CN109116299A - A kind of fingerprint positioning method, terminal, computer readable storage medium - Google Patents
A kind of fingerprint positioning method, terminal, computer readable storage medium Download PDFInfo
- Publication number
- CN109116299A CN109116299A CN201710486648.8A CN201710486648A CN109116299A CN 109116299 A CN109116299 A CN 109116299A CN 201710486648 A CN201710486648 A CN 201710486648A CN 109116299 A CN109116299 A CN 109116299A
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- value
- measurement report
- report information
- grid
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/10—Scheduling measurement reports ; Arrangements for measurement reports
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Collating Specific Patterns (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses fingerprint positioning method, terminal, computer readable storage mediums, this method comprises: obtaining the measurement report information of terminal to be positioned;Extract the validity feature value of information in measurement report information;Using the validity feature value of information as input, it is sent to output positioning coordinate information after neural network model is fitted;Wherein, the foundation of neural network model includes: to be optimized by genetic algorithm to the finger print data in fingerprint database;Neural network model is obtained by the training of neural network location model.The terminal includes the computer program for storing the fingerprint positioning method for realizing the embodiment of the present invention that can be run on a memory and on a processor.The computer-readable recording medium storage has the fingerprint location program for the fingerprint positioning method that the embodiment of the present invention is realized when being executed by processor.The present invention can solve the problems such as fingerprint database in existing fingerprinting localization algorithm is fuzzy and positioning accuracy is insufficient.
Description
Technical field
The present invention relates to fingerprint location technology field more particularly to a kind of fingerprint positioning method, terminal, computer-readable deposit
Storage media.
Background technique
In recent years, with the arrival of mobile Internet and the rapid proliferation of intelligent mobile phone terminal, people's lives mode
Huge change stealthily occurs with behavioural habits.The clothing, food, lodging and transportion -- basic necessities of life of people are all inevitably contacted with internet generation,
People habitually find meal by location based service (Location Based Service, LBS) in daily life
The Room, bank, take-away, or even make friends etc..In addition to this, much the demand concerning the scene of life security to location information is also got over
Come more urgent, such as nursing of the hospital to patient, rescue of the rescue personnel to trapped person, the security monitoring etc. of underground coal mine
Deng.The practical scene of the above provides vast market prospect and development space for LBS and its application.
Quick with 3G/4G network is popularized, and realizes that the real-time status of terminal is also got over using mobile communications network
Carry out more concerns.By acquire all terminal users of mobile network report measurement report (Measurement Report,
MR) data, in test analysis localization region all reference points reception information strength (Received Signal Strength,
RSS), and extract the signal characteristic of RSS signal, the signal characteristic after exceptional value and the position of corresponding reference point will be eliminated
Coordinate is stored in location fingerprint database together, then the signal characteristic of point to be determined is obtained using same method, according to certain
Matching algorithm and location fingerprint database matched, to obtain the estimated position of point to be determined.However existing positioning
Algorithm is there is fingerprint database location fuzzy, the defects of positioning accuracy is not high, therefore proposes that a kind of novel fingerprint location is calculated
Method seems particularly necessary.
Summary of the invention
In view of this, the purpose of the present invention is to provide fingerprint positioning method, terminal, computer readable storage medium, with
Solve fingerprint database location fuzzy, the not high problem of positioning accuracy.
It is as follows that the present invention solves technical solution used by above-mentioned technical problem:
According to an aspect of the present invention, a kind of fingerprint positioning method is provided, comprising:
Obtain the measurement report information of terminal to be positioned;
Extract the validity feature value of information in the measurement report information;
Using the validity feature value of information as input, it is sent to output positioning coordinate after neural network model is fitted
Information;
Wherein, the foundation of the neural network model includes:
It acquires the measurement report information in fingerprint location region and accordingly generates fingerprint database;
The finger print data in the fingerprint database is optimized by genetic algorithm;
The neural network model is obtained by the training of neural network location model.
In a possible design, the validity feature value of information includes at least one of TA value, RSRP value.
In a possible design, the measurement report information acquired in fingerprint location region simultaneously accordingly generates fingerprint
Database includes:
The fingerprint location region is subjected to network rasterizing, obtains several grids;
Obtain the serving cell that measurement report information all in each grid includes;
The serving cell is calculated in the RSRP value and TA value of the grid;
Using the corresponding all serving cells of the grid the grid RSRP value and TA value as a fingerprint
Data are stored in the fingerprint database.
In a possible design, the calculating serving cell includes: in the RSRP value and TA value of the grid
Whether the number for judging the corresponding measurement report information of the serving cell is one;
If so, using in the measurement report information RSRP value and TA value as the serving cell in the grid
RSRP value and TA value;
If it is not, then obtaining the corresponding all measurement report information of the serving cell;
According to the AGPS value in the measurement report information calculate the measurement report information to the grid central point
Manhattan distance;
It chooses the Manhattan and is calculated apart from the smallest first 2 or 3 measurement report information by WKNN algorithm
RSRP value of the serving cell in the grid.
In a possible design, the calculating serving cell includes: in the RSRP value and TA value of the grid
The TA value of the corresponding all measurement report information of the serving cell is averaged, as the serving cell described
The TA value of grid.
It is described excellent to the finger print data progress in the fingerprint database by genetic algorithm in a possible design
Change includes:
Determine objective optimization function;
Optimal finger print data is obtained by initialization, crossover operation, mutation operation, selection operation.
In a possible design, after the measurement report information for obtaining terminal to be positioned, further includes:
Judge whether the measurement report information meets preset rules, if so, extremely by the measurement report information update
The fingerprint database.
In a possible design, the preset rules include reaching apart from the time that last time updates fingerprint database
Preset threshold.
In a possible design, obtaining the neural network model by the training of neural network location model includes:
Neural network location model is constructed, and network parameter is initialized;
Forward calculation is carried out by the learning parameter and input data of initialization, obtains predicted value;
It is compared according to the predicted value with preset desired value, judges whether the difference of the two is less than preset threshold;
If it is not, then adjusting network parameter to reduce the cross entropy of the two, by successive ignition, until entropy is stablized.
According to another aspect of the present invention, a kind of terminal provided, comprising: memory, processor and be stored in described
On memory and the computer program that can run on the processor, the sheet when computer program is executed by the processor
The step of fingerprint positioning method that inventive embodiments provide.
According to another aspect of the present invention, a kind of computer readable storage medium provided, it is described computer-readable to deposit
It is stored with fingerprint location program on storage media, realizes that the embodiment of the present invention provides when the fingerprint location program is executed by processor
Fingerprint positioning method the step of.
Fingerprint positioning method, terminal, the computer readable storage medium of the embodiment of the present invention, utilize the adaptive of genetic algorithm
Optimizing and population iterative characteristic are answered, to optimize the accuracy of fingerprint database;By establishing BP neural network model, Ke Yishi
Now to the study in fingerprint signal space and physical location Space Nonlinear relationship, thus optimum position precision.
Detailed description of the invention
Fig. 1 is the flow diagram of the fingerprint positioning method of the embodiment of the present invention;
Fig. 2 is the flow diagram of the generation step of the fingerprint database of the embodiment of the present invention;
Fig. 3 is the embodiment of the present invention based on WKNN algorithm fingerprint database generation exemplary diagram;
Fig. 4 is the fingerprint database optimization algorithm flow chart based on genetic algorithm of the embodiment of the present invention;
Fig. 5 is the mistake neural network location model training process figure of the embodiment of the present invention;
Fig. 6 is the neural network location model hierarchy chart of the embodiment of the present invention;
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
In order to be clearer and more clear technical problems, technical solutions and advantages to be solved, tie below
Drawings and examples are closed, the present invention will be described in further detail.It should be appreciated that specific embodiment described herein is only
To explain the present invention, it is not intended to limit the present invention.
As shown in Figure 1, the fingerprint positioning method that first embodiment of the invention provides, comprising:
S101, the measurement report information for obtaining terminal to be positioned;
The validity feature value of information in S102, the extraction measurement report information;
Generally, which refers to the characteristic information that can distinguish multiple measurement report information, this has
Imitating characteristic information value includes TA value, RSRP (Reference Signal Receiving Power, Reference Signal Received Power)
At least one of value;It certainly can also include the validity feature value of information in addition to TA value, RSRP value, such as neighboring BS information etc.
The present invention is without limitation;It should be noted that if RSRP report value be less than or equal to RSRP minimal detectable power thresholding (-
Cell 140dBm), then RSRP value is not re-used as the validity feature value of information;Because the RSRP for being less than reception power threshold reports value
It is all indicated with 0, so can not be as the accurate characterization value of the MR;
S103, using the validity feature value of information as input, be sent to after neural network model is fitted export it is fixed
Position coordinate information;
After obtaining effective input information, by positioning the fitting of network model, the coordinate bit of output can be obtained
Confidence breath;
Wherein, the foundation of the neural network model includes:
S111, the measurement report information in acquisition fingerprint location region simultaneously accordingly generate fingerprint database;
S112, the finger print data in the fingerprint database is optimized by genetic algorithm;
S113, the neural network model is obtained by the training of neural network location model.
On the basis of Fig. 1 corresponding embodiment, as shown in Fig. 2, the measurement report in the acquisition fingerprint location region
Information simultaneously accordingly generates fingerprint database and includes:
S201, the fingerprint location region is subjected to network rasterizing, obtains several grids;
In the specific implementation, it can first determine that fingerprint database grid point size GRID_SIZE, grid point selected conference
Cause positioning accurate to spend difference, select the too small fingerprint database that will lead to excessively huge, and to promotion positioning accuracy without help.Root
From the point of view of the result for using practical field data to emulate, in the present embodiment using grid point size be 10m × 10m (i.e.
GRID_SIZE is 10m);
S202, the serving cell that measurement report information all in each grid includes is obtained;
S203, the serving cell is calculated in the RSRP value and TA value of the grid;
More specifically, whether the number that can first judge the corresponding measurement report information of the serving cell is one
It is a;
If so, using in the measurement report information RSRP value and TA value as the serving cell in the grid
RSRP value and TA value;
If it is not, then obtaining the corresponding all measurement report information of the serving cell;Believed according to the measurement report
AGPS value in breath calculates the Manhattan distance of central point of the measurement report information to the grid;Described in selection
Manhattan calculates the serving cell in institute by WKNN algorithm apart from the smallest first 2 or 3 measurement report information
State the RSRP value of grid;
As shown in Figure 3, that is to say, that each grid 301, obtain the clothes that all MR fallen in the grid 301 include
Business cell list, calculates the corresponding point of all measurement report information to grid center of a lattice since first serving cell of list
The Manhattan distance of point 303.Take the Manhattan distance apart from the corresponding point 302 of shortest preceding 3 measurement report information
Value is reported with its RSRP, and cell ID is calculated in the RSRP of grid using the WKNN of K=3 (weight k nearest neighbor algorithm)
Value Rc,
K=3 in above formula, DiFor the Manhattan distance apart from shortest preceding 3 MR point, RiFor apart from shortest first 3
The corresponding RSRP value of MR point, RCFor the RSRP value of the central point 303 of grid.If to a certain cell ID, the note of MR in grid
Number is recorded less than 3, then processing in this way: only 1 record, then the RSRP value reported is exactly the RSRP value of grid point, there is 2 records,
(K=2 in formula) is equally then calculated using above-mentioned formula.
Meanwhile the TA value of the corresponding all measurement report information of the serving cell can be averaged, as
TA value of the serving cell in the grid;
S204, using the corresponding all serving cells of the grid the grid RSRP value and TA value as one
Finger print data is stored in the fingerprint database.
In fingerprint database process of construction, if the MR data of all periods are built library, this process may be spent
Take the long time, and also can not just be positioned in this period.Therefore, based on any of the above embodiments, institute
After stating the measurement report information for obtaining terminal to be positioned, further includes:
Judge whether the measurement report information meets preset rules, if so, extremely by the measurement report information update
The fingerprint database.Above-mentioned preset rules include having reached preset threshold apart from the time that last time updates fingerprint database;It should
Preset threshold is, for example, 12h or for 24 hours.In the specific implementation, a window can be set, generated according to the data in current window
The poor fingerprint database of one relative accuracy can continue to update fingerprint database when the MR data of next window arrive,
To obtain a better fingerprint database.Here it is for 24 hours that time window, which is arranged, in we.
If fingerprint database data update, and 3 measurement report information that a certain serving cell of a certain grid newly obtains
Distance when thering is any one to be less than one of 3 distance values in fingerprint database, then reported with new distance value and new RSRP
Value replaces the value in fingerprint database, and recalculates to obtain the RSRP value of new grid using the WKNN algorithm in step 203.
The corresponding all TA values of a certain cell of grid are added with the summation of TA value in database, solve average value as updated TA
Value.
If a certain grid has new serving cell to report, by the RSRP value of the new corresponding grid of cell ID,
Distance value and RSRP of the Manhattan apart from shortest 3 MR report value to be stored in fingerprint database corresponding position, and solve new small
The average value of the corresponding all TA in area is stored in database corresponding position.
In fact, the basic fingerprint database generated has fingerprint fuzzy, i.e., grid point several different
Possess identical finger print data.The embodiment of the present invention uses genetic algorithm, optimizes to the ambiguity in fingerprint space.More specifically
Ground, it is described that the finger print data in the fingerprint database is carried out by genetic algorithm on the basis of Fig. 1 corresponding embodiment
Optimization comprises determining that objective optimization function;Optimal fingerprint number is obtained by initialization, crossover operation, mutation operation, selection operation
According to.
Determine the objective optimization function in fingerprint space:
F=ω P (d < d0)
Wherein ω is weight factor, P (d < d0) it is that fingerprint fuzzy region is less than error distance d0The probability of error;
Optimal finger print data is obtained by initialization, crossover operation, mutation operation, selection operation.Specific algorithm stream
Journey is as shown in Figure 4:
S401, the objective optimization function for determining fingerprint space;
S402, setting parameter, initialization population, x=(x1, x2... ..., xN)T;
S403, fitness: i=1 is calculated;
S404, judge whether n is greater than G;If so, terminating process as shown in step S405;If it is not, then entering step
S406;
Wherein, G is superposition number;
S406, judge whether i is greater than N;If so, entering step S407, n=n+1 is enabled;Then return step S403;If
It is no, then enter step 408;
Wherein, N is population number;
S408, crossover operation and mutation operation are carried out, generates new offspring individual
S409, selection operation, judgement are carried outIt is whether true;If so, as shown in step S410, more
New individual enablesIf it is not, keeping former individual then as shown in step S411;
S412, n=n+1, and return step S406 are enabled.
On the basis of Fig. 1 corresponding embodiment, as shown in figure 5, described obtained by the training of neural network location model
The neural network model includes:
S501, building neural network location model, and network parameter is initialized;
From the perspective of statistical learning, a regression problem can be regarded as by the method that fingerprint is positioned.And
Since there is non-linear relations for fingerprint signal space and locational space, this orientation problem can be regarded as non-linear time
Return problem.Fingerprint positioning method based on machine learning exactly converts offline fingerprint database and physics for fingerprint location problem
The signal space information of input is converted into corresponding position by establishing model by the problem concerning study of non-linear relation between position
It is exported between emptying, to realize positioning.Fingerprint location model based on BP neural network mainly include input layer, multilayer hide
Layer, output layer, concrete model level.Referring to Fig. 6, Fig. 6 is neural network location model hierarchy chart, in the present embodiment,
Neural network location model includes four layers, i.e. l=0, l=1, l=2, l=3, respectively corresponds input layer n, hidden layer n1, hide
Layer n2And output layer m;It should be noted that hidden layer is 2 layers, but hidden layer can also be 1 layer, 3 layers, 5 in the present embodiment
Layer etc., the specific number of plies can regard demand sets itself;In the specific implementation, as input measurement report information MR, n is therefrom extracted
A primitive character x1, x2……xnTo input layer n;Pass through network weight W1 ijFisrt feature is generated to hidden layer n1Afterwards, then pass through
Network weight W2 ijSecond feature is generated to hidden layer n2Afterwards, finally by network weight W3 ijThird feature is generated to output layer m;
Generally, the number of primitive character is less than fisrt feature or the number of second feature;The number of primitive character is not more than third spy
The number of sign;
S502, forward calculation is carried out by the learning parameter and input data of initialization, obtains predicted value;
S503, it is compared according to the predicted value with preset desired value, it is default to judge whether the difference of the two is less than
Threshold value;If it is not, then entering step S504;If so, entering step S505;
S504, network parameter is adjusted to reduce the cross entropy of the two, by successive ignition, until entropy is stablized;
The network parameter is primarily referred to as network weight;In the specific implementation, step can be returned to after adjusting network weight
Rapid S503;
S505, terminate training, preservation model.
The present invention also provides a kind of terminals, comprising: memory, processor and is stored on the memory and can be described
The computer program run on processor realizes any embodiment of the present invention when the computer program is executed by the processor
The step of fingerprint positioning method of offer.
It should be noted that above-mentioned terminal embodiment and embodiment of the method belong to same design, specific implementation process is detailed
See embodiment of the method, and the technical characteristic in embodiment of the method is corresponding applicable in Installation practice, which is not described herein again.
The present invention also provides a kind of computer readable storage medium, fingerprint is stored on the computer readable storage medium
Finder realizes the step of any embodiment of the present invention provides when the fingerprint location program is executed by processor.
It should be noted that above-mentioned computer readable storage medium embodiment and embodiment of the method belong to same design,
Specific implementation process is detailed in embodiment of the method, and the technical characteristic in embodiment of the method is corresponding applicable in Installation practice,
Which is not described herein again.
Fingerprint positioning method, terminal and computer readable storage medium provided in an embodiment of the present invention introduce genetic algorithm,
Using the characteristic of the adaptive optimizing of genetic algorithm, the grid point for possessing same fingerprint to different grid points is optimized, decision
Optimal fingerprint out, and generate new fingerprint database.BP neural network is introduced, by fingerprint signal space and physical location
The non-linear relation in space is modeled, its hiding information characteristics is learnt.Then the MR data with location information feature are utilized
It is trained, obtains reliable and stable learning model.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to be realized by hardware, but very much
In the case of the former be more preferably embodiment.Based on this understanding, technical solution of the present invention is substantially in other words to existing
The part that technology contributes can be embodied in the form of software products, which is stored in a storage
In medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal device (can be mobile phone, calculate
Machine, server, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
Preferred embodiments of the present invention have been described above with reference to the accompanying drawings, not thereby limiting the scope of the invention.This
Without departing from the scope and spirit of the invention, there are many variations to implement the present invention by field technical staff, for example as one
The feature of a embodiment can be used for another embodiment and obtain another embodiment.It is all to use institute within technical concept of the invention
Any modifications, equivalent replacements, and improvements of work, should all be within interest field of the invention.
Claims (10)
1. a kind of fingerprint positioning method characterized by comprising
Obtain the measurement report information of terminal to be positioned;
Extract the validity feature value of information in the measurement report information;
Using the validity feature value of information as input, it is sent to output positioning coordinate letter after neural network model is fitted
Breath;
Wherein, the foundation of the neural network model includes:
It acquires the measurement report information in fingerprint location region and accordingly generates fingerprint database;
The finger print data in the fingerprint database is optimized by genetic algorithm;
The neural network model is obtained by the training of neural network location model.
2. fingerprint positioning method according to claim 1, which is characterized in that the measurement in the acquisition fingerprint location region
Report information simultaneously accordingly generates fingerprint database and includes:
The fingerprint location region is subjected to network rasterizing, obtains several grids;
Obtain the serving cell that measurement report information all in each grid includes;
The serving cell is calculated in the RSRP value and TA value of the grid;
Using the corresponding all serving cells of the grid the grid RSRP value and TA value as a finger print data
It is stored in the fingerprint database.
3. fingerprint positioning method according to claim 2, which is characterized in that described to calculate the serving cell in the grid
The RSRP value and TA value of lattice include:
Whether the number for judging the corresponding measurement report information of the serving cell is one;
If so, using in the measurement report information RSRP value and TA value as the serving cell the grid RSRP
Value and TA value;
If it is not, then obtaining the corresponding all measurement report information of the serving cell;
According to the AGPS value in the measurement report information calculate the measurement report information to the grid central point
Manhattan distance;
The Manhattan is chosen to pass through described in the calculating of WKNN algorithm apart from the smallest first 2 or 3 measurement report information
RSRP value of the serving cell in the grid.
4. fingerprint positioning method according to claim 2, which is characterized in that described to calculate the serving cell in the grid
The RSRP value and TA value of lattice include: that the TA value of the corresponding all measurement report information of the serving cell is averaged,
As the serving cell the grid TA value.
5. fingerprint positioning method according to claim 1, which is characterized in that it is described by genetic algorithm to the fingerprint number
It is optimized according to the finger print data in library and includes:
Determine objective optimization function;
Optimal finger print data is obtained by initialization, crossover operation, mutation operation, selection operation.
6. fingerprint positioning method according to claim 1, which is characterized in that the measurement report for obtaining terminal to be positioned
After information, further includes:
Judge whether the measurement report information meets preset rules, if so, by the measurement report information update to described
Fingerprint database.
7. fingerprint positioning method according to claim 6, which is characterized in that the preset rules include updating apart from last time
The time of fingerprint database has reached preset threshold.
