CN114125709A - Real-time data mining and positioning method combining GIS road network and Bluetooth beacon - Google Patents

Real-time data mining and positioning method combining GIS road network and Bluetooth beacon Download PDF

Info

Publication number
CN114125709A
CN114125709A CN202210083010.0A CN202210083010A CN114125709A CN 114125709 A CN114125709 A CN 114125709A CN 202210083010 A CN202210083010 A CN 202210083010A CN 114125709 A CN114125709 A CN 114125709A
Authority
CN
China
Prior art keywords
data
time
positioning
personnel
beacon
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
Application number
CN202210083010.0A
Other languages
Chinese (zh)
Other versions
CN114125709B (en
Inventor
王三明
王聪明
胡小敏
李玉哲
王浩
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Anyuan Technology Co.,Ltd.
Original Assignee
Nanjing Anyuan Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nanjing Anyuan Technology Co ltd filed Critical Nanjing Anyuan Technology Co ltd
Priority to CN202210083010.0A priority Critical patent/CN114125709B/en
Publication of CN114125709A publication Critical patent/CN114125709A/en
Application granted granted Critical
Publication of CN114125709B publication Critical patent/CN114125709B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • 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
    • H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • General Physics & Mathematics (AREA)
  • Remote Sensing (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a real-time data mining and positioning method combining a GIS road network and a Bluetooth beacon, which comprises the following steps: step 1, recording beacon historical positioning data and receiving personnel beacon data; step 2, positioning to obtain the position probability of the possible area of the person through real-time positioning data; step 3, the GIS spatial data storage and calculation module performs road network overlapping calculation according to the position probability of the possible personnel regions to obtain the probability of the possible personnel regions after filtration; step 4, judging whether the data of the inspection historical library exists or not, determining real-time position data, and step 5, predicting the possible position of future time by using DTW, a road network range and a positioning possible range; the method has high tolerance on the accuracy of the positioning method, can convert the positioning problem into the probability problem, and can prevent large abnormity of positioning by using long-time sequence data for correction.

Description

Real-time data mining and positioning method combining GIS road network and Bluetooth beacon
Technical Field
The invention relates to the technical field of personnel positioning, in particular to a real-time data mining and positioning method combining a GIS road network and a Bluetooth beacon.
Background
The Bluetooth positioning is based on RSSII (Received Signal Strength Indication) value, and positioning is carried out by a triangulation positioning principle. The existing Bluetooth beacon continuously sends broadcast, and after Bluetooth signals are collected by a positioning card, related Bluetooth information is sent to a server through preliminary calculation, and positioning method calculation is carried out. The obtained personnel positioning data is combined with a map to complete the management of personnel positioning, but because the accuracy of the Bluetooth beacon is usually 2-5 meters, the problems of sudden personnel position, withdrawing of a traveling route, wall penetration and the like occur in practical application.
Disclosure of Invention
The purpose of the invention is as follows: in order to overcome the defects in the prior art, the invention provides a method for mining personnel positioning information by combining GIS road network spatial data and data, so that the problems of position fluctuation, route withdrawal, wall penetration and the like are solved, and the effect of improving the positioning precision is achieved
The technical scheme is as follows:
in a first aspect, a method for mining and positioning real-time data by combining a GIS road network and a bluetooth beacon is provided, which comprises the following steps:
step 1, recording beacon historical positioning data through a beacon counting module 1, receiving beacon data when people walk, and obtaining real-time positioning data of the people according to the beacon historical positioning data and the beacon data when the people walk; meanwhile, the obtained real-time positioning data of the person is provided to the positioning possible area calculation module 2.
Step 2, the possible positioning area calculating module 2 obtains the position probability P of the possible area of the person through the real-time positioning data of the person; and simultaneously transmitting the obtained position probability P of the possible region of the personnel to a GIS space data storage and calculation module 3.
And 3, performing road network overlapping calculation by the GIS spatial data storage and calculation module 3 according to the possible region of the personnel to obtain the probability Pm of the possible region of the personnel after filtering.
Step 4, judging whether the personnel in the step 3 patrol the data of the historical library through the personnel patrol the historical library 4;
if the personnel in the step 3 have no data in the personnel inspection historical library 4, taking the position of the square area with the maximum probability as the real-time position data of the personnel in the step 3; the optimal position of the person in step 3 is P _ x = max (pm),
and if the personnel has the data of the inspection historical library, executing the step 5.
And 5, inquiring a continuous period of time before the current time point by the personnel inspection historical library 4 through the real-time position data mining and positioning module 5, calling road sections which pass through the continuous period of time before the acquired current time point in the historical library data, screening corresponding matched personnel according to the called road sections which pass through the road sections, and recording the sequence of the screened corresponding matched personnel passing through the same road sections at the previous time.
The historical data are structured according to a time sequence, an X axis represents time, a Y axis represents the distance of a beacon connecting line of each road section, and the distance is accumulated according to the current road section sequence to obtain a time sequence position diagram moving according to time; the projection of the beacon connecting lines on the table and the sequence of the road sections are used for sorting, and the sorting is simplified into two-dimensional time sequence data according to road network planning, Y is abstracted into the distance from the starting point, and X is natural time.
And searching a warping path by adopting a time-based dynamic warping similarity method according to the obtained two-dimensional time sequence data to minimize the warping distance.
Figure 809892DEST_PATH_IMAGE002
Where ED (Q, C) represents a measure of DTW, Q represents a query sequence, C represents a content sequence,
Figure 429223DEST_PATH_IMAGE004
the value of query sequence Q representing the r-th path match point,
Figure 541536DEST_PATH_IMAGE006
a value of the content sequence C representing the r-th path matching point,
Figure 470177DEST_PATH_IMAGE008
indicating the number of path matching points.
If the historical curves have o [ C1, C2, … Co ], then each square of the computation of road network overlap by the GIS spatial data storage and computation module 3 according to the possible region of the person is a query sequence Q [ Q1, Q2, …, Qm ]; the query sequence Q is respectively calculated with the content sequence C to respectively obtain the measures ED (Qm, C1) and … ED (Qm, Co) of DTW; the weights obtained according to the DTW method are:
Dm=-(pre(m)-min(m))/sig(m)*k+1
where Dm denotes the weight obtained according to the DTW method, sig (m) is the standard deviation of the set of data, pre (m) is the mean of the set of data, min (m) is the minimum of the set of data, and k is the empirical value.
And (3) taking the moving range of the time difference between the time to be predicted and the current time to obtain the Pm value of the rectangular area at the time point to be predicted, wherein the possible position P _ x of the predicted future time is as follows:
P_x=max(P1*D1，……，Pm*Dm)
where P _ x represents an optimal correction point, m represents m squares, Pm represents the probability of the mth square, and Dm is a weight obtained according to the DTW method.
Further, the real-time positioning data of the person in step 1 includes a maximum real-time positioning distance max (d), a minimum real-time positioning distance min (d), and an average real-time positioning distance pre (d).
d = pow(10， float((abs(RSSI) - A) / (10 * n)))。
A = (math.log10(d1) * abs(RSSI2) - math.log10(d2) * abs(RSSI1)) / (math.log10(d1) - math.log10(d2)) 。
n = (abs(RSSI1) - abs(RSSI2)) / (10 * (math.log10(d1) - math.log10(d2)))。
Wherein d represents the personnel positioning distance, pow represents the POWER function, RSSI represents the received signal strength, A represents the signal strength when the transmitting end and the receiving end are separated by 1 meter, n represents the environmental attenuation factor,
two different sets of d-value and RSSI-value are collected as (d1, RSSI1) (d2, RSSI2), d1 represents the first set calculated positioning distance, RSSI1 represents the first set received signal strength, d2 represents the second set calculated positioning distance, RSSI2 represents the second set received signal strength, abs represents an absolute value function, and math.log10 represents that a logarithmic function takes 10 as a base.
Further, the method for the location probability P of the possible area of the person obtained by the location data calculation module 2 of the beacon in step 2 is as follows:
Figure 667940DEST_PATH_IMAGE010
wherein the content of the first and second substances,Pindicating the probability of the location of the likely region of the person,
Figure 90963DEST_PATH_IMAGE012
for persons
Figure 792202DEST_PATH_IMAGE014
The probability of (a) of (b) being,Mrepresenting the number of people, assuming that the distribution of the beacon statistics is normal, and 12 standard deviations sigma between the maximum and minimum values,
σ=(max(d)-min(d))/12。
u=pre(d)。
uindicates expectation and σ indicates standard deviation.
Further, in step 3, the GIS spatial data storage and calculation module 3 performs a road network overlap calculation method according to the possible regions of the people: subdividing the possible personnel area according to the square with the side length of g, dividing m squares, and calculating for each square by using a probability formula of the possible personnel area positioning calculation module 2 to obtain the probability Pm of the possible personnel area after filtering.
Further, the GIS spatial data storage and calculation module 3 uses a spatial database to store map data of indoor and outdoor road networks and all Bluetooth beacon positions, receives possible position ranges of personnel, and then calculates the range of an intersection part by taking intersection with the road networks; the receiving person's starting position and destination position calculate a possible travel path.
Further, the personnel inspection historical database 4 records historical positioning data of personnel inspection, statistically regulates routes of the personnel, and uses a spatial database of a GIS road network to perform the following segmentation:
firstly, a road network in the GIS space data storage and calculation module 3 is split into a plurality of continuous road sections according to intersections, and the road sections are marked as route (n), wherein n represents the marking sequence on the road network. Then, the beacons on the route (n) are recorded as an array of sequences [ B1, B2, B3, … … Bx ] according to the relative distances, which is called a beacon link.
The statistical regularization method for the routes of the personnel comprises the following steps: the positioning data is: time t, position probability P of possible region of person. Projecting the position probability P of the possible area of the person to a beacon connecting line of the current road section, recording the position probability P as a projection distance rd, and recording the positioning data of a period of time as an array: [ t (1), p (1), rd (1), Route (1) ], [ t (2), p (2), rd (2), Route (2) ], [ t (3), p (3), rd (3), Route (3) ], … … [ t (n), p (n), rd (n), Route (n) ].
Furthermore, the side length g of the square in the step 3 is 0.1-0.3 meter.
Further, the empirical value k in step 5 is 0.1 to 0.4.
On the other hand, a real-time data mining positioning system combining a GIS road network and a Bluetooth beacon comprises a GIS spatial data storage and calculation module 3, a beacon statistics module 1, a personnel inspection historical library 4, a possible positioning region calculation module 2 and a real-time position data mining positioning module 5, wherein the beacon statistics module 1 is respectively connected with the possible positioning region calculation module 2 and the real-time position data mining positioning module 5, the GIS spatial data storage and calculation module 3, the personnel inspection historical library 4 and the possible positioning region calculation module 2 are respectively connected with the real-time position data mining positioning module 5, and the GIS spatial data storage and calculation module 3, the personnel inspection historical library 4 and the possible positioning region calculation module 2 are respectively connected with the real-time position data mining positioning module 5, wherein:
the beacon counting module 1 is used for recording beacon historical positioning data, receiving beacon data when people walk, and obtaining real-time positioning data of people according to the beacon historical positioning data and the beacon data when the people walk. Meanwhile, the obtained real-time positioning data of the person is provided to the positioning possible area calculation module 2.
The positioning possible area calculating module 2 is used for obtaining the position probability P of the possible area of the person through the real-time positioning data of the person. And simultaneously transmitting the obtained position probability P of the possible region of the personnel to a GIS space data storage and calculation module 3.
And the GIS spatial data storage and calculation module 3 carries out road network overlapping calculation according to the possible regions of the personnel to obtain the probability Pm of the possible regions of the personnel after filtration.
The personnel inspection historical library 4 is used for judging whether the personnel has inspection historical library data or not,
the historical database stores path action data of multiple days of personnel, and the judgment can be carried out only by finding a plurality of records consistent with the current action sequence.
If the current action sequence is a road section sequence [ Route 1.. Route n ] passing within 20 to 40 minutes, the historical records of the person from Route 1 to Route n end in the past week are inquired according to the day, and in the historical records, the passing road section name set is consistent with the current path name set, and the historical records are used as the judgment basis of the data of the routing inspection historical library.
And if the personnel in the step 3 have no data in the personnel inspection historical library 4, taking the position of the square area with the maximum probability as the real-time position data of the personnel in the step 3.
And if the personnel in the step 3 have the data of the routing inspection historical library, performing data correction through a real-time position data mining positioning module 5.
The real-time position data mining and positioning module 5 is used for inquiring the personnel inspection historical library 4, acquiring a continuous period of time before the current time point, calling road sections which pass through the continuous period of time before the acquired current time point in the historical library data, screening corresponding matching personnel according to the called road sections which pass through the road sections, and recording the sequence of the screened corresponding matching personnel passing through the same road sections at the previous period of time.
And (3) organizing each historical data according to a time sequence, wherein an X axis represents time, a Y axis represents the distance of a beacon connecting line of each road section, and the distance is accumulated according to the current road section sequence to obtain a time sequence position diagram moving according to time. The projection of the beacon connecting lines on the table and the sequence of the road sections are used for sorting, and the sorting is simplified into two-dimensional time sequence data according to road network planning, Y is abstracted into the distance from the starting point, and X is natural time.
And searching a warping path by adopting a time dynamic warping similarity-based method according to the obtained two-dimensional time sequence data to minimize the warping distance.
Figure 157325DEST_PATH_IMAGE016
Where ED (Q, C) represents a measure of DTW, Q represents a query sequence, C represents a content sequence,
Figure 576805DEST_PATH_IMAGE018
the value of query sequence Q representing the r-th path match point,
Figure 724889DEST_PATH_IMAGE020
a value of the content sequence C representing the r-th path matching point,
Figure 424511DEST_PATH_IMAGE022
indicating the number of path matching points.
Assuming that there are o historical curves [ C1, C2, … Co ], each square of the computation of road network overlap by the GIS spatial data storage and computation module 3 in step 3 is a query sequence Q [ Q1, Q2, …, Qm ] according to the possible region of the person. The query sequence Q is calculated with the content sequence C to obtain the measures ED (Qm, C1) and … ED (Qm, Co) of DTW. The weights obtained according to the DTW method are:
Dm=-(pre(m)-min(m))/sig(m)*k+1
where Dm denotes the weight obtained according to the DTW method, sig (m) is the standard deviation of the set of data, pre (m) is the mean of the set of data, min (m) is the minimum of the set of data, and k is the empirical value.
And (3) taking the moving range of the time difference between the time to be predicted and the current time to obtain the Pm value of the rectangular area at the time point to be predicted, wherein the possible position P _ x of the predicted future time is as follows:
P_x=max(P1*D1，……，Pm*Dm)
where P _ x represents an optimal correction point, m represents m squares, Pm represents the probability of the mth square, and Dm is a weight obtained according to the DTW method.
Further, the method for obtaining the position probability P of the possible area of the person by the positioning data of the beacon by the positioning possible area calculating module 2 is as follows:
Figure 835900DEST_PATH_IMAGE024
wherein
Figure 601731DEST_PATH_IMAGE026
Indicating the probability of the location of the likely region of the person,
Figure 491190DEST_PATH_IMAGE012
for persons
Figure 229339DEST_PATH_IMAGE028
The probability of (a) of (b) being,Mrepresenting the number of people, assuming that the distribution of the beacon statistics is normal, and 12 standard deviations sigma between the maximum and minimum values,
σ=(max(d)-min(d))/12。
u=pre(d)。
uindicates expectation and σ indicates standard deviation.
Compared with the prior art, the invention has the following beneficial effects:
1, the tolerance of the positioning method on the accuracy is high, the positioning problem is converted into the probability problem, and the correction can be carried out not only in local time, but also in a comprehensive manner for a long time.
2, the long-time sequence data is used for correction, so that large positioning abnormity (the position change in time is considered) can be prevented, and the position of the personnel can be predicted by the colleague.
Drawings
FIG. 1 is a flow chart of the implementation of data mining positioning.
FIG. 2 is a schematic diagram of a classical triangulation method.
FIG. 3 is a graph illustrating comparison of time series data.
Fig. 4 is a time-series position diagram of the movement in time.
Detailed Description
The present invention is further illustrated by the following description in conjunction with the accompanying drawings and the specific embodiments, it is to be understood that these examples are given solely for the purpose of illustration and are not intended as a definition of the limits of the invention, since various equivalent modifications will occur to those skilled in the art upon reading the present invention and fall within the limits of the appended claims.
Referring to fig. 1 to 4, the present invention provides a technical solution: a real-time data mining and positioning method combining a GIS road network and a Bluetooth beacon comprises the following steps:
step 1, recording the historical beacon positioning data through the beacon counting module 1, receiving the beacon data of people walking at the same time, obtaining the real-time personnel positioning data according to the historical beacon positioning data and the beacon data of people walking, and providing the obtained real-time personnel positioning data for the possible positioning area calculating module 2.
The personnel real-time positioning data comprises a maximum personnel real-time positioning distance max (d), a minimum personnel real-time positioning distance min (d) and an average personnel real-time positioning distance pre (d).
d = pow(10， float((abs(RSSI) - A) / (10 * n)))。
A = (math.log10(d1) * abs(RSSI2) - math.log10(d2) * abs(RSSI1)) / (math.log10(d1) - math.log10(d2)) 。
n = (abs(RSSI1) - abs(RSSI2)) / (10 * (math.log10(d1) - math.log10(d2)))。
Wherein d represents the personnel positioning distance, pow represents the POWER function, RSSI represents the received signal strength, A represents the signal strength when the transmitting end and the receiving end are separated by 1 meter, and n represents the environmental attenuation factor.
Two different sets of d-value and RSSI-value are collected as (d1, RSSI1) (d2, RSSI2), d1 represents the first set calculated positioning distance, RSSI1 represents the first set received signal strength, d2 represents the second set calculated positioning distance, RSSI2 represents the second set received signal strength, abs represents an absolute value function, and math.log10 represents that a logarithmic function takes 10 as a base.
And 2, obtaining the position probability P of the possible area of the person by the positioning possible area calculation module 2 through the real-time positioning data of the person. And simultaneously transmitting the obtained position probability P of the possible region of the personnel to a GIS space data storage and calculation module 3.
Processing the positioning data of the beacon usually by a triangulation method, as shown in fig. 2, setting three non-collinear base stations BS1, BS2, BS3 and an unknown terminal E on a plane, and having measured distances from the three base stations to the terminal E as r1, r2 and r3, then three intersecting circles can be drawn by taking coordinates of the three base stations as a circle center and distances from the three base stations to the unknown terminal as radii, as shown in the figure below, the unknown node coordinates are intersection points of the three circles.
The method for obtaining the position probability P of the possible area of the person by the positioning data of the beacon by the positioning possible area calculation module 2 comprises the following steps:
Figure 421417DEST_PATH_IMAGE030
wherein P represents the position probability of possible region of people, f (x) is the probability of x people, M represents the number of people, the distribution of the beacon statistics is assumed to be normal distribution, and 12 standard deviations sigma exist between the maximum value and the minimum value,
σ=(max(d)-min(d))/12。
u=pre(d)。
u denotes expectation and σ denotes standard deviation.
And 3, calling a GIS spatial data storage and calculation module 3 by the real-time position data mining and positioning module 5 according to the position probability P of the possible region of the personnel, and performing road network overlapping calculation by the GIS spatial data storage and calculation module 3 according to the possible region of the personnel to obtain the probability Pm of the possible region of the personnel after filtering.
The method for performing road network overlapping calculation by the GIS spatial data storage and calculation module 3 according to the possible regions of the personnel comprises the following steps:
subdividing the possible personnel area according to a square with the side length of g, dividing m squares, and calculating by using a probability formula of a possible personnel area positioning calculation module 2 for each square to obtain the probability Pm of the filtered possible personnel area, wherein the side length g of the square is 0.2 m.
The GIS space data storage and calculation module 3 stores map data of indoor and outdoor road networks and all Bluetooth beacon positions by using a space database, receives possible position ranges of personnel, and then calculates the range of an intersection part by taking intersection with the road networks; the receiving person's starting position and destination position calculate a possible travel path.
And 4, judging whether the personnel in the step 3 patrol the historical database data or not through the personnel patrol the historical database 4.
And if the personnel in the step 3 have no data in the personnel inspection historical library 4, taking the position of the square area with the maximum probability as the real-time position data of the personnel in the step 3. The position of the square region with the highest probability is taken as the real-time position data for the person in step 3. The optimal position for the person in step 3 is P _ x = max (pm),
and if the personnel has the data of the inspection historical library, executing the step 5.
The personnel patrol historical database 4 records historical positioning data of personnel patrol, statistically regulates routes of the personnel, and uses a spatial database of a GIS road network to perform the following segmentation:
firstly, a road network in the GIS space data storage and calculation module 3 is split into a plurality of continuous road sections according to intersections, and the road sections are marked as route (n), wherein n represents the marking sequence on the road network. Then, the beacons on the route (n) are recorded as an array of sequences [ B1, B2, B3, … … Bx ] according to the relative distances, which is called a beacon link.
The statistical regularization method for the routes of the personnel comprises the following steps: the positioning data is: time t, position probability P of possible region of person. Projecting the position probability P of the possible area of the person to a beacon connecting line of the current road section, recording the position probability P as a projection distance rd, and recording the positioning data of a period of time as an array: [ [ t (1), p (1), rd (1), Route (1) ], [ t (2), p (2), rd (2), Route (2) ], [ t (3), p (3), rd (3), Route (3) ], … …, [ t (n), p (n), rd (n), Route (n) ].
As shown in fig. 3, each point in the graph represents the position of a person on a road segment at a certain moment in time, and the projection of the person on the beacon link. The start and end of the recording time of each historical time series are different, and the number of recordings is also different. The rectangular area in the figure is the projection of the range of possible people calculated by module d onto the beacon link. The correction point C is a result which needs to be corrected, original multi-dimensional data is simplified into two-dimensional time sequence data according to road network planning by using the sequence of projection on a beacon connecting line and road sections, Y is abstracted into a distance from a starting point, and X is natural time.
And 5, inquiring the personnel inspection historical library 4 through the real-time position data mining and positioning module 5, acquiring a continuous period of time before the current time point, calling road sections which pass through the acquired continuous period of time before the current time point in the historical library data, screening corresponding matched personnel according to the called road sections which pass through the road sections, and recording the sequence of the screened corresponding matched personnel passing through the same road sections at the previous period of time.
And (3) organizing each historical data according to a time sequence, wherein an X axis represents time, a Y axis represents the distance of a beacon connecting line of each road section, and the distance is accumulated according to the current road section sequence to obtain a time sequence position diagram moving according to time. The projection of the beacon connecting lines on the table and the sequence of the road sections are used for sorting, and the sorting is simplified into two-dimensional time sequence data according to road network planning, Y is abstracted into the distance from the starting point, and X is natural time.
And searching a warping path by adopting a time-based dynamic warping similarity method according to the obtained two-dimensional time sequence data to minimize the warping distance.
Figure 612227DEST_PATH_IMAGE032
Where ED (Q, C) represents a measure of DTW, Q represents a query sequence, C represents a content sequence,
Figure 39797DEST_PATH_IMAGE034
the value of query sequence Q representing the r-th path match point,
Figure 366873DEST_PATH_IMAGE036
a value of the content sequence C representing the r-th path matching point,
Figure 979120DEST_PATH_IMAGE038
indicating the number of path matching points.
If the historical curves have o [ C1, C2, … Co ], then each square of the computation of road network overlap by the GIS spatial data storage and computation module 3 according to the possible region of the person is a query sequence Q [ Q1, Q2, …, Qm ]; the query sequence Q is respectively calculated with the content sequence C to respectively obtain the measures ED (Qm, C1) and … ED (Qm, Co) of DTW; the weights obtained according to the DTW method are:
Dm=-(pre(m)-min(m))/sig(m)*k+1
where Dm denotes the weight obtained according to the DTW method, sig (m) is the standard deviation of the set of data, pre (m) is the mean of the set of data, min (m) is the minimum of the set of data, and k is the empirical value.
And (3) taking the moving range of the time difference between the time to be predicted and the current time to obtain the Pm value of the rectangular area at the time point to be predicted, wherein the possible position P _ x of the predicted future time is as follows:
P_x=max(P1*D1，……，Pm*Dm)
where P _ x represents an optimal correction point, m represents m squares, Pm represents the probability of the mth square, and Dm is a weight obtained according to the DTW method.
On the other hand, the invention provides a real-time data mining and positioning system combining a GIS road network and a Bluetooth beacon, which comprises a GIS spatial data storage and calculation module 3, a beacon statistics module 1, a personnel inspection historical library 4, a possible positioning region calculation module 2 and a real-time position data mining and positioning module 5, wherein the beacon statistics module 1 is respectively connected with the possible positioning region calculation module 2 and the real-time position data mining and positioning module 5, the GIS spatial data storage and calculation module 3, the personnel inspection historical library 4 and the possible positioning region calculation module 2 are respectively connected with the real-time position data mining and positioning module 5, and the GIS spatial data storage and calculation module 3, the personnel inspection historical library 4 and the possible positioning region calculation module 2 are respectively connected with the real-time position data mining and positioning module 5, wherein:
the beacon counting module 1 is used for recording beacon historical positioning data, receiving beacon data when people walk, and obtaining real-time positioning data of people according to the beacon historical positioning data and the beacon data when the people walk. Meanwhile, the obtained real-time positioning data of the person is provided to the positioning possible area calculation module 2.
The positioning possible area calculating module 2 is used for obtaining the position probability P of the possible area of the person through the real-time positioning data of the person. The possible positioning area calculating module 2 simultaneously transmits the obtained position probability P of the possible personnel area to the GIS space data storage and calculation module 3.
The method for obtaining the position probability P of the possible area of the person by the positioning data of the beacon by the positioning possible area calculation module 2 comprises the following steps:
Figure 657226DEST_PATH_IMAGE030
wherein the content of the first and second substances,Pindicating the probability of the location of the likely region of the person,
Figure 888487DEST_PATH_IMAGE040
for persons
Figure 335649DEST_PATH_IMAGE042
The probability of (a) of (b) being,Mrepresenting the number of people, assuming that the distribution of the beacon statistics is normal, and 12 standard deviations sigma between the maximum and minimum values,
σ=(max(d)-min(d))/12。
u=pre(d)。
uindicates expectation and σ indicates standard deviation.
And the GIS spatial data storage and calculation module 3 carries out road network overlapping calculation according to the possible regions of the personnel to obtain the probability Pm of the possible regions of the personnel after filtration.
And the personnel inspection historical library 4 is used for judging whether the personnel has inspection historical library data or not.
The historical database stores path action data of multiple days of personnel, and only needs to find a plurality of records consistent with the current action sequence, and the current action sequence is assumed to be a road section sequence (Route 1.. Route n) generally passed by 30 minutes
Then inquiring the historical records of the person from Route 1 to Route n in the past week according to the days, wherein the passed road section name set is consistent with the current path name set in the historical records, and the historical records are used as the judgment basis of whether the data of the routing inspection historical library is consistent.
If the personnel has the data of the inspection historical library, the data is corrected through the real-time position data mining positioning module 5.
The real-time position data mining and positioning module 5 is used for inquiring the personnel inspection historical library 4, acquiring a continuous period of time before the current time point, calling road sections which pass through the continuous period of time before the acquired current time point in the historical library data, screening corresponding matching personnel according to the called road sections which pass through the road sections, and recording the sequence of the screened corresponding matching personnel passing through the same road sections at the previous period of time.
And (3) organizing each historical data according to a time sequence, wherein an X axis represents time, a Y axis represents the distance of a beacon connecting line of each road section, and the distance is accumulated according to the current road section sequence to obtain a time sequence position diagram moving according to time. The projection of the beacon connecting lines on the table and the sequence of the road sections are used for sorting, and the sorting is simplified into two-dimensional time sequence data according to road network planning, Y is abstracted into the distance from the starting point, and X is natural time.
And searching a warping path by adopting a time dynamic warping similarity-based method according to the obtained two-dimensional time sequence data to minimize the warping distance.
Figure 603950DEST_PATH_IMAGE044
Wherein ED (Q, C) represents a measure of DTW, with smaller being more similar, Q representing a query sequence, C representing a content sequence,
Figure 769352DEST_PATH_IMAGE046
the value of query sequence Q representing the r-th path match point,
Figure 538725DEST_PATH_IMAGE048
a value of the content sequence C representing the r-th path matching point,
Figure 105973DEST_PATH_IMAGE050
indicating the number of path matching points.
Assuming that there are o historical curves [ C1, C2, … Co ], each square of the computation of road network overlap by the GIS spatial data storage and computation module 3 in step 3 is a query sequence Q [ Q1, Q2, …, Qm ] according to the possible region of the person. The query sequence Q is calculated with the content sequence C to obtain the measures ED (Qm, C1) and … ED (Qm, Co) of DTW. The weights obtained according to the DTW method are:
Dm=-(pre(m)-min(m))/sig(m)*k+1
where Dm denotes the weight obtained according to the DTW method, sig (m) is the standard deviation of the set of data, pre (m) is the mean of the set of data, min (m) is the minimum of the set of data, and k is the empirical value.
And (3) taking the moving range of the time difference between the time to be predicted and the current time to obtain the Pm value of the rectangular area at the time point to be predicted, wherein the possible position P _ x of the predicted future time is as follows:
P_x=max(P1*D1，……，Pm*Dm)
where P _ x represents an optimal correction point, m represents m squares, Pm represents the probability of the mth square, and Dm is a weight obtained according to the DTW method.
By using the method, the possible position of the future time can be predicted according to the historical data, the moving range of the previous time (the time difference between the time to be predicted and the current time) is taken, the rectangular area of the time point to be predicted is obtained, and if the Pm values of the rectangular area are all 1, the optimal P _ x can be calculated according to the formula, and the P _ x is the possible position of the predicted future time.
In the embodiment, the historical data of the personnel is normalized into the standard time sequence data, the path is normalized into the single-dimensional standard according to the road section, the DTW, the road network range and the possible positioning range are used for comprehensively correcting the position of the user, and the predicted position in short time is realized. And long-time sequence data is used for correction, so that large abnormity can be prevented from occurring in positioning.
The above description is only of the preferred embodiments of the present invention, and it should be noted that: it will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the principles of the invention and these are intended to be within the scope of the invention.

Claims (10)

1. A real-time data mining and positioning method combining a GIS road network and a Bluetooth beacon is characterized by comprising the following steps:
step 1, recording beacon historical positioning data through a beacon statistical module (1), receiving beacon data when people walk, and obtaining real-time positioning data of the people according to the beacon historical positioning data and the beacon data when the people walk; meanwhile, the obtained real-time positioning data of the person is provided to a possible positioning area calculation module (2);
step 2, a possible positioning area calculating module (2) obtains the position probability P of the possible area of the person through the real-time positioning data of the person; simultaneously, transmitting the obtained position probability P of the possible region of the personnel to a GIS space data storage and calculation module (3);
step 3, the GIS spatial data storage and calculation module (3) performs road network overlapping calculation according to the possible personnel regions to obtain the probability Pm of the filtered possible personnel regions;
step 4, judging whether the personnel in the step 3 have the data of the inspection historical library through the personnel inspection historical library (4);
if the personnel in the step 3 have no data in the personnel inspection historical library (4), taking the position of the square area with the maximum probability as the real-time position data of the personnel in the step 3; the optimal position of the person in step 3 is P _ x = max (pm),
if the personnel has the data of the inspection historical library, executing the step 5;
step 5, a continuous period of time before the current time point is obtained through a real-time position data mining and positioning module (5) inquiry personnel inspection historical library (4), road section routes which pass through the continuous period of time before the obtained current time point in historical library data are called, meanwhile, corresponding matched personnel are screened out according to the called road section routes which pass through, and the sequence of the screened corresponding matched personnel passing through the same road section at the previous period of time is recorded;
the historical data are structured according to a time sequence, an X axis represents time, a Y axis represents the distance of a beacon connecting line of each road section, and the distance is accumulated according to the current road section sequence to obtain a time sequence position diagram moving according to time; the method comprises the steps of sequencing by using the projection of a beacon connecting line on a table and the sequence of road sections, simplifying the projection and the sequence into two-dimensional time sequence data according to road network planning, abstracting Y into the distance from a starting point, and enabling X to be natural time;
a regularization path is searched by adopting a time-based dynamic regularization similarity method according to the obtained two-dimensional time sequence data to enable the regularization distance to be minimum;
Figure 4330DEST_PATH_IMAGE002
where ED (Q, C) represents a measure of DTW, Q represents a query sequence, C represents a content sequence,
Figure 249366DEST_PATH_IMAGE004
the value of query sequence Q representing the r-th path match point,
Figure 294683DEST_PATH_IMAGE006
a value of the content sequence C representing the r-th path matching point,
Figure 893154DEST_PATH_IMAGE008
representing the number of path matching points;
setting o historical curves [ C1, C2 and … Co ], wherein the GIS spatial data storage and calculation module (3) in the step 3 carries out road network overlapping calculation according to the possible regions of people, and each square is a query sequence Q [ Q1, Q2, … and Qm ]; the query sequence Q is respectively calculated with the content sequence C to respectively obtain the measures ED (Qm, C1) and … ED (Qm, Co) of DTW; the weights obtained according to the DTW method are:
Dm=-(pre(m)-min(m))/sig(m)*k+1
where Dm denotes a weight obtained according to the DTW method, sig (m) is a standard deviation of the set of data, pre (m) is an average of the set of data, min (m) is a minimum of the set of data, and k is an empirical value;
and (3) taking the moving range of the time difference between the time to be predicted and the current time to obtain the Pm value of the rectangular area at the time point to be predicted, wherein the possible position P _ x of the predicted future time is as follows:
P_x=max(P1*D1，……，Pm*Dm)
where P _ x represents an optimal correction point, m represents m squares, Pm represents the probability of the mth square, and Dm is a weight obtained according to the DTW method.
2. The method of claim 1, wherein the method comprises the following steps: the real-time personnel positioning data in the step 1 comprises a maximum real-time personnel positioning distance max (d), a minimum real-time personnel positioning distance min (d) and an average real-time personnel positioning distance pre (d);
d = pow(10， float((abs(RSSI) - A) / (10 * n)))；
A = (math.log10(d1) * abs(RSSI2) - math.log10(d2) * abs(RSSI1)) / (math.log10(d1) - math.log10(d2)) ；
n = (abs(RSSI1) - abs(RSSI2)) / (10 * (math.log10(d1) - math.log10(d2)))；
wherein d represents a personnel positioning distance, pow represents a POWER function, RSSI represents received signal strength, a represents signal strength when a transmitting end and a receiving end are separated by 1 meter, n represents an environment attenuation factor, two different sets of d values and RSSI values are collected to be respectively (d1, RSSI1) (d2, RSSI2), d1 represents a first set of calculated positioning distance, RSSI1 represents the received signal strength of the first set, d2 represents a second set of calculated positioning distance, RSSI2 represents the received signal strength of the second set, abs represents an absolute value function, and math.log10 represents that a logarithmic function takes 10 as a base.
3. The method of claim 2, wherein the method comprises the following steps: the method for obtaining the position probability P of the possible area of the person by the positioning data of the beacon by the positioning possible area calculation module (2) in the step 2 comprises the following steps:
Figure 973106DEST_PATH_IMAGE010
wherein the content of the first and second substances,Pindicating the probability of the location of the likely region of the person,
Figure 871267DEST_PATH_IMAGE012
for persons
Figure 403880DEST_PATH_IMAGE014
The probability of (a) of (b) being,Mrepresenting the number of people, assuming that the distribution of the beacon statistics is normal, and the maximum and minimum values are betweenIs a function of 12 standard deviations sigma,
σ=(max(d)-min(d))/12；
u=pre(d)；
uindicates expectation and σ indicates standard deviation.
4. The method of claim 3, wherein the method comprises the following steps: in the step 3, a GIS space data storage and calculation module (3) carries out road network overlapping calculation according to possible regions of people:
subdividing the possible region of the person according to a square with the side length of g, and separatingmAnd the squares are calculated by using a probability formula of the possible positioning region calculation module (2) for each square, so that the probability Pm of the possible personnel regions after filtering is obtained.
5. The method of claim 4, wherein the method comprises the following steps: the GIS space data storage and calculation module (3) uses a space database to store map data of an indoor road network and map data of an outdoor road network and all Bluetooth beacon positions, receives possible position ranges of personnel, and then calculates the range of an intersection part by taking intersection with the road network; the receiving person's starting position and destination position calculate a possible travel path.
6. The method of claim 5, wherein the method comprises the following steps: the personnel patrol historical database (4) records historical positioning data of personnel patrol, statistically regulates routes of the personnel, and uses a spatial database of a GIS road network to perform the following segmentation:
firstly, a road network in a GIS space data storage and calculation module (3) is split into a plurality of continuous road sections according to intersections, and the road sections are marked as route (n), wherein n represents the marking sequence on the road network; then, recording beacons on the road section route (n) as a sequence array [ B1, B2, B3, … … Bx ] according to the relative distance, and calling the sequence array as a beacon connecting line;
the statistical regularization method for the routes of the personnel comprises the following steps: the positioning data is: time t, position probability P of possible regions of people; projecting the position probability P of the possible area of the person to a beacon connecting line of the current road section, recording the position probability P as a projection distance rd, and recording the positioning data of a period of time as an array: [ [ t (1), p (1), rd (1), Route (1) ], [ t (2), p (2), rd (2), Route (2) ], [ t (3), p (3), rd (3), Route (3) ], … …, [ t (n), p (n), rd (n), Route (n) ].
7. The method of claim 6, wherein the method comprises the following steps: the side length g of the square in the step 3 is 0.1-0.3 m.
8. The method of claim 7, wherein the method comprises the following steps: the empirical value k in step 5 is 0.1-0.3.
9. The utility model provides a real-time data mining positioning system who combines GIS road network and bluetooth beacon which characterized in that: including GIS spatial data storage and calculation module (3), beacon statistics module (1), personnel patrol and examine historical library (4), the possible regional calculation module of location (2), real-time position data excavate orientation module (5), beacon statistics module (1) is connected with the possible regional calculation module of location (2), real-time position data excavate orientation module (5) respectively, GIS spatial data storage and calculation module (3), personnel patrol and examine historical library (4), the possible regional calculation module of location (2) are connected with real-time position data excavate orientation module (5) respectively, wherein:
the beacon counting module (1) is used for recording the historical beacon positioning data, receiving the beacon data of people when the people walk, and obtaining the real-time person positioning data according to the historical beacon positioning data and the beacon data of the people when the people walk; meanwhile, the obtained real-time positioning data of the person is provided to a possible positioning area calculation module (2);
the possible positioning area calculating module (2) is used for obtaining the position probability P of the possible area of the person through the real-time positioning data of the person; simultaneously, transmitting the obtained position probability P of the possible region of the personnel to a GIS space data storage and calculation module (3);
the GIS spatial data storage and calculation module (3) performs road network overlapping calculation according to the possible personnel regions to obtain filtered possible personnel region probability Pm;
if the personnel in the step 3 have no data in the personnel inspection historical library (4), taking the position of the square area with the maximum probability as the real-time position data of the personnel in the step 3;
if the personnel in the step 3 have the data of the inspection historical library, the data are corrected through a real-time position data mining and positioning module (5);
the real-time position data mining and positioning module (5) is used for inquiring the personnel inspection historical library (4), acquiring a continuous period of time before the current time point, calling road sections which pass through the acquired continuous period of time before the current time point in the historical library data, screening out corresponding matched personnel according to the called road sections which pass through the road sections, and recording the sequence of the screened corresponding matched personnel passing through the same road sections at the previous period of time;
the historical data are structured according to a time sequence, an X axis represents time, a Y axis represents the distance of a beacon connecting line of each road section, and the distance is accumulated according to the current road section sequence to obtain a time sequence position diagram moving according to time; the method comprises the steps of sequencing by using the projection of a beacon connecting line on a table and the sequence of road sections, simplifying the projection and the sequence into two-dimensional time sequence data according to road network planning, abstracting Y into the distance from a starting point, and enabling X to be natural time;
searching a regular path by adopting a time-based dynamic regular similarity method according to the obtained two-dimensional time sequence data to minimize the regular distance;
Figure 806042DEST_PATH_IMAGE016
among them, ED (Q, C)Denotes a measure of DTW, Q denotes a query sequence, C denotes a content sequence,
Figure 740500DEST_PATH_IMAGE018
the value of query sequence Q representing the r-th path match point,
Figure 61760DEST_PATH_IMAGE020
a value of the content sequence C representing the r-th path matching point,
Figure 81669DEST_PATH_IMAGE022
representing the number of path matching points;
setting o historical curves [ C1, C2 and … Co ], wherein the GIS spatial data storage and calculation module (3) in the step 3 carries out road network overlapping calculation according to the possible regions of people, and each square is a query sequence Q [ Q1, Q2, … and Qm ]; the query sequence Q is respectively calculated with the content sequence C to respectively obtain the measures ED (Qm, C1) and … ED (Qm, Co) of DTW; the weights obtained according to the DTW method are:
Dm=-(pre(m)-min(m))/sig(m)*k+1
where Dm denotes a weight obtained according to the DTW method, sig (m) is a standard deviation of the set of data, pre (m) is an average of the set of data, min (m) is a minimum of the set of data, and k is an empirical value;
and (3) taking the moving range of the time difference between the time to be predicted and the current time to obtain the Pm value of the rectangular area at the time point to be predicted, wherein the possible position P _ x of the predicted future time is as follows:
P_x=max(P1*D1，……，Pm*Dm)
where P _ x represents an optimal correction point, m represents m squares, Pm represents the probability of the mth square, and Dm is a weight obtained according to the DTW method.
10. The real-time data mining positioning system combining the GIS road network and the bluetooth beacon as claimed in claim 9, wherein: the method for obtaining the position probability P of the possible area of the person by the positioning data of the beacon by the positioning possible area calculation module (2) comprises the following steps:
Figure 21943DEST_PATH_IMAGE024
wherein the content of the first and second substances,Pindicating the probability of the location of the likely region of the person,
Figure 810907DEST_PATH_IMAGE026
for persons
Figure 240752DEST_PATH_IMAGE028
The probability of (a) of (b) being,Mrepresenting the number of people, assuming that the distribution of the beacon statistics is normal, and 12 standard deviations sigma between the maximum and minimum values,σ=(max(d)-min(d))/12，u= pre(d)，uindicates expectation and σ indicates standard deviation.
CN202210083010.0A 2022-01-25 2022-01-25 Real-time data mining and positioning method combining GIS road network and Bluetooth beacon Active CN114125709B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210083010.0A CN114125709B (en) 2022-01-25 2022-01-25 Real-time data mining and positioning method combining GIS road network and Bluetooth beacon

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210083010.0A CN114125709B (en) 2022-01-25 2022-01-25 Real-time data mining and positioning method combining GIS road network and Bluetooth beacon

Publications (2)

Publication Number Publication Date
CN114125709A true CN114125709A (en) 2022-03-01
CN114125709B CN114125709B (en) 2022-04-15

Family

ID=80360930

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210083010.0A Active CN114125709B (en) 2022-01-25 2022-01-25 Real-time data mining and positioning method combining GIS road network and Bluetooth beacon

Country Status (1)

Country Link
CN (1) CN114125709B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114580798A (en) * 2022-05-09 2022-06-03 南京安元科技有限公司 Device point location prediction method and system based on transformer

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110133587A (en) * 2018-02-08 2019-08-16 上海询诺通信科技发展有限公司 A kind of comprehensive bluetooth localization method and system
CN111914287A (en) * 2020-06-17 2020-11-10 西安交通大学 Improved DTW (delay tolerant W) measurement method for track privacy protection, storage device and equipment
CN112272407A (en) * 2020-12-21 2021-01-26 南京和电科技有限公司 Indoor Bluetooth positioning method and device based on geographic information system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110133587A (en) * 2018-02-08 2019-08-16 上海询诺通信科技发展有限公司 A kind of comprehensive bluetooth localization method and system
CN111914287A (en) * 2020-06-17 2020-11-10 西安交通大学 Improved DTW (delay tolerant W) measurement method for track privacy protection, storage device and equipment
CN112272407A (en) * 2020-12-21 2021-01-26 南京和电科技有限公司 Indoor Bluetooth positioning method and device based on geographic information system

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114580798A (en) * 2022-05-09 2022-06-03 南京安元科技有限公司 Device point location prediction method and system based on transformer

Also Published As

Publication number Publication date
CN114125709B (en) 2022-04-15

Similar Documents

Publication Publication Date Title
CN107766808B (en) Method and system for clustering moving tracks of vehicle objects in road network space
CN102170697B (en) Indoor positioning method and device
CN106931974B (en) Method for calculating personal commuting distance based on mobile terminal GPS positioning data record
CN102521973B (en) A kind of mobile phone switches the road matching method of location
CN110516708B (en) Path prediction method based on track and road network matching
CN112182410B (en) User travel mode mining method based on space-time track knowledge graph
CN109813273B (en) Agricultural machinery repeated operation area judgment method based on spatial analysis
JP2008146249A (en) Probe data analysis system
CN106323301A (en) Road information obtaining method and device
CN108566620B (en) Indoor positioning method based on WIFI
US9515752B2 (en) Method for mapping wi-fi fingerprints by means of blind collection of RSS measurements
CN116797055B (en) Urban road planning method and system based on Internet of things
CN110413855B (en) Region entrance and exit dynamic extraction method based on taxi boarding point
CN114125709B (en) Real-time data mining and positioning method combining GIS road network and Bluetooth beacon
CN113932801A (en) Crowdsourcing-based real-time matching updating method for auxiliary driving map
CN103200390A (en) Method for monitoring indoor object moving track
CN110727714A (en) Resident travel feature extraction method integrating space-time clustering and support vector machine
CN110990661A (en) Interest area entrance and exit extraction method based on road network constraint and density clustering
CN113596989A (en) Indoor positioning method and system for intelligent workshop
CN111698774A (en) Indoor positioning method and device based on multi-source information fusion
CN110636437B (en) Fingerprint pair-based auxiliary positioning method
CN109672986A (en) A kind of space-time big data analysis system
CN107290714B (en) Positioning method based on multi-identification fingerprint positioning
CN110750730B (en) Group detection method and system based on space-time constraint
CN116796904A (en) Method, system, electronic equipment and medium for predicting new line passenger flow of rail transit

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
CP01 Change in the name or title of a patent holder

Address after: 11-14 / F, tower a, Tengfei building, 88 Jiangmiao Road, yanchuangyuan, Jiangbei new district, Nanjing, Jiangsu Province 210000

Patentee after: Anyuan Technology Co.,Ltd.

Address before: 11-14 / F, tower a, Tengfei building, 88 Jiangmiao Road, yanchuangyuan, Jiangbei new district, Nanjing, Jiangsu Province 210000

Patentee before: NANJING ANYUAN TECHNOLOGY Co.,Ltd.

CP01 Change in the name or title of a patent holder