CN111654808A - Method and system for updating fingerprint database and wifi positioning method and system - Google Patents
Method and system for updating fingerprint database and wifi positioning method and system Download PDFInfo
- Publication number
- CN111654808A CN111654808A CN201910162247.6A CN201910162247A CN111654808A CN 111654808 A CN111654808 A CN 111654808A CN 201910162247 A CN201910162247 A CN 201910162247A CN 111654808 A CN111654808 A CN 111654808A
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- updating
- fingerprint database
- online
- signal intensity
- 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.)
- Granted
Links
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)
- Collating Specific Patterns (AREA)
Abstract
The invention provides a method and a system for updating a fingerprint database and a wifi positioning method and a wifi positioning system, wherein the method for updating the fingerprint database comprises the following steps: recording a positioning position corresponding to the original signal intensity; recording the average signal intensity value detected by each probe at the positioning position and recording the detection times; selecting the average signal intensity value of the probe with the front detection times from an online fingerprint library to form the online fingerprint signal intensity at the position; and selecting an adjusting coefficient, and combining the signal intensity of the position of the online fingerprint library with the signal intensity of the position in the offline fingerprint library to obtain the new signal intensity of the position. The workload of updating the fingerprint database can be greatly reduced, the reliability of the fingerprint database can be ensured, and the WiFi positioning precision is improved; the labor cost is saved, the tester can be easily operated and executed, and 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 optimizing a fingerprint database, in particular to a method and a system for updating the fingerprint database and a wifi positioning method.
[ background of the invention ]
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 triangular 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) based method. 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, AP 2.., 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. But in practice often much data is not useful, and a "good" fingerprint should not cause errors in positioning, or at least "probably not". 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 in actual position, and have a small euclidean distance in signal space, and such fingerprint acquisition may not improve performance, but may cause extra calculation amount in positioning. Placing such fingerprints in a fingerprint library may even reduce the positioning accuracy. In the prior art, the offline databases of the online fingerprint database are often separated, the data function of the offline database is not fully utilized, and the automatic updating precision of the fingerprint database is low; meanwhile, the reliability of the fingerprint library is low, and the wifi positioning precision is low; if the automatic updating of the fingerprint database is realized, great labor cost is required.
[ summary of the invention ]
The technical problem to be solved by the invention is to provide a method and a system for updating a fingerprint database and a wifi positioning method, wherein an online fingerprint database can be generated by a statistical method, and the online fingerprint database and the offline fingerprint database are combined by a random approximation method to realize automatic updating of fingerprints; the workload of updating the fingerprint database can be greatly reduced, the reliability of the fingerprint database can be ensured, and the WiFi positioning precision is improved; the labor cost is saved, the tester can be easily operated and executed, and the large-scale popularization of the engineering is facilitated.
To solve the foregoing technical problem, in one aspect, an embodiment of the present invention provides a method for updating a fingerprint database, including: recording a positioning position corresponding to the original signal intensity; recording the average signal intensity value detected by each probe at the positioning position and recording the detection times; selecting the average signal intensity value of the probe with the front detection times from an online fingerprint library to form the online fingerprint signal intensity at the position; and selecting an adjusting coefficient, and combining the signal intensity of the position in the online fingerprint library with the signal intensity of the position in the offline fingerprint library to obtain the new signal intensity of the position.
Preferably, the adjustment coefficients include an online fingerprint library adjustment coefficient α and an offline fingerprint library adjustment coefficient β.
Preferably, the recording of the average signal intensity value detected by each probe at the location of the position and the recording of the number of detections comprises: and filtering the coordinate data of the equipment to be positioned.
Preferably, the online fingerprint database is generated by signals received by wifi equipment in real time.
Preferably, the value range of the adjustment coefficient alpha of the online fingerprint database is 0-1.
Preferably, the value range of the off-line fingerprint database adjusting coefficient beta is 0-1.
Preferably, the sum of the online fingerprint library adjustment coefficient α and the offline fingerprint library adjustment coefficient β is 1, that is, α + β ═ 1.
Preferably, the off-line fingerprint database is generated by manual measurement or signal transmission loss model generation or by updating a fingerprint database.
Preferably, before recording the location corresponding to the original signal strength, the method includes: the wifi device collects fingerprint information, the fingerprint information comprises fingerprint coordinates and RSSI, and the fingerprint coordinates are generated with the distance d between the wifi device coordinates and the loss parameter and constant K of the RSSI.
