CN114662864A - Team work intelligent management and control method and system based on artificial intelligence - Google Patents
Team work intelligent management and control method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN114662864A CN114662864A CN202210203726.XA CN202210203726A CN114662864A CN 114662864 A CN114662864 A CN 114662864A CN 202210203726 A CN202210203726 A CN 202210203726A CN 114662864 A CN114662864 A CN 114662864A
- Authority
- CN
- China
- Prior art keywords
- abnormal phenomenon
- abnormal
- target
- pixel point
- image
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a team work intelligent management and control method and system based on artificial intelligence, wherein the method comprises the following steps: receiving service data of a plurality of dispersedly deployed independent operation information systems, and performing data association merging and standardization processing to obtain an operation plan set; receiving first monitoring video data, and identifying a first abnormal phenomenon based on the first monitoring video data, wherein the first abnormal phenomenon represents a static abnormal phenomenon of an electric power scene; second monitoring video data are called based on the operation plan, and the execution progress, the first abnormal phenomenon and the second abnormal phenomenon of the operation plan are identified based on the second monitoring video data, wherein the second abnormal phenomenon represents the abnormal phenomenon related to the operation execution process. The invention realizes unified management of the operation plan information related to various systems, avoids the problem of repeated entry of team operation plan data, and simultaneously realizes intelligent identification of potential safety hazards of violation of operation sites and macroscopically controls the safety of the operation sites.
Description
Technical Field
The invention relates to the technical field of electric power operation management, in particular to a team and group operation intelligent management and control method and system based on artificial intelligence.
Background
In recent years, information technologies such as cloud computing, big data, internet of things and mobile application are rapidly developed, new opportunities are brought to the changes of production modes and management modes of power enterprises, and conditions are provided for promoting the technical changes and innovative development of power industries. However, in the aspect of achieving the final goals of online operation, data sharing and support intelligence of the security supervision team, certain gaps still exist, for example, due to the fact that plan management dimensions are different and different requirements exist in a plurality of professional departments such as company power transmission, power transformation, power distribution, communication, infrastructure, marketing and the like, an operation plan has the situation that a plurality of sets of service systems are repeatedly input, and further operation site safety control cannot be effectively conducted according to operation plan requirements.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides an intelligent team work management and control method and system based on artificial intelligence, which are used for uniformly managing work plan information related to various systems, so that the intelligent identification of potential safety hazards of a work site and the macro control of the safety of the work site are realized. The technical scheme is as follows:
in a first aspect, the invention provides an intelligent team work management and control method based on artificial intelligence, which comprises the following steps:
s1: receiving service data of a plurality of dispersedly deployed independent operation information systems, and performing data association combination and normalization processing to obtain an operation plan set;
s2: receiving first monitoring video data of a first preset monitoring point, and identifying a first abnormal phenomenon based on the first monitoring video data, wherein the first abnormal phenomenon represents a static abnormal phenomenon of an electric power scene;
s3: second monitoring video data of a second monitoring point are called based on the operation plan, the execution progress, the first abnormal phenomenon and the second abnormal phenomenon of the operation plan are identified based on the second monitoring video data, and the second abnormal phenomenon represents the abnormal phenomenon related to the operation execution process.
Preferably, the step S2 includes:
acquiring a first characteristic pixel point in a scene image based on the scene image of a first preset monitoring point, wherein the first characteristic pixel point corresponds to a target in the scene image;
and identifying whether the target corresponding to the first characteristic pixel point is abnormal or not based on the first characteristic pixel point and a preset first analysis algorithm.
Preferably, the identifying whether the target corresponding to the first characteristic pixel point is abnormal or not based on the first characteristic pixel point and a preset first analysis algorithm includes:
acquiring a preset target area generation algorithm, and combining the target area generation algorithm and the first characteristic pixel points to obtain a scene image target area corresponding to the first characteristic pixel points;
and determining whether the target in the target area is abnormal or not based on the target type based on the preset second analysis algorithm and the target area of the scene image.
Preferably, the method for acquiring the first characteristic pixel point includes:
(1) selecting a candidate first characteristic pixel point position in a first preset monitoring point scene image;
(2) taking the candidate first characteristic pixel point position as a center, searching for a peripheral pixel point, judging the magnitude of the incidence relation between the peripheral pixel point and the candidate first characteristic pixel point, and stopping until the peripheral pixel point of which the incidence relation is smaller than a preset incidence threshold value is searched;
(3) judging whether pixel points which are not searched exist, if so, selecting a candidate first characteristic pixel point position from the pixel points which are not searched;
(4) and (4) repeating the steps (2) and (3) until all pixel points of the scene image of the first preset monitoring point are searched, and acquiring first characteristic pixel points based on all candidate first characteristic pixel points.
Preferably, when the first characteristic pixel point is obtained, the method includes:
analyzing the neighborhood pixels of the candidate first characteristic pixel points, comparing the pixel point characteristics of the neighborhood pixels with the pixel point characteristics of the candidate first characteristic pixel points, if the distribution difference of the comparison result between the first characteristic pixel points and the neighborhood pixels is larger than a preset threshold value, selecting one pixel point in the neighborhood pixels as a new candidate first characteristic pixel point, and if the distribution difference of the comparison result is smaller than or equal to the preset threshold value, determining to keep the candidate first characteristic pixel points.
Preferably, the determining whether the target area is abnormal or not based on the target type and the target area of the scene image based on a preset second analysis algorithm includes:
determining a target type of the target area based on the scene image target area;
and determining whether the target in the target area is abnormal or not based on the target type or the target type based on the mutual distance relationship between the target type of the target area and the target geographic position of the target area.
Preferably, the step S3 includes:
acquiring continuous image frames based on second monitoring video data of a second monitoring point;
and respectively carrying out image analysis from space and time based on the continuous image frames, and determining static abnormal phenomena in a single image frame and dynamic abnormal phenomena in the continuous image frames.
Preferably, the determining the static abnormal phenomena in the single image frame and the dynamic abnormal phenomena in the continuous image frames based on the image analysis performed on the continuous image frames from space and time respectively comprises:
carrying out operation area positioning and area personnel number determination on operators in the operation scene image;
judging the type of the violation behaviors to be detected in the operation area according to the operation plan;
determining an image analysis area for each operator in the operation area based on the type of the violation behaviors to be detected;
and summarizing and analyzing the sub-regions of the images to be analyzed of each operator corresponding to the same type of illegal behaviors to be detected, and determining whether the abnormal phenomenon occurs and the operator with the abnormal phenomenon according to the summarized result.
Preferably, the summarizing and analyzing the sub-regions of the image to be analyzed of each operator corresponding to the same type of violation behaviors to be detected includes:
extracting a first characteristic parameter from a sub-region of an image to be analyzed of each operator, which is acquired based on the same type of illegal behaviors to be detected, wherein the first characteristic parameter represents pixel distribution characteristics in the sub-region of the image;
and clustering based on each first characteristic parameter to obtain candidate violation workers corresponding to the first characteristic parameter category of the violation behaviors in the characterization image sub-area.
Preferably, the clustering is performed based on each first characteristic parameter to obtain the candidate violation workers corresponding to the first characteristic parameter category of the violation behaviors appearing in the characterization image sub-region, and the method further includes:
acquiring each image subregion in a first characteristic parameter category representing the violation behaviors in the image subregions based on the clustering result of the first characteristic parameter;
and identifying the behavior of the image subareas based on each image subarea in the first characteristic parameter category of the violation behaviors in the acquired characterization image subareas, and determining whether the violation behaviors occur in the image subareas.
In a second aspect, the present invention provides an intelligent team work management and control system based on artificial intelligence, including:
the operation plan association and combination module is used for receiving the service data of a plurality of dispersedly deployed independent operation information systems, performing data association and combination and standardization processing and acquiring an operation plan set;
the first abnormal phenomenon monitoring module is used for receiving first monitoring video data of a first preset monitoring point and identifying a first abnormal phenomenon based on the first monitoring video data, wherein the first abnormal phenomenon represents a static abnormal phenomenon of an electric power scene;
and the second abnormal phenomenon monitoring module is used for calling second monitoring video data of a second monitoring point based on the operation plan, and identifying the execution progress, the first abnormal phenomenon and the second abnormal phenomenon of the operation plan based on the second monitoring video data, wherein the second abnormal phenomenon represents the abnormal phenomenon associated with the operation execution process.
The team work intelligent management and control method and system based on artificial intelligence have the following beneficial effects: the method comprises the steps of carrying out data association and combination on service data of a plurality of independent operation information systems which are deployed in a scattered mode to obtain a unified operation plan set, providing effective data for safety control management in the subsequent operation execution process based on the unified operation plan set, and meanwhile achieving intelligent identification of various potential safety hazards of an operation field and macroscopically controlling the safety of the operation field.
Drawings
FIG. 1 is a flowchart illustrating an intelligent team work management method based on artificial intelligence according to an embodiment of the present disclosure;
fig. 2 is a structural diagram of an intelligent team work management and control system based on artificial intelligence according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the application provides an intelligent team work management and control method based on artificial intelligence, which comprises the following steps:
s1: receiving service data of a plurality of dispersedly deployed independent operation information systems, and performing data association combination and normalization processing to obtain an operation plan set;
s2: receiving first monitoring video data of a first preset monitoring point, and identifying a first abnormal phenomenon based on the first monitoring video data, wherein the first abnormal phenomenon represents a static abnormal phenomenon of an electric power scene;
s3: second monitoring video data of a second monitoring point are called based on the operation plan, the execution progress, the first abnormal phenomenon and the second abnormal phenomenon of the operation plan are identified based on the second monitoring video data, and the second abnormal phenomenon represents the abnormal phenomenon related to the operation execution process.
In the embodiment of the application, data association and combination are carried out on service data of a plurality of dispersedly deployed independent operation information systems, a unified operation plan set is obtained, and effective data are provided for safety management and control management in the subsequent operation execution process based on the unified operation plan set.
Further, for a non-real-time operation area, in the embodiment of the present application, it is mainly to analyze whether a first abnormal phenomenon occurs to equipment in an electric power scene, such as a line foreign matter, smoke, a mountain fire, a crane, a tower crane, an excavator, etc., and for a real-time operation area, in the embodiment of the present application, it is mainly to analyze and detect a violation behavior and a dangerous behavior of an operator, such as a violation behavior of correct wearing, smoking, gathering of a safety helmet, a safety belt, a work clothes, etc.
According to the embodiment of the application, unified management of the operation plan information related to various systems is achieved, the problem of repeated entry of team operation plan data is solved, meanwhile, intelligent identification of potential safety hazards of operation site violation is achieved, and the safety of the operation site is controlled macroscopically.
Further, the step S2 includes:
acquiring a first characteristic pixel point in a scene image based on the scene image of a first preset monitoring point, wherein the first characteristic pixel point corresponds to a target in the scene image;
and identifying whether the target corresponding to the first characteristic pixel point is abnormal or not based on the first characteristic pixel point and a preset first analysis algorithm.
In the embodiment of the application, whether the target corresponding to the first characteristic pixel point is abnormal or not is further determined by determining the first characteristic pixel point, so that under the conditions of uncertain number of targets, uncertain target positions and uncertain target types in a scene image, the scene image is repeatedly identified by directly adopting a plurality of target detection algorithms and a plurality of abnormal phenomenon analysis algorithms, the number of targets and the approximate position of each target in the scene image can be simultaneously determined based on the number and the position of the first pixel points, and further based on the first characteristic pixel points and the preset first analysis algorithm, the target area of each target consisting of a plurality of pixel points belonging to the same target as the first characteristic pixel points of the scene image can be determined, the type of the target can be determined based on the pixel characteristics of the plurality of pixel points belonging to the same target as the first characteristic pixel points, and whether the target has an abnormal phenomenon can be further determined.
Further, the identifying whether the target corresponding to the first characteristic pixel point is abnormal based on the first characteristic pixel point and a preset first analysis algorithm includes:
acquiring a preset target area generation algorithm, and combining the target area generation algorithm and the first characteristic pixel points to obtain a scene image target area corresponding to the first characteristic pixel points;
and determining whether the target in the target area is abnormal or not based on the target type based on a preset second analysis algorithm and the target area of the scene image.
Further, the method for acquiring the first characteristic pixel point includes:
(1) selecting a candidate first characteristic pixel point position in a first preset monitoring point scene image;
(2) taking the candidate first characteristic pixel point position as a center, searching for a peripheral pixel point, judging the magnitude of the incidence relation between the peripheral pixel point and the candidate first characteristic pixel point, and stopping until the peripheral pixel point of which the incidence relation is smaller than a preset incidence threshold value is searched;
(3) judging whether pixel points which are not searched exist, if so, selecting a candidate first characteristic pixel point position from the pixel points which are not searched;
(4) and (4) repeating the steps (2) and (3) until all pixel points of the scene image of the first preset monitoring point are searched, and acquiring first characteristic pixel points based on all candidate first characteristic pixel points.
In the embodiment of the application, in the acquisition of the first characteristic pixel point, with the candidate first characteristic pixel point as a center, the pixel point is acquired by peripheral search, the peripheral pixel point with the incidence relation smaller than the preset incidence threshold value is searched, a target area cut-off region of a target corresponding to the first characteristic pixel point can be determined, the pixel point acquired by the peripheral search is the pixel point in a target area of another target, namely the pixel point acquired by the peripheral search is continued in the target area cut-off region, and the pixel point can be another candidate first characteristic pixel point. In the embodiment of the application, the defect that the targets in the scene image are repeatedly detected and identified by directly adopting various target detection algorithms is further avoided, and the process of identifying and detecting the targets of multiple target types in the scene image is reduced.
Further, when obtaining the first characteristic pixel point, the method includes:
analyzing the neighborhood pixels of the candidate first characteristic pixel points, comparing the pixel point characteristics of the neighborhood pixels with the pixel point characteristics of the candidate first characteristic pixel points, if the distribution difference of the comparison result between the first characteristic pixel points and the neighborhood pixels is larger than a preset threshold value, selecting one pixel point in the neighborhood pixels as a new candidate first characteristic pixel point, and if the distribution difference of the comparison result is smaller than or equal to the preset threshold value, determining to keep the candidate first characteristic pixel points.
In the embodiment of the application, after the candidate first feature pixel points are obtained through the steps (1) to (4), the position analysis of the candidate first feature pixel points is performed, whether the candidate first feature pixel points are located at the boundary position of the target area is analyzed, if yes, one pixel point is selected from the neighborhood pixels to replace the candidate first feature pixel points, and it is ensured that the first feature pixel points correspond to the target in the scene image. Specifically, when the distribution of the comparison results of the first characteristic pixel point and the neighboring pixels is similar, it is determined that the position of the first characteristic pixel point is not the boundary position of the target region, and when the distribution difference of the comparison results of the first characteristic pixel point and the neighboring pixels is large, it is determined that the position of the first characteristic pixel point is the boundary position of the target region. The comparison result of the first characteristic pixel point and the neighboring pixel may be a characteristic difference loss value of the first characteristic pixel point and the neighboring pixel, and may be calculated based on a loss function.
Further, the determining whether the target in the target area is abnormal or not based on the preset second analysis algorithm and the target area of the scene image or determining whether the target in the target area is abnormal based on the target type includes:
determining a target type of the target area based on the scene image target area;
and determining whether the target in the target area is abnormal or not based on the target type based on the mutual distance relationship between the target type of the target area and the target geographic position of the target area.
In the embodiment of the application, the analysis of the first abnormal phenomenon comprises the analysis of the line foreign matter, the smoke, the mountain fire, the crane, the tower crane and the excavator, after the line target area and the line position in the scene image are determined, the distance relation between other targets in the scene image, such as the crane, the tower crane and the excavator, and the line is analyzed, so that whether the line hidden danger exists or not is determined, whether other targets in the scene image are the line foreign matter, the smoke and the mountain fire or not is analyzed, and if the line hidden danger exists, the line hidden danger is determined.
In this embodiment of the application, determining the target type of the target area may be performed by using a target detection algorithm, which is not limited herein.
Further, the step S3 includes:
acquiring continuous image frames based on second monitoring video data of a second monitoring point;
and respectively carrying out image analysis from space and time based on the continuous image frames, and determining static abnormal phenomena in a single image frame and dynamic abnormal phenomena in the continuous image frames.
In the embodiment of the present application, the analysis of the second abnormal phenomenon may be a static abnormal phenomenon in a single image frame and a dynamic abnormal phenomenon in a continuous image frame based on the continuous image frame. For example, if it is determined that the operator aggregation phenomenon has occurred based on a number of consecutive image frames, it may be determined that the abnormal phenomenon has occurred in a single image frame, for example, if the trajectory of the operator is determined based on a number of consecutive image frames, it may be determined whether the operator's trajectory has an abnormal phenomenon, that is, it may be determined whether a dynamic abnormal phenomenon has occurred in consecutive image frames.
Further, the above-mentioned determining the static abnormal phenomena in the single image frame and the dynamic abnormal phenomena in the continuous image frames based on the image analysis performed on the continuous image frames from space and time respectively includes:
performing operation area positioning and area personnel number determination on operators in the operation scene image;
judging the type of the violation behaviors to be detected in the operation area according to the operation plan;
determining an image analysis area for each operator in the operation area based on the type of the violation behaviors to be detected;
and summarizing and analyzing the sub-regions of the images to be analyzed of each operator corresponding to the same type of illegal behaviors to be detected, and determining whether the abnormal phenomenon occurs and the operator with the abnormal phenomenon according to the summarized result.
The type of the violation behaviors to be detected in the operation area is judged according to the operation plan, for example, if the operation plan contains ascending operations, the violation behaviors to be detected can be determined to include the violation behaviors possibly existing in the ascending operations, such as whether safety belts are worn correctly or not. Personnel detection and positioning can be performed on all operating personnel in the operating plan, and the types of the violation behaviors to be detected are determined to include whether the safety helmet is worn correctly, whether the working clothes are worn correctly, whether smoking occurs, whether personnel gather and the like.
Summarizing and analyzing image subregions to be analyzed of each operator corresponding to the same type of violation behaviors to be detected, determining whether an abnormal phenomenon occurs and operators with the abnormal phenomenon according to a summarizing result, for example, detecting whether safety helmets of the operators wear the safety helmets, positioning the head region image subregion of each operator, summarizing and analyzing based on the head region image subregions of all the operators, wherein it can be understood that in one case, the total number of people who need to wear the safety helmets is determined based on all the operators in an operation plan, in a case that all the operators who need to wear the safety helmets, the summarizing result of the head region image subregions of all the operators corresponds to a theoretical summarizing image characteristic parameter, and in summarizing and analyzing the head region image subregions of all the operators, and if the difference between the summary analysis result and the theoretical summary image characteristic parameter is larger than a preset difference threshold value, determining that the phenomenon of abnormal wearing of the safety helmet of the operator exists. In the embodiment of the application, the complex calculation of the safety helmet wearing detection is avoided directly being carried out on all the operating personnel one by one.
Further, the summarizing and analyzing the sub-area of the image to be analyzed of each operator corresponding to the same type of violation behaviors to be detected includes:
extracting a first characteristic parameter from a sub-region of an image to be analyzed of each operator, which is acquired based on the same type of illegal behaviors to be detected, wherein the first characteristic parameter represents pixel distribution characteristics in the sub-region of the image;
and clustering based on each first characteristic parameter to obtain candidate violation workers corresponding to the first characteristic parameter category with violation behaviors in the characterization image sub-region.
In the embodiment of the application, the first characteristic parameter is extracted from the image subarea to be analyzed of each operator, which is obtained by the same type of illegal activity to be detected, and the first characteristic parameter is clustered, so that it can be understood that the image subarea of the operator who has the illegal activity and the image subarea of the operator who does not have the illegal activity are obviously different, a class set of the image subareas which are judged to have the illegal activity can be obtained by clustering the first characteristic parameter of the image subarea, the possibility that the illegal activity occurs to the operator corresponding to the image subarea in the class set is higher, namely, the probability of the illegal activity is higher than the probability of the illegal activity.
Further, the above clustering based on each first characteristic parameter to obtain the candidate violation workers corresponding to the first characteristic parameter category in which the violation occurs in the characterization image sub-region further includes:
acquiring each image subregion in a first characteristic parameter category representing that the violation behaviors occur in the image subregions based on the clustering result of the first characteristic parameters;
and identifying the behavior of the image subareas based on each image subarea in the first characteristic parameter category of the violation behaviors in the acquired characterization image subareas, and determining whether the violation behaviors occur in the image subareas.
In the embodiment of the application, image analysis is respectively carried out from space and time based on continuous image frames, static abnormal phenomena in a single image frame and dynamic abnormal phenomena in the continuous image frames are determined, whether the static abnormal phenomena exist in the single image frame is determined based on the spatial pixel distribution characteristics of the single image frame, position change of a target area of a same target in the continuous time sequence image frames is positioned and tracked based on the continuous image frames, a plurality of target area images of the same target in the continuous time sequence image frames are obtained, and whether the dynamic abnormal phenomena occur in the target is analyzed based on the plurality of target area images of the same target.
In the embodiment of the application, in order to avoid misjudgment of the operating personnel violation behaviors corresponding to the first characteristic parameter category for representing the violation behaviors in the image sub-regions in the clustering result, the image sub-regions in the class set of the image sub-regions judged to have the violation behaviors are further subjected to behavior identification, and whether the image sub-regions have the violation behaviors or not is determined.
The embodiment of the application further provides a team work intelligent management and control system based on artificial intelligence, include:
the operation plan association and combination module is used for receiving the service data of a plurality of dispersedly deployed independent operation information systems, performing data association and combination and standardization processing and acquiring an operation plan set;
the first abnormal phenomenon monitoring module is used for receiving first monitoring video data of a first preset monitoring point and identifying a first abnormal phenomenon based on the first monitoring video data, wherein the first abnormal phenomenon represents a static abnormal phenomenon of an electric power scene;
and the second abnormal phenomenon monitoring module is used for calling second monitoring video data of a second monitoring point based on the operation plan, and identifying the execution progress, the first abnormal phenomenon and a second abnormal phenomenon of the operation plan based on the second monitoring video data, wherein the second abnormal phenomenon represents the abnormal phenomenon related to the operation execution process.
In some embodiments, the group work intelligent management and control system provided in the embodiments of the present application may be implemented by a combination of software and hardware, for example, the group work intelligent management and control system provided in the embodiments of the present application may be directly embodied as a combination of software modules executed by a processor, the software modules may be located in a storage medium, the storage medium is located in a memory, the processor reads executable instructions included in the software modules in the memory, and the group work intelligent management and control method provided in the embodiments of the present application is completed in combination with necessary hardware (for example, including the processor and other components connected to a bus).
It should be noted that: the intelligent team work management and control system provided in this embodiment and the intelligent team work management and control method provided in the above embodiments belong to the same concept, and specific implementation processes thereof are detailed in the embodiments of the intelligent team work management and control method, and are not described herein again.
The present invention is not limited to the above-described embodiments, and those skilled in the art will be able to make various modifications without creative efforts from the above-described conception, and fall within the scope of the present invention.
Claims (10)
1. Team work intelligent management and control method based on artificial intelligence is characterized by comprising the following steps:
s1: receiving service data of a plurality of dispersedly deployed independent operation information systems, and performing data association merging and standardization processing to obtain an operation plan set;
s2: receiving first monitoring video data of a first preset monitoring point, and identifying a first abnormal phenomenon based on the first monitoring video data, wherein the first abnormal phenomenon represents a static abnormal phenomenon of an electric power scene;
s3: second monitoring video data of a second monitoring point are called based on the operation plan, the execution progress, the first abnormal phenomenon and the second abnormal phenomenon of the operation plan are identified based on the second monitoring video data, and the second abnormal phenomenon represents the abnormal phenomenon related to the operation execution process.
2. The intelligent team work management and control method according to claim 1, wherein the step S2 includes:
acquiring a first characteristic pixel point in a scene image based on the scene image of a first preset monitoring point, wherein the first characteristic pixel point corresponds to a target in the scene image;
and identifying whether the target corresponding to the first characteristic pixel point is abnormal or not based on the first characteristic pixel point and a preset first analysis algorithm.
3. The intelligent team work management and control method based on artificial intelligence of claim 2, wherein the identifying whether the target corresponding to the first characteristic pixel point is abnormal or not based on the first characteristic pixel point and a preset first analysis algorithm comprises:
acquiring a preset target area generation algorithm, and combining the target area generation algorithm and the first characteristic pixel points to obtain a scene image target area corresponding to the first characteristic pixel points;
and determining whether the target in the target area is abnormal or not based on the target type based on the preset second analysis algorithm and the target area of the scene image.
4. The intelligent team work management and control method based on artificial intelligence of claim 3, wherein the method for obtaining the first characteristic pixel point comprises:
(1) selecting a candidate first characteristic pixel point position in a first preset monitoring point scene image;
(2) taking the candidate first characteristic pixel point position as a center, searching for a peripheral to obtain pixel points, and judging the magnitude of the association relationship between the peripheral pixel point and the candidate first characteristic pixel point until the peripheral pixel point with the association relationship smaller than a preset association threshold value is searched;
(3) judging whether pixel points which are not searched exist, if so, selecting a candidate first characteristic pixel point position from the pixel points which are not searched;
(4) and (4) repeating the steps (2) and (3) until all pixel points of the scene image of the first preset monitoring point are searched, and acquiring first characteristic pixel points based on all candidate first characteristic pixel points.
5. The intelligent team work management and control method based on artificial intelligence of claim 4, wherein when obtaining the first feature pixel point, the method comprises:
analyzing the neighborhood pixels of the candidate first characteristic pixel points, comparing the pixel point characteristics of the neighborhood pixels with the pixel point characteristics of the candidate first characteristic pixel points, if the distribution difference of the comparison result between the first characteristic pixel points and the neighborhood pixels is larger than a preset threshold value, selecting one pixel point in the neighborhood pixels as a new candidate first characteristic pixel point, and if the distribution difference of the comparison result is smaller than or equal to the preset threshold value, determining to keep the candidate first characteristic pixel points.
6. The intelligent management and control method for team work based on artificial intelligence as claimed in claim 3, wherein the determining whether the target area is abnormal or not based on the target type based on the target area of the scene image and the preset second analysis algorithm comprises:
determining a target type of the target area based on the scene image target area;
and determining whether the target in the target area is abnormal or not based on the target type based on the mutual distance relationship between the target type of the target area and the target geographic position of the target area.
7. The intelligent team work management and control method according to claim 1, wherein the step S3 includes:
acquiring continuous image frames based on second monitoring video data of a second monitoring point;
and respectively carrying out image analysis from space and time based on the continuous image frames, and determining static abnormal phenomena in a single image frame and dynamic abnormal phenomena in the continuous image frames.
8. The intelligent management and control method for team work based on artificial intelligence as claimed in claim 7, wherein said image analysis is performed from space and time based on the continuous image frames, and said determining the static abnormal phenomena in the single image frame and the dynamic abnormal phenomena in the continuous image frames comprises:
carrying out operation area positioning and area personnel number determination on operators in the operation scene image;
judging the type of the violation behaviors to be detected in the operation area according to the operation plan;
determining an image analysis area for each operator in the operation area based on the type of the violation behaviors to be detected;
and summarizing and analyzing the sub-regions of the images to be analyzed of each operator corresponding to the same type of illegal behaviors to be detected, and determining whether the abnormal phenomenon occurs and the operator with the abnormal phenomenon according to the summarized result.
9. The intelligent management and control method for team work based on artificial intelligence of claim 8, wherein the summarizing and analyzing of the sub-regions of the images to be analyzed of each worker corresponding to the same type of violation behaviors to be detected comprises:
extracting a first characteristic parameter from a sub-region of an image to be analyzed of each operator, which is acquired based on the same type of illegal behaviors to be detected, wherein the first characteristic parameter represents pixel distribution characteristics in the sub-region of the image;
and clustering based on each first characteristic parameter to obtain candidate violation workers corresponding to the first characteristic parameter category of the violation behaviors in the characterization image sub-area.
10. Team work intellectuality management and control system based on artificial intelligence, its characterized in that includes:
the operation plan association and combination module is used for receiving the service data of a plurality of dispersedly deployed independent operation information systems, performing data association and combination and standardization processing and acquiring an operation plan set;
the first abnormal phenomenon monitoring module is used for receiving first monitoring video data of a first preset monitoring point and identifying a first abnormal phenomenon based on the first monitoring video data, wherein the first abnormal phenomenon represents a static abnormal phenomenon of an electric power scene;
and the second abnormal phenomenon monitoring module is used for calling second monitoring video data of a second monitoring point based on the operation plan, and identifying the execution progress, the first abnormal phenomenon and the second abnormal phenomenon of the operation plan based on the second monitoring video data, wherein the second abnormal phenomenon represents the abnormal phenomenon associated with the operation execution process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210203726.XA CN114662864A (en) | 2022-03-03 | 2022-03-03 | Team work intelligent management and control method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210203726.XA CN114662864A (en) | 2022-03-03 | 2022-03-03 | Team work intelligent management and control method and system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114662864A true CN114662864A (en) | 2022-06-24 |
Family
ID=82027420
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210203726.XA Pending CN114662864A (en) | 2022-03-03 | 2022-03-03 | Team work intelligent management and control method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114662864A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116579609A (en) * | 2023-05-15 | 2023-08-11 | 三峡科技有限责任公司 | Illegal operation analysis method based on inspection process |
| CN116844097A (en) * | 2023-07-04 | 2023-10-03 | 北京安录国际技术有限公司 | Intelligent man-vehicle association analysis method and system |
| CN117095465A (en) * | 2023-10-19 | 2023-11-21 | 华夏天信智能物联(大连)有限公司 | Coal mine safety supervision method and system |
| CN117151675A (en) * | 2023-03-16 | 2023-12-01 | 杭州水务数智科技股份有限公司 | Remote operation and maintenance method and system based on video monitoring and encryption |
-
2022
- 2022-03-03 CN CN202210203726.XA patent/CN114662864A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117151675A (en) * | 2023-03-16 | 2023-12-01 | 杭州水务数智科技股份有限公司 | Remote operation and maintenance method and system based on video monitoring and encryption |
| CN117151675B (en) * | 2023-03-16 | 2024-04-09 | 杭州水务数智科技股份有限公司 | Remote operation and maintenance method and system based on video monitoring and encryption |
| CN116579609A (en) * | 2023-05-15 | 2023-08-11 | 三峡科技有限责任公司 | Illegal operation analysis method based on inspection process |
| CN116579609B (en) * | 2023-05-15 | 2023-11-14 | 三峡科技有限责任公司 | Illegal operation analysis method based on inspection process |
| CN116844097A (en) * | 2023-07-04 | 2023-10-03 | 北京安录国际技术有限公司 | Intelligent man-vehicle association analysis method and system |
| CN116844097B (en) * | 2023-07-04 | 2024-01-23 | 北京安录国际技术有限公司 | Intelligent man-vehicle association analysis method and system |
| CN117095465A (en) * | 2023-10-19 | 2023-11-21 | 华夏天信智能物联(大连)有限公司 | Coal mine safety supervision method and system |
| CN117095465B (en) * | 2023-10-19 | 2024-02-06 | 华夏天信智能物联(大连)有限公司 | Coal mine safety supervision method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114662864A (en) | Team work intelligent management and control method and system based on artificial intelligence | |
| CN112769796B (en) | Cloud network side collaborative defense method and system based on end side edge computing | |
| CN111163115A (en) | Internet of things safety monitoring method and system based on double engines | |
| CN113673459B (en) | Video-based production and construction site safety inspection method, system and equipment | |
| CN111199200A (en) | Wearing detection method and device based on electric protection equipment and computer equipment | |
| CN116781430B (en) | Network information security system and method for gas pipe network | |
| CN110991282A (en) | Construction safety management method and device based on unmanned aerial vehicle and computer equipment | |
| KR101692982B1 (en) | Automatic access control system of detecting threat using log analysis and automatic feature learning | |
| CN112381435A (en) | Gridding directional pushing management method for dynamic risk in hydropower station operation process | |
| CN111259390A (en) | Method and device for monitoring malicious process in real time and computer device | |
| CN113569682A (en) | Video monitoring method and device for intelligently capturing mine identification elements | |
| CN114155614A (en) | Method and system for identifying anti-violation behaviors in operation site | |
| CN116229688A (en) | Engineering construction safety risk early warning method and system | |
| CN115941317A (en) | Network security comprehensive analysis and situation awareness platform | |
| KR101972055B1 (en) | CNN based Workers and Risky Facilities Detection System on Infrared Thermal Image | |
| CN104200162A (en) | Computer program product for information security monitoring and defense and method thereof | |
| CN113128760A (en) | Double-control management method, device, equipment and storage medium for safety production | |
| CN113408338A (en) | Method, device and system for monitoring abnormal behavior of miner | |
| CN113297913A (en) | Method for identifying dressing specification of distribution network field operating personnel | |
| CN111582183A (en) | Mask identification method and system in public place | |
| CN114448718B (en) | Network security guarantee method for parallel detection and repair | |
| CN117648689B (en) | Automatic response method for industrial control host safety event based on artificial intelligence | |
| CN115394025A (en) | Monitoring method, monitoring device, electronic equipment and storage medium | |
| KR102372607B1 (en) | Alarm system and method based on image analysis data of real-time parallel compound event processing type | |
| CN113965353A (en) | Monitoring and early warning system and monitoring and early warning method for infrastructure equipment |
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 |