CN107121661A - Localization method, apparatus and system and server - Google Patents
Localization method, apparatus and system and server Download PDFInfo
- Publication number
- CN107121661A CN107121661A CN201710233961.0A CN201710233961A CN107121661A CN 107121661 A CN107121661 A CN 107121661A CN 201710233961 A CN201710233961 A CN 201710233961A CN 107121661 A CN107121661 A CN 107121661A
- Authority
- CN
- China
- Prior art keywords
- signal strength
- wireless signal
- current
- strength vector
- vector
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
- G01S5/0252—Radio frequency fingerprinting
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/0009—Transmission of position information to remote stations
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The application provides a kind of localization method, apparatus and system and server, wherein, localization method includes:Receive the wireless signal from current device of multiple anchor node collections;Wireless signal is pre-processed, to obtain the wireless signal strength vector of current device;Wireless signal strength vector is handled using preset algorithm, and result and the location fingerprint storehouse that generates online are compared, to obtain the positional information of current device, wherein, preset algorithm is identical with the generating algorithm in location fingerprint storehouse.The embodiment of the present application, it is not necessary to manually gather wireless signal, saves manpower and time cost, meanwhile, the result of wireless signal strength vector and the location fingerprint storehouse that generates online are compared, locating accuracy height.
Description
Technical field
The application is related to wearable device technical field, more particularly to a kind of localization method, apparatus and system and server.
Background technology
With the popularization of mobile Internet and intelligent terminal, people are growing day by day for the demand of indoor positioning information.Enterprise
The interior such as industry, market, museum, airport place needs to provide accurate positioning to realize based on indoor location service (Indoor
Location Based Services, abbreviation ILBS), to automatically provide position enquiring, hot statistics, periphery letter for user
Breath, message push, route guidance etc. are serviced.Conventional indoor locating system mainly uses radio frequency identification (Radio at present
Frequency Identification, abbreviation RFID), infrared ray, ultrasonic wave, purple honeybee (Zigbee), bluetooth, Wireless Fidelity
(WiFi) wireless signal such as.
From the point of view of localization method, location fingerprint (Location Fingerprint) method because its positioning precision is high, pair set
It is standby to require that low advantage is widely adopted in existing alignment system.Location fingerprint method is divided into off-line training and tuning on-line
Two stages.In off-line training step, wireless signal first is received in located space collection, the wireless signal for gathering reception is passed through
Training generation characteristic value, using the location fingerprint as each location point, is deposited into database, the database is also referred to as electronics
Map (Radio Map), the stage is completed by artificial collection;In positioning stage, the signal characteristic gathered in real time and position are referred to
Line storehouse is compared, to obtain positional information.
But, above-mentioned location fingerprint method needs artificial collection wireless signal, and will certainly be expended with the increase in space
Very big manpower and time cost, in addition, transmission of wireless signals is blocked by human body, humiture change, furniture displacement etc. environment because
The influence dynamic fluctuation of element is larger, and it is wireless that this can cause that the location fingerprint storehouse generated in the training stage and positioning stage gather
Signal is inconsistent, and then causes locating accuracy low.
The content of the invention
In view of this, the application, which is provided in a kind of new technical scheme, implementation process, need not manually gather wireless signal,
Manpower and time cost are saved, meanwhile, by the result of wireless signal strength vector and the location fingerprint storehouse generated online
It is compared, locating accuracy is high.
To achieve the above object, the application offer technical scheme is as follows:
According to the first aspect of the application, it is proposed that a kind of localization method, methods described includes:
Receive the wireless signal from current device of multiple anchor node collections;
The wireless signal is pre-processed, to obtain the wireless signal strength vector of the current device;
Wireless signal strength vector is handled using preset algorithm, and by result and the position that generates online
Fingerprint base is put to be compared, to obtain the positional information of the current device, wherein, the preset algorithm and the location fingerprint
The generating algorithm in storehouse is identical.
According to the second aspect of the application, it is proposed that a kind of positioner, described device includes:
Receiving module, the wireless signal from current device for receiving multiple anchor node collections;
Pretreatment module, it is described to obtain for being pre-processed to the wireless signal that the receiving module is received
The wireless signal strength vector of current device;
First locating module, for the wireless signal strength that is obtained to the pretreatment module using preset algorithm to
Amount is handled, and result and the location fingerprint storehouse that generates online are compared, to obtain the position of the current device
Confidence ceases, wherein, the preset algorithm is identical with the generating algorithm in the location fingerprint storehouse.
According to the third aspect of the application, it is proposed that a kind of server, the server includes:
Processor;Memory for storing the processor-executable instruction;
Wherein, the processor, is configured as performing above-mentioned localization method.
According to the fourth aspect of the application, it is proposed that a kind of alignment system, the system includes location-server, anchor node
And current device, wherein:
The current device, for launching wireless signal;
The anchor node, sends for gathering the wireless signal from the current device, and to the location-server
The wireless signal collected;
The location-server includes above-mentioned positioner.
From above technical scheme, the wireless signal gathered by multiple anchor nodes to reception is pre-processed, with
The wireless signal strength vector of current device is obtained, and wireless signal strength vector is handled using preset algorithm, then
Result and the location fingerprint storehouse that generates online are compared, so as to obtain the positional information of current device, realized
During need not manually gather wireless signal, save manpower and time cost, meanwhile, by wireless signal strength vector place
Reason result is compared with the location fingerprint storehouse generated online, and locating accuracy is high.
Brief description of the drawings
Fig. 1 shows the flow chart of the localization method of one example embodiment of the present invention;
Fig. 2 shows the structural representation of the alignment system of the present invention;
Fig. 3 shows the flow chart in the on-line training generation location fingerprint storehouse of one example embodiment of the present invention;
Fig. 4 A show the use positional stability judgment mode screening wireless signal of one example embodiment of the present invention
The flow chart of vector;
Fig. 4 B show the vectorial average variance judgment mode screening wireless communication of the use of one example embodiment of the present invention
Number vectorial flow chart;
Fig. 4 C show the strong signal neighbour judgment mode screening wireless signal of the use of one example embodiment of the present invention
The flow chart of vector;
Fig. 5 shows the flow chart in the renewal location fingerprint storehouse of one example embodiment of the present invention;
Fig. 6 shows the structural representation of the positioner of one example embodiment of the present invention;
Fig. 7 shows the structural representation of the positioner of the another exemplary embodiment of the present invention;
Fig. 8 shows the structural representation of the positioner of the another exemplary embodiment of the present invention;
Fig. 9 shows the structural representation of the positioner of the another exemplary embodiment of the present invention;
Figure 10 shows the structural representation of the positioner of the another exemplary embodiment of the present invention;
Figure 11 shows the structural representation of the positioner of the another exemplary embodiment of the present invention.
Embodiment
Here exemplary embodiment will be illustrated in detail, its example is illustrated in the accompanying drawings.Following description is related to
During accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawings represent same or analogous key element.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with the application.On the contrary, they be only with it is such as appended
The example of the consistent apparatus and method of some aspects be described in detail in claims, the application.
It is the purpose only merely for description specific embodiment in term used in this application, and is not intended to be limiting the application.
" one kind ", " described " and "the" of singulative used in the application and appended claims are also intended to including majority
Form, unless context clearly shows that other implications.It is also understood that term "and/or" used herein refers to and wrapped
It may be combined containing one or more associated any or all of project listed.
It will be appreciated that though various information, but this may be described using term first, second, third, etc. in the application
A little information should not necessarily be limited by these terms.These terms are only used for same type of information being distinguished from each other out.For example, not departing from
In the case of the application scope, the first information can also be referred to as the second information, similarly, and the second information can also be referred to as
One information.Depending on linguistic context, word as used in this " if " can be construed to " ... when " or " when ...
When " or " in response to determining ".
Fig. 1 shows the flow chart of the localization method of one example embodiment of the present invention, as shown in figure 1, this method can
Applied on location-server, for more clearly description scheme, the alignment system that the present embodiment can be with reference to shown in Fig. 2 is retouched
State, this method comprises the following steps:
Step S101, receives the wireless signal from current device of multiple anchor node collections.
As shown in Fig. 2 the alignment system includes location-server 21, anchor node 22 and current device, wherein, current device
Wearable bluetooth equipment such as bracelet 23 can be included but is not limited to, it can periodically launch wireless signal, anchor node
22 need to pre-set known location indoors, such as roof, wall, for gathering the wireless signal from current device,
And the wireless signal collected is sent to location-server 21, location-server 21 can receive what all anchor nodes 22 were collected
Wireless signal, it is possible to obtain the real time position of current device accordingly.
In this embodiment, current device such as bracelet can be worn in wrist, and it can periodically launch bluetooth
Broadcast singal, it often launches a broadcast singal, and fixed multiple anchor nodes indoors can gather the broadcast singal, then,
Multiple anchor nodes can send the wireless signal collected to location-server.
Step S102, is pre-processed to wireless signal, to obtain the wireless signal strength vector of current device.
In this embodiment, the wireless signal that location-server can be collected to each anchor node carries out time slip-window
Processing, for example, can be calculated according to one time window of current point in time forward slip (such as 3 seconds) in this time window
The statistical value of multiple wireless signal strengths of each anchor node collection received, the statistical value can be including but not limited to maximum
Value or average value, and the wireless signal for the current device that the statistical value is received as correspondence anchor node in current point in time is strong
Degree, the wireless signal strength of the current device then received according to all anchor nodes in current point in time, generation wireless signal is strong
Degree vector.
Step S103, is handled wireless signal strength vector using preset algorithm, and by result and raw online
Into location fingerprint storehouse be compared, to obtain the positional information of current device, wherein, the life in preset algorithm and location fingerprint storehouse
It is identical into algorithm.
Wherein, preset algorithm can include but is not limited to Markov model (HMM), it is SVMs (SVM), artificial
A kind of machine learning algorithm in neutral net (ANN).
In this embodiment, preset algorithm is identical with the generating algorithm in location fingerprint storehouse, it is therefore an objective to can will be currently available
The result of wireless signal strength vector be compared with the location fingerprint storehouse that generates online, so as to obtain current device
Positional information.
In addition, after step s 102, can also include:Determine the maximum dimension of signal intensity in wireless signal strength vector
Degree, and using the position where the corresponding anchor node of determined dimension as current device estimated location, so, if not depositing currently
In position fingerprint base, then can using the estimated location as current device positional information.
Above-described embodiment, the wireless signal gathered by multiple anchor nodes to reception is pre-processed, current to obtain
The wireless signal strength vector of equipment, and wireless signal strength vector is handled using preset algorithm, then processing is tied
Fruit is compared with the location fingerprint storehouse generated online, so as to obtain in the positional information of current device, implementation process not
Need manually to gather wireless signal, save manpower and time cost, meanwhile, by wireless signal strength vector result with
The location fingerprint storehouse generated online is compared, and locating accuracy is high.
Fig. 3 shows the flow chart in the on-line training generation location fingerprint storehouse of one example embodiment of the present invention, the reality
Apply example to be described from location-server side, as shown in figure 3, the process includes:
Step S301, is pre-processed to the wireless signal of reception, to obtain the wireless signal strength vector of current device.
Step S302, determines the maximum dimension of signal intensity in wireless signal strength vector, and determined dimension is corresponding
Anchor node where position as current device estimated location.
Step S303, records and preserves the corresponding relation of wireless signal strength vector sum estimated location.
Step S304, statistics receives the duration of wireless signal, judges whether the duration reaches preset duration, if reaching default
Duration, then perform step S305, if not up to preset duration, is continued waiting for.
Wherein, step S304 is optional step, and preset duration can be 12 hours etc..
Step S305, carries out Screening Treatment, with the data after being screened to the wireless signal strength vector of preservation.
Wherein it is possible to carry out Screening Treatment to wireless signal strength vector using a variety of screening modes, for example, it can use
Any one or a few in the various ways such as positional stability judges, vectorial average variance judges and strong signal neighbour judges,
These screening modes can complement each other, and carry out Screening Treatment to wireless signal strength vector jointly.
It should be noted that the realization that strong signal neighbour judges is not on condition that the movement velocity of current device is especially fast.
Separately below to position judgement of stability mode, vectorial average variance judgment mode and strong signal neighbour judgment mode
It is described in detail:
(1) positional stability judgment mode
As shown in Figure 4 A, positional stability judgment mode may comprise steps of:
Step S4011, for each wireless signal strength vector, determines the current radio signal strength vector corresponding time
Point, and very first time window is built according to the time point.
Assuming that current radio signal strength vector corresponding time point is t, then very first time window can be built centered on t
Mouthful, such as time window (- w/2~w/2) is built centered on t.
Step S4012, obtains the wireless signal strength vector set in very first time window.
Assuming that the length of window of very first time window is w, then there are w groups signal intensity vector, this w group signal in the window
Intensity vector may be constructed a set i.e. wireless signal strength vector set.
Step S4013, the estimated location for calculating all wireless signal strength vectors in wireless signal strength vector set is many
Number, and retained according to result of calculation or delete that current radio signal strength is vectorial and its corresponding estimated location.
Wherein, step S4013 can include:It regard the estimated location of current radio signal strength vector as current estimation position
Put, the estimated location of other wireless signal strength vectors in wireless signal strength vector set is compared with current estimated location
Compared with, if being more than or equal to predetermined number with the vectorial quantity of current estimated location identical, retain current radio signal strength to
Amount and its corresponding positional information, if being less than predetermined number with the vectorial quantity of current estimated location identical, delete currently without
Line signal intensity is vectorial and its corresponding positional information.
Estimate for example, other wireless signal strengths are vectorial during wireless signal strength vector can be gathered by below equation
Meter position is compared with current estimated location:
Wherein, i represents current radio signal strength vector, and Label represents estimated location, and w is length of window.
If being more than or equal to predetermined number with the vectorial quantity of current estimated location identical, then it is assumed that current estimated location
It is stable, its corresponding signal intensity vector namely current radio signal vector can be used for generation location fingerprint storehouse, therefore,
Retain that current radio signal is vectorial and its corresponding estimated location.
(2) vectorial average variance judgment mode
As shown in Figure 4 B, after above-mentioned steps S4012, vectorial average variance judgment mode can also include following step
Suddenly:
Step S4021, calculates the side of all each dimensions of wireless signal strength vector in wireless signal strength vector set
Difference.
Step S4022, according to the variance of each dimension of all wireless signal strengths vector, calculate wireless signal strength to
The mean of variance of all dimensions of all wireless signal strength vectors in duration set, and it is pre- to judge whether mean of variance is less than
Gating is limited, if less than pre-determined threshold, performing step S4023, if more than or equal to pre-determined threshold, performing step S4024.
Step S4023, retains that current radio signal strength is vectorial and its corresponding positional information.
Step S4024, deletes that current radio signal strength is vectorial and its corresponding positional information.
Vectorial average variance judgment mode is judged according to the stability of signal intensity vector, vectorial mean of variance
Value is smaller, represents that the vectorial otherness in adjacent windows is smaller, therefore current signal strength vector can be used for generation position and refer to
Line storehouse.
(3) strong signal neighbour's judgment mode
As shown in Figure 4 C, strong signal neighbour judgment mode may comprise steps of:
Step S4031, for each wireless signal strength vector, with other dimensions during acquisition current radio signal strength is vectorial
The signal strength difference of degree is more than the dimension of default value, and records the position where the corresponding anchor node of acquired dimension.
If certain one dimensional numerical in a signal intensity vector is larger (value usually higher than other dimensions is more),
Greater probability judges that the moment current device is near corresponding anchor node.
Step S4032, determines current radio signal strength vector corresponding time point.
Step S4033, obtain in other wireless signal strengths vector and current radio signal strength vector time difference
Less than the wireless signal strength vector of predetermined threshold value.
If the moment current device is near certain anchor node, the signal intensity of the moment nearby in time window to
Amount should also fall near the anchor node.It therefore, it can obtain the time nearby according to the time point of current radio signal strength vector
Signal intensity vector in window.
