CN114611400B - Early warning information screening method and system - Google Patents
Early warning information screening method and system Download PDFInfo
- Publication number
- CN114611400B CN114611400B CN202210269221.3A CN202210269221A CN114611400B CN 114611400 B CN114611400 B CN 114611400B CN 202210269221 A CN202210269221 A CN 202210269221A CN 114611400 B CN114611400 B CN 114611400B
- Authority
- CN
- China
- Prior art keywords
- information
- neural network
- condition
- real
- cnn neural
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000012216 screening Methods 0.000 title claims abstract description 35
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 49
- 238000003062 neural network model Methods 0.000 claims abstract description 32
- 238000013528 artificial neural network Methods 0.000 claims abstract description 20
- 238000012549 training Methods 0.000 claims abstract description 17
- 238000002372 labelling Methods 0.000 claims abstract description 14
- 125000004122 cyclic group Chemical group 0.000 claims abstract description 7
- 238000007781 pre-processing Methods 0.000 claims description 13
- 239000013598 vector Substances 0.000 claims description 11
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000005520 cutting process Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 230000003321 amplification Effects 0.000 claims description 2
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 claims 10
- 238000011897 real-time detection Methods 0.000 abstract description 10
- 239000000463 material Substances 0.000 abstract description 3
- 238000012545 processing Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 6
- 238000001914 filtration Methods 0.000 description 5
- 238000013473 artificial intelligence Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 238000012800 visualization Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a method and a system for screening early warning information, and relates to the field of security protection. The invention comprises the following steps: acquiring a historical warning condition, and labeling the historical warning condition, wherein the labels are 0 and 1; constructing a CNN neural network, and training the CNN neural network by using the history warning condition with the label; performing repeated cyclic training to obtain a CNN neural network model; acquiring a real-time detection alarm condition, and inputting the real-time detection alarm condition into a CNN neural network model; if the screening result of the CNN neural network model is 1, triggering an alarm; and if the screening result of the CNN neural network model is 0, false early warning information is obtained. The invention improves the accuracy of alarming, avoids wasting a great deal of manpower, material resources and time caused by processing security personnel according to false alarm conditions, and improves the stability and accuracy of a security system.
Description
Technical Field
The invention relates to the field of security protection, in particular to a method and a system for screening early warning information.
Background
Along with the continuous progress of scientific information technology, digitization, networking and intellectualization are rapidly developed, and the application of new generation artificial intelligence technology rapidly rises worldwide, so that the mode of economic and social development is fundamentally changed, the production and living modes of people are changed, and the competition pattern of enterprises in society is changed. In recent years, the application of artificial intelligence in security industry is gradually complete and mature, the overall improvement of the technology and efficiency of the security industry is promoted, and the security and happiness of people are brought to people, so that the artificial intelligence is also widely paid attention to people.
The safety precaution means that the safety precaution to personnel, equipment, buildings or areas is comprehensively realized in the building or building group (including surrounding areas) or in specific places and areas by adopting modes of manpower precaution, technical precaution, physical precaution and the like. However, the existing security system has a false alarm phenomenon, which consumes a lot of manpower and material resources, so how to reduce the false alarm phenomenon is needed to be solved by those skilled in the art.
Disclosure of Invention
In view of the above, the present invention provides a method and a system for screening early warning information to solve the above problems.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
a method for screening early warning information comprises the following steps:
acquiring a historical warning condition, and labeling the historical warning condition, wherein the labels are 0 and 1;
constructing a CNN neural network, and training the CNN neural network by using the history warning condition with the label;
performing repeated cyclic training to obtain a CNN neural network model;
acquiring a real-time detection alarm condition, and inputting the real-time detection alarm condition into a CNN neural network model;
if the screening result of the CNN neural network model is 1, triggering an alarm;
and if the screening result of the CNN neural network model is 0, false early warning information is obtained.
Optionally, the step of labeling the historical alert is as follows:
extracting characteristic points of the historical police conditions, and detecting the characteristic points;
removing abnormal characteristic points;
constructing a scale model according to the reserved characteristic points;
determining feature vectors of the feature points on the basis of the scale model;
determining the direction of the feature points according to the feature vectors;
and determining the tags of the historical police conditions according to the directions of the feature points.
Optionally, the method further comprises dimension reduction of a clustering method of the feature vector of the feature point based on the item distribution approximation of the information entropy.
Optionally, the specific method for acquiring the real-time warning condition is as follows:
acquiring voice information and image information of a real-time alarm condition;
preprocessing voice information and image information;
and classifying the preprocessed voice information and the preprocessed image information according to a preset safety threshold value to obtain accurate voice information and accurate image information.
The technical scheme has the following beneficial effects:
by preprocessing the real-time warning condition, the filtering precision of the early warning information is improved, and the calculated amount of the neural network is reduced.
Optionally, the specific process of preprocessing the voice information is as follows:
whether the decibel number of the voice information is smaller than a preset threshold value or not;
if not, eliminating noise by using a Gaussian algorithm;
if yes, signal amplification is carried out on the voice information, and noise is removed by means of Gaussian algorithm.
Optionally, preprocessing the image information includes: and cutting the edge of the image to remove the redundant noise point image.
An early warning information screening system, comprising:
historical alert labeling module: the method comprises the steps of obtaining a historical warning condition, and labeling the historical warning condition, wherein the labels are 0 and 1;
the neural network training module: the method is used for constructing a CNN neural network, and training the CNN neural network by utilizing the history warning condition with the label;
the neural network model building module: the method is used for repeated cyclic training to obtain a CNN neural network model;
the real-time warning condition acquisition module is used for: the method comprises the steps of acquiring a real-time detection alarm condition, and inputting the real-time detection alarm condition into a CNN neural network model;
the early warning information screening module: the method is used for screening the early warning information: if the screening result of the CNN neural network model is 1, triggering an alarm; and if the screening result of the CNN neural network model is 0, false early warning information is obtained.
Optionally, the real-time warning condition acquisition module acquires the real-time warning condition through a camera and an infrared information sensing device.
Compared with the prior art, the invention discloses and provides the early warning information screening method and system, which have the following beneficial effects:
by combining the historical alarm conditions and utilizing a neural network model, the weight of the authenticity of the alarm condition information is calculated, whether the alarm condition is the true alarm condition is judged, and the accuracy of triggering the alarm by the alarm condition is remarkably improved. Furthermore, the invention improves the calculation speed of the neural network by preprocessing the real-time alarm condition and lays a foundation for filtering false alarm conditions. The invention improves the accuracy of alarming, avoids wasting a great deal of manpower, material resources and time caused by processing security personnel according to false alarm conditions, and improves the stability and accuracy of a security system.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of the present invention;
fig. 2 is a schematic structural view of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The embodiment of the invention discloses a method for screening early warning information, which is shown in fig. 1 and comprises the following steps:
acquiring a historical warning condition, and labeling the historical warning condition with the labels of 0 and 1;
constructing a CNN neural network, and training the CNN neural network by using the history warning condition with the label;
performing repeated cyclic training to obtain a CNN neural network model;
acquiring a real-time detection alarm condition, and inputting the real-time detection alarm condition into a CNN neural network model;
if the screening result of the CNN neural network model is 1, triggering an alarm;
and if the screening result of the CNN neural network model is 0, false early warning information is obtained.
In the embodiment, an artificial intelligence-convolutional neural network CNN method is used for building a filtering and warning platform, the platform is arranged at a cloud end, and front-end video information is transmitted into a platform CNN system to carry out deep learning of the cloud end platform. The method fully utilizes the human recognition, face recognition technology and infrared microwave perception technology of a camera, utilizes the computer vision technology to realize false alarm condition filtering, uncertain information police linkage and security treatment, automatically uploads real crime information to the public security bureau 110 platform, integrates a command and dispatch system, automatically commands the nearest police to hold a mobile phone APP on-site video visualization alarm and police management mechanism visualization video command, and realizes management and control, information severe judgment and a graph display.
Specifically, the CNN convolutional neural network is an item taking big data acquisition, deep learning and intelligent pushing as main technical frameworks, and the working principle is that static and dynamic information acquired by the front-end AI humanoid recognition camera and the AI facial recognition camera is uploaded to the CNN convolutional neural network for deep learning, and the result is treated in a representation form of '0=correct and 1=error'. 0 = correct = illegal intrusion or fire hazard = automatic push public security bureau video integration command platform. 1=error=memory information=filter false alarm records.
Further, the step of labeling the history warning condition is as follows:
extracting characteristic points of the historical police conditions, and detecting the characteristic points;
removing abnormal characteristic points;
constructing a scale model according to the reserved characteristic points;
determining feature vectors of the feature points on the basis of the scale model;
determining the direction of the feature points according to the feature vectors;
and determining the tags of the historical police conditions according to the directions of the feature points.
Furthermore, the method also comprises the step of dimension reduction on the clustering method of the item distribution approximation of the feature vector of the feature point based on the information entropy.
The specific method for acquiring the real-time warning condition comprises the following steps:
acquiring voice information and image information of a real-time alarm condition;
preprocessing voice information and image information;
and classifying the preprocessed voice information and the preprocessed image information according to a preset safety threshold value to obtain accurate voice information and accurate image information.
The specific process of preprocessing the voice information is as follows:
whether the decibel number of the voice information is smaller than a preset threshold value or not;
if not, eliminating noise by using a Gaussian algorithm;
if yes, the voice information is amplified, and noise is removed by using a Gaussian algorithm.
Preprocessing the image information includes: and cutting the edge of the image to remove the redundant noise point image.
The technical scheme has the following beneficial effects:
by preprocessing the real-time warning condition, the filtering precision of the early warning information is improved, and the calculated amount of the neural network is reduced.
The embodiment also discloses a system for screening early warning information, as shown in fig. 2, including:
historical alert labeling module: the method is used for acquiring the historical warning situation and labeling the historical warning situation, wherein the labels are 0 and 1;
the neural network training module: the method is used for constructing a CNN neural network, and training the CNN neural network by utilizing the history warning condition with the label;
the neural network model building module: the method is used for repeated cyclic training to obtain a CNN neural network model;
the real-time warning condition acquisition module is used for: the method comprises the steps of acquiring a real-time detection alarm condition, and inputting the real-time detection alarm condition into a CNN neural network model;
the early warning information screening module: the method is used for screening the early warning information: if the screening result of the CNN neural network model is 1, triggering an alarm; and if the screening result of the CNN neural network model is 0, false early warning information is obtained.
The real-time warning condition acquisition module acquires the real-time warning condition through the camera and the infrared information sensing device. The front end uses a human-shape recognition camera to set time in the camera, human-shape information in the time is uploaded, and false information possibly appearing during alarming is that the human shape of a clothing model and the lamplight of an automobile throw outdoor human shadows into the indoor, similar to human-shape articles and the like.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (6)
1. The early warning information screening method is characterized by comprising the following steps of:
acquiring a historical warning condition, and labeling the historical warning condition, wherein the labels are 0 and 1;
constructing a CNN neural network, and training the CNN neural network by using the history warning condition with the label;
performing repeated cyclic training to obtain a CNN neural network model;
acquiring a real-time monitoring alarm condition, and inputting the real-time monitoring alarm condition into a CNN neural network model; the real-time monitoring alarm condition comprises human shape information uploaded by a human shape recognition camera within a set time in the camera, false information which possibly occurs during alarm is that the human shape of a clothing model and the light of an automobile throw outdoor human shadows into the indoor, and the human shape is similar to articles;
if the screening result of the CNN neural network model is 1, triggering an alarm;
if the screening result of the CNN neural network model is 0, false early warning information is obtained;
the steps of labeling the historical warning condition are as follows:
extracting characteristic points of the historical police conditions, and detecting the characteristic points;
removing abnormal characteristic points;
constructing a scale model according to the reserved characteristic points;
determining feature vectors of the feature points on the basis of the scale model;
determining the direction of the feature points according to the feature vectors;
determining a tag of the historical police condition according to the direction of the feature points;
the specific method for acquiring the real-time monitoring alarm condition comprises the following steps:
acquiring voice information and image information of a real-time monitoring police condition;
preprocessing voice information and image information;
and classifying the preprocessed voice information and the preprocessed image information according to a preset safety threshold value to obtain accurate voice information and accurate image information.
2. The method for screening early warning information according to claim 1, further comprising performing dimension reduction on a clustering method of feature vectors of feature points based on item distribution approximation of information entropy.
3. The method for screening early warning information according to claim 1, wherein the specific process of preprocessing the voice information is as follows:
whether the decibel number of the voice information is smaller than a preset threshold value or not;
if not, eliminating noise by using a Gaussian algorithm;
if yes, signal amplification is carried out on the voice information, and noise is removed by means of Gaussian algorithm.
4. The method for screening early warning information according to claim 1, wherein preprocessing the image information comprises: and cutting the edge of the image to remove the redundant noise point image.
5. An early warning information screening system, comprising:
historical alert labeling module: the method comprises the steps of obtaining a historical warning condition, and labeling the historical warning condition, wherein the labels are 0 and 1;
the neural network training module: the method is used for constructing a CNN neural network, and training the CNN neural network by utilizing the history warning condition with the label;
the neural network model building module: the method is used for repeated cyclic training to obtain a CNN neural network model;
the real-time warning condition acquisition module is used for: the method comprises the steps of acquiring a real-time monitoring alarm condition, and inputting the real-time monitoring alarm condition into a CNN neural network model; the real-time monitoring alarm condition comprises human shape information uploaded by a human shape recognition camera within a set time in the camera, false information which possibly occurs during alarm is that the human shape of a clothing model and the light of an automobile throw outdoor human shadows into the indoor, and the human shape is similar to articles;
the early warning information screening module: the method is used for screening the early warning information: if the screening result of the CNN neural network model is 1, triggering an alarm; if the screening result of the CNN neural network model is 0, false early warning information is obtained;
the real-time alert acquisition module is specifically configured to: acquiring voice information and image information of a real-time monitoring police condition; preprocessing voice information and image information; classifying the preprocessed voice information and the preprocessed image information according to a preset safety threshold value to obtain accurate voice information and accurate image information;
the history warning condition labeling module is specifically used for: extracting characteristic points of the historical police conditions, and detecting the characteristic points; removing abnormal characteristic points; constructing a scale model according to the reserved characteristic points; determining feature vectors of the feature points on the basis of the scale model; determining the direction of the feature points according to the feature vectors; and determining the tags of the historical police conditions according to the directions of the feature points.
