CN112800166B - Community correction object activity track supervision and early warning method, system and device - Google Patents

Community correction object activity track supervision and early warning method, system and device Download PDF

Info

Publication number
CN112800166B
CN112800166B CN202110380829.9A CN202110380829A CN112800166B CN 112800166 B CN112800166 B CN 112800166B CN 202110380829 A CN202110380829 A CN 202110380829A CN 112800166 B CN112800166 B CN 112800166B
Authority
CN
China
Prior art keywords
activity
track
community correction
correction object
parameters
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.)
Active
Application number
CN202110380829.9A
Other languages
Chinese (zh)
Other versions
CN112800166A (en
Inventor
陈冲
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.)
Hunan Judicial Police Vocational College
Original Assignee
Hunan Judicial Police Vocational College
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 Hunan Judicial Police Vocational College filed Critical Hunan Judicial Police Vocational College
Priority to CN202110380829.9A priority Critical patent/CN112800166B/en
Publication of CN112800166A publication Critical patent/CN112800166A/en
Application granted granted Critical
Publication of CN112800166B publication Critical patent/CN112800166B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • 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
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • 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
    • G06F16/25—Integrating or interfacing systems involving database management systems
    • 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
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y20/00—Information sensed or collected by the things
    • G16Y20/10—Information sensed or collected by the things relating to the environment, e.g. temperature; relating to location
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y20/00—Information sensed or collected by the things
    • G16Y20/40—Information sensed or collected by the things relating to personal data, e.g. biometric data, records or preferences
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/10—Detection; Monitoring
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/20—Analytics; Diagnosis
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/50—Safety; Security of things, users, data or systems
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/60—Positioning; Navigation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Remote Sensing (AREA)
  • Signal Processing (AREA)
  • Tourism & Hospitality (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Biomedical Technology (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Computer Security & Cryptography (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Computational Linguistics (AREA)
  • Environmental & Geological Engineering (AREA)
  • Toxicology (AREA)
  • Alarm Systems (AREA)
  • Train Traffic Observation, Control, And Security (AREA)

Abstract

The invention discloses a method, a system and a device for supervising and early warning of activity tracks of community correction objects, wherein a plurality of preset activity tracks are formed by collecting relevant information of the community correction objects, the actual activity tracks of the community correction objects are obtained through a Beidou positioning system, and the similarity between the preset activity tracks and the actual activity tracks is determined; traversing position parameters and corresponding time length parameters which are coincident with bus stations, railway stations, airports, high-speed entrances and the like in the actual activity track of the community correction object, and calculating a specific site calibration coefficient; the virtual track line is obtained by calculating the variation trend of the actual moving track, the distance between the end point of the actual moving track and the intersection point of the virtual track line and the safety fence is calculated, and whether the actual moving track is abnormal or not is judged by setting a corresponding threshold value. The invention also discloses a system and a device for realizing the method. The method and the device can predict whether the activity track of the community correction object is abnormal in advance, and have high calculation accuracy and simple and convenient calculation.

Description

Community correction object activity track supervision and early warning method, system and device
Technical Field
The invention relates to the technical field of intelligent monitoring, in particular to a method, a system and a device for monitoring and early warning of activity tracks of community correction objects.
Background
In China, community correction refers to non-prohibited criminal execution activities implemented by criminals with lighter criminal behaviors aiming at four types of criminals controlled, declared and delayed, adjudicated and released and temporarily executed outside prison, the movable range of a community correction object is different according to the criminal condition of the community correction object, and the community correction object cannot leave a residential city or county without approval according to the provisions of twenty-seventh article of the community correction law and twenty-sixth article of the community correction implementation method. All actions that are not approved to leave a particular range are violations.
Along with the promulgation and implementation of a community correction method, higher requirements are provided for the supervision of strengthening community correction objects, the supervision of the community correction objects in the prior art is mainly positioned through a Beidou positioning system, the positions of the community correction objects are monitored only according to the position information of the Beidou positioning system, the mode can be discovered by a supervisor after the community correction objects exceed the limited region for a certain time due to the fact that navigation signal transmission is delayed, therefore, only the post supervision can be achieved, early warning can not be performed in advance according to an activity track, the supervisor is reminded, and the collected positioning data information amount is huge, if key parameters are not extracted in a targeted mode, the calculation is carried out step by step, the calculation is complex, and the operation efficiency is low.
In addition, the community correction object is different from a person to be monitored or other objects in a relatively closed environment, and the activity range of the community correction object is very large, so that the existing monitoring method for the monitored object generally adopts detection devices such as an infrared sensor, a camera and a radar, and then monitors the monitored object according to information collected by the detection devices. This and similar approaches are not suitable for supervision of community correction subjects, since the detection devices cannot be installed in a wide range.
Disclosure of Invention
(1) Technical problem to be solved
The invention aims to provide a method, a system and a device for supervising and early warning of the activity track of a community correction object, aiming at overcoming the defects of the prior art, effectively pre-judging whether the activity track of the community correction object is abnormal or not in advance according to the behavior of the community correction object, and then timely sending early warning information to a supervisor and the community correction object.
(2) Technical scheme
The invention provides a supervision and early warning method for an activity track of a community correction object, which comprises the following steps:
step 1, constructing a vector map, and marking position coordinates of a specific place in the vector map;
step 2, setting a safety fence in the vector map according to the moving range of the community correction object to obtain an area map;
step 3, collecting multi-dimensional data of community correction objects, importing the multi-dimensional data into the regional map to generate a plurality of preset activity tracks (i); wherein i is more than or equal to 1;
step 4, obtaining activity parameters of the community correction object based on the Beidou positioning system, wherein the activity parameters comprise: generating an actual movement track according to the position parameters and the corresponding time length parameters;
step 5, calculating the similarity values D (i) of the actual motion track and the plurality of preset motion tracks one by one to obtain the minimum similarity value DminIf D isminIf the similarity is smaller than the similarity threshold value, the activity track is considered to be normal, the step 4 is entered, and if D is smaller than the similarity threshold valueminIf the similarity is greater than the similarity threshold, entering step 6;
step 6, traversing position parameters in the activity parameters, extracting position points coincident with the specific places, and then calculating specific place calibration coefficients P according to time length parameters corresponding to the position points, wherein the calibration coefficients P are obtained by superposing the values of the position points, wherein the value of the calibration coefficient P is 1 when the position points stay for a certain time length, and if the value of P is greater than a specific place calibration threshold, the activity track is considered to be abnormal, and the step 8 is entered; and if the P is smaller than the specific site calibration threshold, entering a step 7.
Step 7, calculating the variation trend of the actual activity track to obtain a distance parameter T from the end point of the actual activity track to the safety fence, if the T is greater than a distance parameter threshold value, considering the activity track to be normal, entering step 4, and if the T is less than the distance threshold value, considering the activity track to be abnormal, entering step 8;
and 8, if the activity track is judged to be abnormal, feeding back early warning information to the supervisor and the community correction object.
Further, the specific places comprise bus stops, railway stations, airports, docks and high-speed entrances, and the regional map refers to a vector map within a security fence range and mainly comprises a city map and a district-county map.
Further, the multidimensional data comprise residence places, working units and travel modes, the travel modes comprise walking, public transportation and driving, and a plurality of preset activity tracks are obtained according to different travel modes.
Further, the similarity calculation method adopts a Huasdorff distance algorithm.
Further, the location-specific calibration coefficient P is calculated according to the following formula:
P=
Figure 408017DEST_PATH_IMAGE001
，
wherein, PkRepresenting the position points coincident with bus stops, train stations, airports, docks and high-speed entrances in the activity parameters of the community rectification objects, and when there are coincident position points, PkValue is 1, otherwise 0, PkRepresented by a 5 x 5 diagonal matrix;
hkthe time length of the residence of the community correction object on the overlapped position point is represented, wherein the value is 0 when the community correction object stays at a bus stop, a railway station, an airport and a wharf for 0-5 minutes, and the value is 1 when the community correction object stays for more than 5 minutes; when the time length of the residence at the high-speed inlet is 0-2 minutes, the value is 0, and when the residence time exceeds 2 minutes, the value is 1, hkRepresented by a 5 x 5 diagonal matrix; the site specific calibration threshold is set to 1.
Further, calculating the variation trend of the actual activity track to obtain a distance parameter T from the end point of the actual activity track to the security fence, specifically: calculating the change trend of the movable track according to the actual movable track, obtaining a virtual track line intersected with the safety fence along the direction of the change trend, and calculating a distance parameter T according to the terminal point coordinate of the actual movable track and the intersection point coordinate of the virtual track line and the safety fence, wherein the calculation formula is as follows:
T=
Figure 179664DEST_PATH_IMAGE002
，
wherein T isbyY coordinate value, Tb, representing the point of intersection b of the virtual trajectory line with the security fencexAn x-coordinate value representing the intersection b of the virtual trajectory line and the safety fence; tayY coordinate value, Ta, representing the end of the actual motion trajectoryxAnd x-coordinate value representing the actual motion track endpoint.
Further, the minimum similarity value D is calculatedminCalculated according to the formula Dmin=min（D（i））。
The invention also discloses a monitoring and early warning system for the activity track of the community correction object, which comprises,
the map module is used for constructing a vector map and marking the position coordinates of a specific place in the vector map;
the security fence module is used for dividing boundaries in the vector map according to the moving range of the community correction object so as to obtain maps of different areas;
the information acquisition module is used for acquiring personal multidimensional data of a community correction object to generate a preset activity track;
the positioning module is used for acquiring activity parameters of the community correction object based on the Beidou positioning system, and the activity parameters comprise: generating an actual movement track according to the position parameters and the time length parameters;
a similarity calculation module for calculating the similarity between the actual motion track and the preset motion tracks one by one and extracting the minimum value D of the similaritymin；
The precise analysis module is used for traversing the position parameters in the activity parameters to obtain position points coincident with the specific places, calculating a calibration coefficient P of the specific places according to the corresponding time length parameters, and calculating a distance parameter T from a track end point to the security fence according to the variation trend of the actual activity track;
and the information communication module is used for feeding back the early warning information to the manager and the community correction object.
The invention also discloses computer equipment which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the monitoring and early warning method for the activity track of the community correction object when executing the computer program.
(3) Advantageous effects
The invention sets a preset activity track, based on the preset activity track, based on a Beidou positioning system, obtains activity parameters of community correction objects, generates an actual activity track, firstly compares the actual activity track with the preset activity track for judgment, then calculates a calibration coefficient of a specific place according to a position point which is coincident with the position of the specific place in the activity parameters and combines with a corresponding time length parameter for judgment, and finally calculates a distance parameter for judgment by analyzing the variation trend of the actual activity track, thereby obtaining the following beneficial effects:
1. according to the behavior of the community correction object, whether the activity track is abnormal or not is judged in advance, and an early warning message is sent to a supervisor and the community correction object in advance, so that the problem of untimely supervision caused by navigation signal delay is solved.
2. According to the difficulty degree of calculation, the thinking of easiness before difficulty is adopted, and the similarity of the activity track, the calibration coefficient of a specific place and the distance parameter are calculated in sequence to judge whether the activity track is abnormal or not, so that the complexity of calculation of all parameters is avoided, and the calculation efficiency is improved.
3. The time length corresponding to the position point coincident with the specific place is considered, the situations of passing, waiting for traffic lights and the like are eliminated, and the early warning accuracy is improved. In addition, the particularity of the specific place of the high-speed entrance is particularly considered, and the early warning accuracy is further improved.
4. The consideration of the factor of the change trend of the actual activity track is introduced, the behavior of the community correction object is considered in a multi-dimensional mode, and the early warning accuracy is further improved.
Drawings
FIG. 1 is a flow chart of a monitoring and early warning method for the movement track of a community correction object
FIG. 2 is a schematic view of a pre-determined motion trajectory and a safety fence
FIG. 3 is a schematic diagram of the calculation of similarity by the Huasdorff distance algorithm
FIG. 4 is a schematic diagram of an analysis of the trend of the actual moving track
FIG. 5 is a schematic diagram of a monitoring and early warning system for community correction objects
Detailed Description
The embodiments of the present invention will be described in further detail with reference to the drawings and examples. The following detailed description of the embodiments and the accompanying drawings are provided to illustrate the principles of the invention and are not intended to limit the scope of the invention, i.e., the invention is not limited to the described embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
According to the regulations of relevant laws and regulations, the object to be subjected to community correction can only move in a specific area and can not exceed a limited area, and in real life, a part of the community correction object can exceed the limited area intentionally or unintentionally. The community correction object out-of-limit-area activities mainly comprise two situations, one is subjectively wanted to be out of the limit area activities, and the other is careless out-of-limit-area activities, such as more common out-of-limit-area activities to other cities due to human and animal situations. In these situations, the escape from the restricted area activity can be avoided by pre-judging in advance and then reminding.
The invention discloses a monitoring and early warning method for an activity track of a community correction object, which is mainly used for monitoring and managing the activity parameter of the community correction object by analyzing the activity parameter of the community correction object so as to realize the effect of early warning. As shown in fig. 1-4, the method specifically comprises the following steps:
step 1, constructing a vector map, and marking the position coordinates of a specific place in the vector map.
Vehicles such as long-distance buses, high-speed rails, trains, airplanes and ferries are common modes for cross-regional travel, so that bus stations, train stations, airports and docks are mainly concerned when monitoring community correction objects, and if the community correction objects frequently come in and go out in the places or stay for too long time, the monitoring is highly concerned. Based on the method, places such as bus stations, railway stations, airports, docks and the like are listed as specific places, and position coordinates are marked in a vector map for analyzing the movement track of the community correction object.
In addition, going to other cities through a highway is a common travel mode at present, so that a high-speed entrance also serves as one of specific places, and the factor is always ignored. The invention lists the high-speed entrance as one of specific places and marks the position coordinate in the vector map, thereby ensuring that the accuracy of the supervision early warning result is higher. However, the high-speed entrance still has great difference from traveling in other specific places, and needs to be treated separately when taking values, which will be described in detail in the following steps.
And 2, setting a safety fence in the vector map according to the moving range of the community correction object to obtain an area map.
Specifically, as shown in fig. 2, a boundary is defined in the established vector map according to the activity range of the community correction object, the boundary is a security fence, the area in the security fence is the area map according to the present invention, and the community correction object exceeding the security fence violates the relevant regulations. The safety fence is determined to have two meanings, on one hand, the safety fence is monitored and early-warned by community correction objects and can also be considered as a starting point of the whole scheme. On the other hand, after the security fence is defined, the region outside the security fence is not considered, so that the complexity of calculation is simplified, and the efficiency is improved.
The different regional maps mainly comprise a city region and a district-county region, wherein the city region refers to a certain local-level city range, and the district-county region refers to a district or county-level range. Of course, extension to the provincial range is also possible as desired.
Step 3, collecting multi-dimensional data of community correction objects, importing the multi-dimensional data into the regional map to generate a plurality of preset activity tracks (i); wherein i is greater than or equal to 1.
The invention is not limited herein, but more importantly, the invention also requires collecting the travel modes of the community correction object from the residence to the working unit or the frequent place, such as walking, public transportation or driving, from one place to another, and different travel modes can form different activity tracks on the regional map. The purpose of collecting the travel mode is to obtain different daily activity tracks of community correction objects, the daily activity tracks are used as preset activity tracks for similarity analysis with actual activity tracks, as shown in fig. 2, a schematic diagram of 3 preset activity tracks is provided, which does not mean that the invention only comprises 3 preset activity tracks, and actually there are multiple preset activity tracks.
The preset activity track (i) represents a plurality of different preset activity tracks, wherein the value of i is an integer greater than or equal to 1.
Step 4, obtaining activity parameters of the community correction object based on the Beidou positioning system, wherein the activity parameters comprise: generating an actual movement track according to the position parameters and the corresponding time length parameters;
the activity parameters of the community correction object are obtained through the Beidou positioning system,
the activity parameters mainly include: a location parameter and a length of time parameter. The position parameter refers to the real-time position of the community correction object obtained through the Beidou positioning system, the time length parameter refers to the stay time length corresponding to the position parameter, and the parameters are stored in a time sequence.
According to the position parameters obtained by the Beidou positioning system, an actual activity track is generated, and the activity track is generated through the position, which belongs to the prior art. The purpose of generating the actual activity track is to facilitate similarity calculation with the preset activity track, and if the actual activity track is highly similar to one of the preset activity tracks, the activity track of the community correction object is considered to be normal, and early warning reminding is not needed.
Step 5, calculating the similarity values D (i) of the actual motion track and the plurality of preset motion tracks one by one to obtain the minimum similarity value DminIf D isminIf the similarity is less than the similarity threshold value, the activity track is considered to be normal, and the operation entersStep 4, if DminIf the similarity is greater than the similarity threshold, entering step 6;
the Huasdorff distance algorithm calculates the similarity of the two curves by calculating the distance between the two curves, the maximum distance between the two curves is the Huasdorff distance value, the greater the Huasdorff distance value is, the lower the similarity of the two curves is, and the smaller the Huasdorff distance value is, the higher the similarity of the two curves is. In addition, the Huangasdorff distance algorithm can be well adapted to the situation that the lengths of the two curves are not in one-to-one correspondence, and the length of the obtained actual activity track of the community correction object is not necessarily consistent with the preset activity track, so that the Huangasdorff distance algorithm is one of the most suitable methods. The following detailed description is made with reference to the accompanying drawings:
as shown in fig. 3, the dashed line in fig. 3 represents an actual motion trajectory, the solid line represents a preset motion trajectory, and the husdorff distance values between the actual motion trajectory and each preset motion trajectory are obtained through the calculation of the husdorff, and are respectively: d (1), D (2), D (3), where the preset motion trajectory may be more than one.
After obtaining a plurality of the Huangasdorff distance values, it cannot be determined whether the similarity between the actual motion trajectory and the preset motion trajectory exceeds the preset range. The invention provides that when the minimum value of the Huangdorff distance value is smaller than the threshold value, the actual movement track is considered to be normal, and when the minimum value is larger than the threshold value, the method enters step 6 for further judgment. The invention obtains the minimum value in all the Huangdorff distance values by adopting a Min () function. The similarity threshold value in the invention is set to be 1-2 km.
Whether the activity track of the community correction object is normal or not can be preliminarily judged by judging the similarity of the activity track, and when the similarity is smaller than a threshold value, the position parameter of the community correction object does not need to be traversed, so that the calculation workload is reduced. And only when the similarity is greater than the threshold, the method considers that the actual activity track of the community correction object has a large possibility of abnormity, and the step 6 needs to be carried out for judgment.
Step 6, traversing position parameters in the activity parameters, extracting position points coincident with the specific places, and then calculating specific place calibration coefficients P according to time length parameters corresponding to the position points, wherein the calibration coefficients P are obtained by superposing the values of the position points, wherein the value of the calibration coefficient P is 1 when the position points stay for a certain time length, and if the value of P is greater than a specific place calibration threshold, the activity track is considered to be abnormal, and the step 8 is entered; and if the P is smaller than the specific site calibration threshold, entering a step 7.
Specifically, when the multi-dimensional data of the community correction object is collected, the position of a specific place is not collected, so that the specific place is not included in the preset activity track. Therefore, when the distance value between the actual activity track and the preset activity track is larger than the threshold value, whether the community correction object appears in a specific place such as a bus stop, a railway station, an airport, a dock and a high-speed entrance is considered first.
Traversing the position parameters of the community correction object, marking the position parameters of the community correction object and the position point parameters of the coincidence of the specific place, then extracting the time length parameters corresponding to the coincident position parameters, and calculating the calibration coefficient of the specific place according to the two parameters. The basis for calculating the calibration coefficient of the specific place according to the position parameter and the time length parameter is as follows: when community correction objects appear in a specific place and stay for a long time, the community correction objects are generally considered to be possibly out of the range of the safety fence by traveling in public transportation.
In the invention, the situation that the position of the community correction object is at the high-speed entrance is considered to be greatly different from other specific places, because according to practical consideration, the specific places such as bus stops, railway stations and the like need to go through the processes of ticket buying, ticket checking, waiting for getting on and the like, and the high-speed entrance has timeliness, is easier to enter the highway, and consumes much less time than other modes. Therefore, special consideration should be given when considering the time parameter, otherwise, false early warning may be caused, or early warning is not timely.
The specific site calibration coefficient P of the invention is calculated according to the following formula:
P=
Figure 67985DEST_PATH_IMAGE003
，
wherein, PkRepresenting the value of the position parameter in the activity parameter coincident with the bus stop, the railway station, the airport, the wharf and the high-speed entrance, when the position of the community correction object is coincident with the specific place, PkThe value is 1, otherwise the value is 0;
hkthe time length of the community correction object staying at the overlapped position is represented, when the time length parameter of the community correction object staying at a bus stop, a railway station, a wharf and an airport is 0-5 minutes, the value is 0 (the conditions of passing or waiting traffic lights and the like are possible at the moment), and when the time length parameter exceeds 5 minutes, the value is 1; pkAnd hkAre represented by 5 x 5 diagonal arrays.
When the time length parameter of the stay at the high-speed inlet is 0-2 minutes, the value is 0, and when the time length parameter exceeds 2 minutes, the value is 1. By specially considering a specific place, the condition that the high-speed entrance stays for 2-5 minutes is avoided from being omitted, and the accuracy of early warning is improved.
In the invention, a specific place calibration threshold is also set, and the threshold can be set according to the supervision requirement, for example, the abnormal condition is reminded when 2 specific places are considered to be visited, in the invention, the abnormal condition of the activity track is considered to be caused when 1 specific place is visited and the specific place stays for a certain time, and an early warning message needs to be sent out, therefore, the specific place calibration threshold is set to be 1. And when the calculated specific place calibration coefficient is larger than the threshold value, the activity track is considered to be abnormal, and the step 8 is carried out. And when the specific site calibration coefficient is smaller than the threshold value, the step 7 is carried out.
