CN113766635B

CN113766635B - Indoor positioning method and system

Info

Publication number: CN113766635B
Application number: CN202111115879.0A
Authority: CN
Inventors: 王欣; 李元波; 岳一民; 周波
Original assignee: CCB Finetech Co Ltd
Current assignee: CCB Finetech Co Ltd
Priority date: 2021-09-23
Filing date: 2021-09-23
Publication date: 2024-04-19
Anticipated expiration: 2041-09-23
Also published as: CN113766635A

Abstract

The invention provides an indoor positioning method and system, which relate to the technical field of machine learning and positioning, wherein the method comprises the following steps: a pre-positioning step: setting a Bluetooth beacon for broadcasting Bluetooth signals in a space to be positioned; setting data acquisition equipment for acquiring Bluetooth signals in a space to be positioned, wherein the data acquisition equipment carries regional position information; machine learning is carried out on the Bluetooth signals and the regional position information, and characteristic analysis is carried out to obtain a positioning model of the space to be positioned, so that the pre-positioning of the space to be positioned is completed; positioning: and the equipment to be positioned is positioned in the space to be positioned, which is subjected to the pre-positioning, the Bluetooth signals broadcasted by the Bluetooth beacons are collected to generate positioning data, the positioning data are matched with the positioning model, the space position information of the equipment to be positioned is obtained, and the positioning is finished. According to the invention, the positioning model is built through machine learning, so that the positioning accuracy can be effectively improved during positioning, and the equipment can be flexibly deployed to meet various positioning precision requirements.

Description

Indoor positioning method and system

Technical Field

The present invention relates to the field of machine learning and positioning technologies, and in particular, to an indoor positioning method and system.

Background

In recent years, with the vigorous development of the technology of the Internet of things, various spatial position locating technologies and related systems are rapidly developed. Currently, the GPS positioning system and the Beidou positioning system are widely applied in the aspect of positioning navigation. However, the signal intensity of the two positioning system signals is greatly attenuated due to the influence of building shielding, so that the indoor positioning accuracy is seriously affected. Therefore, how to realize indoor accurate positioning is an important subject for research in various fields and research institutions.

At present, the mainstream indoor positioning method mainly comprises the following steps: zigBee technology, UWB technology, wireless local area network technology, bluetooth technology, and the like. The ZigBee technology has the advantages of good penetrability, low energy consumption and the like, but is easy to interfere, and the positioning precision is low, so that the positioning system is difficult to popularize; the wireless local area network technology has the advantages of low deployment cost, simple algorithm and the like, but the signal is easy to be interfered, and the Wi-Fi beacon needs to be connected with a wired power supply in the arrangement process, so that the application is limited; the UWB positioning technology has high energy consumption and high cost, and needs a specific tag (compared with a natural tag of a terminal such as a mobile phone); the Bluetooth technology has the advantages that the equipment is small in size and can be integrated into a micro mobile terminal, and along with the development of the Bluetooth technology, the power consumption is lower, the transmission distance, the stability and the safety are greatly improved, so that the Bluetooth technology has great advantages in indoor positioning.

The main stream of Bluetooth indoor positioning modes is base station triangulation positioning: by receiving the base station signal, performing triangulation by using the signal characteristics (the triangulation positioning is a mode of calculating the spatial position of a target by calculating a spherical intersection point through a base point and ranging), determining the relative position with the base station, and determining the current indoor position by combining the base station coordinate position, wherein the wireless positioning, the infrared positioning and the ultrasonic positioning belong to the base station positioning. The main drawbacks of this positioning approach are the computational effort, the need to deploy additional equipment, which will add significantly to the cost. In view of the foregoing, there is a need for a bluetooth positioning scheme that overcomes the above-mentioned drawbacks, reduces the deployment of devices, and reduces the computational effort.

Disclosure of Invention

In order to solve the problems in the prior art, the invention provides an indoor positioning method and an indoor positioning system. The invention uses sample data and machine learning mode to logically divide the positioning space, abstract the positioning space into machine learning target types, and then classifies the collected Bluetooth signals to obtain positioning results; the invention has better fault tolerance rate, smaller calculation workload and more flexible equipment deployment quantity.

In a first aspect of an embodiment of the present invention, an indoor positioning method is provided, where the method includes:

A pre-positioning step: setting a Bluetooth beacon for broadcasting Bluetooth signals in a space to be positioned;

setting data acquisition equipment for acquiring the Bluetooth signals in the space to be positioned, wherein the data acquisition equipment carries regional position information;

machine learning is carried out on the Bluetooth signals and the regional position information, and characteristic analysis is carried out to obtain a positioning model of the space to be positioned, so that the pre-positioning of the space to be positioned is completed;

Positioning: and the equipment to be positioned is positioned in the space to be positioned, which is subjected to the pre-positioning, the Bluetooth signals broadcasted by the Bluetooth beacons are collected to generate positioning data, the positioning data are matched with the positioning model, the space position information of the equipment to be positioned is obtained, and the positioning is finished.

Further, the bluetooth beacon continuously broadcasts bluetooth signals according to the set signal intensity, wherein the broadcast bluetooth signals comprise mac addresses of the bluetooth beacon.

Further, the area location information includes: scene information, map information, and area information; wherein, the scene information is the attribution of the map; the map information is a plan view of a scene, the plan view is divided according to meshing, and each grid is provided with corresponding coordinates; the region information includes mesh data and coordinate data.