Step S4034, reads the estimated location of the wireless signal strength vector obtained, judges the estimated location and step read
The distance between position recorded in rapid S4031 whether within a preset range, if within a preset range, performing step S4035,
If outside preset range, performing step S4036.
Wherein, the position of record refer in step S4031 obtain current radio signal strength vector in other dimensions
Signal strength difference be more than default value dimension after, the position where the corresponding anchor node of acquired dimension of record.
Step S4035, retains that current radio signal strength is vectorial and its corresponding estimated location.
Step S4036, deletes that current radio signal strength is vectorial and its corresponding estimated location.
Afterwards, by the estimated location of the wireless signal strength vector in neighbouring time window and the position where corresponding anchor node
It is compared, and retains that the wireless signal strength being located near anchor node is vectorial and its corresponding estimated location.
Using strong signal neighbour judgment mode can retain wireless signal strength that the above two judgment modes can not retain to
Amount, so as to improve the anti-interference in location fingerprint storehouse.
As can be seen here, Screening Treatment can be carried out to wireless signal strength vector using various ways, and based on screening
The location fingerprint storehouse strong interference immunity of data generation afterwards.
Data after screening are handled by step S306 using preset algorithm, to generate location fingerprint storehouse.
Wherein, a kind of machine learning algorithm that preset algorithm can include but is not limited in HMM, SVM, ANN.Assuming that raw
The algorithm used during into location fingerprint storehouse is HMM, then in position fixing process, and also wireless signal strength vector is carried out using HMM
Processing, so as to which the result of wireless signal strength vector is compared with location fingerprint storehouse, obtains current device
Positional information.
Above-described embodiment, it is only necessary to demarcate anchor node in advance, you can receive wireless signal, without complicated off-line training
Stage, i.e., extra artificial collection and training process, greatly reduce training cost.
Blocked by human body due to transmission of wireless signals, humiture change, the environmental factor such as furniture displacement influenceed fluctuation compared with
Greatly, in order to reduce influence of the environmental factor to wireless location, the embodiment of the present application proposes to change over time renewal location fingerprint storehouse
Scheme, as shown in figure 5, the renewal process in the location fingerprint storehouse includes:
Step S501, the generation time in record current location fingerprint storehouse.
Step S502, from the generation time, location fingerprint storehouse is updated every preset time period.
Wherein, preset time period can for 7 days, 10 etc., it is assumed that the generation time in current location fingerprint storehouse be this Monday on
9 points of noon, preset time period is 7 days, then a whole morning 9 is lighted and starts to update location fingerprint storehouse in next week, updates location fingerprint storehouse
Process is similar to the process in generation location fingerprint storehouse, be all to the wireless signal strength preserved in preset duration such as 24 hours to
Amount carries out Screening Treatment, and the data after screening are handled using preset algorithm, to obtain new location fingerprint storehouse.Fixed
Behind location fingerprint storehouse new Shi Shengcheng, replacement completely or the mode of increment can be taken to update location fingerprint storehouse.
Above-described embodiment, updates location fingerprint storehouse by timing, it is possible to reduce influence of the environmental factor to wireless location, enters
One step improves locating accuracy.
Fig. 6 shows the structural representation of the positioner of one example embodiment of the present invention, as shown in fig. 6, the dress
Put including:Receiving module 61, the locating module 63 of pretreatment module 62 and first.
Receiving module 61 is used for the wireless signal from current device for receiving multiple anchor node collections.
Pretreatment module 62 is used to pre-process the wireless signal that receiving module 61 is received, to obtain current device
Wireless signal strength vector.
First locating module 63 is used to enter the wireless signal strength vector that pretreatment module 62 is obtained using preset algorithm
Row processing, and result and the location fingerprint storehouse that generates online are compared, to obtain the positional information of current device, its
In, preset algorithm is identical with the generating algorithm in location fingerprint storehouse.
Fig. 7 shows the structural representation of the positioner of the another exemplary embodiment of the present invention, as shown in fig. 7,
On the basis of above-mentioned embodiment illustrated in fig. 6, the device can also include:The locating module 72 of position determination module 71 and second.
Position determination module 71 is used for after pretreatment module is pre-processed to wireless signal, determines that wireless signal is strong
The maximum dimension of signal intensity in degree vector, and it regard the position where the corresponding anchor node of determined dimension as current device
Estimated location.
If the second locating module 72 is used to there is currently no location fingerprint storehouse, the estimation that position determination module 71 is determined
Position as current device positional information.
Fig. 8 shows the structural representation of the positioner of the another exemplary embodiment of the present invention, as shown in figure 8,
On the basis of above-mentioned embodiment illustrated in fig. 7, the device can also include:Record preserving module 81, statistics screening module 82 and life
Into module 83.
Recording preserving module 81 is used for the position where the corresponding anchor node of determined dimension in position determination module 71
After the estimated location of current device, the corresponding relation of wireless signal strength vector sum estimated location is recorded and preserved.
Counting screening module 82 is used to carry out Screening Treatment to the wireless signal strength vector that record preserving module 81 is preserved,
With the data after being screened.
Generation module 83 is used to handle counting the data after the screening that screening module 82 is obtained using preset algorithm,
To generate location fingerprint storehouse.
Fig. 9 shows the structural representation of the positioner of the another exemplary embodiment of the present invention, as shown in figure 9,
On the basis of above-mentioned embodiment illustrated in fig. 8, statistics screening module 82 can include:It is determined that building submodule 821, set obtains son
Module 822 and calculating sifting submodule 823.
It is determined that build submodule 821 be used for for each wireless signal strength vector, determine current radio signal strength to
Measure corresponding time point, and very first time window is built according to time point.
Set, which obtains submodule 822, to be used to obtain wireless in the very first time window that determination structure submodule 821 is built
Signal intensity vector set.
Calculating sifting submodule 823 is used for set of computations and obtains the wireless signal strength vector set that submodule 822 is obtained
In all wireless signal strengths vector estimated location mode and/or average variance, and retain or delete according to result of calculation and work as
Preceding wireless signal strength is vectorial and its corresponding estimated location.
In an optional embodiment, calculating sifting submodule 823 can include:Determining unit, comparing unit, reservation are single
Member and deletion unit, but not shown in figure.
Determining unit, for regarding the estimated location of current radio signal strength vector as current estimated location.
Comparing unit, for by the estimated location of other wireless signal strengths vector in wireless signal strength vector set with
The current estimated location that determining unit is determined is compared.
Stick unit, if the comparative result for comparing unit be more than with the vectorial quantity of current estimated location identical or
Equal to predetermined number, then retain that current radio signal strength is vectorial and its corresponding positional information.
Unit is deleted, if the comparative result for comparing unit is to be less than in advance with the vectorial quantity of current estimated location identical
If quantity, then delete that current radio signal strength is vectorial and its corresponding positional information.
In another optional embodiment, calculating sifting submodule 823 can include:Variance computing unit, average value meter
Calculate unit, stick unit and delete unit, but not shown in figure.
Variance computing unit, for calculating all each dimensions of wireless signal strength vector in wireless signal strength vector set
The variance of degree.
Average calculation unit, for each dimension of all wireless signal strengths vector calculated according to variance computing unit
Variance, calculate the mean of variance of all dimensions of all wireless signal strengths vector in wireless signal strength vector set
Value.
Stick unit, if being less than pre-determined threshold for the mean of variance that average calculation unit is calculated, retains and works as
Preceding wireless signal strength is vectorial and its corresponding positional information.
Unit is deleted, if being more than or equal to pre-determined threshold for the mean of variance that average calculation unit is calculated,
Delete that current radio signal strength is vectorial and its corresponding positional information.
Figure 10 shows the structural representation of the positioner of the another exemplary embodiment of the present invention, as shown in Figure 10,
On the basis of above-mentioned embodiment illustrated in fig. 8, statistics screening module 82 can also include:Acquisition record sub module 824, time are true
Stator modules 825, vectorial acquisition submodule 826 and reading screening submodule 827.
Obtain record sub module 824 be used for for each wireless signal strength vector, obtain current radio signal strength to
It is more than the dimension of default value in amount with the signal strength difference of other dimensions, and records the acquired corresponding anchor node institute of dimension
Position.
Time determination sub-module 825 is used to determine current radio signal strength vector corresponding time point.
Vectorial acquisition submodule 826 is used to obtain true with time determination sub-module 825 in other wireless signal strength vectors
The difference of the time of fixed current radio signal strength vector is less than the wireless signal strength vector of predetermined threshold value.
Reading screening submodule 827 is used to read estimating for the wireless signal strength vector that vectorial acquisition submodule 826 is obtained
Position is counted, if the estimated location read is with obtaining the distance between position that record sub module 824 is recorded within a preset range,
Retain that current radio signal strength is vectorial and its corresponding estimated location, if distance is outside preset range, delete current wireless
Signal intensity is vectorial and its corresponding estimated location.
Figure 11 shows the structural representation of the positioner of the another exemplary embodiment of the present invention, as shown in figure 11,
On the basis of above-mentioned embodiment illustrated in fig. 6, pretreatment module 62 can include:Build submodule 621, calculate determination sub-module
622 generate submodule 623 with vector.
Building submodule 621 is used to build the second time window according to current point in time.
Calculating determination sub-module 622 is used to calculate what is received in the second time window for building the structure of submodule 621 respectively
The statistical value of multiple wireless signal strengths of each anchor node collection, and using statistical value as correspondence anchor node in current point in time
The wireless signal strength of the current device of reception.
Vector generation submodule 623 is used for all anchor nodes determined according to calculating determination sub-module 622 in current time
The wireless signal strength for the current device that point is received, generation wireless signal strength vector.
The embodiment of the present invention, it is only necessary to demarcate anchor node in advance, you can receive wireless signal, without complicated offline instruction
Practice stage, i.e., extra artificial collection and training process, greatly reduce training cost;Adopted by multiple anchor nodes to reception
The wireless signal of collection is pre-processed, to obtain the wireless signal strength vector of current device, and using preset algorithm to wireless
Signal intensity vector is handled, and then result and the location fingerprint storehouse that generates online are compared, so as to must
To the positional information of current device, wireless signal need not be manually gathered in implementation process, manpower and time cost is saved, together
When, the result of wireless signal strength vector and the location fingerprint storehouse that generates online are compared, locating accuracy height;It is logical
Cross timing and update location fingerprint storehouse, it is possible to reduce influence of the environmental factor to wireless location, further improve locating accuracy.
On the device in above-described embodiment, wherein modules perform the concrete mode of operation in relevant this method
Embodiment in be described in detail, explanation will be not set forth in detail herein.
Those skilled in the art will readily occur to its of the application after considering specification and putting into practice invention disclosed herein
Its embodiment.The application is intended to any modification, purposes or the adaptations of the application, these modifications, purposes or
Person's adaptations follow the general principle of the application and including the undocumented common knowledge in the art of the application
Or conventional techniques.Description and embodiments are considered only as exemplary, and the true scope of the application and spirit are by following
Claim is pointed out.
It should also be noted that, term " comprising ", "comprising" or its any other variant are intended to nonexcludability
Comprising so that process, method, commodity or equipment including a series of key elements are not only including those key elements, but also wrap
Include other key elements being not expressly set out, or also include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that wanted including described
Also there is other identical element in process, method, commodity or the equipment of element.
The preferred embodiment of the application is the foregoing is only, not to limit the application, all essences in the application
God is with principle, and any modification, equivalent substitution and improvements done etc. should be included within the scope of the application protection.
Claims (18)
1. a kind of localization method, it is characterised in that methods described includes:
Receive the wireless signal from current device of multiple anchor node collections;
The wireless signal is pre-processed, to obtain the wireless signal strength vector of the current device;
Wireless signal strength vector is handled using preset algorithm, and result and the position that generates online are referred to
Line storehouse is compared, to obtain the positional information of the current device, wherein, the preset algorithm and the location fingerprint storehouse
Generating algorithm is identical.
2. according to the method described in claim 1, it is characterised in that it is described the wireless signal is pre-processed after,
Methods described also includes:
Determine the maximum dimension of signal intensity in wireless signal strength vector, and by the corresponding anchor node institute of determined dimension
Position as the current device estimated location;
If there is currently no the location fingerprint storehouse, using the estimated location as the current device positional information.
3. method according to claim 2, it is characterised in that where the corresponding anchor node by determined dimension
After estimated location of the position as the current device, methods described also includes:
Record and preserve the corresponding relation of the wireless signal strength vector sum estimated location;
Screening Treatment is carried out to the wireless signal strength vector of preservation, with the data after being screened;
The data after the screening are handled using the preset algorithm, to generate the location fingerprint storehouse.
4. method according to claim 3, it is characterised in that the wireless signal strength vector of described pair of preservation is carried out
Screening Treatment, including:
For each wireless signal strength vector, current radio signal strength vector corresponding time point is determined, and according to described
Time point builds very first time window;
Obtain the wireless signal strength vector set in the very first time window;
Calculate in the wireless signal strength vector set estimated location mode of all wireless signal strengths vectors and/or average
Variance, and retained according to result of calculation or delete that the current radio signal strength is vectorial and its corresponding estimated location.
5. method according to claim 4, it is characterised in that the wireless signal strength vector of described pair of preservation is carried out
Screening Treatment, in addition to:
For each wireless signal strength vector, the difference in signal strength with other dimensions in current radio signal strength vector is obtained
Value is more than the dimension of default value, and records the position where the corresponding anchor node of acquired dimension;
Determine the current radio signal strength vector corresponding time point;
Obtain in other wireless signal strengths vectors and current radio signal strength vector time difference be less than it is pre-
If the wireless signal strength vector of threshold value;
The estimated location of the wireless signal strength vector obtained is read, if the estimated location read and the position of record
The distance between within a preset range, then retain that current radio signal strength is vectorial and its corresponding estimated location, if it is described away from
From outside the preset range, then delete that current radio signal strength is vectorial and its corresponding estimated location.
6. method according to claim 4, it is characterised in that institute in the calculating wireless signal strength vector set
There is the estimated location mode of wireless signal strength vector, and retained according to result of calculation or delete the current radio signal strength
Vectorial and its corresponding positional information, including:
It regard the estimated location of current radio signal strength vector as current estimated location;
By the estimated location of other wireless signal strength vectors and the current estimation in wireless signal strength vector set
Position is compared;
If being more than or equal to predetermined number with the vectorial quantity of the current estimated location identical, retain the current wireless communication
Number intensity vector and its corresponding positional information;
If being less than the predetermined number with the vectorial quantity of the current estimated location identical, the current radio signal is deleted
Intensity vector and its corresponding positional information.
7. method according to claim 4, it is characterised in that institute in the calculating wireless signal strength vector set
There is the average variance of wireless signal strength vector, and retained according to result of calculation or delete the current radio signal strength vector
And its corresponding positional information, including:
Calculate the variance of all each dimensions of wireless signal strength vector in the wireless signal strength vector set;
According to the variance of all each dimensions of wireless signal strength vector, the wireless signal strength vector set is calculated
In all wireless signal strengths vector all dimensions mean of variance;
If the mean of variance is less than pre-determined threshold, retain that the current radio signal strength is vectorial and its corresponding position
Information;
If the mean of variance is more than or equal to the pre-determined threshold, delete current radio signal strength vector and its
Corresponding positional information.
8. according to the method described in claim 1, it is characterised in that described that the wireless signal is pre-processed, to obtain
The wireless signal strength vector of the current device, including:
Second time window is built according to current point in time;
The statistical value of multiple wireless signal strengths of each anchor node collection received in second time window is calculated respectively,
And the wireless signal strength for the current device for receiving the statistical value in current point in time as correspondence anchor node;
The wireless signal strength of the current device received according to all anchor nodes in current point in time, generates the wireless communication
Number intensity vector.
9. a kind of positioner, it is characterised in that described device includes:
Receiving module, the wireless signal from current device for receiving multiple anchor node collections;
Pretreatment module, it is described current to obtain for being pre-processed to the wireless signal that the receiving module is received
The wireless signal strength vector of equipment;
First locating module, the wireless signal strength vector for being obtained using preset algorithm to the pretreatment module is entered
Row processing, and result and the location fingerprint storehouse that generates online are compared, to obtain the position letter of the current device
Breath, wherein, the preset algorithm is identical with the generating algorithm in the location fingerprint storehouse.
10. device according to claim 9, it is characterised in that described device also includes:
Position determination module, after being pre-processed in the pretreatment module to the wireless signal, determines the nothing
The maximum dimension of signal intensity in line signal intensity vector, and it regard the position where the corresponding anchor node of determined dimension as institute
State the estimated location of current device;
Second locating module, if for there is currently no the location fingerprint storehouse, the institute that the position determination module is determined
Estimated location is stated as the positional information of the current device.
11. device according to claim 10, it is characterised in that described device also includes:
Record preserving module, for the position determination module using the position where the corresponding anchor node of determined dimension as
After the estimated location of the current device, the correspondence pass of the wireless signal strength vector sum estimated location is recorded and preserved
System;
Screening module is counted, the wireless signal strength vector that the record preserving module is preserved is carried out at screening for uniting
Reason, with the data after being screened;
Generation module, for being carried out using the preset algorithm to the data counted after the screening that screening module is obtained
Processing, to generate the location fingerprint storehouse.
12. device according to claim 11, it is characterised in that the statistics screening module includes:
It is determined that submodule is built, for for each wireless signal strength vector, determining current radio signal strength vector correspondence
Time point, and according to the time point build very first time window;
Set obtains submodule, for obtaining the wireless communication for determining to build in the very first time window of submodule structure
Number intensity vector set;
Calculating sifting submodule, is obtained in the wireless signal strength vector set that submodule is obtained for calculating the set
The estimated location mode and/or average variance of all wireless signal strength vectors, and according to result of calculation reservation or deleting
Current radio signal strength is vectorial and its corresponding estimated location.
13. device according to claim 12, it is characterised in that the statistics screening module also includes:
Obtain record sub module, for for each wireless signal strength vector, obtain current radio signal strength vector in
The signal strength difference of other dimensions is more than the dimension of default value, and records the position where the corresponding anchor node of acquired dimension
Put;
Time determination sub-module, for determining the current radio signal strength vector corresponding time point;
Vectorial acquisition submodule, is determined for obtaining in other wireless signal strength vectors with the time determination sub-module
The current radio signal strength vector time difference be less than predetermined threshold value wireless signal strength vector;
Screening submodule is read, the estimation for reading the wireless signal strength vector that the vectorial acquisition submodule is obtained
Position, if the distance between described position that the estimated location read is recorded with the acquisition record sub module is in preset range
It is interior, then retain that current radio signal strength is vectorial and its corresponding estimated location, if the distance is outside the preset range,
Delete that current radio signal strength is vectorial and its corresponding estimated location.
14. device according to claim 12, it is characterised in that the calculating sifting submodule includes:
Determining unit, for regarding the estimated location of current radio signal strength vector as current estimated location;
Comparing unit, for by the estimated location of other wireless signal strengths vector in wireless signal strength vector set with
The current estimated location that the determining unit is determined is compared;
Stick unit, if the comparative result for the comparing unit is big with the vectorial quantity of the current estimated location identical
In or equal to predetermined number, then retain that the current radio signal strength is vectorial and its corresponding positional information;
Unit is deleted, if the comparative result for the comparing unit is small with the vectorial quantity of the current estimated location identical
In the predetermined number, then delete that the current radio signal strength is vectorial and its corresponding positional information.
15. device according to claim 12, it is characterised in that the calculating sifting submodule includes:
Variance computing unit, for calculating all each dimensions of wireless signal strength vector in the wireless signal strength vector set
The variance of degree;
Average calculation unit, all wireless signal strength vectors for being calculated according to the variance computing unit are each
The variance of dimension, calculates the side of all dimensions of all wireless signal strength vectors in the wireless signal strength vector set
Poor average value;
Stick unit, if being less than pre-determined threshold for the mean of variance that the average calculation unit is calculated, is protected
Stay the current radio signal strength vectorial and its corresponding positional information;
Unit is deleted, if being more than or equal to for the mean of variance that the average calculation unit is calculated described default
Thresholding, then delete that the current radio signal strength is vectorial and its corresponding positional information.
16. device according to claim 9, it is characterised in that the pretreatment module includes:
Submodule is built, for building the second time window according to current point in time;
Determination sub-module is calculated, what is received for calculating respectively in second time window that the structure submodule is built is every
The statistical value of multiple wireless signal strengths of individual anchor node collection, and using the statistical value as correspondence anchor node in current time
The wireless signal strength for the current device that point is received;
Vector generation submodule, all anchor nodes for being determined according to the calculating determination sub-module are received in current point in time
The current device wireless signal strength, generate wireless signal strength vector.
17. a kind of server, it is characterised in that the server includes:
Processor;Memory for storing the processor-executable instruction;
Wherein, the processor, is configured as performing any described methods of the claims 1-8.
18. a kind of alignment system, it is characterised in that the system includes location-server, anchor node and current device, wherein:
The current device, for launching wireless signal;
The anchor node, is gathered for gathering the wireless signal from the current device, and being sent to the location-server
The wireless signal arrived;
The location-server includes the positioner as described in claim 9-16 is any.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710233961.0A CN107121661B (en) | 2017-04-11 | 2017-04-11 | Positioning method, device and system and server |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710233961.0A CN107121661B (en) | 2017-04-11 | 2017-04-11 | Positioning method, device and system and server |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107121661A true CN107121661A (en) | 2017-09-01 |
CN107121661B CN107121661B (en) | 2019-12-06 |
Family
ID=59725201
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710233961.0A Active CN107121661B (en) | 2017-04-11 | 2017-04-11 | Positioning method, device and system and server |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107121661B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110632552A (en) * | 2018-06-22 | 2019-12-31 | K11集团有限公司 | User wireless positioning method and system |
CN111239681A (en) * | 2020-02-14 | 2020-06-05 | 深圳空循环科技有限公司 | Positioning method and device and electronic equipment |
CN113124868A (en) * | 2019-12-31 | 2021-07-16 | 华为技术有限公司 | Terminal positioning method and related equipment |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101420749A (en) * | 2008-12-02 | 2009-04-29 | 中国科学技术大学苏州研究院 | Determining method for indoor node region of wireless sensor network |
CN101938832A (en) * | 2010-09-15 | 2011-01-05 | 中国人民解放军海军航空工程学院 | Division and refinement-based node self-positioning method for wireless sensor network |
CN103458369A (en) * | 2013-08-09 | 2013-12-18 | 南京信息工程大学 | WiFi indoor positioning method based on anchor point and position fingerprints |
US20150195682A1 (en) * | 2014-01-03 | 2015-07-09 | Electronics And Telecommunications Research Institute | Method and apparatus for recognizing indoor location using received signal strength intensity map |
CN105873211A (en) * | 2016-04-29 | 2016-08-17 | 安徽华米信息科技有限公司 | Positioning method and device |
CN106021490A (en) * | 2016-05-19 | 2016-10-12 | 中国地质大学(武汉) | Indoor peripheral position query system |
-
2017
- 2017-04-11 CN CN201710233961.0A patent/CN107121661B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101420749A (en) * | 2008-12-02 | 2009-04-29 | 中国科学技术大学苏州研究院 | Determining method for indoor node region of wireless sensor network |
CN101938832A (en) * | 2010-09-15 | 2011-01-05 | 中国人民解放军海军航空工程学院 | Division and refinement-based node self-positioning method for wireless sensor network |
CN103458369A (en) * | 2013-08-09 | 2013-12-18 | 南京信息工程大学 | WiFi indoor positioning method based on anchor point and position fingerprints |
US20150195682A1 (en) * | 2014-01-03 | 2015-07-09 | Electronics And Telecommunications Research Institute | Method and apparatus for recognizing indoor location using received signal strength intensity map |
CN105873211A (en) * | 2016-04-29 | 2016-08-17 | 安徽华米信息科技有限公司 | Positioning method and device |
CN106021490A (en) * | 2016-05-19 | 2016-10-12 | 中国地质大学(武汉) | Indoor peripheral position query system |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110632552A (en) * | 2018-06-22 | 2019-12-31 | K11集团有限公司 | User wireless positioning method and system |
CN113124868A (en) * | 2019-12-31 | 2021-07-16 | 华为技术有限公司 | Terminal positioning method and related equipment |
CN111239681A (en) * | 2020-02-14 | 2020-06-05 | 深圳空循环科技有限公司 | Positioning method and device and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN107121661B (en) | 2019-12-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109212476B (en) | RFID indoor positioning algorithm based on DDPG | |
US11017325B2 (en) | Passive visit detection | |
CN102762957B (en) | Historial traffic data compression | |
US7532113B2 (en) | System and methods for determining the location dynamics of a portable computing device | |
zeng Wang et al. | Improvement on APIT localization algorithms for wireless sensor networks | |
CN108960785B (en) | Information prompting method and device | |
CN111212383B (en) | Method, device, server and medium for determining number of regional permanent population | |
CN107121661A (en) | Localization method, apparatus and system and server | |
CN104715043A (en) | Information pushing method and system | |
CN105629196B (en) | Alignment system and correlation method based on computer vision and dynamic fingerprint | |
WO2004095192A3 (en) | Systems and methods for securing wireless computer networks | |
CN110688589A (en) | Store arrival identification method and device, electronic equipment and readable storage medium | |
CN105898711B (en) | A kind of localization method and device based on earth magnetism reference line | |
US11782496B2 (en) | Smart context subsampling on-device system | |
CN109239661A (en) | A kind of RFID indoor locating system and algorithm based on depth Q network | |
CN116757348A (en) | Travel information intelligent planning management system and method based on artificial intelligence | |
Sommer et al. | Energy-and mobility-aware scheduling for perpetual trajectory tracking | |
CN111132027A (en) | Scene recognition network graph drawing method, scene recognition method and device | |
CN110443287A (en) | A kind of mobile stream method for drafting of the crowd based on sparse track data | |
CN109121081B (en) | Indoor positioning method based on position candidate set and EM algorithm | |
CN109520508A (en) | Localization method, device and positioning device | |
CN111654843B (en) | Method and system for automatically updating fingerprint database, wifi positioning method and system | |
Chandio et al. | Towards adaptable and tunable cloud-based map-matching strategy for GPS trajectories | |
KR101094688B1 (en) | Indoor moving object database updating method | |
JP6367771B2 (en) | POSITION ESTIMATION DEVICE, POSITION ESTIMATION METHOD, AND POSITION ESTIMATION PROGRAM |
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 |