CN111182452A - Classified self-learning-based WIFI positioning method and system - Google Patents
Classified self-learning-based WIFI positioning method and system Download PDFInfo
- Publication number
- CN111182452A CN111182452A CN202010058070.8A CN202010058070A CN111182452A CN 111182452 A CN111182452 A CN 111182452A CN 202010058070 A CN202010058070 A CN 202010058070A CN 111182452 A CN111182452 A CN 111182452A
- Authority
- CN
- China
- Prior art keywords
- positioning
- algorithm
- user terminal
- learning
- wireless
- 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
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
- H04W4/023—Services making use of location information using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
-
- 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
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
Abstract
The invention discloses a classification self-learning-based WIFI positioning method and system, wherein the learning stage of wireless positioning is S1: z1, detecting signal RSSI information on a WIFI communication interface by using N wireless positioning devices, and sending the signal RSSI information to the positioning engine platform, wherein the positions of the wireless positioning devices are known, and the positioning engine platform can establish a fingerprint information base for the position of each wireless positioning device by synthesizing the wireless RSSI information reported by the N wireless positioning devices. According to the WIFI positioning method and system based on classification self-learning, automation of the whole positioning process is achieved, the whole process from learning to positioning can be completed without manual intervention, the complexity of deployment, implementation and operation of the positioning system is greatly reduced, rapid popularization and deployment of the system are facilitated, the deployment and use cost of the positioning system can be greatly saved, and manual intervention is still not needed when the position of the positioning environment or wireless positioning equipment is changed.
Description
Technical Field
The invention relates to the technical field of WIFI positioning, in particular to a classification self-learning-based WIFI positioning method and system.
Background
With the rapid development of the mobile internet, various Location Based Services (LBS) applications are becoming more and more popular. For outdoor positioning, the Global Positioning System (GPS) currently in common use is already well established; however, in the indoor environment, since the satellite signal is easily blocked by a building, the GPS system cannot function in indoor positioning. The current indoor positioning technology mainly comprises WIFI positioning, RFID positioning, infrared positioning, ultrasonic positioning, Bluetooth positioning, LED visible light positioning, geomagnetic positioning, visual positioning and the like. Due to the wide deployment of WIFI, WIFI positioning has become a mainstream technology of indoor positioning, is widely researched and realizes a large amount of deployment.
Currently, WIFI positioning methods can be roughly divided into two categories: triangulation location methods and location fingerprint location methods. Wherein the triangulation uses a signal attenuation model to estimate the distance between the user equipment and a plurality of positioning devices, and then determines the position of the user equipment by using the principle of triangulation geometry. The position fingerprint method is that signal strength (RSSI) sets of WIFI are collected at a plurality of known positions in a positioning area in advance to serve as fingerprint information of the positions; when the positioning is realized, the fingerprint of the position of the user equipment is matched with the fingerprint information base which is acquired in advance, and the position of the user equipment is calculated from the position of the closest fingerprint.
Due to the fact that the WIFI signal strength is greatly influenced by environmental factors, the error of the triangulation method is large. The position fingerprint method adopts a classification method based on machine learning, can better cope with the influence of WIFI signal fluctuation, benefits from the evolution of a machine learning algorithm, and is superior to a triangulation method in positioning accuracy and development prospect.
In the existing position fingerprint positioning method, a positioning area needs to be divided into fingerprint sampling points with the distance of 1-2 meters, and a WIFI device is used at each sampling point to acquire a Received Signal Strength (RSSI) value between the position and a plurality of positioning devices. This process is time consuming and labor intensive, and also requires repeated manual execution when the environment of the localized area changes. Therefore, the fingerprint sampling points with finer granularity need to be adopted, which is related to the commonly used fingerprint matching algorithm at present. The K-nearest neighbor method (KNN) widely used at present selects K reference points of a fingerprint, i.e., the closest signal space distance, and uses the average value of the K reference point positions as an output positioning position. The algorithm therefore requires a sufficient number of sample points to achieve satisfactory positioning accuracy.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a classified self-learning-based WIFI positioning method and system, and solves the problems that in the existing position fingerprint positioning method, a positioning area needs to be divided into fingerprint sampling points with the distance of 1-2 meters, and the WIFI equipment is used at each adopted point to obtain the received signal intensity values between the position and a plurality of positioning equipment, so that time and labor are wasted, and the process needs to be repeatedly executed manually after the environment of the positioning area changes.
In order to achieve the purpose, the invention is realized by the following technical scheme: a classification self-learning-based WIFI positioning method specifically comprises the following steps:
s1, learning stage of wireless positioning:
z1, detecting signal RSSI information on a WIFI communication interface by using N wireless positioning devices, and sending the signal RSSI information to the positioning engine platform, wherein the positions of the wireless positioning devices are known, and the positioning engine platform can establish a fingerprint information base for the position of each wireless positioning device by integrating the wireless RSSI information reported by the N wireless positioning devices;
z2, when accumulating enough fingerprint data for each position, the positioning engine platform runs the supervised machine learning algorithm based on classification, wherein the fingerprint RSSI set is used as training characteristic, the known wireless positioning device position is used as category, the positioning engine platform simultaneously executes a plurality of classified learning algorithms, the precision and recall rate of each algorithm are obtained according to the confusion matrix obtained by each algorithm aiming at the training data set, different weights are given to each algorithm on the basis, when the learning precision of all the positions is confirmed to reach a certain standard through cross validation, the general standard is that the accuracy is more than 95%, the positioning engine platform saves all the learning models and the weight parameters of each learning algorithm, and stops the learning process.
S2, positioning stage of wireless positioning:
q1, detecting signal RSSI information on WIFI communication interfaces of peripheral user terminals by N wireless positioning devices and sending the signal RSSI information to a positioning engine platform, wherein the positioning engine platform establishes a dynamic fingerprint information base for each user terminal;
q2, for each user terminal, the positioning engine platform continuously generates a location fingerprint for the user terminal in the manner described above and executes a location positioning algorithm with this as input.
S3, executing the position positioning algorithm:
a1, when receiving RSSI information of each user terminal collected by the wireless positioning equipment, starting the execution of the algorithm;
a2, the positioning algorithm establishes an RSSI fingerprint information database for the user terminal corresponding to the received current information;
a3, the positioning algorithm judges whether the RSSI quantity in the user terminal fingerprint database is more than or equal to a certain set value M, M is not less than 3, if yes, a5 is executed, otherwise, a4 is executed;
a4, saving the RSSI value of the current user terminal to the fingerprint database of the terminal, and waiting to receive more RSSI information aiming at the user terminal;
a5 and a6, the positioning algorithm inputs the position fingerprint of the user terminal into each trained machine learning algorithm model, and obtains the approximation degree of the position of the user terminal and each wireless positioning device position according to the weight of each algorithm, and the approximation degree is expressed by percentage or rate;
a7, on the basis of the probability from the known user terminal position to each known position, converting the solution of the user terminal position into an optimization algorithm problem, and designing a cost function for the optimization algorithm problem;
a8, the positioning algorithm executes a differential evolution optimization algorithm to obtain the predicted coordinate value of the user terminal position.
Preferably, in step z1, in order to achieve accurate positioning, a value of N is not less than 3, where the location fingerprint refers to an RSSI set of a WIFI communication interface of a wireless positioning device located at the location, which is detected by each wireless positioning device, and a common supervised machine learning algorithm based on classification in step z2 includes: a K neighbor algorithm, a decision tree algorithm, a naive Bayes algorithm, a support vector machine algorithm, an adaBoost algorithm, etc.
Preferably, in step q1, the fingerprint information of the user terminal location is a set of RSSI collected by each wireless positioning device at the same time, and considering that the detection of the same user terminal signal by multiple wireless positioning devices is prior in time, a small sliding time window, for example, 10 seconds, is set for each user terminal in the fingerprint collection interval, and the set of RSSI falling in the time window is used as the location fingerprint of the user terminal.
