Electric power operation violation identification space video field and its intelligent data processing system and method

Abstract

The application discloses a kind of electric power operation violation identification space video field and its intelligent data processing system and method, the vector field data processing of electric power operation site video data stream obtained by power grid system video monitoring network, including: standard space dynamic video vector field database and its construction, electric power operation site space dynamic video vector field database and its collection construction, double-layer data pre-optimization and data comparison processing, etc., intelligent identification of illegal operation risk is carried out.The application develops data processing technology related to electric power operation violation intelligent identification, and provides basic and core support for the improvement and optimization of the informatization and intelligent level of power grid safety production risk platform.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric power, in particular to the data processing technology for identifying violations in electric power operation sites. BACKGROUND

[0002] The safety and supervision of the power grid is the guarantee of the construction and operation of the national power grid. While the national power grid is developing rapidly, the complex industrial structure adjustment of the power system brings a series of unstable factors. This series of changes also puts forward higher requirements for power safety. The safety and supervision of the power grid become the top priority of the construction and operation of the power grid. Only by ensuring the safe operation of the power grid and reducing the occurrence of power grid accidents can it be more conducive to the rapid development of social economy.

[0003] At present, based on the safety production requirements of State Grid Corporation of China, Hebei Company combines the actual safety production to strengthen "science and technology to promote safety", and actively explores and researches in the integration of informatization and safety production. After years of construction in risk early warning control, operation plan control, site supervision, site operation personnel management, enterprise personnel safety access, dangerous chemical risk management, information system safety time early warning, and safety tools whole process management, certain safety control results have been achieved. At the 2021 safety committee of State Grid Corporation of China, it is pointed out that safety is the foundation of all work and the lifeline of company work. We must crack down on security, use science and technology to protect security, manage security, reform to promote security, and promote the modernization of the company's safety production governance system and governance capacity to provide safe and reliable power guarantee for the new journey of building a modern socialist country. We must resolutely prevent personal accidents and implement the "four control" requirements to strengthen the control of various operations. We must resolutely prevent major equipment accidents and implement the equipment owner system to improve the equipment state perception and diagnosis capability. We must accelerate the integration of technology and production business, promote the landing of technologies such as "big cloud, big data, big intelligence, and big chain" in the field of safety production, and accelerate the integration of technology and safety supervision to promote full coverage, full-time, and full-process safety control and improve safety technical defense capabilities. According to the requirements of the "Notice on the Key Tasks of Digital Safety Control in 2021" issued by the Safety Supervision Department of State Grid Corporation of China, in order to further implement the spirit of the fourth meeting of the State Grid Company's trade union congress and the 2021 work conference, strictly implement the "2021 Safety Production Work Opinion" of the company, deepen the application of safety production risk control platform, promote the digital safety control terminal, standardize the operation of safety control center, and comprehensively promote the development and efficient operation of the three-in-one digital safety control system, and provide strong support for the implementation of the four controls, and promote the transformation and upgrading of site safety control to digital and intelligent.

[0004] However, in the application of intelligent violation identification technology, the identification of violation behavior at the work site, the judgment of violation type, and the recording of violation photos through intelligent technology have not been widely applied. A large amount of terminal image monitoring data still needs to be supervised by manual labor, which requires high labor costs and cannot meet the timeliness of violation and construction safety hazard discovery. Therefore, it is urgent to expand the intelligent identification related application development work on the basis of the safety production risk control platform of State Grid Hubei Electric Power Company. SUMMARY

[0005] The technical problem to be solved by the present application is to overcome the various shortcomings of the prior art and provide a power operation violation identification space video field and an intelligent data processing system and method thereof.

[0006] To solve the above technical problems, the technical solutions adopted by the present application are as follows.

[0007] An intelligent data processing system based on a power operation violation identification space video field performs vector field data processing on the power operation site video data stream obtained by the power grid system video monitoring network and performs intelligent identification of violation operation risks.

[0008] As a preferred technical solution of the present application, the execution process of the system includes:

[0009] A, standard space dynamic video vector field database and its construction: the standard database is constructed as a dynamic atypical vector field data model;

[0010] The vector field corresponds to the construction of the monitoring target of the power operation as a vector function relative to the specified data zero point. The data expression of the vector allows the use of a plane mode, i.e., a double data set (m, n) to data table the spatial position of the monitoring target, or a space mode, i.e., a three data set (l, m, n) to data table the spatial position of the monitoring target;

[0011] The atypical corresponds to the image of the vector function, which is not a typical spatial data point, i.e., a double data set or a three data set corresponding to the double data set (m, n) or the three data set (l, m, n). The data configuration of the image is a two-parameter model, the first parameter is the time parameter t, and the second parameter is the number of monitored power operation objects (α, β, γ, …); wherein the first parameter t is a dynamic independent variable data, and the second parameter (α, β, γ, …) is a static marker data, which is used to collect the vector field functions corresponding to specific detection objects, so as to realize the packaging of multiple groups of function values, so as to facilitate the processing of the packaged combined data, thereby saving the computing resources of the system; the vector function is the dependent variable of the first parameter, i.e., the dynamic independent variable data t;

[0012] The vector field configuration of the dynamic correspondence database is a dynamic vector field, and the compatible data changes over time;

[0013] B, power operation site space dynamic video vector field database and its collection and construction:

[0014] The objects of the power construction site are grouped and numbered, the grouping rules are determined according to the physical and engineering relationship of the power operation object itself, the numbering rules are consistent with the second parameter, that is, the static marking data (α, β, γ, …) in the standard space dynamic video vector field database, or although inconsistent, but keep a fixed single mapping relationship; The dynamic independent variable data of the power operation site space dynamic video vector field is recorded as t';

[0015] The implementation basis of the illegal monitoring is to compare the standard data with the site data, so the configuration of the power operation site space dynamic video vector field database is consistent with the standard space dynamic video vector field database; Specifically, it includes three elements of vector field, atypical, dynamic, and the connotation of the three elements of vector field, atypical, dynamic is consistent with the standard space dynamic video vector field database;

[0016] Finally, the construction of the power operation site space dynamic video vector field database is completed through data collection; Unlike the multiple optional construction ways of the standard space dynamic video vector field database, the data source of the power operation site space dynamic video vector field database is a single way, that is, the filling and construction of the database is completed by collecting video data of the power construction site;

[0017] C, by data preprocessing and data comparison of the standard space dynamic video vector field database and the power operation site space dynamic video vector field database, the illegal risk identification of the power construction site is carried out.

[0018] As a preferred technical solution of the application, in step A, the construction way of the standard space dynamic video vector field database includes: constructing by collecting video data of the calibrated standardized power construction operation; constructing by data input according to the standardized power construction operation model; based on the standardized power construction operation model, constructing by data rule making, and automatically generating a standard dynamic atypical vector database by data rule; other standardized construction ways; the above ways are selected to construct the standard space dynamic video vector field database;

[0019] As a preferred technical solution of the present application, in step A, for the original image data and vector function data in the standard space dynamic video vector field database, a certain range of operation flexibility is allowed based on the standardized operation model, which makes the original image data and vector function data in the database exhibit a range of values; or the original image data t is calibrated, and the vector function data is set as a range of values.

[0020] As a preferred technical solution of the present application, in step C, the data preprocessing includes data translation processing: since the dynamic independent variable data t' of the power operation site space dynamic video vector field database is obtained based on field video acquisition, it is naturally inconsistent with the dynamic independent variable data t of the standard space dynamic video vector field database, so data translation processing is needed to make them consistent; the data translation operation can be selected from the following norms: the dynamic independent variable data t' and t in the two databases are simultaneously zero-processed according to the event starting point; any t' is translated to a position consistent with t;

[0021] As a preferred technical solution of the present application, in step C, the data preprocessing includes data scaling and its interaction with data translation processing: on the one hand, the key nodes of the power construction process are calibrated as conservative data points, and the entire power construction operation process is segmented and scaled according to the calibrated conservative data points, or the conservative data points are used as data comparison center points; on the other hand, the power construction operation process is segmented and translated according to the distribution of the conservative data points; through the interaction of scaling and translation, the comparison value coefficient of the two groups of databases is improved, especially the data comparison value coefficient near the conservative data points;

[0022] As a preferred technical solution of the present application, in step C, the data preprocessing includes: constructing a double-layer vector field data model to obtain inner-layer comparison data as auxiliary comparison parameters for violation identification; specifically, for the vector function data of different power operation objects packaged into the same group, i.e. the real-time space vector data of power operation objects labeled as α, β, γ, …, a vector data group is obtained as an in-box difference data group through finite difference data processing; on the other hand, a center of gravity vector of the entire packaged data group is obtained through the center of gravity algorithm of the space vector data, which is expressed as a single space vector data; the in-box difference data group and the center of gravity vector are used as inner-layer comparison data as auxiliary comparison parameters for violation identification.

[0023] As a preferred technical solution of the present application, the system is also compatible with the following data recognition subcomponents developed by means of function guidance: anti-high-falling recognition subcomponent, anti-electric shock recognition subcomponent, anti-falling pole recognition subcomponent, anti-deep foundation pit operation violation recognition subcomponent, anti-falling object injury recognition subcomponent, anti-crane operation violation recognition subcomponent, and other violation recognition subcomponent.

[0024] As a preferred technical solution of the present application, the system is also compatible with the following parallel subsystems: intelligent anti-violation subsystem; including: ① violation warning information real-time reminding: through the hanging and integration with an external information sending platform, real-time violation warning notification based on job site monitoring is realized; ② violation automatic generation and information pre-filling: through the hanging and integration with a data port or a data platform, according to the device ID feedback of the analysis result, information such as job plan name, job type, construction unit, opportunity unit to which the construction unit belongs, and job risk level is inquired and automatically filled into the violation warning; ③ intelligent analysis of violation identification and secondary confirmation: the existing violation rectification process is reformed, the violation information found by intelligent analysis is specially marked, and a manual confirmation link is added before the violation process is handled; violation data permission control: through data permission control, only the port with permission is allowed to view the data before exposure.

[0025] As a preferred technical solution of the present application, the system is also compatible with the following parallel subsystems: intelligent anti-violation information visualization subsystem; including: ① intelligent recognition data overview: supporting real-time and historical data query and violation detail display; supporting searching by job name, violation type, violation unit, and violation location; ② intelligent recognition data statistics: through the integration of historical violation handling conditions, violation types, violation units, violation locations, and other data, according to the number of violations, the number of each type of violation, violation handling efficiency, and violation distribution area, dynamic statistics and display are performed.

[0026] The beneficial effects produced by the above technical solution are that the present application develops data processing technologies related to power operation violation intelligent identification, and provides basic and core support for the improvement and optimization of the informatization and intelligent level of the power grid safety production risk platform.

[0027] The present application is developed based on the related platform of State Grid Corporation, and the video field data model adopted by the present application has direct compatibility, storage saving, and rapid calculation for the data transmitted and displayed by the existing video monitoring platform, and has higher data level or data capacity, and higher logical intuitiveness compared with the single-byte summary analysis and calculation model.

[0028] The standardized data model constructed by this invention has a comprehensive configuration that is vector-inclusive, dynamic, and atypical. It is compatible with the construction, storage, and processing of two-dimensional or three-dimensional data. The vector-inclusive nature of the data model naturally encapsulates video-related source data, which not only improves the data coverage of the data model but also simplifies the logical efficiency of system data processing. The atypical data structure artificially vectorizes other necessary and closely related data dimensions beyond video data stream information, enabling the data configuration to globally correlate and represent dynamic power operation site information as a processing carrier, greatly improving the system's visual simplicity.

[0029] The data construction and processing model of this invention ensures that the configuration of the spatial dynamic video vector field database for power operation sites is consistent with that of the standard spatial dynamic video vector field database; it includes three elements: vector field, atypical, and dynamic, and the connotations of these three elements are consistent with those of the standard spatial dynamic video vector field database.

[0030] This invention constructs multiple preprocessing models, as well as a two-layer data processing and optimization comparison mode, all of which are unique and original.

[0031] This invention also has good monitoring and scalability, making it easy to interface with system platforms and develop subsequent functions using similar data models. Detailed Implementation

[0032] In the following description of embodiments, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of this application with unnecessary detail. It should be understood that, as used in this specification and the appended claims, the term "comprising" indicates the presence of a described feature, integral, step, operation, element, and / or component, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or collections thereof. It should also be understood that, as used in this specification and the appended claims, the term "and / or" refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations.

[0033] As used in the specification and appended claims herein, the term “if’ can be interpreted as meaning “when” or “upon” or “in response to a determination” or “in response to a detection” depending on the context. Similarly, the phrase “if it is determined” or “if [the described condition or event] is detected” can be interpreted as meaning “upon a determination” or “in response to a determination” or “upon a detection of [the described condition or event]” or “in response to a detection of [the described condition or event]” depending on the context. Additionally, in the description of the specification and appended claims, the terms “first,” “second,” “third,” etc. are used merely as labels for the convenience of the reader and do not necessarily connote relative importance of the elements being described.

[0034] Example 1, bottom technical framework and technical specification

[0035] The State Grid Corporation launched the basic version of the safety production risk control platform, and carried out the deployment and implementation of the safety production risk control platform. Its functions include homepage, work safety intelligent control, enterprise personnel safety access, safety event statistical analysis, accident hidden danger investigation and management, safety control center duty management, information system safety event early warning, power grid risk early warning control, risk panoramic perception and statistical analysis, on-site safety supervision visualization, safety tool whole process management, and dangerous chemical risk management. Among them, there are 11 first-level function points, 34 second-level function points, and 22 third-level function points. Since the safety production risk control platform has been put into operation, the city-level, county-level, and work area team-level of State Grid Hubei Electric Power Co., Ltd. have jointly applied it. The number of registered users of the system is nearly 3000, the number of daily system access users is nearly 300, and the number of work sites controlled in real time through the platform is about 70 per day. Through the work safety intelligent control, enterprise personnel safety access, safety event statistical analysis, accident hidden danger investigation and management, safety control center duty management, information system safety event early warning, power grid risk early warning control, risk panoramic perception and statistical analysis, on-site safety supervision visualization, safety tool whole process management, and dangerous chemical risk management modules of the safety production risk control platform, the functions of the modules are used regularly in various units of the company, and in the control of various types of work sites, certain safety control results have been achieved, supporting the daily management, emergency disposal, risk control, enterprise access control, personnel control, tool control, and dangerous chemical control of work sites.

[0036] The safety production risk platform is provided with the following first-level sub-platforms: work safety intelligent management and control sub-platform, enterprise personnel safety access sub-platform, safety event data statistical analysis sub-platform, accident hidden danger investigation data sub-platform, safety management and control center value inquiry sub-platform, information system safety event early warning sub-platform, risk early warning mechanism sub-platform, risk panoramic perception and statistical analysis sub-platform, field safety supervision visualization sub-platform, safety tool whole-process sub-platform, and dangerous chemical risk sub-platform. The work safety intelligent management and control sub-platform is provided with the following second-level sub-platforms: power grid infrastructure and construction work planning, power grid infrastructure and construction inspection, and power grid infrastructure and construction illegal safety risk. Further, the power grid infrastructure and construction illegal safety risk second-level sub-platform is provided with the following third-level sub-platforms: power work site illegal identification and power work site illegal information visualization. The server computing capacity, server storage capacity, data communication protocol and data security protocol, and data communication port are allocated according to the actual capacity of the system construction.

[0037] Finally, the power work site illegal identification third-level sub-platform and the power work site illegal information visualization third-level sub-platform are synchronously mapped to the following two second-level sub-platforms under the safety production risk platform by using the quick way type data model: risk panoramic perception and statistical analysis sub-platform and field safety supervision visualization sub-platform.

[0038] The newly added technical development related technical basis and specifications include: “Opinions of State Grid Corporation of China on Accelerating the Construction of New Digital Infrastructure” (State Grid Interconnection

[2020] No. 260), “Notice of the State Grid Work Safety Department on Issuing the Functional and Practical Acceptance Standards for the Safety Production Risk Control Platform (Trial)” and “Notice of the State Grid Work Safety Department on Issuing the Interface and Data Specifications for the Safety Production Risk Control Platform (Trial)” (Anquan II

[2020] No. 15), “Notice of the State Grid Work Safety Department on Issuing the Key Tasks of the Safety Production Risk Control Platform in 2020” (Anquan II

[2020] No. 3), “Notice of the State Grid Work Safety Department on Issuing the Functional Highlights of the Safety Production Risk Control Platform” (Anquan II

[2019] No. 51), “Notice of the State Grid Work Safety Department on Issuing the Special Program for the Construction and Application of the Safety Production Risk Control Platform” (Anquan II

[2019] No. 25), “State Grid Corporation of China Safety Hazard Identification and Governance Management Method” (State Grid Anquan

[2014] No. 481), “State Grid Corporation of China Safety Accident Investigation Procedures” (2017 revised edition), “Power Grid Operation Risk Early Warning Control Work Specification” (QGDW 11711-2017), “Production Operation Safety Control Standardization Work Specification (Trial)” (State Grid Anquan

[2016] No. 356), “State Grid Corporation of China Transmission and Distribution Project Construction Safety Risk Early Warning Control Work Specification (Trial)” (State Grid Anquan

[2015] No. 972), “State Grid Corporation of China Safety Production Anti-Violation Work Management Method” (State Grid Anquan

[2014] No. 156), “State Grid Corporation of China Business Outsourcing Safety Supervision and Management Method” (State Grid (Anquan / 4) 853-2017), “State Grid Corporation of China Electric Power Safety Tools Management Regulations” (State Grid (Anquan / 4) 289-2014), “Power Grid Video Monitoring System and Interface” (Q / GDW 1517.1-2014); and other applicable specifications.

[0039] Example 2, Technology Integration

[0040] The existing technologies are integrated to obtain data information of the whole-process comprehensive digital management platform for infrastructure, PMS2.0, OMS, S6000, I6000, etc. The integrated specific information is shown in the following table. The deployment environment is a micro-service cloud mode, and the overall platform is deployed in the management information area. The subsequent development can follow its architecture.

[0041]

[0042] Example 3, Development Orientation

[0043] The video information flow is expanded and constructed based on the safety production risk platform of the power grid system to identify the safety production risk of the power infrastructure and the operation site, and to perform information transmission and processing on the risk operation; including: ①collaborative integration of existing software and hardware facilities of the power grid system; ②newly built hardware facility components and executable data components for identifying violations in the power operation site, and are cooperatively loaded on the existing software and hardware facility platform of the power grid system after collaborative integration, and are expanded on the system platform.

[0044] Embodiment 4, collaborative integration of software and hardware facilities of the power grid system

[0045] The collaborative integration includes: network communication integration and construction of the existing software and hardware facilities of the power grid system; the network communication includes: power grid internal network wired communication protocol and port construction, and / or power grid internal network wireless communication protocol and port construction, and / or power grid internal-external network wired communication protocol and port construction, and / or power grid internal-external network wireless communication protocol and port construction; wherein, the communication protocol includes not only data transmission protocol but also data security protocol meeting the internal requirements of the power grid system; data integration and construction of the existing software and hardware facilities of the power grid system; data integration includes data format unification and / or data interface unification.

[0046] Embodiment 5, hardware facility components

[0047] The newly built hardware facility components are supplemented according to the project requirements of the power operation risk violation identification, including the supplement of video monitoring facilities, the new laying of communication lines, the addition of risk identification and processing stations, the capacity expansion of data processing servers, and the addition of other facilities, which can be added on demand according to the existing architecture of the power grid system safety production risk platform;

[0048] Embodiment 6, video data processing

[0049] The video data processing belongs to the newly built executable data components, which processes the video data stream obtained by the power grid system video monitoring network in the power operation site, intelligently identifies the violation operation risk, and acquires and records the risk node data array after identifying the violation risk, and the risk node data array is constructed as a risk node database; specifically, the risk node database is constructed by the following parallel data groups: violation site space-time node data column, violation site image interception data column, violation site video recording data column, violation site construction project topic data column, violation site operation personnel information and contact information data column, violation site construction project superior department data column; other data columns; expandable blank data column.

[0050] The video data processing component processes the power operation site video data stream obtained by the power grid system video monitoring network to intelligently identify the risk of illegal operation; the data processing process includes:

[0051] A. Construction of a standard space dynamic video vector field database.

[0052] The standard database is constructed as a dynamic atypical vector field data model. The vector field refers to constructing the monitoring target of power operation as a vector function relative to a specified data zero point. The data representation of the vector allows using a planar mode, i.e., using a double data set (m, n) to represent the spatial position of the monitoring target, or using a spatial mode, i.e., using a triple data set (l, m, n) to represent the spatial position of the monitoring target. Atypical refers to the preimage of the vector function, which is not a typical spatial data point, i.e., a double data set or a triple data set corresponding to the double data set (m, n) or the triple data set (l, m, n). The data configuration of the preimage is a double-parameter model, with the first parameter being the time parameter t and the second parameter being the number of monitored power operation objects (α, β, γ, …). The first parameter t is a dynamic independent variable data, and the second parameter (α, β, γ, …) is a static marker data, which is used to aggregate the vector field functions corresponding to specific detection objects to realize the packaging of multiple groups of function values, so as to facilitate subsequent processing of the packaged combined data, thereby saving system computing resources; the vector function is the dependent variable of the first parameter, i.e., the dynamic independent variable data t. Dynamic refers to the vector field being a dynamic vector field that changes over time.

[0053] The construction approach of the standard space dynamic video vector field database includes: δ, constructing by collecting site video data of standardized power construction operations; ε, constructing by data input according to the standardized power construction operation model; ζ, based on the standardized power construction operation model, constructing by data rule setting and automatically generating a standard dynamic atypical vector database by the data rule; η, other standardized construction approaches; the above approaches are selected to construct the standard space dynamic video vector field database.

[0054] For the preimage data and vector function data in the standard space dynamic video vector field database, due to the existence of a certain range of operation flexibility based on the standardized operation model, the preimage data and vector function data in this database exhibit range values; or the preimage data t is calibrated, and the vector function data is set as a range value.

[0055] B. Collection and construction of the power operation site space dynamic video vector field database.

[0056] The objects of the electric power construction site are grouped and numbered, the grouping rules are determined according to the physical and engineering relationship of the electric power operation objects, the numbering rules are consistent with the second parameters, i.e. static marking data (α, β, γ, …) in the standard space dynamic video vector field database or are fixed single mapping relationship although not consistent; the dynamic independent variable data of the electric power operation site space dynamic video vector field is recorded as t';

[0057] The implementation basis of the violation monitoring lies in comparing the standard data with the site data, therefore the configuration of the electric power operation site space dynamic video vector field database is consistent with the standard space dynamic video vector field database; specifically, it includes three elements of vector field, atypical and dynamic, and the connotations of the three elements of vector field, atypical and dynamic are consistent with the standard space dynamic video vector field database; finally, the construction of the electric power operation site space dynamic video vector field database is completed through the data acquisition approach; different from the multiple optional construction approaches of the standard space dynamic video vector field database, the data source of the electric power operation site space dynamic video vector field database is a single approach, i.e. the filling construction of the database is completed through the video data acquisition of the electric power construction operation site.

[0058] C, the illegal risk of the power construction site is identified by data preprocessing and data comparison of the standard space dynamic video vector field database and the power construction site space dynamic video vector field database. The data preprocessing includes data translation processing: since the dynamic independent variable data t' of the power construction site space dynamic video vector field database is obtained based on the site video collection, it is naturally inconsistent with the dynamic independent variable data t of the standard space dynamic video vector field database, so data translation processing is needed to make them consistent; the data translation operation can be selected from the following norms: the dynamic independent variable data t' and t in the two databases are simultaneously processed to zero according to the event starting point; any t' is translated to the consistent position with t; the data preprocessing includes data scaling and the interactive processing of data scaling and data translation: on the one hand, the key nodes of the power construction process are calibrated as conservative data points, and the entire power construction process is segmented and scaled according to the calibrated conservative data points, or the conservative data points are used as the data comparison center point; on the other hand, the power construction process is segmented and translated according to the distribution of the conservative data points; the interactive processing of scaling and translation improves the comparison value coefficient of the two groups of databases, especially the data comparison value coefficient near the conservative data points; the data preprocessing includes: constructing a double-layer vector field data model to obtain the inner layer comparison data as the auxiliary comparison parameters for illegal identification; specifically, for the vector function data of different power operation objects packaged into the same group, i.e. the real-time space vector data of power operation objects labeled as α, β, γ, …, a vector data group is obtained as the box differential data group through finite difference data processing; on the other hand, a center of gravity vector of the entire packaged data group is obtained through the center of gravity algorithm of the space vector data, and the center of gravity vector is expressed as a single space vector data; the box differential data group and the center of gravity vector are used as the inner layer comparison data as the auxiliary comparison parameters for illegal identification.

[0059] The video data processing assembly can also be expanded and developed in the form of function guide as follows: anti-high fall identification subassembly, anti-electric shock identification subassembly, anti-falling pole identification subassembly, anti-deep foundation pit operation illegal identification subassembly, anti-high falling object injury identification subassembly, anti-crane operation illegal identification subassembly, and other illegal identification subassembly.

[0060] Embodiment 7, information transmission processing of operation risk

[0061] The information transmission processing of the operation risk belongs to a newly established executable data component, which is constructed as an integrated functional component. First, the video data processing component identifies the violation information and sends it to the safety production risk platform through the violation information sending module. Further, the data interaction is performed between the data authority approach and the risk node data array. The data interaction between the data authority approach and the risk node data array refers to that the information transmission processing component of the operation risk sends the risk violation information and then performs the bidirectional data communication with the “violation scene operation personnel information and contact information data” and the “violation scene construction project superior responsibility department data” in the risk node database through the data authority approach, thereby achieving the subsequent risk data processing requirements and further generating the related database. The alarm, query, focus, risk processing, risk processing feedback, risk processing supervision, risk processing effect evaluation and other functions are realized for the multi-level management department and the operation scene, and the violation risk identification and processing process database are generated and constructed. The generation and construction specifically include that the information transmission processing component of the operation risk performs the system log recording and backup on the related data in the risk information sending link and the data interaction link with the risk node data array.

[0062] Embodiment 8, associated technology selection and technology platform

[0063] Associated technology selection path. Interface display technology: mature interface display technologies are used, including HTML, CSS, Ajax, JSP and related technologies. Server development technology selection: a technology route of mixed development of Python, C++, Java, Java EE and servlet is selected. Coding specification: UTF-8 coding is uniformly used for codes, components, data serialization and related files and data. Open source software: ECharts, jQuery, VUE and Redis. Middleware: message middleware kafka and distributed cache redis. Database: MySQL level and FastDFS (based on cloud platform). Container engine: Docker. Inteli-rec: Docker, Python and PyTorch.

[0064] Associated technology platform path. SG-UAP3.0, Flask, Spring cloud framework and PyTorch

[0065] In the above embodiments, the description of each embodiment has its own emphasis. The parts not described or recorded in detail in a certain embodiment can be referred to the related description of other embodiments.

[0066] In various embodiments, the hardware implementation of the technology can directly use existing intelligent devices, including but not limited to industrial computers, PC computers, smart phones, handheld computers, floor-standing computers, etc. The input device thereof is preferably a screen keyboard, the data storage and calculation module thereof uses existing memory, calculators, controllers, the internal communication module thereof uses existing communication ports and protocols, and the remote communication thereof uses existing gprs networks, the Internet, etc. Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is taken as an example for illustration, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit, and the integrated unit can be realized in the form of hardware or software. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the present application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0067] In the embodiments provided by the present application, it should be understood that the disclosed device / terminal equipment and method can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic, and the division of the modules or units is only a logical function division, and there can be another division way in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection between interfaces can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms. The units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0068] The various function units in the various embodiments of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software function unit. When the integrated module / unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms, etc. The computer readable medium can include any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier wave signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include electric carrier wave signal and telecommunication signal.

[0069] The above embodiments are only used to illustrate the technical solutions of the present application, but not limit it; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalent; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. An intelligent data processing system based on spatial video field for identifying violations during power operations, characterized in that: The power operation site video data stream obtained by the power grid system video monitoring network is subjected to vector field data processing, and intelligent identification of illegal operation risk is performed; including: A, standard space dynamic video vector field database: the standard database is constructed as a "dynamic, atypical, vector field" structured database; Wherein, "vector field" corresponds to constructing the monitoring target of power operation as a vector function relative to a specified data zero point, and the data expression of the vector adopts a plane mode, that is, a double data set (m, n) is used to data table the spatial position of the monitoring target, or a space mode, that is, a three data set (l, m, n) is used to data table the spatial position of the monitoring target; Wherein, "atypical" corresponds to the original image of the vector function which is not a typical spatial data point, that is, the data configuration of the original image corresponding to the double data set (m, n) or the three data set (l, m, n) is a double parameter model, the first parameter is a time parameter t, and the second parameter is the number of the monitored power operation object (α, β, γ, …); wherein the first parameter t is a dynamic independent variable data, and the second parameter (α, β, γ, …) is a static marking data, which is used to collect the vector field functions corresponding to specific detection objects and realize the packaging of multiple vector function values, so as to facilitate subsequent processing of the packaged combined data; the vector function is the dependent variable of the first parameter, that is, the dynamic independent variable data t; Wherein, "dynamic" corresponds to the vector field configuration of the database being a dynamic vector field, compatible with the change of data over time; B, power operation site space dynamic video vector field database: The objects in the power construction site are grouped and numbered, the grouping rule is determined according to the physical and engineering relationship of the power operation object itself, the numbering rule is consistent with the second parameter, that is, the static marking data (α, β, γ, …) in the standard space dynamic video vector field database, or although it is not consistent but maintains a fixed single mapping relationship; the dynamic independent variable data of the power operation site space dynamic video vector field is denoted as t'; The implementation basis of illegal monitoring lies in comparing the standard data with the site data, and the configuration of the power operation site space dynamic video vector field database is consistent with the standard space dynamic video vector field database; specifically, it includes three elements of vector field, atypical, dynamic, and the connotations of the three elements are consistent with the standard space dynamic video vector field database; Finally, the construction of the power operation site space dynamic video vector field database is completed through data acquisition; the data source of the power operation site space dynamic video vector field database is a single way, and the database is filled and constructed by video data acquisition of the power construction site; C, through data preprocessing and data comparison of the standard space dynamic video vector field database and the power operation site space dynamic video vector field database, the illegal risk identification of the power construction operation site is performed.

2. The intelligent data processing system for identifying space video scene based on power operation violation according to claim 1, characterized in that: In step A, the construction approach of the standard space dynamic video vector field database includes: constructing by field video data collection of the standardized electric power construction operation; constructing by data input according to the standardized electric power construction operation model; constructing by data rule setting based on the standardized electric power construction operation model, and automatically generating the standard dynamic non-typical vector database by the data rule; other standard construction approaches; and constructing the standard space dynamic video vector field database by one of the above approaches. 3.The intelligent data processing system for identifying space video scenes based on power operation violation according to claim 1, wherein: In step A, for the original image data and vector function data in the standard space dynamic video vector field database, the original image data and the vector function data in the database are expressed as range values; or the original image data t is calibrated, and the vector function data is set as range values.

4. The intelligent data processing system for identifying space video scene based on power operation violation according to claim 1, characterized in that: In step C, the data preprocessing includes data translation processing: since the dynamic independent variable data t' of the electric power operation field space dynamic video vector field database is obtained based on field video collection, it is naturally inconsistent with the dynamic independent variable data t of the standard space dynamic video vector field database, so that the two are kept consistent by data translation processing; the data translation operation can be selected from the following norms: the dynamic independent variable data t' and t in the two databases are simultaneously processed to zero according to the event starting point; any t' is translated to a position consistent with t.

5. The intelligent data processing system based on the space video field of power operation violation identification according to claim 1, characterized in that: In step C, the data preprocessing includes data scaling and the interaction processing thereof with data translation: on the one hand, the key nodes of the electric power construction process are calibrated as conservative data points, and the entire electric power construction operation process is segmented and scaled according to the calibrated conservative data points, or the conservative data points are taken as data comparison center points; on the other hand, the electric power construction operation process is segmented and translated according to the distribution of the conservative data points; the interaction processing of scaling and translation improves the comparison value coefficient of the two groups of databases and improves the data comparison value coefficient near the conservative data points.

6. The intelligent data processing system based on the space video field of power operation violation identification according to claim 1, characterized in that: In step C, the data preprocessing includes: constructing a double-layer vector field data model to obtain inner-layer comparison data as auxiliary comparison parameters for violation identification; specifically, for the vector function data of different electric power operation objects packaged into the same group, i.e., the real-time space vector data of electric power operation objects labeled as α, β, γ,..., a vector data group is obtained as an in-box difference data group through finite difference data processing; on the other hand, a barycentric vector of the entire packaged data group is obtained through a barycentric algorithm of the space vector data, and the barycentric vector is expressed as a single space vector data; the in-box difference data group and the barycentric vector are taken as the inner-layer comparison data and used as auxiliary comparison parameters for violation identification.

7. The intelligent data processing system based on the space video field of power operation violation identification according to claim 1, characterized in that: The system is also compatible with the following data identification sub-components developed by means of function guidance: anti-high-altitude-falling identification sub-component, anti-electric shock identification sub-component, anti-falling-pole identification sub-component, anti-deep-foundation-operation violation identification sub-component, anti-high-altitude-falling-object injury identification sub-component, anti-crane-operation violation identification sub-component, and other violation identification sub-components. 8.The intelligent data processing system based on the space video field of power operation violation identification according to claim 1, wherein: The system is also compatible with the following parallel subsystems: intelligent anti-violation subsystem; including: ① violation warning information real-time reminder: through the hanging and integration with the external information sending platform, realize the real-time violation warning notification based on the job site monitoring; ② violation automatic generation and information prefilling: through the hanging and integration with the data port or data platform, according to the device ID feedback of the analysis result, search the job plan name, job type, construction unit, construction unit belonging to business opportunity unit, job risk level and other information and automatically fill in the violation warning; ③ intelligent analysis of violation identification and secondary confirmation: the existing violation rectification process is modified, the violation information found by intelligent analysis is specially marked, and the manual confirmation link is added before the violation process treatment; violation data permission control: through data permission control, only the port with permission is allowed to view the data before exposure. 9.The intelligent data processing system based on the space video field of power operation violation identification according to claim 1, characterized in that: The system is also compatible with the following parallel subsystems: intelligent anti-violation information visualization subsystem; including: ① intelligent identification data overview: support real-time and historical data query and violation detail display; support searching by job name, violation type, violation unit, violation location; ② intelligent identification data statistics: through the integration of historical violation handling, violation type, violation unit, violation location and other data, according to the number of violations, the number of each type of violation, violation handling efficiency, violation distribution area for dynamic statistics and display.

Images