorithm for WSNs with Mobile Anchor Node Based on Optimzed K-Nearest Neighbers | |
| Pan et al. | Application of a WiFi/Geomagnetic Combined Positioning Method in a Single Access Point Environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |