CN110231593A - Indoor orientation method, device, computer readable storage medium and terminal device - Google Patents
Indoor orientation method, device, computer readable storage medium and terminal device Download PDFInfo
- Publication number
- CN110231593A CN110231593A CN201910289268.4A CN201910289268A CN110231593A CN 110231593 A CN110231593 A CN 110231593A CN 201910289268 A CN201910289268 A CN 201910289268A CN 110231593 A CN110231593 A CN 110231593A
- Authority
- CN
- China
- Prior art keywords
- print data
- finger print
- current
- floor
- terminal device
- 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.)
- Pending
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
Abstract
The invention belongs to indoor positioning technologies field more particularly to a kind of indoor orientation method, device, computer readable storage medium and terminal devices.The method obtains the current Wi-Fi finger print data that terminal device acquires in specified building;The current Wi-Fi finger print data is handled using preset floor disaggregated model, obtains terminal device current floor locating in the specified building;Wi-Fi finger print data word bank corresponding with the current floor is chosen from the Wi-Fi fingerprint database of the specified building;Positioning coordinate of the terminal device in the specified building is calculated according to the current Wi-Fi finger print data and the Wi-Fi finger print data word bank.Through the embodiment of the present invention, by entire indoor positioning procedure decomposition for two processes of floor location and coordinate setting, compared to traditional direct mode for carrying out coordinate setting in whole building, calculation amount is greatly reduced, it is more practical in large-scale indoor positioning.
Description
Technical field
The invention belongs to indoor positioning technologies field more particularly to a kind of indoor orientation method, device, computer-readable deposit
Storage media and terminal device.
Background technique
In recent years, the extensive use due to internet and technology of Internet of things and smart phone and other wireless devices exist
The continuous of market is popularized, and various indoor positioning technologies are also developed and improve.It is present that there are many (the whole world GNSS in the market
Navigational satellite system) receiver etc product, these products use GPS (global positioning system), GLONASS (GLONASS
Navigation system), Galileo (galileo satellite navigation system) or dipper system, positioned for real-time satellite.Since satellite is believed
Number pass through building surface when will cause signal decaying therefore its reach indoor environment when a large amount of energy has been lost, furthermore
It is indoor and outdoor because environment (factors such as atmospheric density, temperature, pressure) difference will cause multipath reflection phenomenon so as to cause multipath
Propagation effect, eventually generates a large amount of artificial uncontrollable errors, therefore general Global Satellite Navigation System can not be
Play the role of in building effective.
In recent years, the method for occurring carrying out indoor positioning based on Wi-Fi fingerprint, since Wi-Fi covers in the world
Cover area is wide, therefore is in most cases easy in most area and all get Wi-Fi signal strength data.Add
The deployment of upper Wi-Fi network does not need excessive hardware-dependent other than necessary modem and router, so the skill
Art cost is lower compared with other indoor positioning technologies.In addition, Wi-Fi signal strength parameter is compared with other attributes such as Time And Space Parameters
It is more stable, for example angle or arrival time can be because it constantly change to bring biggish error, Wi-Fi fingerprint is fixed
It can produce relatively accurate result in the technical know-how of position.But the existing method that indoor positioning is carried out based on Wi-Fi fingerprint
It is only more practical in the indoor positioning of small range (single floor), and the calculation amount in the indoor positioning of a wide range of (multiple floors)
Very huge, practicability is poor.
Summary of the invention
In view of this, the embodiment of the invention provides a kind of indoor orientation method, device, computer readable storage medium and
Terminal device is calculated in large-scale indoor positioning with solving the existing method for carrying out indoor positioning based on Wi-Fi fingerprint
Measure very huge, the poor problem of practicability.
The first aspect of the embodiment of the present invention provides a kind of indoor orientation method, may include:
Obtain the current Wi-Fi finger print data that terminal device acquires in specified building;
The current Wi-Fi finger print data is handled using preset floor disaggregated model, the terminal is obtained and sets
Standby locating current floor in the specified building;
Wi-Fi fingerprint corresponding with the current floor is chosen from the Wi-Fi fingerprint database of the specified building
Data word bank;
The terminal device is calculated in institute according to the current Wi-Fi finger print data and the Wi-Fi finger print data word bank
State the positioning coordinate in specified building.
Further, the floor disaggregated model is made of self-encoding encoder and classifier, described to use preset floor point
Class model handles the current Wi-Fi finger print data, and it is locating in the specified building to obtain the terminal device
Current floor include:
Dimensionality reduction and Principle component extraction are carried out to the current Wi-Fi finger print data using the self-encoding encoder, obtained self-editing
Code device output data;
Classified using the classifier to the self-encoding encoder output data, determines the terminal device in the finger
Determine current floor locating in building.
Further, described according to the current Wi-Fi finger print data and Wi-Fi finger print data word bank calculating
Positioning coordinate of the terminal device in the specified building include:
Calculate separately each Euclidean distance referring between Wi-Fi finger print data and the current Wi-Fi finger print data, institute
Stating referring to Wi-Fi finger print data is the Wi-Fi finger print data in the Wi-Fi finger print data word bank;
Most from the Euclidean distance chosen in the Wi-Fi finger print data word bank between the current Wi-Fi finger print data
K small Wi-Fi finger print data is as preferred Wi-Fi finger print data, wherein K is the integer greater than 1;
Positioning coordinate of the terminal device in the specified building is calculated according to the following formula:
Wherein, i is the serial number of the preferred Wi-Fi finger print data, 1≤i≤K, XiFor with i-th of preferred Wi-Fi fingerprint
The corresponding coordinate of data, WiFor weighting coefficient corresponding with i-th of preferred Wi-Fi finger print data, Y is the terminal device in institute
State the positioning coordinate in specified building.
Further, the setting up procedure of the weighting coefficient includes:
Weighting coefficient corresponding with each preferred Wi-Fi finger print data is calculated according to the following formula:
Wherein, diFor the Euclidean distance between i-th of preferred Wi-Fi finger print data and the current Wi-Fi finger print data.
Further, the indoor orientation method further include:
Training is iterated to the floor disaggregated model using the Wi-Fi fingerprint database, and is training it every time
Afterwards, the error of the floor disaggregated model is calculated;
If the error is greater than or equal to preset error threshold, according to the error to the floor disaggregated model
Parameter is adjusted, and is continued to execute and be iterated trained process to the floor disaggregated model;
If the error is less than the error threshold, terminate to be iterated trained mistake to the floor disaggregated model
Journey.
The second aspect of the embodiment of the present invention provides a kind of indoor positioning device, may include:
Fingerprint data collection module, the current Wi-Fi fingerprint number acquired in specified building for obtaining terminal device
According to;
Floor location module, for using preset floor disaggregated model to the current Wi-Fi finger print data at
Reason obtains terminal device current floor locating in the specified building;
Database chooses module, for chosen from the Wi-Fi fingerprint database of the specified building with it is described current
The corresponding Wi-Fi finger print data word bank of floor;
Coordinate calculation module is positioned, for according to the current Wi-Fi finger print data and the Wi-Fi finger print data word bank
Calculate positioning coordinate of the terminal device in the specified building.
Further, the floor disaggregated model is made of self-encoding encoder and classifier, and the floor location module can be with
Include:
Coding unit, for carrying out dimensionality reduction and principal component to the current Wi-Fi finger print data using the self-encoding encoder
It extracts, obtains self-encoding encoder output data;
Taxon determines the end for classifying using the classifier to the self-encoding encoder output data
End equipment current floor locating in the specified building.
Further, the positioning coordinate calculation module may include:
Metrics calculation unit, for calculating separately each reference Wi-Fi finger print data and the current Wi-Fi finger print data
Between Euclidean distance, it is described referring to Wi-Fi finger print data be the Wi-Fi finger print data word bank in Wi-Fi finger print data;
Data selecting unit, for being chosen and the current Wi-Fi finger print data from the Wi-Fi finger print data word bank
Between the smallest K Wi-Fi finger print data of Euclidean distance as preferred Wi-Fi finger print data, wherein K be it is whole greater than 1
Number;
Coordinate calculating unit is positioned, for calculating positioning of the terminal device in the specified building according to the following formula
Coordinate:
Wherein, i is the serial number of the preferred Wi-Fi finger print data, 1≤i≤K, XiFor with i-th of preferred Wi-Fi fingerprint
The corresponding coordinate of data, WiFor weighting coefficient corresponding with i-th of preferred Wi-Fi finger print data, Y is the terminal device in institute
State the positioning coordinate in specified building.
Further, the positioning coordinate calculation module can also include:
Coefficient calculation unit, for calculating weighting system corresponding with each preferred Wi-Fi finger print data according to the following formula
Number:
Wherein, diFor the Euclidean distance between i-th of preferred Wi-Fi finger print data and the current Wi-Fi finger print data.
Further, the indoor positioning device can also include:
Model training unit, for being iterated instruction to the floor disaggregated model using the Wi-Fi fingerprint database
Practice, and in the error for after training, calculating the floor disaggregated model every time;
Parameter adjustment unit, if being greater than or equal to preset error threshold for the error, according to the error pair
The parameter of the floor disaggregated model is adjusted, and is continued to execute and be iterated trained mistake to the floor disaggregated model
Journey;
Terminate training unit, if being less than the error threshold for the error, terminates to the floor disaggregated model
It is iterated trained process.
The third aspect of the embodiment of the present invention provides a kind of computer readable storage medium, the computer-readable storage
Media storage has computer-readable instruction, and the computer-readable instruction realizes that any of the above-described kind of interior is fixed when being executed by processor
The step of position method.
The fourth aspect of the embodiment of the present invention provides a kind of terminal device, including memory, processor and is stored in
In the memory and the computer-readable instruction that can run on the processor, the processor executes the computer can
The step of any of the above-described kind of indoor orientation method is realized when reading instruction.
Existing beneficial effect is the embodiment of the present invention compared with prior art: the embodiment of the present invention obtains terminal device and exists
The current Wi-Fi finger print data acquired in specified building;Using preset floor disaggregated model to the current Wi-Fi fingerprint
Data are handled, and terminal device current floor locating in the specified building is obtained;From the specified building
Wi-Fi finger print data word bank corresponding with the current floor is chosen in the Wi-Fi fingerprint database of object;According to described current
Wi-Fi finger print data and the Wi-Fi finger print data word bank calculate positioning of the terminal device in the specified building
Coordinate.Through the embodiment of the present invention, first by entire indoor positioning procedure decomposition for two processes of floor location and coordinate setting
It first passes through preset floor disaggregated model and completes the process of floor location, so that orientation range is greatly reduced, on this basis,
It is further carried out accurately coordinate setting, compared to traditional direct mode for carrying out coordinate setting in whole building,
Calculation amount is greatly reduced, it is more practical in large-scale indoor positioning.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is a kind of one embodiment flow chart of indoor orientation method in the embodiment of the present invention;
Fig. 2 is the schematic diagram of floor disaggregated model;
Fig. 3 is the schematic diagram of self-encoding encoder;
Fig. 4 is the schematic diagram of neural network model;
Fig. 5 is a kind of one embodiment structure chart of indoor positioning device in the embodiment of the present invention;
Fig. 6 is a kind of schematic block diagram of terminal device in the embodiment of the present invention.
Specific embodiment
In order to make the invention's purpose, features and advantages of the invention more obvious and easy to understand, below in conjunction with the present invention
Attached drawing in embodiment, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that disclosed below
Embodiment be only a part of the embodiment of the present invention, and not all embodiment.Based on the embodiments of the present invention, this field
Those of ordinary skill's all other embodiment obtained without making creative work, belongs to protection of the present invention
Range.
Referring to Fig. 1, a kind of one embodiment of indoor orientation method may include: in the embodiment of the present invention
Step S101, the current Wi-Fi finger print data that terminal device acquires in specified building is obtained.
Wi-Fi fingerprint refers to that terminal device collected reception signal in an interior for being covered with Wi-Fi signal is strong
It spends (Received Signal Strength, RSS).Because Wi-Fi signal strength can be with propagation during spatial
The increase of distance and weaken, therefore terminal device is closer with a distance from signal emitting-source, and the RSS value obtained is bigger, conversely, eventually
End equipment is remoter from signal emitting-source, and the RSS value obtained is with regard to smaller.
In the present embodiment, the number of all signal emitting-sources in the specified building is denoted as N, then theoretically,
Terminal device can be respectively received the RSS value namely the collected Wi-Fi fingerprint number of terminal device of this N number of signal emitting-source
According to the data for being a N-dimensional, each dimension both corresponds to the RSS value an of signal emitting-source.
Step S102, the current Wi-Fi finger print data is handled using preset floor disaggregated model, obtains institute
State terminal device current floor locating in the specified building.
Preferably, as shown in Fig. 2, the floor disaggregated model can be made of self-encoding encoder and classifier.
Wherein, self-encoding encoder (Autoencoder) is a kind of training method of deep learning, its essence is a kind of in fact
The compression dimension-reduction algorithm of data, wherein the compression and decompression function of data is that data are relevant, damages, is automatic from sample
Learn and pass through a process of neural fusion.
As shown in figure 3, the model of self-encoding encoder includes two processes: coding and decoding, the main function of cataloged procedure are
High-dimensional vector matrix is passed through by encoder and mutually projects the matrix for being reduced to a low dimensional, but main input number
According to characteristic feature still maintain, only give up to fall some inessential characteristic informations, be equivalent to a signal filter;Decoding
Process is the matrix data that the vector matrix of low-dimensional is restored to original dimension by decoder by characteristic equation back projection.It compiles
The input of code device is Wi-Fi finger print data (vector form), and the output of decoder is that reconstruct and input keep identical dimensional
Vector (is compared, the numerical value of principal component part is identical, and other numerical value are zeroed out) with input, and HL represents hidden layer, in bracket
Number represents the quantity of neuron in layer.
Classifier can be neural network model as shown in Figure 4, and neural network model is one and utilizes multiple hidden layers
With nonlinear activation function tectonic model, continuous weighted sum iteration is carried out to multiple input datas, to reach single output
Machine learning algorithm.The model includes an input layer, multiple hidden layers and a single output layer, when neural network mould
It is classification, the characteristic value that output is predicted when neural network returns for one that type, which does output when classifying,.
Before being handled using the floor disaggregated model the current Wi-Fi finger print data, need using institute
The Wi-Fi fingerprint database for stating specified building is trained the floor disaggregated model.
The Wi-Fi fingerprint database is (known in each predetermined position of the specified building in designated period of time
Its floor and specific three-dimensional coordinate) acquisition Wi-Fi finger print data set.It is said below with a specific example
Bright, specifying building is a 5 floor teaching building, which deploys 992 signal emitting-sources in total, and the data of acquisition include two groups
Wi-Fi finger print data.Wherein one group of data is used for the training of floor disaggregated model, and another group of data are for floor disaggregated model
Test, contains 697 trained Wi-Fi finger print datas and 3951 test Wi-Fi finger print datas in total, then used herein to arrive
There are mainly four types of data:
(1) training Wi-Fi finger print data: one 697 × 992 matrix;
(2) training coordinate (three-dimensional coordinate): one 697 × 3 matrix;
(3) Wi-Fi finger print data: one 3951 × 992 matrix is tested;
(4) coordinate (three-dimensional coordinate) is tested: one 3951 × 3 matrix.
After constructing the good Wi-Fi fingerprint database, that is, it can be used the Wi-Fi fingerprint database to the floor
Disaggregated model is iterated training, and in the error namely predicted value for after training, calculating the floor disaggregated model every time and
Error between expected standard value, if the error is greater than or equal to preset error threshold, according to the error to institute
The parameter for stating floor disaggregated model is adjusted, and is continued to execute and be iterated trained process to the floor disaggregated model,
The error that training obtains after each adjusting parameter all can constantly reduce, and repeat the process until error drops to acceptable threshold
Value terminates to be iterated trained process to the floor disaggregated model hereinafter, if the error is less than the error threshold,
Obtain to put into the floor disaggregated model of actual use.
After the completion of training, that is, the floor disaggregated model can be used to handle the current Wi-Fi finger print data,
Specifically, dimensionality reduction and Principle component extraction are carried out to the current Wi-Fi finger print data using the self-encoding encoder first, obtained certainly
Then encoder output data classify to the self-encoding encoder output data using the classifier, determine the terminal
Equipment current floor locating in the specified building.
Due to containing a large amount of no signal data in Wi-Fi finger print data, (Wi- only is detected containing a small amount of useful information
The data of Fi signal), therefore input data first imported into encoder and carries out dimensionality reduction and Principle component extraction by the model, deletion portion
Point garbage reduces amount of input information simultaneously, so that the calculation amount of neural network model below is reduced, it then will be after coding
Data carry out classification processing as the input of neural network model, improve classification results precision.
Step S103, it is chosen from the Wi-Fi fingerprint database of the specified building corresponding with the current floor
Wi-Fi finger print data word bank.
In the present embodiment, the Wi-Fi fingerprint database can be divided into multiple word banks, each word bank respectively corresponds
In a floor of the specified building, for example, can by 1 building acquire all Wi-Fi finger print datas as with 1 building
Corresponding Wi-Fi finger print data word bank, by all Wi-Fi finger print datas acquired at 2 buildings as Wi-Fi corresponding with 2 buildings
Finger print data word bank, and so on.
Step S104, the terminal is calculated according to the current Wi-Fi finger print data and the Wi-Fi finger print data word bank
Positioning coordinate of the equipment in the specified building.
Firstly, calculate separately it is each referring between Wi-Fi finger print data and the current Wi-Fi finger print data it is European away from
From.
The reference Wi-Fi finger print data is the Wi-Fi finger print data in the Wi-Fi finger print data word bank.Herein will
The vector form of the current Wi-Fi finger print data is denoted as: (r1,r2,r3,...,rn,...,rN), wherein n is signal emitting-source
Serial number, 1≤n≤N, rnRSS value for n-th of signal emitting-source in the current Wi-Fi finger print data similarly can
Any vector form referring to Wi-Fi finger print data to be denoted as: (ρ1,ρ2,ρ3,...,ρn,...,ρN), wherein ρnFor the ginseng
According to the RSS value of n-th of signal emitting-source in Wi-Fi finger print data, then can calculate according to the following formula between the two it is European away from
From:
Wherein, D is Euclidean distance between the two.
Then, from the Wi-Fi finger print data word bank choose and the current Wi-Fi finger print data between it is European away from
From the smallest K Wi-Fi finger print data as preferred Wi-Fi finger print data.
Wherein, K is the integer greater than 1, and specific value is configured according to the actual situation, for example, can be arranged
For 3,5,10 or other values etc., the present embodiment is not especially limited it.
Finally, calculating positioning coordinate of the terminal device in the specified building according to the following formula:
Wherein, i is the serial number of the preferred Wi-Fi finger print data, 1≤i≤K, XiFor with i-th of preferred Wi-Fi fingerprint
The corresponding coordinate of data, it should be noted that this is a three-dimensional coordinate, that is, is had on x, tri- change in coordinate axis direction of y, z
Value, WiFor weighting coefficient corresponding with i-th of preferred Wi-Fi finger print data, can calculate according to the following formula and each preferred Wi-
The corresponding weighting coefficient of Fi finger print data:diFor i-th of preferred Wi-Fi finger print data and the current Wi-
Euclidean distance between Fi finger print data, Y are positioning coordinate of the terminal device in the specified building.
It should be noted that K preferably Wi-Fi finger print data respective coordinates can also be taken in a kind of optional scheme
Positioning coordinate of the average value as the terminal device in the specified building, still, this operation being averaged
Certain error can be brought, therefore, has brought weighting coefficient into the present embodiment for the K of selection preferably Wi-Fi finger print datas,
Enable and each obtains bigger weight apart from closer point.The form of the weight and inverse function (inverse) positive of distance
It closes, therefore bigger apart from the weight that smaller point obtains, the weight that the bigger point of distance obtains is also relatively small, so as to
To more accurate positioning result.
In conclusion the embodiment of the present invention obtains the current Wi-Fi fingerprint number that terminal device acquires in specified building
According to;The current Wi-Fi finger print data is handled using preset floor disaggregated model, obtains the terminal device in institute
State current floor locating in specified building;It chooses from the Wi-Fi fingerprint database of the specified building and works as with described
The corresponding Wi-Fi finger print data word bank of preceding floor;According to the current Wi-Fi finger print data and Wi-Fi finger print data
Library calculates positioning coordinate of the terminal device in the specified building.It through the embodiment of the present invention, will be entire indoor fixed
Position procedure decomposition is completed floor by preset floor disaggregated model first and is determined for two processes of floor location and coordinate setting
The process of position on this basis, is further carried out accurately coordinate setting to greatly reduce orientation range, compared to
Traditional direct mode that coordinate setting is carried out in whole building, greatly reduces calculation amount, large-scale indoor fixed
It is more practical in position.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
Corresponding to a kind of indoor orientation method described in foregoing embodiments, Fig. 5 shows provided in an embodiment of the present invention one
One embodiment structure chart of kind indoor positioning device.
In the present embodiment, a kind of indoor positioning device may include:
Fingerprint data collection module 501, the current Wi-Fi fingerprint acquired in specified building for obtaining terminal device
Data;
Floor location module 502, for being carried out using preset floor disaggregated model to the current Wi-Fi finger print data
Processing obtains terminal device current floor locating in the specified building;
Database chooses module 503, works as choosing from the Wi-Fi fingerprint database of the specified building with described
The corresponding Wi-Fi finger print data word bank of preceding floor;
Coordinate calculation module 504 is positioned, for according to the current Wi-Fi finger print data and the Wi-Fi finger print data
Word bank calculates positioning coordinate of the terminal device in the specified building.
Further, the floor location module may include:
Coding unit, for carrying out dimensionality reduction and principal component to the current Wi-Fi finger print data using the self-encoding encoder
It extracts, obtains self-encoding encoder output data;
Taxon determines the end for classifying using the classifier to the self-encoding encoder output data
End equipment current floor locating in the specified building.
Further, the positioning coordinate calculation module may include:
Metrics calculation unit, for calculating separately each reference Wi-Fi finger print data and the current Wi-Fi finger print data
Between Euclidean distance, it is described referring to Wi-Fi finger print data be the Wi-Fi finger print data word bank in Wi-Fi finger print data;
Data selecting unit, for being chosen and the current Wi-Fi finger print data from the Wi-Fi finger print data word bank
Between the smallest K Wi-Fi finger print data of Euclidean distance as preferred Wi-Fi finger print data, wherein K be it is whole greater than 1
Number;
Coordinate calculating unit is positioned, for calculating positioning of the terminal device in the specified building according to the following formula
Coordinate:
Wherein, i is the serial number of the preferred Wi-Fi finger print data, 1≤i≤K, XiFor with i-th of preferred Wi-Fi fingerprint
The corresponding coordinate of data, WiFor weighting coefficient corresponding with i-th of preferred Wi-Fi finger print data, Y is the terminal device in institute
State the positioning coordinate in specified building.
Further, the positioning coordinate calculation module can also include:
Coefficient calculation unit, for calculating weighting system corresponding with each preferred Wi-Fi finger print data according to the following formula
Number:
Wherein, diFor the Euclidean distance between i-th of preferred Wi-Fi finger print data and the current Wi-Fi finger print data.
Further, the indoor positioning device can also include:
Model training unit, for being iterated instruction to the floor disaggregated model using the Wi-Fi fingerprint database
Practice, and in the error for after training, calculating the floor disaggregated model every time;
Parameter adjustment unit, if being greater than or equal to preset error threshold for the error, according to the error pair
The parameter of the floor disaggregated model is adjusted, and is continued to execute and be iterated trained mistake to the floor disaggregated model
Journey;
Terminate training unit, if being less than the error threshold for the error, terminates to the floor disaggregated model
It is iterated trained process.
It is apparent to those skilled in the art that for convenience and simplicity of description, the device of foregoing description,
The specific work process of module and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in detail or remembers in some embodiment
The part of load may refer to the associated description of other embodiments.
The schematic block diagram that Fig. 6 shows a kind of terminal device provided in an embodiment of the present invention is only shown for ease of description
Part related to the embodiment of the present invention.
As shown in fig. 6, the indoor positioning terminal device 6 of the embodiment includes: processor 60, memory 61 and is stored in
In the memory 61 and the computer program 62 that can be run on the processor 60.The processor 60 executes the calculating
Realize the step in above-mentioned each indoor orientation method embodiment when machine program 62, such as step S101 shown in FIG. 1 is to step
S104.Alternatively, the processor 60 realizes each module/unit in above-mentioned each Installation practice when executing the computer program 62
Function, such as module 501 shown in Fig. 5 is to the function of module 504.
Illustratively, the computer program 62 can be divided into one or more module/units, it is one or
Multiple module/units are stored in the memory 61, and are executed by the processor 60, to complete the present invention.Described one
A or multiple module/units can be the series of computation machine program instruction section that can complete specific function, which is used for
Implementation procedure of the computer program 62 in the indoor positioning terminal device 6 is described.For example, the computer program 62
Calling module, adjustment module, shooting module can be divided into.
The indoor positioning terminal device 6 can be mobile phone, tablet computer, smartwatch/bracelet, intelligent glasses, on table
Type computer, notebook and cloud server etc. calculate equipment.It will be understood by those skilled in the art that Fig. 6 is only indoor fixed
The example of position terminal device 6, does not constitute the restriction to indoor positioning terminal device 6, may include more more or less than illustrating
Component, perhaps combine certain components or different components, such as the indoor positioning terminal device 6 can also include defeated
Enter output equipment, network access equipment, bus etc..
The processor 60 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng.
The memory 61 can be the internal storage unit of the indoor positioning terminal device 6, such as indoor positioning end
The hard disk or memory of end equipment 6.The memory 61 is also possible to the External memory equipment of the indoor positioning terminal device 6,
Such as the plug-in type hard disk being equipped on the indoor positioning terminal device 6, intelligent memory card (Smart Media Card, SMC),
Secure digital (Secure Digital, SD) card, flash card (Flash Card) etc..Further, the memory 61 may be used also
With the internal storage unit both including the indoor positioning terminal device 6 or including External memory equipment.The memory 61 is used
Other programs and data needed for storing the computer program and the indoor positioning terminal device 6.The memory
61 can be also used for temporarily storing the data that has exported or will export.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing
The all or part of function of description.Each functional unit in embodiment, module can integrate in one processing unit, can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units, it is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.In addition, each function list
Member, the specific name of module are also only for convenience of distinguishing each other, the protection scope being not intended to limit this application.Above system
The specific work process of middle unit, module, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in detail or remembers in some embodiment
The part of load may refer to the associated description of other embodiments.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In embodiment provided by the present invention, it should be understood that disclosed device/terminal device and method, it can be with
It realizes by another way.For example, device described above/terminal device embodiment is only schematical, for example, institute
The division of module or unit is stated, only a kind of logical function partition, there may be another division manner in actual implementation, such as
Multiple units or components can be combined or can be integrated into another system, or some features can be ignored or not executed.Separately
A bit, shown or discussed mutual coupling or direct-coupling or communication connection can be through some interfaces, device
Or the INDIRECT COUPLING or communication connection of unit, it can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can store in a computer readable storage medium.Based on this understanding, the present invention realizes above-mentioned implementation
All or part of the process in example method, can also instruct relevant hardware to complete, the meter by computer program
Calculation machine program can be stored in a computer readable storage medium, the computer program when being executed by processor, it can be achieved that on
The step of stating each embodiment of the method.Wherein, the computer program includes computer program code, the computer program generation
Code can be source code form, object identification code form, executable file or certain intermediate forms etc..The computer-readable medium
It may include: any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic that can carry the computer program code
Dish, CD, computer storage, read-only memory (ROM, Read-Only Memory), random access memory (RAM,
Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that described
The content that computer-readable medium includes can carry out increasing appropriate according to the requirement made laws in jurisdiction with patent practice
Subtract, such as does not include electric carrier signal and electricity according to legislation and patent practice, computer-readable medium in certain jurisdictions
Believe signal.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations;Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features;And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of indoor orientation method characterized by comprising
Obtain the current Wi-Fi finger print data that terminal device acquires in specified building;
The current Wi-Fi finger print data is handled using preset floor disaggregated model, the terminal device is obtained and exists
Locating current floor in the specified building;
Wi-Fi finger print data corresponding with the current floor is chosen from the Wi-Fi fingerprint database of the specified building
Word bank;
The terminal device is calculated in the finger according to the current Wi-Fi finger print data and the Wi-Fi finger print data word bank
Determine the positioning coordinate in building.
2. indoor orientation method according to claim 1, which is characterized in that the floor disaggregated model by self-encoding encoder and
Classifier composition, it is described that the current Wi-Fi finger print data is handled using preset floor disaggregated model, it obtains described
Terminal device current floor locating in the specified building includes:
Dimensionality reduction and Principle component extraction are carried out to the current Wi-Fi finger print data using the self-encoding encoder, obtain self-encoding encoder
Output data;
Classified using the classifier to the self-encoding encoder output data, determines that the terminal device is built in described specify
Build current floor locating in object.
3. indoor orientation method according to claim 1, which is characterized in that described according to the current Wi-Fi fingerprint number
Include: according to positioning coordinate of the terminal device in the specified building is calculated with the Wi-Fi finger print data word bank
Calculate separately each Euclidean distance referring between Wi-Fi finger print data and the current Wi-Fi finger print data, the ginseng
According to the Wi-Fi finger print data that Wi-Fi finger print data is in the Wi-Fi finger print data word bank;
From the smallest K of Euclidean distance chosen in the Wi-Fi finger print data word bank between the current Wi-Fi finger print data
A Wi-Fi finger print data is as preferred Wi-Fi finger print data, wherein K is the integer greater than 1;
Positioning coordinate of the terminal device in the specified building is calculated according to the following formula:
Wherein, i is the serial number of the preferred Wi-Fi finger print data, 1≤i≤K, XiFor with i-th of preferred Wi-Fi finger print data pair
The coordinate answered, WiFor weighting coefficient corresponding with i-th of preferred Wi-Fi finger print data, Y is the terminal device described specified
Positioning coordinate in building.
4. indoor orientation method according to claim 3, which is characterized in that the setting up procedure of the weighting coefficient includes:
Weighting coefficient corresponding with each preferred Wi-Fi finger print data is calculated according to the following formula:
Wherein, diFor the Euclidean distance between i-th of preferred Wi-Fi finger print data and the current Wi-Fi finger print data.
5. indoor orientation method according to any one of claim 1 to 4, which is characterized in that using preset floor
Before disaggregated model handles the current Wi-Fi finger print data, further includes:
Training is iterated to the floor disaggregated model using the Wi-Fi fingerprint database, and after training, is being counted every time
Calculate the error of the floor disaggregated model;
If the error is greater than or equal to preset error threshold, according to the error to the parameter of the floor disaggregated model
It is adjusted, and continues to execute and trained process is iterated to the floor disaggregated model;
If the error is less than the error threshold, terminate to be iterated trained process to the floor disaggregated model.
6. a kind of indoor positioning device characterized by comprising
Fingerprint data collection module, the current Wi-Fi finger print data acquired in specified building for obtaining terminal device;
Floor location module is obtained for being handled using preset floor disaggregated model the current Wi-Fi finger print data
The current floor locating in the specified building to the terminal device;
Database chooses module, for choosing and the current floor from the Wi-Fi fingerprint database of the specified building
Corresponding Wi-Fi finger print data word bank;
Coordinate calculation module is positioned, for calculating according to the current Wi-Fi finger print data and the Wi-Fi finger print data word bank
Positioning coordinate of the terminal device in the specified building.
7. indoor positioning device according to claim 6, which is characterized in that the floor disaggregated model by self-encoding encoder and
Classifier composition, the floor location module include:
Coding unit, for carrying out dimensionality reduction and Principle component extraction to the current Wi-Fi finger print data using the self-encoding encoder,
Obtain self-encoding encoder output data;
Taxon determines that the terminal is set for classifying using the classifier to the self-encoding encoder output data
Standby locating current floor in the specified building.
8. indoor positioning device according to claim 6 or 7, which is characterized in that the positioning coordinate calculation module includes:
Metrics calculation unit, it is each referring between Wi-Fi finger print data and the current Wi-Fi finger print data for calculating separately
Euclidean distance, it is described referring to Wi-Fi finger print data be the Wi-Fi finger print data word bank in Wi-Fi finger print data;
Data selecting unit, for being chosen between the current Wi-Fi finger print data from the Wi-Fi finger print data word bank
The smallest K Wi-Fi finger print data of Euclidean distance as preferred Wi-Fi finger print data, wherein K is integer greater than 1;
Coordinate calculating unit is positioned, is sat for calculating positioning of the terminal device in the specified building according to the following formula
Mark:
Wherein, i is the serial number of the preferred Wi-Fi finger print data, 1≤i≤K, XiFor with i-th of preferred Wi-Fi finger print data pair
The coordinate answered, WiFor weighting coefficient corresponding with i-th of preferred Wi-Fi finger print data, Y is the terminal device described specified
Positioning coordinate in building.
9. a kind of computer readable storage medium, the computer-readable recording medium storage has computer-readable instruction, special
Sign is, realizes that the interior as described in any one of claims 1 to 5 is fixed when the computer-readable instruction is executed by processor
The step of position method.
10. a kind of terminal device, including memory, processor and storage are in the memory and can be on the processor
The computer-readable instruction of operation, which is characterized in that the processor realizes such as right when executing the computer-readable instruction
It is required that the step of indoor orientation method described in any one of 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910289268.4A CN110231593A (en) | 2019-04-11 | 2019-04-11 | Indoor orientation method, device, computer readable storage medium and terminal device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910289268.4A CN110231593A (en) | 2019-04-11 | 2019-04-11 | Indoor orientation method, device, computer readable storage medium and terminal device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110231593A true CN110231593A (en) | 2019-09-13 |
Family
ID=67860846
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910289268.4A Pending CN110231593A (en) | 2019-04-11 | 2019-04-11 | Indoor orientation method, device, computer readable storage medium and terminal device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110231593A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112987064A (en) * | 2021-02-09 | 2021-06-18 | 北京百度网讯科技有限公司 | Building positioning method, device, equipment, storage medium and terminal equipment |
CN113015117A (en) * | 2021-02-04 | 2021-06-22 | 北京百度网讯科技有限公司 | User positioning method and device, electronic equipment and storage medium |
CN114208221A (en) * | 2020-07-28 | 2022-03-18 | 蜂图志科技控股有限公司 | Positioning method, positioning device, mobile terminal and storage medium |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102791025A (en) * | 2011-05-20 | 2012-11-21 | 盛乐信息技术(上海)有限公司 | Wireless fidelity (WIFI) based layered positioning system and implementing method |
CN103096466A (en) * | 2013-01-17 | 2013-05-08 | 哈尔滨工业大学 | Wireless fidelity (Wi-Fi) indoor positioning method |
US20140301490A1 (en) * | 2011-07-01 | 2014-10-09 | Certusview Technologies, Llc | Ingress-mitigated rf cable plants and ingress mitigation methods for same |
CN104602342A (en) * | 2015-01-13 | 2015-05-06 | 浙江大学 | IBeacon device based efficient indoor positioning method |
CN107018495A (en) * | 2017-03-28 | 2017-08-04 | 徐康庭 | A kind of indoor user Hierarchical Location method and system based on signaling data |
US20170371024A1 (en) * | 2014-12-04 | 2017-12-28 | Here Global B.V. | Supporting a collaborative collection of data |
CN107896362A (en) * | 2017-10-25 | 2018-04-10 | 电子科技大学 | A kind of WIFI location fingerprints localization method and system based on deep learning |
CN108414970A (en) * | 2018-03-09 | 2018-08-17 | 郑州大学 | Indoor orientation method |
CN108449712A (en) * | 2018-02-07 | 2018-08-24 | 大连理工大学 | A kind of building floor based on Wi-Fi signal finger print information determines method |
CN108810799A (en) * | 2018-05-28 | 2018-11-13 | 湖南大学 | A kind of more floor indoor orientation methods and system based on linear discriminant analysis |
CN109041206A (en) * | 2018-07-03 | 2018-12-18 | 东南大学 | A kind of indoor positioning floor method of discrimination based on improvement fuzzy kernel clustering |
CN109040957A (en) * | 2018-08-14 | 2018-12-18 | 广东小天才科技有限公司 | A kind of indoor orientation method and device based on WIFI |
CN109151995A (en) * | 2018-09-04 | 2019-01-04 | 电子科技大学 | A kind of deep learning recurrence fusion and positioning method based on signal strength |
-
2019
- 2019-04-11 CN CN201910289268.4A patent/CN110231593A/en active Pending
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102791025A (en) * | 2011-05-20 | 2012-11-21 | 盛乐信息技术(上海)有限公司 | Wireless fidelity (WIFI) based layered positioning system and implementing method |
US20140301490A1 (en) * | 2011-07-01 | 2014-10-09 | Certusview Technologies, Llc | Ingress-mitigated rf cable plants and ingress mitigation methods for same |
CN103096466A (en) * | 2013-01-17 | 2013-05-08 | 哈尔滨工业大学 | Wireless fidelity (Wi-Fi) indoor positioning method |
US20170371024A1 (en) * | 2014-12-04 | 2017-12-28 | Here Global B.V. | Supporting a collaborative collection of data |
CN104602342A (en) * | 2015-01-13 | 2015-05-06 | 浙江大学 | IBeacon device based efficient indoor positioning method |
CN107018495A (en) * | 2017-03-28 | 2017-08-04 | 徐康庭 | A kind of indoor user Hierarchical Location method and system based on signaling data |
CN107896362A (en) * | 2017-10-25 | 2018-04-10 | 电子科技大学 | A kind of WIFI location fingerprints localization method and system based on deep learning |
CN108449712A (en) * | 2018-02-07 | 2018-08-24 | 大连理工大学 | A kind of building floor based on Wi-Fi signal finger print information determines method |
CN108414970A (en) * | 2018-03-09 | 2018-08-17 | 郑州大学 | Indoor orientation method |
CN108810799A (en) * | 2018-05-28 | 2018-11-13 | 湖南大学 | A kind of more floor indoor orientation methods and system based on linear discriminant analysis |
CN109041206A (en) * | 2018-07-03 | 2018-12-18 | 东南大学 | A kind of indoor positioning floor method of discrimination based on improvement fuzzy kernel clustering |
CN109040957A (en) * | 2018-08-14 | 2018-12-18 | 广东小天才科技有限公司 | A kind of indoor orientation method and device based on WIFI |
CN109151995A (en) * | 2018-09-04 | 2019-01-04 | 电子科技大学 | A kind of deep learning recurrence fusion and positioning method based on signal strength |
Non-Patent Citations (7)
Title |
---|
KYEONG SOO KIM,ET AL: "Large-Scale Location-Aware Services in Access:Hierarchical Building/Floor Classification and Location Estimation using Wi-Fi Fingerprinting Based on Deep Neural Networks", 《ARXIV:1611.02049V2》 * |
MICHAŁ NOWICKI,ET AL: "Low-effort place recognition with WiFi fingerprints using deep learning", 《 SPRINGER》 * |
梁冀等: "基于深度神经网络的WiFi室内定位系统设计", 《内蒙古大学学报(自然科学版)》 * |
王攀等: "《优化与控制中的软计算方法研究》", 31 January 2017 * |
王霖娜: "基于WiFi指纹定位系统的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
程光等编著: "《人工智能原理及应用》", 31 December 2018, 东南大学出版社 * |
陈敏编著: "《认知计算导论》", 31 May 2017, 华中科技大学出版社 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114208221A (en) * | 2020-07-28 | 2022-03-18 | 蜂图志科技控股有限公司 | Positioning method, positioning device, mobile terminal and storage medium |
CN113015117A (en) * | 2021-02-04 | 2021-06-22 | 北京百度网讯科技有限公司 | User positioning method and device, electronic equipment and storage medium |
CN113015117B (en) * | 2021-02-04 | 2023-07-21 | 北京百度网讯科技有限公司 | User positioning method and device, electronic equipment and storage medium |
CN112987064A (en) * | 2021-02-09 | 2021-06-18 | 北京百度网讯科技有限公司 | Building positioning method, device, equipment, storage medium and terminal equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106485353B (en) | Air pollutant concentration forecasting procedure and system | |
CN110231593A (en) | Indoor orientation method, device, computer readable storage medium and terminal device | |
CN109829399A (en) | A kind of vehicle mounted road scene point cloud automatic classification method based on deep learning | |
CN103139907B (en) | A kind of indoor wireless positioning method utilizing fingerprint technique | |
CN109300310A (en) | A kind of vehicle flowrate prediction technique and device | |
CN107396322A (en) | Indoor orientation method based on route matching Yu coding and decoding Recognition with Recurrent Neural Network | |
CN110213003A (en) | A kind of wireless channel large-scale fading modeling method and device | |
CN110533389A (en) | The determination method and device of Project Cost | |
CN102136073A (en) | Learning apparatus, method, recognizing apparatus method and information processing system | |
CN113297174B (en) | Land utilization change simulation method based on deep learning | |
CN112218330A (en) | Positioning method and communication device | |
CN114493052B (en) | Multi-model fusion self-adaptive new energy power prediction method and system | |
CN102646164A (en) | Land use change modeling method and system implemented in combination with spatial filtering | |
CN110232584A (en) | Parking lot site selecting method, device, computer readable storage medium and terminal device | |
CN105868906A (en) | Optimized method for analyzing maturity of regional development | |
CN109993753A (en) | The dividing method and device of urban function region in remote sensing image | |
CN112001435A (en) | Method and system for constructing training sample set in regional landslide early warning and storage medium | |
CN108875936A (en) | The method for solving the minimum distance in three-dimensional space between any two polyhedron | |
CN107633421A (en) | A kind of processing method and processing device of market prediction data | |
CN104105049A (en) | Room impulse response function measuring method allowing using quantity of microphones to be reduced | |
CN110457469A (en) | Information classification approach, device based on shot and long term memory network, computer equipment | |
CN106658538B (en) | Mobile phone base station signal coverage area simulation method based on Thiessen polygon | |
CN109242141A (en) | A kind of prediction technique and device of commodity stocks quantity | |
CN110211227A (en) | A kind of method for processing three-dimensional scene data, device and terminal device | |
CN109889981A (en) | A kind of localization method and system based on two sorting techniques |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190913 |