CN108802673A - Passenger's Trip chain querying method based on high in the clouds plateform system - Google Patents
Passenger's Trip chain querying method based on high in the clouds plateform system Download PDFInfo
- Publication number
- CN108802673A CN108802673A CN201810714583.2A CN201810714583A CN108802673A CN 108802673 A CN108802673 A CN 108802673A CN 201810714583 A CN201810714583 A CN 201810714583A CN 108802673 A CN108802673 A CN 108802673A
- Authority
- CN
- China
- Prior art keywords
- passenger
- clouds
- plateform system
- querying method
- trip chain
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
- G01S5/0252—Radio frequency fingerprinting
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The present invention relates to field of locating technology, especially a kind of passenger's Trip chain querying method based on high in the clouds plateform system includes the following steps, step S101：Training stage establishes the mapping relations of a coordinate points and high in the clouds AP signal strengths vector, to establish a fingerprint database；Step S102：Positioning stage matches the RSSI vectors of the AP received with the value in fingerprint database according to matching algorithm, finds a suitable value and returns to coordinate.After the above method, in the practice by RSSI rangings, since indoor environment disposes complexity, signal interference is big, the frequent deviation of result obtained by this method is larger, and the present invention, which uses, combines the location algorithm based on fingerprint database and cosine similarity to have good accuracy.
Description
Technical field
The present invention relates to trip field of locating technology, especially a kind of passenger's trip chain query based on high in the clouds plateform system
Method.
Background technology
Location information plays important role in daily life.It is public safety and emergency response first,
In case of emergency, everyone wants to be pin-pointed to by rescue personnel, the big position for arriving building, even floor or
Room number.Secondly, mobile phone shopping, mobile e-business, personalized advertisement/favor information be can be applied to.User can wish to
Enough directly acquire shop or the position of required product.Again, airport, hospital, megastore, conference and exhibition center, large size are located in
Parking lot can have very extensive application.
Most professional positioning system is global positioning system (Global Positioning System, GPS), including army
Many industries including thing, law enforcement, bus dispatching, taxi dispatching, logistics, planning are all the users of global positioning system.With
That GPS client receiver volumes are smaller and smaller, and the precision of client is higher and higher, GPS positioning function by it is extensive used it is each
Each industry of row, the mobile terminals such as some smart mobile phones, notebook are even embedded into terminal using GPS functions as its standard configuration.
With the fast development of wireless mobile telecommunication technology, A-GPS (Assisted that GPS and cellular network are combined
Global Positioning System) positioning method emergency relief and it is various be based on location-based service (LBS, Location-
Based Services) in gradually applied.But since satellite-signal is easy to be blocked by various barriers, GPS/APGS
Equal satellite positioning tech are not particularly suited for indoor or built-up occasion, and wireless indoor location technology rapidly develops at present,
As the strong supplement of GPS.
Invention content
The technical problem to be solved in the invention is to provide a kind of passenger Trip chain issuer based on high in the clouds plateform system
Method.
In order to solve the above technical problems, passenger's Trip chain querying method of the invention based on high in the clouds plateform system, packet
Include following steps,
Step S101：Training stage establishes the mapping relations of a coordinate points and high in the clouds AP signal strengths vector, to build
Found a fingerprint database；
Step S102：Positioning stage will be in the RSSI vectors for the AP that received and fingerprint database according to matching algorithm
Value is matched, and is found a suitable value and is returned to coordinate.
Further, the signal of different location is acquired by script in step S101 and is sent to server.
Further, script acquires a data on each position every 4-6S, acquires this data of 80-120 in total,
And it upload the data on server；After acquisition, fingerprint database is established using the RSSI mean values of AP to each fingerprint characteristic.
Further, matching algorithm is to be combined cosine similarity and NN algorithms in the step S102.
Further, the cosine similarity is the cosine value of the angle by measuring two inner product of vectors spaces to sentence
Similarity degree between fixed two vectors；For cosine value closer to 1, angle indicates that two vectors are more similar closer to 0.
After the above method, in the practice by RSSI rangings, since indoor environment disposes complicated, signal interference
Greatly, the frequent deviation of result obtained by this method is larger, and the present invention uses combination similar based on fingerprint database and cosine
Property location algorithm have good accuracy.
Description of the drawings
The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.
Fig. 1 is that the present invention is based on the schematic diagrames of passenger's Trip chain querying method of high in the clouds plateform system.
Fig. 2 is the schematic diagram of the vectorial cosine similarity of the present invention two.
Specific implementation mode
As shown in Figure 1, passenger's Trip chain querying method based on high in the clouds plateform system of the present invention, includes the following steps,
Step S101：Training stage establishes the mapping relations of a coordinate points and high in the clouds AP signal strengths vector, to build
Found a fingerprint database.The signal of different location is acquired by script in step S101 and is sent to server.Script is every
A data are acquired every 4-6S on a position, acquire this data of 80-120 in total, and upload the data on server；Acquisition
Afterwards, fingerprint database is established using the RSSI mean values of AP to each fingerprint characteristic.By script in each position in present embodiment
It sets and acquires a data every 5s, acquire 100 data in total, and upload the data on server.After acquisition, we are right
Each fingerprint characteristic uses the RSSI mean values such as formula (1) of high in the clouds AP：
The multiple data of same high in the clouds AP acquisitions are averaged, fingerprint database is established with this.
Step S102：Positioning stage will be in the RSSI vectors for the AP that received and fingerprint database according to matching algorithm
Value is matched, and is found a suitable value and is returned to coordinate.Matching algorithm is by cosine similarity and NN in the step S102
Algorithm is combined.
As shown in Fig. 2, the cosine value between two vectors can obtain formula according to Euclid's dot product and the magnitude derivation of equation
(2):
AB=| | A | | | | B | | COS (θ) (2)
By formula (2) and theory, we can obtain similarity formula (3):
The cosine similarity is the cosine value of the angle by measuring two inner product of vectors spaces to judge two vectors
Between similarity degree；For cosine value closer to 1, angle indicates that two vectors are more similar closer to 0.Our collected clouds
The signal strength values of AP are held then to calculate cosine similarity with the data in fingerprint database as a vector, obtained value is got over
Close to 1, represent more similar.
NN algorithms
The RSS observations of test point are S=[SS1, SS2... ..., SSn], existing in fingerprint database is recorded as S1=
[SS1, SS2... ..., SSn], wherein n represents the different high in the clouds AP numbers detected on tested point；I ∈ [1, NT], NTFor in database
Record number；NiThe different high in the clouds AP numbers stored in i-th record are represented, then NN algorithms can be expressed as following formula (4)：
L=argminI ∈ (1, NT)||S-Si||
(4)
Wherein, | | S-Si| | represent S and SiBetween Euclidean distance.
Indoor positioning influence factor：
1, first, the same signal source in actual wireless communication, in the wireless signal strength of the same position of the same space
It is considered as Gaussian distributed.Wireless signal spatial ideally, spatial position distance signal source is closer,
Then the signal strength of the point is stronger；Spatial position is remoter from signal source, then the signal strength of the point is weaker, and signal is strong
Degree is with spatial apart from existence function relationship.
2, co-channel interference；The wireless signal of different AP signal sources is individually present in the signal strength of space same position, i.e.,
The wireless signal presence or absence of one signal source and signal strength do not interfere with the wireless signal in other signals source in the point
Signal strength.Independent thing of the signal strength of signal source each in this way in the power of space same position is considered as Probability
Part, the wireless signal strength between different signal source will not influence each other.Since the wireless signal of different signal sources is in space
Distribution is mutual indepedent, and signal source then can use joint general in the signal strength Gaussian distributed of space given position
Rate distribution come describe multiple access points spacing wireless signal distribution situation.
3, the channel disturbance between same frequency range distinct device；Since the frequency range of entire AP is all in common frequency band, bluetooth,
Industrial 2.4G wireless communications, RDID, UWM ultra-wideband communications；
4, wireless signal causes multipath fading due to phenomena such as there is reflection and scattering in actual environment, other uses
The equipment of the frequency range interferes with each other so that the wireless signal of identical signal source is on the same position of the same space, signal
It is not a determining value that intensity can change with time change, has certain randomness, but Gaussian distributed.
5, secondly, using the localization method based on signal strength, location-server must preserve different letters in localizing environment
The distribution situation of number source in the signal strength of difference, it is desirable to which the distribution situation for preserving the signal strength of each point is impossible
, and signal source in the signal strength of each point is Gaussian distributed in localizing environment, can pass through and preserve signal strength
Gaussian Profile average value and standard deviation, come want to save signal source the feature of the Gaussian Profile of each signal strength and to the greatest extent
Possible reduction data to be saved amount.
Due to the flowing of air in localizing environment, the variation of temperature, personnel such as walk about at the reasons, each point measures in space
Signal strength can change at any time, while the direction of dual-mode antenna can also influence the signal strength of the point, mobile terminal
The randomness of the signal strength values measured is bigger, and it is fixed to be influenced on the different disposal method that the signal strength of mobile terminal uses
Position error.Increase setting accuracy to achieve the purpose that reduce position error, the method that we use probabilistic model.It is positioning
Probabilistic model is established in system.
Finally, when being positioned in real time, mobile terminal needs each different signal source that will be collected into the signal of the point
The location datas such as intensity, are sent to location-server, and location-server utilizes the letter of specified point in saved localizing environment
The average value and standard deviation of the Gaussian Profile of number intensity, according to the signal strength of the correspondence signal source measured in real time in current point,
Remove the Joint Gaussian distribution probability of all signal sources of calculating covering current point.
This probability value is bigger, indicates mobile terminal current location closer to the saved point of location-server.Due to
The finiteness of the continuity and location-server memory space of located space, by the height of the signal strength of all the points in localizing environment
It is impossible that this distribution characteristics, which preserves lower beam,.Specifically it is known as so choosing some according to the characteristics of environment in localizing environment
Training points, and the gaussian distribution characteristic of the signal strength of these training points is preserved, so that these points is become positioning mobile eventually
The datum mark at end, all positioning result are all generated so that training points are as a reference point.
For the WLAN of each indoor environment, wireless signal strength distribution map is built first, that is, builds signal
Intensity empirical value database.Indoor plane figure, the positions AP, AP transmission powers etc. in mobile terminal it has been determined that be likely to occur
Different directions (antenna has certain directionality), multi collect signal strength, in this, as structure are divided in the larger place of probability
The data of empirical value database.The data format of acquisition is as follows：
(position_x,position_y,RSSI,MAC) (2)
Wherein, position_X, position_y are current position coordinates, and RSSI is that the signal that current location is received is strong
Degree, MAC is the MAC Address of the AP points, for distinguishing different AP points.
After completing acquisition, the Value Data of acquisition is pre-processed, target data format is as follows：
(position_x, position_y, RSSI_AVG, RSSI_DEV, MAC) (3)
Wherein, position_x, position_y are current position coordinates, and RSSI_AVG is the RSSI mean values of the AP,
RSSI_DEV is the standard deviation of the RSSI of the AP, and MAC is the MAC Address of the AP points.In order to preserve the signal strength of training points
The feature of i before Gauss point, while considering the modification to these data and newer convenience, preserve these numbers using database
According to.
Although specific embodiments of the present invention have been described above, those skilled in the art should be appreciated that this
It is merely illustrative of, various changes or modifications can be made to present embodiment, without departing from the principle and substance of the present invention,
Protection scope of the present invention is only limited by the claims that follow.
Claims (5)
1. a kind of passenger's Trip chain querying method based on high in the clouds plateform system, which is characterized in that include the following steps, step
S101：Training stage establishes the mapping relations of a coordinate points and high in the clouds AP signal strengths vector, to establish a fingerprint number
According to library；
Step S102：Positioning stage, according to matching algorithm, by the value in the RSSI vectors of the AP received and fingerprint database into
Row matching finds a suitable value and returns to coordinate.
2. passenger's Trip chain querying method described in accordance with the claim 1 based on high in the clouds plateform system, it is characterised in that：Step
The signal of different location is acquired by script in S101 and is sent to server.
3. passenger's Trip chain querying method based on high in the clouds plateform system according to claim 2, it is characterised in that：Script
A data are acquired every 4-6S on each position, acquire this data of 80-120 in total, and upload the data on server；
After acquisition, fingerprint database is established using the RSSI mean values of AP to each fingerprint characteristic.
4. passenger's Trip chain querying method described in accordance with the claim 1 based on high in the clouds plateform system, it is characterised in that：It is described
Matching algorithm is to be combined cosine similarity and NN algorithms in step S102.
5. passenger's Trip chain querying method based on high in the clouds plateform system according to claim 4, it is characterised in that：It is described
Cosine similarity is the cosine value of the angle by measuring two inner product of vectors spaces to judge the similar journey between two vectors
Degree；For cosine value closer to 1, angle indicates that two vectors are more similar closer to 0.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810714583.2A CN108802673A (en) | 2018-07-03 | 2018-07-03 | Passenger's Trip chain querying method based on high in the clouds plateform system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810714583.2A CN108802673A (en) | 2018-07-03 | 2018-07-03 | Passenger's Trip chain querying method based on high in the clouds plateform system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108802673A true CN108802673A (en) | 2018-11-13 |
Family
ID=64073089
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810714583.2A Pending CN108802673A (en) | 2018-07-03 | 2018-07-03 | Passenger's Trip chain querying method based on high in the clouds plateform system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108802673A (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107124455A (en) * | 2017-04-25 | 2017-09-01 | 北京大有中城科技有限公司 | Indoor orientation method based on high in the clouds plateform system |
-
2018
- 2018-07-03 CN CN201810714583.2A patent/CN108802673A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107124455A (en) * | 2017-04-25 | 2017-09-01 | 北京大有中城科技有限公司 | Indoor orientation method based on high in the clouds plateform system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pu et al. | Indoor positioning system based on BLE location fingerprinting with classification approach | |
| CN111521969B (en) | Passive indoor positioning method based on Wi-Fi | |
| US7599796B2 (en) | Dual-mode location position system | |
| US11550024B2 (en) | Interferometric location sensing | |
| Fang et al. | Is FM a RF-based positioning solution in a metropolitan-scale environment? A probabilistic approach with radio measurements analysis | |
| Cengiz | Comprehensive analysis on least-squares lateration for indoor positioning systems | |
| CN107124455A (en) | Indoor orientation method based on high in the clouds plateform system | |
| CN104181500A (en) | Real-time locating method based on inertia information and chance wireless signal characteristics | |
| Adege et al. | Applying Deep Neural Network (DNN) for large-scale indoor localization using feed-forward neural network (FFNN) algorithm | |
| Aguilar-Garcia et al. | Enhancing RFID indoor localization with cellular technologies | |
| CN106793087A (en) | A kind of array antenna indoor positioning algorithms based on AOA and PDOA | |
| CN105531599A (en) | Method and apparatus for time of flight fingerprint and geo-location | |
| CN101975938A (en) | Five-dimensional positioning method and system based on radio-frequency signals | |
| Su et al. | A hybrid indoor-position mechanism based on bluetooth and WiFi communications for smart mobile devices | |
| Kim et al. | Passive WiFi fingerprinting method | |
| Pihlajasalo et al. | Absolute positioning with unsupervised multipoint channel charting for 5G networks | |
| US10454597B1 (en) | Systems and methods for locating telecommunication cell sites | |
| KR20130106954A (en) | Indoor positioning method and system and apparatus therefor | |
| Tanbo et al. | Active RFID attached object clustering method based on RSSI series for finding lost objects | |
| CN108802673A (en) | Passenger's Trip chain querying method based on high in the clouds plateform system | |
| Xu et al. | Indoor localization based on hybrid Wi-Fi hotspots | |
| Krishnamurthy | Technologies for positioning in indoor Areas | |
| CN109714704A (en) | A kind of indoor orientation method and device based on wisdom room point | |
| Cheng et al. | Fast setup and robust wifi localization for the exhibition industry | |
| Wu et al. | Global Wi-Fi Positioning Method Based on Online Clustering Algorithm |
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 | ||
| CB02 | Change of applicant information |
Address after: 101499 room 409, 4th floor, South, 113 Kaifang Road, Huairou District, Beijing Applicant after: Ruizhi Technology Group Co.,Ltd. Address before: 101499 room 409, 4th floor, South, 113 Kaifang Road, Huairou District, Beijing Applicant before: BEIJING RAYSDATA Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181113 |
|
| RJ01 | Rejection of invention patent application after publication |