6. The system according to claim 5, wherein the real-time warning information acquisition module acquires the real-time monitoring warning information through a camera and an infrared information sensing device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210269221.3A CN114611400B (en) | 2022-03-18 | 2022-03-18 | Early warning information screening method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210269221.3A CN114611400B (en) | 2022-03-18 | 2022-03-18 | Early warning information screening method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114611400A CN114611400A (en) | 2022-06-10 |
| CN114611400B true CN114611400B (en) | 2023-08-29 |
Family
ID=81865628
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210269221.3A Active CN114611400B (en) | 2022-03-18 | 2022-03-18 | Early warning information screening method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114611400B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102402621A (en) * | 2011-12-27 | 2012-04-04 | 浙江大学 | Image retrieval method based on image classification |
| CN107003977A (en) * | 2014-06-27 | 2017-08-01 | 亚马逊技术股份有限公司 | System, method and apparatus for organizing the photo of storage on a mobile computing device |
| CN107204106A (en) * | 2017-07-11 | 2017-09-26 | 河北金锁安防工程股份有限公司 | The alarm method and system of false alert are filtered out in a kind of safety-protection system |
| CN107609601A (en) * | 2017-09-28 | 2018-01-19 | 北京计算机技术及应用研究所 | A kind of ship seakeeping method based on multilayer convolutional neural networks |
| CN107968787A (en) * | 2017-12-07 | 2018-04-27 | 徐珊 | A kind of rete mirabile signaling alarm systems of man-computer cooperation |
| CN110414320A (en) * | 2019-06-13 | 2019-11-05 | 温州大学激光与光电智能制造研究院 | A kind of method and system of safety manufacture supervising |
| CN110738985A (en) * | 2019-10-16 | 2020-01-31 | 江苏网进科技股份有限公司 | Cross-modal biometric feature recognition method and system based on voice signals |
| CN110910425A (en) * | 2019-11-20 | 2020-03-24 | 上海无线电设备研究所 | Target tracking method for approaching flight process |
| CN111881791A (en) * | 2020-07-16 | 2020-11-03 | 北京宙心科技有限公司 | Security identification method and system |
| CN112070212A (en) * | 2020-08-26 | 2020-12-11 | 江苏建筑职业技术学院 | Artificial intelligence CNN, LSTM neural network dynamic identification system |
| WO2021073152A1 (en) * | 2019-10-14 | 2021-04-22 | 平安科技（深圳）有限公司 | Data label generation method and apparatus based on neural network, and terminal and medium |
| WO2021136455A1 (en) * | 2019-12-31 | 2021-07-08 | 清华大学 | Method and apparatus for recognizing police emergency similarity, and device |
| CN113096819A (en) * | 2021-03-25 | 2021-07-09 | 南通美丽霞虹智能科技有限公司 | Epidemic situation prevention, control, screening and early warning system based on neural convolutional network |
| CN113935423A (en) * | 2021-10-18 | 2022-01-14 | 广州能源检测研究院 | Power battery fault early warning method and system for coupling fuzzy control rule with Elman neural network |
| CN114021484A (en) * | 2021-11-24 | 2022-02-08 | 江苏科技大学 | Antenna simulation design optimization method based on CNN stack width learning system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018052586A1 (en) * | 2016-09-14 | 2018-03-22 | Konica Minolta Laboratory U.S.A., Inc. | Method and system for multi-scale cell image segmentation using multiple parallel convolutional neural networks |
| CN108875821A (en) * | 2018-06-08 | 2018-11-23 | Oppo广东移动通信有限公司 | The training method and device of disaggregated model, mobile terminal, readable storage medium storing program for executing |
| US11966673B2 (en) * | 2020-03-13 | 2024-04-23 | Nvidia Corporation | Sensor simulation and learning sensor models with generative machine learning methods |
-
2022
- 2022-03-18 CN CN202210269221.3A patent/CN114611400B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102402621A (en) * | 2011-12-27 | 2012-04-04 | 浙江大学 | Image retrieval method based on image classification |
| CN107003977A (en) * | 2014-06-27 | 2017-08-01 | 亚马逊技术股份有限公司 | System, method and apparatus for organizing the photo of storage on a mobile computing device |
| CN107204106A (en) * | 2017-07-11 | 2017-09-26 | 河北金锁安防工程股份有限公司 | The alarm method and system of false alert are filtered out in a kind of safety-protection system |
| CN107609601A (en) * | 2017-09-28 | 2018-01-19 | 北京计算机技术及应用研究所 | A kind of ship seakeeping method based on multilayer convolutional neural networks |
| CN107968787A (en) * | 2017-12-07 | 2018-04-27 | 徐珊 | A kind of rete mirabile signaling alarm systems of man-computer cooperation |
| CN110414320A (en) * | 2019-06-13 | 2019-11-05 | 温州大学激光与光电智能制造研究院 | A kind of method and system of safety manufacture supervising |
| WO2021073152A1 (en) * | 2019-10-14 | 2021-04-22 | 平安科技（深圳）有限公司 | Data label generation method and apparatus based on neural network, and terminal and medium |
| CN110738985A (en) * | 2019-10-16 | 2020-01-31 | 江苏网进科技股份有限公司 | Cross-modal biometric feature recognition method and system based on voice signals |
| CN110910425A (en) * | 2019-11-20 | 2020-03-24 | 上海无线电设备研究所 | Target tracking method for approaching flight process |
| WO2021136455A1 (en) * | 2019-12-31 | 2021-07-08 | 清华大学 | Method and apparatus for recognizing police emergency similarity, and device |
| CN111881791A (en) * | 2020-07-16 | 2020-11-03 | 北京宙心科技有限公司 | Security identification method and system |
| CN112070212A (en) * | 2020-08-26 | 2020-12-11 | 江苏建筑职业技术学院 | Artificial intelligence CNN, LSTM neural network dynamic identification system |
| CN113096819A (en) * | 2021-03-25 | 2021-07-09 | 南通美丽霞虹智能科技有限公司 | Epidemic situation prevention, control, screening and early warning system based on neural convolutional network |
| CN113935423A (en) * | 2021-10-18 | 2022-01-14 | 广州能源检测研究院 | Power battery fault early warning method and system for coupling fuzzy control rule with Elman neural network |
| CN114021484A (en) * | 2021-11-24 | 2022-02-08 | 江苏科技大学 | Antenna simulation design optimization method based on CNN stack width learning system |
Non-Patent Citations (1)
| Title |
|---|
| 信息融合技术在企业预警***中的应用;吴韫夏;龚花萍;;微计算机信息(第12期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114611400A (en) | 2022-06-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110745704B (en) | Tower crane early warning method and device | |
| CN109657592B (en) | Face recognition method of intelligent excavator | |
| CN110996067A (en) | Personnel safety real-time intelligent video monitoring system under high-risk operation environment based on deep learning | |
| CN209543514U (en) | Monitoring and alarm system based on recognition of face | |
| CN103839373A (en) | Sudden abnormal event intelligent identification alarm device and system | |
| CN113903081A (en) | Visual identification artificial intelligence alarm method and device for images of hydraulic power plant | |
| CN110674761B (en) | Regional behavior early warning method and system | |
| CN111341068A (en) | Drilling site dangerous area early warning system and method based on deep learning | |
| CN105426820A (en) | Multi-person abnormal behavior detection method based on security monitoring video data | |
| CN113066248B (en) | Intelligent community construction security monitoring intelligent management system based on video image processing | |
| CN113191273A (en) | Oil field well site video target detection and identification method and system based on neural network | |
| CN111523397A (en) | Intelligent lamp pole visual identification device, method and system and electronic equipment | |
| CN113743256A (en) | Construction site safety intelligent early warning method and device | |
| CN115100813B (en) | Intelligent community system based on digital twins | |
| CN114494630A (en) | Transformer substation infrastructure intelligent safety management and control method and system based on precise positioning technology | |
| CN105741503B (en) | A kind of parking lot real time early warning method under existing monitoring device | |
| CN115496640A (en) | Intelligent safety system of thermal power plant | |
| CN108776453B (en) | Building safety monitoring system based on computer | |
| CN114611400B (en) | Early warning information screening method and system | |
| CN111339970B (en) | Smoking behavior detection method suitable for public environment | |
| CN117541054A (en) | Community security monitoring method and system based on intelligent property | |
| CN113179389A (en) | System and method for identifying crane jib of power transmission line dangerous vehicle | |
| CN111597919A (en) | Human body tracking method in video monitoring scene | |
| CN116246445A (en) | Knowledge-graph-based warehouse safety multi-source Internet-of-things data early warning method | |
| CN116052035A (en) | Power plant personnel perimeter intrusion detection method based on convolutional neural network |
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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A Method and System for Screening Early Warning Information Granted publication date: 20230829 Pledgee: Agricultural Bank of China Limited Baoding Technology Branch Pledgor: HEBEI GOLDEN LOCK SAFETY ENGINEERING Co.,Ltd. Registration number: Y2024980007684 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |