CN110225453A - Mobile terminal locating method, device, electronic equipment and storage medium - Google Patents
Mobile terminal locating method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN110225453A CN110225453A CN201910551856.0A CN201910551856A CN110225453A CN 110225453 A CN110225453 A CN 110225453A CN 201910551856 A CN201910551856 A CN 201910551856A CN 110225453 A CN110225453 A CN 110225453A
- Authority
- CN
- China
- Prior art keywords
- mobile terminal
- grid
- probability distribution
- base station
- region
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/025—Services making use of location information using location based information parameters
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The disclosure provides a kind of mobile terminal locating method, device, electronic equipment and storage medium, is related to field of communication technology.The mobile terminal locating method that the disclosure provides, device, electronic equipment and storage medium, it is multiple grids by the region division that will include multiple base stations, and obtain the position of the be located at grid in the region base station Nei Ge, behind the position for obtaining the be located at grid in the region base station Nei Ge, the location model obtained based on preparatory training, the characteristic of each mobile terminal and each base station in the region is calculated, obtain the probability distribution that each mobile terminal is located at each grid, and then obtain the probability distribution of the position of each mobile terminal in the area, realize the accurate positionin of mobile terminal.
Description
Technical field
This disclosure relates to which field of communication technology, sets in particular to a kind of mobile terminal locating method, device, electronics
Standby and storage medium.
Background technique
Running fix refers to through specific location technology the location information for obtaining mobile terminal.Currently, mobile terminal
Localization method is positioned based on algorithm of support vector machine mostly, and this method accuracy is lower.
Summary of the invention
Based on the studies above, the disclosure provides a kind of mobile terminal locating method, device, electronic equipment and storage medium.
The mobile terminal locating method that the disclosure provides, comprising:
It will be multiple grids including the region division of multiple base stations, and obtain each be located at grid in base station in the region
Position.
Based on the location model that preparatory training obtains, to the characteristic of each mobile terminal and each base station in the region
According to being calculated, the probability distribution that each mobile terminal is located at each grid is obtained, to obtain each mobile terminal
The probability distribution of position in the area.
Further, the step of position for obtaining each mobile terminal probability distribution in the area includes:
Obtain the longitude and latitude at each the grid center and boundary, and according to the longitude and latitude at each the grid center and boundary,
The probability distribution that each mobile terminal is located at each grid is mapped to the probability that each mobile terminal is located at longitude and latitude
Distribution, obtains the probability distribution of the position of each mobile terminal in the area.
Further, the location model is obtained by following steps training:
It is multiple grids by region division, and label is carried out to each grid, with each grid marked as classification logotype,
Training dataset is constructed with the characteristic of each mobile terminal and each base station.
The training dataset is input in neural network model and is trained, based on default loss function, by anti-
It is adjusted to parameter of the propagation algorithm to the neural network, until the output of the default loss function is less than default threshold
Value, obtains the location model.
Further, the neural network model includes output layer, and the output member quantity of the output layer is the grid
Quantity.
The disclosure provides a kind of mobile terminal location device, and described device includes data read module and processing module.
Region division of the data read module for that will include multiple base stations is multiple grids, is obtained each in the region
The position of the be located at grid in base station.
The processing module is used for the location model obtained based on preparatory training, to each mobile terminal in the region and respectively
The characteristic of the base station is calculated, and the probability distribution that each mobile terminal is located at each grid is obtained, to obtain
The probability distribution of the position of each mobile terminal in the area.
Further, the processing module is used for:
Obtain the longitude and latitude at each the grid center and boundary, and according to the longitude and latitude at each the grid center and boundary,
The probability distribution that each mobile terminal is located at each grid is mapped to the probability that each mobile terminal is located at longitude and latitude
Distribution, obtains the probability distribution of the position of each mobile terminal in the area.
Further, the mobile terminal location device further includes building module and training module.
The building module is used to region division be multiple grids, and carries out label to each grid, with each grid
Marked as classification logotype, training dataset is constructed with the characteristic of each mobile terminal and each base station.
The training module is trained for the training dataset to be input in neural network model, based on default
Loss function is adjusted by parameter of the back-propagation algorithm to the neural network, until the default loss function
Output is less than preset threshold, obtains the location model.
Further, the first quantity of the output of the output layer of the neural network model is the quantity of the grid.
The disclosure provides a kind of electronic equipment, and the electronic equipment includes memory, processor and movement described above
Terminal positioning device, the mobile terminal location device are located at the memory and are held including one or more by the processor
Capable software function module.
The disclosure provides a kind of storage medium, is stored thereon with computer program, and the computer program is real when being executed
Step in existing mobile terminal locating method described above.
Mobile terminal locating method, device, electronic equipment and the storage medium that the disclosure provides, by that will include multiple bases
The region division stood is multiple grids, and obtains the position of the be located at grid in the region base station Nei Ge, each in the region obtaining
Behind the position of the be located at grid in base station, based on the location model that preparatory training obtains, to each mobile terminal in the region and respectively
The characteristic of base station is calculated, and obtains the probability distribution that each mobile terminal is located at each grid, and then obtain each mobile terminal
Position probability distribution in the area, realize the accurate positionin of mobile terminal.
To enable the above objects, features, and advantages of the disclosure to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
In order to illustrate more clearly of the technical solution of the disclosure, letter will be made to attached drawing needed in the embodiment below
It singly introduces, it should be understood that the following drawings illustrates only some embodiments of the disclosure, therefore is not construed as to range
It limits, it for those of ordinary skill in the art, without creative efforts, can also be according to these attached drawings
Obtain other relevant attached drawings.
Fig. 1 is a kind of block diagram of electronic equipment provided by the disclosure.
Fig. 2 is a kind of flow diagram of mobile terminal locating method provided by the disclosure.
Fig. 3 is another flow diagram of mobile terminal locating method provided by the disclosure.
Fig. 4 is a kind of structural schematic diagram of neural network model provided by the disclosure.
Fig. 5 is a kind of block diagram of mobile terminal location device provided by the disclosure.
Icon: 100- electronic equipment;10- mobile terminal location device;11- data read module;12- processing module;13-
Construct module;14- training module;20- memory;30- processor;40- communication unit.
Specific embodiment
Below in conjunction with attached drawing in the disclosure, the technical solution in the disclosure is clearly and completely described, it is clear that
Described embodiment is only disclosure a part of the embodiment, instead of all the embodiments.Usually retouched in attached drawing here
The component for the disclosure stated and shown can be arranged and be designed with a variety of different configurations.Therefore, below to mentioning in the accompanying drawings
The detailed description of the embodiment of the disclosure of confession is not intended to limit claimed the scope of the present disclosure, but is merely representative of this
Disclosed selected embodiment.Based on embodiment of the disclosure, those skilled in the art are in the premise for not making creative work
Under every other embodiment obtained, belong to the disclosure protection range.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.
Running fix refers to through specific location technology the location information for obtaining mobile terminal.Currently, mobile terminal
Localization method is positioned based on algorithm of support vector machine mostly.
Support vector machines (Support Vector Machine, SVM) algorithm is a kind of two sorting algorithms, in the prior art
Multivariate classification is carried out using one-to-one (one versus one) method, is needed to every two grid one classifier of training.Cause
This needs to train n (n-1)/2 support vector machine classifier for the region of n grid of division.If the area of localization region
Increase, the quantity of grid will be caused to increase, then need trained classifier number will be with n2Mode increase.This method needs
Consuming a large amount of computing resource could complete to position.
In addition, in the prior art, each classifier is only effective to specific two grids, and each classifier is for output
Binary outcome has different definition standards.Because the accuracy of each classifier is unable to reach 100%, if being related to multiple points
Class device is positioned, then each classifier may generate contradictory outcome, at this moment, then needs to carry out two to the contradictory outcome of generation
Subseries judgement.For example, as shown in the table, ABCD is 4 adjacent grids, when some grid (such as A) is determined as 1, surrounding
Grid (including BCD) be determined as 0, it is believed that mobile terminal is within the boundary of grid A;When A and B are determined as 1, other are
0, it is believed that mobile terminal is on the boundary of A and B;When A and D are determined as 1 and B and C are determined as 0, movement is determined according to A and D
Terminal should be in A and D interface point, but B and C but give opposite judgement, and provides the classifier quantity determined on the contrary
It is equal.Its accuracy is to be improved.
A | B |
C | D |
In addition to this, algorithm of support vector machine can not calculate probability distribution of the mobile terminal in whole region, for
It is 1 that the optimal result that the position positioning of mobile terminal provides, which is target grid, and other grids are 0.This two sorting algorithm exists
It carries out having lost useful feature information during classification judgement, therefore, the binary outcome of output is difficult to carry out subsequent
Analysis.
Based on the studies above, the disclosure provides a kind of mobile terminal locating method, device, electronic equipment and storage medium,
To improve the above problem.
Fig. 1 is please referred to, the mobile terminal locating method that the disclosure provides is applied to electronic equipment 100, by the electricity
Sub- equipment 100 executes mobile terminal locating method provided by the disclosure.In the disclosure, the electronic equipment 100 can be,
But it is not limited to, PC (Personal Computer, PC), laptop, personal digital assistant (Personal
Digital Assistant, PDA) or the electronic equipment 100 with data-handling capacity such as server.
The electronic equipment 100 include mobile terminal location device 10 shown in FIG. 1, memory 20, processor 30 and
Communication unit 40, the memory 20, processor 30 and each element of communication unit 40 are directly or indirectly electric between each other
Property connection, to realize the transmission or interaction of data.For example, these elements mutually directly can by one or more communication bus or
Signal wire, which is realized, to be electrically connected.The mobile terminal location device 10 includes at least one can be with software or firmware (Firmware)
Form be stored in the software function module in the memory 20, the processor 30 is stored in memory 20 by operation
Software program and module, thereby executing various function application and data processing.
The memory 20 may be, but not limited to, random access memory (Random Access Memory, RAM),
Read-only memory (Read Only Memory, ROM), programmable read only memory (Programmable Read-Only
Memory, PROM), erasable read-only memory (Erasable Programmable Read-Only Memory, EPROM),
Electricallyerasable ROM (EEROM) (Electric Erasable Programmable Read-Only Memory, EEPROM) etc..
The processor 30 can be a kind of IC chip, the processing capacity with signal.The processor 30 can
To be general processor, including central processing unit (Central Processing Unit, CPU), network processing unit (Network
Processor, NP) etc..
The communication unit 40 is used for the communication established between the electronic equipment 100 and other external equipments by network
Connection, and carried out data transmission by the network.
Fig. 2 is please referred to, Fig. 2 is the flow diagram of mobile terminal locating method provided by the disclosure.It is right below
The detailed process of mobile terminal locating method shown in Fig. 2 is described in detail.
Step S10: it will be multiple grids including the region division of multiple base stations, and obtain each base station institute position in the region
In the position of grid.
Step S20: the location model obtained based on preparatory training, in the region each mobile terminal and each base station
Characteristic calculated, the probability distribution that each mobile terminal is located at each grid is obtained, to obtain each shifting
The probability distribution of the position of dynamic terminal in the area.
Wherein, the region positioned for needs, first divides the region, obtains multiple grids, and determines each
Then the longitude and latitude at grid center and boundary obtains in the region again, the position of each be located at grid in base station, with each base station
The position of be located at grid is specific position.Behind the position for determining the be located at grid in each base station, obtain in the region, it is each to move
The characteristic of dynamic terminal and each base station, the characteristic of each mobile terminal and base station is input to and trains what is obtained to determine in advance
It is calculated in bit model, obtains the probability distribution that each mobile terminal is located at each grid, and then can be according to each mobile terminal position
In the probability of each grid, the probability distribution of the position of each mobile terminal in the area is obtained.
In the disclosure, the characteristic of each mobile terminal and each base station be each mobile terminal in receiving area with each base
The interactive information stood, the communication distance etc. of position, base station and mobile terminal including base station.
Further, the step of position for obtaining each mobile terminal probability distribution in the area includes:
Obtain the longitude and latitude at each the grid center and boundary, and according to the longitude and latitude at each the grid center and boundary,
The probability distribution that each mobile terminal is located at each grid is mapped to the probability that each mobile terminal is located at longitude and latitude
Distribution, obtains the probability distribution of the position of each mobile terminal in the area.
Wherein, in the probability distribution for obtaining each mobile terminal and being located at each grid, according to the longitude and latitude at each grid center and boundary
The probability distribution mapping that each mobile terminal is located at each grid is become a probability distribution based on geospatial coordinates, i.e., by degree
Each mobile terminal is located at the probability distribution of longitude and latitude, and then the probability distribution of each mobile terminal in the area can be obtained.
The mobile terminal locating method that the disclosure provides, it is entire by inputting based on the location model that preparatory training obtains
The characteristic of each mobile terminal and each base station in region, to the characteristic of each mobile terminal and each base station in the region
It is calculated, by once determining, i.e., the probability distribution of the position of exportable each mobile terminal in the area is high-efficient, quasi-
True rate is high, and output probability distribution results are more conducive to the subsequent analysis based on mobile terminal location.
Further, Fig. 3 is please referred to, the location model is obtained by step S30 to step S40 training.
Step S30: being multiple grids by region division, and carry out label to each grid, with each grid marked as
Classification logotype constructs training dataset with the characteristic of each mobile terminal and each base station.
Wherein, region is divided into multiple grids, and label is carried out to each grid, for example, being divided into some region
Multiple grids, and after carrying out label to each grid, such as [A1, A2, A3 ..., An], then A1 corresponds to the 1st to grid label
A grid, A2 correspond to the 2nd grid, and A3 corresponds to the 3rd grid, and An corresponds to n-th of grid, and each grid is one corresponding
Class categories.
In the disclosure, the grid that each base station is located at is appointed as particular grid, the spy of each mobile terminal and each base station
Sign data are the characteristic that can be exchanged into the grid that each mobile terminal is located at and correspond to particular grid.In the disclosure, it instructs
To practice in data set, the grid that each mobile terminal is located at is known results, for example, when mobile terminal is located in grid A1, it is corresponding
The result is that [1,0 ..., 0], n result correspond to n grid, institute is resultful and is 1.
Step S40: the training dataset being input in neural network model and is trained, based on default loss letter
Number, is adjusted, until the output of the default loss function is small by parameter of the back-propagation algorithm to the neural network
In preset threshold, the location model is obtained.
Wherein, please refer to Fig. 4, neural network model include input layer, original output layer, softmax layers, it is final defeated
Layer and it is located in the middle hidden layer out.The disclosure is transformed original output layer, and the output member quantity of original output layer is
Grid quantity, for example, original output layer has n output member, n output member corresponds to n grid, i.e. n classification.
Input layer inputs training dataset, is calculated based on intermediate hidden layer, and original output layer exports PRELIMINARY RESULTS,
Then the softmax layers of output valve by original output layer is converted to probability, and then obtains the classification of the be located at grid of each movement, will
The classification and training data of obtained the be located at grid of each mobile terminal concentrate the classification of the be located at grid of each mobile terminal to carry out
Comparison is adjusted based on default loss function by parameter of the back-propagation algorithm to neural network model, until default damage
The output for losing function is less than preset threshold, obtains location model.Optionally, the default loss function is to intersect entropy loss letter
Number.
In the disclosure, the output valve of original output layer is converted to by probability based on following formula Softmax layers.
Wherein, yi, yjFor the output valve of original output layer, Si is the probability of i-th of classification, i.e., the probability of i-th grid, n
For the output member quantity of original output layer.
After Softmax layers calculate, the output result of final output layer is that each mobile terminal is located at the general of each grid
Rate.After the probability for obtaining being located at by each mobile terminal each grid, according to the latitude and longitude information of each grid, it can will be defeated
Result is mapped to the probability distribution that each mobile terminal is located at longitude and latitude out.
In the disclosure, it after location model training obtains, also needs to test location model, recall rate and standard can be passed through
True rate assesses location model.
The mobile terminal locating method that the disclosure provides constructs location model based on neural network, by inputting entire area
The characteristic of each mobile terminal in domain and each base station, to the characteristic of each mobile terminal and each base station in the region into
Row calculates, and by once determining, i.e., the probability distribution of the position of exportable each mobile terminal in the area is high-efficient and accurate
Rate is high.
On the basis of the above, Fig. 5 is please referred to, the disclosure provides a kind of mobile terminal location device 10, the movement
Terminal positioning device 10 includes data read module 11 and processing module 12.
Region division of the data read module 11 for that will include multiple base stations is multiple grids, is obtained in the region
The position of each be located at grid in the base station.
The processing module 12 is used for the location model obtained based on preparatory training, in the region each mobile terminal with
The characteristic of each base station is calculated, and the probability distribution that each mobile terminal is located at each grid is obtained, with
To the probability distribution of the position of each mobile terminal in the area.
