CN117053784A - Method, device, equipment and medium for updating radio frequency fingerprint library - Google Patents

Method, device, equipment and medium for updating radio frequency fingerprint library Download PDF

Info

Publication number
CN117053784A
CN117053784A CN202210493455.6A CN202210493455A CN117053784A CN 117053784 A CN117053784 A CN 117053784A CN 202210493455 A CN202210493455 A CN 202210493455A CN 117053784 A CN117053784 A CN 117053784A
Authority
CN
China
Prior art keywords
cluster
data
sub
fingerprint
fingerprint data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210493455.6A
Other languages
Chinese (zh)
Inventor
许正一
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
ZTE Corp
Original Assignee
ZTE Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by ZTE Corp filed Critical ZTE Corp
Priority to CN202210493455.6A priority Critical patent/CN117053784A/en
Priority to PCT/CN2023/090782 priority patent/WO2023216882A1/en
Publication of CN117053784A publication Critical patent/CN117053784A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/20—Instruments for performing navigational calculations
    • G01C21/206—Instruments for performing navigational calculations specially adapted for indoor navigation
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/20—Instruments for performing navigational calculations
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G01S5/01—Determining conditions which influence positioning, e.g. radio environment, state of motion or energy consumption
    • G01S5/012—Identifying whether indoors or outdoors
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
    • G01S5/0252—Radio frequency fingerprinting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/02—Arrangements for optimising operational condition
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H04W4/33—Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Theoretical Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Collating Specific Patterns (AREA)

Abstract

The present disclosure provides a method for updating a radio frequency fingerprint database, wherein historical fingerprint data in the radio frequency fingerprint database includes cluster information and sub-cluster information, and the method includes: acquiring real-time fingerprint data, and dividing the real-time fingerprint data into different types of data sets according to cluster information, wherein the data sets at least comprise boundary data sets; updating a radio frequency fingerprint library according to each type of data set; and aiming at the first fingerprint data in the boundary data set, determining a first sub-cluster closest to the position of the first fingerprint data according to the sub-cluster information, and updating the sub-cluster information of the historical first fingerprint data in the radio frequency fingerprint library according to the information of the first sub-cluster. The embodiment of the disclosure can perform sub-cluster boundary movement optimization processing on the fingerprint data of the sub-cluster boundary which is easy to misjudge, and improve the reliability of the fingerprint data in the radio frequency fingerprint library, thereby improving the indoor positioning accuracy of the terminal. The disclosure also provides a device for updating the radio frequency fingerprint library, a computer device and a readable medium.

Description

Method, device, equipment and medium for updating radio frequency fingerprint library
Technical Field
The disclosure relates to the technical field of communication, in particular to a method, a device, computer equipment and a readable medium for updating a radio frequency fingerprint library.
Background
The implementation of indoor positioning of a terminal depends on fingerprint data in a radio frequency fingerprint library, the fingerprint library is divided into a plurality of areas, after the fingerprint data of a to-be-positioned point is obtained in a positioning stage, the to-be-positioned point is determined in a certain area, and finally, the position accuracy is determined in the area. The accuracy of indoor positioning of a terminal depends on the reliability of fingerprint data in a radio frequency fingerprint library to a great extent, so how to improve the reliability of fingerprint data is important.
The existing radio frequency fingerprint library updating scheme is concentrated on processing the crowdsourcing data, namely, the crowdsourcing data is excessively depended on, and reliability judgment of the data is completely given to a user, so that the reliability of the fingerprint data is poor. The other is to update the radio frequency fingerprint database based on the historical data and the incremental data, and the regional division is inaccurate, so that the reliability of the fingerprint data is also greatly reduced.
Disclosure of Invention
The present disclosure provides a method, apparatus, computer device and readable medium for updating a radio frequency fingerprint library.
In a first aspect, an embodiment of the present disclosure provides a method for updating a radio frequency fingerprint database, where historical fingerprint data in the radio frequency fingerprint database includes cluster information and sub-cluster information, the method including:
Acquiring real-time fingerprint data, and dividing the real-time fingerprint data into different types of data sets according to the cluster information, wherein the data sets at least comprise boundary data sets;
updating the radio frequency fingerprint library according to each type of data set; and aiming at the first fingerprint data in the boundary data set, determining a first sub-cluster closest to the position of the first fingerprint data according to the sub-cluster information, and updating the sub-cluster information of the historical first fingerprint data in the radio frequency fingerprint database according to the information of the first sub-cluster.
In some embodiments, the determining, according to the sub-cluster information, the first sub-cluster closest to the location of the first fingerprint data includes:
determining a second sub-cluster with a distance smaller than a preset first threshold value from the position of the first fingerprint data according to the sub-cluster information;
and calculating a first distance between the first fingerprint data and the center point of each second sub-cluster, and determining the first sub-cluster closest to the position where the first fingerprint data is located according to the first distance and the cluster where the first fingerprint data belongs in the radio frequency fingerprint library.
In some embodiments, the determining, according to the first distance and the cluster to which the first fingerprint data belongs in the radio frequency fingerprint library, a first sub-cluster closest to the location where the first fingerprint data is located includes:
Sequencing the first distances from small to large to obtain a distance sequence;
determining a current first distance according to the sequence of the first distances in the distance sequence, and determining a cluster to which a third sub-cluster corresponding to the current first distance belongs;
determining a first sub-cluster closest to the first fingerprint data as the third sub-cluster in response to the fact that the cluster to which the third sub-cluster belongs is the same as the cluster to which the historical first fingerprint data in the radio frequency fingerprint database belongs;
and responding to the fact that the cluster to which the third sub-cluster belongs is different from the cluster to which the historical first fingerprint data belongs in the radio frequency fingerprint library, selecting the next first distance according to the distance sequence until the cluster to which the third sub-cluster corresponding to the first distance selected currently belongs is the same as the cluster to which the historical first fingerprint data belongs in the radio frequency fingerprint library, and determining the first sub-cluster closest to the first fingerprint data as the third sub-cluster corresponding to the first distance selected currently.
In some embodiments, the method further comprises: dividing historical fingerprint data in the radio frequency fingerprint library into clusters and dividing each cluster into sub-clusters to generate cluster information and sub-cluster information; the step of clustering the historical fingerprint data in the radio frequency fingerprint library comprises the following steps:
Determining a sub-cluster of each cluster in turn;
wherein the sub-clusters of the clusters are determined by:
sequentially determining the center point of each sub-cluster of the cluster;
for each sub-cluster, determining the range of the sub-cluster according to the center point of the sub-cluster and a preset second threshold;
and determining the historical fingerprint data contained in the sub-cluster according to the range of the sub-cluster and the position information of the historical fingerprint data in the cluster.
In some embodiments, in the case where the current sub-cluster is the non-first sub-cluster of the belonging cluster, the center point of the current sub-cluster is determined by:
determining the shortest distance between the position of each residual historical fingerprint data in the cluster and the center point of each selected sub-cluster;
respectively calculating the probability of taking each residual historical fingerprint data in the cluster as the center point of the current sub-cluster according to the shortest distance between the position of each residual historical fingerprint data in the cluster and the center point of each selected sub-cluster and the distance between each residual historical fingerprint data in the cluster and the center point of each selected sub-cluster;
and determining the center point of the current sub-cluster according to the probability that each residual historical fingerprint data in the cluster is taken as the center point of the current sub-cluster.
In some embodiments, in the case that the current sub-cluster is the first sub-cluster of the cluster, one historical fingerprint data is randomly selected from the historical fingerprint data in the cluster as the center point of the first sub-cluster of the cluster.
In some embodiments, the real-time fingerprint data includes at least location information, the dividing the real-time fingerprint data into different types of data sets according to the cluster information includes:
determining a cluster to which historical fingerprint data corresponding to the real-time fingerprint data belongs according to the position information of the real-time fingerprint data and the cluster information;
calculating the central point of the cluster, and calculating a second distance between the position of the real-time fingerprint data and the central point of the cluster;
calculating a third distance between historical fingerprint data of the boundary position of the cluster and the central point of the cluster;
marking the real-time fingerprint data according to at least the second distance and the third distance;
a dataset is generated from the markers of the real-time fingerprint data.
In some embodiments, the data set further comprises an anomaly data set, the method further comprising, prior to marking the real-time fingerprint data according to at least the second distance and the third distance: acquiring an evaluation result of the position correctness of the real-time fingerprint data, which is sent by a user terminal, of the user;
The marking the real-time fingerprint data according to at least the second distance and the third distance includes:
in response to the evaluation result being an error and the second distance being greater than the third distance, marking the real-time fingerprint data as first anomaly data;
and screening second abnormal data, the distance between the position of which and the central point of the cluster to which the real-time fingerprint data belongs, from the first abnormal data is smaller than a preset third threshold value, and marking the second abnormal data as boundary data, wherein data in the boundary data set are the boundary data, and data in the abnormal data set are data except the boundary data in the first abnormal data.
In some embodiments, in the case that the dataset is an abnormal dataset, the updating the rf fingerprint library according to each type of dataset includes: and deleting the historical fingerprint data corresponding to the abnormal data set in the radio frequency fingerprint database.
In some embodiments, the data set further comprises a strongly correlated data set, the marking the real-time fingerprint data based at least on the second distance and the third distance further comprising:
And in response to the evaluation result being correct and the second distance being smaller than the third distance, marking the real-time fingerprint data as strongly correlated data, wherein the data in the strongly correlated data set are the strongly correlated data.
In some embodiments, where the dataset is a strongly correlated dataset, the updating the rf fingerprint library from each type of dataset comprises: updating the radio frequency fingerprint library according to the strong correlation data in the strong correlation data set;
after updating the radio frequency fingerprint library according to the strongly correlated data in the strongly correlated data set, the method further comprises:
and dividing the historical fingerprint data in the updated radio frequency fingerprint library into clusters and dividing each cluster into sub-clusters so as to update the cluster information and the sub-cluster information.
In yet another aspect, an embodiment of the present disclosure further provides an apparatus for updating a radio frequency fingerprint database, where the history fingerprint data in the radio frequency fingerprint database includes cluster information and sub-cluster information, and the radio frequency fingerprint database updating apparatus includes a data acquisition module, a data processing module, and a data updating module;
the data acquisition module is used for acquiring real-time fingerprint data;
The data processing module is used for dividing the real-time fingerprint data into different types of data sets according to the cluster information, wherein the data sets at least comprise boundary data sets;