And 7, calculating the variation trend of the actual activity track to obtain a distance parameter T from the end point of the actual activity track to the safety fence, if the T is greater than a distance parameter threshold value, considering the activity track to be normal, entering the step 4, and if the T is less than the distance threshold value, considering the activity track to be abnormal, and entering the step 8.
When the similarity between the actual activity track of the community correction object and the preset activity track does not meet the threshold requirement, which indicates that the difference between the actual activity track and the preset activity track is large, and the calibration coefficient of the specific place is smaller than the threshold, there is a possibility that the community correction object moves towards a certain direction and gradually approaches the security fence even though the community correction object does not pass through the specific place, which is also a problem that the community correction object is often ignored. In addition, if only the distance between the community correction object and the safety fence is calculated for early warning, and the activity trend reflected by the activity track is not considered, the residence or the working place of the community correction object can be misjudged near the safety fence. Therefore, it is very necessary to consider the variation trend of the activity trace.
The invention provides a specific implementation mode for judging whether the activity track is abnormal or not by calculating the change trend of the actual activity track, which comprises the following steps:
as shown in fig. 4, a schematic diagram of the variation trend of the actual activity track of the present invention is given. The method comprises the steps of firstly calculating the change trend of an actual activity track to obtain a virtual track line, calculating the change trend of an irregular curve, and finishing the change trend by the prior art.
Next, the distance parameter T from the end point a of the actual moving track to the intersection point b is calculated according to the following formula:
T=
Figure 137441DEST_PATH_IMAGE004
，
wherein TbyY coordinate value, Tb, representing the point of intersection b of the virtual trajectory line with the security fencexAn x-coordinate value representing the intersection b of the virtual trajectory line and the safety fence; tayY coordinate value, Ta, representing the end of the actual motion trajectoryxAnd x-coordinate value representing the actual motion track endpoint.
And when the distance parameter T from the terminal point of the actual activity track to the safety fence is smaller than a certain range, the community correction object is considered to be close to the safety fence when continuing to move, the distance parameter T exceeds the limited area, an early warning message is sent to a supervisor, and the step 8 is entered. And when the distance parameter T is larger than a certain range, the community correction object is far away from the safety fence and belongs to a safe state, and an early warning message is not required to be sent to a supervisor, and the step 4 is returned to continue supervision. The distance threshold may be set according to the activity range of the community correction object, or may be set as an absolute distance, and the present invention is not limited specifically herein.
And 8, if the activity track is judged to be abnormal, feeding back early warning information to the manager and the community correction object.
Specifically, when judging that the activity track is unusual, correct the object to supervisor and community simultaneously, on the one hand, the supervisor can in time get in touch with community correction object, reminds it to abide by relevant regulation, and the effectual community of avoiding corrects the object and intentionally or unintentionally leaves the supervision ground, and on the other hand, community correction object receives after the relevant early warning message, also can effectually warn community correction object initiative to abide by relevant regulation.
The invention also discloses an early warning system 100 for implementing the supervision early warning method, comprising,
a map module 110, configured to construct a vector map, and mark location coordinates of a specific location in the vector map, where the specific location includes: bus stops, train stations, airports, docks, and high-speed entrances.
The security fence module 120 is configured to, according to the activity range of the community correction object, demarcate a boundary in the vector map, determine a security fence, obtain a regional map, and according to the activity range of the community correction object, the regional map includes a city area and a county area.
The information acquisition module 130 is configured to acquire personal multidimensional data of the community correction object and generate a preset activity track.
The positioning module 140 is configured to obtain activity parameters of the community correction object based on the beidou positioning system, where the activity parameters include: the position parameters and the time length parameters, and generating an actual activity track according to the position parameters.
The similarity calculation module 150 is configured to calculate similarities between the actual motion trajectory and the plurality of preset motion trajectories one by one, and perform minimum value processing on the similarity result, where a particular calculation method of the similarities adopts a husdorff distance algorithm.
And the accurate analysis module 160 is configured to traverse the position parameters in the activity parameters to obtain a position point coinciding with the specific location, calculate a specific location calibration coefficient P according to the corresponding time length parameter, calculate a distance parameter T from the track end point to the security fence according to the change trend of the actual activity track, and determine whether the actual activity track is abnormal according to the set specific location calibration threshold and the distance threshold.
And the information communication module 170 is used for feeding back the early warning information to the manager and the community correction object.
The invention also discloses computer equipment which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the monitoring and early warning method for the activity track of the community correction object when executing the computer program.
As mentioned above, only the specific embodiments of the present application are provided, and technical objects in the field can clearly understand that, for convenience and brevity of description, the specific working processes of the system, the module and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope of the present application, and these modifications or substitutions should be covered by the scope of the present application.

Claims (8)

1. A community correction object activity track supervision and early warning method is characterized by comprising the following steps:
step 1, constructing a vector map, and marking position coordinates of a specific place in the vector map;
step 2, setting a safety fence in the vector map according to the moving range of the community correction object to obtain an area map;
step 3, collecting multi-dimensional data of a community correction object, and importing the multi-dimensional data into the regional map to generate a plurality of preset activity tracks (i); wherein i is more than or equal to 1;
step 4, obtaining activity parameters of the community correction object based on the Beidou positioning system, wherein the activity parameters comprise: generating an actual movement track according to the position parameters and the corresponding time length parameters;
step 5, calculating the similarity values D (i) of the actual motion track and the plurality of preset motion tracks one by one to obtain the minimum similarity value DminIf D isminIf the similarity is smaller than the similarity threshold value, the activity track is considered to be normal, the step 4 is entered, and if D is smaller than the similarity threshold valueminIf the similarity is greater than the similarity threshold, entering step 6;
step 6, traversing position parameters in the activity parameters, extracting position points coincident with the specific places, and then calculating specific place calibration coefficients P according to time length parameters corresponding to the position points, wherein the calibration coefficients P are obtained by superposing the values of the position points, wherein the value of the calibration coefficient P is 1 when the position points stay for a certain time length, and if the value of P is greater than a specific place calibration threshold, the activity track is considered to be abnormal, and the step 8 is entered; if P is smaller than the specific site calibration threshold, entering step 7;
step 7, calculating the variation trend of the actual activity track to obtain a distance parameter T from the end point of the actual activity track to the safety fence, specifically: calculating the change trend of the movable track according to the actual movable track, obtaining a virtual track line intersected with the safety fence along the direction of the change trend, and calculating a distance parameter T according to the terminal point coordinate of the actual movable track and the intersection point coordinate of the virtual track line and the safety fence, wherein the calculation formula is as follows:
T=
Figure 779833DEST_PATH_IMAGE001
，
wherein TbyY coordinate value, Tb, representing the point of intersection b of the virtual trajectory line with the security fencexAn x-coordinate value representing the intersection b of the virtual trajectory line and the safety fence; tayY coordinate value, Ta, representing the end of the actual motion trajectoryxAn x coordinate value representing an actual motion trajectory end point;
if T is larger than the distance parameter threshold, the activity track is considered to be normal, and the step 4 is entered, and if T is smaller than the distance threshold, the activity track is considered to be abnormal, and the step 8 is entered;
and 8, if the activity track is judged to be abnormal, feeding back early warning information to the supervisor and the community correction object.
2. The supervised pre-warning method of claim 1, wherein: the specific places comprise bus stops, railway stations, airports, docks and high-speed entrances, and the regional map refers to a vector map within a security fence range and mainly comprises a city region map and a district region map.
3. The supervised pre-warning method of claim 1, wherein: the multidimensional data comprise residence places, working units and travel modes, the travel modes comprise walking, public transportation and driving, and a plurality of preset activity tracks are obtained according to different travel modes.
4. The supervised pre-warning method of claim 1, wherein: the similarity calculation method adopts a Huasdorff distance algorithm.
5. The supervised precaution method as recited in claim 1, 2, 3, or 4, wherein: the specific site calibration coefficient P is calculated according to the following formula:
P=
Figure 593068DEST_PATH_IMAGE002
，
wherein, PkRepresenting the position points coincident with bus stops, train stations, airports, docks and high-speed entrances in the activity parameters of the community rectification objects, and when there are coincident position points, PkValue is 1, otherwise 0, PkRepresented by a 5 x 5 diagonal matrix;
hkindicating the length of time that the community correction object stays at the coincident location point, when in the automobileWhen the station, the railway station, the airport and the wharf stay for 0-5 minutes, the value is 0, and when the stay time exceeds 5 minutes, the value is 1; when the time length of the residence at the high-speed inlet is 0-2 minutes, the value is 0, and when the residence time exceeds 2 minutes, the value is 1, hkRepresented by a 5 x 5 diagonal matrix; the site specific calibration threshold is set to 1.
6. The supervised precaution method as recited in claim 1, 2, 3, or 4, wherein: calculating the minimum similarity value DminCalculated according to the formula Dmin=min（D（i））。
7. An early warning system for implementing the supervised early warning method of any one of claims 1 to 6, wherein: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
the map module is used for constructing a vector map and marking the position coordinates of a specific place in the vector map;
the security fence module is used for dividing boundaries in the vector map according to the moving range of the community correction object so as to obtain maps of different areas;
the information acquisition module is used for acquiring personal multidimensional data of a community correction object and generating a preset activity track;
the positioning module is used for acquiring activity parameters of the community correction object based on the Beidou positioning system, and the activity parameters comprise: generating an actual movement track according to the position parameters and the time length parameters;
a similarity calculation module for calculating the similarity between the actual motion track and the preset motion tracks one by one and extracting the minimum value D of the similaritymin；
The precise analysis module is used for traversing the position parameters in the activity parameters to obtain position points coincident with the specific places, calculating a calibration coefficient P of the specific places according to the corresponding time length parameters, and calculating a distance parameter T from a track end point to the security fence according to the variation trend of the actual activity track;
and the information communication module is used for feeding back the early warning information to the manager and the community correction object.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor realizes the steps of the method of any one of claims 1 to 6 when executing the computer program.
CN202110380829.9A 2021-04-09 2021-04-09 Community correction object activity track supervision and early warning method, system and device Active CN112800166B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110380829.9A CN112800166B (en) 2021-04-09 2021-04-09 Community correction object activity track supervision and early warning method, system and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110380829.9A CN112800166B (en) 2021-04-09 2021-04-09 Community correction object activity track supervision and early warning method, system and device

Publications (2)

Publication Number Publication Date
CN112800166A CN112800166A (en) 2021-05-14
CN112800166B true CN112800166B (en) 2021-07-06

Family

ID=75816669

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110380829.9A Active CN112800166B (en) 2021-04-09 2021-04-09 Community correction object activity track supervision and early warning method, system and device

Country Status (1)

Country Link
CN (1) CN112800166B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113688679B (en) * 2021-07-22 2024-03-08 南京视察者智能科技有限公司 Method for preventing and controlling early warning of key personnel
CN114326790A (en) * 2021-12-06 2022-04-12 特金智能科技(上海)有限公司 Unmanned aerial vehicle violation determination method and device, electronic equipment and storage medium
CN115641105B (en) * 2022-12-01 2023-08-08 中网道科技集团股份有限公司 Data processing method for monitoring leave-out of community correction object
CN117998293B (en) * 2024-04-03 2024-06-28 苏州真趣信息科技有限公司 Positioning deviation correcting method, system, device and storage medium

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8990107B2 (en) * 2011-10-21 2015-03-24 Alohar Mobile Inc. Determining user stays of a user of a mobile device
CN106211073A (en) * 2016-07-21 2016-12-07 宁波力芯科信息科技有限公司 A kind of trip prediction based on geographical position safety index and alarm method
CN110232800A (en) * 2019-07-01 2019-09-13 李瑶 A kind of prison positioning service system

Also Published As

Publication number Publication date
CN112800166A (en) 2021-05-14

Similar Documents

Publication Publication Date Title
CN112800166B (en) Community correction object activity track supervision and early warning method, system and device
US11990036B2 (en) Driver behavior monitoring
CN110136447A (en) Lane change of driving a vehicle detects and method for distinguishing is known in illegal lane change
CN106448267B (en) Road traffic accident chain based on car networking blocks system
CN104809887B (en) A kind of retrograde detection method of vehicle on expressway and autoalarm
EP3403219A1 (en) Driver behavior monitoring
CN110164132B (en) Method and system for detecting road traffic abnormity
CN103150908B (en) Average vehicle speed detecting method based on video
CN108346316A (en) A kind of prevention and control system violating the regulations of the intelligence based on lane detection
CN110428604A (en) It is a kind of based on the taxi illegal parking of GPS track data and map datum monitoring and method for early warning
Wang et al. Operational design domain of autonomous vehicles at skewed intersection
CN106530714B (en) A kind of secondary traffic accident time forecasting methods based on traffic flow data
CN107784832A (en) A kind of method and apparatus for being used to identify the accident black-spot in traffic route
Anwari et al. Investigating surrogate safety measures at midblock pedestrian crossings using multivariate models with roadside camera data
CN112382068B (en) Station waiting line crossing detection system based on BIM and DNN
CN106600950B (en) A kind of secondary traffic accident prediction technique based on traffic flow data
CN115440071B (en) Automatic driving illegal parking detection method
CN104408942A (en) Intelligent vehicle speed measuring device and method
Yang et al. Rapid analysis and detection algorithm and prevention countermeasures of urban traffic accidents under artificial intelligence
CN113128847A (en) Entrance ramp real-time risk early warning system and method based on laser radar
Alagarsamy et al. A Novel Machine Learning Technique for Predicting Road Accidents
Yu et al. Simulation-based safety analysis of diversion and confluence area in urban underground loop
Noh et al. Vision based pedestrian potential risk analysis based on automated behavior feature extraction for smart and safe city
Yao et al. Enhancement of Detection Functions of a 3D-Laser-Radar-Type Obstacle Detection System at a Level Crossing
CN117392876B (en) Intelligent wearable equipment monitoring management system for road safety construction

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