CN113063420B - Indoor positioning method, device, electronic equipment and storage medium - Google Patents

Indoor positioning method, device, electronic equipment and storage medium Download PDF

Info

Publication number
CN113063420B
CN113063420B CN202110287485.7A CN202110287485A CN113063420B CN 113063420 B CN113063420 B CN 113063420B CN 202110287485 A CN202110287485 A CN 202110287485A CN 113063420 B CN113063420 B CN 113063420B
Authority
CN
China
Prior art keywords
position information
geomagnetic
signal data
determining
prediction
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.)
Active
Application number
CN202110287485.7A
Other languages
Chinese (zh)
Other versions
CN113063420A (en
Inventor
彭聪
王雪
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
CCB Finetech Co Ltd
Original Assignee
CCB Finetech Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by CCB Finetech Co Ltd filed Critical CCB Finetech Co Ltd
Priority to CN202110287485.7A priority Critical patent/CN113063420B/en
Publication of CN113063420A publication Critical patent/CN113063420A/en
Application granted granted Critical
Publication of CN113063420B publication Critical patent/CN113063420B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/20—Instruments for performing navigational calculations
    • G01C21/206—Instruments for performing navigational calculations specially adapted for indoor navigation
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/04—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by terrestrial means
    • G01C21/08—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by terrestrial means involving use of the magnetic field of the earth
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
    • G01S5/0257—Hybrid positioning
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
    • G01S5/06—Position of source determined by co-ordinating a plurality of position lines defined by path-difference measurements
    • 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
    • H04W4/023—Services making use of location information using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
    • 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
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/80—Services using short range communication, e.g. near-field communication [NFC], radio-frequency identification [RFID] or low energy communication
    • 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 embodiment of the invention discloses an indoor positioning method, an indoor positioning device, electronic equipment and a storage medium. The indoor positioning method comprises the following steps: acquiring equipment signal data and geomagnetic signal data of at least three positioning equipment acquired by a target object at a to-be-positioned point; determining device predicted location information from the device signal data based on a pre-trained location prediction machine learning model; based on a pre-determined geomagnetic fingerprint library, determining fusion predicted position information of a to-be-positioned point according to geomagnetic signal data and equipment predicted position information, and taking the fusion predicted position information as a final positioning result. The embodiment of the invention determines the equipment prediction position information based on the equipment signal data, and then determines the fusion prediction position information based on the equipment prediction position information according to the geomagnetic signal data, thereby realizing the comprehensive utilization of the advantages of various positioning methods, ensuring the accuracy of positioning the positioning point to be positioned, avoiding the dependence on single positioning information, and having strong compatibility and wide application range.