Preferably, the method further comprises the steps of matching signal data received by the wifi device in real time with the fingerprint database, and calculating coordinate data of the device to be positioned according to the fingerprint coordinate data.
Preferably, the distance d between the fingerprint coordinates and the wifi device coordinates and the loss parameter and constant K of RSSI are obtained by adopting a linear fitting mode.
Preferably, the signal data received by the wifi device in real time is matched with the fingerprint database, and a probabilistic algorithm or a deterministic algorithm or a computational similarity algorithm is adopted for matching.
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 or 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.
On the other hand, an embodiment of the present invention provides a system for updating a fingerprint database, including a wifi device, a POE power module, and a server, where the system executes the method for updating a fingerprint database.
In another aspect, an embodiment of the present invention provides a wifi positioning method, where the wifi positioning method executes the above method for updating a fingerprint database.
On the other hand, an embodiment of the present invention provides a wifi positioning system, where the system includes a wifi device, a POE power supply module, and a server, and the system executes the method for updating a fingerprint database.
Compared with the prior art, the technical scheme has the following advantages: an online fingerprint database is generated by a statistical method, and the online fingerprint database and the offline fingerprint database are combined by a random approximation method to realize automatic updating of fingerprints; the workload of updating the fingerprint database can be greatly reduced, the reliability of the fingerprint database can be ensured, and the WiFi positioning precision is improved; the labor cost is saved, the tester can be easily operated and executed, and 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 for the method of updating a fingerprint database of the present invention;
FIG. 5 is a flow chart of a method of updating a fingerprint database of the present invention;
FIG. 6 is a flowchart of a wifi positioning method based on the method of updating fingerprint database of the present invention;
FIG. 7 is another flowchart of the wifi positioning method based on the fingerprint database updating method of the present invention;
FIG. 8 is a diagram illustrating an online fingerprint database storage structure in the method for updating a fingerprint database according to the present invention;
FIG. 9 is a diagram illustrating an off-line fingerprint database storage structure in the method for updating a fingerprint database according to the present invention;
FIG. 10 is a block diagram of an update fingerprint database system of the present invention;
FIG. 11 is a schematic diagram of the data server storage of FIG. 10;
fig. 12 is a schematic diagram of the location server storage in fig. 10.
[ 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 the proximity of the wireless wifi access point based on wifi detection technology. The method comprises the steps that a smart phone or a WiFi terminal (a notebook, a tablet computer and the like) with a Wifi function is started, a user does not need to actively access WiFi, a probe can identify the user, whether IOS or android system can detect the user, and the MAC address of equipment 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 amount Of fingerprints in the implementation process, although the labor cost is low, the positioning accuracy is poor, and the algorithm complexity is high, so the requirement on hardware equipment is high.
Example one
FIG. 4 is a schematic diagram of location fingerprint location of the method of updating a fingerprint database of the present invention. The location fingerprinting positioning technology is non-ranging positioning based on Received Signal Strength Indicator (RSSI), and deduces a position to be positioned by using different RSSI characteristics through different received signal strength (RSSI values) characteristics at different positions. Fig. 4 shows that the method comprises two stages of off-line training and on-line positioning.
Off-line training: the method aims to establish a position fingerprint database, firstly, a plane distribution diagram 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, the coordinates of the reference points are obtained through measurement in advance, signals of all detected APs around the reference points are collected on each reference point, and information of each AP, received signal strength (RSSI value) and the positions of the reference points are stored into the position fingerprint database as a 'fingerprint'.
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 in the 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 a method for updating a fingerprint database according to the present invention. As shown in fig. 5, a method for updating a fingerprint database includes the steps of: recording a positioning position corresponding to the original signal intensity; recording the average signal intensity value detected by each probe at the positioning position and recording the detection times; selecting the average signal intensity value of the probe with the front detection times from an online fingerprint library to form the online fingerprint signal intensity at the position; and selecting an adjusting coefficient, and combining the signal intensity of the position in the online fingerprint library with the signal intensity of the position in the offline fingerprint library to obtain the new signal intensity of the position. Recording a positioning position corresponding to the original signal intensity; the average signal intensity value detected by each probe at the location is recorded, and the number of detections is recorded to essentially generate an online fingerprint library. Selecting the average signal intensity value of the probe with the front detection times from an online fingerprint library to form the online fingerprint signal intensity at the position; and selecting an adjustment coefficient, and combining the signal intensity of the position of the online fingerprint library with the signal intensity of the position in the offline fingerprint library to obtain new signal intensity of the position, which is substantially an updated fingerprint library.
