CN115904499A - Artificial intelligence-based dangerous situation perception real-time early warning system and method - Google Patents
Artificial intelligence-based dangerous situation perception real-time early warning system and method Download PDFInfo
- Publication number
- CN115904499A CN115904499A CN202310169098.2A CN202310169098A CN115904499A CN 115904499 A CN115904499 A CN 115904499A CN 202310169098 A CN202310169098 A CN 202310169098A CN 115904499 A CN115904499 A CN 115904499A
- Authority
- CN
- China
- Prior art keywords
- instruction
- technical
- technical instruction
- early warning
- execution
- 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
Links
Images
Classifications
-
- 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
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention discloses a dangerous scene perception real-time early warning system and method based on artificial intelligence, relating to the technical field of artificial intelligence and comprising the following steps: s100, acquiring a first technical instruction sent to computer equipment by different terminal equipment; s200, analyzing the first technical instruction to obtain a second technical instruction and a special technical instruction; s300, analyzing and judging the scene based on the action behavior of the execution terminal; s400, performing confidence coefficient analysis on the first technical instruction by using an early warning system, and selecting whether to perform early warning according to a distribution interval of the confidence coefficient; s500, performing relevance verification on the first technical instruction and the second technical instruction; s600, when the early warning system captures a second technical instruction and a special technical instruction which do not pass correlation verification, early warning is selected, correlation and functionality are matched, systematic management of computer safety in the field of artificial intelligence is achieved, and scientificity, effectiveness and accuracy of the early warning system are improved.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a dangerous situation perception real-time early warning system and method based on artificial intelligence.
Background
Like steam engines in the steam era, power generators in the electrical era, computers in the information era and the internet, artificial intelligence is becoming the decisive force for promoting human beings to enter the intelligent era; artificial intelligence is used as the core force of a new technological revolution and industrial change, and is promoting the upgrading and updating of the traditional industry and driving the rapid development of the unmanned economy; industrial personal computers can be considered simply controllers in industrial automation machines. In addition to the mechanical part, the controller is the most critical part of a machine, from the input of data and signals to the movement of the whole machine. Each instruction in the program is analyzed and sent by the controller, so that the aim of automatically working each part of the machine is fulfilled. Due to the rapid development of computer technology, the application of connection between multiple computers and connection between external devices and computers is becoming more and more widespread. At present, most of production is not assisted by a computer, and the computer replaces manpower to a certain extent, so that the production efficiency is improved; for example, the computer sends an operation instruction to working equipment such as a machine tool and the like to control the machine to operate and produce; but there are certain problems in the process of using the computer, sometimes can cause the threat to property and even life; for example, when the computer receives the error information, the operation instruction sent out may have a certain risk, which causes a certain potential safety hazard to the production; however, a specific method is needed for determining which information is dangerous and which information has high confidence. Therefore, a dangerous situation perception real-time early warning system and a dangerous situation perception real-time early warning method based on artificial intelligence are needed to solve the problems.
Therefore, a dangerous situation perception real-time early warning system and a dangerous situation perception real-time early warning method based on artificial intelligence are urgently needed to solve the technical problems.
Disclosure of Invention
The invention aims to provide a dangerous situation perception real-time early warning system and a dangerous situation perception real-time early warning method based on artificial intelligence, and aims to solve the problems in the prior art.
In order to achieve the purpose, the invention provides the following technical scheme: a dangerous situation perception real-time early warning method based on artificial intelligence comprises the following steps:
s100, acquiring a first technical instruction sent to computer equipment by different terminal equipment by an early warning system;
s200, analyzing the first technical instruction by using an early warning system to obtain a second technical instruction required to be sent by the computer equipment and a special technical instruction required to be sent by the execution terminal when the execution terminal completes a plurality of technical instructions simultaneously;
s300, analyzing and judging scenes based on the action behaviors of the execution terminal by using an early warning system;
s400, performing confidence analysis on the first technical instructions received from each terminal device by using an early warning system, and selecting whether to perform early warning according to the distribution interval of the confidence;
s500, performing relevance verification on the first technical instruction received by the computer equipment and the analyzed second technical instruction by using an early warning system;
s600, when the early warning system captures a second technical instruction and a special technical instruction which do not pass the correlation verification, selecting to carry out early warning.
According to the above technical solution, in S100, the method includes the steps of:
s101, respectively acquiring action behaviors of different execution terminals when receiving a first technical instruction and a special technical instruction sent by computer equipment based on artificial intelligence and analyzing;
s102, acquiring the analysis process and result, and judging whether the first technical instruction and the special technical instruction cause danger or not.