Preferably, the cost function principle of the optimization algorithm in step a7 is to calculate the euclidean distances from the location of the user terminal to each known location, and then obtain the minimum distance equation according with the proportional relationship according to the proportional relationship between the distances.
The invention also discloses a classified self-learning-based WIFI positioning system, which comprises a positioning engine platform, wireless positioning equipment and a user terminal, wherein the positioning engine platform comprises a data receiving, processing and storing module, a supervised classified machine learning module, a differential evolution intelligent optimization algorithm module, a positioning coordinate output module and a positioning result output interface, the output end of the data receiving, processing and storing module is connected with the input end of the supervised classified machine learning module, the output end of the supervised classified machine learning module is connected with the input end of the differential evolution intelligent optimization algorithm module, the output end of the differential evolution intelligent optimization algorithm module is connected with the input end of the positioning coordinate output module, and the output end of the positioning coordinate output module is connected with the input end of the positioning result output interface.
Preferably, the wireless positioning device comprises a first WIFI communication interface module and a WIFI interception interface module, the first WIFI communication interface module and the WIFI interception interface module are in bidirectional connection, and the first WIFI communication interface module is in bidirectional connection with the data receiving, processing and storing module.
Preferably, the user terminal comprises a second WIFI communication interface module, and the second WIFI communication interface module is in bidirectional connection with the WIFI interception interface module.
Advantageous effects
The invention provides a classification self-learning-based WIFI positioning method and system. Compared with the prior art, the method has the following beneficial effects:
(1) according to the WIFI positioning method and system based on classification self-learning, automation is achieved in the whole positioning process, the whole process from learning to positioning can be completed under the condition that manual intervention is not needed, the complexity of positioning system deployment, implementation and operation is greatly reduced, rapid popularization and deployment of the system are facilitated, the deployment and use cost of the positioning system can be greatly saved, when the position of a positioning environment or a wireless positioning device is changed, the above processes can be automatically executed again, and manual intervention is still not needed.
(2) According to the classification self-learning-based WIFI positioning method and system, the integrated learning and intelligent optimization algorithm which summarizes various learning algorithms is adopted, so that coarse-grained discrete classification position positioning is converted into continuous position coordinate positioning in a positioning space, and accurate positioning of the user terminal is realized.
(3) According to the classification self-learning-based WIFI positioning method and system, in the positioning training stage, the automatic establishment of the sampling point is realized by using the mutual self-learning capability of the wireless positioning equipment, and the time-consuming and labor-consuming manual sampling process is avoided.
Drawings
FIG. 1 is a schematic block diagram of the architecture of the system of the present invention;
FIG. 2 is a schematic flow chart of the learning phase of the present invention;
FIG. 3 is a schematic flow chart of the positioning stage of the present invention;
FIG. 4 is a flow chart illustrating the execution phase of the positioning algorithm of the present invention.
In the figure: 1. positioning an engine platform; 2. a wireless positioning device; 3. a user terminal; 11. a data receiving, processing and storing module; 12. a supervised classification machine learning module; 13. a differential evolution intelligent optimization algorithm module; 14. a positioning coordinate output module; 15. a positioning result output interface; 21. a first WIFI communication interface module; 22. a WIFI interception interface module; 31. and the second WIFI communication interface module.
Detailed Description
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.
Referring to fig. 1-4, the present invention provides a technical solution: a classification self-learning-based WIFI positioning method specifically comprises the following steps:
s1, learning stage of wireless positioning:
z1, detecting signal RSSI information on a WIFI communication interface by using N wireless positioning devices, and sending the signal RSSI information to the positioning engine platform, wherein the positions of the wireless positioning devices are known, and the positioning engine platform can establish a fingerprint information base for the position of each wireless positioning device by integrating the wireless RSSI information reported by the N wireless positioning devices;
z2, when accumulating enough fingerprint data for each position, the positioning engine platform runs the supervised machine learning algorithm based on classification, wherein the fingerprint RSSI set is used as training characteristic, the known wireless positioning device position is used as category, the positioning engine platform simultaneously executes a plurality of classified learning algorithms, the precision and recall rate of each algorithm are obtained according to the confusion matrix obtained by each algorithm aiming at the training data set, different weights are given to each algorithm on the basis, when the learning precision of all the positions is confirmed to reach a certain standard through cross validation, the general standard is that the accuracy is more than 95%, the positioning engine platform saves all the learning models and the weight parameters of each learning algorithm, and stops the learning process.
S2, positioning stage of wireless positioning:
q1, detecting signal RSSI information on WIFI communication interfaces of peripheral user terminals by N wireless positioning devices and sending the signal RSSI information to a positioning engine platform, wherein the positioning engine platform establishes a dynamic fingerprint information base for each user terminal;
q2, for each user terminal, the positioning engine platform continuously generates a location fingerprint for the user terminal in the manner described above and executes a location positioning algorithm with this as input.
S3, executing the position positioning algorithm:
a1, when receiving RSSI information of each user terminal collected by the wireless positioning equipment, starting the execution of the algorithm;
a2, the positioning algorithm establishes an RSSI fingerprint information database for the user terminal corresponding to the received current information;
a3, the positioning algorithm judges whether the RSSI quantity in the user terminal fingerprint database is more than or equal to a certain set value M, M is not less than 3, if yes, a5 is executed, otherwise, a4 is executed;
a4, saving the RSSI value of the current user terminal to the fingerprint database of the terminal, and waiting to receive more RSSI information aiming at the user terminal;
a5 and a6, the positioning algorithm inputs the position fingerprint of the user terminal into each trained machine learning algorithm model, and obtains the approximation degree of the position of the user terminal and each wireless positioning device position according to the weight of each algorithm, and the approximation degree is expressed by percentage or rate;
a7, on the basis of the probability from the known user terminal position to each known position, converting the solution of the user terminal position into an optimization algorithm problem, and designing a cost function for the optimization algorithm problem;
a8, the positioning algorithm executes a differential evolution optimization algorithm to obtain the predicted coordinate value of the user terminal position.
In the present invention, in order to implement accurate positioning in step z1, a value of N is not less than 3, where the location fingerprint refers to an RSSI set of a WIFI communication interface of a wireless positioning device located at the location detected by each wireless positioning device, and a common supervised machine learning algorithm based on classification in step z2 includes: a K neighbor algorithm, a decision tree algorithm, a naive Bayes algorithm, a support vector machine algorithm, an adaBoost algorithm, etc.
In the present invention, the fingerprint information of the user terminal location in step q1 is the RSSI set collected by each wireless positioning device at the same time, and after considering that the detection of the same user terminal signal by multiple wireless positioning devices is prior in time, a small sliding time window, for example, 10 seconds, is set for each user terminal in the fingerprint collection interval, and the RSSI set falling in the time window is used as the location fingerprint of the user terminal.
In the invention, the cost function principle of the optimization algorithm in the step a7 is to calculate the Euclidean distances from the user terminal position to each known position respectively, and then obtain the minimum gap equation according with the proportional relation according to the proportional relation between the distances.
The invention also discloses a classified self-learning-based WIFI positioning system, which comprises a positioning engine platform 1, a wireless positioning device 2 and a user terminal 3, wherein the positioning engine platform 1 comprises a data receiving, processing and storing module 11, a supervised classified machine learning module 12, a differential evolution intelligent optimization algorithm module 13, a positioning coordinate output module 14 and a positioning result output interface 15, the output end of the data receiving, processing and storing module 11 is connected with the input end of the supervised classified machine learning module 12, the output end of the supervised classified machine learning module 12 is connected with the input end of the differential evolution intelligent optimization algorithm module 13, the output end of the differential evolution intelligent optimization algorithm module 13 is connected with the input end of the positioning coordinate output module 14, and the output end of the positioning coordinate output module 14 is connected with the input end of the positioning result output interface 15.
In the present invention, the wireless positioning device 2 includes a first WIFI communication interface module 21 and a WIFI interception interface module 22, and the first WIFI communication interface module 21 and the WIFI interception interface module 22 realize a bidirectional connection, and the first WIFI communication interface module 21 and the data receiving, processing and storing module 11 realize a bidirectional connection.
In the present invention, the user terminal 3 includes the second WIFI communication interface module 31, and the second WIFI communication interface module 31 and the WIFI listening interface module 22 are connected in a bidirectional manner.
It should be noted that: the user terminal 3 is various user devices such as a mobile phone, a tablet computer, a notebook computer, etc. The user terminal is internally provided with a WIFI communication module, the WIFI communication module is kept in an open state for positioning the user terminal, but is not required to be associated with a certain wireless Access Point (AP), and the user terminal 3 comprises a second WIFI communication interface module 31 which can be detected by wireless positioning equipment when the module works;
the wireless positioning equipment is a hardware equipment with a built-in WIFI communication module, and the WIFI communication module of the equipment works in two modes simultaneously: one is a common WIFI client mode, namely, the WIFI client mode is connected to an AP to realize a networking function and realize the intercommunication with a positioning engine platform in a network layer; the other mode is a WIFI interception mode, namely, a WIFI signal transmitted by surrounding WIFI user terminal equipment is intercepted, intercepted information is transmitted to a positioning engine platform according to a certain format, the wireless positioning equipment 2 comprises a first WIFI communication interface module 21 and a WIFI interception interface module 22, the former is responsible for establishing wireless network connection so as to achieve the purpose of communicating with the positioning engine platform, meanwhile, the interface is also capable of being detected by all the wireless positioning equipment, and the latter is responsible for intercepting information of all the wireless positioning equipment and wireless interfaces of the user terminals;
the positioning engine platform 1 is a server host running related server software, receives raw sampling data from the wireless positioning device, runs a positioning algorithm, and outputs positioning location information of the user device.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (9)
1. A classification self-learning-based WIFI positioning method is characterized by comprising the following steps: the method specifically comprises the following steps:
s1, learning stage of wireless positioning:
z1, detecting signal RSSI information on a WIFI communication interface by using N wireless positioning devices, and sending the signal RSSI information to the positioning engine platform, wherein the positions of the wireless positioning devices are known, and the positioning engine platform can establish a fingerprint information base for the position of each wireless positioning device by integrating the wireless RSSI information reported by the N wireless positioning devices;
z2, when accumulating enough fingerprint data for each position, the positioning engine platform runs the supervised machine learning algorithm based on classification, wherein the fingerprint RSSI set is used as training characteristic, the known wireless positioning device position is used as category, the positioning engine platform simultaneously executes a plurality of classified learning algorithms, the precision and recall rate of each algorithm are obtained according to the confusion matrix obtained by each algorithm aiming at the training data set, different weights are given to each algorithm on the basis, when the learning precision of all the positions is confirmed to reach a certain standard through cross validation, the general standard is that the accuracy is more than 95%, the positioning engine platform saves all the learning models and the weight parameters of each learning algorithm, and stops the learning process.
S2, positioning stage of wireless positioning:
q1, detecting signal RSSI information on WIFI communication interfaces of peripheral user terminals by N wireless positioning devices and sending the signal RSSI information to a positioning engine platform, wherein the positioning engine platform establishes a dynamic fingerprint information base for each user terminal;
q2, for each user terminal, the positioning engine platform continuously generates a location fingerprint for the user terminal in the manner described above and executes a location positioning algorithm with this as input.
S3, executing the position positioning algorithm:
a1, when receiving RSSI information of each user terminal collected by the wireless positioning equipment, starting the execution of the algorithm;
a2, the positioning algorithm establishes an RSSI fingerprint information database for the user terminal corresponding to the received current information;
a3, the positioning algorithm judges whether the RSSI quantity in the user terminal fingerprint database is more than or equal to a certain set value M, M is not less than 3, if yes, a5 is executed, otherwise, a4 is executed;
a4, saving the RSSI value of the current user terminal to the fingerprint database of the terminal, and waiting to receive more RSSI information aiming at the user terminal;
a5 and a6, the positioning algorithm inputs the position fingerprint of the user terminal into each trained machine learning algorithm model, and obtains the approximation degree of the position of the user terminal and each wireless positioning device position according to the weight of each algorithm, and the approximation degree is expressed by percentage or rate;
a7, on the basis of the probability from the known user terminal position to each known position, converting the solution of the user terminal position into an optimization algorithm problem, and designing a cost function for the optimization algorithm problem;
a8, the positioning algorithm executes a differential evolution optimization algorithm to obtain the predicted coordinate value of the user terminal position.
4. The classified self-learning-based WIFI positioning method and system according to claim 1, wherein: in step z1, in order to implement accurate positioning, a value of N is not less than 3, where the location fingerprint refers to an RSSI set of a WIFI communication interface of a wireless positioning device located at the location, which is detected by each wireless positioning device, and a common supervised machine learning algorithm based on classification in step z2 includes: a K neighbor algorithm, a decision tree algorithm, a naive Bayes algorithm, a support vector machine algorithm, an adaBoost algorithm, etc.
5. The classified self-learning-based WIFI positioning method and system according to claim 1, wherein: in the step q1, the fingerprint information of the location of the user terminal is the RSSI set collected by each wireless positioning device at the same time, and after considering that the detection of the same user terminal signal by multiple wireless positioning devices is prior in time, a small sliding time window, for example, 10 seconds, is set for each user terminal in the fingerprint collection interval, and the RSSI set falling in the time window is used as the location fingerprint of the user terminal.
6. The classified self-learning-based WIFI positioning method and system according to claim 1, wherein: the cost function principle of the optimization algorithm in the step a7 is to calculate the euclidean distances from the user terminal position to each known position, and then obtain the minimum difference equation according with the proportional relationship according to the proportional relationship between the distances.
7. The utility model provides a WIFI positioning system based on categorised self-learning, includes positioning engine platform (1), wireless locating device (2) and user terminal (3), its characterized in that: the positioning engine platform (1) comprises a data receiving, processing and storing module (11), a supervision and classification machine learning module (12), a differential evolution intelligent optimization algorithm module (13), a positioning coordinate output module (14) and a positioning result output interface (15), wherein the output end of the data receiving, processing and storing module (11) is connected with the input end of the supervision and classification machine learning module (12), the output end of the supervision and classification machine learning module (12) is connected with the input end of the differential evolution intelligent optimization algorithm module (13), the output end of the differential evolution intelligent optimization algorithm module (13) is connected with the input end of the positioning coordinate output module (14), and the output end of the positioning coordinate output module (14) is connected with the input end of the positioning result output interface (15).
8. The classified self-learning-based WIFI positioning system according to claim 5, wherein: the wireless positioning device (2) comprises a first WIFI communication interface module (21) and a WIFI interception interface module (22), the first WIFI communication interface module (21) and the WIFI interception interface module (22) are connected in a two-way mode, and the first WIFI communication interface module (21) is connected with the data receiving, processing and storage module (11) in a two-way mode.
9. The classified self-learning-based WIFI positioning system according to claim 6, wherein: the user terminal (3) comprises a second WIFI communication interface module (31), and the second WIFI communication interface module (31) is in bidirectional connection with the WIFI interception interface module (22).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010058070.8A CN111182452A (en) | 2020-01-19 | 2020-01-19 | Classified self-learning-based WIFI positioning method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010058070.8A CN111182452A (en) | 2020-01-19 | 2020-01-19 | Classified self-learning-based WIFI positioning method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111182452A true CN111182452A (en) | 2020-05-19 |
Family
ID=70658108
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010058070.8A Pending CN111182452A (en) | 2020-01-19 | 2020-01-19 | Classified self-learning-based WIFI positioning method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111182452A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112146761A (en) * | 2020-08-14 | 2020-12-29 | 上海数川数据科技有限公司 | Human body temperature measurement compensation method based on machine learning |
CN113873423A (en) * | 2020-06-29 | 2021-12-31 | 中国电信股份有限公司 | Terminal positioning method, device and system |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108495263A (en) * | 2018-04-04 | 2018-09-04 | 南京邮电大学 | A kind of indoor orientation method based on broad sense multi-kernel function |
CN109151995A (en) * | 2018-09-04 | 2019-01-04 | 电子科技大学 | A kind of deep learning recurrence fusion and positioning method based on signal strength |
CN110381580A (en) * | 2019-07-25 | 2019-10-25 | 上海开域信息科技有限公司 | A kind of WiFi localization method based on ratio optimization |
-
2020
- 2020-01-19 CN CN202010058070.8A patent/CN111182452A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108495263A (en) * | 2018-04-04 | 2018-09-04 | 南京邮电大学 | A kind of indoor orientation method based on broad sense multi-kernel function |
CN109151995A (en) * | 2018-09-04 | 2019-01-04 | 电子科技大学 | A kind of deep learning recurrence fusion and positioning method based on signal strength |
CN110381580A (en) * | 2019-07-25 | 2019-10-25 | 上海开域信息科技有限公司 | A kind of WiFi localization method based on ratio optimization |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113873423A (en) * | 2020-06-29 | 2021-12-31 | 中国电信股份有限公司 | Terminal positioning method, device and system |
CN113873423B (en) * | 2020-06-29 | 2024-01-26 | 中国电信股份有限公司 | Terminal positioning method, device and system |
CN112146761A (en) * | 2020-08-14 | 2020-12-29 | 上海数川数据科技有限公司 | Human body temperature measurement compensation method based on machine learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105261366B (en) | Audio recognition method, speech engine and terminal | |
US9632169B2 (en) | Using inertial navigation for calibration of indoor positioning system | |
CN111935820B (en) | Positioning implementation method based on wireless network and related equipment | |
CN106211084B (en) | Environment perception method based on GSM signal | |
CN111182452A (en) | Classified self-learning-based WIFI positioning method and system | |
US20200348388A1 (en) | Systems and methods to determine room occupancy | |
CN103748862A (en) | Context extraction | |
CN113596989A (en) | Indoor positioning method and system for intelligent workshop | |
CN102253365A (en) | Indoor positioning method based on estimation of wireless signal source parameters | |
CN109899932B (en) | Control method and device of air conditioner | |
US9571977B2 (en) | Use of a trained classifier to determine if a pair of wireless scans came from the same location | |
CN114792469A (en) | Method and device for testing sensing system and testing equipment | |
CN111836194B (en) | Indoor positioning method based on WiFi and Bluetooth | |
CN115665852B (en) | Indoor positioning method, device, equipment and storage medium | |
CN110049442B (en) | Indoor WiFi fingerprint positioning automatic calibration method and system based on smart phone | |
CN110381580B (en) | WiFi positioning method based on proportion optimization | |
CN105392194B (en) | Energy consumption precision equalization methods based on heterogeneous network indoor positioning frame optimal communication | |
CN112948763B (en) | Piece quantity prediction method and device, electronic equipment and storage medium | |
CN109212464B (en) | Method and equipment for estimating terminal distance and position planning | |
CN110611880B (en) | Household WiFi prediction method and device, electronic equipment and storage medium | |
CN109298390B (en) | Indoor positioning method based on wireless signal strength | |
CN112188613A (en) | Multi-antenna indoor positioning method and device based on deep learning | |
CN112867141A (en) | Positioning control method, Bluetooth service node and electronic equipment | |
Khilari | Fingerprinting Based Indoor Positioning System using RSSI Bluetooth | |
TW201618564A (en) | Electronic devices and indoor positioning methods and computer products thereof |
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: 20200519 |
|
RJ01 | Rejection of invention patent application after publication |