8. fingerprint positioning method according to claim 1, which is characterized in that described to pass through the training of neural network location model
Obtaining the neural network model includes: building neural network location model, and is initialized to network parameter;
Forward calculation is carried out by the learning parameter and input data of initialization, obtains predicted value;
It is compared according to the predicted value with preset desired value, judges whether the difference of the two is less than preset threshold;
If it is not, then adjusting network parameter to reduce the cross entropy of the two, by successive ignition, until entropy is stablized.
9. a kind of terminal characterized by comprising memory, processor and be stored on the memory and can be at the place
The computer program run on reason device is realized when the computer program is executed by the processor as appointed in claim 1 to 8
The step of fingerprint positioning method described in one.
10. a kind of computer readable storage medium, which is characterized in that it is fixed to be stored with fingerprint on the computer readable storage medium
Position program, realizes such as fingerprint location described in any item of the claim 1 to 8 when the fingerprint location program is executed by processor
The step of method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710486648.8A CN109116299B (en) | 2017-06-23 | 2017-06-23 | Fingerprint positioning method, terminal and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710486648.8A CN109116299B (en) | 2017-06-23 | 2017-06-23 | Fingerprint positioning method, terminal and computer readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109116299A true CN109116299A (en) | 2019-01-01 |
CN109116299B CN109116299B (en) | 2023-06-16 |
Family
ID=64732200
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710486648.8A Active CN109116299B (en) | 2017-06-23 | 2017-06-23 | Fingerprint positioning method, terminal and computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109116299B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110856255A (en) * | 2019-11-25 | 2020-02-28 | 北京眸星科技有限公司 | Anti-difference position fingerprint positioning method |
CN111541986A (en) * | 2019-01-22 | 2020-08-14 | 博彦科技股份有限公司 | Positioning method, positioning device, storage medium and processor |
CN111836358A (en) * | 2019-12-24 | 2020-10-27 | 北京嘀嘀无限科技发展有限公司 | Positioning method, electronic device, and computer-readable storage medium |
CN112423333A (en) * | 2020-11-18 | 2021-02-26 | 上海大学 | Cellular network wireless positioning method based on position fingerprint matching |
CN114222238A (en) * | 2020-09-03 | 2022-03-22 | 中国电信股份有限公司 | Positioning method, positioning device and computer-readable storage medium |
WO2023097634A1 (en) * | 2021-12-03 | 2023-06-08 | Oppo广东移动通信有限公司 | Positioning method, model training method, and device |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH04322437A (en) * | 1991-04-23 | 1992-11-12 | Fujitsu Ltd | Reflow soldering mehtod for electronic component |
CN102264097A (en) * | 2011-08-26 | 2011-11-30 | 北京铭润创展科技有限公司 | Method for positioning GSM (global system for mobile communication) mobile communication network terminal |
CN102932738A (en) * | 2012-10-31 | 2013-02-13 | 北京交通大学 | Improved positioning method of indoor fingerprint based on clustering neural network |
CN106376081A (en) * | 2016-10-28 | 2017-02-01 | 江南大学 | Mixed similarity-based indoor fingerprint positioning method |
CN106804046A (en) * | 2017-02-16 | 2017-06-06 | 广州杰赛科技股份有限公司 | Mobile location method and device based on measurement report |
CN106879065A (en) * | 2015-12-11 | 2017-06-20 | 中南大学 | A kind of Wi-Fi indoor orientation methods based on improvement WKNN |
-
2017
- 2017-06-23 CN CN201710486648.8A patent/CN109116299B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH04322437A (en) * | 1991-04-23 | 1992-11-12 | Fujitsu Ltd | Reflow soldering mehtod for electronic component |
CN102264097A (en) * | 2011-08-26 | 2011-11-30 | 北京铭润创展科技有限公司 | Method for positioning GSM (global system for mobile communication) mobile communication network terminal |
CN102932738A (en) * | 2012-10-31 | 2013-02-13 | 北京交通大学 | Improved positioning method of indoor fingerprint based on clustering neural network |
CN106879065A (en) * | 2015-12-11 | 2017-06-20 | 中南大学 | A kind of Wi-Fi indoor orientation methods based on improvement WKNN |
CN106376081A (en) * | 2016-10-28 | 2017-02-01 | 江南大学 | Mixed similarity-based indoor fingerprint positioning method |
CN106804046A (en) * | 2017-02-16 | 2017-06-06 | 广州杰赛科技股份有限公司 | Mobile location method and device based on measurement report |
Non-Patent Citations (1)
Title |
---|
赵宇 等: "城市移动无线传感器网络协同定位算法", 《电视技术》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111541986A (en) * | 2019-01-22 | 2020-08-14 | 博彦科技股份有限公司 | Positioning method, positioning device, storage medium and processor |
CN110856255A (en) * | 2019-11-25 | 2020-02-28 | 北京眸星科技有限公司 | Anti-difference position fingerprint positioning method |
CN111836358A (en) * | 2019-12-24 | 2020-10-27 | 北京嘀嘀无限科技发展有限公司 | Positioning method, electronic device, and computer-readable storage medium |
CN111836358B (en) * | 2019-12-24 | 2021-09-14 | 北京嘀嘀无限科技发展有限公司 | Positioning method, electronic device, and computer-readable storage medium |
CN114222238A (en) * | 2020-09-03 | 2022-03-22 | 中国电信股份有限公司 | Positioning method, positioning device and computer-readable storage medium |
CN114222238B (en) * | 2020-09-03 | 2024-04-26 | 中国电信股份有限公司 | Positioning method, apparatus and computer readable storage medium |
CN112423333A (en) * | 2020-11-18 | 2021-02-26 | 上海大学 | Cellular network wireless positioning method based on position fingerprint matching |
WO2023097634A1 (en) * | 2021-12-03 | 2023-06-08 | Oppo广东移动通信有限公司 | Positioning method, model training method, and device |
Also Published As
Publication number | Publication date |
---|---|
CN109116299B (en) | 2023-06-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109116299A (en) | A kind of fingerprint positioning method, terminal, computer readable storage medium | |
CN109743683B (en) | Method for determining position of mobile phone user by adopting deep learning fusion network model | |
CN109948066B (en) | Interest point recommendation method based on heterogeneous information network | |
CN104615616B (en) | group recommendation method and system | |
CN105488528B (en) | Neural network image classification method based on improving expert inquiry method | |
CN110503531A (en) | The dynamic social activity scene recommended method of timing perception | |
CN108829766B (en) | Interest point recommendation method, system, equipment and computer readable storage medium | |
KR102129400B1 (en) | Radio map construction method | |
CN112818690B (en) | Semantic recognition method and device combined with knowledge graph entity information and related equipment | |
CN108280121B (en) | Method for obtaining social network opinion leader based on K-kernel decomposition | |
CN109104688A (en) | Wireless network access point model is generated using aggregation technique | |
Ramezanian | Estimation of the profiles in posteriori ELECTRE TRI: A mathematical programming model | |
Kulkarni et al. | Mobidict: A mobility prediction system leveraging realtime location data streams | |
CN112911626A (en) | Wireless network flow prediction method based on multi-graph convolution | |
CN111738447B (en) | Mobile social network user relationship inference method based on spatio-temporal relationship learning | |
CN109977324A (en) | A kind of point of interest method for digging and system | |
CN117077041B (en) | Intelligent community management method and system based on Internet of things | |
US20220007133A1 (en) | System and method for identifying associated subjects from location histories | |
CN113947123B (en) | Personnel trajectory identification method, system, storage medium and equipment | |
CN113409096B (en) | Target object identification method and device, computer equipment and storage medium | |
CN112861692B (en) | Method and device for constructing room classification model, and method and device for classifying rooms | |
CN109886313A (en) | A kind of Dynamic Graph clustering method based on density peak | |
CN108174359A (en) | For the message push processing method of mobile terminal | |
CN112926999B (en) | Self-adaptive recommendation method and system for association supervision range of bulk commodity transaction platform | |
Zhang et al. | Multi-scale segmentation algorithm parameters optimization based on evolutionary computation |
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 | ||
TR01 | Transfer of patent right |
Effective date of registration: 20230919 Address after: Building 8, ZTE Changsha R&D and Production Base, No. 103, Wanglong Road, High tech Development Zone, Changsha, Hunan 410000 Patentee after: Changsha Zhongxing Software Co.,Ltd. Address before: 518000 Zhongnan communication tower, South China Road, Nanshan District high tech Industrial Park, Shenzhen, Guangdong Patentee before: ZTE Corp. |
|
TR01 | Transfer of patent right |