CN111726743A - Wifi positioning method and system based on online learning - Google Patents
Wifi positioning method and system based on online learning Download PDFInfo
- Publication number
- CN111726743A CN111726743A CN201910162851.9A CN201910162851A CN111726743A CN 111726743 A CN111726743 A CN 111726743A CN 201910162851 A CN201910162851 A CN 201910162851A CN 111726743 A CN111726743 A CN 111726743A
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- wifi
- online learning
- coordinates
- positioning method
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 72
- 238000001914 filtration Methods 0.000 claims description 15
- 239000013598 vector Substances 0.000 claims description 13
- 230000005540 biological transmission Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 5
- 238000007476 Maximum Likelihood Methods 0.000 claims description 3
- 239000000523 sample Substances 0.000 description 30
- 238000010586 diagram Methods 0.000 description 18
- 238000003860 storage Methods 0.000 description 8
- 238000012549 training Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 238000005562 fading Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 238000000060 site-specific infrared dichroism spectroscopy Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
-
- 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
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention provides a wifi positioning method and system based on online learning, wherein the method comprises the following steps: collecting fingerprint information to generate a fingerprint database; the fingerprint information comprises fingerprint coordinates, strength indication RSSI of a received signal, a distance d between the fingerprint coordinates and wifi equipment coordinates, and a loss parameter and a constant K of the RSSI; and matching the signal data received by the wifi device from the device to be positioned in real time with the data in the fingerprint database, and calculating the coordinate data of the device to be positioned according to the fingerprint coordinate data. By adopting the wifi positioning method and system based on online learning, the workload of fingerprint library acquisition can be greatly reduced, the reliability of the fingerprint library can be ensured, and the wifi positioning precision is improved; the labor cost is saved, and the tester can be easily operated and executed, so that the large-scale popularization of the engineering is facilitated.
Description
[ technical field ] A method for producing a semiconductor device
The invention relates to the technical field of wifi positioning, in particular to a wifi positioning method and system based on online learning.
[ background of the invention ]
In wifi positioning, common positioning algorithms include a triangulation positioning algorithm and a positioning algorithm based on position fingerprints, and the two positioning algorithms have advantages and disadvantages respectively.
The triangulation algorithm generally uses a mathematical model established by a triangulation geometry principle to calculate the position Of the mobile terminal, and commonly used methods include a Time Of Arrival (TOA), a Time Difference Of Arrival (TDOA), and an Angle Of incidence (AOA). A large amount of fingerprints are not required to be collected in the implementation process, so that the labor cost is low; but the positioning accuracy is poor, and the requirement on hardware equipment is high due to the high algorithm complexity.
The location fingerprint positioning algorithm comprises an offline training process and an online matching process, wherein a large number of fingerprints need to be acquired in the offline training process, and each location fingerprint consists of a group of Received Signal Strength Indicator (RSSI) (received Signal Strength indicator) vectors [ AP1, AP2, … … and API ] and coordinate information of the location. Due to the unstable factors of the external environment, the reliability of the manually acquired RSSI vector is low. Such a time and labor investment is necessary if all of the collected data is useful to improve the performance of the system. However, in practice, many data are not useful, and positioning errors are easily caused. From the RSSI fingerprint point of view, the variance of RSSI should be as small as possible, with no other location fingerprint in the signal space being very close to it. However, some fingerprints are not close to each other in actual position, and the euclidean distance in the signal space is relatively small, so that the performance may not be improved by the fingerprint acquisition, and an extra calculation amount may be caused in the positioning process, and the positioning accuracy may be even reduced by putting the fingerprints into the fingerprint library.
[ summary of the invention ]
The technical problem to be solved by the invention is to provide a wifi positioning method and system based on online learning, which can greatly reduce the workload of collecting a fingerprint library, ensure the reliability of the fingerprint library and improve the wifi positioning precision; the labor cost is saved, and the tester can be easily operated and executed, so that the large-scale popularization of the engineering is facilitated.
In order to solve the above technical problem, in one aspect, an embodiment of the present invention provides a wifi positioning method based on online learning, including: collecting fingerprint information to generate a fingerprint database; the fingerprint information comprises fingerprint coordinates, strength indication RSSI of a received signal, a distance d between the fingerprint coordinates and wifi equipment coordinates, and loss parameters and a constant K of the RSSI; and matching the signal data received by the wifi device from the device to be positioned in real time with the data in the fingerprint database, and calculating the coordinate data of the device to be positioned according to the fingerprint coordinate data.
Preferably, the distance d between the generated fingerprint coordinates and the wifi device coordinates and the loss parameter and constant K of the RSSI are obtained by linear fitting.
Preferably, the matching of the signal data received by the wifi device from the device to be positioned in real time with the data in the fingerprint database, and the calculating of the coordinate data of the device to be positioned according to the fingerprint coordinate data further include: and filtering the coordinate data of the equipment to be positioned.
Preferably, the signals received by the wifi device in real time are matched with the fingerprint database by adopting a probabilistic algorithm, a deterministic algorithm or a computational similarity algorithm.
Preferably, the generating the fingerprint database includes: and calculating the received signal intensity of the equipment to be positioned according to the distance d between the fingerprint coordinates and the wifi equipment coordinates and a transmission loss model of the wireless signals, wherein the signal intensity forms a group of signal vectors [ AP1, AP2, … … and APn ], and a piece of fingerprint information is formed and stored by combining the position coordinates of the equipment to be positioned.
Preferably, after filtering the coordinate data of the device to be positioned, the method further includes: and storing the coordinate data of the equipment to be positioned in the corresponding fingerprint database.
Preferably, the filtering of the coordinates to be located adopts a moving average filtering method or a kalman filtering method.
Preferably, the probabilistic algorithm comprises a naive bayes method, a kernel function method or a maximum likelihood probability method.
Preferably, the deterministic algorithm comprises: and estimating the position coordinates of the equipment to be positioned by adopting a deterministic inference algorithm.
Preferably, the deterministic algorithm comprises: a nearest neighbor method or a K weighted neighbor method or a dynamic K-value weighted algorithm.
Preferably, the computational similarity algorithm comprises a cosine similarity algorithm.
Preferably, the cosine similarity algorithm comprises: and taking the content subjected to similarity comparison as a vector, calculating the rest chord values, and selecting a fingerprint coordinate with the highest similarity to calculate the position coordinate of the equipment to be positioned.
In another aspect, an embodiment of the present invention provides a wifi positioning system based on online learning, including: the system comprises wifi equipment, a POE power supply module and a server, and the system executes the positioning method.
Compared with the prior art, the technical scheme has the following advantages: the workload of collecting the fingerprint library can be greatly reduced, the reliability of the fingerprint library can be ensured, and the wifi positioning precision is improved; the labor cost is saved, and the tester can be easily operated and executed, so that the large-scale popularization of the engineering is facilitated.
[ description of the drawings ]
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive labor.
FIG. 1 is a diagram Of a prior art Time Of Arrival (TOA) based positioning concept;
FIG. 2 is a diagram Of a prior art Time Difference Of Arrival (TDOA) based positioning scheme;
FIG. 3 is a schematic diagram Of positioning based on an Angle Of incidence (AOA) method in the prior art;
FIG. 4 is a schematic diagram of location fingerprint location of the wifi location method based on online learning according to the present invention
FIG. 5 is a flow chart of the wifi positioning method based on online learning of the present invention;
FIG. 6 is a flow chart of another wifi positioning method based on online learning according to the present invention;
FIG. 7 is a schematic diagram of fingerprint library storage in the wifi positioning method based on online learning according to the present invention;
FIG. 8 is a block diagram of a wifi positioning system based on online learning of the present invention;
FIG. 9 is a schematic diagram of the data server storage of FIG. 7;
fig. 10 is a schematic diagram of the location server storage in fig. 7.
[ detailed description ] embodiments
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
wifi devices are many, such as smart phones, tablet and notebook computers, wireless routers, and the like. The wifi probe identifies wireless device information near the wireless wifi access point based on wifi detection technology. The smart phone or WiFi terminal (notebook, tablet computer, etc.) with WiFi function is turned on, the user does not need to actively access WiFi, the probe can identify the user, whether IOS or android system can detect the user, and the MAC address of the device is obtained. The Wi-Fi probe can provide basic identity identification data, and can associate the collected MAC address data with data of telecommunication enterprises and public security organs, so that a multi-dimensional public security monitoring system can be established. The MAC address serves as a unique identification code of the smart phone and can serve as identification of identity information. The Wi-Fi probe has wide coverage by combining video perception deployment position construction, can collect MAC addresses within a range, is not limited by data, and can collect massive MAC addresses. The Wi-Fi probe can realize real-time transmission of data, and monitoring data can be transmitted back in real time; identity matching: the MAC address is used as a unique identification code of the mobile phone, and identity matching can be realized by combining other data. The wifi device is illustrated by using a wifi probe as an example in the following examples.
Fig. 1 is a diagram Of a Time Of Arrival (TOA) based positioning principle in the prior art. Fig. 2 is a diagram Of a Time Difference Of Arrival (TDOA) based positioning principle in the prior art. Fig. 3 is a schematic diagram Of positioning based on an Angle Of incidence (AOA) method in the prior art, as described in the background art, the three methods do not need to collect a large number Of fingerprints in the implementation process, although the labor cost is low, the positioning accuracy is poor, and the requirement on hardware preparation is high due to the high algorithm complexity.
Example one
FIG. 4 is a schematic diagram of location fingerprint location of the wifi location method based on online learning according to the present invention. The location fingerprint positioning technology is a non-ranging positioning based on received signal strength indicator RSSI (received signal strength indicator), and deduces a position to be positioned by using different RSSI characteristics through different received signal strength (RSSI value) characteristics at different positions, and comprises two stages of offline training and online positioning:
off-line training: the daily standard is to establish a position fingerprint database, firstly, a plane distribution map of a region to be positioned is obtained, a series of position fingerprint sampling points (namely reference points RPs are distributed in the region to be positioned at equal intervals according to a grid in advance, and the coordinates of the reference points are obtained by measurement in advance.
And (3) online positioning: the method comprises the steps that a user to be positioned collects RSSI values of all APs scanned by a mobile terminal in real time at a certain position in an area to be positioned, MAC addresses, names (BSSIDs) and RSSI values corresponding to all APs form a fingerprint vector to serve as input data of a matching positioning algorithm, the specific matching algorithm is matched with position fingerprint database data, and coordinates to be positioned are calculated through coordinates of reference points.
The position fingerprint positioning algorithm needs to acquire a large number of fingerprints in an off-line training process, and the position fingerprints are composed of a group of RSSI vectors [ AP1, AP 2.., APi ] and coordinate information of the position.
FIG. 5 is a flowchart of the wifi positioning method based on online learning according to the present invention. The wifi positioning method based on online learning comprises the following steps: collecting fingerprint information to generate a fingerprint database; the fingerprint information comprises fingerprint coordinates, strength indication RSSI of a received signal, a distance d between the fingerprint coordinates and wifi equipment coordinates, and loss parameters and a constant K of the RSSI; (ii) a And matching the signal data received by the wifi device from the device to be positioned in real time with the data in the fingerprint database, and calculating the coordinate data of the device to be positioned according to the fingerprint coordinate data.
FIG. 6 is a flow chart of another wifi locating method based on online learning according to the present invention. The difference from fig. 5 is that after the step of calculating the coordinate data of the device to be positioned according to the fingerprint coordinate data, the method further comprises the step of storing the coordinate data of the device to be positioned in the fingerprint database and outputting the positioning result of the position coordinate of the device to be positioned.
And storing the coordinate data of the equipment to be positioned in the fingerprint database, so that a user can conveniently track the fingerprint data history of the detected equipment to be positioned.
And outputting a positioning result of the position coordinates of the equipment to be positioned, so that the user can conveniently check the positioning result.
In practical implementation, since the wireless signal is usually affected by path loss, shadow, fading, and the like during transmission, the relationship between the power of the received signal and the distance can be given by the signal transmission loss model.
The transmission loss model typically employs a simplified model as follows:
Pr(d)＝K-10lg(d)(dBm)
wherein d represents the distance between the receiver and the transmitter, represents the loss factor in free space, Pr(d) Represents the value of the signal power transmission loss when the distance between the receiver and the transmitter is d, dBm being the unit: decibel milliwatts, as a unit of signal power. K is a constant and can be selected as desired.
From the above, the average RSSI at different distances from the fixed signal emission source is proportional to the logarithm of the distance, and based on this model, the distance d and the P of the received signal can be found by on-line learningr(d) The relationship between them.
It should be noted that the fixed emission source may be a wifi probe device, a bluetooth device, or other radio devices. This case is illustrated by taking wifi probes as an example, and the online learning wifi localization scheme is as follows:
(1) initialization parameters and K
From the above formula, if the loss factor and the constant K are known in a propagation environment, the RSSI at different distances from the fixed transmission source can be estimated.
And K can be initialized by means of empirical values or online learning. The online learning method comprises the following steps: in the coverage area of the probe, fingerprint information (including coordinates and RSSI) of equipment to be positioned is collected, and parameters K of the distance and the RSSI are generated in a linear fitting mode.
(2) Generating a fingerprint database
Collecting fingerprint coordinates (only including position coordinates and not including RSSI) of equipment to be positioned in the coverage area of the probe, calculating the distance d between all the fingerprint coordinates and wifi probe coordinates, and according to a transmission loss model P of a wireless signalr(d) K-10lg (d) (dbm), calculating the received signal strength of different wifi probes at different positions, and combining the received signal strength of different probes into a set of signal vectors [ AP1, AP2]Combining the position coordinates to form a piece of fingerprint information to be stored. The memory structure is shown in fig. 7. FIG. 7 is a schematic diagram of fingerprint database storage in the wifi positioning method based on online learning, in which each row of data represents the ith fingerprint information code number, the ith fingerprint information X-coordinate value, the ith fingerprint information Y-coordinate value, different probe detection numbersThe measured signal vector.
It should be noted that, in combination with the attenuation law of the actual signal, if the distance between a certain fingerprint coordinate and the wifi probe coordinate is greater than the threshold d0If the received signal is very weak, the signal of the corresponding probe cannot be received at the fingerprint position coordinate, and the signal strength of the probe is not stored. In specific implementation, the distance threshold d0The specific selection is related to the environment and the probe coverage.
(3) On-line matching
The on-line matching method and the on-line positioning stage in the position fingerprint positioning scheme are matched by calculating a signal received in real time and fingerprint database data according to a certain matching algorithm, and the coordinates of the equipment to be positioned are calculated according to the fingerprint coordinates.
In general, typical online matching methods are classified into probabilistic algorithms and deterministic algorithms.
Commonly used probabilistic algorithms include: naive Bayes, kernel function, maximum likelihood probability, etc. The core idea is as follows: in the off-line stage, the RSSI probability distribution function of each reference point is fitted through the RSSI observed value (represented by a random variable x) collected from APs at each reference point. And (3) calculating the conditional probability or posterior probability of the RSSI of the point to be positioned by assuming the actually measured RSSI vector (represented by a random variable y) at the point to be positioned. Selecting the reference point X with the maximum posterior probability0The method is used as the estimation position of the point to be positioned, or a plurality of reference points with high posterior probability are selected, and the positions of the reference points participate in the estimation of the position of the point to be positioned together.
Unlike probabilistic algorithms based on probabilities, deterministic algorithms use deterministic inference algorithms to estimate the location of the terminal to be located, such as Nearest Neighbor (NN), K-nearest neighbor (KNN), K-weighted neighbor (WKNN), dynamic K-value weighting algorithms (EWKNN), etc.
Meanwhile, the method also comprises an online matching method for calculating the similarity, such as a cosine similarity method. The cosine similarity method is to calculate similarity by means of cosine, wherein cosine is an included angle between two vectors, content needing similarity comparison is regarded as a vector, and other chord values are calculated. And selecting a fingerprint coordinate with the highest similarity to calculate the coordinate to be positioned.
(4) Filtering
And (4) filtering the coordinate data of the equipment to be positioned in the step (3), wherein the dynamic track of each user is predicted. Common filtering methods include moving average filtering, kalman filtering, and the like.
(5) Outputting the positioning result
And (4) storing the filtered result in the corresponding database in a format shown in FIG. 9, and outputting the positioning result. In the figure, each row of data represents the number of the equipment to be positioned, the MAC address of the equipment to be positioned, the name of the equipment to be positioned, the discovery time of the equipment to be positioned and the RSSI (received signal strength indicator) detected by the first wifi probe equipment1RSSI of the signal detected by the second wifi probe device2… …, signal strength RSSI detected by the n-1 th wifi probe devicen-1RSSI (received Signal Strength indicator) detected by nth wifi probe devicen。
Example two
Fig. 8 is a structural diagram of the wifi positioning system based on online learning of the present invention. The system comprises: the system comprises wifi probe equipment, a POE power supply module and a server, and the system executes the positioning method. Wherein wifi equipment uses wifi probe equipment as an example, generally includes following function:
(1) the built-in induction module transmits a high connection frequency SSID to induce the equipment to be positioned to be connected, and the probability of capturing the MAC address of the equipment to be positioned is increased.
(2) And scanning all channels, and capturing the MAC address of the equipment to be positioned without missing packets.
(3) And encrypting and returning information such as the strength of the marked MAC signal, the connection time difference and the like to a position calculation server to perform accurate calculation of the position coordinate of the equipment to be positioned.
And the POE power supply module is used for transmitting the signal data received by the wifi equipment in real time back to the database server while supplying power to the wifi probe equipment.
The server comprises a database server and a positioning database. Database server as a store of MAC of devices to be locatedThe address database is used for rapidly comparing the MAC address of the equipment to be positioned, which is captured by the WiFi probe equipment, transmitting the successfully compared data to the positioning server, updating the connection duration of the equipment marked with the MAC into the fingerprint database according to the information of time, position and the like, and the storage schematic diagram of the data server is shown in the attached figure 9. Fig. 9 is a schematic diagram of the data server storage in fig. 8. The data server stores the format that each row of data represents the serial number ID of the equipment to be positioned, the MAC address of the equipment to be positioned, the name of the equipment to be positioned, the discovery time of the equipment to be positioned and the RSSI (received signal strength indicator) detected by the first wifi probe equipment1RSSI of the signal detected by the second wifi probe device2… …, signal strength RSSI detected by the n-1 th wifi probe devicen-1RSSI (received Signal Strength indicator) detected by nth wifi probe devicen。
And the positioning server runs a positioning algorithm, matches the signals received in real time through calculation with the data of the fingerprint database, calculates the coordinates to be positioned according to the fingerprint coordinates, and a schematic diagram for storing the positioning results is shown in the attached figure 10. Fig. 10 is a schematic diagram of the location server storage in fig. 8. The storage format of the positioning server is that each row of data represents the number ID of the equipment to be positioned, the MAC address of the equipment to be positioned, the name of the equipment to be positioned, the X coordinate of the equipment to be positioned, the Y coordinate of the equipment to be positioned and the report time.
According to the above description, the wifi positioning method and system based on online learning according to the invention can greatly reduce the workload of fingerprint library collection, ensure the reliability of the fingerprint library and improve the wifi positioning accuracy; the labor cost is saved, and the tester can be easily operated and executed, so that the large-scale popularization of the project is facilitated; for example, bluetooth positioning, wireless communication algorithms, etc.
The above embodiments of the present invention are described in detail, and the principle and the implementation of the present invention are explained by applying specific embodiments, and the above description of the embodiments is only used to help understanding the method of the present invention and the core idea thereof; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (13)
1. A wifi positioning method based on online learning is characterized by comprising the following steps:
collecting fingerprint information to generate a fingerprint database;
the fingerprint information comprises fingerprint coordinates, strength indication RSSI of a received signal, a distance d between the fingerprint coordinates and wifi equipment coordinates, and loss parameters and a constant K of the RSSI;
and matching the signal data received by the wifi device from the device to be positioned in real time with the data in the fingerprint database, and calculating the coordinate data of the device to be positioned according to the fingerprint coordinate data.
2. The wifi positioning method based on online learning of claim 1 is characterized in that the distance d between the fingerprint coordinates and wifi device coordinates, and the loss parameter and constant K of RSSI are obtained by linear fitting.
3. The wifi positioning method based on online learning of claim 1, wherein the matching of the signal data received by the wifi device from the device to be positioned in real time with the data in the fingerprint database, and the calculating of the coordinate data of the device to be positioned according to the fingerprint coordinate data further comprises: and filtering the coordinate data of the equipment to be positioned.
4. The wifi positioning method based on online learning of claim 1 is characterized in that the signal received by wifi device in real time is matched with the fingerprint database by adopting probabilistic algorithm, deterministic algorithm or computational similarity algorithm.
5. The wifi positioning method based on online learning of claim 2, wherein the generating fingerprint database includes: and calculating the received signal intensity of the equipment to be positioned according to the distance d between the fingerprint coordinates and the wifi equipment coordinates and a transmission loss model of the wireless signals, wherein the signal intensity forms a group of signal vectors [ AP1, AP2, … … and APn ], and a piece of fingerprint information is formed and stored by combining the position coordinates of the equipment to be positioned.
6. The wifi positioning method based on online learning of claim 3 is characterized in that after filtering the coordinate data of the device to be positioned, the method further comprises: and storing the coordinate data of the equipment to be positioned in the corresponding fingerprint database.
7. The wifi positioning method based on online learning of claim 3 is characterized in that the filtering of the coordinate data of the device to be positioned adopts a moving average filtering method or a Kalman filtering method.
8. The wifi positioning method based on online learning of claim 4 is characterized in that the probabilistic algorithm includes naive Bayes method, kernel function method or maximum likelihood probability method.
9. The wifi positioning method based on online learning of claim 4, wherein the deterministic algorithm includes: and estimating the position coordinates of the equipment to be positioned by adopting a deterministic inference algorithm.
10. The wifi positioning method based on online learning of claim 4, wherein the deterministic algorithm includes: a nearest neighbor method or a K weighted neighbor method or a dynamic K-value weighted algorithm.
11. The wifi positioning method based on online learning of claim 4 is characterized in that the calculation similarity algorithm includes cosine similarity algorithm.
12. The wifi positioning method based on online learning of claim 11, wherein the cosine similarity algorithm includes: and taking the content subjected to similarity comparison as a vector, calculating the rest chord values, and selecting a fingerprint coordinate with the highest similarity to calculate the position coordinate of the equipment to be positioned.
13. The utility model provides a wifi positioning system based on online learning which characterized in that includes: wifi device, POE power module, server, the system performs the positioning method of any of claims 1 to 12.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910162851.9A CN111726743A (en) | 2019-03-04 | 2019-03-04 | Wifi positioning method and system based on online learning |
| PCT/CN2019/112531 WO2020177333A1 (en) | 2019-03-04 | 2019-10-22 | On-line learning-based wi-fi positioning method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910162851.9A CN111726743A (en) | 2019-03-04 | 2019-03-04 | Wifi positioning method and system based on online learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111726743A true CN111726743A (en) | 2020-09-29 |
Family
ID=72337675
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910162851.9A Pending CN111726743A (en) | 2019-03-04 | 2019-03-04 | Wifi positioning method and system based on online learning |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111726743A (en) |
| WO (1) | WO2020177333A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023047619A1 (en) * | 2021-09-21 | 2023-03-30 | 株式会社日立製作所 | Management device, communication control system, and communication control method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104359480A (en) * | 2014-11-04 | 2015-02-18 | 浙江工业大学 | Mixing chamber indoor location method by using inert navigation and Wi-Fi fingerprint |
| CN104703276A (en) * | 2015-03-08 | 2015-06-10 | 西安电子科技大学 | Locating system and method in light-weight light weight chamber based on channel state information ranging |
| CN107484123A (en) * | 2017-07-21 | 2017-12-15 | 中山大学 | A kind of WiFi indoor orientation methods based on integrated HWKNN |
| CN107607118A (en) * | 2017-08-10 | 2018-01-19 | 浙江科技学院 | A kind of vehicle positioning method of parking garage |
| CN109275095A (en) * | 2018-11-09 | 2019-01-25 | 中科数字健康科学研究院（南京）有限公司 | A kind of indoor locating system based on bluetooth, positioning device and localization method |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104038901B (en) * | 2014-05-30 | 2017-04-26 | 中南大学 | Indoor positioning method for reducing fingerprint data acquisition workload |
| KR102363828B1 (en) * | 2014-11-01 | 2022-02-16 | 삼성전자주식회사 | Method and system for generating a signal strength map |
| CN105611502B (en) * | 2015-12-22 | 2018-12-18 | 广西瀚特信息产业股份有限公司 | A kind of indoor locating system and method based on WiFi Mesh network |
| CN106304331A (en) * | 2016-08-19 | 2017-01-04 | 青岛海尔智能技术研发有限公司 | A kind of WiFi fingerprint indoor orientation method |
| CN107087259A (en) * | 2017-04-18 | 2017-08-22 | 国际关系学院 | Region Wi-Fi hotspot position finding technology based on mobile phone |
-
2019
- 2019-03-04 CN CN201910162851.9A patent/CN111726743A/en active Pending
- 2019-10-22 WO PCT/CN2019/112531 patent/WO2020177333A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104359480A (en) * | 2014-11-04 | 2015-02-18 | 浙江工业大学 | Mixing chamber indoor location method by using inert navigation and Wi-Fi fingerprint |
| CN104703276A (en) * | 2015-03-08 | 2015-06-10 | 西安电子科技大学 | Locating system and method in light-weight light weight chamber based on channel state information ranging |
| CN107484123A (en) * | 2017-07-21 | 2017-12-15 | 中山大学 | A kind of WiFi indoor orientation methods based on integrated HWKNN |
| CN107607118A (en) * | 2017-08-10 | 2018-01-19 | 浙江科技学院 | A kind of vehicle positioning method of parking garage |
| CN109275095A (en) * | 2018-11-09 | 2019-01-25 | 中科数字健康科学研究院（南京）有限公司 | A kind of indoor locating system based on bluetooth, positioning device and localization method |
Non-Patent Citations (1)
| Title |
|---|
| 黄有山，候鸣，徐玲，秦宏帅，周佩光，漏鸣杰: "《基于ZigBee的室内定位方法分析和验证》", 《智能物联技术》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023047619A1 (en) * | 2021-09-21 | 2023-03-30 | 株式会社日立製作所 | Management device, communication control system, and communication control method |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020177333A1 (en) | 2020-09-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Marques et al. | Combining similarity functions and majority rules for multi-building, multi-floor, WiFi positioning | |
| CN104883734B (en) | A kind of indoor Passive Location based on geographical fingerprint | |
| TWI510112B (en) | Wireless communication device capable of performing enhanced fingerprint mapping and location identification | |
| Fang et al. | Calibration-free approaches for robust Wi-Fi positioning against device diversity: A performance comparison | |
| Zou et al. | Standardizing location fingerprints across heterogeneous mobile devices for indoor localization | |
| Iglesias et al. | Indoor person localization system through RSSI Bluetooth fingerprinting | |
| Robinson et al. | Received signal strength based location estimation of a wireless LAN client | |
| KR101600190B1 (en) | Indoor positioning apparatus considering environmental parameters and method thereof | |
| Viel et al. | Why is fingerprint-based indoor localization still so hard? | |
| KR20160075735A (en) | Method and apparatus for cross device automatic calibration | |
| US10200965B2 (en) | Analysis and monitoring of a positioning infrastructure | |
| Li et al. | Location estimation in large indoor multi-floor buildings using hybrid networks | |
| Shih et al. | Intelligent radio map management for future WLAN indoor location fingerprinting | |
| Tiku et al. | PortLoc: a portable data-driven indoor localization framework for smartphones | |
| Yang et al. | Multi-floor indoor localization based on RBF network with initialization, calibration, and update | |
| CN111654808B (en) | Method and system for updating fingerprint database and wifi positioning method and system | |
| CN111654843A (en) | Method and system for automatically updating fingerprint database and wifi positioning method and system | |
| Wei et al. | Handling device heterogeneity in Wi-Fi based indoor positioning systems | |
| CN111726743A (en) | Wifi positioning method and system based on online learning | |
| CN105866729B (en) | A kind of indoor orientation method and device based on user behavior characteristics | |
| Othman et al. | Effectiveness of online RF fingerprinting for indoor localization | |
| Chen et al. | Automatic radio map adaptation for wifi fingerprint positioning systems | |
| CN116033345A (en) | Indoor abnormal signal high-precision positioning method, system and device | |
| Han et al. | A weighted algorithm based on physical distance and cosine similarity for Indoor localization | |
| Yonghao et al. | A calibration-free indoor localization system using pseudo-distances in WLAN environments |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200929 |
|
| RJ01 | Rejection of invention patent application after publication |