CN116299165A - Bluetooth beacon personnel positioning correction method and system based on positioning card path model - Google Patents

Bluetooth beacon personnel positioning correction method and system based on positioning card path model Download PDF

Info

Publication number
CN116299165A
CN116299165A CN202310549236.XA CN202310549236A CN116299165A CN 116299165 A CN116299165 A CN 116299165A CN 202310549236 A CN202310549236 A CN 202310549236A CN 116299165 A CN116299165 A CN 116299165A
Authority
CN
China
Prior art keywords
positioning
path
model
personnel
path model
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
CN202310549236.XA
Other languages
Chinese (zh)
Other versions
CN116299165B (en
Inventor
王三明
王聪明
胡小敏
赵伟帆
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.)
Qiye Cloud Big Data Nanjing Co ltd
Anyuan Technology Co ltd
Original Assignee
Qiye Cloud Big Data Nanjing Co ltd
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 Qiye Cloud Big Data Nanjing Co ltd, Anyuan Technology Co ltd filed Critical Qiye Cloud Big Data Nanjing Co ltd
Priority to CN202310549236.XA priority Critical patent/CN116299165B/en
Publication of CN116299165A publication Critical patent/CN116299165A/en
Application granted granted Critical
Publication of CN116299165B publication Critical patent/CN116299165B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G01S5/0205—Details
    • G01S5/021—Calibration, monitoring or correction
    • 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
    • H04W4/029—Location-based management or tracking services
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/80—Services using short range communication, e.g. near-field communication [NFC], radio-frequency identification [RFID] or low energy communication
    • 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Position Fixing By Use Of Radio Waves (AREA)

Abstract

The invention discloses a Bluetooth beacon personnel positioning correction method and system based on a positioning card path model, comprising an RSSI (received signal strength indicator) based ranging positioning unit, a path model unit, a correction unit and an output unit, wherein the RSSI is used for performing ranging positioning based on the ranging positioning method; constructing a path model according to the historical positioning data; acquiring Bluetooth beacon personnel data in real time, and predicting positioning point coordinates through a path model according to the Bluetooth beacon personnel data acquired in real time; and correcting the model locating point coordinates obtained by predicting the path model by using the centroid locating point coordinates obtained by obtaining the Bluetooth beacon personnel data in real time through the RSSI based on the ranging locating method to obtain final predicted locating coordinates. The invention evaluates and corrects the error positioning by combining the relation between the credible error and the RSSI and the moving path of the positioning card, so the positioning accuracy is high.

Description

Bluetooth beacon personnel positioning correction method and system based on positioning card path model
Technical Field
The invention relates to a Bluetooth beacon personnel positioning correction method and system based on a positioning card path model, and belongs to the technical field of path positioning planning.
Background
Bluetooth positioning is performed through a triangle centroid positioning algorithm based on RSSI (received signal strength indicator) values, and many mature business applications exist in the fields of aged people positioning, transformer substation personnel positioning, chemical plant personnel positioning, building site personnel positioning and the like.
After the Bluetooth signals are collected by the positioning card, the relevant Bluetooth information is sent to the server through preliminary calculation, and the calculation of a triangle centroid positioning algorithm is carried out.
The accuracy of the Bluetooth beacon is 2-5 meters, and because the triangle centroid algorithm is used, the problems of personnel position negligence, travel route withdrawal, wall penetration and the like can occur in practical application. In the prior art, the optimization scheme for personnel positioning is adopted by common manufacturers to optimize abnormal points by methods of enhancing the deployment density of Bluetooth beacons, increasing the management of the beacons in the same group, taking the average value in a short time and the like, but the schemes basically all require personnel intervention for operation and maintenance, so that the labor cost is increased.
Disclosure of Invention
The invention aims to: in order to overcome the defects in the prior art, the invention provides a high-precision Bluetooth beacon personnel positioning correction method and system based on a positioning card path model.
The technical scheme is as follows: in order to achieve the above purpose, the invention adopts the following technical scheme:
a Bluetooth beacon personnel positioning correction method based on a positioning card path model comprises the following steps:
and step 1, performing ranging positioning by using the RSSI based on a ranging positioning method.
And 2, constructing a path model according to the historical positioning data.
Obtaining a time period based on a ranging positioning method according to RSSI
Figure SMS_2
Calculates the RSSI data of the personnel at each moment
Figure SMS_10
Centroid setpoint coordinates of (c)
Figure SMS_11
Form a path time sequence
Figure SMS_3
，
Figure SMS_4
The number of times of day is indicated,
Figure SMS_7
represent the first
Figure SMS_9
Time information for each time instant. Then a path matrix composed of a plurality of people
Figure SMS_1
Training by using a deep learning model Social LSTM as input, constructing and obtaining a path model,
Figure SMS_5
the number of persons is indicated and,
Figure SMS_6
represent the first
Figure SMS_8
The path time series of the individual persons.
And step 3, acquiring the Bluetooth beacon personnel data in real time, and predicting positioning point coordinates through a path model according to the Bluetooth beacon personnel data acquired in real time.
And 4, correcting an error result.
And (3) correcting the model locating point coordinates obtained in the step (3) according to the path model prediction by using the centroid locating point coordinates obtained by acquiring the Bluetooth beacon personnel data in real time through the RSSI based distance measurement locating method to obtain final predicted locating coordinates.
Preferably: the deep learning model Social LSTM comprises a long-term memory artificial neural network LSTM, an input embedded layer, a Social pooling layer, a tensor embedded layer and an output layer, wherein the input embedded layer is used for
Figure SMS_14
The time position embedding operation obtains an input embedding result, and the social pooling layer is used for carrying out the operation according to the time position
Figure SMS_16
Time of day LSTM hidden layer
Figure SMS_18
Obtaining
Figure SMS_13
Pooling hidden state tensor at moment
Figure SMS_15
The tensor embedding layer is used for pooling hidden state tensors
Figure SMS_17
The tensor embedding result is obtained, the input embedding result and the tensor embedding result are input into the long-short-term memory artificial neural network LSTM through stacking operation, and the hidden layer state is obtained
Figure SMS_19
The output layer is used for carrying out full connection operation and outputting
Figure SMS_12
And predicting a result of the moment.
Preferably: step 2 Path model
Figure SMS_20
Time of day and time of day
Figure SMS_21
The personnel path at the moment is expressed as:
Figure SMS_22
Figure SMS_23
Figure SMS_24
represent the first
Figure SMS_25
The individual is at
Figure SMS_26
The location of the moment.
Preferably: step 3, utilizing a path model to make a time period
Figure SMS_27
Predicting the positioning point of the model to obtain the coordinate of the predicted positioning point of the model
Figure SMS_28
。
Preferably: and 4, obtaining a final predicted positioning coordinate method:
combining map data for each time
Figure SMS_29
Solving through RSSI based on distance measurement positioning method to obtain centroid positioning point coordinates as
Figure SMS_30
The coordinates of the model locating points obtained according to the path model prediction are
Figure SMS_31
When (when)
Figure SMS_32
And
Figure SMS_33
if the distance of (2) exceeds 0.5r
Figure SMS_34
Locating coordinates for final predictions, otherwise
Figure SMS_35
For the final predicted location coordinates, r is the average interval of bluetooth beacon deployments.
Preferably: in the step 1, the method for performing ranging positioning based on the ranging positioning method by using RSSI: according to the path loss model, the distances between the receiving end and the three Bluetooth beacons are calculated respectively by using RSSI values, and the barycenter locating point coordinates are obtained according to the distances between the receiving end and the three Bluetooth beacons.
The Bluetooth beacon personnel positioning and correcting system based on the locator card path model adopts the Bluetooth beacon personnel positioning and correcting method based on the locator card path model, and comprises an RSSI (received signal strength indicator) based ranging and positioning unit, a path model unit, a correcting unit and an output unit, wherein:
the RSSI based ranging positioning unit is used for performing ranging positioning through an RSSI based ranging positioning method.
The path model unit is used for obtaining a time period based on a ranging positioning method according to the RSSI
Figure SMS_37
Calculates the RSSI data of the personnel at each moment
Figure SMS_40
Centroid setpoint coordinates of (c)
Figure SMS_42
Form a path time sequence
Figure SMS_36
，
Figure SMS_39
The number of times of day is indicated,
Figure SMS_41
represent the first
Figure SMS_44
Time information for each time instant. Then a path matrix composed of a plurality of people
Figure SMS_38
Training by using a deep learning model Social LSTM as input, constructing and obtaining a path model,
Figure SMS_43
the number of persons is indicated and,
Figure SMS_45
represent the first
Figure SMS_46
The path time series of the individual persons.
The correction unit is used for correcting the coordinates of the centroid locating point obtained by acquiring the data of the Bluetooth beacon personnel in real time through the RSSI based on the ranging locating method to the coordinates of the model locating point obtained according to the prediction of the path model, so as to obtain the final predicted locating coordinates.
The output unit is used for outputting final predicted positioning coordinates.
Preferably: the path model unit comprises a deep learning model Social LSTM module, the deep learning model Social LSTM module comprises a long-term and short-term memory artificial neural network LSTM, an input embedded layer, a Social pooling layer, a tensor embedded layer and an output layer, and the input embedded layer is used for
Figure SMS_48
The time position embedding operation obtains an input embedding result, and the social pooling layer is used for carrying out the operation according to the time position
Figure SMS_50
Temporal LSTM hidden layerStatus of
Figure SMS_52
Obtaining
Figure SMS_49
Pooling hidden state tensor at moment
Figure SMS_51
The tensor embedding layer is used for pooling hidden state tensors
Figure SMS_53
The tensor embedding result is obtained, the input embedding result and the tensor embedding result are input into the long-short-term memory artificial neural network LSTM through stacking operation, and the hidden layer state is obtained
Figure SMS_54
The output layer is used for carrying out full connection operation and outputting
Figure SMS_47
And predicting a result of the moment.
Compared with the prior art, the invention has the following beneficial effects:
the invention evaluates and corrects the error positioning by the relation between the trusted error and the RSSI and by collecting data for a plurality of times and combining the moving path of the positioning card, thus the positioning accuracy is high.
Drawings
FIG. 1 is a schematic flow chart of the present invention.
FIG. 2 is a Social LSTM time step
Figure SMS_55
Is a schematic diagram of the operation of (a).
Fig. 3 is a schematic diagram of a Social LSTM hidden layer.
Fig. 4 is a near-term time period anchor point coordinate.
Detailed Description
The present invention is further illustrated in the accompanying drawings and detailed description which are to be understood as being merely illustrative of the invention and not limiting of its scope, and various equivalent modifications to the invention will fall within the scope of the appended claims to the skilled person after reading the invention.
A Bluetooth beacon personnel positioning correction method based on a positioning card path model, as shown in figure 1, comprises the following steps:
and step 1, performing ranging positioning by using the RSSI based on a ranging positioning method.
According to the path loss model, the distances between the receiving end and the three Bluetooth beacons are calculated respectively by using the RSSI values, and three circles can be drawn by taking the Bluetooth beacons as circle centers and the corresponding distances as radiuses. Because of the loss of Bluetooth signals, three circles are generally not intersected at one point, the circle centers of the two circles and the intersection point of the two circles are connected, the intersection point of the two straight lines is a strategy point, three strategy points can be obtained by the three circles, the connection line of the strategy points is a triangular area, and the centroid of the area is the required coordinate position of the to-be-positioned point (namely, a triangle centroid method), namely, the centroid positioning point coordinate obtained according to the distance between the receiving end and the three Bluetooth beacons.
And 2, constructing a path model according to the historical positioning data.
As shown in fig. 2 and 3, the time period is obtained based on the ranging positioning method according to the RSSI
Figure SMS_57
Calculates the RSSI data of the personnel at each moment
Figure SMS_59
Centroid setpoint coordinates of (c)
Figure SMS_61
Form a path time sequence
Figure SMS_58
，
Figure SMS_60
The number of times of day is indicated,
Figure SMS_62
represent the first
Figure SMS_63
Time information for each time instant. Then a path matrix composed of a plurality of people
Figure SMS_56
Training by using a deep learning model Social LSTM as input, constructing and obtaining a path model,
Figure SMS_64
the number of persons is indicated and,
Figure SMS_65
represent the first
Figure SMS_66
The path time series of the individual persons.
The deep learning model Social LSTM comprises LSTM (long short term memory artificial neural network), a first full-connection layer (input embedded layer), a Social pooling layer, a second full-connection layer (tensor embedded layer), and a third full-connection layer (output layer), wherein the first full-connection layer is used for
Figure SMS_68
The time position embedding operation obtains an input embedding result, and the social pooling layer is used for carrying out the operation according to the time position
Figure SMS_70
Time of day LSTM hidden layer
Figure SMS_73
Obtaining
Figure SMS_69
Pooling hidden state tensor at moment
Figure SMS_71
The second full connection layer is used for pooling hidden state tensors
Figure SMS_75
To obtain tensor embedding result, the input embedding result andinputting the tensor embedded result into LSTM through stacking operation, said
Figure SMS_76
Hidden layer state of time
Figure SMS_67
I.e. hidden layer state of LSTM, said hidden layer state
Figure SMS_72
Performing full connection operation through the third full connection layer, and outputting
Figure SMS_74
And predicting a result of the moment.
In a path model
Figure SMS_77
Time of day and time of day
Figure SMS_78
The personnel path at the moment is expressed as:
Figure SMS_79
Figure SMS_80
Figure SMS_81
represent the first
Figure SMS_82
The individual is at
Figure SMS_83
The location of the moment.
And step 3, acquiring the Bluetooth beacon personnel data in real time, and predicting positioning point coordinates through a path model according to the Bluetooth beacon personnel data acquired in real time.
As shown in FIG. 4, the path model is utilized for the time period
Figure SMS_84
Predicting the positioning point of the model to obtain the coordinate of the predicted positioning point of the model
Figure SMS_85
。
And 4, correcting an error result.
And (3) correcting the model locating point coordinates obtained in the step (3) according to the path model prediction by using the centroid locating point coordinates obtained by acquiring the Bluetooth beacon personnel data in real time through the RSSI based distance measurement locating method to obtain final predicted locating coordinates.
Combining map data for each time
Figure SMS_86
Solving through RSSI based on distance measurement positioning method to obtain centroid positioning point coordinates as
Figure SMS_87
The coordinates of the model locating points obtained according to the path model prediction are
Figure SMS_88
When (when)
Figure SMS_89
And
Figure SMS_90
if the distance of (2) exceeds 0.5r
Figure SMS_91
Locating coordinates for final predictions, otherwise
Figure SMS_92
For the final predicted location coordinates, r is the average interval of bluetooth beacon deployments.
The Bluetooth beacon personnel positioning and correcting system based on the locator card path model adopts the Bluetooth beacon personnel positioning and correcting method based on the locator card path model, and comprises an RSSI (received signal strength indicator) based ranging and positioning unit, a path model unit, a correcting unit and an output unit, wherein:
the RSSI based ranging positioning unit is used for performing ranging positioning through an RSSI based ranging positioning method.
The path model unit is used for obtaining a time period based on a ranging positioning method according to the RSSI
Figure SMS_95
Calculates the RSSI data of the personnel at each moment
Figure SMS_96
Centroid setpoint coordinates of (c)
Figure SMS_99
Form a path time sequence
Figure SMS_94
，
Figure SMS_97
The number of times of day is indicated,
Figure SMS_101
represent the first
Figure SMS_102
Time information for each time instant. Then a path matrix composed of a plurality of people
Figure SMS_93
Training by using a deep learning model Social LSTM as input, constructing and obtaining a path model,
Figure SMS_98
the number of persons is indicated and,
Figure SMS_100
represent the first
Figure SMS_103
The path time series of the individual persons.
The path model unit comprises a deep learning model Social LSTM module, and the deep learning model Social LSTM module comprises LSTM (long-short-term memory artificial neural network)A first full connection layer (input embedded layer), a social pooling layer, a second full connection layer (tensor embedded layer), and a third full connection layer (output layer), the first full connection layer is used for
Figure SMS_105
The time position embedding operation obtains an input embedding result, and the social pooling layer is used for carrying out the operation according to the time position
Figure SMS_109
Time of day LSTM hidden layer
Figure SMS_112
Obtaining
Figure SMS_106
Pooling hidden state tensor at moment
Figure SMS_107
The second full connection layer is used for pooling hidden state tensors
Figure SMS_110
Obtaining tensor embedding results, wherein the input embedding results and tensor embedding results are input into LSTM through stacking operation, and the
Figure SMS_113
Hidden layer state of time
Figure SMS_104
I.e. hidden layer state of LSTM, said hidden layer state
Figure SMS_108
Performing full connection operation through the third full connection layer, and outputting
Figure SMS_111
And predicting a result of the moment.
The correction unit is used for correcting the coordinates of the centroid locating point obtained by acquiring the data of the Bluetooth beacon personnel in real time through the RSSI based on the ranging locating method to the coordinates of the model locating point obtained according to the prediction of the path model, so as to obtain the final predicted locating coordinates.
The output unit is used for outputting final predicted positioning coordinates.
The model of the data can gradually fix some core parameters through long-term accumulation, so that the prediction precision is further improved. The path model is more effective in a unidirectional moving scene. The invention can be used for hysteresis repair.
The foregoing is only a preferred embodiment of the invention, it being 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 present invention, and such modifications and adaptations are intended to be comprehended within the scope of the invention.

Claims (8)

1. A Bluetooth beacon personnel positioning correction method based on a positioning card path model is characterized by comprising the following steps:
step 1, performing ranging positioning by using RSSI based on a ranging positioning method;
step 2, constructing a path model according to the historical positioning data;
obtaining a time period based on a ranging positioning method according to RSSI
Figure QLYQS_2
Is calculated for each time instant +.>
Figure QLYQS_7
Barycenter setpoint coordinates->
Figure QLYQS_10
Form a path time sequence +.>
Figure QLYQS_3
，/>
Figure QLYQS_6
Indicating the number of moments>
Figure QLYQS_9
Indicate->
Figure QLYQS_11
Time information of each moment; then a path matrix composed of a plurality of people
Figure QLYQS_1
Training with deep learning model Social LSTM as input, constructing and obtaining path model,/->
Figure QLYQS_4
Indicating the number of people->
Figure QLYQS_5
Indicate->
Figure QLYQS_8
A path time series of individuals;
step 3, acquiring the Bluetooth beacon personnel data in real time, and predicting positioning point coordinates through a path model according to the Bluetooth beacon personnel data acquired in real time;
step 4, correcting an error result;
and (3) correcting the model locating point coordinates obtained in the step (3) according to the path model prediction by using the centroid locating point coordinates obtained by acquiring the Bluetooth beacon personnel data in real time through the RSSI based distance measurement locating method to obtain final predicted locating coordinates.
2. The bluetooth beacon personnel location correction method based on the locator card path model according to claim 1, wherein the method comprises the following steps: the deep learning model Social LSTM comprises a long-term memory artificial neural network LSTM, an input embedded layer, a Social pooling layer, a tensor embedded layer and an output layer, wherein the input embedded layer is used for
Figure QLYQS_13
The position embedding operation of the moment obtains an input embedding result, and the social pooling layer is used for carrying out the method according to +.>
Figure QLYQS_15
LSTM hidden layer state at time->
Figure QLYQS_17
Obtain->
Figure QLYQS_14
Time-of-day pooling hidden state tensor +.>
Figure QLYQS_16
The tensor embedding layer is used for pooling hidden state tensors->
Figure QLYQS_18
The tensor embedding result is obtained, the input embedding result and the tensor embedding result are input into the long-short-term memory artificial neural network LSTM through stacking operation, and the hidden layer state is->
Figure QLYQS_19
The output layer is used for carrying out full connection operation and outputting +.>
Figure QLYQS_12
And predicting a result of the moment.
3. The bluetooth beacon personnel location correction method based on the locator card path model according to claim 2, wherein: step 2 Path model
Figure QLYQS_20
Time and->
Figure QLYQS_21
The personnel path at the moment is expressed as:
Figure QLYQS_22
Figure QLYQS_23
Figure QLYQS_24
indicate->
Figure QLYQS_25
Personnel are->
Figure QLYQS_26
The location of the moment.
4. The bluetooth beacon personnel location correction method based on the locator card path model according to claim 3, wherein: step 3, utilizing a path model to make a time period
Figure QLYQS_27
Predicting the positioning point of the model to obtain the coordinate of the predicted positioning point of the model +.>
Figure QLYQS_28
。
5. The bluetooth beacon personnel location correction method based on the locator card path model according to claim 4, wherein: and 4, obtaining a final predicted positioning coordinate method:
combining map data for each time
Figure QLYQS_29
Solving through RSSI based on distance measurement positioning method to obtain centroid positioning point coordinate as +.>
Figure QLYQS_30
The coordinates of a model locating point obtained by prediction according to the path model are +.>
Figure QLYQS_31
When->
Figure QLYQS_32
And->
Figure QLYQS_33
If the distance of (2) exceeds 0.5r
Figure QLYQS_34
Positioning coordinates for final prediction, otherwise +.>
Figure QLYQS_35
For the final predicted location coordinates, r is the average interval of bluetooth beacon deployments.
6. The bluetooth beacon personnel location correction method based on the locator card path model according to claim 5, wherein the method comprises the following steps: in the step 1, the method for performing ranging positioning based on the ranging positioning method by using RSSI: according to the path loss model, the distances between the receiving end and the three Bluetooth beacons are calculated respectively by using RSSI values, and the barycenter locating point coordinates are obtained according to the distances between the receiving end and the three Bluetooth beacons.
7. A bluetooth beacon personnel location correction system based on locator card path model, its characterized in that: the bluetooth beacon personnel positioning correction method based on the positioning card path model according to claim 1, comprising an RSSI based ranging positioning unit, a path model unit, a correction unit and an output unit, wherein:
the RSSI based ranging positioning unit is used for performing ranging positioning through an RSSI based ranging positioning method;
the path model unit is used for obtaining a time period based on a ranging positioning method according to the RSSI
Figure QLYQS_37
Is calculated for each time instant +.>
Figure QLYQS_41
Barycenter setpoint coordinates->
Figure QLYQS_44
Form a path time sequence
Figure QLYQS_38
，/>
Figure QLYQS_40
Indicating the number of moments>
Figure QLYQS_43
Indicate->
Figure QLYQS_46
Time information of each moment; then a path matrix composed of a plurality of persons is +.>
Figure QLYQS_36
Training with deep learning model Social LSTM as input, constructing and obtaining path model,/->
Figure QLYQS_39
Indicating the number of people->
Figure QLYQS_42
Indicate->
Figure QLYQS_45
A path time series of individuals;
the correction unit is used for correcting the coordinates of the locating point of the model, which are obtained according to the prediction of the path model, of the centroid locating point, which is obtained by acquiring the data of the Bluetooth beacon personnel in real time, through the RSSI based on the ranging locating method, so as to obtain the final predicted locating coordinate;
the output unit is used for outputting final predicted positioning coordinates.
8. The locator card path model-based bluetooth beacon personnel location correction system according to claim 7, wherein: the saidThe path model unit comprises a deep learning model Social LSTM module, wherein the deep learning model Social LSTM module comprises a long-term and short-term memory artificial neural network LSTM, an input embedded layer, a Social pooling layer, a tensor embedded layer and an output layer, and the input embedded layer is used for
Figure QLYQS_48
The position embedding operation of the moment obtains an input embedding result, and the social pooling layer is used for carrying out the method according to +.>
Figure QLYQS_50
LSTM hidden layer state at time->
Figure QLYQS_53
Obtain->
Figure QLYQS_49
Time-of-day pooling hidden state tensor +.>
Figure QLYQS_51
The tensor embedding layer is used for pooling hidden state tensors->
Figure QLYQS_52
The tensor embedding result is obtained, the input embedding result and the tensor embedding result are input into the long-short-term memory artificial neural network LSTM through stacking operation, and the hidden layer state is->
Figure QLYQS_54
The output layer is used for carrying out full connection operation and outputting +.>
Figure QLYQS_47
And predicting a result of the moment.
CN202310549236.XA 2023-05-16 2023-05-16 Bluetooth beacon personnel positioning correction method and system based on positioning card path model Active CN116299165B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310549236.XA CN116299165B (en) 2023-05-16 2023-05-16 Bluetooth beacon personnel positioning correction method and system based on positioning card path model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310549236.XA CN116299165B (en) 2023-05-16 2023-05-16 Bluetooth beacon personnel positioning correction method and system based on positioning card path model

Publications (2)

Publication Number Publication Date
CN116299165A true CN116299165A (en) 2023-06-23
CN116299165B CN116299165B (en) 2023-08-29

Family

ID=86830871

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310549236.XA Active CN116299165B (en) 2023-05-16 2023-05-16 Bluetooth beacon personnel positioning correction method and system based on positioning card path model

Country Status (1)

Country Link
CN (1) CN116299165B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108616812A (en) * 2017-01-20 2018-10-02 武汉金石猫眼科技有限公司 Positioning of mobile equipment and tracing system based on deep learning and its application method
CN110913338A (en) * 2019-12-17 2020-03-24 深圳奇迹智慧网络有限公司 Positioning track correction method and device, computer equipment and storage medium
US20210012180A1 (en) * 2019-07-10 2021-01-14 Swisscom Ag Methods and systems for low power wide area network localization
CN114462667A (en) * 2021-12-20 2022-05-10 上海智能网联汽车技术中心有限公司 SFM-LSTM neural network model-based street pedestrian track prediction method

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108616812A (en) * 2017-01-20 2018-10-02 武汉金石猫眼科技有限公司 Positioning of mobile equipment and tracing system based on deep learning and its application method
US20210012180A1 (en) * 2019-07-10 2021-01-14 Swisscom Ag Methods and systems for low power wide area network localization
CN110913338A (en) * 2019-12-17 2020-03-24 深圳奇迹智慧网络有限公司 Positioning track correction method and device, computer equipment and storage medium
CN114462667A (en) * 2021-12-20 2022-05-10 上海智能网联汽车技术中心有限公司 SFM-LSTM neural network model-based street pedestrian track prediction method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
朱晓君等: "基于RSSI的室内蓝牙定位的设计与实现", 《物联网技术》, pages 22 - 26 *

Also Published As

Publication number Publication date
CN116299165B (en) 2023-08-29

Similar Documents

Publication Publication Date Title
CN107045673B (en) Public bicycle flow variation prediction method based on stack model fusion
CN103955009B (en) A kind of method extracting Objective Typhoon forecast information from numerical forecasting product
CN105206057B (en) Detection method and system based on Floating Car resident trip hot spot region
CN107193060B (en) A kind of multipath Typhoon Storm Surge Over method for quick predicting and system
KR20200006167A (en) Vessel automatic tracking method and system based on deep learning network and average movement
CN113919231B (en) PM2.5 concentration space-time change prediction method and system based on space-time diagram neural network
CN108983320A (en) A kind of numerical weather forecast-artificial intelligence coupling prediction method of coastal typhoon Maximum wind speed
CN110910440B (en) Power transmission line length determination method and system based on power image data
CN110991690A (en) Multi-time wind speed prediction method based on deep convolutional neural network
CN110675494A (en) Three-dimensional visualization optimization method for wind turbine position of wind power plant
CN110009037A (en) A kind of engineering wind speed Forecasting Approach for Short-term and system based on physical message coupling
CN112069573A (en) City group space simulation method, system and equipment based on cellular automaton
CN105574593A (en) Track state static-state detection and control system and method based on cloud computing and big data
CN110414359A (en) The analysis of long distance pipeline unmanned plane inspection data and management method and system
CN113298295B (en) Meteorological forecast system for power production
CN109978275A (en) A kind of extreme wind wind speed forecasting method and system mixing CFD and deep learning
CN103914737B (en) A kind of existing the weather information computational methods of power transmission and transformation line full line
CN105654151B (en) A kind of workpiece localization method and positioning system
CN115585731A (en) Space-air-ground integrated hydropower station space state intelligent monitoring management system and method thereof
CN116299165B (en) Bluetooth beacon personnel positioning correction method and system based on positioning card path model
CN107133636B (en) Method and system for obtaining similar typhoons
CN112215416B (en) Intelligent planning inspection route system and method
CN116664095B (en) Security inspection prediction method based on deep learning
CN105489010A (en) System and method for monitoring and analyzing fast road travel time reliability
CN115905997B (en) Wind turbine generator meteorological disaster early warning method and system based on prediction deviation optimization

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