the data updating module is used for updating the radio frequency fingerprint library according to various data sets; and aiming at the first fingerprint data in the boundary data set, determining a first sub-cluster closest to the position of the first fingerprint data according to the sub-cluster information, and updating the sub-cluster information of the historical first fingerprint data in the radio frequency fingerprint database according to the information of the first sub-cluster.
In yet another aspect, the disclosed embodiments also provide a computer device, comprising: one or more processors; a storage device having one or more programs stored thereon; the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the radio frequency fingerprint library updating method as described above.
In yet another aspect, the disclosed embodiments also provide a computer readable medium having a computer program stored thereon, wherein the program when executed implements a method for updating a radio frequency fingerprint library as described above.
The embodiment of the disclosure provides a method for updating a radio frequency fingerprint database, wherein historical fingerprint data in the radio frequency fingerprint database comprises cluster information and sub-cluster information, and the method comprises the following steps: acquiring real-time fingerprint data, and dividing the real-time fingerprint data into different types of data sets according to cluster information, wherein the data sets at least comprise boundary data sets; updating a radio frequency fingerprint library according to each type of data set; and aiming at the first fingerprint data in the boundary data set, determining a first sub-cluster closest to the position of the first fingerprint data according to the sub-cluster information, and updating the sub-cluster information of the historical first fingerprint data in the radio frequency fingerprint library according to the information of the first sub-cluster. The embodiment of the disclosure can perform sub-cluster boundary movement optimization processing on the fingerprint data of the sub-cluster boundary which is easy to misjudge, and improve the reliability of the fingerprint data in the radio frequency fingerprint library, thereby improving the indoor positioning accuracy of the terminal.
Drawings
Fig. 1 is a schematic diagram of a method for updating a radio frequency fingerprint library according to an embodiment of the disclosure;
fig. 2 is a schematic flowchart of determining a first sub-cluster closest to a location where first fingerprint data is located according to an embodiment of the present disclosure;
fig. 3 is a second flowchart of determining a first sub-cluster closest to a location where first fingerprint data is located according to an embodiment of the present disclosure;
Fig. 4 is a schematic flow chart of clustering historical fingerprint data in a radio frequency fingerprint library according to an embodiment of the present disclosure;
fig. 5 is a schematic flow chart of determining a center point of a non-first sub-cluster of a cluster according to an embodiment of the disclosure;
FIG. 6 is a flow chart of partitioning real-time fingerprint data into different types of data sets according to an embodiment of the present disclosure;
fig. 7 is a schematic flow chart of marking real-time fingerprint data according to an embodiment of the disclosure;
fig. 8 is a schematic diagram two of a method for updating a radio frequency fingerprint library according to an embodiment of the disclosure;
fig. 9 is a schematic structural diagram of a device for updating a rf fingerprint library according to an embodiment of the disclosure;
fig. 10 is a schematic structural diagram of a device for updating a rf fingerprint library according to an embodiment of the disclosure.
Detailed Description
Example embodiments will be described more fully hereinafter with reference to the accompanying drawings, but may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. 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.
As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. As used herein, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
Embodiments described herein may be described with reference to plan and/or cross-sectional views with the aid of idealized schematic diagrams of the present disclosure. Accordingly, the example illustrations may be modified in accordance with manufacturing techniques and/or tolerances. Thus, the embodiments are not limited to the embodiments shown in the drawings, but include modifications of the configuration formed based on the manufacturing process. Thus, the regions illustrated in the figures have schematic properties and the shapes of the regions illustrated in the figures illustrate the particular shapes of the regions of the elements, but are not intended to be limiting.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The existing method for updating the radio frequency fingerprint library based on the crowdsourcing data mainly filters the active and passive updated fingerprint libraries by collecting the crowdsourcing data and establishing the updated fingerprint library so as to update the fingerprint library. In addition, there is a fingerprint library updating method based on historical data and increment, a distance threshold is used to judge the neighborhood of the clusters, namely, after each time a cluster is formed, the distance threshold is used to find the next possible cluster area, and the disadvantage of the scheme is that when the clusters have different densities, the setting of the distance threshold changes with the density. This disadvantage also occurs in very high dimensional data, and therefore the distance threshold becomes difficult to estimate, so that the reliability of the fingerprint data is also compromised.
In order to solve the problem of poor reliability of fingerprint data in the above-mentioned radio frequency fingerprint library updating scheme, the embodiment of the disclosure provides a method for updating a radio frequency fingerprint library, where historical fingerprint data in the radio frequency fingerprint library includes cluster information and sub-cluster information, and it is to be noted that one cluster corresponds to one location area. As shown in fig. 1, the method for updating the radio frequency fingerprint library comprises the following steps:
And step 1, acquiring real-time fingerprint data, and dividing the real-time fingerprint data into data sets of different types according to cluster information, wherein the data sets at least comprise boundary data sets.
The real-time fingerprint data is crowdsourcing data (Crowdsourcing Data), and the data in the radio frequency fingerprint database is a crowdsourcing data set, wherein the crowdsourcing data set represents a data set constructed in cooperation with a user. The crowdsourcing data is acquired in real time in the fingerprint data acquisition process, so that the active feedback effect of a user on a positioning result can be exerted to a certain extent, and the timeliness of the fingerprint data is improved.
In this step, the user terminal updates the real-time fingerprint data to the network side (the rf fingerprint library updating device), triggers the rf fingerprint library update, and the rf fingerprint library updating device classifies the real-time fingerprint data into different types of data sets according to the clusters and the clusters previously classified in the rf fingerprint library.
In some embodiments, the data sets may include strongly correlated data sets, outlier data sets, and boundary data sets.
Step 2, updating a radio frequency fingerprint library according to the data sets of each type; and aiming at the first fingerprint data in the boundary data set, determining a first sub-cluster closest to the position of the first fingerprint data according to the sub-cluster information, and updating the sub-cluster information of the historical first fingerprint data in the radio frequency fingerprint library according to the information of the first sub-cluster.
In this step, for the first fingerprint data in the boundary data set, a first sub-cluster closest to the location of the first sub-cluster is found, if the cluster to which the first sub-cluster belongs is the same as the cluster to which the historical first fingerprint data belongs in the radio frequency fingerprint library, the first fingerprint data is incorporated into the first sub-cluster, that is, a part of the boundary of the first sub-cluster is moved toward the location of the first fingerprint data (i.e., the boundary of the first sub-cluster is finely adjusted) until the first fingerprint data falls into the first sub-cluster, and the radio frequency fingerprint library is updated according to the information of the first sub-cluster after the boundary adjustment.
The embodiment of the disclosure provides a method for updating a radio frequency fingerprint database, wherein historical fingerprint data in the radio frequency fingerprint database comprises cluster information and sub-cluster information, and the method comprises the following steps: acquiring real-time fingerprint data, and dividing the real-time fingerprint data into different types of data sets according to cluster information, wherein the data sets at least comprise boundary data sets; updating a radio frequency fingerprint library according to each type of data set; and aiming at the first fingerprint data in the boundary data set, determining a first sub-cluster closest to the position of the first fingerprint data according to the sub-cluster information, and updating the sub-cluster information of the historical first fingerprint data in the radio frequency fingerprint library according to the information of the first sub-cluster. The embodiment of the disclosure can perform sub-cluster boundary movement optimization processing on the fingerprint data of the sub-cluster boundary which is easy to misjudge, and improve the reliability of the fingerprint data in the radio frequency fingerprint library, thereby improving the indoor positioning accuracy of the terminal.
In some embodiments, as shown in fig. 2, the determining, according to the sub-cluster information, the first sub-cluster closest to the location where the first fingerprint data is located (i.e. step 2) includes the following steps:
and step 21, determining a second sub-cluster with the distance smaller than a preset first threshold value from the position where the first fingerprint data is located according to the sub-cluster information.
In this step, first fingerprint data in the boundary data set are sequentially selected, and a plurality of second sub-clusters near the current first fingerprint data are found according to the sub-cluster information with respect to the current first fingerprint data, that is, the distance between the center point of the second sub-cluster and the first fingerprint data is smaller than a preset first threshold.
Step 22, calculating a first distance between the first fingerprint data and the center point of each second sub-cluster, and determining a first sub-cluster closest to the position where the first fingerprint data is located according to the first distance and the cluster where the first fingerprint data belongs in the radio frequency fingerprint library.
In this step, a first distance between the center point of each second sub-cluster and the current first fingerprint data is calculated, and whether the corresponding sub-cluster is the first sub-cluster closest to the current first fingerprint data is judged one by one according to the first distance.
In some embodiments, as shown in fig. 3, the determining a first sub-cluster closest to the location of the first fingerprint data according to the first distance and the cluster to which the first fingerprint data belongs in the rf fingerprint library (i.e. step 22) includes the following steps:
step 221, sorting the first distances from small to large to obtain a distance sequence.
Step 222, determining the current first distance according to the sequence of the first distances in the distance sequence, and determining the cluster to which the third sub-cluster corresponding to the current first distance belongs.
In the step, a current first distance is determined according to the sequence of the first distances in the distance sequence, the current first distance corresponds to a third sub-cluster, and the cluster to which the third sub-cluster belongs is determined according to cluster information and sub-cluster information of historical fingerprint data in the radio frequency fingerprint library. The first fingerprint data comprises position information, and the clusters and the sub-clusters in the radio frequency fingerprint library are all divided according to the position information of the fingerprint data, so that in the step, the corresponding clusters can be determined according to the position information of the first fingerprint data.
Step 223, if the cluster to which the third sub-cluster belongs is the same as the cluster to which the historical first fingerprint data belongs in the radio frequency fingerprint database, step 224 is executed; otherwise, step 225 is performed.
In this step, the cluster to which the third sub-cluster belongs is compared with the cluster to which the historical first fingerprint data belongs in the radio frequency fingerprint database, if the clusters are consistent, step 224 is executed, and the third sub-cluster is the first sub-cluster closest to the first fingerprint data; if the two are inconsistent, step 225 is performed, i.e. the next first distance is selected from the distance sequence, the cluster to which the third sub-cluster corresponding to the first distance currently selected belongs is determined, and compared with the cluster to which the corresponding historical first fingerprint data belongs in the radio frequency fingerprint library, until the cluster to which the third sub-cluster corresponding to the first distance currently selected belongs is the same as the cluster to which the historical first fingerprint data belongs in the radio frequency fingerprint library, in which case the third sub-cluster corresponding to the first distance currently selected is the first sub-cluster closest to the first fingerprint data.
In step 224, the first sub-cluster closest to the first fingerprint data is determined to be the third sub-cluster.
And 225, selecting the next first distance according to the first distance in the distance sequence until the cluster of the third sub-cluster corresponding to the first distance selected currently is the same as the cluster of the historical first fingerprint data in the radio frequency fingerprint database, and determining the first sub-cluster closest to the first fingerprint data as the third sub-cluster corresponding to the first distance selected currently.
In this step, after selecting the next first distance from the distance sequence, steps 222 and 223 are circularly performed until the third sub-cluster corresponding to the first distance selected at present is the same as the cluster corresponding to the first fingerprint data in the radio frequency fingerprint database, and the third sub-cluster corresponding to the first distance selected at the time of the circulation termination is the first sub-cluster closest to the first fingerprint data.
By the method, the sub-cluster to which the first fingerprint data belongs in the boundary data set can be subjected to fine adjustment, namely the sub-cluster information of the first fingerprint data is adjusted, the radio frequency fingerprint library is updated by using the adjusted first fingerprint data, and the reliability of the fingerprint data in the radio frequency fingerprint library is improved.
The process of adjusting the sub-cluster information of the first fingerprint data is described in detail below with reference to a specific example.
The cluster of a certain first fingerprint data in the boundary data set in the radio frequency fingerprint library is C1, and the first sub cluster closest to the position of the first fingerprint data is C25. However, due to the defect of the rf fingerprint library or the change of the actual scene, the first sub-cluster C25 belongs to the C2 cluster, but not the C1 cluster, and then the first sub-cluster closest to the location where the first fingerprint data is located needs to be continuously found. Namely, selecting the next first distance from the distance sequence, determining a third sub-cluster corresponding to the first distance selected currently, and assuming that the third sub-cluster at this time is C15, the cluster to which the third sub-cluster C15 belongs is C1, and the cluster to which the historical first fingerprint data corresponding to the first fingerprint data belongs in the radio frequency fingerprint library is the same, so that the first sub-cluster closest to the first fingerprint data is the third sub-cluster C15. At this time, the first fingerprint data is incorporated into the third sub-cluster C15, and the result is to fine tune the boundary of the third sub-cluster C15 until the first fingerprint data is included.
In some embodiments, the method for updating a radio frequency fingerprint library further comprises the steps of: and dividing the historical fingerprint data in the radio frequency fingerprint library into clusters and dividing each cluster into sub-clusters to generate cluster information and sub-cluster information. It should be noted that, the steps of dividing the historical fingerprint data in the initial rf fingerprint library into clusters and dividing each cluster into sub-clusters are performed in the initialization stage, which is a preprocessing step for the initial rf fingerprint library, and in this step, clustering is performed on the historical fingerprint data in the initial rf fingerprint library to obtain a plurality of clusters, where each cluster corresponds to a location area. The user terminal opens the wireless positioning system and is connected with WI FI signals, the radio frequency fingerprint database updating device acquires fingerprint data to generate an initial radio frequency fingerprint database, and the initial radio frequency fingerprint database is initialized, wherein the content of the initialization comprises: and clustering the initial radio frequency fingerprint library. Firstly, the disordered fingerprint data in the initial radio frequency fingerprint library are clustered into a plurality of clusters, wherein the clusters can be two-dimensional or three-dimensional, each cluster corresponds to a position area, namely, the clusters and the positions form a one-to-one correspondence. For each cluster, carrying out secondary clustering on each cluster by means of differential ideas, and sequentially determining the sub-clusters of each cluster.
In some embodiments, as shown in fig. 4, the step of determining a sub-cluster of a cluster for each cluster includes:
step 41, determining the center point of each sub-cluster of the cluster in turn.
In some embodiments, C may be calculated according to the following equation (1) i Each sub cluster C in the cluster ij Is defined by the center point of (a):
wherein mu ij Is a sub cluster C ij N is the center point of the sub cluster C ij Total number of internal history fingerprint data, X n Is a sub cluster C ij Historical fingerprint data, X n (X, y, z) is X n N is the identity of the historical fingerprint data, n= (1, 2, …, N).
Step 42, for each sub-cluster, determining the range of the sub-cluster according to the center point of the sub-cluster and a preset second threshold.
The preset second threshold is the radius of the sub-cluster, and the area range of the sub-cluster can be determined according to the central point of the sub-cluster and the second threshold.
And step 43, determining the historical fingerprint data contained in the sub-cluster according to the range of the sub-cluster and the position information of the historical fingerprint data in the cluster.
In this step, the historical fingerprint data whose position information falls within the range of the sub-cluster is selected from the historical fingerprint data of the cluster, and these historical fingerprint data are members of the sub-cluster.
In some embodiments, as shown in fig. 5, in the case that the current sub-cluster is a non-first sub-cluster of the belonging cluster, the step of determining the center point of the current sub-cluster includes:
In step 411, the shortest distance between the location of each remaining historical fingerprint data in the cluster and the center point of each selected sub-cluster is determined.
The residual historical fingerprint data in the cluster refers to other historical fingerprint data except for the central point of the sub-cluster, wherein the cluster refers to the current sub-cluster C ij Cluster C to which the cluster (i.e. the sub-cluster of which the center point is to be determined) belongs i . In this step, for each remaining history fingerprint data in the cluster, a distance D between the location of the remaining history fingerprint data and the center point of each selected sub-cluster (the center point of the selected (j-1) sub-cluster) is calculated kp ，D kp ＝(D k1 ,D k2 ,…，D k(j-1) ) K is the identification of the remaining historical fingerprint data in the cluster, k= (1, 2, …, M), M is the total number of the remaining historical fingerprint data in the cluster, and p is the identification of the sub-cluster in the cluster. Determining D kp Is the minimum value D of (2) k ，D k ＝MIN(D k1 ,D k2 ,…，D k(j-1) )。
Step 412, calculating the probability of each remaining history fingerprint data in the cluster as the center point of the current sub-cluster according to the shortest distance between the position of each remaining history fingerprint data in the cluster and the center point of each selected sub-cluster and the distance between each remaining history fingerprint data in the cluster and the center point of each selected sub-cluster.
In this step, the sum D of distances between each remaining historical fingerprint data in the cluster and the center point of each selected sub-cluster is calculated, Calculating the probability of each remaining historical fingerprint data in the cluster as the center point of the current sub-cluster according to the following formula (2):
wherein P is kj The probability of the center point of the current sub-cluster j being the historical fingerprint data k.
In step 413, the center point of the current sub-cluster is determined according to the probability that each remaining historical fingerprint data in the cluster is used as the center point of the current sub-cluster.
In the step, the historical fingerprint data corresponding to the maximum probability value is selected as the center point of the current sub-cluster, so that the larger the distance between the center points of the sub-clusters is, the better the distance between the center points of the sub-clusters is in the process of selecting the center points of the sub-clusters, and the cross coincidence of adjacent sub-clusters is avoided.
Taking the remaining 2 history fingerprint data (history fingerprint data 1, history fingerprint data 2) in the cluster as an example, 2 sub-cluster center points (sub-cluster center point a, sub-cluster center point B) have been selected, the process of determining the 3 rd sub-cluster center point is as follows: for the historical fingerprint data 1, calculating the distance D between the historical fingerprint data 1 and the center point A of the sub-cluster 1A And the distance D between the historical fingerprint data 1 and the central point B of the sub cluster 1B The shortest distance between the history fingerprint data 1 and the center point of each selected sub-cluster is D1, d1=min (D 1A ，D 1B ). For the historical fingerprint data 2, calculating the distance D between the historical fingerprint data 2 and the center point A of the sub-cluster 2A And the distance D between the historical fingerprint data 2 and the central point B of the sub cluster 2B The shortest distance between the history fingerprint data 2 and the center point of each selected sub-cluster is D2, d2=min (D 2A ，D 2B ). Sum d=d of distances between each remaining historical fingerprint data in a cluster and the center point of each selected sub-cluster 1A +D 1B +D 2A +D 2B Respectively calculating probabilities P of the historical fingerprint data 1 as the center points of the third sub-cluster 13 And the probability P of the historical fingerprint data 2 as the center point of the third sub-cluster 23 ，P 13 ＝D1 2 /D 2 ，P 23 ＝D2 2 /D 2 . Comparison P 13 And P 23 And taking the historical fingerprint data corresponding to the maximum probability value as the center point of the third sub-cluster.
In the presently disclosed embodiments, for each cluster C i The aim of clustering is to improve the whole by secondary clusteringThe resolution ratio of the fingerprint data in the clusters facilitates the follow-up reliable judgment of the fingerprint data which is easy to be misjudged at the juncture or boundary of a plurality of positions.
In some embodiments, in the case that the current sub-cluster is the first sub-cluster of the cluster, one historical fingerprint data is randomly selected from the historical fingerprint data in the cluster as the center point of the first sub-cluster of the cluster. That is, if the center point of the first sub-cluster in the cluster is determined, one is randomly selected as the center point of the first sub-cluster in the cluster directly from each of the history fingerprint data in the cluster.
In some embodiments, the real-time fingerprint data includes at least location information. As shown in fig. 6, the method for dividing the real-time fingerprint data into different types of data sets according to the cluster information (i.e., step 1) includes the following steps:
and step 11, determining the cluster to which the history fingerprint data corresponding to the real-time fingerprint data belongs according to the position information and the cluster information of the real-time fingerprint data.
And step 12, calculating the center point of the cluster, and calculating a second distance between the position of the real-time fingerprint data and the center point of the cluster.
In this step, the calculation formula for calculating the center point of the cluster is similar to the formula (1), and it should be noted that, N is the total number of historical fingerprint data in the cluster and X n Is historical fingerprint data within the cluster. After calculating the center point of the cluster, calculating a second distance d between the position of the real-time fingerprint data and the center point.
And step 13, calculating a third distance between the historical fingerprint data of the boundary position of the cluster and the central point of the cluster.
In this step, a plurality of history fingerprint data of the cluster boundary position are determined, and a second distance d between each history fingerprint data of the cluster boundary position and the center point of the cluster is calculated, wherein the history fingerprint data corresponding to the maximum value of the second distance d is the history fingerprint data of the cluster boundary position, and the maximum value of the second distance d is a third distance d i,furthest 。
And 14, marking the real-time fingerprint data according to at least the second distance and the third distance.
In this step, according to the second distance d and the third distance d i,furthest And marking the real-time fingerprint data. In some embodiments, the real-time fingerprint data may be marked as strongly correlated data, outlier data, and boundary data.
And 15, generating a data set according to the marks of the real-time fingerprint data.
The same marked live fingerprint data forms the same dataset, and thus, in some embodiments, the live fingerprint data may generate strongly correlated datasets, outlier datasets, and boundary datasets.
In some embodiments, as shown in fig. 7, the method for updating the rf fingerprint library may further include the steps of, before marking the real-time fingerprint data according to at least the second distance and the third distance (i.e., step 14): and 14', acquiring an evaluation result of the position correctness of the real-time fingerprint data, which is sent by the user terminal, of the user.
After the initialization of the radio frequency fingerprint library is finished, the wireless positioning system interacts with the baseband of the user terminal to obtain fingerprint characteristic information (such as wireless signal intensity, amplitude-phase frequency information and the like) and corresponding position information in the area where the user terminal is located, the position information is presented on a user interface of the user terminal, a user can judge the position information, correct checking is performed when the position information is consistent with the actual position, and errors are checked when the position information is inconsistent with the actual position. And the user terminal uploads the position information and the fingerprint characteristic information of the crowd-sourced data (real-time fingerprint data) and the position evaluation result given by the user to a server (namely a radio frequency fingerprint library updating device) at the network side.
In some embodiments, as shown in fig. 7, the marking (i.e. step 14) of the real-time fingerprint data according to at least the second distance and the third distance includes the steps of:
step 141, in response to the evaluation result being erroneous and the second distance being greater than the third distance (d>d i,furthest ) The real-time fingerprint data is marked as first anomaly data.
And 142, screening second abnormal data with the distance between the position and the central point of the cluster to which the real-time fingerprint data belongs being smaller than a preset third threshold value from the first abnormal data, marking the second abnormal data as boundary data, wherein the data in the boundary data set are boundary data, and the data in the abnormal data set are data except the boundary data in the first abnormal data.
In some embodiments, as shown in fig. 7, the marking (i.e. step 14) of the real-time fingerprint data according to at least the second distance and the third distance further includes the steps of:
step 143, in response to the evaluation result being correct and the second distance being less than the third distance (d<d i,furthest ) And marking the real-time fingerprint data as strongly-correlated data, wherein the data in the strongly-correlated data set are the strongly-correlated data.
In the embodiment of the disclosure, a double confirmation mechanism is adopted to divide a data set for fingerprint data, and if the real-time fingerprint data fall into corresponding clusters in a radio frequency fingerprint library through double confirmation, the real-time fingerprint data are marked as strong correlation data to form a strong correlation data set; and if the real-time fingerprint data do not fall into the corresponding clusters in the radio frequency fingerprint library through double confirmation, marking the real-time fingerprint data as first abnormal data. Wherein, the first abnormal data is subjected to secondary judgment, if the first abnormal data is at the boundary position of the cluster, namely the distance d between the first abnormal data and the center point of the cluster is approximately equal to the third distance d between the historical fingerprint data of the boundary position of the cluster and the center point of the cluster i,furthest The real-time fingerprint data of this kind is marked as boundary data, forming a boundary data set. After the boundary data set is formed, the boundary data set is removed from the first abnormal data, and then the abnormal data set can be obtained.
In some embodiments, in the case that the data set is an abnormal data set, the updating the rf fingerprint library according to each type of data set (i.e. step 2) includes the following steps: and deleting the historical fingerprint data corresponding to the abnormal data set in the radio frequency fingerprint database, namely deleting the first abnormal data from which the second abnormal data is deleted in the radio frequency fingerprint database.
In some embodiments, in the case that the data set is a strongly correlated data set, the updating the rf fingerprint library according to each type of data set (i.e. step 2) includes the following steps: and updating the radio frequency fingerprint database according to the strong correlation data in the strong correlation data set, namely, replacing corresponding historical fingerprint data in the radio frequency fingerprint database by the strong correlation data in the strong correlation data set.
As shown in fig. 8, after the rf fingerprint library is updated according to the strong correlation data in the strong correlation data set (i.e., step 2), the rf fingerprint library updating method further includes the steps of:
And step 3, dividing clusters of historical fingerprint data in the updated radio frequency fingerprint library and sub-clusters of each cluster to update cluster information and sub-cluster information.
In this step, after the rf fingerprint library is updated by using the strong correlation data set, the fingerprint data in the rf fingerprint library is divided into clusters and sub-clusters again to update the cluster information and the sub-cluster information for use in next update of the rf fingerprint library.
According to the embodiment of the disclosure, crowdsourcing data is acquired in the process of acquiring the radio frequency fingerprint data, so that the active feedback effect of a user on a positioning result is exerted to a certain extent, and the timeliness of the fingerprint data is improved. And comparing the position judgment result of the user in the crowdsourcing data with a secondary differential clustering result in the preprocessing process of the radio frequency fingerprint database, performing correlation classification on the crowdsourcing data, and particularly performing sub-cluster boundary differential movement optimization processing on the fingerprint data which is easy to misjudge, thereby improving the reliability of the fingerprint data in the radio frequency fingerprint database and the indoor positioning accuracy of the terminal.
Based on the same technical concept, the embodiment of the disclosure further provides a device for updating a radio frequency fingerprint database, as shown in fig. 9, where the device is used for updating the radio frequency fingerprint database, historical fingerprint data in the radio frequency fingerprint database includes cluster information and sub-cluster information, and the device for updating the radio frequency fingerprint database includes a data acquisition module 101, a data processing module 102 and a data updating module 103.
The data acquisition module 101 is configured to acquire real-time fingerprint data.
The data processing module 102 is configured to divide the real-time fingerprint data into different types of data sets according to the cluster information, where the data sets at least include boundary data sets.
The data updating module 103 is configured to update the rf fingerprint library according to each type of data set; and aiming at the first fingerprint data in the boundary data set, determining a first sub-cluster closest to the position of the first fingerprint data according to the sub-cluster information, and updating the sub-cluster information of the historical first fingerprint data in the radio frequency fingerprint database according to the information of the first sub-cluster.
In some embodiments, the data updating module 103 is configured to determine, according to the sub-cluster information, a second sub-cluster having a distance from the location where the first fingerprint data is located that is smaller than a preset first threshold; and calculating a first distance between the first fingerprint data and the center point of each second sub-cluster, and determining the first sub-cluster closest to the position where the first fingerprint data is located according to the first distance and the cluster where the first fingerprint data belongs in the radio frequency fingerprint library.
In some embodiments, the data updating module 103 is configured to sort the first distances from small to large to obtain a distance sequence; determining a current first distance according to the sequence of the first distances in the distance sequence, and determining a cluster to which a third sub-cluster corresponding to the current first distance belongs; determining a first sub-cluster closest to the first fingerprint data as the third sub-cluster in response to the fact that the cluster to which the third sub-cluster belongs is the same as the cluster to which the historical first fingerprint data in the radio frequency fingerprint database belongs; and responding to the fact that the cluster to which the third sub-cluster belongs is different from the cluster to which the historical first fingerprint data belongs in the radio frequency fingerprint library, selecting the next first distance according to the distance sequence until the cluster to which the third sub-cluster corresponding to the first distance selected currently belongs is the same as the cluster to which the historical first fingerprint data belongs in the radio frequency fingerprint library, and determining the first sub-cluster closest to the first fingerprint data as the third sub-cluster corresponding to the first distance selected currently.
In some embodiments, as shown in fig. 10, the apparatus for updating a radio frequency fingerprint library further includes a preprocessing module 104, where the preprocessing module 104 is configured to divide a cluster of historical fingerprint data in the radio frequency fingerprint library and divide each cluster into sub-clusters to generate the cluster information and sub-cluster information; determining a sub-cluster of each cluster in turn; wherein the sub-clusters of the clusters are determined by: sequentially determining the center point of each sub-cluster of the cluster; for each sub-cluster, determining the range of the sub-cluster according to the center point of the sub-cluster and a preset second threshold; and determining the historical fingerprint data contained in the sub-cluster according to the range of the sub-cluster and the position information of the historical fingerprint data in the cluster.
In some embodiments, the preprocessing module 104 is configured to determine, in a case where the current sub-cluster is a non-first sub-cluster of the cluster to which the current sub-cluster belongs, a center point of the current sub-cluster by: determining the shortest distance between the position of each residual historical fingerprint data in the cluster and the center point of each selected sub-cluster; respectively calculating the probability of taking each residual historical fingerprint data in the cluster as the center point of the current sub-cluster according to the shortest distance between the position of each residual historical fingerprint data in the cluster and the center point of each selected sub-cluster and the distance between each residual historical fingerprint data in the cluster and the center point of each selected sub-cluster; and determining the center point of the current sub-cluster according to the probability that each residual historical fingerprint data in the cluster is taken as the center point of the current sub-cluster.
In some embodiments, the preprocessing module 104 is configured to randomly select, in a case where the current sub-cluster is a first sub-cluster of the cluster to which the current sub-cluster belongs, one historical fingerprint data from the historical fingerprint data in the cluster as a center point of the first sub-cluster of the cluster.
In some embodiments, the real-time fingerprint data at least includes location information, and the data processing module 102 is configured to determine, according to the location information of the real-time fingerprint data and the cluster information, a cluster to which historical fingerprint data corresponding to the real-time fingerprint data belongs; calculating the central point of the cluster, and calculating a second distance between the position of the real-time fingerprint data and the central point of the cluster; calculating a third distance between historical fingerprint data of the boundary position of the cluster and the central point of the cluster; marking the real-time fingerprint data according to at least the second distance and the third distance; a dataset is generated from the markers of the real-time fingerprint data.
In some embodiments, the data set further includes an abnormal data set, and the data acquisition module 101 is further configured to obtain an evaluation result of the position correctness of the real-time fingerprint data sent by the user terminal, before the data processing module 102 marks the real-time fingerprint data according to at least the second distance and the third distance.
The data processing module 102 is configured to mark the real-time fingerprint data as first abnormal data in response to the evaluation result being an error and the second distance being greater than the third distance; and screening second abnormal data, the distance between the position of which and the central point of the cluster to which the real-time fingerprint data belongs, from the first abnormal data is smaller than a preset third threshold value, and marking the second abnormal data as boundary data, wherein data in the boundary data set are the boundary data, and data in the abnormal data set are data except the boundary data in the first abnormal data.
In some embodiments, the data updating module 103 is configured to delete, in a case where the data set is an abnormal data set, historical fingerprint data corresponding to the abnormal data set in the rf fingerprint database.
In some embodiments, the data set further comprises a strongly correlated data set, and the data processing module 102 is further configured to mark the real-time fingerprint data as strongly correlated data in response to the evaluation result being correct and the second distance being less than the third distance, the data in the strongly correlated data set being the strongly correlated data.
In some embodiments, the data updating module 103 is configured to update the rf fingerprint library according to strongly correlated data in the strongly correlated data set, in case the data set is the strongly correlated data set.
The preprocessing module 104 is further configured to, after updating the rf fingerprint library according to the strong correlation data in the strong correlation data set, divide clusters of historical fingerprint data in the updated rf fingerprint library and divide sub-clusters of each cluster, so as to update the cluster information and the sub-cluster information.
The disclosed embodiments also provide a computer device comprising: one or more processors and a storage device; the storage device stores one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method for updating the rf fingerprint library provided in the foregoing embodiments.
The disclosed embodiments also provide a computer readable medium having a computer program stored thereon, wherein the computer program when executed implements the radio frequency fingerprint library updating method as provided by the foregoing embodiments.
Those of ordinary skill in the art will appreciate that all or some of the steps of the methods, functional modules/units in the apparatus disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. In a hardware implementation, the division between the functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed cooperatively by several physical components. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as known to those skilled in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Furthermore, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media.
Example embodiments have been disclosed herein, and although specific terms are employed, they are used and should be interpreted in a generic and descriptive sense only and not for purpose of limitation. In some instances, it will be apparent to one skilled in the art that features, characteristics, and/or elements described in connection with a particular embodiment may be used alone or in combination with other embodiments unless explicitly stated otherwise. It will therefore be understood by those of ordinary skill in the art that various changes in form and details may be made therein without departing from the scope of the present invention as set forth in the following claims.

Claims (14)

1. A method for updating a radio frequency fingerprint library, wherein historical fingerprint data in the radio frequency fingerprint library comprises cluster information and sub-cluster information, the method comprising:
acquiring real-time fingerprint data, and dividing the real-time fingerprint data into different types of data sets according to the cluster information, wherein the data sets at least comprise boundary data sets;
updating the radio frequency fingerprint library according to each type of data set; and aiming at the first fingerprint data in the boundary data set, determining a first sub-cluster closest to the position of the first fingerprint data according to the sub-cluster information, and updating the sub-cluster information of the historical first fingerprint data in the radio frequency fingerprint database according to the information of the first sub-cluster.
2. The method of claim 1, wherein determining, according to the sub-cluster information, a first sub-cluster closest to a location where the first fingerprint data is located, comprises:
determining a second sub-cluster with a distance smaller than a preset first threshold value from the position of the first fingerprint data according to the sub-cluster information;
and calculating a first distance between the first fingerprint data and the center point of each second sub-cluster, and determining the first sub-cluster closest to the position where the first fingerprint data is located according to the first distance and the cluster where the first fingerprint data belongs in the radio frequency fingerprint library.
3. The method of claim 2, wherein determining a first sub-cluster closest to the location of the first fingerprint data according to the first distance and the cluster to which the first fingerprint data belongs in the rf fingerprint library, comprises:
sequencing the first distances from small to large to obtain a distance sequence;
determining a current first distance according to the sequence of the first distances in the distance sequence, and determining a cluster to which a third sub-cluster corresponding to the current first distance belongs;
determining a first sub-cluster closest to the first fingerprint data as the third sub-cluster in response to the fact that the cluster to which the third sub-cluster belongs is the same as the cluster to which the historical first fingerprint data in the radio frequency fingerprint database belongs;
And responding to the fact that the cluster to which the third sub-cluster belongs is different from the cluster to which the historical first fingerprint data belongs in the radio frequency fingerprint library, selecting the next first distance according to the distance sequence until the cluster to which the third sub-cluster corresponding to the first distance selected currently belongs is the same as the cluster to which the historical first fingerprint data belongs in the radio frequency fingerprint library, and determining the first sub-cluster closest to the first fingerprint data as the third sub-cluster corresponding to the first distance selected currently.
4. The method as recited in claim 1, further comprising: dividing historical fingerprint data in the radio frequency fingerprint library into clusters and dividing each cluster into sub-clusters to generate cluster information and sub-cluster information; the step of clustering the historical fingerprint data in the radio frequency fingerprint library comprises the following steps:
determining a sub-cluster of each cluster in turn;
wherein the sub-clusters of the clusters are determined by:
sequentially determining the center point of each sub-cluster of the cluster;
for each sub-cluster, determining the range of the sub-cluster according to the center point of the sub-cluster and a preset second threshold;
and determining the historical fingerprint data contained in the sub-cluster according to the range of the sub-cluster and the position information of the historical fingerprint data in the cluster.
5. The method of claim 4, wherein in the case that the current sub-cluster is a non-first sub-cluster of the belonging cluster, the center point of the current sub-cluster is determined by:
determining the shortest distance between the position of each residual historical fingerprint data in the cluster and the center point of each selected sub-cluster;
respectively calculating the probability of taking each residual historical fingerprint data in the cluster as the center point of the current sub-cluster according to the shortest distance between the position of each residual historical fingerprint data in the cluster and the center point of each selected sub-cluster and the distance between each residual historical fingerprint data in the cluster and the center point of each selected sub-cluster;
and determining the center point of the current sub-cluster according to the probability that each residual historical fingerprint data in the cluster is taken as the center point of the current sub-cluster.
6. The method of claim 4, wherein in case that the current sub-cluster is a first sub-cluster of the cluster to which the current sub-cluster belongs, one history fingerprint data is randomly selected from among history fingerprint data within the cluster as a center point of the first sub-cluster of the cluster.
7. The method according to any of claims 1-6, wherein the real-time fingerprint data comprises at least location information, and wherein the partitioning of the real-time fingerprint data into different types of data sets based on the cluster information comprises:
Determining a cluster to which historical fingerprint data corresponding to the real-time fingerprint data belongs according to the position information of the real-time fingerprint data and the cluster information;
calculating the central point of the cluster, and calculating a second distance between the position of the real-time fingerprint data and the central point of the cluster;
calculating a third distance between historical fingerprint data of the boundary position of the cluster and the central point of the cluster;
marking the real-time fingerprint data according to at least the second distance and the third distance;
a dataset is generated from the markers of the real-time fingerprint data.
8. The method of claim 7, wherein the dataset further comprises an anomaly dataset, the method further comprising, prior to marking the real-time fingerprint data based at least on the second distance and the third distance: acquiring an evaluation result of the position correctness of the real-time fingerprint data, which is sent by a user terminal, of the user;
the marking the real-time fingerprint data according to at least the second distance and the third distance includes:
in response to the evaluation result being an error and the second distance being greater than the third distance, marking the real-time fingerprint data as first anomaly data;
And screening second abnormal data, the distance between the position of which and the central point of the cluster to which the real-time fingerprint data belongs, from the first abnormal data is smaller than a preset third threshold value, and marking the second abnormal data as boundary data, wherein data in the boundary data set are the boundary data, and data in the abnormal data set are data except the boundary data in the first abnormal data.
9. The method of claim 8, wherein, in the case where the dataset is an anomalous dataset, the updating the rf fingerprint library from each type of dataset comprises: and deleting the historical fingerprint data corresponding to the abnormal data set in the radio frequency fingerprint database.
10. The method of claim 8, wherein the dataset further comprises a strongly correlated dataset, the marking the real-time fingerprint data based at least on the second distance and the third distance, further comprising:
and in response to the evaluation result being correct and the second distance being smaller than the third distance, marking the real-time fingerprint data as strongly correlated data, wherein the data in the strongly correlated data set are the strongly correlated data.
11. The method of claim 10, wherein, in the case where the dataset is a strongly correlated dataset, the updating the rf fingerprint library from each type of dataset comprises: updating the radio frequency fingerprint library according to the strong correlation data in the strong correlation data set;
after updating the radio frequency fingerprint library according to the strongly correlated data in the strongly correlated data set, the method further comprises:
and dividing the historical fingerprint data in the updated radio frequency fingerprint library into clusters and dividing each cluster into sub-clusters so as to update the cluster information and the sub-cluster information.
12. The device is used for updating a radio frequency fingerprint library, wherein historical fingerprint data in the radio frequency fingerprint library comprises cluster information and sub-cluster information, and the radio frequency fingerprint library updating device comprises a data acquisition module, a data processing module and a data updating module;
the data acquisition module is used for acquiring real-time fingerprint data;
the data processing module is used for dividing the real-time fingerprint data into different types of data sets according to the cluster information, wherein the data sets at least comprise boundary data sets;
the data updating module is used for updating the radio frequency fingerprint library according to various data sets; and aiming at the first fingerprint data in the boundary data set, determining a first sub-cluster closest to the position of the first fingerprint data according to the sub-cluster information, and updating the sub-cluster information of the historical first fingerprint data in the radio frequency fingerprint database according to the information of the first sub-cluster.
13. A computer device, comprising:
one or more processors;
a storage device having one or more programs stored thereon;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the radio frequency fingerprint library updating method of any of claims 1-11.
14. A computer readable medium having stored thereon a computer program, wherein the program when executed implements the radio frequency fingerprint library updating method of any of claims 1-11.
CN202210493455.6A 2022-05-07 2022-05-07 Method, device, equipment and medium for updating radio frequency fingerprint library Pending CN117053784A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202210493455.6A CN117053784A (en) 2022-05-07 2022-05-07 Method, device, equipment and medium for updating radio frequency fingerprint library
PCT/CN2023/090782 WO2023216882A1 (en) 2022-05-07 2023-04-26 Radio-frequency fingerprint library updating method and apparatus, and computer device and computer storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210493455.6A CN117053784A (en) 2022-05-07 2022-05-07 Method, device, equipment and medium for updating radio frequency fingerprint library

Publications (1)

Publication Number Publication Date
CN117053784A true CN117053784A (en) 2023-11-14

Family

ID=88667951

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210493455.6A Pending CN117053784A (en) 2022-05-07 2022-05-07 Method, device, equipment and medium for updating radio frequency fingerprint library

Country Status (2)

Country Link
CN (1) CN117053784A (en)
WO (1) WO2023216882A1 (en)

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104113868A (en) * 2014-06-20 2014-10-22 浙江工业大学 Crowdsourcing maintenance-based indoor position fingerprint database establishment method and system
CN105813194B (en) * 2016-05-06 2019-04-23 西安电子科技大学昆山创新研究院 Indoor orientation method based on fingerprint database secondary correction
CN106714109B (en) * 2017-01-12 2020-08-25 上海交通大学 WiFi fingerprint database updating method based on crowdsourcing data
CN107241700B (en) * 2017-04-23 2020-09-25 西安电子科技大学 Indoor positioning method based on CSI space-frequency characteristic and reference point position clustering algorithm
CN108009485B (en) * 2017-11-28 2020-06-26 元力云网络有限公司 Wireless fingerprint database updating method based on crowdsourcing data
US10641610B1 (en) * 2019-06-03 2020-05-05 Mapsted Corp. Neural network—instantiated lightweight calibration of RSS fingerprint dataset

Also Published As

Publication number Publication date
WO2023216882A1 (en) 2023-11-16

Similar Documents

Publication Publication Date Title
CN106714109B (en) WiFi fingerprint database updating method based on crowdsourcing data
CN106646338B (en) A kind of quickly accurate indoor orientation method
EP2111721B1 (en) System and method for generating non-uniform grid points from calibration data
CN109168177B (en) Longitude and latitude backfill method based on soft mining signaling
CN110166991B (en) Method, device, apparatus and storage medium for locating electronic device
CN113160274A (en) Improved deep sort target detection tracking method based on YOLOv4
CN114449452B (en) Wi-Fi indoor positioning method based on CNN-RNN
CN103916820A (en) Wireless indoor locating method based on access point stability degree
CN109348416B (en) Fingerprint indoor positioning method based on binary k-means
CN108764157B (en) Building laser foot point extraction method and system based on normal vector Gaussian distribution
CN112462347B (en) Laser radar point cloud rapid classification filtering algorithm based on density clustering
CN117874690B (en) Intelligent management method for geographic information mapping data
CN111444294A (en) Track completion method and device and electronic equipment
CN109246728B (en) Method and device for identifying coverage abnormal cell
CN112203324B (en) MR positioning method and device based on position fingerprint database
CN117053784A (en) Method, device, equipment and medium for updating radio frequency fingerprint library
CN113079466B (en) Fingerprint database construction method, device, equipment and computer storage medium
CN116500703B (en) Thunderstorm monomer identification method and device
CN114423025B (en) Scene recognition method, device, equipment and storage medium
CN115830342A (en) Method and device for determining detection frame, storage medium and electronic device
CN113689526A (en) Method and device for dividing invalid area in map and electronic equipment
Hu et al. Reducing Wi-Fi fingerprint collection based on affinity propagation clustering and WKNN interpolation algorithm
CN116342826B (en) AR map construction method and device
CN113326805B (en) Human body cover updating method and device, electronic equipment and storage medium
CN111935817B (en) AP (access point) selection positioning method and device based on eight-matrix diagram and intelligent equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication