CN113688679A - Key personnel prevention, control and early warning method - Google Patents

Key personnel prevention, control and early warning method Download PDF

Info

Publication number
CN113688679A
CN113688679A CN202110831378.6A CN202110831378A CN113688679A CN 113688679 A CN113688679 A CN 113688679A CN 202110831378 A CN202110831378 A CN 202110831378A CN 113688679 A CN113688679 A CN 113688679A
Authority
CN
China
Prior art keywords
prevention
key personnel
trace
early warning
control
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
CN202110831378.6A
Other languages
Chinese (zh)
Other versions
CN113688679B (en
Inventor
蔡鸿林
周金明
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.)
Nanjing Inspector Intelligent Technology Co Ltd
Original Assignee
Nanjing Inspector Intelligent Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nanjing Inspector Intelligent Technology Co Ltd filed Critical Nanjing Inspector Intelligent Technology Co Ltd
Priority to CN202110831378.6A priority Critical patent/CN113688679B/en
Publication of CN113688679A publication Critical patent/CN113688679A/en
Application granted granted Critical
Publication of CN113688679B publication Critical patent/CN113688679B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/22Matching criteria, e.g. proximity measures
    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B31/00Predictive alarm systems characterised by extrapolation or other computation using updated historic data

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Business, Economics & Management (AREA)
  • Computing Systems (AREA)
  • Emergency Management (AREA)
  • Alarm Systems (AREA)
  • Image Processing (AREA)
  • Image Analysis (AREA)

Abstract

The invention discloses a method for preventing, controlling and early warning key personnel, which comprises the steps of 1, loading information of arranged prevention and control points P, 2, presetting a normal trajectory line array A of a certain key personnel, 3, and if the normal trajectory line array A is positioned at the prevention and control points PxIdentifying the image of the key personnel, uploading the image of the key personnel and the occurrence prevention and control point P through the terminalxAnd processing the information, and sending an early warning message to the abnormal condition. The method can reduce a large amount of manpower input, accurately judge whether the personnel track is abnormal or not, and improve the early warning accuracy.

Description

Key personnel prevention, control and early warning method
Technical Field
The invention relates to the field of data processing and image recognition research, in particular to a method for prevention, control and early warning of key personnel.
Background
In case treatment day-to-day work, except for normal case reception and treatment. And the personnel who visit many times or maliciously visit need to be prevented and controlled, so that the personnel can be prevented from taking a series of behaviors which disturb normal working order, such as override, overstimulation and the like. The traditional prevention and control mode is that a monitoring probe is installed in a residence or a working unit of an applicant, a specially-assigned person is dispatched to monitor, a many-to-one manual staring mode is adopted, the mental state of key personnel is required to be observed at any time to judge whether the key personnel can make an overstimulation behavior, and the key personnel can conduct persuasion before serious consequences occur, so that a large amount of manpower and material resources are wasted, meanwhile, the travel track of the applicant is difficult to monitor, and the real-time early warning is achieved for some abnormal behaviors without a method.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a method for preventing, controlling and early warning of key personnel, which can reduce a large amount of manpower input, accurately judge whether the personnel track is abnormal and improve the early warning accuracy.
The technical scheme is as follows:
the invention provides a method for preventing, controlling and early warning key personnel, which comprises the following steps:
step 1, loading information of the arranged prevention and control points P, wherein the information comprises longitude and latitude of the prevention and control points, red and green identification of the prevention and control points, position types of the prevention and control points, directions monitored by the prevention and control points and the like; when the prevention and control point is positioned at the key position or the sensitive position, the red and green marks of the prevention and control point are red, otherwise, the prevention and control point is green; if key personnel appear in the prevention and control points with red and green marks, early warning information needs to be sent.
Step 2, presetting a normal trajectory line array A of a certain key person, wherein the specific setting method comprises the following steps:
selecting a plurality of points a of daily activities of the key personnel1、a2、a3…, forming a plurality of normal trajectory lines according to the daily activity sequence, namely forming an important person normal trajectory line array A, wherein the normal trajectory lines can not form a loop.
Step 3, if the point is at the prevention and control point PxIdentifying the image of the key personnel, uploading the image of the key personnel and the occurrence prevention and control point P through the terminalxThe uploaded information is processed as follows:
judging whether the key personnel has a track line array D of the day:
if not, then newly building track line array D, and controlling point PxDot as trajectory line D1Head node d of11I.e. D1The first node of (a);
if the array of the trajectory line D { D } of the current day already exists1(d11-d12-d13-……)、D2(d21-d22-d23-……)……Dn(dn1-dn2-dn3-……) }, the prevention and control point P is setxAdding the data into a trajectory line array D, specifically: take the latest trajectory line DnObtaining a trajectory line DnTail node d ofniI.e. trajectory line DnThe last node of (2), the judgment prevention and control point PxAnd tail node dniIf the distance is less than R, the prevention and control point P is setxAdding trajectory line DnIn, and update PxIs DnThe tail node of (1); if not, a new trajectory line D is created for the key personneln+1And is provided with PxIs Dn+1The head node of (1).
Judging prevention and control point PxWhether the red and green marks are red or not is judged, if yes, an early warning message is directly sent;
if the point P is controlledxThe red and green marks are green, and the prevention and control point P is further judgedxIf the action of the uploading event needs long-term monitoring, updating the key personnel monitoring queue, and monitoring the key personnel for a long time, if the action does not need long-term monitoring, then monitoring the key personnel for a long time; and acquiring the trace lines with the trace point number exceeding a threshold value N in the trace line array D, respectively carrying out similarity calculation on the trace lines with the trace lines in the normal trace line array A, wherein the trace points with the trace point number exceeding the threshold value N are respectively subjected to similarity calculation, and when the similarity is smaller than a certain threshold value, sending an early warning message.
Preferably, the information of the prevention and control point P in step 1 is information of a corresponding image recognition camera.
Preferably, the further judgment of the prevention and control point P in the step 3xWhether the action of uploading the event needs long-term monitoring is determined according to the type of the prevention and control point and the monitored direction information.
Preferably, the threshold N in step 3 is determined according to the number of normal track points of the key person.
Preferably, in step 3, the similarity calculation is performed between the trace line with the number of each trace point exceeding the threshold N and the trace line in the normal trace line array a, and when the similarity is smaller than a certain threshold, an early warning message is sent, and instead, the judgment is performed according to the discrete Frechet distance, specifically:
setting the number of trace points in a trace line array D exceeding a threshold value N as H, setting the number of trace points in an array A as Q, and setting the H to be composed of H trace points and the Q to be composed of Q trace points;
using sigma (H) ═ u1,u2,u3…uh),σ(Q)=(v1,v2,v3…vq) Respectively representing a sequential set of two trace points. The following sequence point pairs L can be obtained:
Figure BDA0003175688590000021
wherein a is1=1,b1=1,am=h,bmQ, with a for any i 1i+1=aiOr ai+1=ai+1 and bi+1=bi
H. The length L between the sequence pairs between the Q trace points is defined as the maximum value of the euclidean distance in each sequence pair, that is:
Figure BDA0003175688590000022
then the discrete Frechet distance is expressed as follows: deltadF(H,Q)=min(||L||)。
Calculating the discrete Frechet distance between the curve meeting the conditions in the D and all the curves in the A, and taking s-min (delta)dF(H, Q)) is the minimum Frechet distance of the key personnel, whether the minimum Frechet distance s is larger than a threshold value M or not is judged, and if yes, an early warning message is sent.
Compared with the prior art, one of the technical schemes has the following beneficial effects: through image recognition, the positions of key personnel are accurately monitored, a track line array is established for the key personnel, a plurality of normal track paths are set for the key personnel, and early warning is timely carried out if actions deviating from normal tracks appear through comparison. A large amount of human input is reduced, whether the staff track is abnormal or not is accurately judged, and the early warning accuracy is improved.
Drawings
Fig. 1 is a flow chart of prevention, control and early warning for key personnel according to an embodiment of the disclosure.
Detailed Description
In order to clarify the technical solution and the working principle of the present invention, the embodiments of the present disclosure will be described in further detail with reference to the accompanying drawings. All the above optional technical solutions may be combined arbitrarily to form the optional embodiments of the present disclosure, and are not described herein again.
The method for preventing, controlling and early warning key personnel provided by the embodiment of the disclosure comprises the following steps:
step 1, loading information of the arranged prevention and control points P, wherein the information comprises longitude and latitude of the prevention and control points, red and green identification of the prevention and control points, position types of the prevention and control points, directions monitored by the prevention and control points and the like; when the prevention and control point is positioned at the key position or the sensitive position, the red and green marks of the prevention and control point are red, otherwise, the prevention and control point is green; if key personnel appear in the prevention and control points with red and green marks, early warning information needs to be sent.
Preferably, the information of the prevention and control point P in step 1 is information of a corresponding image recognition camera.
Step 2, presetting a normal trajectory line array A of a certain key person, wherein the specific setting method comprises the following steps:
selecting a plurality of points a of daily activities of the key personnel1、a2、a3…, forming a plurality of normal trajectory lines according to the daily activity sequence, namely forming an important person normal trajectory line array A, wherein the normal trajectory lines can not form a loop.
Step 3, if the point is at the prevention and control point PxIdentifying the image of the key personnel, uploading the image of the key personnel and the occurrence prevention and control point P through the terminalxThe uploaded information is processed as follows.
Judging whether the key personnel has a track line array D of the day:
if not, then newly building track line array D, and controlling point PxDot as trajectory line D1Head node d of11I.e. D1The first node of (1).
If the array of the trajectory line D { D } of the current day already exists1(d11-d12-d13-……)、D2(d21-d22-d23-……)……Dn(dn1-dn2-dn3… …), the prevention and control point P is setxAdding the data into a trajectory line array D, specifically: take the latest trajectory line DnObtaining a trajectory line DnTail node d ofniI.e. trajectory line DnThe last node of (2), the judgment prevention and control point PxAnd tail node dniIf the distance is less than R, the prevention and control point P is setxAdding trajectory line DnIn, and update PxIs DnThe tail node of (1); if not, a new trajectory line D is created for the key personneln+1And is provided with PxIs Dn+1The head node of (1).
Judging prevention and control point PxAnd if the red and green marks are red, the early warning message is directly sent.
If the point P is controlledxThe red and green marks are green, and the prevention and control point P is further judgedxIf the action of the uploading event needs long-term monitoring, updating the key personnel monitoring queue, and monitoring the key personnel for a long time, if the action does not need long-term monitoring, then monitoring the key personnel for a long time; and acquiring the trace lines with the trace point number exceeding a threshold value N in the trace line array D, respectively carrying out similarity calculation on the trace lines with the trace lines in the normal trace line array A, wherein the trace points with the trace point number exceeding the threshold value N are respectively subjected to similarity calculation, and when the similarity is smaller than a certain threshold value, sending an early warning message.
Preferably, the further judgment of the prevention and control point P in the step 3xWhether the action of uploading the event needs long-term monitoring is determined according to the type of the prevention and control point and the monitored direction information. Such as: when a key person is present at a prevention and control point of a residential area type and enters a door, whether the key person has a long-term home condition needs to be monitored. The abnormal state of key personnel is pre-judged through long-term monitoring of actions such as home, leaving, departure and the like, and the personnel is informed to investigate in time.
Preferably, the threshold N in step 3 is determined according to the number of normal track points of the key person.
Preferably, in step 3, the similarity calculation is performed between the trace line with the number of each trace point exceeding the threshold N and the trace line in the normal trace line array a, and when the similarity is smaller than a certain threshold, an early warning message is sent, and instead, the judgment is performed according to the discrete Frechet distance, specifically:
the trajectory line that trajectory point quantity surpassed threshold value N in the trajectory line array D is set for H, and the trajectory line in array A is Q, and it has H trajectory point to constitute to set up H, and Q has Q trajectory point to constitute.
Using sigma (H) ═ u1,u2,u3…uh),σ(Q)=(v1,v2,v3…vq) Respectively representing a sequential set of two trace points. The following sequence point pairs L can be obtained:
Figure BDA0003175688590000041
wherein a is1=1,b1=1,am=h,bmQ, with a for any i 1i+1=aiOr ai+1=ai+1 and bi+1=bi
H. The length L between the sequence pairs between the Q trace points is defined as the maximum value of the euclidean distance in each sequence pair, that is:
Figure BDA0003175688590000042
then the discrete Frechet distance is expressed as follows: deltadF(H,Q)=min(||L||)。
Calculating the discrete Frechet distance between the curve meeting the conditions in the D and all the curves in the A, and taking s-min (delta)dF(H, Q)) is the minimum Frechet distance of the key personnel, whether the minimum Frechet distance s is larger than a threshold value M or not is judged, and if yes, an early warning message is sent.
The invention has been described above by way of example with reference to the accompanying drawings, it being understood that the invention is not limited to the specific embodiments described above, but is capable of numerous insubstantial modifications when implemented in accordance with the principles and solutions of the present invention; or directly apply the conception and the technical scheme of the invention to other occasions without improvement and equivalent replacement, and the invention is within the protection scope of the invention.

Claims (5)

1. A method for preventing, controlling and early warning key personnel is characterized by comprising the following steps:
step 1, loading information of the arranged prevention and control points P, wherein the information comprises longitude and latitude of the prevention and control points, red and green identification of the prevention and control points, position types of the prevention and control points, directions monitored by the prevention and control points and the like; when the prevention and control point is positioned at the key position or the sensitive position, the red and green marks of the prevention and control point are red, otherwise, the prevention and control point is green; if key personnel appear in the prevention and control points with red and green marks, early warning information needs to be sent;
step 2, presetting a normal trajectory line array A of a certain key person, wherein the specific setting method comprises the following steps:
selecting a plurality of points a of daily activities of the key personnel1、a2、a3…, forming a plurality of normal trajectory lines according to the daily activity sequence, namely forming a key personnel normal trajectory line array A, wherein the normal trajectory lines can not form a loop;
step 3, if the point is at the prevention and control point PxIdentifying the image of the key personnel, uploading the image of the key personnel and the occurrence prevention and control point P through the terminalxThe uploaded information is processed as follows:
judging whether the key personnel has a track line array D of the day:
if not, then newly building track line array D, and controlling point PxDot as trajectory line D1Head node d of11I.e. D1The first node of (a);
if the array of the trajectory line D { D } of the current day already exists1(d11-d12-d13-……)、D2(d21-d22-d23-……)……Dn(dn1-dn2-dn3… …), the prevention and control point P is setxAdding the data into a trajectory line array D, specifically: take the latest trajectory line DnObtaining a trajectory line DnTail node d ofniI.e. trajectory line DnThe last node of (2), the judgment prevention and control point PxAnd tail node dniIf the distance is less than R, the prevention and control point P is setxAdding trajectory line DnIn, and update PxIs DnThe tail node of (1); if not, a new trajectory line D is created for the key personneln+1And is provided with PxIs Dn+1A head node of (a);
judging prevention and control point PxWhether the red and green marks are red or not is judged, if yes, an early warning message is directly sent;
if the point P is controlledxThe red and green marks are green, and the prevention and control point P is further judgedxIf the action of the uploading event needs long-term monitoring, updating the key personnel monitoring queue, and monitoring the key personnel for a long time, if the action does not need long-term monitoring, then monitoring the key personnel for a long time; and acquiring the trace lines with the trace point number exceeding a threshold value N in the trace line array D, respectively carrying out similarity calculation on the trace lines with the trace lines in the normal trace line array A, wherein the trace points with the trace point number exceeding the threshold value N are respectively subjected to similarity calculation, and when the similarity is smaller than a certain threshold value, sending an early warning message.
2. The method for prevention, control and early warning of key personnel according to claim 1, wherein the information of the prevention and control point P in step 1 is information of a corresponding image recognition camera.
3. The method for prevention, control and early warning of key personnel according to claim 1, wherein the step 3 is further for judging the prevention and control point PxWhether the action of uploading the event needs long-term monitoring is determined according to the type of the prevention and control point and the monitored direction information.
4. The method for prevention, control and early warning of key personnel according to claim 1, wherein the threshold N in step 3 is determined according to the number of normal tracing points of the key personnel.
5. The method for prevention, control and early warning of key personnel according to any one of claims 1 to 4, wherein in step 3, the similarity calculation is performed on the trajectory lines with the number of each trajectory point exceeding the threshold N and the trajectory lines in the normal trajectory line array A, when the similarity is smaller than a certain threshold, the early warning message is sent, and instead of the judgment according to the discrete Frechet distance, specifically:
setting the number of trace points in a trace line array D exceeding a threshold value N as H, setting the number of trace points in an array A as Q, and setting the H to be composed of H trace points and the Q to be composed of Q trace points;
using sigma (H) ═ u1,u2,u3…uh),σ(Q)=(v1,v2,v3…vq) Respectively representing the sequential sets of the two track points; the following sequence point pairs L can be obtained:
Figure FDA0003175688580000021
wherein a is1=1,b1=1,am=h,bmQ, with a for any i 1i+1=aiOr ai+1=ai+1 and bi+1=bi
H. The length L between the sequence pairs between the Q trace points is defined as the maximum value of the euclidean distance in each sequence pair, that is:
Figure FDA0003175688580000022
then the discrete Frechet distance is expressed as follows: deltadF(H,Q)=min(||L||),
Calculating the discrete Frechet distance between the curve meeting the conditions in the D and all the curves in the A, and taking s-min (delta)dF(H, Q)) is the minimum Frechet distance of the key personnel, whether the minimum Frechet distance s is larger than a threshold value M or not is judged, and if yes, an early warning message is sent.
CN202110831378.6A 2021-07-22 2021-07-22 Method for preventing and controlling early warning of key personnel Active CN113688679B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110831378.6A CN113688679B (en) 2021-07-22 2021-07-22 Method for preventing and controlling early warning of key personnel

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110831378.6A CN113688679B (en) 2021-07-22 2021-07-22 Method for preventing and controlling early warning of key personnel

Publications (2)

Publication Number Publication Date
CN113688679A true CN113688679A (en) 2021-11-23
CN113688679B CN113688679B (en) 2024-03-08

Family

ID=78577696

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110831378.6A Active CN113688679B (en) 2021-07-22 2021-07-22 Method for preventing and controlling early warning of key personnel

Country Status (1)

Country Link
CN (1) CN113688679B (en)

Citations (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101334845A (en) * 2007-06-27 2008-12-31 中国科学院自动化研究所 Video frequency behaviors recognition method based on track sequence analysis and rule induction
US20110205359A1 (en) * 2010-02-19 2011-08-25 Panasonic Corporation Video surveillance system
CN104408459A (en) * 2014-10-27 2015-03-11 国家电网公司 Image identification method applied to power equipment monitoring
US20160217345A1 (en) * 2013-08-26 2016-07-28 International Business Machines Corporation Role-based tracking and surveillance
CN106210634A (en) * 2016-07-18 2016-12-07 四川君逸数码科技股份有限公司 A kind of wisdom gold eyeball identification personnel fall down to the ground alarm method and device
CN107665591A (en) * 2017-09-14 2018-02-06 王淑芳 A kind of emphasis commerial vehicle is driven over the speed limit monitoring method and system
CN109784162A (en) * 2018-12-12 2019-05-21 成都数之联科技有限公司 A kind of identification of pedestrian behavior and trace tracking method
CN109815848A (en) * 2018-12-29 2019-05-28 深圳市天彦通信股份有限公司 Parking lot safety pre-warning system and method
CN110245554A (en) * 2019-04-29 2019-09-17 中科智城(广州)信息科技有限公司 A kind of method, system platform and the storage medium of the early warning of pedestrian movement's trend
CN110379163A (en) * 2019-07-26 2019-10-25 银江股份有限公司 A kind of vehicle abnormality decelerating area detection method and system based on track data
CN110443109A (en) * 2019-06-11 2019-11-12 万翼科技有限公司 Abnormal behaviour monitor processing method, device, computer equipment and storage medium
CN110766895A (en) * 2019-09-17 2020-02-07 重庆特斯联智慧科技股份有限公司 Intelligent community abnormity alarm system and method based on target trajectory analysis
WO2020082900A1 (en) * 2018-10-25 2020-04-30 北京嘀嘀无限科技发展有限公司 Order service security detection apparatus and method
CN111667697A (en) * 2019-03-06 2020-09-15 北京京东尚科信息技术有限公司 Abnormal vehicle identification method and device, and computer-readable storage medium
CN111832400A (en) * 2020-06-04 2020-10-27 北京航空航天大学 Mask wearing condition monitoring system and method based on probabilistic neural network
CN112800166A (en) * 2021-04-09 2021-05-14 湖南司法警官职业学院 Community correction object activity track supervision and early warning method, system and device

Patent Citations (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101334845A (en) * 2007-06-27 2008-12-31 中国科学院自动化研究所 Video frequency behaviors recognition method based on track sequence analysis and rule induction
US20110205359A1 (en) * 2010-02-19 2011-08-25 Panasonic Corporation Video surveillance system
US20160217345A1 (en) * 2013-08-26 2016-07-28 International Business Machines Corporation Role-based tracking and surveillance
CN104408459A (en) * 2014-10-27 2015-03-11 国家电网公司 Image identification method applied to power equipment monitoring
CN106210634A (en) * 2016-07-18 2016-12-07 四川君逸数码科技股份有限公司 A kind of wisdom gold eyeball identification personnel fall down to the ground alarm method and device
CN107665591A (en) * 2017-09-14 2018-02-06 王淑芳 A kind of emphasis commerial vehicle is driven over the speed limit monitoring method and system
WO2020082900A1 (en) * 2018-10-25 2020-04-30 北京嘀嘀无限科技发展有限公司 Order service security detection apparatus and method
CN111105243A (en) * 2018-10-25 2020-05-05 北京嘀嘀无限科技发展有限公司 Order service security detection method and device and computer readable storage medium
CN109784162A (en) * 2018-12-12 2019-05-21 成都数之联科技有限公司 A kind of identification of pedestrian behavior and trace tracking method
CN109815848A (en) * 2018-12-29 2019-05-28 深圳市天彦通信股份有限公司 Parking lot safety pre-warning system and method
CN111667697A (en) * 2019-03-06 2020-09-15 北京京东尚科信息技术有限公司 Abnormal vehicle identification method and device, and computer-readable storage medium
CN110245554A (en) * 2019-04-29 2019-09-17 中科智城(广州)信息科技有限公司 A kind of method, system platform and the storage medium of the early warning of pedestrian movement's trend
CN110443109A (en) * 2019-06-11 2019-11-12 万翼科技有限公司 Abnormal behaviour monitor processing method, device, computer equipment and storage medium
CN110379163A (en) * 2019-07-26 2019-10-25 银江股份有限公司 A kind of vehicle abnormality decelerating area detection method and system based on track data
CN110766895A (en) * 2019-09-17 2020-02-07 重庆特斯联智慧科技股份有限公司 Intelligent community abnormity alarm system and method based on target trajectory analysis
CN111832400A (en) * 2020-06-04 2020-10-27 北京航空航天大学 Mask wearing condition monitoring system and method based on probabilistic neural network
CN112800166A (en) * 2021-04-09 2021-05-14 湖南司法警官职业学院 Community correction object activity track supervision and early warning method, system and device

Also Published As

Publication number Publication date
CN113688679B (en) 2024-03-08

Similar Documents

Publication Publication Date Title
US11982409B2 (en) Safety monitoring methods and Internet of Things systems of pipe network reliability degree based on intelligent gas
CN114137916B (en) Supervision and control system for circuit board production based on data analysis
JP6960525B2 (en) Plant health monitoring methods and equipment
EP3917315A1 (en) Systems and methods for measuring beehive strength
DE112015000496T5 (en) Sensor network with an event-based triggered message
EP3557357B1 (en) Operation monitoring method
US20230172167A1 (en) Automated poultry or livestock welfare tracking
CN107632132A (en) A kind of water quality monitoring warning system with forecast function
CN116295662B (en) Crop growth state monitoring method and device, electronic equipment and medium
CN111199535A (en) Animal state monitoring method and device, electronic equipment and storage medium
DE112021004174T5 (en) FEDERATED LEARNING FOR ANOMALY DETECTION
CN113688679A (en) Key personnel prevention, control and early warning method
TW202306347A (en) Health management method and device for base station operation and computer-readable storage medium
CN109102080B (en) Numerical financial data quality monitoring system and method
CN110207827B (en) Electrical equipment temperature real-time early warning method based on abnormal factor extraction
CN109949930A (en) Animal epidemics diagnostic method and system based on Bayesian network
CN117319809A (en) Intelligent adjusting method for monitoring visual field
CN108681724A (en) Farming operations monitoring method and device
CN116844105A (en) Logistics service monitoring system
CN106651314A (en) School attending prediction method and device
CN106375470A (en) Information transmission method and information transmission system
CN114692738A (en) Lightweight real-time series anomaly detection method
CN109973355A (en) A kind of energy-saving method towards air compressor
CN112131069B (en) Equipment operation monitoring method and system based on clustering
CN114022302A (en) Pregnant goat intelligent management system and management method based on video monitoring

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