A gas station digital safety insight system management and display platform

Through the digital security insight system management and display platform of gas stations, combined with intelligent analysis of monitoring video and sensing data, the problem of low efficiency of traditional security systems is solved, efficient safety supervision and early warning of gas stations is realized, and safety control capabilities are improved.

CN115050171BActive Publication Date: 2024-11-01SHENZHEN WEICHE TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210727679.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-06-22
Publication Date
2024-11-01
Estimated Expiration
2042-06-22

AI Technical Summary

Technical Problem

The security system of traditional gas stations is inefficient and has low real-time performance, and cannot achieve unified control and system supervision, resulting in lagging safety risks identification and prone to safety accidents.

Method used

Design a gas station digital security insight system management and display platform, and realize automatic security patrol, intelligent identification and early warning through monitoring and acquisition end, identification and judgment end, comprehensive analysis end and comprehensive display end, combining camera monitoring and multiple sensor data , conduct digital comprehensive analysis and visual display.

Benefits of technology

It has improved the active safety control capabilities of gas stations, achieved pre-prevention, in-process linkage dispatch and post-reservation certificates, and improved the real-time and efficiency of safety supervision.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115050171B_ABST
    Figure CN115050171B_ABST
Patent Text Reader

Abstract

The present invention provides a gas station digital security insight system management and display platform, including: a monitoring acquisition end, used to obtain relevant monitoring videos and terminal monitoring data of the gas station; an identification and judgment end, used to identify a first risk factor in the relevant monitoring video, and at the same time, based on the terminal monitoring data, judge a second risk factor in the gas station; a comprehensive analysis end, used to perform a digital comprehensive analysis on the first risk factor and the second risk factor to obtain corresponding analysis results; a comprehensive display end, used to visualize the analysis results in a corresponding IOC data dashboard; based on the existing gas station terminal monitoring device, security insight analysis and display are performed, and automatic security inspections, intelligent identification and early warning, and display of gas stations are realized based on digital technology, so as to achieve pre-prevention, post-event evidence retention, and in-event linkage scheduling, and comprehensively improve the active safety management and control capabilities of gas stations.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of gas station safety supervision, and in particular to a gas station digital safety insight system management and display platform. Background Art

[0002] At present, the digital upgrade of the industry is developing rapidly. On the basis of integrating and optimizing the previous enterprise information system, the management and operation level is improved, and the new technical means are used to enhance the new technical capabilities of enterprises. The wide application of digital technology in all walks of life has played a great role in promoting the improvement of production efficiency in the whole society. For the gas station industry, industry leaders have also begun to carry out large-scale digital and intelligent transformation of gas station retail systems, security systems, etc., by connecting customer business process management with the Internet, and then combining cloud computing and big data to become measurable numbers and data, so that it can adapt to a more convenient online environment and management needs, and realize process automation without human intervention in all aspects. Apply a new generation of information technology to upgrade the consumption experience and scenario of gas stations, and take a leading position in the competition of science and technology.

[0003] The traditional video construction mode of the gas station security system is a hard disk recorder + camera, which mainly realizes online monitoring and storage of key areas such as the gas station operation area, storage tank area, cashier, entrance and exit, etc. It belongs to static monitoring, which manually identifies non-safe factors, has low efficiency and low real-time performance. At present, many gas stations have backup security measures, such as smoke sensors, temperature sensors and other equipment for division of labor supervision, which cannot achieve unified control and system supervision and intuitive display. During the operation of the gas station, if the safety risks of the operation and environment (open flames, cigarette butts, etc.) are not identified in time, safety explosion accidents are very likely to occur. The existing division of labor supervision mode of manual + monitoring can no longer meet the needs of modern enterprises for gas station safety management.

[0004] Therefore, the present invention proposes a gas station digital safety insight system management and display platform. Summary of the invention

[0005] The present invention provides a gas station digital safety insight system management and display platform, which is used to perform digital analysis and display of safety insights based on the existing gas station terminal monitoring device, realize automatic security inspection, intelligent identification and early warning and display of gas stations based on digital technology, achieve pre-emptive prevention, post-event evidence retention, and in-event linkage scheduling, and comprehensively improve the active safety management and control capabilities of gas stations.

[0006] The present invention provides a gas station digital safety insight system management and display platform, including:

[0007] The monitoring acquisition terminal is used to obtain relevant monitoring videos and terminal monitoring data of the gas station;

[0008] An identification and judgment terminal, used to identify the first risk factor in the relevant monitoring video, and at the same time, judge the second risk factor in the gas station based on the terminal monitoring data;

[0009] A comprehensive analysis terminal, used for performing a digital comprehensive analysis on the first risk factor and the second risk factor to obtain corresponding analysis results;

[0010] The comprehensive display terminal is used to visualize the analysis results in the corresponding IOC data dashboard.

[0011] Preferably, the monitoring acquisition terminal includes:

[0012] A surveillance camera module, used for acquiring relevant surveillance videos inside and outside the gas station based on a camera;

[0013] A terminal sensing module, used for acquiring real-time sensing data in the gas station based on a variety of sensors arranged in the gas station;

[0014] An intelligent inspection module, used for obtaining inspection data in the gas station according to a preset period based on manual inspection or automatic inspection;

[0015] The Internet of Things transmission module is used to transmit the real-time sensing data and the inspection data as the terminal monitoring data corresponding to the gas station to the identification and judgment terminal based on the Internet of Things.

[0016] Preferably, the monitoring camera module includes:

[0017] An internal monitoring unit, used to obtain an internal monitoring video of the gas station based on a camera set at a corresponding position in the gas station;

[0018] An external monitoring unit, used for acquiring a video of the surrounding environment of the gas station based on cameras arranged at corresponding positions around the gas station;

[0019] The multiplexing unit is used to transmit all the internal monitoring videos and all the surrounding environment videos as the relevant monitoring videos corresponding to the gas station to the identification and judgment end.

[0020] Preferably, the identification and judgment terminal includes:

[0021] A first identification module, used to identify the current illegal behavior and the first potential risk factor of the gas station in the internal monitoring video;

[0022] A second identification module is used to identify a second potential risk factor currently existing around the gas station in the surrounding environment video;

[0023] A first judgment module, used for judging the sensor alarm event and the third potential risk factor currently existing in the gas station based on the real-time sensor data;

[0024] A second judgment module, used for judging the faulty equipment and the fourth potential risk factor currently existing in the gas station based on the inspection data;

[0025] Wherein, the first risk factor includes: the illegal behavior and the first potential risk factor and the second potential risk factor;

[0026] The second risk factor includes: the sensor alarm event, faulty equipment, the third potential risk factor, and the fourth potential risk factor.

[0027] Preferably, the first identification module includes:

[0028] A first identification unit, configured to identify, from the internal surveillance video, current violations within the gas station;

[0029] The second identification unit is used to identify the unconventional behavior currently existing in the gas station in the internal monitoring video, and mark the unconventional behavior as the first potential risk factor currently existing in the gas station.

[0030] Preferably, the first judgment module includes:

[0031] A sensor alarm unit, used for comparing the first sub-sensor data obtained by each sensor in the real-time sensor data with the corresponding safety sensor data range, and screening out the second sub-sensor data exceeding the corresponding safety sensor data range, giving an alarm based on the second sub-sensor data, and recording the corresponding sensor alarm event;

[0032] an actual acquisition unit, used for acquiring actual sensor change data corresponding to each third sub-sensor data remaining in the real-time sensor data except the second sub-sensor data within a sampling period;

[0033] a standard acquisition unit, configured to determine the influencing factors and the corresponding influencing relationships corresponding to the third sub-sensor data, determine the influencing factor distribution data corresponding to the third sub-sensor data within the sampling period based on the influencing factors, and determine the corresponding standard sensor change data based on the influencing factor distribution data and the corresponding influencing relationships;

[0034] a deviation fitting unit, configured to obtain corresponding alignment data after aligning the actual sensor change data with the corresponding standard sensor change data, take a plurality of sampling points on the alignment data, calculate a corresponding sensor deviation ratio based on first data corresponding to the sampling points in the actual sensor change data and second data corresponding to the corresponding standard sensor change data, and fit a corresponding sensor deviation ratio curve based on the sensor deviation ratio corresponding to the sampling points;

[0035] a first sorting unit, configured to align the sensor deviation ratio curves corresponding to all the third sub-sensor data to obtain a corresponding alignment curve, divide the alignment curve into a plurality of intervals, calculate an average deviation ratio of the sensor deviation ratio curve in each interval, take an average of the average deviation ratios of all the sensor deviation ratio curves in the corresponding interval as a standard mean of the corresponding interval, calculate a first difference between the average deviation ratio of each sensor deviation ratio curve in the corresponding interval and the standard mean, and sort the corresponding third sub-sensor data in ascending order based on the first difference to obtain a corresponding first sorting result;

[0036] a second fitting unit, configured to determine a sorting ordinal number of the third sub-sensor data in the first sorting result, sort the sorting ordinals corresponding to the third sub-sensor data based on the order of the intervals in the alignment curve to obtain a corresponding sorting ordinal number sequence, and fit a corresponding ordinal curve based on the sorting ordinal number sequence;

[0037] A potential screening unit is used to determine the monotonically decreasing partial curves contained in the ordinal curve, determine the proportion of the monotonically decreasing partial curves in the ordinal curve and the average decreasing rate in each monotonically decreasing partial curve, calculate the corresponding potential risk level based on the proportion and the average decreasing rate, screen out the fourth sub-sensor data with potential risk based on the potential risk level, and regard the fourth sub-sensor data as the third potential risk factor corresponding to the gas station.

[0038] Preferably, the second judgment module includes:

[0039] an equipment identification unit, configured to determine all first equipment currently in use in the gas station based on the inspection data, compare the sub-inspection data corresponding to each first equipment contained in the inspection data with the fault identification data corresponding to the first equipment, determine a second equipment in the first equipment that has a fault, and regard the second equipment as a faulty equipment currently existing in the gas station;

[0040] a rule determination unit, configured to mark the first device in the complete device topology map corresponding to the gas station, obtain the corresponding current marked network, determine a first usage association rule between the first devices based on the current marked network, judge the usage status corresponding to the first device based on the sub-inspection data corresponding to each first device included in the inspection data, and determine a second usage association rule between the first devices based on the usage status;

[0041] a relationship determination unit, configured to determine a current device association layout corresponding to the gas station based on the first usage association rule and the second usage association rule, and determine all first association relationships between the first devices based on the current device association layout;

[0042] A first generating unit is used to determine a first data deviation between the first device and the corresponding fault identification data, and to determine a second data deviation between the first data deviations of the associated devices corresponding to each association relationship, and to generate a corresponding association deviation matrix based on the current device association layout and the second data deviation;

[0043] A second generating unit is configured to use the second data deviation between the first data deviations corresponding to the second device and contained in the association deviation matrix as an iteration center, set all iteration centers contained in the association deviation matrix to 0, and obtain a corresponding iteration matrix;

[0044] An accumulative iteration unit, used for multiplying the correlation deviation matrix by the iteration matrix in turn for a preset number of iterations to obtain an iteration result matrix corresponding to each iteration process, and sorting the iteration result matrix based on the number of iterations to obtain a corresponding iteration result matrix sequence;

[0045] A potential identification unit is used to determine, based on the association relationship corresponding to the numerical value that becomes 0 in the iterative result matrix, the third data deviation between the sub-inspection data corresponding to the third device contained in the association relationship and the corresponding fault judgment data, and the third device corresponding to the larger third data deviation is used as the corresponding potential fault device, and the potential fault devices are sorted based on the iterative result matrix sequence to obtain the corresponding potential fault device sequence, and the potential fault device sequence is used as the fourth potential risk factor currently existing in the gas station.

[0046] Preferably, the comprehensive analysis terminal includes:

[0047] A first analysis module, configured to comprehensively analyze the current risk factors of the gas station based on the illegal behavior, the sensor alarm event, and the faulty equipment;

[0048] The second analysis module is used to comprehensively analyze the potential risk factors of the gas station based on the first potential risk factor, the second potential risk factor, the third potential risk factor and the fourth potential risk factor.

[0049] Preferably, the comprehensive display terminal includes:

[0050] A sorting module, used to sort the corresponding risk factors based on the display mode of each risk factor included in the analysis result to obtain corresponding information to be displayed;

[0051] A display module is used to transmit the information to be displayed to the corresponding IOC data dashboard for visual display;

[0052] Among them, the risk factors are the third risk factor included in the current risk factors and the fourth risk factor included in the potential risk factors.

[0053] Preferably, the first analysis module includes:

[0054] A fundamental determination unit, configured to determine corresponding fundamental risk factors based on potential relationships between the violation, the sensor alarm event, and the faulty equipment;

[0055] The criticality ranking unit is used to calculate the corresponding comprehensive criticality based on the criticality of the fundamental risk factor and the weight value, and to rank the fundamental risk factors based on the comprehensive criticality to obtain the current risk factors of the gas station.

[0056] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0057] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0059] Figure 1 A schematic diagram of a gas station digital safety insight system management and display platform in an embodiment of the present invention;

[0060] Figure 2 This is a schematic diagram of a monitoring acquisition terminal in an embodiment of the present invention;

[0061] Figure 3 A schematic diagram of a monitoring camera module in an embodiment of the present invention;

[0062] Figure 4 This is a schematic diagram of an identification and judgment terminal in an embodiment of the present invention;

[0063] Figure 5 This is a schematic diagram of a first identification module in an embodiment of the present invention;

[0064] Figure 6 This is a schematic diagram of a first judgment module in an embodiment of the present invention;

[0065] Figure 7 This is a schematic diagram of a second judgment module in an embodiment of the present invention;

[0066] Figure 8 This is a schematic diagram of a comprehensive analysis terminal in an embodiment of the present invention;

[0067] Fig. 9 This is a schematic diagram of a comprehensive display terminal in an embodiment of the present invention;

[0068] Fig.10 This is a schematic diagram of a first analysis module in an embodiment of the present invention. DETAILED DESCRIPTION

[0069] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0070] Embodiment 1:

[0071] The present invention provides a gas station digital safety insight system management and display platform, referring to Figure 1 ,include:

[0072] The monitoring acquisition terminal is used to obtain relevant monitoring videos and terminal monitoring data of the gas station;

[0073] An identification and judgment terminal, used to identify the first risk factor in the relevant monitoring video, and at the same time, judge the second risk factor in the gas station based on the terminal monitoring data;

[0074] A comprehensive analysis terminal, used for performing a digital comprehensive analysis on the first risk factor and the second risk factor to obtain corresponding analysis results;

[0075] The comprehensive display terminal is used to visualize the analysis results in the corresponding IOC data dashboard.

[0076] In this embodiment, the relevant surveillance video is the surveillance video inside and outside the gas station.

[0077] In this embodiment, the terminal monitoring data is the sensor data and inspection data in the gas station obtained based on sensors.

[0078] In this embodiment, the first risk factor is the risk factor included in the relevant monitoring video.

[0079] In this embodiment, the second risk factor is the risk factor in the gas station determined based on the terminal monitoring data.

[0080] In this embodiment, the analysis result is the result obtained after comprehensive analysis of the first risk factor and the second risk factor.

[0081] In this embodiment, the IOC (Intelligent Operations Center) data dashboard is the smart city intelligent operations center data dashboard.

[0082] The beneficial effects of the above technology are: based on the existing gas station terminal monitoring devices, safety insight analysis and display are carried out, and automatic security inspections, intelligent identification and early warning, and display of gas stations are realized based on digital technology, so as to achieve pre-emptive prevention, post-event evidence retention, and in-event linkage dispatch, and comprehensively improve the active safety management and control capabilities of gas stations.

[0083] Embodiment 2:

[0084] Based on Example 1, the monitoring acquisition end refers to Figure 2 ,include:

[0085] A surveillance camera module, used for acquiring relevant surveillance videos inside and outside the gas station based on a camera;

[0086] A terminal sensing module, used for acquiring real-time sensing data in the gas station based on a variety of sensors arranged in the gas station;

[0087] An intelligent inspection module, used for obtaining inspection data in the gas station according to a preset period based on manual inspection or automatic inspection;

[0088] The Internet of Things transmission module is used to transmit the real-time sensing data and the inspection data as the terminal monitoring data corresponding to the gas station to the identification and judgment terminal based on the Internet of Things.

[0089] In this embodiment, the various sensors include, for example, a smoke sensor, a temperature sensor, and the like.

[0090] In this embodiment, the real-time sensor data is sensor data in the gas station acquired in real time based on a variety of sensors installed in the gas station.

[0091] In this embodiment, the inspection data is data obtained by inspecting gas stations based on manual inspection or automatic inspection in accordance with a preset period.

[0092] In this embodiment, the preset period is the inspection period.

[0093] The beneficial effects of the above technology are: obtaining surveillance videos inside and outside the gas station based on cameras, and obtaining sensor data inside the gas station based on multiple sensors. At the same time, obtaining inspection data inside the gas station, providing a data foundation for subsequent automatic security inspections, intelligent identification and early warning, and display of gas stations based on digital technology.

[0094] Embodiment 3:

[0095] On the basis of Example 2, the monitoring camera module, referring to Figure 3 ,include:

[0096] An internal monitoring unit, used to obtain an internal monitoring video of the gas station based on a camera set at a corresponding position in the gas station;

[0097] An external monitoring unit, used for acquiring a video of the surrounding environment of the gas station based on cameras arranged at corresponding positions around the gas station;

[0098] The multiplexing unit is used to transmit all the internal monitoring videos and all the surrounding environment videos as the relevant monitoring videos corresponding to the gas station to the identification and judgment end.

[0099] In this embodiment, the internal surveillance video is a surveillance video for monitoring the interior of the gas station obtained based on a camera installed in the gas station.

[0100] In this embodiment, the surrounding environment video is a surveillance video for monitoring the surrounding area of ​​the gas station obtained based on cameras installed around the gas station.

[0101] The beneficial effects of the above technology are: based on the acquisition of surveillance videos inside and around the gas station based on multiple cameras installed inside and around the gas station, comprehensive monitoring of the inside and around the gas station is achieved, and a data basis is provided for the subsequent realization of digital security monitoring of the gas station.

[0102] Embodiment 4:

[0103] Based on Example 1, the identification and judgment end refers to Figure 4 ,include:

[0104] A first identification module, used to identify the current illegal behavior and the first potential risk factor of the gas station in the internal monitoring video;

[0105] A second identification module is used to identify a second potential risk factor currently existing around the gas station in the surrounding environment video;

[0106] A first judgment module, used for judging the sensor alarm event and the third potential risk factor currently existing in the gas station based on the real-time sensor data;

[0107] A second judgment module, used for judging the faulty equipment and the fourth potential risk factor currently existing in the gas station based on the inspection data;

[0108] Wherein, the first risk factor includes: the illegal behavior and the first potential risk factor and the second potential risk factor;

[0109] The second risk factor includes: the sensor alarm event, faulty equipment, the third potential risk factor, and the fourth potential risk factor.

[0110] In this embodiment, the illegal behavior is the current illegal behavior of the gas station identified in the gas station surveillance video.

[0111] In this embodiment, the first potential risk factor is the potential risk factor currently existing in the gas station identified in the internal surveillance video.

[0112] In this embodiment, the second potential risk factor is the potential risk factor currently existing around the gas station identified in the surrounding environment video.

[0113] In this embodiment, the sensor alarm event is an event that currently requires an alarm in the gas station determined based on real-time sensor data.

[0114] In this embodiment, the third potential risk factor is the potential risk factor currently existing in the gas station determined based on the real-time sensor data.

[0115] In this embodiment, the faulty equipment is the faulty equipment currently existing in the gas station determined based on the inspection data.

[0116] In this embodiment, the fourth potential risk factor is the potential risk factor currently existing in the gas station determined based on the inspection data.

[0117] The beneficial effects of the above technology are: by identifying the corresponding internal surveillance videos, surrounding surveillance videos, real-time sensor data, and inspection data of the gas station, it is possible to determine the current violations, sensor alarm events, faulty equipment, and potential dangerous factors in the gas station, providing a key data foundation for the subsequent digital safety insight management of the gas station.

[0118] Embodiment 5:

[0119] Based on Example 4, the first identification module refers to Figure 5 ,include:

[0120] A first identification unit, configured to identify, from the internal surveillance video, current violations within the gas station;

[0121] The second identification unit is used to identify the unconventional behavior currently existing in the gas station in the internal monitoring video, and mark the unconventional behavior as the first potential risk factor currently existing in the gas station.

[0122] In this embodiment, the unconventional behavior is the unconventional behavior included in the non-violation behavior.

[0123] The beneficial effect of the above technology is that by identifying illegal and unconventional behaviors in the internal surveillance video, all dangerous factors and potential dangerous factors currently existing in the gas station can be identified and determined.

[0124] Embodiment 6:

[0125] Based on Example 4, the first judgment module refers to Figure 6 ,include:

[0126] A sensor alarm unit, used for comparing the first sub-sensor data obtained by each sensor in the real-time sensor data with the corresponding safety sensor data range, and screening out the second sub-sensor data exceeding the corresponding safety sensor data range, giving an alarm based on the second sub-sensor data, and recording the corresponding sensor alarm event;

[0127] an actual acquisition unit, used for acquiring actual sensor change data corresponding to each third sub-sensor data remaining in the real-time sensor data except the second sub-sensor data within a sampling period;

[0128] a standard acquisition unit, configured to determine the influencing factors and the corresponding influencing relationships corresponding to the third sub-sensor data, determine the influencing factor distribution data corresponding to the third sub-sensor data within the sampling period based on the influencing factors, and determine the corresponding standard sensor change data based on the influencing factor distribution data and the corresponding influencing relationships;

[0129] a deviation fitting unit, configured to obtain corresponding alignment data after aligning the actual sensor change data with the corresponding standard sensor change data, take a plurality of sampling points on the alignment data, calculate a corresponding sensor deviation ratio based on first data corresponding to the sampling points in the actual sensor change data and second data corresponding to the corresponding standard sensor change data, and fit a corresponding sensor deviation ratio curve based on the sensor deviation ratio corresponding to the sampling points;

[0130] a first sorting unit, configured to align the sensor deviation ratio curves corresponding to all the third sub-sensor data to obtain a corresponding alignment curve, divide the alignment curve into a plurality of intervals, calculate an average deviation ratio of the sensor deviation ratio curve in each interval, take an average of the average deviation ratios of all the sensor deviation ratio curves in the corresponding interval as a standard mean of the corresponding interval, calculate a first difference between the average deviation ratio of each sensor deviation ratio curve in the corresponding interval and the standard mean, and sort the corresponding third sub-sensor data in ascending order based on the first difference to obtain a corresponding first sorting result;

[0131] a second fitting unit, configured to determine a sorting ordinal number of the third sub-sensor data in the first sorting result, sort the sorting ordinals corresponding to the third sub-sensor data based on the order of the intervals in the alignment curve to obtain a corresponding sorting ordinal number sequence, and fit a corresponding ordinal curve based on the sorting ordinal number sequence;

[0132] A potential screening unit is used to determine the monotonically decreasing partial curves contained in the ordinal curve, determine the proportion of the monotonically decreasing partial curves in the ordinal curve and the average decreasing rate in each monotonically decreasing partial curve, calculate the corresponding potential risk level based on the proportion and the average decreasing rate, screen out the fourth sub-sensor data with potential risk based on the potential risk level, and regard the fourth sub-sensor data as the third potential risk factor corresponding to the gas station.

[0133] In this embodiment, the first sub-sensing data is the sub-sensing data corresponding to the corresponding sensor included in the real-time sensing data.

[0134] In this embodiment, the safety sensor data range is the range of sensor data corresponding to the corresponding sensor when no alarm event occurs.

[0135] In this embodiment, the second sub-sensing data is the sub-sensing data included in the real-time sensing data and corresponding to the safety sensing data range.

[0136] In this embodiment, the third sub-sensing data is the remaining sub-sensing data in the real-time sensing data except the second sub-sensing data.

[0137] In this embodiment, the actual sensor change data is the sensor change data corresponding to the third sub-sensor data within the sampling period.

[0138] In this embodiment, the sampling period is a period for acquiring actual sensor change data.

[0139] In this embodiment, the influencing factors are factors that affect the third sub-sensing data, such as temperature, humidity, etc.

[0140] In this embodiment, the influence relationship is the influence function relationship between the third and corresponding influence factors.

[0141] In this embodiment, the influencing factor distribution data is the change data corresponding to the influencing factor within the sampling period.

[0142] In this embodiment, the standard sensor change data is the sensor change data determined based on the influencing factor distribution data and the corresponding influencing relationship.

[0143] In this embodiment, the alignment data is data obtained by aligning the actual sensing change data with the corresponding standard sensing change data.

[0144] In this embodiment, the sampling points are a plurality of points determined at preset intervals on the alignment data.

[0145] In this embodiment, the first data is the value corresponding to the sampling point in the actual sensor change data.

[0146] In this embodiment, the second data is the value corresponding to the sampling point in the corresponding standard sensor change data.

[0147] In this embodiment, the corresponding sensing deviation ratio is calculated based on the first data corresponding to the sampling point in the actual sensing change data and the second data corresponding to the sampling point in the corresponding standard sensing change data, including:

[0148]

[0149] Wherein, b is the sensor deviation ratio between the currently calculated first data and the corresponding second data in the corresponding standard sensor change data, e is a natural constant and the value of e is 2.72, s1 is the first data corresponding to the sampling point in the actual sensor change data, and s2 is the second data corresponding to the sampling point in the corresponding standard sensor change data;

[0150] For example, if s1 is 10 and s2 is 20, then b is 0.65.

[0151] In this embodiment, the sensing deviation ratio curve is a curve fitted based on the sensing deviation ratios corresponding to the sampling points.

[0152] In this embodiment, the alignment curve is a curve obtained by aligning the sensing deviation ratio curves corresponding to all the third sub-sensing data.

[0153] In this embodiment, the interval is a curve segment obtained by dividing the alignment curve according to a preset interval.

[0154] In this embodiment, the average deviation ratio is the average value of the sensing deviation ratio of the sensing deviation ratio curve corresponding to the sensing deviation ratio curve.

[0155] In this embodiment, the standard mean is the mean of the average deviation ratios of all sensor deviation ratio curves in the corresponding interval.

[0156] In this embodiment, the first difference is the difference between the average deviation ratio of the sensing deviation ratio curve in the corresponding interval and the corresponding standard mean.

[0157] In this embodiment, the first sorting result is a result obtained by sorting the corresponding third sub-sensor data in ascending order based on the first difference value.

[0158] In this embodiment, the sorting sequence number is the sequence number of the third sub-sensor data in the first sorting result.

[0159] In this embodiment, the sorting ordinal number sequence is a sequence obtained by sorting the sorting ordinal numbers corresponding to the third sub-sensor data based on the order of the intervals in the alignment curve.

[0160] In this embodiment, the ordinal curve is a curve fitted based on the sorted ordinal sequence.

[0161] In this embodiment, the monotonically decreasing portion curve is a curve of the monotonically decreasing portion contained in the ordinal curve.

[0162] In this embodiment, the proportion value is the ratio of the abscissa length of the monotonically decreasing portion of the curve to the total abscissa length of the ordinal curve.

[0163] In this embodiment, the average decreasing rate is the average value of the absolute value of the first-order derivative in the corresponding monotonically decreasing portion of the curve.

[0164] In this embodiment, the corresponding potential risk level is calculated based on the proportion value and the average decreasing rate, including:

[0165]

[0166] In the formula, q is the potential risk, w is the proportion, e is the average decreasing rate, and e0 is the standard decreasing rate;

[0167] For example, w is 0.5, e is 10, e0 is 20, and q is 0.25.

[0168] In this embodiment, the fourth sub-sensor data is the sub-sensor data with potential danger that is screened out based on the potential danger degree.

[0169] The beneficial effect of the above technology is: by analyzing the degree of deviation and change between the actual sensor change data of the third sub-sensor data corresponding to the sensor in the real-time sensor data that has not caused an alarm event and the corresponding standard sensor change data, the potential dangerous factors in the gas station can be identified based on the real-time sensor data.

[0170] Embodiment 7:

[0171] Based on Example 4, the second judgment module refers to Figure 7 ,include:

[0172] an equipment identification unit, configured to determine all first equipment currently in use in the gas station based on the inspection data, compare the sub-inspection data corresponding to each first equipment contained in the inspection data with the fault identification data corresponding to the first equipment, determine a second equipment in the first equipment that has a fault, and regard the second equipment as a faulty equipment currently existing in the gas station;

[0173] a rule determination unit, configured to mark the first device in the complete device topology map corresponding to the gas station, obtain the corresponding current marked network, determine a first usage association rule between the first devices based on the current marked network, judge the usage status corresponding to the first device based on the sub-inspection data corresponding to each first device included in the inspection data, and determine a second usage association rule between the first devices based on the usage status;

[0174] a relationship determination unit, configured to determine a current device association layout corresponding to the gas station based on the first usage association rule and the second usage association rule, and determine all first association relationships between the first devices based on the current device association layout;

[0175] A first generating unit is used to determine a first data deviation between the first device and the corresponding fault identification data, and to determine a second data deviation between the first data deviations of the associated devices corresponding to each association relationship, and to generate a corresponding association deviation matrix based on the current device association layout and the second data deviation;

[0176] A second generating unit is configured to use the second data deviation between the first data deviations corresponding to the second device and contained in the association deviation matrix as an iteration center, set all iteration centers contained in the association deviation matrix to 0, and obtain a corresponding iteration matrix;

[0177] An accumulative iteration unit, used for multiplying the correlation deviation matrix by the iteration matrix in turn for a preset number of iterations to obtain an iteration result matrix corresponding to each iteration process, and sorting the iteration result matrix based on the number of iterations to obtain a corresponding iteration result matrix sequence;

[0178] A potential identification unit is used to determine, based on the association relationship corresponding to the numerical value that becomes 0 in the iterative result matrix, the third data deviation between the sub-inspection data corresponding to the third device contained in the association relationship and the corresponding fault judgment data, and the third device corresponding to the larger third data deviation is used as the corresponding potential fault device, and the potential fault devices are sorted based on the iterative result matrix sequence to obtain the corresponding potential fault device sequence, and the potential fault device sequence is used as the fourth potential risk factor currently existing in the gas station.

[0179] In this embodiment, the first device is the device currently in use in the gas station determined based on the inspection data.

[0180] In this embodiment, the sub-inspection data is the inspection data corresponding to the first device contained in the inspection data.

[0181] In this embodiment, the fault identification data is the inspection data range corresponding to when a fault occurs in the corresponding device.

[0182] In this embodiment, the second device is the device in the first device that fails.

[0183] In this embodiment, the faulty device is the screened second device.

[0184] In this embodiment, the complete device topology diagram is a diagram representing the connection relationship between all devices in the gas station.

[0185] In this embodiment, the current marked network is the result obtained after marking the first device in the complete device topology map corresponding to the gas station.

[0186] In this embodiment, the first usage association rule is an association usage rule between first devices determined based on the current tag network, and the association usage rule is a rule that affects each other.

[0187] In this embodiment, the usage status is the current usage status of the first device determined based on the sub-patrol data corresponding to the first device.

[0188] In this embodiment, the second usage association rule is an association usage rule between first devices determined based on the usage status, and the association usage rule is a rule that affects each other.

[0189] In this embodiment, the current device association layout is a layout that characterizes the current associations between devices in the gas station and is determined based on the first usage association rule and the second usage association rule.

[0190] In this embodiment, the first association relationship is all the association relationships between the first devices determined based on the current device association layout.

[0191] In this embodiment, the first data deviation is a deviation value between the first device and the corresponding fault determination data.

[0192] In this embodiment, the second data deviation is the deviation value between the first data deviations corresponding to the associated devices corresponding to each association relationship.

[0193] In this embodiment, the association deviation matrix is ​​a matrix generated based on the current device association layout and the second data deviation, which represents the deviation data between the associated devices contained in the currently used devices.

[0194] In this embodiment, the iteration center is the data deviation between the first data deviation corresponding to the second device and included in the correlation deviation matrix.

[0195] In this embodiment, the iteration matrix is ​​a matrix obtained by taking the second data deviation between the first data deviations corresponding to the second device and included in the association deviation matrix as the iteration center and setting all the iteration centers included in the association deviation matrix to 0.

[0196] In this embodiment, the iteration result matrix is ​​an iteration result matrix corresponding to each iteration process obtained by multiplying the correlation deviation matrix by the iteration matrix in sequence for a preset number of iterations.

[0197] In this embodiment, the iteration result matrix sequence is a matrix sequence obtained by sorting the iteration result matrices based on the number of iterations.

[0198] In this embodiment, the third data deviation is the data deviation between the sub-inspection data corresponding to the third device included in the association relationship and the corresponding fault determination data.

[0199] In this embodiment, the potential faulty device is the third device corresponding to the larger third data deviation.

[0200] In this embodiment, the potential fault device sequence is the device sequence obtained based on the iterative result matrix sequence pair.

[0201] The beneficial effects of the above technology are: based on the inspection data, deviation comparison and iteration are performed on the associated usage rules between the first devices currently in use in the gas station and the sub-inspection data corresponding to each first device, and then the dangerousness of the first devices is ranked based on the iteration results, thereby obtaining the fourth potential risk factor currently existing in the gas station.

[0202] Embodiment 8:

[0203] Based on Example 1, the comprehensive analysis end refers to Figure 8 ,include:

[0204] A first analysis module, configured to comprehensively analyze the current risk factors of the gas station based on the illegal behavior, the sensor alarm event, and the faulty equipment;

[0205] The second analysis module is used to comprehensively analyze the potential risk factors of the gas station based on the first potential risk factor, the second potential risk factor, the third potential risk factor and the fourth potential risk factor.

[0206] In this embodiment, the current risk factors include: illegal behaviors, sensor alarm events, and faulty equipment.

[0207] In this embodiment, the potential risk factors include: a first potential risk factor, a second potential risk factor, a third potential risk factor and a fourth potential risk factor.

[0208] The beneficial effects of the above technology are: all current risk factors and potential risk factors identified and judged based on internal surveillance videos, surrounding surveillance videos, real-time sensor data and inspection data are summarized, realizing digital safety insight and control of gas stations.

[0209] Embodiment 9:

[0210] Based on Example 1, the comprehensive display terminal refers to Fig. 9 ,include:

[0211] A sorting module, used to sort the corresponding risk factors based on the display mode of each risk factor included in the analysis result to obtain corresponding information to be displayed;

[0212] A display module is used to transmit the information to be displayed to the corresponding IOC data dashboard for visual display;

[0213] Among them, the risk factors are the third risk factor included in the current risk factors and the fourth risk factor included in the potential risk factors.

[0214] In this embodiment, the display methods include: video display, text display, table display, etc.

[0215] In this embodiment, the information to be displayed is the display information obtained by sorting the corresponding risk factors based on the display method of each risk factor included in the analysis result.

[0216] The beneficial effects of the above technology are: based on the display method of each risk factor contained in the analysis results, the corresponding risk factors are sorted out to obtain the corresponding display information, and then it is put into the IOC data dashboard for visual display, thereby realizing the visualization of risk factors in the gas station, providing direct reference for pre-prevention, post-event evidence retention, and in-event linkage scheduling, and comprehensively improving the active safety management and control capabilities of gas stations.

[0217] Embodiment 10:

[0218] Based on Example 8, the first analysis module refers to Fig.10 ,include:

[0219] A fundamental determination unit, configured to determine corresponding fundamental risk factors based on potential relationships between the violation, the sensor alarm event, and the faulty equipment;

[0220] The criticality ranking unit is used to calculate the corresponding comprehensive criticality based on the criticality of the fundamental risk factor and the weight value, and to rank the fundamental risk factors based on the comprehensive criticality to obtain the current risk factors of the gas station.

[0221] In this embodiment, the potential relationship is the potential impact relationship between the violation behavior and the sensor alarm event and the faulty equipment.

[0222] In this embodiment, the fundamental risk factor is the most fundamental risk factor determined based on the potential relationship between the violation behavior, the sensor alarm event, and the faulty equipment.

[0223] In this embodiment, the criticality is the criticality determined based on the actual situation of the fundamental risk factor.

[0224] In this embodiment, the weight value is determined based on the preset weight value corresponding to each fundamental risk factor.

[0225] In this embodiment, the comprehensive criticality is the product of the criticality and the weight value.

[0226] The beneficial effects of the above technology are: by determining the fundamental risk factors through the potential relationship between all current risk factors existing in the gas station, and sorting the fundamental risk factors based on the comprehensive criticality determined by the criticality and weight value, the digital analysis and intuitive display of the current risk factors are realized, which comprehensively improves the active safety management and control capabilities of the gas station.

[0227] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A gas station digital safety insight system management and display platform, characterized in that: include: The monitoring acquisition terminal is used to obtain relevant monitoring videos and terminal monitoring data of the gas station; An identification and judgment terminal, used to identify a first risk factor in the relevant monitoring video, and at the same time, to judge a second risk factor in the gas station based on the terminal monitoring data; A comprehensive analysis terminal, used for performing a digital comprehensive analysis on the first risk factor and the second risk factor to obtain corresponding analysis results; A comprehensive display terminal is used to visualize the analysis results in a corresponding IOC data dashboard; The identification and judgment end includes: A first identification module, used to identify the current illegal behavior and the first potential risk factor of the gas station in the internal monitoring video; A second identification module is used to identify a second potential risk factor currently existing around the gas station in the surrounding environment video; A first judgment module is used to judge the sensor alarm events and the third potential risk factors currently existing in the gas station based on the real-time sensor data; A second judgment module is used to judge the faulty equipment and the fourth potential risk factor currently existing in the gas station based on the inspection data; Wherein, the first risk factor includes: the illegal behavior and the first potential risk factor and the second potential risk factor; The second risk factor includes: the sensor alarm event, faulty equipment, the third potential risk factor and the fourth potential risk factor; Wherein, the first judgment module includes: A sensor alarm unit, used for comparing the first sub-sensor data obtained by each sensor in the real-time sensor data with the corresponding safety sensor data range, and screening out the second sub-sensor data exceeding the corresponding safety sensor data range, giving an alarm based on the second sub-sensor data, and recording the corresponding sensor alarm event; an actual acquisition unit, used for acquiring actual sensor change data corresponding to each third sub-sensor data remaining in the real-time sensor data except the second sub-sensor data within a sampling period; a standard acquisition unit, configured to determine the influencing factors and the corresponding influencing relationships corresponding to the third sub-sensor data, determine the influencing factor distribution data corresponding to the third sub-sensor data within the sampling period based on the influencing factors, and determine the corresponding standard sensor change data based on the influencing factor distribution data and the corresponding influencing relationships; a deviation fitting unit, configured to obtain corresponding alignment data after aligning the actual sensor change data with the corresponding standard sensor change data, take a plurality of sampling points on the alignment data, calculate a corresponding sensor deviation ratio based on first data corresponding to the sampling points in the actual sensor change data and second data corresponding to the corresponding standard sensor change data, and fit a corresponding sensor deviation ratio curve based on the sensor deviation ratio corresponding to the sampling points; a first sorting unit, configured to align the sensor deviation ratio curves corresponding to all the third sub-sensor data to obtain a corresponding alignment curve, divide the alignment curve into a plurality of intervals, calculate an average deviation ratio of the sensor deviation ratio curve in each interval, take an average of the average deviation ratios of all the sensor deviation ratio curves in the corresponding interval as a standard mean of the corresponding interval, calculate a first difference between the average deviation ratio of each sensor deviation ratio curve in the corresponding interval and the standard mean, and sort the corresponding third sub-sensor data in ascending order based on the first difference to obtain a corresponding first sorting result; a second fitting unit, configured to determine a sorting ordinal number of the third sub-sensor data in the first sorting result, sort the sorting ordinals corresponding to the third sub-sensor data based on the order of the intervals in the alignment curve to obtain a corresponding sorting ordinal number sequence, and fit a corresponding ordinal curve based on the sorting ordinal number sequence; A potential screening unit is used to determine the monotonically decreasing partial curves contained in the ordinal curve, determine the proportion of the monotonically decreasing partial curves in the ordinal curve and the average decreasing rate in each monotonically decreasing partial curve, calculate the corresponding potential risk level based on the proportion and the average decreasing rate, screen out the fourth sub-sensor data with potential risk based on the potential risk level, and regard the fourth sub-sensor data as the third potential risk factor corresponding to the gas station.

2. A gas station digital safety insight system management and display platform according to claim 1, characterized in that: The monitoring acquisition end includes: A surveillance camera module, used for acquiring relevant surveillance videos inside and outside the gas station based on a camera; A terminal sensing module, used for acquiring real-time sensing data in the gas station based on a variety of sensors arranged in the gas station; An intelligent inspection module, used for obtaining inspection data in the gas station according to a preset period based on manual inspection or automatic inspection; The Internet of Things transmission module is used to transmit the real-time sensing data and the inspection data as the terminal monitoring data corresponding to the gas station to the identification and judgment terminal based on the Internet of Things.

3. A gas station digital safety insight system management and display platform according to claim 2, characterized in that: The monitoring camera module comprises: An internal monitoring unit, used to obtain an internal monitoring video of the gas station based on a camera set at a corresponding position in the gas station; An external monitoring unit, used for acquiring a video of the surrounding environment of the gas station based on cameras arranged at corresponding positions around the gas station; The multiplexing unit is used to transmit all the internal monitoring videos and all the surrounding environment videos as the relevant monitoring videos corresponding to the gas station to the identification and judgment end.

4. A gas station digital safety insight system management and display platform according to claim 1, characterized in that: The first identification module includes: A first identification unit, configured to identify, from the internal surveillance video, current violations within the gas station; The second identification unit is used to identify the unconventional behavior currently existing in the gas station in the internal monitoring video, and mark the unconventional behavior as the first potential risk factor currently existing in the gas station.

5. A gas station digital safety insight system management and display platform according to claim 1, characterized in that: The second judgment module includes: an equipment identification unit, configured to determine all first equipment currently in use in the gas station based on the inspection data, compare the sub-inspection data corresponding to each first equipment contained in the inspection data with the fault identification data corresponding to the first equipment, determine a second equipment in the first equipment that has a fault, and regard the second equipment as a faulty equipment currently existing in the gas station; a rule determination unit, configured to mark the first device in the complete device topology map corresponding to the gas station, obtain the corresponding current marked network, determine a first usage association rule between the first devices based on the current marked network, judge the usage status corresponding to the first device based on the sub-inspection data corresponding to each first device included in the inspection data, and determine a second usage association rule between the first devices based on the usage status; a relationship determination unit, configured to determine a current device association layout corresponding to the gas station based on the first usage association rule and the second usage association rule, and determine all first association relationships between the first devices based on the current device association layout; A first generating unit is used to determine a first data deviation between the first device and the corresponding fault identification data, and to determine a second data deviation between the first data deviations of the associated devices corresponding to each association relationship, and to generate a corresponding association deviation matrix based on the current device association layout and the second data deviation; A second generating unit is configured to use the second data deviation between the first data deviations corresponding to the second device and contained in the association deviation matrix as an iteration center, set all iteration centers contained in the association deviation matrix to 0, and obtain a corresponding iteration matrix; An accumulative iteration unit, used for multiplying the correlation deviation matrix by the iteration matrix in turn for a preset number of iterations to obtain an iteration result matrix corresponding to each iteration process, and sorting the iteration result matrix based on the number of iterations to obtain a corresponding iteration result matrix sequence; A potential identification unit is used to determine, based on the association relationship corresponding to the numerical value that becomes 0 in the iterative result matrix, the third data deviation between the sub-inspection data corresponding to the third device contained in the association relationship and the corresponding fault judgment data, and the third device corresponding to the larger third data deviation is used as the corresponding potential fault device, and the potential fault devices are sorted based on the iterative result matrix sequence to obtain the corresponding potential fault device sequence, and the potential fault device sequence is used as the fourth potential risk factor currently existing in the gas station.

6. A gas station digital safety insight system management and display platform according to claim 1, characterized in that: The comprehensive analysis end includes: A first analysis module, configured to comprehensively analyze the current risk factors of the gas station based on the illegal behavior, the sensor alarm event, and the faulty equipment; The second analysis module is used to comprehensively analyze the potential risk factors of the gas station based on the first potential risk factor, the second potential risk factor, the third potential risk factor and the fourth potential risk factor.

7. A gas station digital safety insight system management and display platform according to claim 6, characterized in that: The comprehensive display terminal includes: A sorting module, used to sort the corresponding risk factors based on the display mode of each risk factor included in the analysis result to obtain corresponding information to be displayed; A display module is used to transmit the information to be displayed to the corresponding IOC data dashboard for visual display; Among them, the risk factors are the third risk factor included in the current risk factors and the fourth risk factor included in the potential risk factors.

8. A gas station digital safety insight system management and display platform according to claim 6, characterized in that: The first analysis module comprises: A fundamental determination unit, configured to determine corresponding fundamental risk factors based on potential relationships between the violation, the sensor alarm event, and the faulty equipment; The criticality ranking unit is used to calculate the corresponding comprehensive criticality based on the criticality and weight value of the fundamental risk factor, and to rank the fundamental risk factors based on the comprehensive criticality to obtain the current risk factor of the gas station.