Further, the processing module 12 is used for:
Obtain the longitude and latitude at each the grid center and boundary, and according to the longitude and latitude at each the grid center and boundary,
The probability distribution that each mobile terminal is located at each grid is mapped to the probability that each mobile terminal is located at longitude and latitude
Distribution, obtains the probability distribution of the position of each mobile terminal in the area.
Further, the mobile terminal location device 10 further includes building module 13 and training module 14.
The building module 13 is used to region division be multiple grids, and carries out label to each grid, with each grid
Lattice marked as classification logotype, training dataset is constructed with the characteristic of each mobile terminal and each base station.
The training module 14 is trained for the training dataset to be input in neural network model, based on pre-
If loss function, it is adjusted by parameter of the back-propagation algorithm to the neural network, until the default loss function
Output be less than preset threshold, obtain the location model.
Further, the first quantity of the output of the output layer of the neural network model is the quantity of the grid.
It is apparent to those skilled in the art that for convenience and simplicity of description, the movement of foregoing description
The specific work process of terminal positioning device 10 no longer can excessively repeat herein with reference to the corresponding process in preceding method.
Turning back to combining refering to fig. 1, the disclosure provides a kind of electronic equipment 100, and the electronic equipment 100 includes memory
20, processor 30 and mobile terminal location device 10 among the above, the mobile terminal location device 10 are located at the memory
20 and the software function module that is executed including one or more by the processor 30.
The a kind of electronic equipment 100 that the disclosure provides, due to including above-mentioned mobile terminal location device 10, the electricity
Sub- equipment 100 has technical characteristic identical with above-mentioned mobile terminal location device 10, and this is no longer going to repeat them, please refers to pair
The explanation of above-mentioned mobile terminal location device 10.
The disclosure provides a kind of storage medium, is stored thereon with computer program, and the computer program is real when being executed
Step in existing above-mentioned mobile terminal locating method.
It is apparent to those skilled in the art that for convenience and simplicity of description, the storage of foregoing description
The specific work process of medium no longer can excessively repeat herein with reference to the corresponding process in preceding method.
To sum up, mobile terminal locating method, device, electronic equipment and storage medium that the disclosure provides, by that will include
The region division of multiple base stations is multiple grids, and obtains the position of the be located at grid in the region base station Nei Ge, is obtaining the area
Behind the position of the be located at grid in the domain base station Nei Ge, based on the location model that preparatory training obtains, to each mobile whole in the region
It holds and is calculated with the characteristic of each base station, obtain the probability distribution that each mobile terminal is located at each grid, and then obtain each shifting
The probability distribution of the position of dynamic terminal in the area, realizes the accurate positionin of mobile terminal, and high-efficient.
In the embodiment provided by the disclosure, it should be understood that disclosed device and method, it can also be by other
Mode realize.Device and method embodiment described above is only schematical, for example, flow chart and frame in attached drawing
Figure shows the system frame in the cards of the device of multiple embodiments according to the disclosure, method and computer program product
Structure, function and operation.In this regard, each box in flowchart or block diagram can represent a module, section or code
A part, a part of the module, section or code includes one or more for implementing the specified logical function
Executable instruction.It should also be noted that function marked in the box can also be with not in some implementations as replacement
It is same as the sequence marked in attached drawing generation.For example, two continuous boxes can actually be basically executed in parallel, they have
When can also execute in the opposite order, this depends on the function involved.It is also noted that in block diagram and or flow chart
Each box and the box in block diagram and or flow chart combination, can function or movement as defined in executing it is dedicated
Hardware based system realize, or can realize using a combination of dedicated hardware and computer instructions.
In addition, each functional module in each embodiment of the disclosure can integrate one independent portion of formation together
Point, it is also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
It, can be with if the function is realized and when sold or used as an independent product in the form of software function module
It is stored in a computer readable storage medium.Based on this understanding, the technical solution of the disclosure is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, electronic equipment or network equipment etc.) execute all or part of step of each embodiment the method for the disclosure
Suddenly.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), deposits at random
The various media that can store program code such as access to memory (RAM, Random Access Memory), magnetic or disk.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to the packet of nonexcludability
Contain, so that the process, method, article or equipment for including a series of elements not only includes those elements, but also including
Other elements that are not explicitly listed, or further include for elements inherent to such a process, method, article, or device.
In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including the element
Process, method, article or equipment in there is also other identical elements.
The foregoing is merely the alternative embodiments of the disclosure, are not limited to the disclosure, for the skill of this field
For art personnel, the disclosure can have various modifications and variations.It is all within the spirit and principle of the disclosure, it is made any to repair
Change, equivalent replacement, improvement etc., should be included within the protection scope of the disclosure.
Claims (10)
1. a kind of mobile terminal locating method, which is characterized in that the described method includes:
It will be multiple grids including the region division of multiple base stations, and obtain the position of each be located at grid in base station in the region
It sets;
Based on the location model that preparatory training obtains, to the characteristic of each mobile terminal and each base station in the region into
Row calculates, and the probability distribution that each mobile terminal is located at each grid is obtained, to obtain the position of each mobile terminal
Probability distribution in the area.
2. mobile terminal locating method according to claim 1, which is characterized in that described to obtain each mobile terminal
The step of position probability distribution in the area includes:
The longitude and latitude at each the grid center and boundary is obtained, and according to the longitude and latitude at each the grid center and boundary, it will be each
The probability distribution that the mobile terminal is located at each grid is mapped to the probability distribution that each mobile terminal is located at longitude and latitude,
Obtain the probability distribution of the position of each mobile terminal in the area.
3. mobile terminal locating method according to claim 1, which is characterized in that the location model passes through following steps
Training obtains:
It is multiple grids by region division, and label is carried out to each grid, with each grid marked as classification logotype, with each
The characteristic of mobile terminal and each base station constructs training dataset;
The training dataset is input in neural network model and is trained, based on default loss function, by reversely passing
Algorithm is broadcast to be adjusted the parameter of the neural network, until the default loss function output be less than preset threshold, obtain
To the location model.
4. mobile terminal locating method according to claim 3, which is characterized in that the neural network model includes output
Layer, the first quantity of the output of the output layer are the quantity of the grid.
5. a kind of mobile terminal location device, which is characterized in that described device includes data read module and processing module;
Region division of the data read module for that will include multiple base stations is multiple grids, is obtained each described in the region
The position of the be located at grid in base station;
The processing module is used for the location model obtained based on preparatory training, in the region each mobile terminal with it is each described
The characteristic of base station is calculated, and the probability distribution that each mobile terminal is located at each grid is obtained, to obtain each institute
State the probability distribution of the position of mobile terminal in the area.
6. mobile terminal location device according to claim 5, which is characterized in that the processing module is used for:
The longitude and latitude at each the grid center and boundary is obtained, and according to the longitude and latitude at each the grid center and boundary, it will be each
The probability distribution that the mobile terminal is located at each grid is mapped to the probability distribution that each mobile terminal is located at longitude and latitude,
Obtain the probability distribution of the position of each mobile terminal in the area.
7. mobile terminal location device according to claim 5, which is characterized in that the mobile terminal location device also wraps
Include building module and training module;
The building module is used to region division be multiple grids, and carries out label to each grid, with the mark of each grid
Number it is classification logotype, training dataset is constructed with the characteristic of each mobile terminal and each base station;
The training module is trained for the training dataset to be input in neural network model, based on default loss
Function is adjusted by parameter of the back-propagation algorithm to the neural network, until the output of the default loss function
Less than preset threshold, the location model is obtained.
8. mobile terminal location device according to claim 7, which is characterized in that the output layer of the neural network model
The first quantity of output be the grid quantity.
9. a kind of electronic equipment, which is characterized in that the electronic equipment includes memory, processor and the claims 5-8
Any one of described in mobile terminal location device, the mobile terminal location device be located at the memory and including one or
Multiple software function modules executed by the processor.
10. a kind of storage medium, is stored thereon with computer program, which is characterized in that the computer program is real when being executed
Step in mobile terminal locating method described in any one of existing the claims 1-4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910551856.0A CN110225453A (en) | 2019-06-24 | 2019-06-24 | Mobile terminal locating method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910551856.0A CN110225453A (en) | 2019-06-24 | 2019-06-24 | Mobile terminal locating method, device, electronic equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110225453A true CN110225453A (en) | 2019-09-10 |
Family
ID=67814695
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910551856.0A Pending CN110225453A (en) | 2019-06-24 | 2019-06-24 | Mobile terminal locating method, device, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110225453A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112540803A (en) * | 2020-12-18 | 2021-03-23 | 深圳赛安特技术服务有限公司 | Form design adaptation method, device, equipment and storage medium |
CN112887897A (en) * | 2019-11-29 | 2021-06-01 | 中国电信股份有限公司 | Terminal positioning method, device and computer readable storage medium |
CN113055901A (en) * | 2019-12-27 | 2021-06-29 | 中国电信股份有限公司 | Terminal positioning method and device |
CN113727435A (en) * | 2021-11-04 | 2021-11-30 | 北京融信数联科技有限公司 | Accurate positioning method, system and storage medium |
CN114726463A (en) * | 2021-01-05 | 2022-07-08 | 大唐移动通信设备有限公司 | Method and device for predicting space-time distribution of mobile communication user based on neural network |
CN114745673A (en) * | 2022-04-15 | 2022-07-12 | 广州易而达科技股份有限公司 | Connection control method and device of Bluetooth headset, Bluetooth headset and storage medium |
CN115980804A (en) * | 2023-03-20 | 2023-04-18 | 中国铁塔股份有限公司 | Indoor positioning method and device |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103945533A (en) * | 2014-05-15 | 2014-07-23 | 济南嘉科电子技术有限公司 | Big data based wireless real-time position positioning method |
WO2015084154A1 (en) * | 2013-12-04 | 2015-06-11 | Mimos Berhad | A system and method for locating a mobile device |
CN106507476A (en) * | 2016-11-22 | 2017-03-15 | 上海斐讯数据通信技术有限公司 | A kind of WiFi localization methods and server and location model construction method |
CN106535326A (en) * | 2016-11-22 | 2017-03-22 | 上海斐讯数据通信技术有限公司 | WiFi locating method based on depth neural network and server |
CN108133188A (en) * | 2017-12-22 | 2018-06-08 | 武汉理工大学 | A kind of Activity recognition method based on motion history image and convolutional neural networks |
CN108594170A (en) * | 2018-04-04 | 2018-09-28 | 合肥工业大学 | A kind of WIFI indoor orientation methods based on convolutional neural networks identification technology |
CN109495846A (en) * | 2018-12-24 | 2019-03-19 | 维沃移动通信有限公司 | A kind of localization method and mobile terminal |
CN109871896A (en) * | 2019-02-26 | 2019-06-11 | 北京达佳互联信息技术有限公司 | Data classification method, device, electronic equipment and storage medium |
CN109918752A (en) * | 2019-02-26 | 2019-06-21 | 华南理工大学 | Mechanical failure diagnostic method, equipment and medium based on migration convolutional neural networks |
-
2019
- 2019-06-24 CN CN201910551856.0A patent/CN110225453A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015084154A1 (en) * | 2013-12-04 | 2015-06-11 | Mimos Berhad | A system and method for locating a mobile device |
CN103945533A (en) * | 2014-05-15 | 2014-07-23 | 济南嘉科电子技术有限公司 | Big data based wireless real-time position positioning method |
CN106507476A (en) * | 2016-11-22 | 2017-03-15 | 上海斐讯数据通信技术有限公司 | A kind of WiFi localization methods and server and location model construction method |
CN106535326A (en) * | 2016-11-22 | 2017-03-22 | 上海斐讯数据通信技术有限公司 | WiFi locating method based on depth neural network and server |
CN108133188A (en) * | 2017-12-22 | 2018-06-08 | 武汉理工大学 | A kind of Activity recognition method based on motion history image and convolutional neural networks |
CN108594170A (en) * | 2018-04-04 | 2018-09-28 | 合肥工业大学 | A kind of WIFI indoor orientation methods based on convolutional neural networks identification technology |
CN109495846A (en) * | 2018-12-24 | 2019-03-19 | 维沃移动通信有限公司 | A kind of localization method and mobile terminal |
CN109871896A (en) * | 2019-02-26 | 2019-06-11 | 北京达佳互联信息技术有限公司 | Data classification method, device, electronic equipment and storage medium |
CN109918752A (en) * | 2019-02-26 | 2019-06-21 | 华南理工大学 | Mechanical failure diagnostic method, equipment and medium based on migration convolutional neural networks |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112887897A (en) * | 2019-11-29 | 2021-06-01 | 中国电信股份有限公司 | Terminal positioning method, device and computer readable storage medium |
CN112887897B (en) * | 2019-11-29 | 2022-07-05 | 中国电信股份有限公司 | Terminal positioning method, device and computer readable storage medium |
CN113055901B (en) * | 2019-12-27 | 2022-09-16 | 中国电信股份有限公司 | Terminal positioning method and device |
CN113055901A (en) * | 2019-12-27 | 2021-06-29 | 中国电信股份有限公司 | Terminal positioning method and device |
CN112540803A (en) * | 2020-12-18 | 2021-03-23 | 深圳赛安特技术服务有限公司 | Form design adaptation method, device, equipment and storage medium |
CN112540803B (en) * | 2020-12-18 | 2023-08-11 | 深圳赛安特技术服务有限公司 | Form design adaptation method, device, equipment and storage medium |
CN114726463A (en) * | 2021-01-05 | 2022-07-08 | 大唐移动通信设备有限公司 | Method and device for predicting space-time distribution of mobile communication user based on neural network |
CN114726463B (en) * | 2021-01-05 | 2023-06-23 | 大唐移动通信设备有限公司 | Method and device for predicting space-time distribution of mobile communication users based on neural network |
CN113727435A (en) * | 2021-11-04 | 2021-11-30 | 北京融信数联科技有限公司 | Accurate positioning method, system and storage medium |
CN113727435B (en) * | 2021-11-04 | 2022-02-08 | 北京融信数联科技有限公司 | Accurate positioning method, system and storage medium |
CN114745673A (en) * | 2022-04-15 | 2022-07-12 | 广州易而达科技股份有限公司 | Connection control method and device of Bluetooth headset, Bluetooth headset and storage medium |
CN115980804A (en) * | 2023-03-20 | 2023-04-18 | 中国铁塔股份有限公司 | Indoor positioning method and device |
CN115980804B (en) * | 2023-03-20 | 2023-08-22 | 中国铁塔股份有限公司 | Indoor positioning method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110225453A (en) | Mobile terminal locating method, device, electronic equipment and storage medium | |
TWI694341B (en) | Data sample label processing method, device and computer equipment | |
US11574105B1 (en) | Using a barycenter compact model for a circuit network | |
CN109034365A (en) | The training method and device of deep learning model | |
CN111932386B (en) | User account determining method and device, information pushing method and device, and electronic equipment | |
CN105912500A (en) | Machine learning model generation method and machine learning model generation device | |
CN109451532A (en) | A kind of check method and device of base station location | |
Hagh et al. | Probabilistic load flow using the particle swarm optimisation clustering method | |
US9292650B2 (en) | Identifying layout pattern candidates | |
Babakmehr et al. | Smart-grid topology identification using sparse recovery | |
CN111459898A (en) | Machine learning method, computer-readable recording medium, and machine learning apparatus | |
Shahnaghi et al. | A robust modelling and optimisation framework for a batch processing flow shop production system in the presence of uncertainties | |
CN114240817A (en) | Data analysis method and device, electronic equipment and storage medium | |
Ashayeri et al. | An aggregated optimization model for multi-head SMD placements | |
Yin et al. | Using probabilistic collocation method for neighbouring wind farms modelling and power flow computation of South Australia grid | |
CN108182457A (en) | For generating the method and apparatus of information | |
CN103530583B (en) | Locating terminal, localization method, positioning system and electronic equipment | |
CN112632857A (en) | Method, device, equipment and storage medium for determining line loss of power distribution network | |
CN108932525A (en) | A kind of behavior prediction method and device | |
CN110084255A (en) | The detection method and device of abnormal data | |
CN108133485A (en) | GIS rasterizings problem area recognition methods, device, terminal and medium in flakes | |
CN105719261A (en) | Point cloud data combination system and method | |
Sansanayuth et al. | RFID 2D-localization improvement using modified LANDMARC with linear MMSE estimation | |
Pan et al. | Modelling of multiple wind farms output correlation based on copula theory | |
CN111262248A (en) | Random power flow analysis and calculation method and system |
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 |
Application publication date: 20190910 |
|
RJ01 | Rejection of invention patent application after publication |