CN111372182A - Positioning method, device, equipment and computer readable storage medium - Google Patents
Positioning method, device, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN111372182A CN111372182A CN201811489429.6A CN201811489429A CN111372182A CN 111372182 A CN111372182 A CN 111372182A CN 201811489429 A CN201811489429 A CN 201811489429A CN 111372182 A CN111372182 A CN 111372182A
- Authority
- CN
- China
- Prior art keywords
- user
- network information
- building
- mobile network
- track
- 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
Images
Classifications
-
- 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
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/33—Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings
-
- 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
Abstract
The invention provides a positioning method, a positioning device, positioning equipment and a computer readable storage medium, which are used for solving the technical problem of poor positioning precision of indoor users in the prior art. The method comprises the following steps: selecting a plurality of sampling points in an area to be analyzed, and collecting mobile network information of each sampling point; generating a plurality of moving tracks based on the plurality of sampling points according to the sequence of the sampling time; processing the characteristic sequence of each moving track by the moving network information of the sampling point contained in each moving track in the plurality of moving tracks; inputting the plurality of movement tracks and the characteristic sequences corresponding to the plurality of movement tracks into an LSTM for learning, and generating a prediction model; processing mobile network information of a user to be positioned into a characteristic sequence, inputting the characteristic sequence into the prediction model, outputting the mobile track of the user to be positioned through the prediction model, and positioning the user to be positioned according to the mobile track of the user to be positioned.
Description
Technical Field
The present invention relates to the field of mobile communications, and in particular, to a positioning method, apparatus, device, and computer readable storage medium.
Background
With the gradual deepening of Long Term Evolution (LTE) network coverage, more than 70% of mobile data services occur indoors at present, indoor activity space of people is larger and more complex, and positioning and guiding requirements of places such as parking lots, superstores, airports, railway stations and the like are stronger and stronger. Meanwhile, industries such as precise marketing, child loss prevention, robots and the like also need a network to be capable of identifying the position of a specific object indoors. From the current technology, the more mature and commonly used technologies include WIreless-Fidelity (Wi-Fi) hotspot maps, Wi-Fi fingerprint positioning and other technologies, and the basic principle is to determine the relative position of a receiver and a known position signal source by relying on the reception of radio signals by the receiver, or to compare the position signal characteristics received by the receiver with a feature map ("fingerprint library") collected in advance to obtain the position.
However, the current positioning technology has certain limitations in indoor positioning, is not comprehensively popularized and applied, lacks a unified standard, lacks a system, and still faces the following problems:
1. most existing Wi-Fi hotspots are laid for wireless internet access, and the positioning requirement is not considered, so that the laying density is much lower than that required by indoor positioning, and the positioning accuracy is difficult to improve; meanwhile, if the hot spot laying density is too high, normal internet surfing is influenced due to interference among channels, and indoor positioning reference with high precision requirement cannot be realized;
2. due to frequent changes of arrangement in shopping malls and buildings, the Wi-Fi received signal strength on different reference points can be permanently changed due to factors such as signal shielding, reflection and scattering, and for a fingerprint database positioning technology, a fingerprint database needs to be frequently updated, so that the labor cost is increased; meanwhile, due to the influence of indoor people flow, signal interference, information source stability and other factors, even if indoor arrangement is unchanged, the received signal strength can fluctuate, and precision is reduced or errors occur.
Therefore, the technical problem that the positioning accuracy of indoor users is poor in the prior art is solved.
Disclosure of Invention
The embodiment of the invention provides a positioning method, a positioning device, positioning equipment and a computer readable storage medium, which are used for solving the technical problem of poor positioning accuracy of indoor users in the prior art.
In a first aspect, an embodiment of the present invention provides a positioning method, including:
selecting a plurality of sampling points in an area to be analyzed, and collecting mobile network information of each sampling point;
generating a plurality of moving tracks based on the plurality of sampling points according to the sequence of the sampling time; processing the characteristic sequence of each moving track by the moving network information of the sampling point contained in each moving track in the plurality of moving tracks;
inputting the plurality of movement tracks and the characteristic sequences corresponding to the plurality of movement tracks into an LSTM for learning, and generating a prediction model; the input of the prediction model is a characteristic sequence, and the output is a movement track;
processing mobile network information of a user to be positioned into a characteristic sequence, inputting the characteristic sequence into the prediction model, outputting the mobile track of the user to be positioned through the prediction model, and positioning the user to be positioned according to the mobile track of the user to be positioned.
Optionally, the mobile network information includes a serving cell ID, a serving cell signal strength, an adjacent cell ID, and an adjacent cell signal strength.
Optionally, processing the feature sequence of each moving track with the mobile network information of the sampling point included in each moving track of the plurality of moving tracks, includes:
vectorizing the mobile network information of each sampling point in each of the plurality of mobile tracks;
and sequencing the mobile network information after the warp quantization processing of all the sampling points in each mobile track according to the sequence of the sampling time to obtain the characteristic sequence of each mobile track.
Optionally, the area to be analyzed is specifically an environmental area including a building;
selecting a plurality of sampling points in a region to be analyzed, and collecting mobile network information of each sampling point, wherein the method specifically comprises the following steps:
respectively carrying out three-dimensional grid modeling on each building in the building environment area to obtain a three-dimensional grid model of each building, wherein the height of a grid in the three-dimensional grid model of each building is the floor height of the building; respectively selecting a plurality of grids as sampling points for each building in the building environment area, and acquiring mobile network information at the positions of the selected grids;
inputting the plurality of movement tracks and the characteristic sequences corresponding to the plurality of movement tracks into a network LSTM for learning, and generating a prediction model, specifically comprising:
respectively inputting the moving track and the characteristic sequence of each building in the building environment area into an LSTM for training to obtain a prediction model of each building;
processing the mobile network information of the user to be positioned into a characteristic sequence and inputting the characteristic sequence into the prediction model, wherein the method specifically comprises the following steps:
and processing the mobile network information of the user to be positioned into a characteristic sequence and inputting the characteristic sequence into a prediction model of the building where the user to be positioned is located.
Optionally, after obtaining the three-dimensional grid model of each building, the method further includes:
using the position information of each grid in the three-dimensional grid model of each building as a training label of the grid; the position information comprises longitude and latitude information and floor information;
positioning the user to be positioned according to the movement track of the user to be positioned, specifically comprising:
and determining the position information of the user to be positioned according to the training label of the grid contained in the movement track of the user to be positioned.
Optionally, before generating the plurality of movement trajectories based on the plurality of sampling points according to the sequence of the sampling times, the method further includes:
deleting sampling points meeting preset conditions from the plurality of sampling points;
wherein the preset conditions comprise one or more of the following conditions:
the distance between the sampling point and the position of the main service cell exceeds a first preset range;
the distance between the sampling point and the position of the adjacent cell exceeds a second preset range;
the signal intensity of the primary service cell is lower than a first preset value;
the signal intensity of the adjacent cell is lower than a second preset value;
the signal intensity of the adjacent cell is higher than that of the main service;
mobile network information or location information of the sampling point is missing.
Optionally, before the mobile network information of the user to be located is processed into a feature sequence and input into the prediction model, the method further includes:
acquiring MRO data reported by a user to be positioned;
and acquiring the mobile network information of the user to be positioned from the MRO data.
In a second aspect, an embodiment of the present invention provides a positioning apparatus, including:
the acquisition module is used for selecting a plurality of sampling points in the area to be analyzed and acquiring the mobile network information of each sampling point;
the processing module is used for generating a plurality of moving tracks based on the plurality of sampling points according to the sequence of the sampling time; processing the characteristic sequence of each moving track by the moving network information of the sampling point contained in each moving track in the plurality of moving tracks;
the learning module is used for inputting the plurality of movement tracks and the characteristic sequences corresponding to the plurality of movement tracks into an LSTM for learning and generating a prediction model; the input of the prediction model is a characteristic sequence, and the output is a movement track;
and the positioning module is used for processing the mobile network information of the user to be positioned into a characteristic sequence and inputting the characteristic sequence into the prediction model, outputting the mobile track of the user to be positioned through the prediction model, and positioning the user to be positioned according to the mobile track of the user to be positioned.
Optionally, the mobile network information includes a serving cell ID, a serving cell signal strength, an adjacent cell ID, and an adjacent cell signal strength.
Optionally, the processing module is specifically configured to:
vectorizing the mobile network information of each sampling point in each of the plurality of mobile tracks;
and sequencing the mobile network information after the warp quantization processing of all the sampling points in each mobile track according to the sequence of the sampling time to obtain the characteristic sequence of each mobile track.
Optionally, the area to be analyzed is specifically an environmental area including a building;
the acquisition module is specifically configured to:
respectively carrying out three-dimensional grid modeling on each building in the building environment area to obtain a three-dimensional grid model of each building, wherein the height of a grid in the three-dimensional grid model of each building is the floor height of the building; respectively selecting a plurality of grids as sampling points for each building in the building environment area, and acquiring mobile network information at the positions of the selected grids;
the learning module is specifically configured to:
respectively inputting the moving track and the characteristic sequence of each building in the building environment area into an LSTM for training to obtain a prediction model of each building;
the positioning module is specifically configured to:
and processing the mobile network information of the user to be positioned into a characteristic sequence and inputting the characteristic sequence into a prediction model of the building where the user to be positioned is located.
Optionally, the acquisition module is further configured to:
after obtaining the three-dimensional grid model of each building, using the position information of each grid in the three-dimensional grid model of each building as a training label of the grid; the position information comprises longitude and latitude information and floor information;
the positioning module is specifically configured to:
and determining the position information of the user to be positioned according to the training label of the grid contained in the movement track of the user to be positioned.
Optionally, the processing module is further configured to:
deleting the sampling points meeting preset conditions in the plurality of sampling points before generating a plurality of moving tracks based on the plurality of sampling points according to the sequence of the sampling time;
wherein the preset conditions comprise one or more of the following conditions:
the distance between the sampling point and the position of the main service cell exceeds a first preset range;
the distance between the sampling point and the position of the adjacent cell exceeds a second preset range;
the signal intensity of the primary service cell is lower than a first preset value;
the signal intensity of the adjacent cell is lower than a second preset value;
the signal intensity of the adjacent cell is higher than that of the main service;
mobile network information or location information of the sampling point is missing.
Optionally, the positioning module is further configured to:
before processing the mobile network information of the user to be positioned into a characteristic sequence and inputting the characteristic sequence into the prediction model, acquiring MRO data reported by the user to be positioned;
and acquiring the mobile network information of the user to be positioned from the MRO data.
In a third aspect, an embodiment of the present invention provides a positioning apparatus, including:
at least one processor, and
a memory communicatively coupled to the at least one processor;
wherein the memory stores instructions executable by the at least one processor, and the at least one processor performs the method according to the first aspect of the embodiments or any alternative implementation of the first aspect of the embodiments by executing the instructions stored in the memory.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores computer instructions that, when executed on a computer, cause the computer to perform the method according to the first aspect of the present invention or any optional implementation manner of the first aspect.
One or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages:
the embodiment of the invention samples the mobile network information of the area to be analyzed, generates a plurality of mobile tracks based on the sequence of sampling time, and processes the mobile network information of the sampling point on each mobile track into the characteristic sequence of the mobile track; inputting the plurality of moving tracks and the characteristic sequences corresponding to the plurality of moving tracks into an LSTM for learning to generate a prediction model; and finally, processing the mobile network information of the user to be positioned into a characteristic sequence, inputting the characteristic sequence into the prediction model, predicting the mobile track of the user to be positioned, and positioning the user to be positioned according to the predicted mobile track. Compared with the traditional Wi-Fi positioning technology, the embodiment of the invention has richer data volume of mobile network information, higher coverage density and more stable signal strength, thereby effectively improving the positioning accuracy; secondly, the technical scheme of the invention utilizes the idea of LSTM learning to position the user position, and has the technical effects of high efficiency and low cost.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
FIG. 1 is a schematic diagram of the principle of the LSTM algorithm in an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a positioning method according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating a mobile network information sampling process according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of sampling information in an embodiment of the present invention;
FIG. 5 is a diagram illustrating a user movement trajectory according to an embodiment of the present invention;
fig. 6 is a schematic diagram of location information of N users in an embodiment of the present invention.
FIG. 7 is a schematic structural diagram of a positioning device according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of a positioning apparatus in an embodiment of the present invention.
Detailed Description
The technical solutions of the present invention are described in detail below with reference to the drawings and the specific embodiments, and it should be understood that the specific features in the embodiments and the embodiments of the present invention are not intended to limit the technical solutions of the present invention, but may be combined with each other without conflict.
It is to be understood that the terms first, second, and the like in the description of the embodiments of the invention are used for distinguishing between the descriptions and not necessarily for describing a sequential or chronological order. "plurality" in the description of the embodiments of the present invention means two or more.
The term "and/or" in the embodiment of the present invention is only one kind of association relationship describing an associated object, and indicates that three relationships may exist, for example, a and/or B may indicate: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
Before the technical scheme of the embodiment of the invention is introduced, the 'LSTM' in the text is introduced:
LSTM (long short-Term Memory) is a long-short Term Memory network, a temporal recurrent neural network, suitable for processing and predicting important events with relatively long intervals and delays in time series.
The LSTM algorithm differs from the Recurrent Neural Network (RNN) mainly in that: a processor (cell) for judging whether information is useful is added, three doors, namely an input door, a forgetting door and an output door, are arranged in one cell, and one information enters the LSTM network and can be judged to be useful according to corresponding rules. Only the information which is in accordance with the algorithm authentication is left, and the information which is not in accordance with the algorithm authentication is forgotten through a forgetting door.
Forget the door: determining how much the unit state c _ t-1 at the previous moment is reserved to the current moment c _ t;
an input gate: determining how much input x _ t of the network at the current moment is stored to a unit state c _ t;
an output gate: how much the control unit state c _ t is output to the current output value h _ t of the LSTM.
Referring to FIG. 1, at time t, there are three inputs to the LSTM: an input value x _ t of a network at the current moment, an output value h _ t-1 of an LSTM at the last moment and a unit state c _ t-1 at the last moment; the output of the LSTM is two: the LSTM at the current time outputs a value h _ t and a cell state c _ t at the current time.
The long-term state control method comprises the following steps: the first switch is responsible for controlling the long-term state c to be continuously stored; the second switch is responsible for controlling the input of the instant state into the long-term state c; and the third switch is responsible for controlling whether the long-term state c is taken as the output of the current LSTM.
Next, a technical solution of an embodiment of the present invention is described.
The embodiment of the invention provides a positioning method, a positioning device, positioning equipment and a computer readable storage medium, which are used for solving the technical problem of poor positioning accuracy of indoor users in the prior art. Referring to fig. 2, the specific process of the method includes:
s101: selecting a plurality of sampling points in an area to be analyzed, and collecting mobile network information of each sampling point;
in the embodiment of the present invention, the existing professional equipment may be utilized to acquire the mobile network information by using network optimization or the professional business terminal may be utilized to acquire the mobile network information, which is not particularly limited in the embodiment of the present invention. The type of the collected mobile network information may specifically be 3G wireless coverage information, 4G wireless coverage information, or 5G wireless coverage information, and the embodiment of the present invention is not limited specifically. The mobile network information may specifically include an Identification (ID) of a serving cell at the sampling point, signal strength of the serving cell, an ID of a neighboring cell, signal strength of the neighboring cell, and the like.
As an optional manner, if the area to be analyzed is an environmental area including a building, the specific implementation of performing mobile network information sampling on the area to be analyzed may be: respectively carrying out three-dimensional grid modeling on each building to obtain a three-dimensional grid model of each building; and aiming at each building, respectively selecting a plurality of grids as sampling points, and collecting the mobile network information at the positions of the selected grids. The height of the grid can be the floor height of the building.
For example, referring to fig. 3, the detailed process of mobile network information sampling includes:
step 201: performing grid division on each layer of each building;
specifically, the height of the grid is specifically the height of the floor, and the length and the width of the grid can be set according to the actual situation, for example, set to be 5cm by 5 cm.
Step 302: at least 500 and 1000 sampling points are required to be collected at each level in the building;
step 203: each floor (including an underground garage) in the building needs to be involved, and the acquisition time of each floor is not less than 20 minutes;
step 204: data are collected within 100 meters of the periphery of the building, and the number of sampling points is required to be not less than 500.
After the collection is completed, the collected sampling data is analyzed, and the information of each floor in the building and the information outside the building are counted, as shown in fig. 4.
As an alternative, in order to ensure the accuracy of the prediction model generated in step S103, after the data of the region to be analyzed is sampled, invalid samples in the sampled data may be further identified and deleted.
The specific implementation comprises the following steps: and deleting the sampling points meeting the preset conditions from the plurality of sampling points. Wherein the preset conditions comprise one or more of the following conditions:
1) the distance between the sampling point and the position of the main service cell exceeds a first preset range;
2) the distance between the sampling point and the position of the adjacent cell exceeds a second preset range;
3) the signal intensity of the primary service cell is lower than a first preset value;
4) the signal intensity of the adjacent cell is lower than a second preset value;
5) the signal intensity of the adjacent cell is higher than that of the main service;
6) mobile network information or location information of the sampling point is missing.
For example, if the position distance of the main service cell in the grid exceeds the range of 1 kilometer, determining that the sampling data of the grid is invalid; for another example, if the distance of the position of the front 6 strong neighbor cells in the grid exceeds the range of 1.5 kilometers, determining that the sampling data of the grid is invalid; as another example, if the signal strength of the primary serving cell in the grid is lower than-95 dB, it is determined that the sampled data of the grid is invalid; for another example, if the signal strength of the neighbor cell in the grid is higher than the signal strength of the main service, the sampled data of the grid is determined to be invalid; as another example, if the signal strength of the neighbor cells in the grid is below-120 dB, the sampled data of the grid is determined to be invalid; for another example, if the floor ID, the signal strength of the master cell, and the signal strength of the neighbor cells in the grid are not complete, the sampled data of the grid is determined to be invalid.
As an optional way, after obtaining the three-dimensional grid model of each building, the position information of each grid in the three-dimensional grid model of each building can be used as a training label of the grid; the location information may specifically include longitude and latitude information of a grid, floor information, and the like.
S102: generating a plurality of moving tracks based on the plurality of sampling points according to the sequence of the sampling time; processing the characteristic sequence of each moving track by the moving network information of the sampling point contained in each moving track in the plurality of moving tracks;
the specific implementation mode for processing the mobile network information of the sampling points contained in each mobile track into the characteristic sequence comprises the following steps: vectorizing the mobile network information of each sampling point in each mobile track; and sequencing the mobile network information after the warp quantization processing of all the sampling points in each mobile track according to the sequence of the sampling time to obtain the characteristic sequence of each mobile track.
For example: for each building, sequencing cells of the whole building to obtain a cell list; the field strength information of the primary and neighboring cells received at each grid is then processed into a vector, for example, Reference Signal Receiving Power (RSRP) of the primary and neighboring cells is used to form an RSRP vector. In order to more accurately locate the position of the user, besides using the field strength information of the cell signal received by the user, the historical information and the variation condition of the user are further used to process the samples into a sequence according to time, for example, 10 adjacent RSRPs are connected into a characteristic sequence with the length of 10 according to the time sequence. Assuming that a user can have N walks from a building entrance to the 4 th floor of the building, i.e. through N different grid sequences, N signature sequences are correspondingly generated.
S103: inputting the plurality of movement tracks and the characteristic sequences corresponding to the plurality of movement tracks into an LSTM for learning, and generating a prediction model; the input of the prediction model is a characteristic sequence, and the output is a movement track;
when the area to be analyzed comprises a plurality of buildings, inputting the moving track and the characteristic sequence of each building in the building environment area into an LSTM for training to obtain a prediction model of each building. For each building, the LSTM performs feature learning through each grid sequence (i.e., movement trajectory) and its feature sequence in the building, thereby obtaining feature sequences corresponding to all grid sequences in the whole building, and generating a prediction model corresponding to the building.
S104: processing mobile network information of a user to be positioned into a characteristic sequence, inputting the characteristic sequence into the prediction model, outputting the mobile track of the user to be positioned through the prediction model, and positioning the user to be positioned according to the mobile track of the user to be positioned.
Specifically, the position information of the user to be positioned is determined according to a training label of a grid (sampling point) included in a grid sequence (moving track) output by the prediction model. For example, as shown in fig. 5, the curve in fig. 5 is an illustration of the movement track of the user, where the position indicated by the five-pointed star is the current position of the user.
Correspondingly, when the area to be analyzed comprises a plurality of buildings, the mobile network information of the user to be positioned is processed into a characteristic sequence and input into a prediction model of the building where the user to be positioned is located.
As an optional manner, when step S104 is executed, a plurality of users to be tested may be processed simultaneously in parallel, so as to realize positioning of the plurality of users to be tested. For example, as shown in fig. 6, positioning information of N users can be obtained by simultaneously positioning N users.
As an optional manner, the source of the mobile network information of the user to be located may be that Measurement Report sample data file (MRO) data reported by the user to be located is obtained, and the mobile network information of the user to be located is obtained from the MRO data.
As an optional manner, after step 103 is executed, each grid may be associated with a Key Quality Indicator (KQI) at the grid, so as to realize intelligent identification and positioning of indoor user perception problems and improve indoor network operation Quality.
According to the technical scheme of the embodiment of the invention, the mobile network information of the area to be analyzed is sampled, a plurality of mobile tracks are generated based on the sequence of sampling time, and the mobile network information of the sampling point on each mobile track is processed with the characteristic sequence of the mobile track; inputting the plurality of moving tracks and the characteristic sequences corresponding to the plurality of moving tracks into an LSTM for learning to generate a prediction model; and finally, processing the mobile network information of the user to be positioned into a characteristic sequence, inputting the characteristic sequence into the prediction model, predicting the mobile track of the user to be positioned, and positioning the user to be positioned according to the predicted mobile track. Compared with the traditional Wi-Fi positioning technology, the embodiment of the invention has richer data volume of mobile network information, higher coverage density and more stable signal strength, thereby effectively improving the positioning accuracy; secondly, the technical scheme of the invention utilizes the idea of LSTM learning to position the user position, and has the technical effects of high efficiency and low cost.
Referring to fig. 7, based on the same inventive concept, an embodiment of the present invention further provides a positioning apparatus, including:
the acquisition module 701 is used for selecting a plurality of sampling points in an area to be analyzed and acquiring mobile network information of each sampling point;
a processing module 702, configured to generate multiple movement trajectories based on the multiple sampling points according to a sequence of sampling times; processing the characteristic sequence of each moving track by the moving network information of the sampling point contained in each moving track in the plurality of moving tracks;
a learning module 703, configured to input the multiple movement tracks and the feature sequences corresponding to the multiple movement tracks into an LSTM for learning, so as to generate a prediction model; the input of the prediction model is a characteristic sequence, and the output is a movement track;
and the positioning module 704 is used for processing the mobile network information of the user to be positioned into a characteristic sequence and inputting the characteristic sequence into the prediction model, outputting the mobile track of the user to be positioned through the prediction model, and positioning the user to be positioned according to the mobile track of the user to be positioned.
Optionally, the mobile network information includes a serving cell ID, a serving cell signal strength, an adjacent cell ID, and an adjacent cell signal strength.
Optionally, the processing module 702 is specifically configured to:
vectorizing the mobile network information of each sampling point in each of the plurality of mobile tracks;
and sequencing the mobile network information after the warp quantization processing of all the sampling points in each mobile track according to the sequence of the sampling time to obtain the characteristic sequence of each mobile track.
Optionally, the area to be analyzed is specifically an environmental area including a building;
the acquisition module 701 is specifically configured to:
respectively carrying out three-dimensional grid modeling on each building in the building environment area to obtain a three-dimensional grid model of each building, wherein the height of a grid in the three-dimensional grid model of each building is the floor height of the building; respectively selecting a plurality of grids as sampling points for each building in the building environment area, and acquiring mobile network information at the positions of the selected grids;
the learning module 703 is specifically configured to:
respectively inputting the moving track and the characteristic sequence of each building in the building environment area into an LSTM for training to obtain a prediction model of each building;
the positioning module 704 is specifically configured to:
and processing the mobile network information of the user to be positioned into a characteristic sequence and inputting the characteristic sequence into a prediction model of the building where the user to be positioned is located.
Optionally, the acquisition module 701 is further configured to:
after obtaining the three-dimensional grid model of each building, using the position information of each grid in the three-dimensional grid model of each building as a training label of the grid; the position information comprises longitude and latitude information and floor information;
the positioning module 704 is specifically configured to:
and determining the position information of the user to be positioned according to the training label of the grid contained in the movement track of the user to be positioned.
Optionally, the processing module 702 is further configured to:
deleting the sampling points meeting preset conditions in the plurality of sampling points before generating a plurality of moving tracks based on the plurality of sampling points according to the sequence of the sampling time;
wherein the preset conditions comprise one or more of the following conditions:
the distance between the sampling point and the position of the main service cell exceeds a first preset range;
the distance between the sampling point and the position of the adjacent cell exceeds a second preset range;
the signal intensity of the primary service cell is lower than a first preset value;
the signal intensity of the adjacent cell is lower than a second preset value;
the signal intensity of the adjacent cell is higher than that of the main service;
mobile network information or location information of the sampling point is missing.
Optionally, the positioning module 704 is further configured to:
before processing the mobile network information of the user to be positioned into a characteristic sequence and inputting the characteristic sequence into the prediction model, acquiring MRO data reported by the user to be positioned;
and acquiring the mobile network information of the user to be positioned from the MRO data.
The method and the device are based on the same inventive concept, and because the principles of solving the problems of the method and the device are similar, the specific implementation modes of the operations executed by the units can refer to the corresponding steps in the positioning method in the embodiment of the invention, so the implementation of the device and the method can be referred to each other, and repeated parts are not described again.
Referring to fig. 8, based on the same inventive concept, an embodiment of the present invention further provides a positioning apparatus, including:
at least one processor 801, and
a memory 802 communicatively coupled to the at least one processor 801;
wherein the memory 802 stores instructions executable by the at least one processor 801, the at least one processor 801 performing the steps of the method as described in the above method embodiments by executing the instructions stored by the memory 802.
Optionally, the processor 801 may specifically include a Central Processing Unit (CPU) and an Application Specific Integrated Circuit (ASIC), may be one or more integrated circuits for controlling program execution, may be a hardware circuit developed by using a Field Programmable Gate Array (FPGA), and may be a baseband processor.
Optionally, processor 801 may include at least one processing core.
Alternatively, the memory 802 may include a Read Only Memory (ROM), a Random Access Memory (RAM), and a disk memory. The memory 802 is used for storing data required by the processor 801 during operation.
Based on the same inventive concept, embodiments of the present invention also provide a computer-readable storage medium storing computer instructions that, when executed on a computer, cause the computer to perform the steps of the method as described in the above method embodiments.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A method of positioning, comprising:
selecting a plurality of sampling points in an area to be analyzed, and collecting mobile network information of each sampling point;
generating a plurality of moving tracks based on the plurality of sampling points according to the sequence of the sampling time; processing the characteristic sequence of each moving track by the moving network information of the sampling point contained in each moving track in the plurality of moving tracks;
inputting the plurality of movement tracks and the characteristic sequences corresponding to the plurality of movement tracks into a long-short term memory network (LSTM) for learning to generate a prediction model; the input of the prediction model is a characteristic sequence, and the output is a movement track;
processing mobile network information of a user to be positioned into a characteristic sequence, inputting the characteristic sequence into the prediction model, outputting the mobile track of the user to be positioned through the prediction model, and positioning the user to be positioned according to the mobile track of the user to be positioned.
2. The method of claim 1, in which the mobile network information comprises a serving cell Identification (ID), a serving cell signal strength, a neighbor cell ID, and a neighbor cell signal strength.
3. The method as claimed in claim 1, wherein processing the mobile network information of the sampling point contained in each of the plurality of movement trajectories to the feature sequence of each movement trajectory comprises:
vectorizing the mobile network information of each sampling point in each of the plurality of mobile tracks;
and sequencing the mobile network information after the warp quantization processing of all the sampling points in each mobile track according to the sequence of the sampling time to obtain the characteristic sequence of each mobile track.
4. A method according to any one of claims 1 to 3, wherein the area to be analyzed is in particular an environmental area comprising buildings;
selecting a plurality of sampling points in a region to be analyzed, and collecting mobile network information of each sampling point, wherein the method specifically comprises the following steps:
respectively carrying out three-dimensional grid modeling on each building in the building environment area to obtain a three-dimensional grid model of each building, wherein the height of a grid in the three-dimensional grid model of each building is the floor height of the building; respectively selecting a plurality of grids as sampling points for each building in the building environment area, and acquiring mobile network information at the positions of the selected grids;
inputting the plurality of movement tracks and the characteristic sequences corresponding to the plurality of movement tracks into a network LSTM for learning, and generating a prediction model, specifically comprising:
respectively inputting the moving track and the characteristic sequence of each building in the building environment area into an LSTM for training to obtain a prediction model of each building;
processing the mobile network information of the user to be positioned into a characteristic sequence and inputting the characteristic sequence into the prediction model, wherein the method specifically comprises the following steps:
and processing the mobile network information of the user to be positioned into a characteristic sequence and inputting the characteristic sequence into a prediction model of the building where the user to be positioned is located.
5. The method of claim 4, wherein after obtaining the three-dimensional grid model for each building, the method further comprises:
using the position information of each grid in the three-dimensional grid model of each building as a training label of the grid; the position information comprises longitude and latitude information and floor information;
positioning the user to be positioned according to the movement track of the user to be positioned, specifically comprising:
and determining the position information of the user to be positioned according to the training label of the grid contained in the movement track of the user to be positioned.
6. The method according to any one of claims 1-3, wherein before generating the plurality of movement trajectories based on the plurality of sampling points according to a precedence order of sampling times, the method further comprises:
deleting sampling points meeting preset conditions from the plurality of sampling points;
wherein the preset conditions comprise one or more of the following conditions:
the distance between the sampling point and the position of the main service cell exceeds a first preset range;
the distance between the sampling point and the position of the adjacent cell exceeds a second preset range;
the signal intensity of the primary service cell is lower than a first preset value;
the signal intensity of the adjacent cell is lower than a second preset value;
the signal intensity of the adjacent cell is higher than that of the main service;
mobile network information or location information of the sampling point is missing.
7. A method according to any of claims 1-3, wherein before processing the mobile network information of the user to be located into a signature sequence into the predictive model, the method further comprises:
acquiring MRO data of a measurement report sample data file reported by a user to be positioned;
and acquiring the mobile network information of the user to be positioned from the MRO data.
8. A positioning device, comprising:
the acquisition module is used for selecting a plurality of sampling points in the area to be analyzed and acquiring the mobile network information of each sampling point;
the processing module is used for generating a plurality of moving tracks based on the plurality of sampling points according to the sequence of the sampling time; processing the characteristic sequence of each moving track by the moving network information of the sampling point contained in each moving track in the plurality of moving tracks;
the learning module is used for inputting the plurality of movement tracks and the characteristic sequences corresponding to the plurality of movement tracks into an LSTM for learning and generating a prediction model; the input of the prediction model is a characteristic sequence, and the output is a movement track;
and the positioning module is used for processing the mobile network information of the user to be positioned into a characteristic sequence and inputting the characteristic sequence into the prediction model, outputting the mobile track of the user to be positioned through the prediction model, and positioning the user to be positioned according to the mobile track of the user to be positioned.
9. A positioning apparatus, comprising:
at least one processor, and
a memory communicatively coupled to the at least one processor;
wherein the memory stores instructions executable by the at least one processor, the at least one processor performing the method of any one of claims 1-7 by executing the instructions stored by the memory.
10. A computer-readable storage medium having stored thereon computer instructions which, when executed on a computer, cause the computer to perform the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811489429.6A CN111372182A (en) | 2018-12-06 | 2018-12-06 | Positioning method, device, equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811489429.6A CN111372182A (en) | 2018-12-06 | 2018-12-06 | Positioning method, device, equipment and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111372182A true CN111372182A (en) | 2020-07-03 |
Family
ID=71209732
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811489429.6A Pending CN111372182A (en) | 2018-12-06 | 2018-12-06 | Positioning method, device, equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111372182A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112040408A (en) * | 2020-08-14 | 2020-12-04 | 山东大学 | Multi-target accurate intelligent positioning and tracking method suitable for supervision places |
| CN115451937A (en) * | 2022-08-12 | 2022-12-09 | 合肥未来计算机技术开发有限公司 | Electronic map generation system and method for safety channel in complex environment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130165143A1 (en) * | 2011-06-24 | 2013-06-27 | Russell Ziskind | Training pattern recognition systems for determining user device locations |
| CN106886552A (en) * | 2016-12-12 | 2017-06-23 | 蔚来汽车有限公司 | Location fingerprint database update method and system |
| CN106912103A (en) * | 2015-12-23 | 2017-06-30 | 中国移动通信集团上海有限公司 | A kind of method of locating terminal and device |
| CN107396322A (en) * | 2017-08-28 | 2017-11-24 | 电子科技大学 | Indoor orientation method based on route matching Yu coding and decoding Recognition with Recurrent Neural Network |
-
2018
- 2018-12-06 CN CN201811489429.6A patent/CN111372182A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130165143A1 (en) * | 2011-06-24 | 2013-06-27 | Russell Ziskind | Training pattern recognition systems for determining user device locations |
| CN106912103A (en) * | 2015-12-23 | 2017-06-30 | 中国移动通信集团上海有限公司 | A kind of method of locating terminal and device |
| CN106886552A (en) * | 2016-12-12 | 2017-06-23 | 蔚来汽车有限公司 | Location fingerprint database update method and system |
| CN107396322A (en) * | 2017-08-28 | 2017-11-24 | 电子科技大学 | Indoor orientation method based on route matching Yu coding and decoding Recognition with Recurrent Neural Network |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112040408A (en) * | 2020-08-14 | 2020-12-04 | 山东大学 | Multi-target accurate intelligent positioning and tracking method suitable for supervision places |
| CN115451937A (en) * | 2022-08-12 | 2022-12-09 | 合肥未来计算机技术开发有限公司 | Electronic map generation system and method for safety channel in complex environment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107333232B (en) | Terminal positioning method and network equipment | |
| Sohn et al. | Dynamic origin–destination flow estimation using cellular communication system | |
| CN108601029B (en) | Base station construction evaluation method and device | |
| CN108109423B (en) | Underground parking lot intelligent navigation method and system based on WiFi indoor positioning | |
| Rezazadeh et al. | A location-based smart shopping system with IoT technology | |
| CN110545558B (en) | High-speed service area crowd density estimation system based on Wi-Fi data | |
| CN108134979B (en) | Small base station switch control method based on deep neural network | |
| CN102984745A (en) | Combined estimation method for Wi-Fi AP (wireless fidelity access point) position and path loss model | |
| CN112686466A (en) | Subway passenger path confirmation method and device | |
| CN111372182A (en) | Positioning method, device, equipment and computer readable storage medium | |
| Molina-Garcia et al. | Enhanced in-building fingerprint positioning using femtocell networks | |
| Roy et al. | Indoor localization using stable set of wireless access points subject to varying granularity levels | |
| CN116957005A (en) | Training method, device, equipment and medium of corresponding relation prediction network | |
| CN113947123B (en) | Personnel trajectory identification method, system, storage medium and equipment | |
| CN113365306B (en) | Network analysis method and device, storage medium and computer system | |
| CN113225674B (en) | Fingerprint positioning method, system, server and storage medium | |
| KR20200061666A (en) | Method and Apparatus for Providing Population Guidance Service | |
| JP2016048529A (en) | Apparatus, program and method capable of determining stay of user carrying mobile terminal | |
| CN112600728B (en) | 5G mobile base station flow prediction analysis system based on big data | |
| CN112601177B (en) | Method, system, server and storage medium for guiding people flow in public area | |
| KR101591566B1 (en) | Position tracking method and apparatus | |
| CN109874170B (en) | Blind detection method, device, equipment and medium for geographic coordinate system | |
| CN107979818B (en) | Method for processing initial data of wireless fingerprint database | |
| CN114599040A (en) | Base station position determining method and device and electronic equipment | |
| CN112929938B (en) | AP topological relation graph generation method and system based on wireless log information |
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: 20200703 |
|
| RJ01 | Rejection of invention patent application after publication |