Rapid positioning method based on mobile single station non-line-of-sight wireless signal

Abstract

The present invention relates to the technical field of wireless positioning, and disclosed is a rapid positioning method based on a mobile single station non-line-of-sight wireless signal, which is applied to an analysis device. A positioning platform is arranged on a mobile single station. The method comprises: acquiring path data and signal data for fingerprint positioning; establishing a fingerprint database on the basis of the path data and the signal data; controlling a mobile single station to move on the basis of a planning algorithm, and during movement, acquiring a first fingerprint feature of a target device by means of a positioning platform; acquiring, from the database, at least one second fingerprint feature matching the first fingerprint feature; and determining position information of the target device on the basis of a reference point corresponding to the at least one second fingerprint feature. Compared with a random movement mode, a fingerprint matching algorithm and a path planning algorithm designed by the present invention can achieve a better positioning effect of a mobile single station through a shorter movement path while implementing passive positioning of a contactless and connectionless wireless device.

Description

A fast positioning method based on non-line-of-sight wireless signals from a mobile single station Technical Field

[0001] The present invention relates to the field of wireless positioning technology, and in particular to a rapid positioning method based on a mobile single-station non-line-of-sight wireless signal. Background Art

[0002] Currently, the market demand for indoor positioning services is expanding. In modern cities, people spend about 80% of their lives indoors.

[0003] Wireless positioning technology is widely used for indoor positioning due to its high accuracy and ease of deployment. In addition to improving indoor positioning accuracy through various algorithms and hardware devices, one of the current challenges in indoor positioning is how to reduce the complexity of positioning systems, making them more universal and applicable to a wider range of scenarios.

[0004] Indoor wireless positioning often uses fingerprint positioning methods suitable for indoor use. In complex indoor environments, under low-cost conditions, spatiotemporal attributes such as angle and arrival time can produce significant errors. Therefore, indoor positioning is often achieved using fingerprinting.

[0005] Traditional indoor wireless fingerprint positioning requires deploying a large number of wireless infrastructure (wireless sites) to achieve reliable positioning. However, many indoor environments, such as residential areas, do not meet these requirements. Furthermore, indoor environments are subject to rapid change, such as during store renovations or shopping mall upgrades. Therefore, deploying a low-complexity positioning system is crucial.

[0006] Single-station positioning can solve the problem of wireless positioning requiring extensive infrastructure deployment. A single base station simplifies deployment and configuration, requiring only one wireless base station within the target area without having to consider the location relationships and time synchronization between multiple base stations. However, current single-station positioning often relies on multiple antennas or the use of CSI signals, which typically requires specialized hardware.

[0007] In large indoor environments or in harsh environments such as shopping malls or disaster relief sites, it is important to consider whether the wireless signal can cover the entire area. Incomplete signal coverage can result in positioning errors in certain areas. In addition, traditional single-station positioning is mostly based on line of sight, which is not suitable for complex indoor environments.

[0008] The limitations of traditional single-station positioning are that it requires special hardware, usually uses line-of-sight positioning, and has a small coverage range.

[0009] Summary of the Invention

[0010] In view of this, the purpose of the present invention is to provide a rapid positioning method based on a mobile single-station non-line-of-sight wireless signal, so that it can solve the problem that the existing single-point positioning method is not suitable for indoor environments with complex environments.

[0011] The present invention solves the above technical problems through the following technical means:

[0012] In a first aspect, the present application provides a positioning method based on a non-line-of-sight wireless signal of a mobile single station, which is applied to an analysis device, wherein the analysis device includes a mobile single station and a positioning platform, and the positioning platform is arranged on the mobile single station. The method includes:

[0013] Obtain path data and signal data for fingerprint positioning;

[0014] Establishing a fingerprint database based on the path data and the signal data; wherein the path data is composed of a plurality of test points;

[0015] Controlling the movement of the mobile station based on a planning algorithm, and obtaining a first fingerprint feature of a target device through the positioning platform during the movement, the first fingerprint feature including signal data and path data;

[0016] Acquire at least one second fingerprint feature matching the first fingerprint feature from the database, where the second fingerprint feature is a fingerprint feature of a pre-recorded reference point;

[0017] The location information of the target device is determined based on a reference point corresponding to the at least one second fingerprint feature.

[0018] According to a preferred embodiment, the establishing of a fingerprint database based on the path data and the signal data includes:

[0019] establishing a fingerprint model based on the path data and the signal data;

[0020] Determining a fingerprint feature of a preset reference point corresponding to the trajectory based on the fingerprint model;

[0021] A fingerprint database is established based on the fingerprint features, and the database records reference point serial numbers, test point serial numbers and fingerprint features.

[0022] According to a preferred embodiment, before obtaining at least one second fingerprint feature matching the first fingerprint feature from the database based on the first fingerprint feature of the target device, the method further includes:

[0023] Normalizing and filtering the signal data and path data in the first fingerprint feature to obtain a preprocessed first fingerprint feature.

[0024] According to a preferred embodiment, obtaining at least one second fingerprint feature matching the first fingerprint feature from the database includes:

[0025] Matching the first fingerprint feature with the fingerprint features of all reference points recorded in the database to obtain similarities between the first fingerprint feature and the fingerprint features of all reference points;

[0026] The fingerprint feature of at least one reference point with the greatest similarity is determined as the second fingerprint feature.

[0027] According to a preferred embodiment, matching the first fingerprint feature with the fingerprint features of all reference points recorded in the database to obtain similarities between the first fingerprint feature and the fingerprint features of all reference points includes:

[0028] The similarity between the first fingerprint feature and the fingerprint features of all reference points is determined by a similarity calculation formula, wherein the similarity calculation formula is:

[0029] Where W represents the similarity between the first fingerprint feature and the fingerprint features of all reference points, e represents the track edge label, and q∈

[0030] [1,Q] represents the sampling point number.

[0031] According to a preferred embodiment, determining the location information of the target device based on a reference point corresponding to at least one second fingerprint feature includes:

[0032] Recording a reference point corresponding to at least one second fingerprint feature as a target reference point, and obtaining position information corresponding to the second fingerprint feature of the target reference point based on an association between fingerprint features and positions;

[0033] Based on the location information of the target reference point, the location information of the target device is determined.

[0034] According to a preferred embodiment, the method further comprises: repeating the following steps a specified number of times:

[0035] Controlling the movement of the mobile station based on a planning algorithm, and obtaining a first fingerprint feature of a target device through the positioning platform during the movement, the first fingerprint feature including signal data and path data;

[0036] Acquire at least one second fingerprint feature matching the first fingerprint feature from the database, where the second fingerprint feature is a fingerprint feature of a pre-recorded reference point;

[0037] The location information of the target device is determined based on a reference point corresponding to the at least one second fingerprint feature.

[0038] In a second aspect, a rapid positioning method based on a non-line-of-sight wireless signal of a mobile single station is applied to a positioning device, which is applied to an analysis device, the analysis device including a mobile single station and a positioning platform, the positioning platform being arranged on the mobile single station, and the device including:

[0039] An acquisition unit, which obtains path data and signal data for fingerprint positioning;

[0040] a modeling unit, which establishes a fingerprint database based on the path data and the signal data; wherein the path data is composed of a plurality of test points;

[0041] a control unit, configured to control the movement of the mobile station based on a planning algorithm, and to obtain a first fingerprint feature of a target device through the positioning platform during the movement, wherein the first fingerprint feature includes signal data and path data;

[0042] an analyzing unit, acquiring from the database at least one second fingerprint feature that matches the first fingerprint feature, where the second fingerprint feature is a fingerprint feature of a pre-recorded reference point;

[0043] The processing unit determines the location information of the target device based on a reference point corresponding to the at least one second fingerprint feature.

[0044] In a third aspect, the present application provides a computer storage medium, in which a computer program is stored. When the computer program is run on a computer, it can execute the above-mentioned rapid positioning method based on non-line-of-sight wireless signals of a mobile single station.

[0045] Beneficial effects of the present invention:

[0046] 1. The present invention can automatically perform signal acquisition, feature extraction, data processing, fingerprint matching and positioning, and path planning processes through a wireless mobile single station. Based on the combination of path and fingerprint positioning, a fingerprint model of path features can be designed, and feature extraction and matching positioning can be achieved by moving a single mobile station. This makes it possible to deploy a large amount of infrastructure in the online stage of wireless fingerprint positioning, reducing the cost and complexity of wireless fingerprint positioning. The combination of mobile single station and wireless fingerprint matching breaks through the limitations of single-station positioning, which has a limited positioning range and can only be performed in line-of-sight mode, and does not require the use of special hardware such as multiple antennas and CSI equipment.

[0047] 2. In terms of mobile single-station positioning, the fingerprint matching algorithm and path planning algorithm designed in the present invention can achieve passive positioning of contactless and connectionless wireless devices, while allowing the mobile single station to achieve better positioning effects in a shorter movement path than random movement.

[0048] 3. The combination of mobile single station and wireless fingerprint positioning eliminates the need to deploy a large amount of wireless infrastructure and enables universal positioning even in special indoor scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] FIG1 is a flow chart of a positioning method based on a non-line-of-sight wireless signal of a mobile single station according to the present invention:

[0050] FIG2 is a comparison diagram of the positioning of a single station in the prior art and the positioning of a mobile single station in the present invention;

[0051] FIG3 is a schematic diagram of a framework of a positioning method based on a non-line-of-sight wireless signal of a mobile single station according to the present invention;

[0052] FIG4 is a schematic diagram of the filtering and normalization principle in the method of the present invention;

[0053] FIG5 is a flow chart of controlling the movement of a single mobile station based on matching similarity in the method of the present invention;

[0054] FIG6 is a block diagram of positioning based on non-line-of-sight wireless signals of a single mobile station according to the present invention;

[0055] Among them, 10, acquisition unit; 20, modeling unit; 30, control unit; 40, analysis unit; 50, processing unit. DETAILED DESCRIPTION

[0056] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0057] The same or similar numbers in the figures of the embodiments of the present invention correspond to the same or similar parts. In the description of the present invention, it should be understood that if the terms "up", "down", "left", "right", "front", "back", etc. indicate the orientation or position relationship, they are based on the orientation or position relationship shown in the figure. This is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation. Therefore, the terms describing the position relationship in the figures are only used for illustrative purposes and cannot be understood as limiting the present invention. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0058] As shown in Figures 1-5, this application provides a rapid positioning method based on non-line-of-sight wireless signals from a mobile station, which is applied to an analysis device. As shown in Figure 2, the analysis device includes a mobile station and a positioning platform, which is deployed on the mobile station. The mobile station includes a movable device and a single wireless station. The wireless station is deployed on the movable device to form a mobile station. The positioning platform is deployed on the mobile station to monitor and collect signal data from the target device to be located and run the positioning algorithm.

[0059] The method as a whole includes an offline stage and an online stage. In the offline stage, an offline fingerprint model about the correspondence between position and fingerprint is established, and path data and signal data of all maps are collected at each reference point. These signal features are subject to data processing, which mainly includes filtering and normalization. Finally, a fingerprint database is established for matching in the online stage.

[0060] During the online phase, the mobile station's movement is controlled based on a planning algorithm. The positioning platform extracts the target device's fingerprint features during the single-station movement. After simple filtering and normalization, it matches and locates the fingerprint data in the fingerprint database, obtaining a corresponding matching result. Using the matching results for the target device in each online movement trajectory, the path planning tool finds the fastest path that ensures accurate positioning. Ultimately, through continuous movement, the target device's location is estimated.

[0061] Specifically: The method includes:

[0062] S1, obtain path data and signal data for fingerprint positioning;

[0063] S2, establishing a fingerprint database based on the path data and the signal data; wherein the path data is composed of multiple test points;

[0064] S3, controlling the movement of the mobile station based on the planning algorithm, and obtaining a first fingerprint feature of the target device through the positioning platform during the movement, the first fingerprint feature including signal data and path data;

[0065] S4, obtaining at least one second fingerprint feature matching the first fingerprint feature from a database, where the second fingerprint feature is a fingerprint feature of a pre-recorded reference point;

[0066] S5. Determine location information of the target device based on a reference point corresponding to the at least one second fingerprint feature.

[0067] Specifically, in step S1, path data and signal data for fingerprint positioning are obtained. The original data includes path data [(x, y), t] and signal data [RSS, t].

[0068] It is understandable that a fingerprint database is established based on the path data and signal data; wherein the path data is composed of multiple test points. Specifically, the following steps are included:

[0069] S210, establishing a fingerprint model based on the path data and the signal data;

[0070] S220, obtaining a fingerprint feature of a trajectory corresponding to a preset reference point based on the fingerprint model;

[0071] S230, establishing a fingerprint database based on the fingerprint features, wherein the database records the reference point serial number, the test point serial number and the fingerprint features.

[0072] Each path segment is represented by m discrete sampling points. Normalization converts the complex signal data into a series of RSS signals corresponding to the reference points along the path. Filtering then occurs. Horizontal filtering removes outliers generated by the chronological order of the signal data using the isolation forest method. Vertical filtering removes outliers generated by multiple measurements, also using the isolation forest method. Finally, the RSS fingerprint for each reference point on each path segment is obtained. This RSS is represented by the change in the average of the m discrete RSS signal values, recorded as RSSvary.

[0073] Each route is represented by Node and Edge. Node represents a set of sampling points, Node∈[1,N], and Edge represents a set of edges, Edge∈[1,E]. RP and TP represent reference points and sampling points, respectively, RP∈[1,Q] and TP∈[1,P]. The fingerprint database finally records the following data [RP_Edge,Avgoffline,RSSvary]. Among them, RP_Edge represents the serial number of RP and Edge corresponding to the fingerprint, and Avgoffline represents the average of a series of RSS values ​​of the fingerprint. The fingerprint model is as follows, RSS q，e,m =[RSSS q,e,1 ,…,RSS q，e,m ]

[0074] In step S3, the mobile station controls movement based on a planning algorithm, and the positioning platform acquires the target device's fingerprint and path data. The positioning platform acquires a first fingerprint of the target device, which includes signal data and path data. Specifically, during the online phase, the mobile station obtains RSS data and path data of the target to be located by moving along different trajectories. After normalization and simple filtering, the RSS data and path data of the target to be located are aligned with the fingerprint data obtained during the offline phase, resulting in RSS_ON = [RSS1, RSS2, ..., RSSm] and the RSS mean value Avg for this trajectory.

[0075] In step S4, at least one second fingerprint feature that matches the first fingerprint feature is retrieved from the database. This second fingerprint feature is a pre-recorded fingerprint feature of a reference point. The data obtained during the online phase can then be matched with the fingerprint data in the fingerprint database to determine the matching similarity. Matching similarity refers to the degree of similarity between the RSS data generated by the target device's location and the RSS data recorded at each RP location in the database. The degree of similarity in the RSS data can be used to determine the degree of location similarity.

[0076] To calculate the matching similarity, we first need to calculate the Euclidean distance between the data obtained in the online phase and the fingerprint stored in the offline phase database. O_Distance = [O1,1,…,Oq,e,…,OQ,E] represents the Euclidean distance between the online and offline RSS matching of the qth RP on the eth trajectory edge. The specific calculation method of the Euclidean distance is as follows: First, compare the RSS mean AvgOnline obtained in the online phase with the AvgOffline of each RP corresponding to this edge in the offline database. Here, taking one RP as an example, we obtain the absolute value difference a, as shown below. a = |Ag Offline -Avg Online |

[0077] Then, the difference between the m data of RSSvary in the offline phase and RSS_ON in the online phase is calculated in sequence, and the difference b of the change value is obtained by the root mean square formula, as shown in the following formula.

[0078] Adding a and b with certain weights to obtain the Euclidean distance Oq,e on edge e with respect to RP q is as shown in the following formula. q，e =α*α+β*b β=1-α

[0079] It's important to note that RSS varies over time. This means that, when all other conditions except time remain the same, the RSS change may be the same, but the absolute RSS value may differ. This document considers that RPs with an absolute mean difference of more than 10 dBm are not within the positioning reference range, and the Euclidean distance for these RPs is assigned a sufficiently large value (e.g., 10,000).

[0080] After normalization, the matching degree between the target device and each reference point RP on this trajectory is obtained, that is, the matching similarity. The Euclidean distance of the trajectory is normalized and weighted to obtain W = [W1,e,…Wq,e,…,WQ,e], q∈[1,Q], e represents the calculated trajectory edge label, and W represents the matching similarity of the trajectory at each RP. The specific algorithm is as follows: w q sum=∑w q，e e∈E

[0081] In step S5, the location information of the target device is determined based on the reference point corresponding to the at least one second fingerprint feature. After obtaining the matching similarity, the top K most likely RPs are obtained through the WKNN algorithm to estimate the location of the target device, as shown in the following formula:

[0082] On the other hand, the matching similarity is passed to the subsequent path planning algorithm to calculate the next trajectory to move. Specifically, the path planning algorithm based on mobile single-station fingerprint positioning is designed as follows: after each trajectory segment, the path planning and positioning algorithm are performed. The matching similarity obtained for each trajectory segment is stored in the empirical matching similarity and continuously updated. The updating method is to add the matching similarity of each RP. In this way, after several movements, the matching similarity weights of the most likely RP positions will increase. The purpose of selecting the next path is to achieve successful positioning more quickly. The key to improving positioning results is the size of the matching similarity. The greater the difference in matching between certain RPs and other RPs, the faster the threshold conditions are met. Because the mean difference a has already been used to screen RPs, the key factor determining the size of the matching similarity is the change in the fingerprint RSS recorded during the offline phase.

[0083] Each time the next edge is selected, the top K most likely RPs (i.e., the RPs with the greatest matching similarity) are selected from the latest empirical matching similarity using the WKNN algorithm. This application believes that for these K RPs with the largest RSS change in the next selectable trajectory, they can obtain more prominent fingerprint features and achieve better positioning results compared to other selectable trajectories. Therefore, in the offline fingerprint database, the fingerprint data of these K RPs corresponding to each selectable edge is weighted and summed. The edge e with the largest PathDe weight will be selected by the algorithm, as shown in the following formula: PathD e =∑(W q *RSSD q，e )q∈R

[0084] However, single-station movement requires a positioning endpoint. K RPs with the largest matching similarities will be selected from the latest empirical matching similarities. When the sum Wsum of the empirical matching similarities of the K RPs is greater than the set TH, positioning is completed. The positioning result obtained by the matching algorithm is the final positioning result, as shown in Figure 5.

[0085] In a second aspect, embodiments of the present application further provide a positioning device based on a mobile single-station non-line-of-sight wireless signal, the positioning device including at least one software function module stored in a storage module in the form of software or firmware or embedded in an operating system (OS) in a control device. An acquisition unit, etc., is used to execute executable modules stored in the storage module, such as the software function modules and computer program modules included in the positioning device based on a mobile single-station non-line-of-sight wireless signal.

[0086] The positioning device is applied to an analysis device, which includes a mobile station and a positioning platform. The positioning platform is arranged on the mobile station. With reference to FIG6 , the device includes a collection unit 10, a modeling unit 20, a control unit 30, an analysis unit 40, and a processing unit 50. The functions of each unit may be as follows:

[0087] The acquisition unit 10 collects path data and signal data for fingerprint positioning;

[0088] A modeling unit 20 establishes a fingerprint database based on the path data and the signal data; wherein the path data is composed of a plurality of test points;

[0089] The control unit 30 controls the movement of the mobile station based on the planning algorithm, and obtains a first fingerprint feature of the target device through the positioning platform during the movement, where the first fingerprint feature includes signal data and path data;

[0090] The analyzing unit 40 obtains at least one second fingerprint feature matching the first fingerprint feature from the database, where the second fingerprint feature is a fingerprint feature of a pre-recorded reference point;

[0091] The processing unit 50 determines the location information of the target device based on the reference point corresponding to the at least one second fingerprint feature.

[0092] The specific use principles of the units such as the collection unit 10, the modeling unit 20 and the control unit 30 can refer to the positioning method based on the non-line-of-sight wireless signal of a mobile single station above, and will not be described in detail here.

[0093] On the third aspect, the present application also provides a computer storage medium, which stores a computer program. When the computer program runs on a computer, it can execute the above-mentioned rapid positioning method based on non-line-of-sight wireless signals of a mobile single station.

[0094] Through the description of the above implementation methods, technical personnel in this field can clearly understand that the present application can be implemented through hardware, or can be implemented with the help of software plus the necessary general hardware platform. Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.), including a number of instructions for enabling a computer device (which can be a personal computer, simulation device, or network device, etc.) to execute the methods of various implementation scenarios of the present application.

[0095] In summary, the present application provides a rapid positioning method based on non-line-of-sight wireless signals from a mobile single station, which is applied to an analysis device, the analysis device including a mobile single station and a positioning platform, the positioning platform being arranged on the mobile single station. The method comprises: obtaining path data and signal data for fingerprint positioning; establishing a fingerprint database based on the path data and the signal data; wherein the path data is composed of multiple test points; controlling the movement of the mobile single station based on a planning algorithm, and during the movement, obtaining a first fingerprint feature of the target device through the positioning platform, the first fingerprint feature including signal data and path data; obtaining at least one second fingerprint feature matching the first fingerprint feature from the database, the second fingerprint feature being a fingerprint feature of a pre-recorded reference point; and determining the location information of the target device based on the reference point corresponding to the at least one second fingerprint feature. In the present application, the wireless mobile single station can automate processes such as signal acquisition, feature extraction, data processing, fingerprint matching positioning, and path planning. Based on the combination of path and fingerprint positioning, a fingerprint model of path features can be designed, and feature extraction and matching positioning can be achieved by the movement of the mobile single station. This eliminates the need to deploy a large amount of infrastructure in the online phase of wireless fingerprint positioning, reducing the cost and complexity of wireless fingerprint positioning. The combination of mobile single station and wireless fingerprint matching breaks through the limitations of single-station positioning, which has limited positioning range and can only be performed in line-of-sight mode, and does not require the use of special hardware such as multi-antennas and CSI equipment.

[0096] In the embodiments provided in the present application, it should be understood that the disclosed devices, systems and methods can also be implemented in other ways. The device, system and method embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of code, and a part of the module, program segment or code includes one or more executable instructions for implementing the specified logical function. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart can be implemented by a dedicated hardware-based system that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions. In addition, the functional modules in the various embodiments of the present application can be integrated together to form an independent part, or each module can exist alone, or two or more modules can be integrated to form an independent part.

[0097] The above are merely examples of the present application and are not intended to limit the scope of protection of the present application. Those skilled in the art will appreciate that various modifications and variations are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A rapid positioning method based on non-line-of-sight wireless signals from a single mobile station, characterized in that: Applied to an analysis device, the analysis device includes a mobile station and a positioning platform, the positioning platform is arranged on the mobile station, and the method includes: Obtain path data and signal data for fingerprint positioning; Establishing a fingerprint database based on the path data and the signal data; wherein the path data is composed of a plurality of test points; Controlling the movement of the mobile station based on a planning algorithm, and obtaining a first fingerprint feature of a target device through the positioning platform during the movement, the first fingerprint feature including signal data and path data; Acquire at least one second fingerprint feature matching the first fingerprint feature from the database, where the second fingerprint feature is a fingerprint feature of a pre-recorded reference point; The location information of the target device is determined based on a reference point corresponding to the at least one second fingerprint feature.

2. The method according to claim 1, characterized in that The establishing of a fingerprint database based on the path data and the signal data includes: establishing a fingerprint model based on the path data and the signal data; Determining the fingerprint characteristics of the preset reference point corresponding to the movement process of the mobile single station based on the fingerprint model; A fingerprint database is established based on the fingerprint features, and the database records reference point serial numbers, test point serial numbers and fingerprint features.

3. The method according to claim 2, characterized in that Before acquiring, based on the first fingerprint feature of the target device, at least one second fingerprint feature matching the first fingerprint feature from the database, the method further includes: Normalizing and filtering the signal data and path data in the first fingerprint feature to obtain a preprocessed first fingerprint feature.

4. The method according to claim 2, characterized in that Acquiring at least one second fingerprint feature matching the first fingerprint feature from the database includes: Matching the first fingerprint feature with the fingerprint features of all reference points recorded in the database to obtain similarities between the first fingerprint feature and the fingerprint features of all reference points; The fingerprint feature of at least one reference point with the greatest similarity is determined as the second fingerprint feature.

5. The method according to claim 2, characterized in that Matching the first fingerprint feature with the fingerprint features of all reference points recorded in the database to obtain similarities between the first fingerprint feature and the fingerprint features of all reference points includes: The similarity between the first fingerprint feature and the fingerprint features of all reference points is determined by a similarity calculation formula, wherein the similarity calculation formula is: Where W represents the similarity between the first fingerprint feature and the fingerprint features of all reference points, e represents the trajectory edge label, and q∈[1,Q] represents the sampling point sequence number.

6. The method according to claim 3, characterized in that Determining location information of the target device based on a reference point corresponding to the at least one second fingerprint feature includes: Recording a reference point corresponding to at least one second fingerprint feature as a target reference point, and obtaining position information corresponding to the second fingerprint feature of the target reference point based on an association relationship between fingerprint features and positions; Based on the location information of the target reference point, the location information of the target device is determined.

7. The method according to claim 6, characterized in that The method further comprises: Repeat the following steps a specified number of times: Controlling the mobile station to move along a new path obtained based on the planning algorithm, and obtaining a first fingerprint feature of the target device through the positioning platform during the movement along the new path, the first fingerprint feature including signal data and path data; Acquire at least one second fingerprint feature matching the first fingerprint feature from the database, where the second fingerprint feature is a fingerprint feature of a pre-recorded reference point; The location information of the target device is determined based on a reference point corresponding to the at least one second fingerprint feature.

Images