Description

Indoor positioning method, device, electronic equipment and storage medium
Technical Field
The embodiment of the invention relates to the technical field of positioning, in particular to an indoor positioning method, an indoor positioning device, electronic equipment and a storage medium.
Background
With the development of satellite positioning navigation technology, location-Based-Service (LBS) is gradually entering people's life. Due to popularization of intelligent terminal equipment and development of location services, people have increasingly high requirements on accuracy and stability of positioning results. GPS is a global positioning navigation system developed by the United states and is also the most widely used and mature positioning system. However, the complexity of the indoor environment results in signals being blocked and disturbed such that the user often does not receive the signals. So GPS cannot meet the indoor positioning needs.
With the continuous development of society, a plurality of indoor buildings such as shopping malls, airports, amusement parks and the like appear, so that the indoor positioning technology has huge development space, and has wide application prospects in the fields of personnel positioning, electronic commerce, intelligent parking and taking and the like. For example, in the financial industry real estate financing business, banks can develop real estate mortgage management and control business of multiple categories, and in addition, in the fields of intelligent security, intelligent park and intelligent equipment management, etc., the application of the internet of things technology, the internet of things equipment is required to provide positioning services.
Ultra wideband positioning UWB and ultrasonic positioning technology are high in precision, but the cost is high, so that the popularization of the ultra wideband positioning UWB and ultrasonic positioning technology is greatly limited. The indoor positioning technology such as Bluetooth, wiFi and RFID utilizes the characteristics of radio frequency signals to judge the position, and the cost is low, but the positioning accuracy is low because the signal propagation distance is short and the signal propagation distance is easily interfered by the external environment. PDR (Pedestrian Dead Reckoning) positioning technology uses accelerometer, magnetometer and gyroscope information to determine the user's position, and this technology does not need to rely on additional auxiliary equipment, is less disturbed by the surrounding environment, but suffers from accumulated errors and is not suitable for long-term use.
Disclosure of Invention
The embodiment of the invention provides an indoor positioning method, an indoor positioning device, electronic equipment and a storage medium, so as to improve the accuracy of indoor positioning.
In a first aspect, an embodiment of the present invention provides an indoor positioning method, including:
acquiring equipment signal data and geomagnetic signal data of at least three positioning equipment acquired by a target object at a to-be-positioned point;
determining device predicted location information from the device signal data based on a pre-trained location prediction machine learning model;
based on a pre-determined geomagnetic fingerprint library, determining fusion predicted position information of a to-be-positioned point according to geomagnetic signal data and equipment predicted position information, and taking the fusion predicted position information as a final positioning result.
In a second aspect, an embodiment of the present invention further provides an indoor positioning device, including:
the signal data acquisition module is used for acquiring equipment signal data and geomagnetic signal data of at least three positioning equipment acquired by a target object at a to-be-positioned point;
the equipment prediction module is used for predicting a machine learning model based on a pre-trained position and determining equipment prediction position information according to the equipment signal data;
and the geomagnetic fusion prediction module is used for determining fusion prediction position information of a to-be-positioned point based on a predetermined geomagnetic fingerprint database according to the geomagnetic signal data and the equipment prediction position information, and taking the fusion prediction position information as a final positioning result.
In a third aspect, an embodiment of the present invention further provides an electronic device, including:
one or more processors;
storage means for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the indoor positioning method according to any of the embodiments of the present invention.
In a fourth aspect, embodiments of the present invention further provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements an indoor positioning method according to any of the embodiments of the present invention.
The embodiment of the invention determines the equipment prediction position information based on the equipment signal data, and then determines the fusion prediction position information based on the equipment prediction position information according to the geomagnetic signal data, thereby realizing the comprehensive utilization of the advantages of various positioning methods, ensuring the accuracy of positioning the positioning point to be positioned, avoiding the dependence on single positioning information, and having strong compatibility and wide application range.
Drawings
Fig. 1 is a flowchart of an indoor positioning method according to a first embodiment of the present invention;
fig. 2 is a flowchart of an indoor positioning method in a second embodiment of the present invention;
Fig. 3 is a flowchart of an indoor positioning method in the third embodiment of the present invention;
fig. 4 is a flowchart of an indoor positioning method in the fourth embodiment of the present invention;
FIG. 5 is a schematic view of an indoor positioning system according to a fifth embodiment of the present invention;
FIG. 6 is a schematic view of an indoor positioning device according to a sixth embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device in a seventh embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.
Example 1
Fig. 1 is a flowchart of an indoor positioning method according to a first embodiment of the present invention, and the present embodiment is applicable to a case of positioning an indoor object. The method may be performed by an indoor positioning device, which may be implemented in software and/or hardware, and may be configured in an electronic device, for example, the electronic device may be a device with communication and computing capabilities, such as a background server. As shown in fig. 1, the method specifically includes:
Step 101, acquiring device signal data and geomagnetic signal data of at least three positioning devices acquired by a target object at a to-be-positioned point.
The target object refers to a device capable of collecting device signal data and geomagnetic signal data, for example, the target object refers to a mobile device provided with software for collecting sensor information. The to-be-positioned point refers to a position point of the signal data acquired by the target object, and specific coordinate information of the position point needs to be determined. The positioning device refers to a device that can provide a reference for location information, for example, the positioning device includes a bluetooth device or a wifi device, etc. The at least three locating devices may be predetermined by unique device identification of the locating device.
Specifically, the positioning device is pre-installed in a space where a to-be-positioned point is located, and sends out a signal, the target object obtains the strength of a positioning signal at the to-be-positioned point through the sensor, the positioning signal comprises device signal data and geomagnetic signal data, and the strength of the positioning signal reflects the distance from the to-be-positioned point to the positioning device. In the embodiment of the invention, the position information of the to-be-positioned point is determined through the equipment signal data and the geomagnetic signal data of at least three positioning equipment. The specific number of positioning devices may be set according to the area of the space where the to-be-positioned point is located, which is not limited herein.
For example, when the positioning device is a bluetooth device, the mobile phone equipped with software for collecting sensor information is used offline to move indoors, and when the mobile phone moves to a to-be-positioned point, the acquired bluetooth signal data are: [ rssi ] BL,1 ,rssi BL,2 ,…,rss BL,j ,…,rssi BL,n ]Wherein, rsti BL,n Representing the received signal strength value sent by the nth Bluetooth device, and acquiring geomagnetic signal data as [ s ] x ,s y ,s z ]Wherein s is x 、s y Sum s z The magnetic field strengths in the three axial directions are respectively indicated. Optionally, because of a certain instability of the geomagnetic signal, preprocessing operation may be performed after acquiring geomagnetic signal data, and exemplary geomagnetic signal data of a preset number of geomagnetic signal data in an area around the to-be-positioned point are acquired, and the geomagnetic signal data of the to-be-positioned point is determined according to the preset number of geomagnetic signal data. For example, a peripheral area is determined by taking a to-be-determined point as a center and a radius of 0.5 m, five geomagnetic signal data are obtained at five position points within the area, [ s ] 1,x ,s 1,y ,s 1,z ]，[s 2,x ,s 2,y ,s 3,z ]…[s 5,x ,s 5,y ,s 5,z ]The geomagnetic signal data after pretreatment is [ sos ] 1 ,sos 2 ,…,sos i ,…,sos 5 ]Wherein, the method comprises the steps of, wherein,by preprocessing geomagnetic signal data, the influence of unstable geomagnetic signal reception is avoided.
Step 102, determining device predicted position information according to device signal data based on a pre-trained position prediction machine learning model.
The position prediction machine learning model is trained in advance, and the characteristic relation between the equipment signal data and the position information is represented. Specifically, the position prediction machine learning model is obtained by training pre-collected device sample signal data and position information of the associated marks. The device signal data is input into a pre-trained position prediction machine learning model, the characteristics of the device signal data are analyzed through the model, position information related to the characteristics of the device signal data is determined, and the position information is output as device prediction position information. The device predicted position information refers to position information of a to-be-positioned point obtained according to signal data of the positioning device.
In one possible embodiment, the training steps of the position prediction machine learning model are as follows:
acquiring device sample fingerprint data of at least three positioning devices; and inputting the fingerprint data of the equipment sample into a machine learning model to obtain a position prediction machine learning model.
Since the position prediction machine learning model is pre-trained, it is necessary to pre-acquire the device sample signal data. Device sample fingerprint data refers to a set of measurements of a locating device signal at a particular location. Illustratively, wifi device sample fingerprint data refers to RSS (Received signal strength ) measurements from surrounding individual router signals. Machine learning models refer to models used to handle classification and regression problems. Illustratively, the machine learning model may employ a machine learning algorithm framework XGBoost, XGBoost, which is an integrated learning algorithm, belonging to an open source algorithm framework of a gradient-lifted tree (BGDT), and may be used to address classification and regression problems in machine learning. Or the machine learning model may also select random forests, neural networks, logistic regression.
Specifically, a plurality of pieces of equipment sample fingerprint data are acquired in the space where the to-be-positioned points are located, and in order to ensure the accuracy of the model training results, the quantity of the equipment sample fingerprint data needs to be as much as possible. Therefore, the device sample signal data of all surrounding positioning devices are acquired at a plurality of position points, the current position is acquired at the same time, and the acquired data is the device sample fingerprint data.
Exemplary, device sample fingerprint data for k locating devices is [ mac 1 :rssi 1,1 ,mac 2 :rssi 1,2 ,…,mac j :rss 1,j ,…,mac k :rssi 1,k ,x 1 ,y 1 ]，[mac 1 :rssi 2,1 ,mac 2 :rssi 2,2 ,...,mac j :rss 2,j ,…,mac k :rssi 2,k ,x 2 ,y 2 ]…[mac 1 :rssi n,1 ,mac 2 :rssi n,2 ,...,mac j :rss n,j ,…,mac k :rssi n,k ,x n ,y n ]Wherein k represents signal data transmitted by k positioning devices which are co-energy detected at the detection position point; n represents the number of collected device sample fingerprint data, namely the number of collected data position points; x is x n ,y n Representing the position information of the nth device sample when the fingerprint data is acquired; rss n,j Representing the signal strength received in the nth device sample fingerprint data from the jth locating device; mac j The unique device identification information representing the jth pointing device may be represented by a mac address (Media Access Control Address ).
Modeling the positioning problem as a machine learning regression problem, inputting the fingerprint data of the equipment sample as training data into a machine learning model, such as inputting an XGBoost algorithm, and training to obtain a position prediction machine learning model. For example, the position information of the to-be-positioned point may be represented by coordinates, and the trained position prediction machine learning model includes an x-coordinate position prediction machine learning model and a y-coordinate position prediction machine learning model, and the x-coordinate value and the y-coordinate value are predicted by using the x-coordinate position prediction machine learning model and the y-coordinate position prediction machine learning model respectively.
In one possible embodiment, before inputting the device sample fingerprint data into the machine learning model, further comprising: determining target positioning equipment from at least three positioning equipment according to the space of the to-be-positioned point; and preprocessing the fingerprint data of the device sample according to the target positioning device.
Since the stability of the signal strength of each positioning device received in the space where the position to be determined is different, in order to ensure the stability of the device sample fingerprint data, the target positioning device is selected from all the positioning devices which can acquire the signals, and the device sample fingerprint data is determined from the device signal data of the target positioning device. The selection of the target positioning device may be determined according to the relationship between the positioning device and the space, and for example, the positioning device in the space is determined as the target positioning device because the signal sent by the positioning device located outside the space may still be acquired indoors, but a certain instability exists. The target locating device is determined, for example, from a unique device identification of the locating device.
Specifically, after the target positioning device is determined, screening all received device signal data according to the unique device identifier of the target positioning device, and obtaining device sample fingerprint data only comprising the signal data of the target positioning device. If the signal data of the target positioning device is not acquired at a certain position point, the signal intensity data of the target positioning device is assigned to a preset value in the device sample fingerprint data corresponding to the position point, so that the consistency of the format of the device sample fingerprint data is ensured, and the subsequent training is facilitated.
Illustratively, based on the above example, the device sample fingerprint data preprocessed according to the mac address of the target positioning device is: [ rssi ] 1,1 ,rssi 1,2 ,…,rss 1,j ,…,rssi 1,m ,x 1 ,y 1 ]，[rssi 2,1 ,rssi 2,2 ,...,rss 2,j ,…,rssi 2,m ,x 2 ,y 2 ]…[rssi n,1 ,rssi n,2 ,...,rss n,j ,…,rssi n,m ,x n ,y n ]The method comprises the steps of carrying out a first treatment on the surface of the Where m represents the number of object locating devices, and only RSS values and current location information of the m object locating devices are included in each device sample fingerprint data. Optionally, in order to ensure accuracy when the device predicts the location information, at least three positioning devices in step 101 are target positioning devices determined during model training.
And step 103, determining fusion predicted position information of the to-be-positioned point according to geomagnetic signal data and equipment predicted position information based on a predetermined geomagnetic fingerprint database, and taking the fusion predicted position information as a final positioning result.
The geomagnetic fingerprint library comprises association relations between position information of each position point in the space where the to-be-positioned point is located and geomagnetic signal data.
Specifically, position information which is most matched with geomagnetic signal data is determined in a geomagnetic fingerprint database according to the geomagnetic signal data to serve as geomagnetic prediction position information, the geomagnetic prediction position information is fused with equipment prediction position information obtained according to equipment signal data of positioning equipment to obtain fusion prediction position information, and the fusion prediction position information serves as a final positioning result of a to-be-positioned point, so that multimode fusion positioning is achieved, and positioning accuracy is improved.
In one possible embodiment, the geomagnetic fingerprint library is determined as follows: acquiring initial geomagnetic fingerprint data at least three position points in a space where a to-be-positioned point is located; dividing an initial geomagnetic fingerprint data set for each position point in turn according to the space distance; sequentially determining final geomagnetic fingerprint data of all the position points according to the initial geomagnetic fingerprint data set; and constructing a geomagnetic fingerprint database according to the final geomagnetic fingerprint data of each position point.
At least three position points indicate that a plurality of pieces of initial geomagnetic fingerprint data need to be acquired in the space, and because the geomagnetic data have certain instability, in order to avoid errors caused by the instability as much as possible, the geomagnetic fingerprint database is determined after preprocessing the initial geomagnetic fingerprint data.
Specifically, the origin at the plurality of acquired location pointsThe magnetic fingerprint data are: [ s ] 1,x ,s 1,y ,s 1,z ,x 1 ,y 1 ]，[s 2,x ,s 2,y ,s 3,z ,x 2 ,y 2 ]…[s n,x ,s n,y ,s n,z ,x n ,y n ]Wherein n represents that n pieces of initial geomagnetic fingerprint data are acquired at n position points in total, and x n And y n Representing the position information of the nth initial geomagnetic fingerprint data; s is(s) n,x ，s n,y Sum s n,z The magnetic field strengths of the magnetic field sensor in the x-axis, y-axis and z-axis directions in the nth initial geomagnetic fingerprint data are respectively represented.
When preprocessing initial geomagnetic fingerprint data, dividing the initial geomagnetic fingerprint data of the initial geomagnetic fingerprint data according to a certain space distance, determining the initial geomagnetic fingerprint data in the space distance belonging to the initial geomagnetic fingerprint data as an initial geomagnetic fingerprint data set, and then determining final geomagnetic fingerprint data according to all initial fingerprint data in the initial geomagnetic fingerprint data set. Exemplary, the first initial geomagnetic fingerprint data is obtained by using a first set of position coordinate points (x 1 ,y 1 ) Is the center of a circle and is set with a preset radius, for example, 0.5 m, and all the initial geomagnetic fingerprint data included in the circle are determined, for example, [ s ] 1,x ,s 1,y ,s 1,z ,x 1 ,y 1 ]，[s 2,x ,s 2,y ,s 3,z ,x 2 ,y 2 ]…[s 5,x ,s 5,y ,s 5,z ,x 5 ,y 5 ]The position information of the five pieces of initial geomagnetic fingerprint data all fall in the circle, then the five pieces of initial geomagnetic fingerprint data are initial geomagnetic fingerprint data sets, and final geomagnetic fingerprint data are determined according to the square sum of magnetic field intensities in three axial directions in the initial geomagnetic fingerprint data sets, for example, the preprocessed final geomagnetic fingerprint data are: [ sos ] 1 ,sos 2 ,…,sos i ,…,sos 5 ,x,y]Wherein, the method comprises the steps of, wherein,(x, y) is (x) 1 ,y 1 ) To the point of(x 5 ,y 5 ) Is defined by a center point of the lens. According to the method, final geomagnetic fingerprint data after preprocessing of all initial geomagnetic fingerprint data are sequentially determined, and finally n pieces of final geomagnetic fingerprint data are obtained to form a geomagnetic fingerprint database.
In one possible embodiment, step 103 includes: determining a geomagnetic signal data set matched with the equipment prediction position information in a geomagnetic fingerprint database; and determining target geomagnetic signal data matched with the geomagnetic signal data in the geomagnetic signal data set, and taking target position information associated with the target geomagnetic signal data as fusion prediction position information.
And in the determined geomagnetic fingerprint database, determining a geomagnetic signal data set matched with the equipment prediction position information according to the relation between the equipment preset position information and the positions in each geomagnetic fingerprint data in the geomagnetic fingerprint database. And then, matching the acquired geomagnetic signal data at the to-be-positioned point with each geomagnetic signal data in the geomagnetic signal data set, and determining target position information associated with the most matched target geomagnetic signal data as fusion prediction position information obtained by fusion of the geomagnetic signal data and the equipment signal data.
In one possible embodiment, determining a geomagnetic signal data set matching with the device predicted location information in a geomagnetic fingerprint library includes: and determining a matched geomagnetic signal data set according to the distance between the equipment prediction position information and candidate position information associated with each candidate geomagnetic signal data in the geomagnetic fingerprint database.
Specifically, in the geomagnetic fingerprint database, the distance between the device prediction position information and the candidate position information associated with each candidate geomagnetic signal data in the geomagnetic fingerprint database is smaller than a preset distance, and the geomagnetic signal data set is formed by all the matched geomagnetic signal data. For example, with the device predicted position information as the center of a circle, a radius threshold is set, for example, the radius threshold is 3 meters, specific data may be set according to the size of the space, which is not limited herein, and geomagnetic fingerprint data located in the circle in the geomagnetic fingerprint library is used as matching geomagnetic fingerprint data.
In one possible embodiment, determining target geomagnetic signal data matching geomagnetic signal data in a geomagnetic signal data set includes: and determining target geomagnetic signal data matched with the geomagnetic signal data in the geomagnetic signal data set based on a dynamic time warping algorithm.
The dynamic time warping algorithm (Dynamic Time Warping, DTW) is a dynamic programming algorithm that can calculate the similarity between two time series (consistent or inconsistent in length). In the embodiment of the invention, the method is used for determining the matching degree of geomagnetic signal data and each candidate geomagnetic signal data in a geomagnetic signal data set.
The embodiment of the invention determines the equipment prediction position information based on the equipment signal data, and then determines the fusion prediction position information based on the equipment prediction position information according to the geomagnetic signal data, thereby realizing the comprehensive utilization of the advantages of various positioning methods, ensuring the accuracy of positioning the positioning point to be positioned, avoiding the dependence on single positioning information, and having strong compatibility and wide application range.
Example two
Fig. 2 is a flowchart of an indoor positioning method in a second embodiment of the present invention, which is further optimized based on the first embodiment. As shown in fig. 2, the method includes:
step 201, acquiring device signal data and geomagnetic signal data of at least three positioning devices acquired by a target object at a to-be-positioned point; the positioning device comprises Bluetooth equipment and wifi equipment.
By arranging a plurality of types of positioning equipment in the space where the to-be-positioned point is located, the types of methods for determining the equipment prediction position information are further increased, the diversity of the equipment prediction position information is improved, multimode fusion positioning is realized, and the influence of single equipment data is avoided.
Step 202, based on a pre-trained wifi position prediction machine learning model, determining wifi device prediction position information according to wifi device signal data in device signal data.
The training steps of the wifi position prediction machine learning model are as follows: acquiring wifi equipment sample fingerprint data of at least three wifi equipment; and inputting the wifi equipment sample fingerprint data into a machine learning model to obtain a wifi position prediction machine learning model. Optionally, before the wifi device sample fingerprint data is input into the machine learning model, the method further includes: determining target wifi equipment from at least three positioning equipment according to the space of the to-be-positioned point; and preprocessing the sample fingerprint data of the wifi equipment according to the target wifi equipment.
The specific model training method may refer to the training method of the position prediction machine learning model in the first embodiment, and will not be described herein. And inputting the collected wifi equipment signal data into a wifi position prediction machine learning model to obtain wifi equipment prediction position information. The position information of the to-be-positioned point can be represented by coordinates, and the trained wifi position prediction machine learning model comprises a wifi-x coordinate position prediction machine learning model and a wifi-y coordinate position prediction machine learning model, and the wifi-x coordinate value and the wifi-y coordinate value are predicted by the wifi-x coordinate position prediction machine learning model and the wifi-y coordinate position prediction machine learning model respectively.
And 203, determining Bluetooth equipment prediction position information according to Bluetooth equipment signal data in the equipment signal data based on a pre-trained Bluetooth position prediction machine learning model.
The training steps of the Bluetooth position prediction machine learning model are as follows: acquiring Bluetooth equipment sample fingerprint data of at least three Bluetooth equipment; and inputting the sample fingerprint data of the Bluetooth equipment into a machine learning model to obtain a Bluetooth position prediction machine learning model. Optionally, before inputting the bluetooth device sample fingerprint data into the machine learning model, the method further comprises: determining a target Bluetooth device from at least three positioning devices according to the space of the to-be-positioned point; and preprocessing sample fingerprint data of the Bluetooth equipment according to the target Bluetooth equipment.
The specific model training method may refer to the training method of the position prediction machine learning model in the first embodiment, and will not be described herein. And inputting the acquired Bluetooth equipment signal data into a Bluetooth position prediction machine learning model to obtain Bluetooth equipment prediction position information. For example, the position information of the to-be-positioned point may be represented by coordinates, and the trained bluetooth position prediction machine learning model includes a bluetooth-x coordinate position prediction machine learning model and a bluetooth-y coordinate position prediction machine learning model, and the bluetooth-x coordinate value and the bluetooth-y coordinate value are predicted by using the bluetooth-x coordinate position prediction machine learning model and the bluetooth-y coordinate position prediction machine learning model, respectively.
And 204, determining a matched first geomagnetic signal data set in a geomagnetic fingerprint database according to wifi equipment prediction position information.
And determining a matched first geomagnetic signal data set according to the distance between the predicted position information of the wifi equipment and candidate position information associated with each candidate geomagnetic signal data in the geomagnetic fingerprint database.
Specifically, in the geomagnetic fingerprint database, the distance between the predicted position information of the wifi device and the candidate position information associated with each candidate geomagnetic signal data in the geomagnetic fingerprint database is smaller than a first preset distance, the first matched geomagnetic signal data are the first geomagnetic signal data, and all the first matched geomagnetic signal data form a first geomagnetic signal data set. The radius threshold is set by taking the wifi equipment prediction position information as the circle center, for example, the radius threshold is 3 meters, specific data can be set according to the space size, the method is not limited herein, and geomagnetic fingerprint data in the circle in the geomagnetic fingerprint library is used as first matched geomagnetic fingerprint data.
Step 205, determining a matched second geomagnetic signal data set in a geomagnetic fingerprint database according to the predicted position information of the Bluetooth device.
And determining a matched second geomagnetic signal data set according to the distance between the predicted position information of the Bluetooth device and candidate position information associated with each candidate geomagnetic signal data in the geomagnetic fingerprint database.
Specifically, in the geomagnetic fingerprint database, the distance between the predicted position information of the bluetooth device and the candidate position information associated with each candidate geomagnetic signal data in the geomagnetic fingerprint database is smaller than a second preset distance, and the second geomagnetic signal data set is formed by all the second matched geomagnetic signal data. For example, with the bluetooth device predicted location information as the center of a circle, a radius threshold is set, for example, the radius threshold is 3 meters, specific data may be set according to the size of the space, which is not limited herein, and geomagnetic fingerprint data located in the circle in the geomagnetic fingerprint library is used as second matching geomagnetic fingerprint data.
Step 206, determining target geomagnetic signal data matched with geomagnetic signal data in the first geomagnetic signal data set and the second geomagnetic signal data set, and taking target position information associated with the target geomagnetic signal data as fusion prediction position information.
And forming a complete geomagnetic signal data set by the first geomagnetic signal data set and the second geomagnetic signal data set, determining target geomagnetic signal data matched with the geomagnetic signal data in the complete geomagnetic signal data set, and taking target position information associated with the target geomagnetic signal data as fusion prediction position information. The specific matching method may refer to the first embodiment, and will not be described herein.
According to the embodiment of the invention, the Bluetooth device predicted position information and the wifi device predicted position information are respectively determined based on the Bluetooth device signal data and the wifi device signal data, and the fusion predicted position information is determined based on the Bluetooth device predicted position information and the wifi device predicted position information according to geomagnetic signal data, so that the advantages of comprehensively utilizing various positioning methods are realized, the accuracy of positioning a positioning point to be positioned is ensured, the dependence on single positioning information is avoided, and the method has strong compatibility and wide application range.
Example III
Fig. 3 is a flowchart of an indoor positioning method in the third embodiment of the present invention, which is further optimized based on the above-described embodiment. As shown in fig. 3, the method includes:
step 301, collecting device signal data and geomagnetic signal data of at least three positioning devices acquired by a target object at a to-be-positioned point, and collecting acceleration data information of the target object at the to-be-positioned point.
The acceleration data information is acquired through an inertial sensor, namely the inertial sensor is arranged in the target object, and the acceleration data information is determined at the to-be-positioned point.
Step 302, determining device predicted location information from device signal data based on a pre-trained location prediction machine learning model.
Step 303, based on a pre-determined geomagnetic fingerprint database, determining fusion predicted position information of the to-be-positioned point according to geomagnetic signal data and equipment predicted position information, and taking the fusion predicted position information as a final positioning result.
And 304, determining acceleration prediction position information according to the acceleration data information.
And determining acceleration prediction position information according to the acceleration data information based on the pedestrian dead reckoning method. Pedestrian Dead Reckoning (PDR) uses inertial sensors to estimate relative position, consisting essentially of three parts: step count: may be implemented using cameras, accelerometers, commercial pedometers. For accelerometers, peak detection, threshold setting, automatic correlation analysis, spectral analysis, and the like may be used. Step size estimation: and acceleration secondary integration and the like. Estimating the heading: typically based on a compass or gyroscope. For example, the acceleration data information is input into a PDR algorithm, and the obtained predicted coordinates are the acceleration predicted position information.
And 305, determining final predicted position information according to the acceleration predicted position information and the fusion predicted position information.
And fusing the acceleration prediction position information and the fusion prediction position information by using an Extended Kalman Filter (EKF) algorithm, a Kalman filter or a particle filter fusion algorithm to obtain final prediction position information. And the fusion prediction position information is obtained by fusion according to the device prediction position information and geomagnetic signal data, wherein the device prediction position information comprises Bluetooth device prediction position information and/or wifi device prediction position information. Specific determination methods can be referred to embodiment one and embodiment two.
According to the embodiment of the invention, the equipment prediction position information is determined based on the equipment signal data, the fusion prediction position information is determined by combining the equipment prediction position information and geomagnetic signal data, and then the new acceleration prediction position information and the fusion prediction position information are further fused to obtain the final prediction position information. The advantage of comprehensively utilizing various positioning methods is realized, so that the accuracy of positioning the positioning point to be positioned is ensured, the dependence on single positioning information is avoided, the compatibility is strong, and the application range is wide.
Example IV
Fig. 4 is a flowchart of an indoor positioning method in a fourth embodiment of the present invention, which is further optimized based on the above-described embodiment. As shown in fig. 4, the method includes:
step 401, acquiring device signal data and geomagnetic signal data of at least three positioning devices acquired by a target object at a to-be-positioned point.
Step 402, determining device predicted location information from device signal data based on a pre-trained location prediction machine learning model.
Step 403, based on a pre-determined geomagnetic fingerprint database, determining fusion predicted position information of the to-be-positioned point according to geomagnetic signal data and equipment predicted position information.
And step 404, correcting the fusion prediction position information according to the predetermined spatial context information to obtain a final positioning result.
The spatial context information is used to describe reachable and unreachable regions in the space where the pending site is located. Because the predicted position information may fall in an area (such as the inside of a wall) which cannot be reached in an indoor environment, the spatial context information is predetermined, and error correction is performed on the fused predicted position information, so that the condition that positioning coordinates are unreasonable is avoided. The fusion prediction position information is obtained by fusion of equipment prediction position information and geomagnetic signal data, or final prediction position information obtained by fusion of acceleration prediction position information and fusion prediction position information, wherein the equipment prediction position information comprises Bluetooth equipment prediction position information and/or wifi equipment prediction position information. Specific determination methods can be referred to embodiment one, embodiment two and embodiment three.
In one possible embodiment, step 404 includes: determining the position information of an reachable area of the space where the to-be-positioned point is located in the space context information; determining whether the fusion predicted location information matches the reachable region location information; if the predicted position information is matched with the predicted position information, determining the predicted position information as a final positioning result; otherwise, determining the position information closest to the fusion predicted position information in the reachable region position information as a final positioning result.
The space context information is predetermined, specifically, the indoor map is marked, and the indoor map is divided into two parts: and obtaining the spatial context information according to the position information of the reachable area and the unreachable area.
When the position correction is carried out, the fusion prediction position information is firstly converted into the coordinates of the pixel where the coordinates are located in the indoor map, whether the coordinates are in the reachable area position information or not is determined, if yes, the matching is successful, and the prediction position information is determined to be a final positioning result. If not, the fusion prediction position information is located in the unreachable area, and the position information closest to the fusion prediction position information in the reachable position information is determined as a final positioning result.
In the embodiment of the invention, the spatial context information is introduced to correct the error of the positioning result, so that the condition of unreasonable positioning coordinates is avoided.
Example five
Fig. 5 is a schematic structural diagram of an indoor positioning system in a fifth embodiment of the present invention, where the system includes a fingerprint data acquisition module, an on-line algorithm module, an off-line sensor data acquisition module, an on-line and off-line positioning algorithm coordinate prediction and fusion module, a spatial context information error correction module, and a positioning result display module.
Fingerprint data acquisition module: device sample fingerprint data for collecting training a position prediction machine learning model. Exemplary: the off-line fingerprint data acquisition is completed by using a smart phone provided with software for acquiring sensor information, the software continuously scans wifi, bluetooth and magnetic field intensity data received by a sensor, obtains the current position at the same time, and writes the acquired data into a file to form wifi equipment sample fingerprint data, bluetooth equipment sample fingerprint data and a geomagnetic fingerprint library.
An online algorithm module: the device sample fingerprint data is respectively input into a machine learning model as training data, and four position prediction machine learning models are obtained through training: f (F) wifi,x ，F wifi,y ，F BL,x ，F BL,y The method comprises the steps of respectively representing a wifi-x coordinate position prediction machine learning model, a wifi-y coordinate position prediction machine learning model, a Bluetooth-x coordinate position prediction machine learning model and a Bluetooth-y coordinate position prediction machine learning model. Wifi fingerprint data are used respectively, and the bluetooth fingerprint data predicts x coordinate and y coordinate value. The online positioning network service is used for testing the trained model, and the http network service is built by using flash to receive sensor data of the offline client and give out predicted coordinates, so that the accuracy of the training result of the model is determined.
The off-line sensor data acquisition module: the system is used for acquiring wifi equipment signal data, bluetooth equipment signal data, geomagnetic signal data and acceleration data information of at least three positioning equipment acquired by a target object at a to-be-positioned point.
And the coordinate prediction and fusion module of the on-line and off-line positioning algorithm: and acquiring data acquired by the off-line sensor data acquisition module, and inputting the data into a machine learning model acquired by the on-line algorithm module to acquire final predicted position information. Specific: respectively inputting the signal data of the wifi equipment into a learning model F wifi,x And F wifi,y Obtained predicted coordinates (x) a ,y a ) The method comprises the steps of carrying out a first treatment on the surface of the Respectively inputting Bluetooth equipment signal data into a machine learning model F BL,x And F BL,y Obtaining predicted coordinates (x) b ,y b ) The method comprises the steps of carrying out a first treatment on the surface of the In geomagnetic fingerprint library, the geomagnetic fingerprint is obtained by using coordinates (x a ,y a ) Radius r 0 Screening geomagnetic fingerprint data set within a range as S 0 In terms of coordinates (x b ,y b ) Radius r 1 Screening geomagnetic fingerprint data set within a range as S 1 . Let s=s 0 ∪S 1 Matching geomagnetic signal data acquired offline with magnetic field fingerprint data in S by using a dynamic time warping algorithm (DTW), and finding out a coordinate corresponding to the geomagnetic fingerprint data which is the best match as (x) c ,y c ). Running a PDR algorithm based on acceleration data information to obtain a predicted coordinate (x d ,y d ) The coordinates (x) are then fused using an Extended Kalman Filter (EKF) algorithm c ,y c ) And (x) d ,y d ) Obtaining coordinates (x) e ,y e ) As final position prediction position information.
And the spatial context information error correction module: determining the position information of an reachable area of the space where the to-be-positioned point is located in the space context information; determining whether the fusion predicted location information matches the reachable region location information; if the predicted position information is matched with the predicted position information, determining the predicted position information as a final positioning result; otherwise, determining the position information closest to the fusion predicted position information in the reachable region position information as a final positioning result.
Positioning result display module: and displaying the final positioning result obtained in the space context information error correction module in an indoor map, for example, using blue points to represent the current coordinate position in the indoor map, and using red points to represent the positions of the coordinate points passing through in history.
The embodiment of the invention comprehensively utilizes the advantages of various positioning modes, provides a set of multimode fusion positioning method for fusion positioning, and improves the positioning precision and stability. And introducing spatial context information to correct the positioning result, so as to avoid the situation that the positioning result is unreasonable.
Example six
Fig. 6 is a schematic structural diagram of an indoor positioning device in a sixth embodiment of the present invention, and the present embodiment is applicable to a case of positioning an indoor object. As shown in fig. 6, the apparatus includes:
The signal data acquisition module 610 is configured to acquire device signal data and geomagnetic signal data of at least three positioning devices acquired by a target object at a to-be-positioned point;
a device prediction module 620 for determining device predicted location information from the device signal data based on a pre-trained location prediction machine learning model;
the geomagnetic fusion prediction module 630 is configured to determine fusion predicted position information of a to-be-positioned point as a final positioning result according to the geomagnetic signal data and the device predicted position information based on a predetermined geomagnetic fingerprint database.
The embodiment of the invention determines the equipment prediction position information based on the equipment signal data, and then determines the fusion prediction position information based on the equipment prediction position information according to the geomagnetic signal data, thereby realizing the comprehensive utilization of the advantages of various positioning methods, ensuring the accuracy of positioning the positioning point to be positioned, avoiding the dependence on single positioning information, and having strong compatibility and wide application range.
Optionally, the geomagnetic fusion prediction module includes:
the geomagnetic signal matching unit is used for determining a geomagnetic signal data set matched with the equipment prediction position information in the geomagnetic fingerprint library;
The signal fusion prediction unit is used for determining target geomagnetic signal data matched with the geomagnetic signal data in the geomagnetic signal data set, and taking target position information associated with the target geomagnetic signal data as the fusion prediction position information.
Optionally, the geomagnetic signal matching unit is specifically configured to:
and determining a matched geomagnetic signal data set according to the distance between the equipment prediction position information and candidate position information associated with each candidate geomagnetic signal data in the geomagnetic fingerprint database.
Optionally, the signal fusion prediction unit is specifically configured to:
and determining target geomagnetic signal data matched with the geomagnetic signal data in the geomagnetic signal data set based on a dynamic time warping algorithm.
Optionally, the positioning device includes a bluetooth device and a wifi device;
correspondingly, the device prediction module is specifically configured to:
based on a pre-trained wifi position prediction machine learning model, determining wifi equipment prediction position information according to wifi equipment signal data in the equipment signal data;
and determining Bluetooth equipment prediction position information according to Bluetooth equipment signal data in the equipment signal data based on a pre-trained Bluetooth position prediction machine learning model.
Optionally, the geomagnetic fusion prediction module is specifically configured to:
determining a matched first geomagnetic signal data set in the geomagnetic fingerprint database according to the wifi equipment prediction position information;
determining a matched second geomagnetic signal data set in the geomagnetic fingerprint database according to the Bluetooth equipment prediction position information;
and determining target geomagnetic signal data matched with the geomagnetic signal data in the first geomagnetic signal data set and the second geomagnetic signal data set, and taking target position information associated with the target geomagnetic signal data as the fusion prediction position information.
Optionally, the signal data acquisition module further includes: collecting acceleration data information of a target object at a to-be-positioned point;
correspondingly, the device further comprises an acceleration prediction module, which is used for determining fusion predicted position information of the to-be-positioned point according to the geomagnetic signal data and the equipment predicted position information:
determining acceleration prediction position information according to the acceleration data information;
and determining final predicted position information according to the acceleration predicted position information and the fusion predicted position information.
Optionally, the apparatus further comprises a context modification module for, after determining the fused predicted position information of the to-be-positioned point based on the geomagnetic signal data and the device predicted position information,
And correcting the fusion prediction position information according to the predetermined spatial context information to obtain a final positioning result.
Optionally, the context modification module is specifically configured to:
determining the position information of an reachable area of the space where the to-be-positioned point is located in the space context information;
determining whether the fused predicted location information matches the reachable region location information;
if the fusion prediction position information is matched, determining the fusion prediction position information as a final positioning result;
otherwise, determining the position information closest to the fusion predicted position information in the reachable region position information as a final positioning result.
Optionally, the apparatus further comprises a machine learning model training module for:
acquiring device sample fingerprint data of the at least three positioning devices;
and inputting the equipment sample fingerprint data into a machine learning model to obtain a position prediction machine learning model.
Optionally, the machine learning model training module further comprises a sample data preprocessing unit for, prior to inputting the device sample fingerprint data into the machine learning model:
determining target positioning equipment from the at least three positioning equipment according to the space of the to-be-positioned point;
And preprocessing the fingerprint data of the device sample according to the target positioning device.
Optionally, the device further includes a geomagnetic fingerprint database determining module, configured to:
acquiring initial geomagnetic fingerprint data at least three position points in a space where a to-be-positioned point is located;
dividing an initial geomagnetic fingerprint data set for each position point in turn according to the space distance;
sequentially determining final geomagnetic fingerprint data of all the position points according to the initial geomagnetic fingerprint data set;
and constructing a geomagnetic fingerprint database according to the final geomagnetic fingerprint data of the position points.
The indoor positioning device provided by the embodiment of the invention can execute the indoor positioning method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the indoor positioning method.
Example seven
Fig. 7 is a schematic structural diagram of an electronic device according to a seventh embodiment of the present invention. Fig. 7 illustrates a block diagram of an exemplary electronic device 12 suitable for use in implementing embodiments of the present invention. The electronic device 12 shown in fig. 7 is merely an example and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.
As shown in fig. 7, the electronic device 12 is in the form of a general purpose computing device. Components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory device 28, a bus 18 that connects the various system components, including the system memory device 28 and the processing unit 16.
Bus 18 represents one or more of several types of bus structures, including a memory device bus or memory device controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include Industry Standard Architecture (ISA) bus, micro channel architecture (MAC) bus, enhanced ISA bus, video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
Electronic device 12 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by electronic device 12 and includes both volatile and nonvolatile media, removable and non-removable media.
The system storage 28 may include computer system readable media in the form of volatile memory such as Random Access Memory (RAM) 30 and/or cache memory 32. The electronic device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from or write to non-removable, nonvolatile magnetic media (not shown in FIG. 7, commonly referred to as a "hard disk drive"). Although not shown in fig. 7, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In such cases, each drive may be coupled to bus 18 through one or more data medium interfaces. The storage device 28 may include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of the embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in storage 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Program modules 42 generally perform the functions and/or methods of the embodiments described herein.
The electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), one or more devices that enable a user to interact with the device 12, and/or any devices (e.g., network card, modem, etc.) that enable the device 12 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 22. Also, the electronic device 12 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet, through a network adapter 20. As shown in fig. 7, the network adapter 20 communicates with other modules of the electronic device 12 over the bus 18. It should be appreciated that although not shown in fig. 7, other hardware and/or software modules may be used in connection with electronic device 12, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
The processing unit 16 executes various functional applications and data processing by running a program stored in the system storage device 28, for example, implementing the indoor positioning method provided by the embodiment of the present invention, including:
acquiring equipment signal data and geomagnetic signal data of at least three positioning equipment acquired by a target object at a to-be-positioned point;
determining device predicted location information from the device signal data based on a pre-trained location prediction machine learning model;
based on a pre-determined geomagnetic fingerprint library, determining fusion predicted position information of a to-be-positioned point according to geomagnetic signal data and equipment predicted position information, and taking the fusion predicted position information as a final positioning result.
Example eight
An eighth embodiment of the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements an indoor positioning method as provided by the embodiment of the present invention, including:
acquiring equipment signal data and geomagnetic signal data of at least three positioning equipment acquired by a target object at a to-be-positioned point;
determining device predicted location information from the device signal data based on a pre-trained location prediction machine learning model;
Based on a pre-determined geomagnetic fingerprint library, determining fusion predicted position information of a to-be-positioned point according to geomagnetic signal data and equipment predicted position information, and taking the fusion predicted position information as a final positioning result.
The computer storage media of embodiments of the invention may take the form of any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations of the present invention may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.

Claims (12)

1. An indoor positioning method, comprising:
acquiring equipment signal data and geomagnetic signal data of at least three positioning equipment acquired by a target object at a to-be-positioned point; collecting acceleration data information of a target object at a to-be-positioned point;
determining device predicted location information from the device signal data based on a pre-trained location prediction machine learning model;
based on a pre-determined geomagnetic fingerprint database, determining fusion predicted position information of a to-be-positioned point according to geomagnetic signal data and equipment predicted position information;
Wherein after determining the fusion predicted position information of the to-be-positioned point according to the geomagnetic signal data and the device predicted position information, the method further comprises:
inputting the acceleration data information into a pedestrian dead reckoning algorithm to obtain a predicted coordinate as acceleration predicted position information;
determining final predicted position information according to the acceleration predicted position information and the fusion predicted position information, and taking the final predicted position information as a final positioning result;
the determining fusion predicted position information of the to-be-positioned point based on the geomagnetic fingerprint database determined in advance according to the geomagnetic signal data and the equipment predicted position information comprises the following steps:
determining a geomagnetic signal data set matched with the equipment prediction position information in the geomagnetic fingerprint library;
determining target geomagnetic signal data matched with the geomagnetic signal data in the geomagnetic signal data set, and taking target position information associated with the target geomagnetic signal data as the fusion prediction position information;
the geomagnetic fingerprint database is determined as follows:
acquiring initial geomagnetic fingerprint data at least three position points in a space where a to-be-positioned point is located;
dividing an initial geomagnetic fingerprint data set for each position point in turn according to the space distance;
Determining final geomagnetic fingerprint data according to the square sum of magnetic field intensities in three axial directions in the initial geomagnetic fingerprint data set;
forming a geomagnetic fingerprint database according to the final geomagnetic fingerprint data of the position points;
determining final predicted position information according to the acceleration predicted position information and the fusion predicted position information, including:
and fusing the acceleration prediction position information and the fusion prediction position information through an extended Kalman filtering algorithm and/or a Kalman filtering or particle filtering fusion algorithm to determine final prediction position information.
2. The method of claim 1, wherein determining a geomagnetic signal data set that matches the device predicted location information in the geomagnetic fingerprint library, comprises:
and determining a matched geomagnetic signal data set according to the distance between the equipment prediction position information and candidate position information associated with each candidate geomagnetic signal data in the geomagnetic fingerprint database.
3. The method of claim 1, wherein determining target geomagnetic signal data that matches the geomagnetic signal data in the set of geomagnetic signal data, comprises:
And determining target geomagnetic signal data matched with the geomagnetic signal data in the geomagnetic signal data set based on a dynamic time warping algorithm.
4. The method of claim 1, wherein the location device comprises a bluetooth device and a wifi device;
accordingly, determining device predicted location information from the device signal data based on a pre-trained location prediction machine learning model, comprising:
based on a pre-trained wifi position prediction machine learning model, determining wifi equipment prediction position information according to wifi equipment signal data in the equipment signal data;
and determining Bluetooth equipment prediction position information according to Bluetooth equipment signal data in the equipment signal data based on a pre-trained Bluetooth position prediction machine learning model.
5. The method of claim 4, wherein determining fused predicted location information for the site to be located based on the geomagnetic signal data and the device predicted location information based on a pre-determined geomagnetic fingerprint library, comprises:
determining a matched first geomagnetic signal data set in the geomagnetic fingerprint database according to the wifi equipment prediction position information;
Determining a matched second geomagnetic signal data set in the geomagnetic fingerprint database according to the Bluetooth equipment prediction position information;
and determining target geomagnetic signal data matched with the geomagnetic signal data in the first geomagnetic signal data set and the second geomagnetic signal data set, and taking target position information associated with the target geomagnetic signal data as the fusion prediction position information.
6. The method of claim 1, further comprising, after determining fused predicted position information for the to-be-positioned point based on the geomagnetic signal data and the device predicted position information:
and correcting the fusion prediction position information according to the predetermined spatial context information to obtain a final positioning result.
7. The method of claim 6, wherein correcting the fused predicted location information based on predetermined spatial context information to obtain a final positioning result comprises:
determining the position information of an reachable area of the space where the to-be-positioned point is located in the space context information;
determining whether the fused predicted location information matches the reachable region location information;
If the fusion prediction position information is matched, determining the fusion prediction position information as a final positioning result;
otherwise, determining the position information closest to the fusion predicted position information in the reachable region position information as a final positioning result.
8. The method of claim 1, wherein the training step of the position prediction machine learning model is as follows:
acquiring device sample fingerprint data of the at least three positioning devices;
and inputting the equipment sample fingerprint data into a machine learning model to obtain a position prediction machine learning model.
9. The method of claim 8, further comprising, prior to inputting the device sample fingerprint data into a machine learning model:
determining target positioning equipment from the at least three positioning equipment according to the space of the to-be-positioned point;
and preprocessing the fingerprint data of the device sample according to the target positioning device.
10. An indoor positioning device, comprising:
the signal data acquisition module is used for acquiring equipment signal data and geomagnetic signal data of at least three positioning equipment acquired by a target object at a to-be-positioned point;
The equipment prediction module is used for predicting a machine learning model based on a pre-trained position and determining equipment prediction position information according to the equipment signal data;
the geomagnetic fusion prediction module is used for determining fusion prediction position information of a to-be-positioned point according to the geomagnetic signal data and the equipment prediction position information based on a predetermined geomagnetic fingerprint database;
the signal data acquisition module is also used for acquiring acceleration data information of the target object at the to-be-positioned point;
the device further comprises an acceleration prediction module, wherein the acceleration prediction module is used for determining fusion predicted position information of a to-be-positioned point according to the geomagnetic signal data and the equipment predicted position information:
inputting the acceleration data information into a pedestrian dead reckoning algorithm to obtain a predicted coordinate as acceleration predicted position information;
determining final predicted position information according to the acceleration predicted position information and the fusion predicted position information, and taking the final predicted position information as a final positioning result;
the geomagnetic fingerprint database determining module is used for:
acquiring initial geomagnetic fingerprint data at least three position points in a space where a to-be-positioned point is located;
dividing an initial geomagnetic fingerprint data set for each position point in turn according to the space distance;
Sequentially determining final geomagnetic fingerprint data of all the position points according to the initial geomagnetic fingerprint data set;
forming a geomagnetic fingerprint database according to the final geomagnetic fingerprint data of the position points;
geomagnetic fusion prediction module, including:
the geomagnetic signal matching unit is used for determining a geomagnetic signal data set matched with the equipment prediction position information in the geomagnetic fingerprint library;
the signal fusion prediction unit is used for determining target geomagnetic signal data matched with the geomagnetic signal data in the geomagnetic signal data set, and taking target position information associated with the target geomagnetic signal data as the fusion prediction position information;
determining final predicted position information according to the acceleration predicted position information and the fusion predicted position information, including:
and fusing the acceleration prediction position information and the fusion prediction position information through an extended Kalman filtering algorithm and/or a Kalman filtering or particle filtering fusion algorithm to determine final prediction position information.
11. An electronic device, comprising:
one or more processors;
storage means for storing one or more programs,
When executed by the one or more processors, causes the one or more processors to implement the indoor positioning method as recited in any one of claims 1-9.
12. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the indoor positioning method according to any one of claims 1-9.
CN202110287485.7A 2021-03-17 2021-03-17 Indoor positioning method, device, electronic equipment and storage medium Active CN113063420B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110287485.7A CN113063420B (en) 2021-03-17 2021-03-17 Indoor positioning method, device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110287485.7A CN113063420B (en) 2021-03-17 2021-03-17 Indoor positioning method, device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN113063420A CN113063420A (en) 2021-07-02
CN113063420B true CN113063420B (en) 2024-02-02

Family

ID=76561079

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110287485.7A Active CN113063420B (en) 2021-03-17 2021-03-17 Indoor positioning method, device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113063420B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114364018B (en) * 2021-12-24 2023-10-13 盒马(中国)有限公司 Positioning method and device

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105043380A (en) * 2015-06-29 2015-11-11 武汉大学 Indoor navigation method based on a micro electro mechanical system, WiFi (Wireless Fidelity) positioning and magnetic field matching
CN106153049A (en) * 2016-08-19 2016-11-23 北京羲和科技有限公司 A kind of indoor orientation method and device
CN106979778A (en) * 2016-01-15 2017-07-25 阿里巴巴集团控股有限公司 A kind of localization method, device and mobile terminal
CN107830862A (en) * 2017-10-13 2018-03-23 桂林电子科技大学 A kind of method of the indoor positioning pedestrian tracking based on smart mobile phone
CN108632761A (en) * 2018-04-20 2018-10-09 西安交通大学 A kind of indoor orientation method based on particle filter algorithm
CN112135250A (en) * 2020-08-12 2020-12-25 浙江大华技术股份有限公司 Indoor positioning method and device, computer equipment and readable storage medium

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105043380A (en) * 2015-06-29 2015-11-11 武汉大学 Indoor navigation method based on a micro electro mechanical system, WiFi (Wireless Fidelity) positioning and magnetic field matching
CN106979778A (en) * 2016-01-15 2017-07-25 阿里巴巴集团控股有限公司 A kind of localization method, device and mobile terminal
CN106153049A (en) * 2016-08-19 2016-11-23 北京羲和科技有限公司 A kind of indoor orientation method and device
CN107830862A (en) * 2017-10-13 2018-03-23 桂林电子科技大学 A kind of method of the indoor positioning pedestrian tracking based on smart mobile phone
CN108632761A (en) * 2018-04-20 2018-10-09 西安交通大学 A kind of indoor orientation method based on particle filter algorithm
CN112135250A (en) * 2020-08-12 2020-12-25 浙江大华技术股份有限公司 Indoor positioning method and device, computer equipment and readable storage medium

Also Published As

Publication number Publication date
CN113063420A (en) 2021-07-02

Similar Documents

Publication Publication Date Title
US10018474B2 (en) Method and system for using offline map information aided enhanced portable navigation
US9696165B2 (en) Last-mile navigation using smartphones
US9326103B2 (en) Indoor location-finding using magnetic field anomalies
US20170219359A1 (en) Method and system for estimating uncertainty for offline map information aided enhanced portable navigation
US10547976B2 (en) Method and system for assigning point of sale information
US9462423B1 (en) Qualitative and quantitative sensor fusion for indoor navigation
CN115685060A (en) Indoor fingerprint map construction method and related device
Shu et al. Efficient image-based indoor localization with MEMS aid on the mobile device
US20220155402A1 (en) Transition Detection
CN113063420B (en) Indoor positioning method, device, electronic equipment and storage medium
CN114554391A (en) Parking lot vehicle searching method, device, equipment and storage medium
CN107889056B (en) Method and device for collecting indoor position data of multi-story building and readable medium
Gong et al. An enhanced indoor positioning solution using dynamic radio fingerprinting spatial context recognition
CN114185003B (en) Indoor positioning method and system based on multi-source signal fusion
CN110853098A (en) Robot positioning method, device, equipment and storage medium
CN107869990B (en) Method and device for acquiring indoor position data, computer equipment and readable medium
Guo et al. Improvement of localization with artificial landmark for mobile manipulator
CN113485347B (en) Motion trail optimization method and system
CN110779533A (en) Navigation method, system and electronic equipment
RU2759773C1 (en) Method and system for determining the location of the user
EP4366339A1 (en) Method for constructing indoor map and related apparatus
CN114526720B (en) Positioning processing method, device, equipment and storage medium
Kamalam et al. Research Article Augmented Reality-Centered Position Navigation for Wearable Devices with Machine Learning Techniques
WO2022261539A1 (en) Smartphone-based inertial odometry
MAILKA et al. An efficient end-to-end EKF-SLAM architecture based on LiDAR, GNSS, and IMU data sensor fusion for autonomous ground vehicles

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant