Method and system for auditing the authenticity of LDAR inspection jobs based on spatiotemporal fingerprints

Abstract

The present disclosure relates to a kind of LDAR detection job authenticity auditing method and system based on space-time fingerprint, which comprises obtaining first time detection result based on first detection interval and preset detection confidence interval;Based on first historical leak detection data, time detection is carried out on first current leak detection data, to obtain second time detection result;First detection interval and mobile time threshold are compared, to obtain first space detection result;Based on first historical leak detection data, spatial detection is carried out on first current leak detection data, to obtain second space detection result;Similar detection is carried out on first current leak detection data and first historical leak detection data, to obtain first similar detection result;The detection result of three dimensions is carried out multi-factor nonlinear fusion processing, to obtain job detection result.Using the embodiment of the present disclosure can realize the logical check of time, space, data similarity three dimensions, significantly improve the detection rate and accuracy of LDAR fraud behavior.

Description

Technical Field

[0001] This disclosure relates to the field of industrial waste gas leak detection and repair (LDAR) technology, and in particular to a system for verifying the authenticity of LDAR detection operations based on spatiotemporal fingerprinting. Background Technology

[0002] Leak Detection and Repair (LDAR) is a core tool for controlling fugitive emissions of volatile organic compounds (VOCs) in the petrochemical and chemical industries. However, the current regulatory model has long faced the dilemma of "difficulty in ensuring data authenticity and difficulty in identifying fraud." Traditional LDAR data auditing mainly relies on manual spot checks. Faced with millions of sealing point detection records from enterprises, the coverage rate is often less than 1%, like "finding a needle in a haystack." More seriously, with the "high-tech" nature of fraud methods, third-party testing agencies often use customized software to generate "perfect fake data" that conforms to static rules (such as fixed detection intervals and reasonable numerical ranges). Individually, these data entries appear flawless and can pass simple threshold checks. Existing technology lacks a three-dimensional auditing mechanism that combines physical kinematic constraints (such as personnel movement speed and spatial topology) with historical behavioral baselines, making it impossible to identify deep-seated and concealed fraudulent behaviors such as "teleportation detection," "through-wall detection," and "data cloning," resulting in difficulties in effectively curbing data fraud.

[0003] In related technologies, single data entries are often verified using static rules such as fixed detection time and reasonable numerical range. However, these technologies are difficult to identify hidden fraudulent behaviors that involve overall logical fraud, making it difficult to ensure data authenticity and identify fraud, which in turn leads to a low fraud detection rate and high regulatory costs. Summary of the Invention

[0004] This disclosure provides a method and system for verifying the authenticity of LDAR detection operations based on spatiotemporal fingerprinting. This addresses at least the problems in related technologies where it is difficult to identify concealed fraudulent activities that compromise the overall logical structure of LDAR data, leading to difficulties in data integrity and fraud detection, resulting in low fraud detection rates and high regulatory costs. The technical solution of this disclosure is as follows: According to a first aspect of the present disclosure, a method for verifying the authenticity of LDAR detection operations based on spatiotemporal fingerprinting is provided, comprising: The system acquires first current leak detection data corresponding to the target sealing point, first historical leak detection data corresponding to the target sealing point, second current leak detection data corresponding to adjacent sealing points of the target sealing point, a preset detection confidence interval, and a movement time threshold. The adjacent sealing points are those adjacent to the target sealing point. The preset detection confidence interval represents a reasonable range of time detection intervals between the target sealing point and the adjacent sealing points. The movement time threshold represents the shortest time required for the adjacent sealing point to travel to the target sealing point for detection. Based on the detection time in the first current leak detection data and the detection time in the second current leak detection data, a first detection interval is determined between the target sealing point and adjacent sealing points; Based on the first detection interval and the preset detection confidence interval, time detection is performed on the first current leakage detection data to obtain the first time detection result; Based on the first historical detection time set in the first historical leakage detection data, time detection is performed on the detection time in the first current leakage detection data to obtain a second time detection result; the first historical detection time set includes multiple historical detection times that characterize the detection time interval of the target sealing point as having historical periodicity; The first detection interval is compared with the movement time threshold to obtain the first spatial detection result; Based on the target historical detection location set in the first historical leakage detection data, spatial detection is performed on the detection locations in the first current leakage detection data to obtain a second spatial detection result; the target historical detection location set includes multiple historical detection locations that characterize the spatial location of the target sealing point and have historical consistency; A similarity detection is performed on the first current leak detection data and the first historical leak detection data to obtain a first similarity detection result; The first spatial detection result, the second spatial detection result, the first time detection result, the second time detection result, and the first similarity detection result are subjected to multi-factor nonlinear fusion processing to obtain the operational detection result of the first current leakage detection data.

[0005] In an optional embodiment, the first historical leak detection data includes multiple historical leak detection data sets, and the step of performing similarity detection on the first current leak detection data and the first historical leak detection data to obtain a first similarity detection result includes: The first current leak detection data and the multiple historical leak detection data are classified and processed to obtain multiple current leak detection datasets; Determine the target leak detection dataset where the first current leak detection data is located; the plurality of current leak detection datasets include the target leak detection dataset; A similarity estimate is performed on any two leakage detection data in the target leakage detection dataset to obtain a first similarity estimate result between the first current leakage detection data and the leakage detection data in the target leakage detection dataset excluding the first current leakage detection data; Based on the first similarity estimation result, the first similarity detection result is obtained.

[0006] In an optional embodiment, the method further includes: Obtain multiple historical detection locations corresponding to the target sealing point; Determine the first position distance between any two historical detection positions among the plurality of historical detection positions; If the distance to the first location is less than a preset distance threshold, the target historical detection location set is obtained based on the multiple historical detection locations.

[0007] In an optional embodiment, the step of performing spatial detection on the detection locations in the first current leak detection data based on the target historical detection location set in the first historical leak detection data to obtain a second spatial detection result includes: Determine the second location distance between the detection location in the first current leakage detection data and multiple historical detection locations in the target historical detection location set; The second spatial detection result is obtained based on the second location distance and the preset distance threshold.

[0008] In an optional embodiment, the method further includes: Obtain multiple historical detection times corresponding to the target sealing point; Determine the detection time interval between two adjacent historical detection times among the plurality of historical detection times; When the detection time interval is a preset detection time interval, the first set of historical detection times is obtained based on the multiple historical detection times.

[0009] In an optional embodiment, the step of performing time detection on the detection time in the first current leakage detection data based on the first historical detection time set in the first historical leakage detection data to obtain the second time detection result includes: Determine a second detection interval between the detection time in the first current leak detection data and multiple historical detection times in the first historical detection time set; The second detection interval is compared with the preset detection time interval to obtain the second time detection result.

[0010] In an optional embodiment, the method further includes: Obtain the historical detection interval characteristics between the target sealing point and adjacent sealing points; Based on the historical detection interval characteristics, the preset detection confidence interval is determined.

[0011] In an optional embodiment, obtaining the historical detection interval features between the target sealing point and adjacent sealing points includes: Obtain the second historical leakage detection data corresponding to the adjacent sealing points; Based on the first historical detection time set in the first historical leakage detection data and the second historical detection time set in the second historical leakage detection data, multiple historical detection intervals between the target sealing point and adjacent sealing points are obtained. The historical detection intervals are fitted to obtain the historical detection interval features.

[0012] Acquire leakage detection data for each of the multiple detection objects; Perform similarity detection on multiple leakage detection data corresponding to the multiple detection objects to obtain the second similarity estimation result corresponding to each of the multiple leakage detection data; Based on the second similarity estimation result, the second similarity detection result corresponding to each of the multiple leakage detection data is determined.

[0013] According to a second aspect of the present disclosure, a device for verifying the authenticity of LDAR detection operations based on spatiotemporal fingerprinting is provided, comprising: The first acquisition module is used to acquire first current leakage detection data corresponding to the target sealing point, first historical leakage detection data corresponding to the target sealing point, second current leakage detection data corresponding to the adjacent sealing points of the target sealing point, a preset detection confidence interval, and a movement time threshold; the adjacent sealing points are sealing points adjacent to the target sealing point; the preset detection confidence interval represents a reasonable range of time detection intervals between the target sealing point and the adjacent sealing points; the movement time threshold represents the shortest time required for the adjacent sealing points to travel to the target sealing point for detection; The first detection interval determination module is used to determine the first detection interval between the target sealing point and the adjacent sealing point based on the detection time in the first current leakage detection data and the detection time in the second current leakage detection data; The first-time detection module is used to perform time detection on the first current leakage detection data based on the first detection interval and the preset detection confidence interval to obtain the first-time detection result; The second time detection module is used to perform time detection on the detection time in the first current leakage detection data based on the first historical detection time set in the first historical leakage detection data, and obtain the second time detection result; the first historical detection time set includes multiple historical detection times that characterize the detection time interval of the target sealing point as having historical periodicity; The first spatial detection module is used to compare the first detection interval with the movement time threshold to obtain the first spatial detection result; The second spatial detection module is used to perform spatial detection on the detection positions in the first current leakage detection data based on the target historical detection position set in the first historical leakage detection data, and obtain the second spatial detection result; the target historical detection position set includes multiple historical detection positions that characterize the spatial position of the target sealing point as having historical consistency; The first similarity detection module is used to perform similarity detection on the first current leakage detection data and the first historical leakage detection data to obtain the first similarity detection result; The fusion processing module is used to perform multi-factor nonlinear fusion processing on the first spatial detection result, the second spatial detection result, the first time detection result, the second time detection result, and the first similarity detection result to obtain the operation detection result of the first current leakage detection data.

[0014] In an optional embodiment, the first historical leak detection data includes multiple historical leak detection data sets, and the first similarity detection module includes: A classification processing unit is used to classify the first current leak detection data and the multiple historical leak detection data to obtain multiple current leak detection datasets; A target leak detection dataset determination unit is used to determine the target leak detection dataset in which the first current leak detection data is located; the plurality of current leak detection datasets include the target leak detection dataset; The similarity estimation unit is used to perform similarity estimation on any two leakage detection data in the target leakage detection dataset to obtain a first similarity estimation result between the first current leakage detection data and the leakage detection data in the target leakage detection dataset other than the first current leakage detection data; The similarity detection result acquisition unit is used to obtain the first similarity detection result based on the first similarity estimation result.

[0015] In an optional embodiment, the apparatus further includes: The second acquisition module is used to acquire multiple historical detection positions corresponding to the target sealing point; The first position distance determination module is used to determine the first position distance between any two historical detection positions among the plurality of historical detection positions; The third acquisition module is used to obtain the target historical detection location set based on the multiple historical detection locations when the distance to the first location is less than a preset distance threshold.

[0016] In an optional embodiment, the second space detection module includes: The second location distance determination module is used to determine the second location distance between the detection location in the first current leakage detection data and multiple historical detection locations in the target historical detection location set; The second spatial detection result acquisition module is used to obtain the second spatial detection result based on the second location distance and a preset distance threshold.

[0017] In an optional embodiment, the apparatus further includes: The fourth acquisition module is used to acquire multiple historical detection times corresponding to the target sealing point; The detection time interval determination module is used to determine the detection time interval between two adjacent historical detection times among the plurality of historical detection times; The fifth acquisition module is used to obtain the first historical detection time set based on the multiple historical detection times when the detection time interval is a preset detection time interval.

[0018] In an optional embodiment, the second time detection module includes: The second detection interval determination module is used to determine a second detection interval between the detection time in the first current leakage detection data and multiple historical detection times in the first historical detection time set; The detection interval comparison module is used to compare the second detection interval with the preset detection time interval to obtain the second time detection result.