Further, machine learning is performed on the bluetooth signals and the regional position information, and characteristic analysis is performed to obtain a positioning model of the space to be positioned, so as to complete the pre-positioning of the space to be positioned, including:

Obtaining positioning data according to the Bluetooth signals acquired by the data acquisition equipment, wherein the positioning data comprises the mac address of the Bluetooth beacon and the strength of the Bluetooth signals;

and obtaining learning data according to the regional position information carried by the data acquisition equipment and the acquired Bluetooth signals, wherein the learning data comprises scene information, map information, regional information, mac addresses of Bluetooth beacons and strength of the Bluetooth signals.

Further, the area information is the minimum unit for dividing the space to be located, and 1 bluetooth beacon corresponds to 1 mac address and 1 area information.

Further, the method further comprises:

And filtering the positioning data and the learning data to obtain the filtered positioning data and learning data.

Further, filtering the positioning data and the learning data to obtain filtered positioning data and learning data, including:

And according to the mac address of the positioning data and the intensity of the Bluetooth signal, learning the mac address of the data, the intensity of the Bluetooth signal and the area position information, filtering the data of which the mac address is not in the mac address range of the Bluetooth beacon in the space to be positioned, the Bluetooth signal intensity is not in the set signal intensity range or the area position information is not in the area position information range carried by the data acquisition equipment, and obtaining the filtered positioning data and the filtered learning data.

performing machine learning according to the learning data, performing characteristic analysis on Bluetooth signals at different area positions to obtain Bluetooth signal characteristics of each area position, establishing association between area position information and the Bluetooth signal characteristics of the area position, and generating a positioning model; the Bluetooth signal characteristics comprise mac addresses of Bluetooth beacons and intensities of Bluetooth signals;

And taking the positioning data as an input sample, carrying out position identification through a positioning model to obtain regional position information, comparing the regional position information with the actual position, and verifying the positioning model according to the comparison result.

Further, taking the positioning data as an input sample, carrying out position recognition through a positioning model to obtain region position information, comparing the region position information with an actual position, and verifying the positioning model according to a comparison result, wherein the method comprises the following steps:

And judging whether the regional position information is consistent with the actual position by a tester, if not, acquiring positioning deviation feedback information reported by the tester, authenticating by a background person, and if the authentication is passed, generating new learning data according to the positioning deviation feedback information, and performing iterative training on the positioning model.

And after iterative training of the positioning model, stopping training and obtaining the positioning model after training is completed when the positioning accuracy of the comparison result reaches a set accuracy threshold.

Further, in the positioning step, the method includes:

And the Bluetooth signals broadcasted by the Bluetooth beacons are collected by the equipment to be positioned so as to generate positioning data, and the filtered positioning data are obtained.

Further, the method for filtering the positioning data generated by collecting the bluetooth signal broadcasted by the bluetooth beacon by the device to be positioned to obtain the filtered positioning data includes:

and filtering the mac address range of the Bluetooth beacon, which is not in the space to be positioned, according to the mac address of the positioning data and the strength of the Bluetooth signal, and obtaining the filtered positioning data.

Further, in the positioning step, the method includes:

Generating positioning data according to Bluetooth signals broadcasted by the Bluetooth beacons acquired by the equipment to be positioned;

Inputting positioning data into the trained positioning model for position identification to obtain the regional position information of the equipment to be positioned;

and identifying and obtaining the spatial position information of the equipment to be positioned according to the regional position information of the equipment to be positioned, and completing positioning.

Further, the data acquisition equipment is a mobile terminal provided with a virtual Bluetooth positioning card;

the device to be positioned is a mobile terminal provided with a virtual Bluetooth positioning card or a Bluetooth positioning card arranged on a moving or fixed object.

Further, the method further comprises:

and staying the data acquisition equipment in the space to be positioned for a set time length, and continuously collecting Bluetooth signals broadcast by the Bluetooth beacons in the area.

Further, the method further comprises:

Setting a data acquisition base station in a space to be positioned; when the equipment to be positioned is a Bluetooth positioning card arranged on a moving or fixed object, the data acquisition base station acquires Bluetooth signals acquired by the Bluetooth positioning card.

Further, the data acquisition base station is a LoRa base station, and a LoRa protocol is adopted to provide data transfer service for the LoRa equipment in the coverage area; and running an agent program in the LoRa base station, and transferring Bluetooth signals acquired by the equipment to be positioned in a LAN mode.

Further, the method further comprises:

Corresponding positioning management is carried out according to a positioning management instruction input by a user, wherein the positioning management instruction comprises: bluetooth beacon management, target object management and fixed positioning object management;

and displaying the device attribute information of the Bluetooth beacon when the Bluetooth beacon management is carried out, wherein the device attribute information of the Bluetooth beacon at least comprises: mac address, device name, device power;

When the target object management is carried out, displaying the space position information of the equipment to be positioned of the target object, and tracking the moving track of the target object;

and displaying the spatial position information of the equipment to be positioned of the fixed positioning object when the fixed positioning object is managed.

In a second aspect of the embodiments of the present invention, an indoor positioning system is provided, the system comprising: bluetooth beacons, data acquisition equipment, a positioning processing device and equipment to be positioned; wherein,

The Bluetooth beacon is arranged in the space to be positioned and used for broadcasting Bluetooth signals;

the data acquisition equipment carries regional position information and is arranged in a space to be positioned and used for acquiring Bluetooth signals broadcasted by the Bluetooth beacons;

When the positioning is performed, the positioning processing device is used for performing machine learning on the Bluetooth signals and the regional position information, performing characteristic analysis to obtain a positioning model of the space to be positioned, and completing the positioning of the space to be positioned;

when positioning, the equipment to be positioned is positioned in a space to be positioned, which is subjected to pre-positioning, and is used for acquiring Bluetooth signals broadcasted by a Bluetooth beacon to generate positioning data;

And the positioning processing device matches the positioning data with the positioning model to obtain the spatial position information of the equipment to be positioned, and positioning is completed.

Further, the positioning processing device is specifically configured to:

when the positioning is performed, positioning data are obtained according to the Bluetooth signals acquired by the data acquisition equipment, wherein the positioning data comprise the mac address of the Bluetooth beacon and the strength of the Bluetooth signals;

Further, the positioning processing device is specifically configured to:

During positioning, positioning data are generated according to Bluetooth signals broadcasted by the Bluetooth beacons acquired by equipment to be positioned;

Further, the data acquisition device is specifically configured to:

Further, the system further comprises: a data acquisition base station; wherein,

The data acquisition base station is arranged in the space to be positioned; when the equipment to be positioned is a Bluetooth positioning card arranged on a moving or fixed object, the data acquisition base station acquires Bluetooth signals acquired by the Bluetooth positioning card.

Further, the system further comprises: the positioning management device is used for carrying out corresponding positioning management according to a positioning management instruction input by a user, wherein the positioning management instruction comprises: bluetooth beacon management, target object management and fixed positioning object management;

In a third aspect of the embodiments of the present invention, a computer device is provided, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing an indoor positioning method when executing the computer program.

In a fourth aspect of the embodiments of the present invention, a computer-readable storage medium storing a computer program that when executed by a processor implements an indoor positioning method is presented.

According to the indoor positioning method and system, the positioning space is logically divided by using the sample data and the machine learning mode, the positioning space is abstracted into the machine learning target type, the acquired Bluetooth signals are classified, so that the positioning result is acquired, the fault tolerance of the whole scheme equipment is better, the probability of generating instability of the whole positioning system due to instability of single equipment is reduced, the influence on the whole positioning effect is small, and only 1 complete beacon equipment is needed for coordinates in determining an area; the calculation workload is less, and when an object is positioned, the position information of the object in the positioning space can be determined only by matching the received Bluetooth signal with the existing model database; the equipment deployment quantity is more flexible, and when the high-precision requirement is met for positioning, bluetooth beacons can be deployed more, so that the positioning precision is improved; only the regional positioning requirement can deploy the beacon equipment, the regional coverage is completed, and the cost for wholly deploying the beacon equipment is lower.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a flow chart of an indoor positioning method according to an embodiment of the invention.

FIG. 2 is a flow chart of data collection and machine learning according to an embodiment of the invention.

Fig. 3 is a schematic diagram illustrating a flow chart of indoor bluetooth positioning according to an embodiment of the present invention.

FIG. 4 is a schematic diagram of an indoor positioning system according to an embodiment of the invention.

FIG. 5 is a schematic diagram of an indoor positioning system according to two embodiments of the present invention.

Fig. 6 is a schematic view of an indoor positioning system architecture according to a third embodiment of the present invention.

FIG. 7 is a schematic diagram of a computer device according to an embodiment of the invention.

Detailed Description

The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are presented merely to enable those skilled in the art to better understand and practice the invention and are not intended to limit the scope of the invention in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

Those skilled in the art will appreciate that embodiments of the invention may be implemented as a system, apparatus, device, method, or computer program product. Accordingly, the present disclosure may be embodied in the following forms, namely: complete hardware, complete software (including firmware, resident software, micro-code, etc.), or a combination of hardware and software.

According to the embodiment of the invention, an indoor positioning method and an indoor positioning system are provided, and relate to the technical field of machine learning and positioning.

According to the invention, a sample data and machine learning mode is used for logically dividing a positioning space, abstracting the positioning space into machine learning target types, and classifying and processing the acquired Bluetooth signals to obtain a positioning result; the calculation workload is less, and when an object is positioned, the position information of the object in the positioning space can be determined only by matching the received Bluetooth signal with the existing model database; the equipment deployment quantity is more flexible, and when the high-precision requirement is met for positioning, bluetooth beacons can be deployed more, so that the positioning precision is improved; only the regional positioning requirement can deploy the beacon equipment, the regional coverage is completed, and the cost for wholly deploying the beacon equipment is lower.

In the embodiments of the present invention, terms to be described are as follows:

beacon: the Bluetooth beacon is used for constructing a basic equipment unit of a Bluetooth signal field; bluetooth beacons are miniature, low-power, broadcast bluetooth signal devices that can be discovered by other devices that actively scan for bluetooth signals. The Bluetooth beacon is small in size and carries a battery, long-time work can be achieved by adjusting power consumption parameters, and the maximum theoretical time can reach 5 years. The information broadcast in the bluetooth broadcast packet of the bluetooth beacon includes 2 aspects: 1. the mac address of the bluetooth beacon can be used as device identification information (slave device from which mac address the broadcast packet comes); 2. the signal strength rssi value of the bluetooth beacon can be used to determine the location information of the device (the signal strength of the scanner when searching for the bluetooth beacon).

Bluetooth positioning card: navCard, a wearable bluetooth device, simultaneously integrated with a LoRa wireless module, can actively discover bluetooth signals broadcast by surrounding bluetooth beacons. The Bluetooth card is bound to a positioned person or article, the device can actively collect peripheral Bluetooth signals and report relevant information to the LoRa base station, and the purpose of position monitoring can be achieved by judging the strength of the collected signals.

Site: can be a park, a site, a building and a scene, and is the home of the map.

Map: the map, the plan view of a certain scene, the CAD-based design drawing, the gridding and the coordinated in the system are used for interface display and as a positioning support.

Area: the mesh defined on the map has independent coordinates.

Machine learning (Supervised learning): the invention adopts supervised learning, and can learn or establish a pattern (learning model) from training data and infer a new instance according to the pattern. Training data is composed of input objects (typically vectors) and expected outputs. The output of the function may be a continuous value (known as regression analysis) or a predictive classification label (known as classification).

APP-virtual locator card: the data acquisition device can realize the function of a virtual positioning card by installing mobile application, actively discovers Bluetooth signals broadcasted by peripheral Bluetooth beacons (beacons), continuously receives the Bluetooth signals broadcasted by the peripheral Bluetooth beacons, and takes acquired information data as sample data learned by an early algorithm.

APP-positioning verification: when the data acquisition equipment continuously generates a displacement process in space and reports Bluetooth signals broadcast by the Bluetooth beacons, a positioning button can be clicked at any time, and whether the positioning position is consistent with the actual position or not is checked through a map mode to perform positioning verification. ( Such as: the positioning is consistent and has no objection; positioning errors and reporting platform feedback; the correct data after user authentication is directly converted into data which can be used by the machine in a learning way, so that the efficiency of machine learning and model building is improved. )

BBLS: bluetooth Based Location System, bluetooth positioning system.

BBLS-biz unit: and a data filtering unit for filtering the data.

BBLS-locate unit: the machine learning unit comprises two parts of functions, namely 1, establishing the association between equipment characteristics mac, rsi and position characteristics site, map, area, namely a data model; 2. providing a location service.

MySQL: and the database unit is used for storing the positioning data model and the positioning related data.

The principles and spirit of the present invention are explained in detail below with reference to several representative embodiments thereof.

Fig. 1 is a flow chart of an indoor positioning method according to an embodiment of the invention. As shown in fig. 1, the method includes: a pre-positioning step and a positioning step;

in the pre-positioning step, the positioning step,

S101, setting a Bluetooth beacon for broadcasting Bluetooth signals in a space to be positioned;

S102, setting data acquisition equipment for acquiring the Bluetooth signals in the space to be positioned, wherein the data acquisition equipment carries regional position information;

S103, machine learning is carried out on the Bluetooth signals and the regional position information, and characteristic analysis is carried out to obtain a positioning model of the space to be positioned, so that the pre-positioning of the space to be positioned is completed;

In the course of the positioning step,

S104, the equipment to be positioned is positioned in the space to be positioned, which is subjected to the pre-positioning, the Bluetooth signals broadcasted by the Bluetooth beacons are collected to generate positioning data, the positioning data are matched with the positioning model, the space position information of the equipment to be positioned is obtained, and the positioning is completed.

In order to more clearly explain the above indoor positioning method, each step is described in detail as follows.

In S101, the bluetooth beacon continuously broadcasts a bluetooth signal according to the set signal strength, where the broadcast bluetooth signal includes the mac address of the bluetooth beacon.

Bluetooth beacons (beacons) have unique identifications and can continuously broadcast bluetooth signals. When the Bluetooth beacon broadcasts and transmits a message, besides broadcasting and transmitting the mac address (unique identifier ID of the device), the strength (rsti field intensity information, RECEIVED SIGNAL STRENGTH indication) of the Bluetooth signal is also broadcasted, and the strength can reflect the distance information between two devices, so that the Bluetooth beacon can be used as the basis of a positioning scheme.

Meanwhile, the Bluetooth beacon has the characteristics of low power consumption, battery power supply, long endurance and low cost, and in project implementation, the Bluetooth beacon has the advantage of being capable of conveniently paving a large area without changing original facilities on a paving site.

The data acquisition equipment is a mobile terminal provided with a virtual Bluetooth positioning card; for example, a mobile phone provided with a data acquisition APP can simulate the function of a Bluetooth positioning card by setting an APP-virtual Bluetooth positioning card.

The data acquisition equipment is portable handheld equipment, usually a mobile phone is used, corresponding signal acquisition software is installed, and data reporting is performed in batches. The device can be mounted on an unmanned aerial vehicle or a robot, and can automatically collect according to a predefined route, so that labor cost is reduced. The device is used in the present invention for the early acquisition of sample data.

The device to be positioned is used by a user when the user needs to be positioned, and can be a mobile terminal provided with a virtual Bluetooth positioning card or a Bluetooth positioning card arranged on an object moving or fixed in the space to be positioned.

Specifically, in the machine learning stage, the data acquisition device may stay in the space to be positioned for a set period of time, and continuously collect bluetooth signals broadcast by bluetooth beacons in the area.

Further, a data acquisition base station is arranged in the space to be positioned; when the equipment to be positioned is a Bluetooth positioning card arranged on a moving or fixed object, the data acquisition base station acquires Bluetooth signals acquired by the Bluetooth positioning card.

The data acquisition base station is a LoRa base station, and a LoRa protocol is adopted to provide data transfer service for the LoRa equipment in the coverage area; and running an agent program in the LoRa base station, and transferring Bluetooth signals acquired by the equipment to be positioned in a LAN mode.

In S102, the area location information includes: scene information, map information, and area information; wherein, the scene information is the attribution of the map; the map information is a plan view of a scene, the plan view is divided according to meshing, and each grid is provided with corresponding coordinates; the region information includes mesh data and coordinate data.

In S103, machine learning is performed on the bluetooth signal and the regional position information, and characteristic analysis is performed to obtain a positioning model of the space to be positioned, and the specific process of completing the pre-positioning of the space to be positioned is as follows:

Specifically, the positioning data is: (mac, rsi);

The learning data are: (site, map, area, mac, rssi);

where site is scene information, map is map information, area is area information, mac is mac address of bluetooth beacon, rsi is strength of bluetooth signal.

The two kinds of data (learning data and positioning data) have different purposes, the learning data is used for establishing the association between the regional position information and the Bluetooth signal when the machine learning is performed, and the positioning data is used for performing position identification according to the machine learning model and testing the positioning model.

The area information is the minimum unit for dividing the space to be positioned, and 1 bluetooth beacon corresponds to 1 mac address and 1 area information.

Further, after learning data and positioning data are obtained, the method further includes:

The specific process of filtering data is as follows:

In practical application, the obtained positioning data or learning data may have bluetooth signals sent by other bluetooth devices outside the predetermined positioning range, so that identification and judgment are needed to be performed, and data not belonging to positioning application are removed; the judgment can be based on mac address, signal strength, regional position information and the like of the Bluetooth beacon.

In S103, the learning data is classified and trained mainly by a machine learning algorithm, a positioning model is established, and finally, the positioning data is matched with the positioning model to realize position identification.

The specific process comprises the following steps:

Specifically, whether the regional position information is consistent with the actual position or not can be judged by a tester, if the regional position information is inconsistent with the actual position, positioning deviation feedback information reported by the tester is obtained, authentication is carried out by a background person, if the authentication is passed, new learning data is generated according to the positioning deviation feedback information, and iterative training is carried out on a positioning model.

In this embodiment, the machine learning method is supervised learning, and the data acquisition device performs data sampling on the bluetooth signal broadcast by the designated bluetooth beacon under the known area information.

In practical application, a corresponding scene and a map can be selected through a signal acquisition application of a mobile terminal (provided with a Bluetooth positioning card), the mobile terminal stays in a region corresponding to a region for a period of time, the signal acquisition application acquires enough sample data, and then the data is sent to a machine learning module for machine learning after signal filtering.

Machine-learned input data vectors [ (site, map, area, mac, rsi) ₁,…,(site,map,area,mac,rssi)_i ], correlate features mac, rsi, and site, map, area in the i sets of data, store the learned sample data and the resulting model in a database for subsequent localization steps.

In S104, the detailed flow of the positioning step is:

acquiring Bluetooth signals acquired by equipment to be positioned through a LoRa base station;

and filtering the positioning data to obtain the filtered positioning data.

When the data is filtered, the mac address of the positioning data and the strength of the Bluetooth signal can be used for filtering the data of which the mac address is not in the mac address range of the Bluetooth beacon in the space to be positioned and the strength of the Bluetooth signal is not in the set signal strength range, so that the filtered positioning data is obtained.

In this embodiment, the user can input a positioning management instruction to perform various positioning management. The positioning management instruction includes:

bluetooth beacon management, target object management and fixed positioning object management;

It should be noted that although the operations of the method of the present invention are described in a particular order in the above embodiments and the accompanying drawings, this does not require or imply that the operations must be performed in the particular order or that all of the illustrated operations be performed in order to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform.

In order to more clearly explain the above indoor positioning method, a specific embodiment will be described below.

Referring to fig. 2, a flow chart of data acquisition and machine learning according to an embodiment of the invention is shown.

As shown in fig. 2, taking a mobile phone as an example of a data acquisition device, data acquisition and machine learning are performed, and the specific flow is as follows:

s201, installing a data acquisition APP on a mobile phone, wherein an APP-virtual positioning card can be arranged in the APP for simulating a Bluetooth positioning card, and the functions of the APP-virtual positioning card are consistent with those of an entity positioning card.

S202, a user places the mobile phone in a map space to be positioned, selects a corresponding scene (site), map (map) and area (area) on the APP, and after clicking a 'acquisition' button, the APP continuously and actively transmits data to a Bluetooth positioning system (BBLS). The data to be uploaded includes mac address of bluetooth beacon, strength of bluetooth signal, and area location information (scene information, map information, area information).

S203, the user can stay each area (area) divided by the mobile phone on the map for a period of time (the mobile phone is randomly displaced in the area during stay and continuously collects Bluetooth signals broadcast by Bluetooth beacons (beacons) of the area, and meanwhile, the user performs positioning verification by clicking a positioning button of the APP during stay).

During the stay region, the APP continuously collects Bluetooth signals broadcast by the Bluetooth beacons in the region and sends the Bluetooth signals to the Bluetooth positioning system according to a certain frequency;

S204, the Bluetooth positioning system obtains learning data according to data sent by the APP: (site, map, area, mac, rssi), positioning data: (mac, rsi).

The Bluetooth positioning system classifies and predicts data through a machine learning algorithm and establishes a data model.

The data filtering unit (BBLS-biz unit) filters learning data and positioning, filters signals broadcast by non-Bluetooth beacons, does not belong to positioning application data, mac addresses are not data of mac addresses of Bluetooth beacons in a space to be positioned (for example, bluetooth signals transmitted by other regional Bluetooth beacons), and data with weak or strong Bluetooth signal intensity (abnormal intensity) is data of regional position information carried by data acquisition equipment in the space to be positioned.

And dividing 'learning data' and 'positioning data' according to the filtered data.

If the learning data is "learning data", the process proceeds to S205, and a learning method of a machine learning unit (BBLS-locate unit) is called; if "positioning data", proceed to S206, call the positioning method of the machine learning unit.

S205, a learning method; the machine learning unit performs machine learning after receiving the filtered "learning data", performs characteristic analysis on bluetooth signals of different map grids, obtains mac combination characteristics and signal strength rssi characteristics of bluetooth beacons of the area, establishes association between an area position tag site, map, area and a bluetooth beacon mac value corresponding to the area and the bluetooth beacon signal strength rssi of the area (i.e. establishes a data model, and finally uses the data model as a positioning basis to realize positioning of tracking objects or fixed objects in the area).

The trained model persists to MySQL.

S206, after the machine learning unit receives the filtered positioning data (mac, rsti), the machine learning unit obtains a recognition result (site, map, area) by matching with a database model established by machine deep learning, and can learn the position information of the signal equipment mobile phone in the positioning map.

For example, if the bluetooth signal received by the APP from the bluetooth beacon is (mac 1, rsi 25), the location is known by matching with the database model: and (3) the intelligent park 1-2 unit 3-building meeting room A1 area, and returning the positioned result to the APP.

By utilizing APP-positioning verification, when the data acquisition equipment continuously generates a displacement process in space and reports Bluetooth signals broadcast by Bluetooth beacons, a positioning button can be clicked at any time, and whether the positioning position is consistent with the actual position or not is checked through a map mode, so that positioning verification is performed. ( Such as: the positioning is consistent and has no objection; positioning errors and reporting platform feedback; the correct data after user authentication is directly converted into data which can be used by the machine in a learning way, so that the efficiency of machine learning and model building is improved. )

In an actual application scene, a map is digitized according to a specific scene, grid discretization is performed on the map, and each grid is encoded. And acquiring sample data through the data acquisition equipment, performing machine learning to acquire Bluetooth signal characteristics of each grid, and finally realizing positioning service capability through the Bluetooth signal characteristics.

Referring to fig. 3, a schematic flow chart of indoor bluetooth positioning according to an embodiment of the invention is shown.

As shown in fig. 3, taking a device to be positioned as an example, bluetooth positioning is performed, and the specific flow is as follows:

s301, continuously collecting Bluetooth signals broadcasted by Bluetooth beacons from the surroundings when equipment to be positioned (a Bluetooth positioning card or an APP virtual card) moves in a park;

and the collected Bluetooth signals are sent to the LoRa base station through a certain frequency by the LoRa protocol, and then forwarded to the Bluetooth positioning system by the LoRa base station.

S302, positioning data (mac, rsi) is generated according to Bluetooth signals, the positioning data is filtered through a data filtering unit, signals broadcast by non-Bluetooth beacons are filtered, data of positioning application is not attributed, mac addresses are not data of mac addresses of Bluetooth beacons in a space to be positioned (for example, bluetooth signals transmitted by Bluetooth beacons in other areas), and the strength of the Bluetooth signals is too weak or too strong (strength is abnormal).

S303, calling a positioning service of a machine learning unit to perform position recognition to obtain a recognition result (site, map, area) corresponding to positioning data (mac, rssi);

S304, displaying the map according to the identification result.

The recognition result may be put in a library (MySQL) for the user to call. The user can utilize the positioning application to carry out Bluetooth beacon management, target object management and fixed positioning object management; wherein,

Bluetooth beacon management: the specific map information (site, map, area) of the bluetooth beacon, the device attribute information, include: mac, device name, device power, etc.

Target object management: the user can view the location information of the tracking target object (site, map, area) in real time, and the trace track of the tracking target object. The Trace track is the moving track of the locator card and is composed of a continuous FootPrint.

Fixed positioning object management: the user can view the position information (site, map, area) of the fixed positioning object and the equipment attribute information of the fixed object in real time.

Having described the method of an exemplary embodiment of the present invention, an indoor positioning system of an exemplary embodiment of the present invention will be described with reference to fig. 4 to 6.

The implementation of the indoor positioning system can be referred to the implementation of the method, and the repetition is not repeated. The term "module" or "unit" as used below may be a combination of software and/or hardware that implements the intended function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.

Based on the same inventive concept, the invention also provides an indoor positioning system, as shown in fig. 4, comprising: bluetooth beacon 110, data acquisition device 120, positioning processing means 130, device to be positioned 140; wherein,

The bluetooth beacon 110 is disposed in the space to be located, and is used for broadcasting bluetooth signals;

the data acquisition device 120 carries area location information and is arranged in a space to be located, and is configured to acquire a bluetooth signal broadcasted by the bluetooth beacon 110;

When the positioning is performed, the positioning processing device 130 is configured to perform machine learning on the bluetooth signal and the regional position information, and perform characteristic analysis to obtain a positioning model of the space to be positioned, so as to complete the positioning of the space to be positioned;

in positioning, the device to be positioned 140 is located in a space to be positioned where the pre-positioning is completed, and is configured to collect bluetooth signals broadcasted by the bluetooth beacon 110 to generate positioning data;

the positioning processing device 130 matches the positioning data with the positioning model to obtain the spatial position information of the equipment 140 to be positioned, and positioning is completed.

In this embodiment, the bluetooth beacon 110 continuously broadcasts a bluetooth signal according to a set signal strength, where the broadcast bluetooth signal includes the mac address of the bluetooth beacon.

In this embodiment, the area location information includes: scene information, map information, and area information; wherein, the scene information is the attribution of the map; the map information is a plan view of a scene, the plan view is divided according to meshing, and each grid is provided with corresponding coordinates; the region information includes mesh data and coordinate data.

In this embodiment, the positioning processing device 130 is specifically configured to:

when the bluetooth beacon is pre-positioned, positioning data is obtained according to the bluetooth signals acquired by the data acquisition device 120, wherein the positioning data comprises the mac address of the bluetooth beacon and the strength of the bluetooth signals;

learning data is obtained according to the region position information carried by the data acquisition device 120 and the acquired bluetooth signals, wherein the learning data comprises scene information, map information, region information, mac addresses of bluetooth beacons and intensities of the bluetooth signals.

During positioning, positioning data are generated according to Bluetooth signals broadcast by the Bluetooth beacons 110 acquired by the equipment 140 to be positioned;

inputting positioning data into the trained positioning model for position identification to obtain the regional position information of the equipment 140 to be positioned;

and identifying and obtaining the spatial position information of the equipment 140 to be positioned according to the regional position information of the equipment 140 to be positioned, and completing positioning.

In this embodiment, the data acquisition device 120 is a mobile terminal provided with a virtual bluetooth locator card;

The device 140 to be located is a mobile terminal provided with a virtual bluetooth locator card or a bluetooth locator card provided on a moving or fixed object.

In this embodiment, the data acquisition device 120 is specifically configured to:

The data acquisition device 120 stays in the space to be positioned for a set period of time, and continuously collects the bluetooth signals broadcast by the bluetooth beacons 110 in the area.

Referring to fig. 5, a system architecture of a second embodiment of the present invention is shown. As shown in fig. 5, the system further includes: a data acquisition base station 150; wherein,

The data acquisition base station 150 is arranged in the space to be positioned; when the to-be-positioned device 140 is a bluetooth positioning card disposed on a moving or fixed object, the data acquisition base station 150 acquires a bluetooth signal acquired by the bluetooth positioning card.

Specifically, the data acquisition base station 150 is a LoRa base station, and adopts a LoRa protocol to provide data transfer service for LoRa equipment in a coverage area; wherein, the proxy program is operated in the LoRa base station, and the Bluetooth signals collected by the equipment to be positioned 140 are transferred by a LAN mode.

Referring to fig. 6, a system architecture of a third embodiment of the present invention is shown. As shown in fig. 6, the system further includes: the positioning management device 160 is configured to perform corresponding positioning management according to a positioning management instruction input by a user, where the positioning management instruction includes: bluetooth beacon management, target object management and fixed positioning object management;

It should be noted that although several modules of the indoor positioning system are mentioned in the above detailed description, this division is merely exemplary and not mandatory. Indeed, the features and functions of two or more modules described above may be embodied in one module in accordance with embodiments of the present invention. Conversely, the features and functions of one module described above may be further divided into a plurality of modules to be embodied.

Based on the foregoing inventive concept, as shown in fig. 7, the present invention further proposes a computer device 700, including a memory 710, a processor 720, and a computer program 730 stored on the memory 710 and executable on the processor 720, where the processor 720 implements the foregoing indoor positioning method when executing the computer program 730.

Based on the foregoing inventive concept, the present invention proposes a computer-readable storage medium storing a computer program which, when executed by a processor, implements the indoor positioning method described above.

The indoor positioning method and the system provided by the invention have at least the following advantages:

1. the fault tolerance rate of the equipment is better: in the implementation process of the invention, the probability of generating instability of the whole positioning system due to instability of single equipment is reduced, and the influence on the whole positioning effect is small. Taking the existing triangulation positioning as an example, the triangulation positioning determines that at least 3 complete beacon devices are needed for a certain area coordinate; the present invention determines the zone coordinates only by 1 complete beacon device.

2. The computational effort is smaller: compared with triangulation positioning, the invention can determine the position information of the object in the positioning space by only matching the received Bluetooth signal with the existing model database, and has smaller calculation workload.

3. The number of equipment deployment is more flexible: the invention can deploy equipment as required, and can deploy Bluetooth beacons when high precision requirement exists for positioning, thereby improving positioning precision; only the area positioning requirement can deploy the beacon equipment to complete the area coverage. And the triangulation positioning deploys the devices according to the distance, the number of the devices is fixed, the unit price cost of the deployed devices is high, and the unit price cost of the deployed beacon devices is lower.

It will be appreciated by those skilled in the art that 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 and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations 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.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

Finally, it should be noted that: the above examples are only specific embodiments of the present invention, and are not intended to limit the scope of the present invention, but it should be understood by those skilled in the art that the present invention is not limited thereto, and that the present invention is described in detail with reference to the foregoing examples: any person skilled in the art may modify or easily conceive of the technical solution described in the foregoing embodiments, or perform equivalent substitution of some of the technical features, while remaining within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. An indoor positioning method, characterized in that the method comprises:

The machine learning is performed on the bluetooth signals and the regional position information, and characteristic analysis is performed to obtain a positioning model of a space to be positioned, so as to complete the pre-positioning of the space to be positioned, including:

the data acquisition equipment is placed in a map space to be positioned, a corresponding scene, a map and a region are selected, the data acquisition equipment continuously and actively transmits data to the Bluetooth positioning system, and the transmitted data comprise mac addresses of Bluetooth beacons, the strength of Bluetooth signals, scene information, map information and region information;

Respectively staying the data acquisition equipment in each area divided on the map for a period of time; during stay, the data acquisition equipment randomly displaces in the area and continuously acquires Bluetooth signals broadcast by the Bluetooth beacons of the area; meanwhile, data is continuously and actively sent to the Bluetooth positioning system through triggering during stay, and positioning verification is carried out;

The Bluetooth positioning system obtains learning data and positioning data according to the uploaded data, wherein the positioning data comprises the mac address of the Bluetooth beacon and the strength of the Bluetooth signal; the learning data comprises scene information, map information, area information, mac address of the Bluetooth beacon and strength of the Bluetooth signal;

When learning data is acquired, calling a learning method of a machine learning unit; when positioning data is acquired, calling a positioning method of the machine learning unit;

The machine learning unit performs machine learning according to the learning data, performs characteristic analysis on Bluetooth signals of different map grids, obtains Bluetooth signal characteristics of each region position, establishes association between region position information and the Bluetooth signal characteristics of the region position, and generates a positioning model; the Bluetooth signal characteristics comprise mac addresses of Bluetooth beacons and intensities of Bluetooth signals; the area location information includes: scene information, map information, area information;

The machine learning unit obtains a recognition result by matching a database model established by machine deep learning according to the positioning data, and determines the regional position information of the signal equipment mobile phone in the positioning map; comparing the regional position information with the actual position, and verifying the positioning model according to the comparison result;

2. The indoor positioning method according to claim 1, wherein the bluetooth beacon continuously broadcasts bluetooth signals according to a set signal strength, wherein the broadcast bluetooth signals include mac addresses of the bluetooth beacons.

3. The indoor positioning method according to claim 2, wherein the scene information is a home location of a map; the map information is a plan view of a scene, the plan view is divided according to meshing, and each grid is provided with corresponding coordinates; the region information includes mesh data and coordinate data.

4. The indoor positioning method according to claim 3, wherein the area information is a minimum unit of dividing a space to be positioned, and 1 bluetooth beacon corresponds to 1 mac address and 1 area information.

5. The indoor positioning method according to claim 3, further comprising:

6. The indoor positioning method according to claim 5, wherein filtering the positioning data and the learning data to obtain filtered positioning data and learning data comprises:

7. The indoor positioning method according to claim 2, wherein the positioning data is used as an input sample, the area position information is obtained by performing position recognition through a positioning model, the area position information is compared with an actual position, and the positioning model is verified according to a comparison result, comprising:

8. The indoor positioning method according to claim 7, wherein the positioning data is used as an input sample, the area position information is obtained by performing position recognition through a positioning model, the area position information is compared with an actual position, and the positioning model is verified according to a comparison result, comprising:

9. The indoor positioning method according to claim 8, characterized in that in the positioning step, comprising:

10. The indoor positioning method according to claim 9, wherein filtering the positioning data generated by the device to be positioned collecting bluetooth signals broadcast by bluetooth beacons to obtain filtered positioning data, comprises:

11. The indoor positioning method according to claim 8, characterized in that in the positioning step, comprising:

12. The indoor positioning method according to claim 1, wherein the data acquisition device is a mobile terminal provided with a virtual bluetooth positioning card;

13. The indoor positioning method of claim 12, further comprising:

14. The indoor positioning method according to claim 13, wherein the data acquisition base station is a LoRa base station, and a LoRa protocol is adopted to provide data transfer service for LoRa devices in a coverage area; and running an agent program in the LoRa base station, and transferring Bluetooth signals acquired by the equipment to be positioned in a LAN mode.

15. The indoor positioning method of claim 13, further comprising:

16. An indoor positioning system, comprising: bluetooth beacons, data acquisition equipment, a positioning processing device and equipment to be positioned; wherein,

When the Bluetooth positioning system is pre-positioned, the data acquisition equipment is placed in a map space to be positioned, a corresponding scene, a map and a region are selected, the data acquisition equipment continuously and actively transmits data to the Bluetooth positioning system, and the transmitted data comprise the mac address of the Bluetooth beacon, the strength of a Bluetooth signal, scene information, map information and region information;

17. The indoor positioning system of claim 16, wherein the bluetooth beacon continuously broadcasts bluetooth signals according to a set signal strength, wherein the broadcast bluetooth signals include mac addresses of the bluetooth beacons.

18. The indoor positioning system of claim 17, wherein the context information is a home location of a map; the map information is a plan view of a scene, the plan view is divided according to meshing, and each grid is provided with corresponding coordinates; the region information includes mesh data and coordinate data.

19. The indoor positioning system of claim 18, wherein the positioning processing device is specifically configured to:

20. The indoor positioning system of claim 19, wherein the positioning processing device is specifically configured to:

21. The indoor positioning system of claim 20, wherein the positioning processing device is specifically configured to:

22. The indoor positioning system of claim 16, wherein the data acquisition device is a mobile terminal provided with a virtual bluetooth locator card;

23. The indoor positioning system of claim 22, further comprising: a data acquisition base station; wherein,

24. The indoor positioning system of claim 23, wherein the data acquisition base station is a LoRa base station that provides data transfer services to LoRa equipment within a coverage area using a LoRa protocol; and running an agent program in the LoRa base station, and transferring Bluetooth signals acquired by the equipment to be positioned in a LAN mode.

25. The indoor positioning system of claim 23, further comprising: the positioning management device is used for carrying out corresponding positioning management according to a positioning management instruction input by a user, wherein the positioning management instruction comprises: bluetooth beacon management, target object management and fixed positioning object management;

26. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1 to 15 when executing the computer program.

27. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program which, when executed by a processor, implements the method of any of claims 1 to 15.