FIG. 6 is a flowchart of a wifi positioning method based on the method of updating fingerprint database of the present invention. As shown in fig. 6, a wifi positioning method based on the method of updating fingerprint database includes the following steps: the method comprises the steps that a wifi device collects fingerprint information, the fingerprint information comprises fingerprint coordinates and RSSI, and the distance d between the fingerprint coordinates and the wifi device coordinates and loss parameters and a constant K of the RSSI are generated; generating a fingerprint database; matching signal data received by the wifi device in real time with the fingerprint database, and calculating coordinate data of the device to be positioned according to the fingerprint coordinate data; updating the fingerprint matching times; and updating the fingerprint database.
The automatic fingerprint updating method based on random approximation comprises two processes of generating an online fingerprint library through a statistical method and updating the fingerprint library through the random approximation method. Assuming that the electronic device to be tested is within the probe coverage, at a certain location such as pos1, the signal strength rssi of the electronic device is monitored by surrounding nearby probes, and the probe server collects the signal strength of the probes monitoring the electronic device to constitute the electronic device at the locationThe signal intensity of (c) is recorded in the following manner: {' AP1′：rssi1，′AP2′：rssi2，′AP3′：rssi3Which we refer to herein as the raw signal strength for that location. The raw signal strength can be used for estimating the positioned position through an online positioning algorithm.
Since the wireless signal is usually affected by path loss, shadow fading, etc. during transmission, the variation of the received signal power with distance can be given by a signal transmission loss model. The transmission loss model typically employs a simplified model as follows: pr(d) K-10lg (d) (dbm), where d represents the distance between the receiver and the transmitter and represents the loss factor of free space, and K is a constant that can be set as desired. From the above, the average RSSI attenuation at different distances from the fixed signal transmission source is proportional to the logarithm of the distance, and based on this model, the relationship between the distance and the received signal can be found by on-line learning.
The process of automatically updating the fingerprint method by random approximation when implemented is as follows:
(1) generating an online fingerprint repository
a. And recording the intensity of each original signal and the corresponding positioning position.
b. The average of the signal intensity detected by each wifi probe at that location was recorded, and the number of detections was recorded.
The fingerprint database is composed of two parts: an online fingerprint database and an offline fingerprint database. The off-line fingerprint database is generated by manual measurement or a signal transmission loss model or an updated fingerprint database, and the on-line fingerprint database is generated by signals received by the wifi device in real time. The online fingerprint database refers to the current dynamic detection process. Offline fingerprint database we can consider it a database consisting of raw signal strength vectors detected by wifi devices at the original location.
Fig. 8 is a schematic diagram of an online fingerprint database storage structure in the method for updating a fingerprint database according to the present invention. As shown in fig. 8, each line of data includes a storage ID number, a current location identifier, an X coordinate of the current location identifier, a Y coordinate of the current location identifier, a wireless probe AP device number, an average signal strength value of the current wireless probe AP device number collected at the current location identifier, and a current matching number. By the method, the position can be detected by the probes, and the signal intensity of the probes gradually becomes stable over time, so that the corresponding generated fingerprint is more reliable.
Fig. 9 is a schematic diagram of an offline fingerprint database storage structure in the method for updating a fingerprint database according to the present invention. As shown in fig. 9, 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, and the signal vectors detected by different probes.
(2) Updating a fingerprint repository
The fingerprint database is updated periodically, and can be updated once a day, a week or a month, and the updating period is related to the environment. The updating of the fingerprint database adopts a random approximate method to combine the online fingerprint database with the offline fingerprint database, thereby achieving the updating effect.
a. Selecting the average signal intensity value of the probe with the former times from the online fingerprint library to form the online fingerprint signal intensity at the position, and recording the online fingerprint signal intensity as rssionline. Taking fig. 8 as an example: the matching times of the AP2, AP3, AP1 and AP4 at the position 2 are advanced, the average signal intensity values detected by the four probes are taken as the online fingerprint at the position 2, namely the signal intensity of the fingerprint 2 is: rsionline＝{AP1：-70，AP2：-65，AP3：-70，AP4：-72}。
b. Selecting adjustment coefficients α and β by adopting a random approximation method, and enabling the signal intensity rssi of the online fingerprint library at the position to be larger than the signal intensity rssionlineAnd the signal strength rssi at that location in the offline fingerprint libraryofflineCombining to obtain new signal strength at the position, and recording as rssinew＝α×rssionline+β×rssiofflinThe α and β parameters are in the range of O-1, the sum of α and β is set to 1 for higher online matching accuracy, and taking fig. 9 as an example, at the position 2, the original signal intensity of the fingerprint 2, i.e. the offline fingerprint signal intensity is rssioffline＝{AP2：-72，AP3：-65，AP4：-68}。
c. Updating the signal strength of the position in the off-line fingerprint library to a new signal strength value rsinewAssuming α -0.3 and β -0.7, rssinew＝{AP1:-21,AP2:-69.9,AP3:-44.1, AP4:-69.2}：
rssinew＝α×rssionline+β×rssioffline
＝0.3×rssionline+0.7×rssioffline
＝0.3×{AP1：-70，AP2：-65，AP3：-70，AP4：-72}
+0.7×{AP2：-72，AP3：-65，AP4：-68}
＝{AP1：-21，AP2：-69.9，AP3：-44.1，AP4：-69.2}
d. After the above steps are adopted to complete the fingerprint updating of all the positions, the signal strength vector { AP 1: -21, AP 2: 69.9, AP 3: 44.1, AP 4: 69.2 instead of the signal vector at position 2 AP 1: -70, AP 2: -65, AP 3: -70, AP 4: -72}.
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 using a Wifi probe as an example, and the adaptive Wifi positioning scheme is as follows:
(1) initialization parameters and K
From Pr(d) As can be seen from the formula K-10lg (d) (dbm), if the loss factor and the constant K are known in a propagation environment, the RSSI at different distances from a 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, a little fingerprint information (comprising coordinates and RSSI) is collected, and parameters K of the distance and the RSSI are generated through a linear fitting mode.
(2) Generating a fingerprint database
Collecting fingerprint coordinates (only including coordinate position and not including RSSI) in the coverage area of the probe, calculating the distance d between all the fingerprint coordinates and the WiFi probe coordinates, and modeling the transmission loss according to wireless signals Pr(d) K-10lg (d) (dbm), calculating the signal strength of different WiFi probes received 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.
It should be noted that, in combination with the attenuation rule 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 weak, the signal of the corresponding probe cannot be received at the fingerprint coordinate position, and the signal intensity of the probe is not stored. Distance threshold d0The specific selection is related to the environment and the coverage range of the probe.
(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 coordinate to be positioned is calculated according to the fingerprint coordinate.
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 observation values (represented by a random variable x) collected from APs at each reference point. And (3) assuming an RSSI vector (represented by a random variable y) measured at the position to be positioned, and calculating the conditional probability or posterior probability of the RSSI of the position 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 position of the terminal to be positioned, 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) Updating fingerprint matching times
And when the current position coordinate is positioned in the signal received by the wifi device in real time, adding one to the corresponding detection times, and updating the current fingerprint matching times.
(5) Periodically updating fingerprint database
The method for updating the fingerprint database periodically can adopt the random approximate automatic updating fingerprint database method mentioned above. And will not be described in detail herein.
(6) Filtering
And (4) filtering the coordinate data of the equipment to be positioned in the step (3), wherein the aim is to predict the dynamic track of each user. Common filtering methods include moving average filtering, kalman filtering, and the like.
(7) And outputting a positioning result.
Fig. 7 is another flowchart of the wifi positioning method based on the fingerprint database updating method of the present invention. It differs from fig. 6 in that filtering is added to the coordinate data of the device to be located, for the purpose of predicting the dynamic trajectory of each user. After the coordinate data of the equipment to be positioned is filtered, the position coordinates of the equipment to be positioned are output, so that the working personnel can conveniently check and follow the equipment to be positioned.
Example two
Fig. 10 is a diagram of a structure of an update fingerprint database system according to 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.
Correspondingly, an embodiment also discloses a wifi positioning system, the system comprises wifi equipment, a POE power supply module and a server, and the system executes the method for updating the fingerprint database.
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 information such as marked MAC signal strength, connection time difference and the like is encrypted and returned to the position calculation server to perform accurate calculation of the position coordinates 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. The database server is used as a database for storing the MAC address of the equipment to be positioned, which is captured by the WiFi probe equipment, is quickly compared, the successfully compared data is transmitted to the positioning server, information such as connection time, connection time and position of the equipment marked with the MAC is updated into the fingerprint database, and the storage and display diagram of the database server is shown in the attached drawing 11. Fig. 11 is a schematic diagram of the data server in fig. 10. 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-1Signal strength RSSI detected by nth wifi probe devicen。
The positioning server runs a positioning algorithm, matches signals received in real time through calculation with data of a fingerprint database, calculates coordinates to be positioned according to the fingerprint coordinates, and a schematic diagram for storing the positioning results is shown in figure 12. Fig. 12 is a schematic diagram of the location server storage in fig. 10. 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 method and the system for updating the fingerprint database, and the wifi positioning method and the wifi positioning system according to the present invention generate the online fingerprint database by a statistical method, combine the online fingerprint database with the offline fingerprint database, and combine the online fingerprint database with the offline fingerprint database by using a random approximation method, so as to realize automatic updating of the fingerprint; the workload of updating the fingerprint database can be greatly reduced, the reliability of the fingerprint database can be ensured, and the WiFi positioning precision is improved; the labor cost is saved, the tester can be easily operated and executed, and the large-scale popularization of the engineering is facilitated.
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 the persons 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 present specification should not be construed as limiting the present invention.
Claims (18)
1. A method of updating a fingerprint database, comprising:
recording the positioning position corresponding to the original message bow strength;
recording the average signal intensity value detected by each probe at the positioning position and recording the detection times;
selecting the average signal intensity value of the probe with the front detection times from an online fingerprint library to form the online fingerprint information bow intensity at the position;
and selecting an adjusting coefficient, and combining the signal intensity of the position of the online fingerprint library with the signal intensity of the position in the offline fingerprint library to obtain the new signal intensity of the position.
2. The method of updating a fingerprint database of claim 1, wherein the adjustment coefficients comprise an online fingerprint library adjustment coefficient α and an offline fingerprint library adjustment coefficient β.
3. The method of updating a fingerprint database of claim 1, wherein said recording the average signal strength value detected by each probe at said localized position and recording the number of detections comprises: and filtering the coordinate data of the equipment to be positioned.
4. The method of updating a fingerprint database of claim 1, wherein the online fingerprint database is generated by a message bow received by a wifi device in real time.
5. The method for updating the fingerprint database according to claim 2, wherein the value of the adjustment coefficient α of the online fingerprint database is in a range of 0 to 1.
6. The method for updating a fingerprint database according to claim 2, wherein the off-line fingerprint database adjustment coefficient β is in a range of 0-1.
7. The method for updating a fingerprint database according to claim 2, wherein the sum of the online fingerprint library adjustment coefficient α and the offline fingerprint library adjustment coefficient β is 1, i.e. α + β ═ 1.
8. The method of updating a fingerprint database of claim 3, wherein the offline fingerprint database is generated by manual measurement or signal transmission loss model generation or updating a fingerprint database.
9. The method for updating fingerprint database according to claim 1, comprising, before recording the location corresponding to the original signal strength: the wifi device collects fingerprint information, the fingerprint information comprises fingerprint coordinates and RSSI, and the fingerprint coordinates are generated with the distance d between the wifi device coordinates and the loss parameter and constant K of the RSSI.
10. The method of updating a fingerprint database of claim 9, further comprising: and matching the message bow data received by the wifi equipment in real time with the fingerprint database, and calculating the coordinate data of the equipment to be positioned according to the fingerprint coordinate data.
11. The method for updating the fingerprint database according to claim 9, wherein the distance d between the fingerprint coordinates and the wifi device coordinates and the loss parameter and constant K of RSSI are obtained by a linear simulation method.
12. The method for updating the fingerprint database according to claim 10, wherein the message bow data received by the wifi device in real time is matched with the fingerprint database by adopting a probabilistic algorithm or a deterministic algorithm or a computational similarity algorithm.
13. The method of updating a fingerprint database of claim 12 wherein said probabilistic algorithm comprises a naive bayes method, a kernel function method, or a maximum likelihood probability method.
14. The method of updating a fingerprint database of claim 12, wherein said deterministic algorithm comprises: and estimating the position coordinates of the equipment to be positioned by adopting a deterministic inference algorithm or a nearest neighbor method or a K weighted neighbor method or a dynamic K value weighted algorithm.
15. The method of updating a fingerprint database of claim 12 wherein said computational similarity algorithm comprises a cosine similarity algorithm.
16. A system for updating a fingerprint database, comprising a wifi device, a POE power module, and a server, wherein the system performs the method for updating a fingerprint database according to any one of claims 1 to 15.
17. A wifi positioning method, characterized in that it performs the method of updating a fingerprint database according to any of claims 1 to 15.
18. A wifi positioning system, characterized by comprising wifi device, POE power module, server, the system performing the method of updating fingerprint database as claimed in any one of claims 1 to 15.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910162247.6A CN111654808B (en) | 2019-03-04 | 2019-03-04 | Method and system for updating fingerprint database and wifi positioning method and system |
| PCT/CN2019/112535 WO2020177334A1 (en) | 2019-03-04 | 2019-10-22 | Method and system for updating fingerprint database, storage medium and processor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910162247.6A CN111654808B (en) | 2019-03-04 | 2019-03-04 | Method and system for updating fingerprint database and wifi positioning method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111654808A true CN111654808A (en) | 2020-09-11 |
| CN111654808B CN111654808B (en) | 2022-11-29 |
Family
ID=72349126
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910162247.6A Active CN111654808B (en) | 2019-03-04 | 2019-03-04 | Method and system for updating fingerprint database and wifi positioning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111654808B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112415472A (en) * | 2020-11-20 | 2021-02-26 | Oppo（重庆）智能科技有限公司 | Indoor positioning method and device, electronic equipment and storage medium |
| CN113347562A (en) * | 2021-05-31 | 2021-09-03 | 广东技术师范大学 | Automatic verification method and equipment for indoor position fingerprint positioning accuracy |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105120479A (en) * | 2015-07-22 | 2015-12-02 | 上海交通大学 | Signal strength difference correction method of Wi-Fi signals between terminals |
-
2019
- 2019-03-04 CN CN201910162247.6A patent/CN111654808B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105120479A (en) * | 2015-07-22 | 2015-12-02 | 上海交通大学 | Signal strength difference correction method of Wi-Fi signals between terminals |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112415472A (en) * | 2020-11-20 | 2021-02-26 | Oppo（重庆）智能科技有限公司 | Indoor positioning method and device, electronic equipment and storage medium |
| CN113347562A (en) * | 2021-05-31 | 2021-09-03 | 广东技术师范大学 | Automatic verification method and equipment for indoor position fingerprint positioning accuracy |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111654808B (en) | 2022-11-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106851573B (en) | Log path loss model-based joint weighting K nearest neighbor indoor positioning method | |
| Han et al. | Cosine similarity based fingerprinting algorithm in WLAN indoor positioning against device diversity | |
| Diaz et al. | Bluepass: An indoor bluetooth-based localization system for mobile applications | |
| US9369986B2 (en) | Wireless communication network for estimating the accuracy of fingerprinting positioning algorithms | |
| TWI461082B (en) | System and method for effectively populating a mesh network model | |
| Zheng et al. | A study of localization accuracy using multiple frequencies and powers | |
| Zhang et al. | Fingerprint-based localization using commercial LTE signals: A field-trial study | |
| Shih et al. | Intelligent radio map management for future WLAN indoor location fingerprinting | |
| Nikitin et al. | Indoor localization accuracy estimation from fingerprint data | |
| CN111654808B (en) | Method and system for updating fingerprint database and wifi positioning method and system | |
| Dashti et al. | Rssi localization with gaussian processes and tracking | |
| Chiou et al. | Design of an adaptive positioning system based on WiFi radio signals | |
| Pandey et al. | SELE: RSS-based Siamese embedding location estimator for a dynamic IoT environment | |
| CN110493731B (en) | Movement track obtaining method and device, storage medium and equipment | |
| Yang et al. | Multi-floor indoor localization based on RBF network with initialization, calibration, and update | |
| Schüssel et al. | Coverage gaps in fingerprinting based indoor positioning: The use of hybrid gaussian processes | |
| Wei et al. | Handling device heterogeneity in Wi-Fi based indoor positioning systems | |
| JP2015040749A (en) | Position estimation device and position estimation program | |
| Santos et al. | Recursive estimation of dynamic RSS fields based on crowdsourcing and Gaussian processes | |
| Bisio et al. | A smart 2 Gaussian process approach for indoor localization with RSSI fingerprints | |
| CN111654843A (en) | Method and system for automatically updating fingerprint database and wifi positioning method and system | |
| CN111726743A (en) | Wifi positioning method and system based on online learning | |
| Xu et al. | Variance-based fingerprint distance adjustment algorithm for indoor localization | |
| Zheng et al. | RSS-based indoor passive localization using clustering and filtering in a LTE network | |
| Han et al. | A weighted algorithm based on physical distance and cosine similarity for Indoor localization |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |