CN109525337A - WiFi fingerprint acquisition methods, device, storage medium and equipment - Google Patents
WiFi fingerprint acquisition methods, device, storage medium and equipment Download PDFInfo
- Publication number
- CN109525337A CN109525337A CN201710853034.9A CN201710853034A CN109525337A CN 109525337 A CN109525337 A CN 109525337A CN 201710853034 A CN201710853034 A CN 201710853034A CN 109525337 A CN109525337 A CN 109525337A
- Authority
- CN
- China
- Prior art keywords
- wifi
- signal strength
- fingerprint
- mark
- wifi fingerprint
- 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.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/309—Measuring or estimating channel quality parameters
- H04B17/318—Received signal strength
-
- 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)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Collating Specific Patterns (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention discloses a kind of WiFi fingerprint acquisition methods, device, storage medium and equipment, belong to indoor positioning technologies field.The described method includes: being identified for each Wireless Fidelity WiFi arrived in a sector scanning, obtains the WiFi in preset duration and identify at least one corresponding signal strength;When the signal strength obeys non-Unimodal Distribution, the signal strength is clustered, until cluster obtains obeying at least two signal strength sets of Unimodal Distribution;The WiFi, which is obtained, according to each signal strength set identifies corresponding Target Signal Strength;Corresponding Target Signal Strength is identified according to each WiFi mark and each described WiFi, generates the WiFi fingerprint in the region.Signal strength level of the present invention due to the WiFi fingerprint that gets due to more can accurately embody a region greatly improves indoor position accuracy on the basis of providing more and more fully reference information for subsequent WiFi fingerprint matching process.
Description
Technical field
The present invention relates to indoor positioning technologies field, in particular to a kind of WiFi fingerprint acquisition methods, device, storage medium
And equipment.
Background technique
As the number of access point of indoor arrangement gradually increases, it is based on WiFi (Wireless Fidelity, Wireless Fidelity)
Fingerprint, which carries out indoor positioning, becomes an important channel for solving the problems, such as indoor positioning at present.Wherein, WiFi fingerprint is by working as
A series of WiFi mark and corresponding signal strength that front position is scanned are constituted, and WiFi mark generally refers to access point
MAC (Media Access Control, medium access control) address.And why can realize that interior is fixed by WiFi fingerprint
Position is the WiFi mark that different location so indoors is got because radio wave has attenuation characteristic in spatial
And signal strength is just different, i.e. WiFi fingerprint can one region of unique identification, therefore at present using WiFi fingerprint come complete
At indoor positioning.
The interior space is usually first divided into several regions, successively obtained later by the relevant technologies when obtaining WiFi fingerprint
The WiFi fingerprint in each region is taken, each of one of WiFi fingerprint WiFi mark is corresponding with a signal strength.
Further, since signal strength has time variation, even if for example adopting for a WiFi mark in same position different time
The signal strength collected also not immobilizes, therefore for the region that each is marked off, determines and arrive in current region scanning
Each WiFi when identifying corresponding signal strength, usually using collected signal strength in a period of time average value or
Median indicates signal strength level.That is, it is usually to collect in a period of time that a WiFi, which identifies corresponding signal strength,
Signal strength average value or median.
In the implementation of the present invention, inventor find the relevant technologies the prior art has at least the following problems:
The access point that above embodiment only meets signal strength data the WiFi mark instruction of Unimodal Distribution is applicable in,
However in practical applications, the signal strength data of an access point may obey bimodal or multi-modal, so foundation
There may be the signal strength level that cannot accurately embody a region to lack for the WiFi fingerprint that above embodiment is got
It falls into, and indoor position accuracy will lead to based on such WiFi fingerprint progress indoor positioning and substantially reduce.
Summary of the invention
The embodiment of the invention provides a kind of WiFi fingerprint acquisition methods, device, storage medium and equipment, can solve
In the related technology since there may be the defects for the signal strength level that cannot accurately embody a region for WiFi fingerprint, in turn
The problem that indoor positioning causes indoor position accuracy low is carried out based on such WiFi fingerprint.The technical solution is as follows:
In a first aspect, providing a kind of WiFi fingerprint acquisition methods, which comprises
For each WiFi mark arrived in a sector scanning, it is corresponding to obtain the WiFi mark in preset duration
At least one signal strength;
When the signal strength obeys non-Unimodal Distribution, the signal strength is clustered, until cluster is taken
From at least two signal strength sets of Unimodal Distribution;
The WiFi, which is obtained, according to each signal strength set identifies corresponding Target Signal Strength;
Corresponding Target Signal Strength is identified according to each WiFi mark and each described WiFi, generates the region
WiFi fingerprint.
Second aspect, provides a kind of WiFi fingerprint acquisition device, and described device includes:
First obtains module, for identifying for each WiFi arrived in a sector scanning, obtains in preset duration
The WiFi identifies at least one corresponding signal strength;
Cluster module, for the signal strength being clustered, directly when the signal strength obeys non-Unimodal Distribution
Obtain obeying at least two signal strength sets of Unimodal Distribution to cluster;
Second obtains module, strong for obtaining the corresponding echo signal of the WiFi mark according to each signal strength set
Degree;
Generation module is strong for identifying corresponding echo signal according to each WiFi mark and each described WiFi
Degree, generates the WiFi fingerprint in the region.
In another embodiment, second module is obtained, be also used to when the signal strength obeys Unimodal Distribution, by institute
The average value or median for stating signal strength are as the corresponding Target Signal Strength of WiFi mark.
In another embodiment, the cluster module is also used to calculate the standard deviation of the signal strength;When the mark
When quasi- difference is greater than first threshold, determine that the signal strength obeys non-Unimodal Distribution.
In another embodiment, the device further include:
Screening module is used for for each described signal strength set, based on the standard deviation of the signal strength set, in institute
It states signal strength concentration and filters out abnormal data;
Second obtains module, for for the signal strength set after each screening, the signal after obtaining the screening to be strong
Degree concentrates the average value of signal strength, identifies corresponding Target Signal Strength for the average value as the WiFi;Or, for
Signal strength set after each screening, the signal strength after obtaining the screening concentrate the median of signal strength, will be described
Median is as the corresponding Target Signal Strength of the signal strength set.
In another embodiment, the device further include:
Comparison module, it is for each WiFi fingerprint for obtaining, the WiFi fingerprint is neighbouring at least one
WiFi fingerprint is compared, and the neighbouring WiFi fingerprint is the second area that distance is less than second threshold between first area
Fingerprint, the first area is corresponding with the WiFi fingerprint, and the second area is corresponding with the neighbouring WiFi fingerprint;
Described second obtains module, is also used to not occur in the WiFi fingerprint when a WiFi mark, and described
When at least one appearance ratio in WiFi fingerprint is greater than third threshold value, it is described at least one in WiFi fingerprint,
It obtains the WiFi and identifies at least one corresponding Target Signal Strength;
First computing module, for calculating described in the WiFi fingerprint according at least one described signal strength
WiFi identifies corresponding Target Signal Strength.
In another embodiment, first computing module, for obtaining at least one described Target Signal Strength
The weighted value of each Target Signal Strength;Based on the weighted value of each Target Signal Strength, to it is described at least one
Target Signal Strength is weighted operation of averaging, and marks obtained operation result as the WiFi described in the WiFi fingerprint
The Target Signal Strength of knowledge;Wherein, the second area of a neighbouring WiFi fingerprint is closer with the distance between first area,
The weighted value of corresponding Target Signal Strength is bigger.
In another embodiment, the device further include:
Processing module, for being identified for any two WiFi arrived in the sector scanning, when described two WiFi are marked
It is sensible like when, WiFi described two in the preset duration are identified into corresponding at least one signal strength and are merged;
Described second obtains module, and being also used to will be in described two WiFi mark when generating the WiFi fingerprint in the region
Any one WiFi identify and delete, and it is strong according to the signal strength after merging to obtain the corresponding echo signal of residue WiFi mark
Degree.
In another embodiment, described two WiFi marks include that the first WiFi mark and the 2nd WiFi are identified, described
Device further include:
Second computing module, for when similar between the first WiFi mark and the coding of the 2nd WiFi mark
When degree is greater than four threshold values, calculates the first WiFi in the preset duration and identify at least one corresponding signal strength and institute
It states the 2nd WiFi and identifies similarity between at least one corresponding signal strength;When obtained similarity is greater than the 5th threshold value
When, determine that described two WiFi marks are similar.
In another embodiment, described two WiFi marks include that the first WiFi mark and the 2nd WiFi are identified, described
Device further include:
Third obtains module, for when similar between the first WiFi mark and the coding of the 2nd WiFi mark
When degree is greater than four threshold values, obtains the first WiFi in each region and identify at least one corresponding signal strength and institute
It states the 2nd WiFi and identifies at least one corresponding signal strength;
Third computing module, for calculating the first WiFi in each region, to identify at least one corresponding signal strong
Degree identifies the similarity between at least one corresponding signal strength with the 2nd WiFi;When obtained similarity is greater than the 6th
When threshold value, determine that described two WiFi marks are similar.
The third aspect provides a kind of computer readable storage medium, at least one finger is stored in the storage medium
Enable, at least a Duan Chengxu, code set or instruction set, at least one instruction, an at least Duan Chengxu, the code set or
Instruction set is loaded as the processor and is executed to realize WiFi fingerprint acquisition methods described in first aspect.
Fourth aspect provides a kind of equipment obtained for WiFi fingerprint, and the equipment includes processor and memory,
It is stored at least one instruction, at least a Duan Chengxu, code set or instruction set in the memory, at least one instruction,
An at least Duan Chengxu, the code set or instruction set are loaded as the processor and are executed to realize described in first aspect
WiFi fingerprint acquisition methods.
Technical solution provided in an embodiment of the present invention has the benefit that
It, can be to its signal strength in preset duration for each WiFi mark arrived in a sector scanning
The analysis of data distribution feature is carried out, the judgement of Unimodal Distribution is realized through the cluster to signal strength and whether obey, it is complete
Its pairs of data structure reasonably adjusts, and then obtains obeying the signal strength set of Unimodal Distribution, and the embodiment of the present invention is also later
The WiFi can be obtained according to each signal strength set and identifies corresponding Target Signal Strength, generating the region to realize
Each WiFi mark and the signal strength of corresponding multiple signal strength sets are saved when WiFi fingerprint, the embodiment of the present invention is got
Signal strength level of the WiFi fingerprint due to more can accurately embody a region, for subsequent WiFi fingerprint matching
Process provides more and more fully on the basis of reference information, greatly improves indoor position accuracy.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is the method flow diagram that a kind of WiFi fingerprint provided in an embodiment of the present invention obtains;
Fig. 2 is the flow diagram provided in an embodiment of the present invention for carrying out the analysis of signal strength data characteristic distributions;
Fig. 3 is the method flow diagram that a kind of WiFi fingerprint provided in an embodiment of the present invention obtains;
Fig. 4 is the flow diagram that a kind of pair of WiFi fingerprint provided in an embodiment of the present invention carries out interpolation filling;
Fig. 5 is the flow diagram that a kind of pair of WiFi fingerprint provided in an embodiment of the present invention carries out interpolation filling;
Fig. 6 is a kind of flow diagram of similar WiFi processing provided in an embodiment of the present invention;
Fig. 7 is that a kind of judgement WiFi provided in an embodiment of the present invention identifies similar flow diagram;
Fig. 8 is that a kind of judgement WiFi provided in an embodiment of the present invention identifies similar flow diagram;
Fig. 9 is that a kind of judgement WiFi provided in an embodiment of the present invention identifies similar flow diagram;
Figure 10 is a kind of structural schematic diagram of WiFi fingerprint acquisition device provided in an embodiment of the present invention;
Figure 11 is a kind of structural schematic diagram of equipment obtained for WiFi fingerprint provided in an embodiment of the present invention.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached drawing to embodiment party of the present invention
Formula is described in further detail.
Before to the embodiment of the present invention carrying out that explanation is explained in detail, first the embodiment of the present invention may relate to one
A little nouns explain.
WiFi fingerprint: due to having when the electromagnetic wave for the access point transmitting being laid out indoors is propagated in space with distance
The characteristic for increasing and gradually decaying, so WiFi mark and signal strength that different location indoors is got are also different
Sample.Therefore, it theoretically can use a series of WiFi mark scanned and corresponding signal strength come unique identification room
An interior region, i.e., so-called fingerprint.
Signal strength (RSSI, Received Signal Strength Indication): it refers to and is located at the interior space
The intensity for the WiFi signal that terminal receives.Wherein, the unit of signal strength is unlike dBm (decibel milliwatt) and dB,
DBm indicates power absolute value, and calculation formula is 10lg (performance number/1mw).
Indoor positioning: the location solution suitable for indoor scene.That is, satellite positioning ought be available environment indoors
When, use indoor positioning technologies as the auxiliary positioning of satellite positioning, solution satellite-signal is weaker when reaching ground, cannot penetrate
The problem of building.In short, indoor positioning refers to progress position positioning in environment indoors, to realize personnel, object etc.
The monitoring position in space indoors.
And indoor positioning is carried out in order to realize based on WiFi fingerprint, it also needs to construct fingerprint database in advance.Wherein, fingerprint
Database is stored in server end, and which stores the interior space (such as a building or a parking lot) interior each regions
Corresponding relationship between location information and WiFi fingerprint.
By taking a building as an example, carry out fingerprint database building when, can the building Xian Jiang the interior space carry out it is multiple
The division in region;The scanning that WiFi mark is carried out in each region come and corresponding letter are being marked off using detection terminal later
The acquisition of number intensity, and by detection terminal by the location information of each region, WiFi scan is identified and corresponding letter
Number intensity is uploaded to server, and then the corresponding pass between the location information of each region and WiFi fingerprint is saved by server
System forms fingerprint database to get indoor wireless signal map is arrived.
Wherein, above-mentioned detection terminal can be any type of electrical equipment with WiFi function, and above-mentioned location information can wrap
Longitude information, latitude information, floor information etc. are included, the embodiment of the present invention is to this without specifically limiting.
In this way, terminal to be positioned can identify a series of WiFi scanned in current location indoors in position fixing process
And corresponding signal strength is uploaded to server, and server passes through the WiFi fingerprint that will be received and fingerprint database carries out
Similarity compares, and where the current location that can determine terminal to be positioned, this process can be referred to as WiFi fingerprint matching again
Process.
As shown in the above, a complete and accurate fingerprint database can be constructed, is had for indoor positioning non-
Often important influence.Based on this, the embodiment of the present invention proposes a kind of acquisition that the quality of data in fingerprint database can be improved
WiFi fingerprint mode greatly improves indoor position accuracy to realize.Wherein, this WiFi fingerprint acquisition modes are applied to service
Device, i.e., in embodiments of the present invention, terminal can be merely responsible for carrying out the acquisition of initial data and collected data are uploaded to clothes
Business device, and specifically the processing of data is all completed by server.Certainly, other than aforesaid way, terminal and server tool
Body is responsible for the part of processing there may also be other forms, such as terminal also processing of the achievable part to data, and the present invention is real
Example is applied to this without specifically limiting.The embodiment of the present invention is only only acquired data with terminal and is illustrated.
In summary, WiFi fingerprint acquisition modes provided in an embodiment of the present invention can solve the problems, such as following several classes:
(a), signal strength has the problem of otherness with time variation and terminal perceptual signal intensity.
Wherein, signal strength with time variation and terminal perceptual signal intensity have otherness be because are as follows: for one
For access point, even if the collected signal strength of the different time that is in the same localities also not immobilizes, signal strength
It may the left and right random fluctuation centered on some value, it is also possible to which there are two or more central values.That is signal strength sheet
Body has time variation, so terminal may also be different in the signal strength of the collected same access point of different time, it is poor to have
It is anisotropic.
(b), the abnormal data in the signal strength got is cleaned.
(c), shortage of data problem caused by the randomness of terminal perception access point.
Wherein, it is limited to the influence for the factors such as switch-in point transmitting power is unstable, terminal perceives access point, and there are randomnesss.
For example, current region is the signal range coverage of access point A, but since the transmission power of access point A is unstable, it is located at current
The terminal in region may not be found the access point in WiFi mark scanning process, in this way in the WiFi for generating current region
This WiFi mark and corresponding signal strength will be lacked when fingerprint.
(d) redundancy WiFi is identified and is handled.Wherein, redundancy WiFi generally refers to letter in embodiments of the present invention
Number distribution and WiFi mark all have the access point of similitude.
It is illustrated in more detail about each part mentioned above and also refers to following embodiments.
Fig. 1 is a kind of flow chart of WiFi fingerprint acquisition methods provided in an embodiment of the present invention.The WiFi fingerprint acquisition side
Method is applied to server, and referring to Fig. 1, method flow provided in an embodiment of the present invention includes:
101, each WiFi arrived in a sector scanning is identified, obtains the WiFi in preset duration and identifies extremely
A few signal strength.
Wherein, the above-mentioned region referred to, which is referred to, carries out any one area obtained after region division to an interior space
Domain.Wherein, for these mark off the region come, the corresponding WiFi fingerprint in a region.Assuming that by an Interior Space
Between be divided into 10 regions, then each of 10 regions region all has a WiFi fingerprint.In addition, each is marked off
The area size come both can be identical or cannot be different, and the embodiment of the present invention is to this without specifically limiting.Such as it can be according to 5m*
The division in 5m size progress region.
In embodiments of the present invention, for each region, when generating WiFi fingerprint, why scanning can be obtained
Each WiFi arrived identifies the signal strength intersection in preset duration, is because signal strength has time variation and terminal
Perceptual signal intensity has otherness, and the embodiment of the present invention is by counting the signal strength of each WiFi mark whithin a period of time
And respective handling is carried out to solve both of these problems.
Wherein, the size of preset duration can be 5 minutes or 10 minutes etc., size of the embodiment of the present invention to preset duration
Without specifically limiting.
It 102, will at least one when at least one signal strength that the WiFi is identified in preset duration obeys non-Unimodal Distribution
A signal strength is clustered, until cluster obtains obeying at least two signal strength sets of Unimodal Distribution.
In embodiments of the present invention, for WiFi mark, get in preset duration it is collected at least
After one signal strength, the characteristic distributions of at least one signal strength are judged first, i.e., first calculate the signal in preset duration
The standard deviation of intensity judges whether at least one signal strength obeys Unimodal Distribution with this.When obtained standard deviation is less than
When one threshold value, show that most of signal strength in the signal strength in preset duration is smaller with difference between average value, determines
At least one signal strength obeys Unimodal Distribution.When obtained standard deviation is greater than first threshold, show the letter in preset duration
Most of signal strength in number intensity determines that at least one signal strength obeys non-unimodal point with differing greatly between average value
Cloth.
Wherein, Unimodal Distribution refers to numerical value left and right centered on a central value and changes, non-Unimodal Distribution refer to numerical value with
Left and right changes centered on two or more central values.And the size of first threshold rule of thumb or can pass through many experiments
It obtains, for example value can be 5%, the embodiment of the present invention is to this without specifically limiting.
In an illustrative embodiment, when calculating the standard deviation of at least one signal strength, it can apply following
Formula is realized:
Standard deviation
Wherein, N is the signal strength number for including at least one signal strength, and u refers to being averaged for N number of signal strength
Value, xiRefer to any of N number of signal strength.
It, can be according to following if at least one signal strength obeys Unimodal Distribution in the embodiment of an exemplary
Two ways identifies corresponding signal strength to calculate the WiFi.
Above-mentioned average value u is identified corresponding signal strength by mode one.
Mode two, using the median in above-mentioned N number of signal strength as generate WiFi fingerprint when the WiFi mark it is corresponding
Signal strength.
Wherein, median refers to that for being arranged in order and occuping middle position in one group of signal strength together.I.e.
In this group of signal strength, there is a half data bigger than median, has a half data smaller than median.
In an illustrative embodiment, if at least one signal strength obeys non-Unimodal Distribution, also need to extremely
A few signal strength is clustered.Wherein, such as K-means algorithm realization can be taken when being clustered, the present invention is implemented
Example is to this without specifically limiting.In a wheel cluster calculating process, the lesser cluster operation of categorical measure, such as class can be carried out
The value of other quantity is 2, and the embodiment of the present invention is to this equally without specifically limiting.And it is carried out at least one signal strength
After one wheel cluster obtains multiple signal strength sets, the embodiment of the present invention can also carry out following places to obtained multiple signal strength sets
Reason.
For each of multiple signal strength sets signal strength set, if the signal strength set obeys non-Unimodal Distribution,
Then continue to cluster the signal strength set, until each obtained signal strength set obeys Unimodal Distribution.That is, this hair
The objective of bright embodiment is that each signal strength set finally obtained obeys Unimodal Distribution, thus obtain by it is above-mentioned at least
After multiple signal strength sets that one signal strength clusters out, it also will continue to judge whether each signal strength set obeys
Unimodal Distribution.
If there is signal strength set obeys non-Unimodal Distribution, then continue in the manner described above to the signal strength set into
Row cluster;And then whether secondary judgement obeys Unimodal Distribution by multiple signal strength sets that the signal strength clustering comes out, such as
Fruit obeys Unimodal Distribution, then no longer clusters.If also disobeying the signal strength set of non-Unimodal Distribution, continue to execute
The process judged again after cluster is stated, each signal strength set finally made obeys Unimodal Distribution.
It should be noted that no matter be also in embodiments of the present invention non-first run cluster for first run cluster, it will be by poly-
The data set that class obtains is referred to as signal strength set.
103, the WiFi is obtained according to each signal strength set and identifies corresponding Target Signal Strength, according to each
WiFi mark and each WiFi identify corresponding Target Signal Strength, generate the WiFi fingerprint in the region.
Wherein, it which is obtained according to each signal strength set identifies corresponding Target Signal Strength and be meant that, by
In being non-Unimodal Distribution, therefore calculate the corresponding signal strength of each signal strength set for obeying Unimodal Distribution, these signals
The corresponding signal strength of strength set constitutes above-mentioned Target Signal Strength.It is similar with being described above, for each signal strength
For collection, when calculating the corresponding signal strength of the signal strength set, and obtains the signal strength and concentrate the multiple letters for including
The mean value or median of number intensity.
In another embodiment, corresponding target letter is identified in addition to saving each WiFi mark and each WiFi
Outside number intensity, the standard deviation of each signal strength set can also be saved, the signal for including is concentrated with clearly each signal strength
The difference of intensity and mean value, the embodiment of the present invention is to this without specifically limiting.
In conclusion the embodiment of the present invention 101 has adjusted to step 103 and collects in preset duration through the above steps
Signal strength data structure, analyzed more completely characteristic distributions of signal strength, solving signal strength has
Time variation and terminal perceptual signal intensity have the problem of otherness, mention for the subsequent WiFi fingerprint matching in position fixing process
More fully reference information has been supplied, and then has improved the precision of indoor positioning.Referring to fig. 2, above-mentioned steps 101 are to step 103
The content can summary and induction be following process flows:
(a), a WiFi is obtained in the same region identify the signal strength in one section of duration.
(b), the standard deviation of signal strength is calculated, to judge the characteristic distributions of signal strength.
If the standard deviation (c), obtained is less than first threshold, signal strength is clustered.
(d), the standard deviation for each signal strength set that cluster obtains is calculated.
If (e), the standard deviation of a signal strength set is less than first threshold, repeats cluster and judgment criteria is poor
The step of size, until each obtained signal strength set obeys Unimodal Distribution.
(f), retain the corresponding signal strength of each signal strength set and standard deviation.
In another embodiment, in order to improve the quality of data in fingerprint database, in subsequent position fixing process
More accurately reference information, the embodiment of the present invention obtain multiple signal strength sets in above-mentioned steps 103 for WiFi fingerprint matching offer
It later, further include to each and before calculating the corresponding signal strength of each signal strength set according to above-mentioned steps 103
The step of abnormal data that signal strength is concentrated is cleaned.In other words, as shown in figure 3, above-mentioned steps 103 can also be following
Step 104, step 105 and step 106 are replaced.
104, for each signal strength set, the signal strength of the standard deviation based on signal strength set concentration is filtered out
Abnormal data.
In embodiments of the present invention, for a signal strength set, abnormal data generally refer to signal strength indication with
Difference between mean value is more than the data of [- 3 σ, 3 σ].Certainly, the boundary value in difference section can also be other than -3 σ and 3 σ
Other numerical value, the embodiment of the present invention is to this without specifically limiting.
In addition, for each obey Unimodal Distribution signal strength set for, due to these abnormal datas belong to from
Group's point, therefore remove it, to ensure the accuracy of the corresponding signal strength of subsequent each signal strength set of calculating.
105, for the signal strength set after each screening, the signal strength after obtaining the screening concentrates signal strength
Average value or median identify corresponding Target Signal Strength using the average value or median as the WiFi.
Wherein, the number of the number for the average value for including in Target Signal Strength or the number of median and signal strength set
Unanimously.
106, corresponding Target Signal Strength is identified according to each WiFi mark and each WiFi, generates the region
WiFi fingerprint.
In another embodiment, as it was noted above, being limited to the influence for the factors such as switch-in point transmitting power is unstable, eventually
End perception access point is there are randomness, and the embodiment of the present invention is in order to solve to perceive caused by the randomness of access point due to terminal
Shortage of data problem additionally provides the process flow that following pairs of missing datas carry out interpolation filling referring to fig. 4:
401, for each obtained WiFi fingerprint, by the WiFi fingerprint and at least one compare adjacent to WiFi fingerprint
It is right.
Wherein, each WiFi fingerprint obtained above is stored in the fingerprint database of server.Of the invention real
It applies in example, is characterized with the region that first area identifies the WiFi fingerprint, with second area to neighbouring WiFi fingerprint institute
The region of mark is characterized.
First point for needing to illustrate be, it is well known that its adjacent domain may extend over its periphery for a region, i.e.,
The adjacent domain in one region may be present multiple, and the only one-to-one a region of a WiFi fingerprint is identified, therefore one
The neighbouring WiFi fingerprint of WiFi fingerprint is also typically present multiple.
The second point for needing to illustrate is, the embodiment of the present invention is at least one region corresponding to the WiFi fingerprint with
It is referred to as in two regions.In embodiments of the present invention, if a distance between region and first area is less than second threshold,
The region is just a second area, and the WiFi fingerprint in the region is just the neighbouring WiFi of the WiFi fingerprint of above-mentioned pending comparison
Fingerprint.
Wherein, it is contemplated that the factors such as signal transmission distance of access point, generally the value size of second threshold between
5m is between 10m.Certainly, the value of second threshold can be also other numerical value, and the embodiment of the present invention is to this without specifically limiting.
For the step, due to being only to compare a certain WiFi to identify whether to lack, only need include by the WiFi fingerprint
WiFi mark identify and be compared with the WiFi that neighbouring WiFi fingerprint includes.
402, do not occur in the WiFi fingerprint when a WiFi is identified, and at least one going out in WiFi fingerprint
When existing ratio is greater than third threshold value, at least one in WiFi fingerprint, obtains the WiFi and identify at least one corresponding mesh
Mark signal strength.
Wherein, the size of third threshold value can be 70% or 80% etc., and the embodiment of the present invention is to this without specifically limiting.
Assuming that neighbouring WiFi fingerprint one shares 4, and there is WiFi mark A in this four neighbouring WiFi fingerprints, but at this
Do not occur WiFi mark A in WiFi fingerprint, since appearance ratio of the WiFi mark A in above-mentioned 4 neighbouring WiFi fingerprints is
100%, it is thus determined that WiFi mark A is the missing data of the WiFi fingerprint, need to also be obtained in above-mentioned 4 neighbouring WiFi fingerprints
WiFi identifies corresponding 4 Target Signal Strengths of A.
403, according at least one Target Signal Strength, it is strong to calculate the echo signal that the WiFi is identified in the WiFi fingerprint
Degree.
In embodiments of the present invention, interpolation algorithm is generallyd use to estimate the WiFi lacked in the WiFi fingerprint
The Target Signal Strength of mark.Wherein, the basic thought of interpolation algorithm are as follows: certain of several discrete points in known spatial
Under conditions of the observation of one attribute, the attribute value at any point on estimation space.That is, interpolation algorithm think attribute it
Between have spatial coherence, similar things can be more like.And the signal strength of access point has spatial coherence, therefore
Target Signal Strength is estimated using interpolation algorithm.
When specifically carrying out anti-distance difference operation, the embodiment of the present invention can obtain at least one Target Signal Strength first
In each Target Signal Strength weighted value;Later, based on the weighted value of each Target Signal Strength come at least one
Target Signal Strength is weighted operation of averaging, so using obtained operation result as in the WiFi fingerprint WiFi mark
Know corresponding Target Signal Strength.
Wherein, anti-distance is meant that the size of each weighted value depends on the inverse of distance or square of inverse.That is, one
The second area of a neighbouring WiFi fingerprint is closer with the distance between above-mentioned first area, the weight of corresponding letter target intensity
It is worth bigger.
Later, which is identified and is filled in the WiFi fingerprint with obtained Target Signal Strength interpolation.
In conclusion above-mentioned steps 401 solve terminal sense by carrying out difference filling for missing data to step 403
Know that access point has randomness, provides more fully for the WiFi fingerprint matching in subsequent position fixing process with reference to letter
Breath, improves the precision of indoor positioning.As shown in figure 5, above-mentioned steps 401 to the content described in step 403 can summary and induction
For following process flows:
(a), obtain WiFi fingerprint is compared with neighbouring WiFi fingerprint.
(b), judge that the WiFi fingerprint identifies deletion condition with the presence or absence of WiFi according to comparison result.
If (c), the WiFi fingerprint lacks certain WiFi marks, interpolation filling is carried out.
In another embodiment, for some access points of space layout indoors, be substantially possible to for
Emit the signal generator of a variety of WiFi signals, i.e. an access point corresponds to multiple WiFi marks.And each WiFi mark
Signal intensity profile has apparent similitude.For example, being adopted for each region that can scan these WiFi mark
The signal strength of each WiFi mark collected may be all very much like.In this way when generating WiFi fingerprint, if by these WiFi
Mark and corresponding signal strength are saved and just cause data redundancy, because only passing through above-mentioned multiple similar WiFi marks
WiFi mark in knowledge can achieve the goal.Based on this, the embodiment of the present invention, which also proposed, identifies similar WiFi
And the step of handling.
For continuing the process flow shown in Fig. 1, referring to Fig. 6, the process flow to similar WiFi includes:
601, any two WiFi arrived in a sector scanning is identified, it, will be pre- when two WiFi marks are similar
If two WiFi identify at least one corresponding signal strength and merge in duration.
602, any one WiFi in two WiFi marks is identified when generating the WiFi fingerprint in the region and is deleted, and root
Residue WiFi, which is obtained, according to the signal strength after merging identifies corresponding Target Signal Strength.
If judging, two WiFi marks are similar, then it is subsequent when generating the WiFi fingerprint in the region, it can be in the region
By a deletion in the two at least one WiFi mark scanned.For example original scanning altogether is identified to 5 WiFi, and
Include the two similar WiFi marks in this 5 WiFi marks, then delete one in the two similar WiFi marks,
So that the sector scanning to WiFi mark quantity reduce to 4.
Later, above-mentioned scheme shown in FIG. 1 can be taken strong based on the signal in collected this 4 WiFi mark in the region
It spends to generate the WiFi fingerprint in the region.Wherein, that WiFi of residue identifies corresponding signal in two similar WiFi marks
Intensity, may be from acquired original to the two WiFi identify the merging of at least one corresponding signal strength.That is, if this
Two WiFi mark be it is similar, then the two WiFi can be identified at least one corresponding signal strength and merged, and base
Signal strength after merging participates in the generation of the WiFi fingerprint in the region.
It should be noted that the embodiment of the present invention can be taken shown in Fig. 7 and Fig. 8 when identifying to similar WiFi
Two ways is realized.Wherein, mode shown in Fig. 7 is by taking the same area as an example, and mode is by taking different zones as an example shown in Fig. 8.With two
WiFi mark is respectively the first WiFi mark with for the 2nd WiFi mark, referring to Fig. 7, carries out identification process to similar WiFi
Include:
701, it when the similarity between the first WiFi mark and the coding of the 2nd WiFi mark is greater than four threshold values, calculates
At least one corresponding signal strength of first WiFi mark at least one signal corresponding with the 2nd WiFi mark in preset duration
Similarity between intensity.
Wherein, the size of the 4th threshold value can be 90% or 95% equal numerical value, and the embodiment of the present invention is to this without specifically limiting
It is fixed.The similarity encoded between two WiFi marks is greater than the 4th threshold value, shows to encode between the two WiFi mark similar.It is false
If WiFi is identified as MAC Address, then encoding similar may include but be not limited to following two kinds of situations:
One kind is the two MAC Address sequential encodings.For example, the two only last difference, and last coding
Sequence is connected.For example, last position of a MAC Address is 4, last position of another MAC Address is 5.
Another kind is that the coding of the two MAC Address is close.For example, the two only last difference, and last
Coded sequence is close.For example, last position of a MAC Address is 4, last position of another MAC Address is 7 or 2.
In embodiments of the present invention, calculate the first WiFi in preset duration identify corresponding at least one signal strength with
It, can be by judging in two signal strength intersections when 2nd WiFi identifies the similarity between at least one corresponding signal strength
The ratio of similar signal strength is realized.Such as it can be by the quantity of similar signal strength in a signal strength intersection and the signal
Ratio in intensity intersection between signal strength total quantity is as above-mentioned similarity.Wherein, strong for this kind of situation similarity signal
The meaning of degree can be referred in two signal strength intersections, for corresponding in collected two WiFi mark of the same moment
Signal strength, if the threshold value that the difference between the two signal strengths is set less than one, the two signal strengths are phase
Likelihood signal intensity.
702, when obtained similarity is greater than five threshold values, determine that two WiFi marks are similar.
Wherein, the size of the 5th threshold value can be 80% or 90% equal numerical value, and the embodiment of the present invention is to this without specifically limiting
It is fixed.After recognizing similar WiFi, the similar WiFi recognized can also be recorded.For example server can pass through a table
To record the similar WiFi of whole recognized.
In another embodiment, referring to Fig. 8, carrying out identification process to similar WiFi may also include that
801, it when the similarity between the first WiFi mark and the coding of the 2nd WiFi mark is greater than four threshold values, obtains
In each region the first WiFi identify corresponding at least one signal strength and the 2nd WiFi mark it is corresponding at least one
Signal strength.
Wherein, it is similar with above-mentioned steps 701 to encode similar judgment step, details are not described herein again.
Come 10 regions assuming that marking off, then herein for WiFi mark for, obtain marking off respectively
Collected signal strength on 10 regions.
802, it calculates the first WiFi in each region and identifies at least one corresponding signal strength and the 2nd WiFi mark
Similarity between at least one corresponding signal strength.
For this kind of situation, the meaning of similar signal strength be can be referred in two signal strength intersections, for same
A collected two WiFi in region identify corresponding signal strength, if the difference between the two signal strengths is less than one
The threshold value of setting, then it is assumed that the two signal strengths are similar signal strength.
803, when obtained similarity is greater than six threshold values, determine that two WiFi marks are similar.
Wherein, the size of the 6th threshold value both can it is identical as the 5th threshold value can also be different, the embodiment of the present invention to this not into
Row is specific to be limited.
In conclusion either for mode shown in mode or Fig. 8 shown in above-mentioned Fig. 7, the identification for similar WiFi
With processing can summary and induction be two aspect, on the one hand be analyze WiFi mark coding characteristic, on the other hand be analysis letter
The similitude of number intensity.That is, referring to Fig. 9, the process of above-mentioned identification and the similar WiFi of processing can summary and induction be following processes:
(a), 1 and WiFi mark 2 is identified for WiFi, first determines whether the coding of the two is similar.
If (b), coding is similar, the calculating of similarity is carried out according to the signal strength intersection of the two WiFi mark.
If (c), similarity is greater than the threshold value of a setting, the two WiFi mark is similar.
It should be noted that completing the generation of WiFi fingerprint by foregoing description, and then realize the structure of fingerprint database
After building, when access point, which occurs, for the interior space updates, for example part access point or the removal of part access point etc., this hair are newly increased
Bright embodiment is also supported to carry out the update of WiFi fingerprint in the way of above-mentioned acquisition WiFi fingerprint, to realize fingerprint database
Data update.
Method provided in an embodiment of the present invention can be right for each WiFi mark arrived in a sector scanning
Its signal strength in preset duration carries out the analysis of data distribution feature, realizes through the cluster to signal strength and is
The no judgement for obeying Unimodal Distribution, completion reasonably adjust its data structure, and then the signal for obtaining obeying Unimodal Distribution is strong
Degree collection, it is strong also to obtain the corresponding echo signal of WiFi mark according to each signal strength set for the embodiment of the present invention later
Degree saves each WiFi mark and the signal of corresponding multiple signal strength sets when generating the WiFi fingerprint in the region to realize
Intensity, signal strength level of the WiFi fingerprint that the embodiment of the present invention is got due to more can accurately embody a region, because
This greatly improves room on the basis of providing more and more fully reference information for subsequent WiFi fingerprint matching process
Interior positioning accuracy.
In addition, the embodiment of the present invention can also clean abnormal data when generating WiFi fingerprint, it is ensured that referring to
The quality of data in line database provides more accurately reference information for the subsequent WiFi fingerprint matching in position fixing process,
Further improve the precision of indoor positioning.
In addition, the embodiment of the present invention in a WiFi fingerprint exist missing WiFi mark in the case where, can also automatically into
Row interpolation filling, also ensures that the quality of data in fingerprint database, provides more precisely for subsequent WiFi fingerprint matching
Reference information, also achieved the purpose that promoted indoor position accuracy.
In addition, the embodiment of the present invention also supports the removing of redundant data to remove repeated characteristic when generating WiFi fingerprint,
It not only reduces operand and has saved memory space, while also can ensure that the quality of data in fingerprint database, be similarly
Subsequent WiFi fingerprint matching provides more accurately reference information, has also achieved the purpose that promote indoor position accuracy.
Figure 10 is a kind of structural schematic diagram of WiFi fingerprint acquisition device provided in an embodiment of the present invention.It, should referring to Figure 10
Device includes:
First obtains module 1001, for identifying for each WiFi arrived in a sector scanning, when obtaining default
The WiFi identifies at least one corresponding signal strength in long;
Cluster module 1002, for when the signal strength obeys non-Unimodal Distribution, the signal strength to be gathered
Class, until cluster obtains obeying at least two signal strength sets of Unimodal Distribution;
Second obtains module 1003, identifies corresponding target letter for obtaining the WiFi according to each signal strength set
Number intensity;
Generation module 1004, for identifying corresponding echo signal according to each WiFi mark and each described WiFi
Intensity generates the WiFi fingerprint in the region.
In another embodiment, second module 1003 is obtained, is also used to when the signal strength obeys Unimodal Distribution,
Corresponding Target Signal Strength is identified using the average value of the signal strength or median as the WiFi.
In another embodiment, cluster module is also used to calculate the standard deviation of the signal strength;When the standard deviation
When greater than first threshold, determine that the signal strength obeys non-Unimodal Distribution.
In another embodiment, the device further include:
Screening module is used for for each described signal strength set, based on the standard deviation of the signal strength set, in institute
It states signal strength concentration and filters out abnormal data;
Second obtains module, for the signal strength set for the signal strength set after each screening, after obtaining screening
The average value is identified corresponding Target Signal Strength by the average value of middle signal strength;Or, for each
Signal strength set after a screening, the signal strength after obtaining the screening concentrates the median of signal strength, by the middle position
Number is as the corresponding Target Signal Strength of the signal strength set.
In another embodiment, the device further include:
Comparison module, it is for each WiFi fingerprint for obtaining, the WiFi fingerprint is neighbouring at least one
WiFi fingerprint is compared, and the neighbouring WiFi fingerprint is the second area that distance is less than second threshold between first area
Fingerprint, the first area is corresponding with the WiFi fingerprint, and the second area is corresponding with the neighbouring WiFi fingerprint;
Second obtains module, is also used to not occur in the WiFi fingerprint when WiFi mark, and it is described at least
When appearance ratio in one neighbouring WiFi fingerprint is greater than third threshold value, it is described at least one in WiFi fingerprint, obtain
The WiFi identifies at least one corresponding Target Signal Strength;
First computing module, for calculating described in the WiFi fingerprint according at least one described signal strength
WiFi identifies corresponding Target Signal Strength.
In another embodiment, the first computing module, it is each at least one described Target Signal Strength for obtaining
The weighted value of a Target Signal Strength;Based on the weighted value of each Target Signal Strength, at least one described target
Signal strength is weighted operation of averaging, and obtained operation result is identified as the WiFi described in the WiFi fingerprint
Target Signal Strength;Wherein, the second area of a neighbouring WiFi fingerprint is closer with the distance between first area, corresponding
Target Signal Strength weighted value it is bigger.
In another embodiment, the device further include:
Processing module, for being identified for any two WiFi arrived in the sector scanning, when described two WiFi are marked
It is sensible like when, WiFi described two in the preset duration are identified into corresponding at least one signal strength and are merged;
Described second obtains module, and being also used to will be in described two WiFi mark when generating the WiFi fingerprint in the region
Any one WiFi identify and delete, and it is strong according to the signal strength after merging to obtain the corresponding echo signal of residue WiFi mark
Degree.
In another embodiment, described two WiFi marks include that the first WiFi mark and the 2nd WiFi are identified, described
Device further include:
Second computing module, for when similar between the first WiFi mark and the coding of the 2nd WiFi mark
When degree is greater than four threshold values, calculates the first WiFi in the preset duration and identify at least one corresponding signal strength and institute
It states the 2nd WiFi and identifies similarity between at least one corresponding signal strength;When obtained similarity is greater than the 5th threshold value
When, determine that described two WiFi marks are similar.
In another embodiment, described two WiFi marks include that the first WiFi mark and the 2nd WiFi are identified, described
Device further include:
Third obtains module, for when similar between the first WiFi mark and the coding of the 2nd WiFi mark
When degree is greater than four threshold values, obtains the first WiFi in each region and identify at least one corresponding signal strength and institute
It states the 2nd WiFi and identifies at least one corresponding signal strength;
Third computing module, for calculating the first WiFi in each region, to identify at least one corresponding signal strong
Degree identifies the similarity between at least one corresponding signal strength with the 2nd WiFi;When obtained similarity is greater than the 6th
When threshold value, determine that described two WiFi marks are similar.
Device provided in an embodiment of the present invention can be right for each WiFi mark arrived in a sector scanning
Its signal strength in preset duration carries out the analysis of data distribution feature, realizes through the cluster to signal strength and is
The no judgement for obeying Unimodal Distribution, completion reasonably adjust its data structure, and then the signal for obtaining obeying Unimodal Distribution is strong
Degree collection, it is strong also to obtain the corresponding echo signal of WiFi mark according to each signal strength set for the embodiment of the present invention later
Degree saves each WiFi mark and the signal of corresponding multiple signal strength sets when generating the WiFi fingerprint in the region to realize
Intensity, signal strength level of the WiFi fingerprint that the embodiment of the present invention is got due to more can accurately embody a region, because
This greatly improves room on the basis of providing more and more fully reference information for subsequent WiFi fingerprint matching process
Interior positioning accuracy.
In addition, the embodiment of the present invention can also clean abnormal data when generating WiFi fingerprint, it is ensured that referring to
The quality of data in line database provides more accurately reference information for the subsequent WiFi fingerprint matching in position fixing process,
Further improve the precision of indoor positioning.
In addition, the embodiment of the present invention in a WiFi fingerprint exist missing WiFi mark in the case where, can also automatically into
Row interpolation filling, also ensures that the quality of data in fingerprint database, provides more precisely for subsequent WiFi fingerprint matching
Reference information, also achieved the purpose that promoted indoor position accuracy.
In addition, the embodiment of the present invention also supports the removing of redundant data to remove repeated characteristic when generating WiFi fingerprint,
It not only reduces operand and has saved memory space, while also can ensure that the quality of data in fingerprint database, be similarly
Subsequent WiFi fingerprint matching provides more accurately reference information, has also achieved the purpose that promote indoor position accuracy.
It should be understood that WiFi fingerprint acquisition device provided by the above embodiment is when obtaining WiFi fingerprint, only more than
The division progress of each functional module is stated for example, can according to need and in practical application by above-mentioned function distribution by difference
Functional module complete, i.e., the internal structure of device is divided into different functional modules, with complete it is described above whole or
Person's partial function.In addition, WiFi fingerprint acquisition device provided by the above embodiment belongs to WiFi fingerprint acquisition methods embodiment
Same design, specific implementation process are detailed in embodiment of the method, and which is not described herein again.
Figure 11 is a kind of server shown according to an exemplary embodiment, which can be used for implementing any of the above-described
WiFi fingerprint acquisition methods shown in exemplary embodiment.Specifically: referring to Figure 11, which can be because of configuration or property
Energy is different and generates bigger difference, may include one or more central processing units (Central Processing
Unit, CPU) 1122 (for example, one or more processors) and memory 1132, one or more storages apply journey
The storage medium 1130 (such as one or more mass memory units) of sequence 1142 or data 1144.Wherein, memory
1132 and storage medium 1130 can be of short duration storage or persistent storage.The program for being stored in storage medium 1130 may include one
A or more than one module (diagram does not mark).
Server 1100 can also include one or more power supplys 1128, one or more wired or wireless nets
Network interface 1150, one or more input/output interfaces 1158, and/or, one or more operating systems 1141, example
Such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM etc..It is deposited in the memory 1132
Contain at least one instruction, at least a Duan Chengxu, code set or instruction set, at least one instruction, an at least Duan Cheng
Sequence, the code set or instruction set are loaded as processor and are executed to realize WiFi fingerprint acquisition side described in above-described embodiment
Method.
Those of ordinary skill in the art will appreciate that realizing that all or part of the steps of above-described embodiment can pass through hardware
It completes, relevant hardware can also be instructed to complete by program, the program can store in a kind of computer-readable
In storage medium, storage medium mentioned above can be read-only memory, disk or CD etc..
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (12)
1. a kind of WiFi fingerprint acquisition methods, which is characterized in that the described method includes:
For each Wireless Fidelity WiFi mark arrived in a sector scanning, the WiFi mark pair in preset duration is obtained
At least one signal strength answered;
When the signal strength obeys non-Unimodal Distribution, the signal strength is clustered, until cluster obtains obeying list
At least two signal strength sets of peak distribution;
The WiFi, which is obtained, according to each signal strength set identifies corresponding Target Signal Strength;
Corresponding Target Signal Strength is identified according to each WiFi mark and each described WiFi, generates the region
WiFi fingerprint.
2. the method according to claim 1, wherein the signal for obtaining the WiFi mark in preset duration
After intensity data, the method also includes:
When the signal strength obeys Unimodal Distribution, using the average value of the signal strength or median as the WiFi
Identify corresponding Target Signal Strength.
3. method according to claim 1 or 2, which is characterized in that it is described the signal strength is clustered before, institute
State method further include:
Calculate the standard deviation of the signal strength;
When the standard deviation is greater than first threshold, determine that the signal strength obeys non-Unimodal Distribution.
4. method according to claim 1 or 2, which is characterized in that the method also includes:
Each described signal strength set is concentrated in the signal strength and sieved based on the standard deviation of the signal strength set
Select abnormal data;
It is described that the corresponding Target Signal Strength of the WiFi mark is obtained according to each signal strength set, comprising:
For the signal strength set after each screening, the signal strength after obtaining the screening concentrates being averaged for signal strength
The average value is identified corresponding Target Signal Strength by value;Or,
For the signal strength set after each screening, the signal strength after obtaining the screening concentrates the middle position of signal strength
Number, using the median as the corresponding Target Signal Strength of the signal strength set.
5. method according to claim 1 or 2, which is characterized in that the method also includes:
For each obtained WiFi fingerprint, the WiFi fingerprint is compared at least one adjacent to WiFi fingerprint, institute
State the fingerprint that neighbouring WiFi fingerprint is the second area that distance is less than second threshold between first area, the first area with
The WiFi fingerprint is corresponding, and the second area is corresponding with the neighbouring WiFi fingerprint;
When WiFi mark does not occur in the WiFi fingerprint, and at least one described appearance in WiFi fingerprint
When ratio is greater than third threshold value, it is described at least one in WiFi fingerprint, obtain WiFi mark corresponding at least one
A Target Signal Strength;
According at least one described Target Signal Strength, calculates the WiFi described in the WiFi fingerprint and identify corresponding target letter
Number intensity.
6. according to the method described in claim 5, it is characterized in that, described at least one Target Signal Strength according to, meter
Calculate the Target Signal Strength of the mark of the WiFi described in the WiFi fingerprint, comprising:
Obtain the weighted value of each Target Signal Strength at least one described Target Signal Strength;
Based on the weighted value of each Target Signal Strength, at least one described Target Signal Strength is weighted and asks equal
It is worth operation, the Target Signal Strength that obtained operation result is identified as the WiFi described in the WiFi fingerprint;
Wherein, the second area of a neighbouring WiFi fingerprint is closer with the distance between the first area, corresponding mesh
The weighted value for marking signal strength is bigger.
7. method according to claim 1 or 2, which is characterized in that the method also includes:
It will be described pre- when described two WiFi mark is similar for any two WiFi mark arrived in the sector scanning
If described two WiFi identify at least one corresponding signal strength and merge in duration;
Any one WiFi in described two WiFi mark is identified when generating the WiFi fingerprint in the region and is deleted, and according to
Signal strength after merging obtains residue WiFi and identifies corresponding Target Signal Strength.
8. the method according to the description of claim 7 is characterized in that described two WiFi mark includes the first WiFi mark and the
Two WiFi mark, the method also includes:
When the similarity between the first WiFi mark and the coding of the 2nd WiFi mark is greater than four threshold values, calculate
It is corresponding with the 2nd WiFi mark to identify at least one corresponding signal strength by the first WiFi in the preset duration
Similarity between at least one signal strength;
When obtained similarity is greater than five threshold values, determine that described two WiFi marks are similar.
9. the method according to the description of claim 7 is characterized in that described two WiFi mark includes the first WiFi mark and the
Two WiFi mark, the method also includes:
When the similarity between the first WiFi mark and the coding of the 2nd WiFi mark is greater than four threshold values, obtain
The first WiFi identifies at least one corresponding signal strength in each region and the 2nd WiFi mark is corresponding
At least one signal strength;
It calculates the first WiFi in each region and identifies at least one corresponding signal strength and the 2nd WiFi mark
Similarity between at least one corresponding signal strength;
When obtained similarity is greater than six threshold values, determine that described two WiFi marks are similar.
10. a kind of WiFi fingerprint acquisition device, which is characterized in that described device includes:
First obtains module, for identifying for each Wireless Fidelity WiFi arrived in a sector scanning, when obtaining default
The WiFi identifies at least one corresponding signal strength in long;
Cluster module, for when the signal strength obeys non-Unimodal Distribution, the signal strength to be clustered, until poly-
Class obtains obeying at least two signal strength sets of Unimodal Distribution;
Second obtains module, identifies corresponding Target Signal Strength for obtaining the WiFi according to each signal strength set;
Generation module, it is raw for identifying corresponding Target Signal Strength according to each WiFi mark and each described WiFi
At the WiFi fingerprint in the region.
11. a kind of computer readable storage medium, which is characterized in that be stored at least one instruction, extremely in the storage medium
A few Duan Chengxu, code set or instruction set, at least one instruction, an at least Duan Chengxu, the code set or instruction
Collection is loaded as the processor and is executed to realize that the WiFi fingerprint as described in any claim in claim 1 to 9 obtains
Method.
12. a kind of equipment obtained for WiFi fingerprint, which is characterized in that the equipment includes processor and memory, described
At least one instruction, at least a Duan Chengxu, code set or instruction set are stored in memory, described at least one instructs, is described
An at least Duan Chengxu, the code set or instruction set are loaded by the processor and are executed to realize as appointed in claim 1 to 9
WiFi fingerprint acquisition methods described in one claim.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710853034.9A CN109525337B (en) | 2017-09-20 | 2017-09-20 | WiFi fingerprint acquisition method, device, storage medium and equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710853034.9A CN109525337B (en) | 2017-09-20 | 2017-09-20 | WiFi fingerprint acquisition method, device, storage medium and equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109525337A true CN109525337A (en) | 2019-03-26 |
CN109525337B CN109525337B (en) | 2021-04-16 |
Family
ID=65769297
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710853034.9A Active CN109525337B (en) | 2017-09-20 | 2017-09-20 | WiFi fingerprint acquisition method, device, storage medium and equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109525337B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111711985A (en) * | 2020-06-16 | 2020-09-25 | 南京林业大学 | Bluetooth RSSI value noise elimination method and Bluetooth positioning method |
CN112269159A (en) * | 2020-11-26 | 2021-01-26 | Oppo(重庆)智能科技有限公司 | Indoor positioning method and device, server and readable storage medium |
CN113806340A (en) * | 2020-06-15 | 2021-12-17 | 北京三快在线科技有限公司 | Store arrival determination method and device, storage medium and electronic equipment |
CN114189806A (en) * | 2021-12-09 | 2022-03-15 | 北京百度网讯科技有限公司 | Method and device for generating wireless signal fingerprint database and electronic equipment |
CN115515223A (en) * | 2021-06-23 | 2022-12-23 | 中移物联网有限公司 | Fingerprint information processing method and device and network equipment |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103648080A (en) * | 2013-11-18 | 2014-03-19 | 中国矿业大学 | Method and system for constructing WiFi indoor positioning fingerprint database |
US20140187270A1 (en) * | 2013-01-03 | 2014-07-03 | Cinarra Systems Pte. Ltd. | Methods and systems for dynamic detection of consumer venue walk-ins |
CN104427610A (en) * | 2013-08-28 | 2015-03-18 | 中国电信集团公司 | Wi-Fi indoor positioning method and Wi-Fi indoor positioning server |
CN105338498A (en) * | 2015-09-29 | 2016-02-17 | 北京航空航天大学 | Construction method for fingerprint database in WiFi indoor positioning system |
CN106162529A (en) * | 2016-07-08 | 2016-11-23 | 北京邮电大学 | Indoor orientation method and device |
CN106295969A (en) * | 2016-08-02 | 2017-01-04 | 贵州电网有限责任公司信息中心 | Power customer is worth a kind of weighting K means method hived off |
CN106603324A (en) * | 2015-10-20 | 2017-04-26 | 富士通株式会社 | Training set acquisition device and training set acquisition method |
CN106772235A (en) * | 2017-02-17 | 2017-05-31 | 电子科技大学 | Indoor orientation method based on RSSI attenuation characteristics and similitude |
US20170188188A1 (en) * | 2015-12-29 | 2017-06-29 | Sk Planet Co., Ltd. | Method, apparatus, and recording medium for radio fingerprint map construction and location tracking |
CN107087256A (en) * | 2017-03-17 | 2017-08-22 | 上海斐讯数据通信技术有限公司 | A kind of fingerprint cluster method and device based on WiFi indoor positionings |
-
2017
- 2017-09-20 CN CN201710853034.9A patent/CN109525337B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140187270A1 (en) * | 2013-01-03 | 2014-07-03 | Cinarra Systems Pte. Ltd. | Methods and systems for dynamic detection of consumer venue walk-ins |
CN104427610A (en) * | 2013-08-28 | 2015-03-18 | 中国电信集团公司 | Wi-Fi indoor positioning method and Wi-Fi indoor positioning server |
CN103648080A (en) * | 2013-11-18 | 2014-03-19 | 中国矿业大学 | Method and system for constructing WiFi indoor positioning fingerprint database |
CN105338498A (en) * | 2015-09-29 | 2016-02-17 | 北京航空航天大学 | Construction method for fingerprint database in WiFi indoor positioning system |
CN106603324A (en) * | 2015-10-20 | 2017-04-26 | 富士通株式会社 | Training set acquisition device and training set acquisition method |
US20170188188A1 (en) * | 2015-12-29 | 2017-06-29 | Sk Planet Co., Ltd. | Method, apparatus, and recording medium for radio fingerprint map construction and location tracking |
CN106162529A (en) * | 2016-07-08 | 2016-11-23 | 北京邮电大学 | Indoor orientation method and device |
CN106295969A (en) * | 2016-08-02 | 2017-01-04 | 贵州电网有限责任公司信息中心 | Power customer is worth a kind of weighting K means method hived off |
CN106772235A (en) * | 2017-02-17 | 2017-05-31 | 电子科技大学 | Indoor orientation method based on RSSI attenuation characteristics and similitude |
CN107087256A (en) * | 2017-03-17 | 2017-08-22 | 上海斐讯数据通信技术有限公司 | A kind of fingerprint cluster method and device based on WiFi indoor positionings |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113806340A (en) * | 2020-06-15 | 2021-12-17 | 北京三快在线科技有限公司 | Store arrival determination method and device, storage medium and electronic equipment |
CN111711985A (en) * | 2020-06-16 | 2020-09-25 | 南京林业大学 | Bluetooth RSSI value noise elimination method and Bluetooth positioning method |
CN111711985B (en) * | 2020-06-16 | 2021-06-18 | 南京林业大学 | Bluetooth RSSI value noise elimination method and Bluetooth positioning method |
CN112269159A (en) * | 2020-11-26 | 2021-01-26 | Oppo(重庆)智能科技有限公司 | Indoor positioning method and device, server and readable storage medium |
CN115515223A (en) * | 2021-06-23 | 2022-12-23 | 中移物联网有限公司 | Fingerprint information processing method and device and network equipment |
CN114189806A (en) * | 2021-12-09 | 2022-03-15 | 北京百度网讯科技有限公司 | Method and device for generating wireless signal fingerprint database and electronic equipment |
CN114189806B (en) * | 2021-12-09 | 2023-08-15 | 北京百度网讯科技有限公司 | Method and device for generating wireless signal fingerprint database and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN109525337B (en) | 2021-04-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109525337A (en) | WiFi fingerprint acquisition methods, device, storage medium and equipment | |
CN109738970B (en) | Method, device and storage medium for realizing lightning early warning based on lightning data mining | |
CN110807385B (en) | Target detection method, target detection device, electronic equipment and storage medium | |
CN105282758A (en) | Self-adaptive dynamic construction method of WIFI indoor positioning system fingerprint database | |
KR101536410B1 (en) | Apparatus and method for managing of data in energy management system | |
CN103889051B (en) | Indoor WLAN fingerprint positioning methods based on AP ID filterings and Kalman filtering | |
CN111488710B (en) | Structure damage identification method based on self-adaptive WOA-VMD and range entropy | |
CN103812577A (en) | Method for automatically identifying and learning abnormal radio signal type | |
CN111174370A (en) | Fault detection method and device, storage medium and electronic device | |
CN108805174A (en) | clustering method and device | |
CN116739829B (en) | Big data-based power data analysis method, system and medium | |
CN113889252A (en) | Remote internet big data intelligent medical system based on vital sign big data clustering core algorithm and block chain | |
CN111294841A (en) | Method and device for processing wireless network problem and storage medium | |
CN110675206A (en) | Group rental discovery method, device, equipment and computer readable medium | |
CN114881157A (en) | Method, device and equipment for detecting working state of converter valve and storage medium | |
CN113256405B (en) | Method, device, equipment and storage medium for predicting cheating user concentrated area | |
CN109798907A (en) | Tourism user's motor behavior real time information monitoring method based on big data analysis | |
CN109711450A (en) | A kind of power grid forecast failure collection prediction technique, device, electronic equipment and storage medium | |
CN117557415A (en) | Community resource management method and system based on intelligent property | |
CN108966169A (en) | For the Analysis on heavy metal pollution early warning system of agricultural land soil | |
CN108519579B (en) | WiFi fingerprint positioning method for analyzing optimal AP based on interval overlapping degree | |
CN115941807A (en) | Efficient data compression method for park security system | |
CN113947123A (en) | Personnel track identification method, system, storage medium and equipment | |
CN110969209B (en) | Stranger identification method and device, electronic equipment and storage medium | |
CN114841490A (en) | Ecological protection priority area identification method, system, device and storage medium |
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 |