According to the technical scheme, in S200:
s201, computer equipment receives first technical instructions sent by M pieces of terminal equipment;
s202, when executing the first technical instruction n, the computerThe device corresponds to an instruction sequence set needing operation and is Y nk Instruction sequence set Y nk Includes { Y nk1 ，Y nk2 ，Y nk3 ，…，Y nkm In which Y is nk1 ，Y nk2 ，Y nk3 ，…，Y nkm Respectively representing 1, 2, 3, … and m technical instructions which need to be operated when the kth execution device finishes the first technical instruction n;
all the execution terminals obtain the basic technical instruction set Y of the operation required when executing the technical instruction n corresponding to the technical instruction sequence set to be executed when finishing the technical instruction n n basic =Y nk ∩Y nk+1 ∩Y nk+2 ∩Y nk+3 ∩…∩Y nk+p (ii) a I.e. Y n is basic The technical instructions in the instruction are the k, k +1, k +2, … when the k + p execution terminals execute the first technical instruction n, the coincident technical instruction which needs to be operated appears;
s203, respectively subtracting the technical instruction sequence set which needs to be operated when different execution terminals execute the first technical instruction n from all basic technical instruction sets which need to be operated when the execution terminals execute the first technical instruction a to obtain special technical instruction sets which need to be operated when the different execution terminals execute the first technical instruction n;
s204, splitting and analyzing the technical instruction sequence set which needs to be operated when the k execution terminals execute the first technical instruction n to obtain Y nk =Y n is basic +Y nk special (ii) a Wherein, Y nk special A special technical instruction set which represents that the kth execution terminal needs to operate when executing the first technical instruction n; y is n is basic The basic technical instruction set represents that all execution terminals need to operate when executing the first technical instruction n;
s205 at Y n is basic And Y nk special The technical instruction sequence which must accord with the time sequence is analyzed and used as a key instruction node.
According to the above technical solution, in S300, the method includes the steps of:
s301, recording and analyzing operation execution tracks of the execution terminal, and forming a vector set E = { E } under the same time period 1 ，e 2 ，e 3 ，…，e a A represents the number of vectors formed by the operation execution trajectories;
s302, analyzing and recording an operation execution track in the actual execution process of the first technical instruction, and forming a vector set F = { F) in the same time period 1 ，f 2 ，f 3 ，…，f b B represents the vector quantity formed by the operation execution tracks in the actual execution process of the first technical instruction;
s303, analyzing the execution operation of the execution terminal in real time, and judging the real-time similarity between the vector set E and the vector set F;
when the real-time similarity meets the requirement, no operation is performed, when the real-time similarity does not meet the requirement, the early warning system sends out early warning prompt, and the computer equipment resets the confidence coefficient of the first technical instruction.
According to the technical scheme, in S400, the early warning system is used for carrying out confidence coefficient analysis on the first technical instructions received from each terminal device based on the computer device, whether early warning is carried out or not is selected according to the distribution interval of the confidence coefficient, meanwhile, confidence coefficient analysis processing is carried out according to the technical instructions returned after the terminal early warning is carried out, and meanwhile, the replanning adjustment is carried out in a manual intervention mode.
According to the technical scheme, in S500, a relevance check is performed on the first technical instruction sent from each terminal device and the second technical instruction received by the execution terminal by using the early warning system, where the relevance check is used to verify whether the relevance between the second technical instruction received by the execution terminal and the first technical instruction sent by the terminal device is consistent.
According to the above technical solution, in S500, performing relevance checking on a first technical instruction sent from each terminal device and a second technical instruction received by an execution terminal includes the following steps:
s501, disassembling the first technical instruction and the second technical instruction according to the instruction operation steps, for example: the method comprises the following steps of disassembling according to actual operation steps of a first technical instruction and a second technical instruction, wherein the first technical instruction consists of five steps when being actually executed, and the first technical instruction is disassembled into five parts according to the actual operation steps;
s502, forming instruction element data sets U and V respectively by the disassembled first technical instruction and second technical instruction, wherein the instruction element data sets U and V are subsets formed by each element independently, and the subsets are composed of partial technical instructions;
s503, calculating the support degree of each subset in the instruction element data sets U and V, and then eliminating the subset with small support degree according to the threshold value of the minimum support degree;
s504, each subset is added with an element which is not included in the original subset to form a plurality of new subsets, the support degree of each subset is calculated, and then the subsets with small support degrees are removed according to the threshold value of the minimum support degree;
s505, sequentially circulating until all subsets of the calculation support degree are removed by the threshold value;
s506, counting the cycle times of all removed subsets in the instruction element data sets U and V, and calculating the difference value of the cycle times of the instruction element data sets U and V;
and when the difference value does not meet the set threshold value, the early warning system performs early warning reminding.
According to the technical scheme, in S600, when the early warning system captures a second technical instruction and a special instruction which do not pass correlation verification, early warning prompt is carried out through the terminal equipment, and the special technical instruction is a new instruction formed by two or more technical instructions.
The steps are equivalent to searching for a technical instruction and a special instruction formed by executing a plurality of technologies on the control instruction when different computer equipment executes the same technical target; a single technical instruction on a manipulation instruction when different computer devices execute the same technical object is also referred to as a common technical instruction, the common instruction is often an instruction that occurs when all the computer devices execute the same technical object, and a special instruction is an instruction that occurs when different computer devices execute the same technical object due to different performance attributes or different permission settings.
According to the technical scheme, when the technical target is correspondingly realized based on one or more technical instructions, the technical instruction sequence conforming to the time sequence is analyzed and used as the key instruction node, so that the relevance connection between the technical instruction equipment end and the execution terminal is realized, the real-time early warning function of the system is realized, and the working safety is improved.
A dangerous situation perception real-time early warning system based on artificial intelligence comprises a technical instruction generation module, an artificial intelligence analysis module, a relevance verification module and an execution terminal; the technical instruction generating module is used for generating a technical instruction which enables the execution terminal to act; the artificial intelligence analysis module is used for intelligently analyzing the generated technical instruction and dividing the system interval according to the confidence coefficient of the analyzed technical instruction; the correlation checking module is used for verifying whether the correlation between the technical instruction received by the execution terminal and the technical execution sent by the technical instruction equipment terminal is consistent or not; the execution terminal is used for verifying whether the technical instruction can be correctly executed and carrying out early warning indication on the technical instruction with low reliability and danger.
According to the technical scheme, the technical instruction generation module comprises a technical instruction generation unit and a technical instruction sending unit; the technical instruction generating unit is used for generating a technical instruction, and the technical instruction sending unit is used for sending the generated technical instruction; the artificial intelligence analysis module comprises a technical instruction receiving and storing unit and an artificial intelligence analysis unit; the technical instruction receiving and storing unit is used for receiving and storing technical instructions, and the artificial intelligence analysis unit is used for analyzing and analyzing similarity of the received technical instructions; the relevance checking module comprises a relevance checking unit; the execution terminal comprises an early warning information generation unit and an early warning information real-time feedback unit, the early warning information generation unit is used for generating early warning information when dangerous scenes appear, and the early warning information real-time feedback unit is used for feeding back the early warning information when the dangerous scenes appear.
Through the technical scheme, the mutual correlation and the mutual matching of the functionality among the modules realize the systematic management of the artificial intelligence field on the computer safety, and the scientificity, the effectiveness and the accuracy of the early warning system are improved.
Compared with the prior art, the invention has the beneficial effects that: the invention provides a dangerous situation perception real-time early warning system and a dangerous situation perception real-time early warning method based on artificial intelligence, which help solve the problem that a computer possibly has certain risk when receiving error information and causes certain potential safety hazard to production, and simultaneously, when a technical target is realized correspondingly based on one or more technical instructions, a technical instruction sequence conforming to time sequence is analyzed out to be used as a key instruction node, so that the relevance connection between a technical instruction equipment end and an execution terminal is realized, the real-time early warning function of the system is realized, and the safety is improved; by utilizing the mutual correlation and functional matching among the modules, the systematic management of the artificial intelligence field on the computer safety is realized, and the scientificity, effectiveness and accuracy of the early warning system are improved.
Drawings
Fig. 1 is a schematic flow chart illustrating steps of a dangerous situation awareness real-time early warning method based on artificial intelligence according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1: as shown in fig. 1, the present invention provides the following technical solutions, a real-time early warning method for sensing dangerous situations based on artificial intelligence, the real-time early warning method comprising the following steps:
s100, acquiring a first technical instruction sent to computer equipment by different terminal equipment by an early warning system;
the method comprises the following steps:
s101, respectively acquiring action behaviors of different execution terminals when receiving a first technical instruction and a special technical instruction sent by computer equipment based on artificial intelligence and analyzing;
s102, acquiring the analysis process and result, and judging whether the first technical instruction and the special technical instruction cause danger or not.
S200, analyzing the first technical instruction by using an early warning system to obtain a second technical instruction required to be sent by the computer equipment and a special technical instruction required to be sent by the execution terminal when the execution terminal completes a plurality of technical instructions simultaneously;
the method comprises the following steps:
s201, computer equipment receives first technical instructions sent by M pieces of terminal equipment;
s202, when the first technical instruction n is executed, the instruction sequence set corresponding to the required operation of the computer equipment is Y nk Instruction sequence set Y nk Includes { Y nk1 ，Y nk2 ，Y nk3 ，…，Y nkm In which Y is nk1 ，Y nk2 ，Y nk3 ，…，Y nkm Respectively representing 1, 2, 3, … and m technical instructions which need to be operated when the kth execution device finishes the first technical instruction n;
when all the execution terminals finish the technical instruction n, the basic technical instruction set Y for the operation required when the technical instruction n is executed is obtained corresponding to the technical instruction sequence set required to be executed n is basic =Y nk ∩Y nk+1 ∩Y nk+2 ∩Y nk+3 ∩…∩Y nk+p (ii) a I.e. Y n is basic Each technical instruction in the system is a technical instruction which is overlapped when the kth, k +1, k +2, … and k + p execution terminals execute the first technical instruction n and is corresponding to the operation;
s203, respectively subtracting the technical instruction sequence set which needs to be operated when different execution terminals execute the first technical instruction n from all basic technical instruction sets which need to be operated when the execution terminals execute the first technical instruction a to obtain special technical instruction sets which need to be operated when the different execution terminals execute the first technical instruction n;
s204, respectively executing the skills required to be operated by the k execution terminals when executing the first technical instruction nResolving the technical instruction sequence set to obtain Y nk =Y n is basic +Y nk special (ii) a Wherein, Y nk special A special technical instruction set which represents that the kth execution terminal needs to operate when executing the first technical instruction n; y is n is basic The basic technical instruction set represents that all execution terminals need to operate when executing the first technical instruction n;
s205 at Y n is basic And Y nk special The technical instruction sequence which must accord with the time sequence is analyzed out to be used as a key instruction node.
S300, analyzing and judging the scene based on the action behavior of the execution terminal by using an early warning system;
the method comprises the following steps:
s301, recording and analyzing operation execution tracks of the execution terminal, and forming a vector set E = { E } under the same time period 1 ，e 2 ，e 3 ，…，e a A represents the number of vectors formed by the operation execution trajectories;
s302, analyzing and recording an operation execution track in the actual execution process of the first technical instruction, and forming a vector set F = { F) in the same time period 1 ，f 2 ，f 3 ，…，f b B represents the vector quantity formed by the operation execution tracks in the actual execution process of the first technical instruction;
s303, analyzing the execution operation of the execution terminal in real time, and judging the real-time similarity between the vector set E and the vector set F;
when the real-time similarity meets the requirement, no operation is performed, when the real-time similarity does not meet the requirement, the early warning system sends out early warning prompt, and the computer equipment resets the confidence coefficient of the first technical instruction.
By recording and analyzing the operation execution track of the execution terminal and analyzing and recording the operation execution track in the actual execution process of the first technical instruction, the similarity analysis of the instruction in the actual execution process can be realized, and whether the second technical instruction is abnormal in the analysis process of the first technical instruction is further judged.
S400, performing confidence coefficient analysis on the first technical instructions received from each terminal device by using an early warning system, and selecting whether to perform early warning according to a distribution interval of the confidence coefficient;
the method comprises the steps of utilizing an early warning system to carry out confidence degree analysis on first technical instructions received from each terminal device based on computer equipment, selecting whether to carry out early warning according to a distribution interval of confidence degrees, carrying out confidence degree analysis processing according to the technical instructions returned after the terminal early warning is executed, carrying out re-planning adjustment in a manual intervention mode, and analyzing the confidence degrees, wherein the method belongs to the prior art, and therefore excessive details are not given in the application.
S500, performing relevance verification on the first technical instruction received by the computer equipment and the analyzed second technical instruction by using an early warning system;
and performing relevance verification on the first technical instruction sent by each terminal device and the second technical instruction received by the execution terminal by using an early warning system, wherein the relevance verification is used for verifying whether the relevance between the second technical instruction received by the execution terminal and the first technical instruction sent by the terminal device is consistent.
The relevance verification of the first technical instruction sent from each terminal device and the second technical instruction received by the execution terminal comprises the following steps:
s501, disassembling the first technical instruction and the second technical instruction according to the instruction operation steps, for example: the method comprises the steps of disassembling according to actual operation steps of a first technical instruction and a second technical instruction, wherein the first technical instruction consists of five steps when actually executed, and the first technical instruction is disassembled into five parts according to the actual operation steps;
s502, forming instruction element data sets U and V respectively by the disassembled first technical instruction and second technical instruction, wherein the instruction element data sets U and V are subsets formed by each element independently, and the subsets are composed of partial technical instructions;
s503, calculating the support degree of each subset in the instruction element data sets U and V, and then eliminating the subset with the small support degree according to the threshold value of the minimum support degree;
s504, each subset is added with an element which is not included in the original subset to form a plurality of new subsets, the support degree of each subset is calculated, and then the subsets with small support degrees are removed according to the threshold value of the minimum support degree;
s505, sequentially circulating until all subsets of the calculation support degree are removed by the threshold value;
s506, counting the cycle times of all removed subsets in the instruction element data sets U and V, and calculating the difference value of the cycle times of the instruction element data sets U and V;
when the difference value meets the set threshold value, the relevance verification of the first technical instruction and the second technical instruction meets the standard, the verification is completed, and when the difference value does not meet the set threshold value, the early warning system carries out early warning reminding.
Through relevance analysis, the difference between the first technical instruction and the second technical instruction can be effectively avoided, because in the actual analysis process of the computer equipment, the analysis of the technical instruction may fail due to computer failure, and if the analysis of the technical instruction by the computer equipment fails, all the technical instructions in the subsequent analysis process of the technical instruction fail, therefore, through relevance analysis, the instruction abnormity caused by the failure of the computer equipment can be effectively avoided, whether the technical instruction is abnormal or not can be analyzed from the source, and the safety of the execution terminal for executing the second technical instruction is ensured.
S600, when the early warning system captures a second technical instruction and a special technical instruction which fail to pass the correlation verification, early warning is selected.
When the early warning system captures a second technical instruction and a special instruction which do not pass the correlation verification, early warning prompt is carried out through the terminal equipment, and the special technical instruction is a new instruction formed by two or more technical instructions.
The steps are equivalent to searching for a technical instruction and a special instruction formed by executing a plurality of technologies on the control instruction when different computer equipment executes the same technical target; a single technical instruction on a manipulation instruction when different computer devices execute the same technical object is also referred to as a common technical instruction, the common instruction is often an instruction that occurs when all the computer devices execute the same technical object, and a special instruction is an instruction that occurs when different computer devices execute the same technical object due to different performance attributes or different permission settings.
According to the technical scheme, when the technical target is correspondingly realized based on one or more technical instructions, the technical instruction sequence conforming to the time sequence is analyzed and used as the key instruction node, so that the relevance connection between the technical instruction equipment end and the execution terminal is realized, the real-time early warning function of the system is realized, and the working safety is improved.
Example 2: a dangerous situation awareness real-time early warning system based on artificial intelligence comprises a technical instruction generation module, an artificial intelligence analysis module, a correlation verification module and an execution terminal; the technical instruction generating module is used for generating a technical instruction which enables the execution terminal to act; the artificial intelligence analysis module is used for intelligently analyzing the generated technical instruction and dividing the system interval according to the confidence coefficient of the analyzed technical instruction; the relevance checking module is used for verifying whether the relevance of the technical instruction received by the execution terminal and the technical execution sent by the technical instruction equipment terminal is consistent; the execution terminal is used for verifying whether the technical instruction can be correctly executed and carrying out early warning indication on the technical instruction with low reliability and danger.
According to the technical scheme, the technical instruction generation module comprises a technical instruction generation unit and a technical instruction sending unit; the technical instruction generating unit is used for generating a technical instruction, and the technical instruction sending unit is used for sending the generated technical instruction; the artificial intelligence analysis module comprises a technical instruction receiving and storing unit and an artificial intelligence analysis unit; the technical instruction receiving and storing unit is used for receiving and storing technical instructions, and the artificial intelligence analysis unit is used for analyzing and analyzing similarity of the received technical instructions; the relevance checking module comprises a relevance checking unit; the execution terminal comprises an early warning information generation unit and an early warning information real-time feedback unit, the early warning information generation unit is used for generating early warning information when dangerous situations occur, and the early warning information real-time feedback unit is used for feeding back the early warning information when the dangerous situations occur.
By mutual correlation and functional matching between the modules, systematic management of the artificial intelligence field on computer safety is realized, and scientificity, effectiveness and accuracy of the early warning system are improved.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (10)
1. A dangerous situation perception real-time early warning method based on artificial intelligence is characterized by comprising the following steps:
s100, acquiring a first technical instruction sent to computer equipment by different terminal equipment by an early warning system;
s200, analyzing the first technical instruction by using an early warning system to obtain a second technical instruction required to be sent by the computer equipment and a special technical instruction required to be sent by the execution terminal when the execution terminal completes a plurality of technical instructions simultaneously;
s300, analyzing and judging scenes based on the action behaviors of the execution terminal by using an early warning system;
s400, performing confidence coefficient analysis on the first technical instructions received from each terminal device by using an early warning system, and selecting whether to perform early warning according to a distribution interval of the confidence coefficient;
s500, performing relevance verification on the first technical instruction received by the computer equipment and the analyzed second technical instruction by using an early warning system;
s600, when the early warning system captures a second technical instruction and a special technical instruction which fail to pass the correlation verification, early warning is selected.
2. The real-time early warning method for dangerous situation awareness based on artificial intelligence of claim 1, wherein in S100, the method comprises the following steps:
s101, respectively acquiring action behaviors of different execution terminals when receiving a first technical instruction and a special technical instruction sent by computer equipment based on artificial intelligence and analyzing;
s102, acquiring the analysis process and result, and judging whether the first technical instruction and the special technical instruction cause danger or not.
3. The artificial intelligence based dangerous context awareness real-time early warning method according to claim 2, wherein in S200:
s201, receiving a first technical instruction sent by M terminal devices by computer equipment;
s202, when the first technical instruction n is executed, the instruction sequence set corresponding to the operation needed by the computer equipment is Y nk Instruction sequence set Y nk Includes { Y nk1 ，Y nk2 ，Y nk3 ，…，Y nkm In which Y is nk1 ，Y nk2 ，Y nk3 ，…，Y nkm Respectively representing 1, 2, 3, … and m technical instructions which need to be operated when the kth execution device finishes the first technical instruction n;
when all the execution terminals finish the technical instruction n, the basic technical instruction set Y for the operation required when the technical instruction n is executed is obtained corresponding to the technical instruction sequence set required to be executed n basic =Y nk ∩Y nk+1 ∩Y nk+2 ∩Y nk+3 ∩…∩Y nk+p (ii) a I.e. Y n basic The technical instructions in the instruction are the k, k +1, k +2, … and k + p executionsWhen the line terminal executes the first technical instruction n, the technical instruction which is required to be operated and is overlapped appears;
s203, respectively subtracting the technical instruction sequence set which needs to be operated when different execution terminals execute the first technical instruction n from all basic technical instruction sets which need to be operated when the execution terminals execute the first technical instruction a to obtain special technical instruction sets which need to be operated when the different execution terminals execute the first technical instruction n;
s204, splitting and analyzing the technical instruction sequence set which needs to be operated when the k execution terminals execute the first technical instruction n to obtain Y nk =Y n basic +Y nk special (ii) a Wherein, Y nk special A special technical instruction set which represents that the kth execution terminal needs to operate when executing the first technical instruction n; y is n basic The basic technical instruction set represents that all execution terminals need to operate when executing the first technical instruction n;
s205 at Y n is basic And Y nk is special The technical instruction sequence which must accord with the time sequence is analyzed out to be used as a key instruction node.
4. The dangerous context awareness real-time early warning method based on artificial intelligence as claimed in claim 3, wherein in S300, the method comprises the following steps:
s301, recording and analyzing the operation execution track of the execution terminal to form a vector set E = { E } under the same time period 1 ，e 2 ，e 3 ，…，e a A represents the vector quantity formed by the operation execution tracks;
s302, analyzing and recording an operation execution track in the actual execution process of the first technical instruction, and forming a vector set F = { F ] in the same time period 1 ，f 2 ，f 3 ，…，f b B represents the vector quantity formed by the operation execution tracks in the actual execution process of the first technical instruction;
s303, analyzing the execution operation of the execution terminal in real time, and judging the real-time similarity between the vector set E and the vector set F;
when the real-time similarity meets the requirement, no operation is performed, when the real-time similarity does not meet the requirement, the early warning system sends out early warning prompt, and the computer equipment resets the confidence coefficient of the first technical instruction.
5. The artificial intelligence based dangerous situation awareness real-time early warning method according to claim 4, wherein: in S400, the early warning system is used to perform confidence level analysis on the first technical instruction received from each terminal device based on the computer device, and whether to perform early warning is selected according to the distribution interval of the confidence level, and meanwhile, the early warning system performs confidence level analysis processing according to the technical instruction returned after performing the terminal early warning, and performs re-planning and adjustment in a manual intervention manner.
6. The artificial intelligence based dangerous situation awareness real-time early warning method according to claim 5, wherein: in S500, a relevance check is performed on the first technical instruction sent from each terminal device and the second technical instruction received by the execution terminal by using the early warning system, where the relevance check is used to verify whether the relevance between the second technical instruction received by the execution terminal and the first technical instruction sent by the terminal device is consistent.
7. The artificial intelligence based dangerous situation awareness real-time early warning method according to claim 6, wherein: in S500, performing relevance checking on the first technical instruction sent from each terminal device and the second technical instruction received by the execution terminal includes the following steps:
s501, disassembling the first technical instruction and the second technical instruction according to the instruction operation steps, for example: the method comprises the steps of disassembling according to actual operation steps of a first technical instruction and a second technical instruction, wherein the first technical instruction consists of five steps when actually executed, and the first technical instruction is disassembled into five parts according to the actual operation steps;
s502, forming instruction element data sets U and V respectively by the disassembled first technical instruction and second technical instruction, wherein the instruction element data sets U and V are subsets formed by each element independently, and the subsets are composed of partial technical instructions;
s503, calculating the support degree of each subset in the instruction element data sets U and V, and then eliminating the subset with small support degree according to the threshold value of the minimum support degree;
s504, each subset is added with an element which is not included in the original subset to form a plurality of new subsets, the support degree of each subset is calculated, and then the subsets with small support degrees are removed according to the threshold value of the minimum support degree;
s505, sequentially circulating until all the subsets for calculating the support degree are removed by the threshold value;
s506, counting the cycle times of all removed subsets in the instruction element data sets U and V, and calculating the difference value of the cycle times of the instruction element data sets U and V;
when the difference value meets the set threshold value, the relevance verification of the first technical instruction and the second technical instruction meets the standard, the verification is completed, and when the difference value does not meet the set threshold value, the early warning system carries out early warning reminding.
8. The artificial intelligence based dangerous context awareness real-time early warning method according to claim 7, wherein: in S600, when the second technical instruction and the special instruction which do not pass the correlation verification are captured by the early warning system, an early warning prompt is performed through the terminal device, and the special technical instruction is a new instruction formed by two or more technical instructions.
9. An artificial intelligence based danger context awareness real-time early warning system for implementing an artificial intelligence based danger context awareness real-time early warning method as claimed in any one of claims 1 to 8, characterized in that: the early warning system comprises a technical instruction generating module, an artificial intelligence analyzing module, a correlation checking module and an execution terminal; the technical instruction generating module is used for generating a technical instruction which enables the execution terminal to act; the artificial intelligence analysis module is used for intelligently analyzing the generated technical instruction and dividing the system interval according to the confidence coefficient of the analyzed technical instruction; the correlation checking module is used for verifying whether the correlation between the technical instruction received by the execution terminal and the technical execution sent by the technical instruction equipment terminal is consistent or not; the execution terminal is used for verifying whether the technical instruction can be correctly executed and carrying out early warning indication on the technical instruction with low reliability and danger.
10. The artificial intelligence based dangerous context awareness real-time early warning system according to claim 9, wherein: the technical instruction generating module comprises a technical instruction generating unit and a technical instruction sending unit; the technical instruction generating unit is used for generating a technical instruction, and the technical instruction sending unit is used for sending the generated technical instruction; the artificial intelligence analysis module comprises a technical instruction receiving and storing unit and an artificial intelligence analysis unit; the technical instruction receiving and storing unit is used for receiving and storing technical instructions, and the artificial intelligence analysis unit is used for analyzing and analyzing similarity of the received technical instructions; the relevance checking module comprises a relevance checking unit; the execution terminal comprises an early warning information generation unit and an early warning information real-time feedback unit, the early warning information generation unit is used for generating early warning information when dangerous situations occur, and the early warning information real-time feedback unit is used for feeding back the early warning information when the dangerous situations occur.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310169098.2A CN115904499B (en) | 2023-02-27 | 2023-02-27 | Dangerous situation awareness real-time early warning system and method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310169098.2A CN115904499B (en) | 2023-02-27 | 2023-02-27 | Dangerous situation awareness real-time early warning system and method based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115904499A true CN115904499A (en) | 2023-04-04 |
| CN115904499B CN115904499B (en) | 2023-05-09 |
Family
ID=85750260
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310169098.2A Active CN115904499B (en) | 2023-02-27 | 2023-02-27 | Dangerous situation awareness real-time early warning system and method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115904499B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105934765A (en) * | 2013-11-29 | 2016-09-07 | 通用电气航空系统有限公司 | Method of construction of anomaly models from abnormal data |
| CN110688877A (en) * | 2018-07-05 | 2020-01-14 | 杭州海康威视数字技术股份有限公司 | Danger early warning method, device, equipment and storage medium |
| CN110853073A (en) * | 2018-07-25 | 2020-02-28 | 北京三星通信技术研究有限公司 | Method, device, equipment and system for determining attention point and information processing method |
| CN111260525A (en) * | 2020-01-16 | 2020-06-09 | 深圳市广道高新技术股份有限公司 | Community security situation perception and early warning method, system and storage medium |
| CN114615255A (en) * | 2022-04-07 | 2022-06-10 | 哈尔滨博敏科技开发有限公司 | Computer remote control management system and method based on artificial intelligence |
| CN114882666A (en) * | 2022-05-05 | 2022-08-09 | 深圳市富菱楼宇科技有限公司 | Intelligent household fire early warning method and system, terminal device and storage medium |
-
2023
- 2023-02-27 CN CN202310169098.2A patent/CN115904499B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105934765A (en) * | 2013-11-29 | 2016-09-07 | 通用电气航空系统有限公司 | Method of construction of anomaly models from abnormal data |
| CN110688877A (en) * | 2018-07-05 | 2020-01-14 | 杭州海康威视数字技术股份有限公司 | Danger early warning method, device, equipment and storage medium |
| CN110853073A (en) * | 2018-07-25 | 2020-02-28 | 北京三星通信技术研究有限公司 | Method, device, equipment and system for determining attention point and information processing method |
| CN111260525A (en) * | 2020-01-16 | 2020-06-09 | 深圳市广道高新技术股份有限公司 | Community security situation perception and early warning method, system and storage medium |
| CN114615255A (en) * | 2022-04-07 | 2022-06-10 | 哈尔滨博敏科技开发有限公司 | Computer remote control management system and method based on artificial intelligence |
| CN114882666A (en) * | 2022-05-05 | 2022-08-09 | 深圳市富菱楼宇科技有限公司 | Intelligent household fire early warning method and system, terminal device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115904499B (en) | 2023-05-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111008473A (en) | Simulation analysis method and device for power equipment and storage medium | |
| US11567489B2 (en) | Method and device for efficient fault analysis through simulated faults in a digital twin | |
| CN104008046A (en) | Method and device for testing programs | |
| CN115904499B (en) | Dangerous situation awareness real-time early warning system and method based on artificial intelligence | |
| CN110570646B (en) | Four-remote signal acceptance method and system based on historical data | |
| CN115687137A (en) | Automatic testing method and device for industrial robot, demonstrator and storage medium | |
| CN112860587B (en) | UI automatic test method and device | |
| Zheng | Real-time simulation in real-time systems: Current status, research challenges and a way forward | |
| CN113672234A (en) | Intelligent progress monitoring method and system for numerical control equipment | |
| EP3608786B1 (en) | Systems and methods of requirements chaining and applications thereof | |
| CN112231062A (en) | Safety test system and method for programmable industrial controller | |
| CN102520676A (en) | Operation order generation method and related device | |
| CN112580942A (en) | Substation operation ticket library configuration method and sequence control operation task generation method | |
| CN113032260A (en) | Fault injection simulation test method and system based on componentized distributed system | |
| JP7421260B1 (en) | Vulnerability mining method and system for competitive industrial control systems | |
| EP4270121A1 (en) | Method and system for seamless transition of runtime system from controller device to digitalization platform | |
| RU2787274C1 (en) | Method for ensuring the stable functioning of a complex hardware and software object of a complex functional-dynamic system | |
| EP4113282A1 (en) | Method and system for generating programs for an automation system by code-similarity based approach | |
| US20220365864A1 (en) | Program development device, and program for providing program development device | |
| CN115826503B (en) | Machine tool remote diagnosis method based on industrial internet big data | |
| EP4254200A1 (en) | Method and system for eradicating programmatical errors from engineering programs in a technical installation | |
| CN115589407B (en) | File transmission verification method based on PLM-DNC integrated system | |
| CN110990998B (en) | Intelligent manufacturing process system for gearbox body | |
| Luckcuck | Monitoring Robotic Systems using CSP: From Safety Designs to Safety Monitors | |
| CN117435894A (en) | Cloud edge cooperation-based intelligent GIS equipment fault positioning detection method and system |
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 |