[0019] In an optional embodiment, the apparatus further includes: The sixth acquisition module is used to acquire the historical detection interval features between the target sealing point and adjacent sealing points; The confidence interval determination module is used to determine the preset detection confidence interval based on the historical detection interval characteristics.

[0020] In an optional embodiment, the sixth acquisition module includes: The first acquisition unit is used to acquire the second historical leakage detection data corresponding to the adjacent sealing points; The second acquisition unit is used to obtain multiple historical detection intervals between the target sealing point and adjacent sealing points based on the first historical detection time set in the first historical leakage detection data and the second historical detection time set in the second historical leakage detection data. The third acquisition unit is used to perform fitting processing on the multiple historical detection intervals to obtain the historical detection interval features.

[0021] In an optional embodiment, the apparatus further includes: The seventh acquisition module is used to acquire leakage detection data corresponding to each of the multiple detection objects; The second similarity detection module is used to perform similarity detection on multiple leakage detection data corresponding to the multiple detection objects, and obtain the second similarity estimation result corresponding to each of the multiple leakage detection data. The second similarity detection result acquisition module is used to determine the second similarity detection result corresponding to each of the multiple leakage detection data based on the second similarity estimation result.

[0022] According to a third aspect of the present disclosure, a system for verifying the authenticity of LDAR detection operations based on spatiotemporal fingerprinting is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute instructions to implement the method as described in any of the first aspects above.

[0023] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided such that, when instructions in the storage medium are executed by a system processor, the system is able to perform any of the methods of the first aspect of the present disclosure.

[0024] The technical solutions provided by the embodiments of this disclosure have at least the following beneficial effects: The system acquires first current leak detection data corresponding to the target sealing point, first historical leak detection data corresponding to the target sealing point, second current leak detection data corresponding to adjacent sealing points, a preset detection confidence interval, and a moving time threshold. The preset detection confidence interval represents a reasonable range of time detection intervals between the target sealing point and adjacent sealing points; the moving time threshold represents the shortest time required for adjacent sealing points to travel to the target sealing point for detection. Based on the dynamic multidimensional spatial fingerprint and dynamic multidimensional temporal fingerprint, spatial and temporal verification can be performed. Based on the detection time in the first and second current leak detection data, a first detection interval between the target sealing point and adjacent sealing points is determined. Based on the first detection interval and the preset detection confidence interval, the first current leak detection data is then subjected to temporal verification. The detection process involves three dimensions: time, space, and data similarity. The system performs time-based detection on the detection time within the current leak detection data, yielding a second time-based detection result. This second time-based detection result is obtained by comparing the first detection interval with a moving time threshold. The system then performs spatial detection on the detection location within the current leak detection data, based on a spatial fingerprint representing historical consistency of spatial location, resulting in a second spatial detection result. Finally, it performs similarity detection on the current leak detection data and historical leak detection data, yielding a first similarity detection result. Finally, a multi-factor nonlinear fusion process is applied to the spatial, temporal, and first similarity detection results to obtain the operational detection result for the current leak detection data. This system integrates logical verification from three independent dimensions—time, space, and data similarity—and employs a multi-factor nonlinear fusion model for comprehensive scoring. The dimensions complement and cross-validate each other, ensuring that even if a fraudster evades detection in a single dimension, the overall score effectively identifies anomalies, significantly improving the detection rate and accuracy of fraudulent activities.

[0025] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0026] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0027] Figure 1 This is a schematic diagram illustrating an application environment according to an exemplary embodiment; Figure 2 This is a flowchart illustrating an LDAR detection operation authenticity verification method based on spatiotemporal fingerprinting, according to an exemplary embodiment. Figure 3This is a block diagram of an LDAR detection operation authenticity verification device based on spatiotemporal fingerprinting, according to an exemplary embodiment. Figure 4 This is a block diagram illustrating a system for verifying the authenticity of LDAR detection operations based on spatiotemporal fingerprints, according to an exemplary embodiment. Figure 5 This is a block diagram illustrating a system for verifying the authenticity of LDAR detection operations based on spatiotemporal fingerprints, according to an exemplary embodiment. Detailed Implementation

[0028] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0029] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar different contents and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0030] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0031] Please see Figure 1 , Figure 1 This is a schematic diagram illustrating an application environment according to an exemplary embodiment, such as... Figure 1 As shown, the application environment may include terminal 100 and server 200.

[0032] In an optional embodiment, terminal 100 can be used to provide authenticity verification services for LDAR detection jobs based on spatiotemporal fingerprints. Specifically, terminal 100 can be, but is not limited to, electronic devices such as smartphones, desktop computers, tablets, laptops, smart speakers, digital assistants, augmented reality (AR) / virtual reality (VR) devices, and smart wearable devices, or software running on the aforementioned electronic devices, such as applications. Optionally, the operating system running on the electronic device can be, but is not limited to, Android, iOS, Linux, Windows, etc.

[0033] In an optional embodiment, server 200 can provide background services to terminal 100 and perform authenticity verification of LDAR detection operations based on spatiotemporal fingerprints. Specifically, server 200 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0034] In addition, it should be noted that, Figure 1 The example shown is merely one application environment provided by this disclosure; in practical applications, other application environments may also be included.

[0035] In the embodiments described in this specification, the terminal 100 and the server 200 can be directly or indirectly connected through wired or wireless communication, and this disclosure does not impose any restrictions.

[0036] Figure 2 This is a flowchart illustrating the authenticity verification of LDAR detection jobs based on spatiotemporal fingerprints, according to an exemplary embodiment. This method for verifying the authenticity of LDAR detection jobs based on spatiotemporal fingerprints is used in a server, such as... Figure 2 As shown, it includes the following steps.

[0037] In step S201, the first current leakage detection data corresponding to the target sealing point, the first historical leakage detection data corresponding to the target sealing point, the second current leakage detection data corresponding to the adjacent sealing points of the target sealing point, the preset detection confidence interval, and the moving time threshold are obtained. In a specific embodiment, the target sealing point can be a sealing location to prevent leakage. Optionally, the target sealing point can include at least one of the following locations: valve, flange, pump, etc. Specifically, the detection of the target sealing point and adjacent sealing points can be a leak detection of the target sealing point and adjacent sealing points. The leak detection data can be data obtained by leak detection of volatile organic compounds. The first current leak detection data can be the current leak detection data corresponding to the target sealing point, the first historical leak detection data can be the historical leak detection data corresponding to the target sealing point, the adjacent sealing point can be the sealing point adjacent to the target sealing point, and the second previous leak detection data can be the current leak detection data corresponding to the adjacent sealing point.

[0038] In one specific embodiment, the preset detection confidence interval can characterize a reasonable range of time detection intervals between the target sealing point and adjacent sealing points.

[0039] In an optional embodiment, the above method may further include: Obtain the historical detection interval features between the target sealing point and adjacent sealing points; Based on the characteristics of historical detection intervals, a preset detection confidence interval is determined.

[0040] In one specific embodiment, the historical detection interval feature can characterize the historical time detection interval feature between the target sealing point and adjacent sealing points. Specifically, the historical time detection interval feature can include the mean and standard deviation of the historical time detection interval between the target sealing point and adjacent sealing points.

[0041] In an optional embodiment, the acquisition of historical detection interval features between the target sealing point and adjacent sealing points may include: Obtain the second historical leakage detection data corresponding to adjacent sealing points; Based on the first historical detection time set in the first historical leakage detection data and the second historical detection time set in the second historical leakage detection data, multiple historical detection intervals between the target sealing point and adjacent sealing points are obtained. By fitting multiple historical detection intervals, the historical detection interval features are obtained.

[0042] In one specific embodiment, the second historical leakage detection data can be the historical leakage detection data corresponding to adjacent sealing points, and the first historical detection time set can be the historical detection time set corresponding to the target sealing point. Specifically, the first historical detection time set can include multiple historical detection times corresponding to the target sealing point, and the second historical detection time set can be the historical detection time set corresponding to adjacent sealing points. Specifically, the second historical detection time set can include multiple historical detection times corresponding to adjacent sealing points.

[0043] In a specific embodiment, multiple historical detection intervals can be multiple historical detection time intervals between the target sealing point and adjacent sealing points in multiple preset detection cycles. Specifically, the historical detection interval characteristics can include the mean and standard deviation of the historical time detection intervals between the target sealing point and adjacent sealing points. The mean and standard deviation of the historical time detection intervals are calculated by performing extreme value removal and normal distribution fitting processing on multiple historical time detection intervals.

[0044] In the above embodiments, by using multiple historical detection intervals as fitting features, the system closely matches the working habits of the site and the testing personnel, significantly reducing misjudgments. Furthermore, by utilizing statistical fitting, the system weakens single-instantaneous interference, thereby improving the stability of the time verification basis.

[0045] In a specific embodiment, a preset detection confidence interval can be set by the mean and standard deviation of the historical time detection interval in the historical time detection interval feature. Specifically, the difference between the mean and the standard deviation of the historical time detection interval can be used as the lower limit of the preset detection confidence interval, and the sum of the mean and the standard deviation of the historical time detection interval can be used as the upper limit of the preset detection confidence interval.

[0046] In one specific embodiment, for example, the average of the historical time detection intervals is used as... The standard deviation of the historical time detection interval is For example, the preset detection confidence interval can be ( - , + ).

[0047] In the above embodiments, by setting a reasonable confidence interval based on the historical detection interval characteristics between the target sealing point and adjacent sealing points, the detection cycle of each point can be automatically identified based on historical data, thereby reducing the false judgment rate.

[0048] In step S203, based on the detection time in the first current leak detection data and the detection time in the second current leak detection data, a first detection interval between the target sealing point and the adjacent sealing point is determined; In one specific embodiment, the first detection interval can be the current detection time interval between the target sealing point and the adjacent sealing point. Specifically, the first detection interval can be obtained by taking the absolute value of the detection time in the first current leakage detection data and the detection time in the second current leakage detection data.

[0049] In step S205, based on the first detection interval and the preset detection confidence interval, time detection is performed on the first current leakage detection data to obtain the first time detection result of the first current leakage detection data; In a specific embodiment, the first-time detection result can be the abnormal detection result of the first current leakage detection data in the time detection dimension. Specifically, the first-time detection result can be obtained by comparing the first detection interval with the preset detection confidence interval. Optionally, the first-time detection result can be obtained by the ratio of the difference between the first detection interval and the mean of the historical time detection interval to the standard deviation of the historical time detection interval.

[0050] In one specific embodiment, for example, the first detection interval may be: The average of the historical time detection intervals between the target sealing point and adjacent sealing points can be... The standard deviation of the historical time detection interval between the target sealing point and adjacent sealing points can be... The preset detection confidence interval can be ( - , + Accordingly, the first-time test results can be obtained by It was stated that the test results were available immediately. If the value is greater than 1, it is determined that there is an anomaly in the current leakage detection data in the time detection dimension, and the detection result is detected immediately. When the value is less than or equal to 1, it is determined that there is no anomaly in the current leakage detection data in the time detection dimension.

[0051] In step S207, based on the first historical detection time set in the first historical leakage detection data, time detection is performed on the detection time in the first current leakage detection data to obtain the second time detection result; In a specific embodiment, the first historical detection time set can be a set of historical detection times corresponding to the target sealing point. The first historical detection time set can include multiple historical detection times that characterize the detection time interval of the target sealing point as having historical periodicity. The second time detection result can characterize whether the first current leakage detection data is abnormal in the time detection dimension. Specifically, the second time detection result can characterize whether the first current leakage detection data and the first historical leakage detection data are consistent in the time detection dimension.

[0052] In an optional embodiment, the above-mentioned time detection based on the first historical detection time set in the first historical leakage detection data to obtain the second time detection result may include: Determine a second detection interval between the detection time in the first current leak detection data and multiple historical detection times in the first historical detection time set; The second detection interval is compared with the preset detection time interval to obtain the second time detection result.

[0053] In one specific embodiment, the second detection interval may be the detection interval between the detection time in the first current leakage detection data and multiple historical detection times in the first historical detection time set.

[0054] In a specific embodiment, the second detection interval can be compared with the preset detection time interval. If the second detection interval is the preset detection time interval, a second time detection result is obtained, which indicates that the first current leakage detection data does not have abnormal detection in the time detection dimension. If the second detection interval is not the preset detection time interval, a second time detection result is obtained, which indicates that the first current leakage detection data has abnormal detection in the time detection dimension.

[0055] In the above embodiments, by using dynamic historical time fingerprints with historical periodicity as a benchmark and comparing them with preset detection time intervals, time dimension fraud can be identified, false judgments can be reduced, and the computation is lightweight, ensuring accurate and efficient time detection.

[0056] In step S209, the first detection interval and the moving time threshold are compared to obtain the first spatial detection result of the first current leakage detection data; In a specific embodiment, the movement time threshold can characterize the shortest time required for an adjacent sealing point to travel to the target sealing point for detection. The first spatial detection result can be the abnormal detection result of the first current leakage detection data in the spatial detection dimension. Specifically, the first spatial detection result can be obtained by comparing the first detection interval and the movement time threshold. Optionally, the first spatial detection result can be obtained by the ratio of the first detection interval to the movement time threshold.

[0057] In one specific embodiment, for example, the shortest straight-line distance between the target sealing point and the adjacent sealing point can be... The maximum movement speed limit for the inspectors can be... The moving time threshold can be The first detection interval can be Correspondingly, the first space detection results can be obtained from It indicates that the results of the first space detection... If the value is greater than 1, it is determined that there is an anomaly in the current leakage detection data in the first spatial detection dimension, and the first spatial detection result is... When the value is less than or equal to 1, it is determined that there is no abnormality in the current leakage detection data in the first spatial detection dimension.

[0058] In step S2011, based on the target historical detection location set in the first historical leakage detection data, spatial detection is performed on the detection location in the first current leakage detection data to obtain the second spatial detection result.

[0059] In a specific embodiment, the target historical detection location set can be a set of historical detection locations corresponding to the target sealing point. The target historical detection location set can include multiple historical detection locations that characterize the spatial location of the target sealing point as having historical consistency. The second spatial detection result can characterize whether the first current leakage detection data is abnormal in the spatial detection dimension. Specifically, the second spatial detection result can characterize whether the first current leakage detection data and the first historical leakage detection data are consistent in the spatial detection dimension.

[0060] In an optional embodiment, the above-mentioned spatial detection of the detection locations in the first current leakage detection data based on the target historical detection location set in the first historical leakage detection data to obtain the second spatial detection result may include: Determine the second location distance between the detection location in the first current leak detection data and multiple historical detection locations in the target historical detection location set; The second spatial detection result is obtained based on the second location distance and the preset distance threshold.

[0061] In one specific embodiment, the second average distance can be the distance between the detection location in the first current leak detection data and multiple historical detection locations in the target historical detection location set.

[0062] In a specific embodiment, the average distance between the detection location and multiple historical detection locations in the first current leak detection data can be calculated based on the second location distance. Specifically, if the average distance between the detection location and multiple historical detection locations in the first current leak detection data reaches a preset distance threshold, a second spatial detection result is obtained that indicates that the first current leak detection data has abnormal detection in the spatial detection dimension. If the average distance between the detection location and multiple historical detection locations in the first current leak detection data does not reach the preset distance threshold, a second spatial detection result is obtained that indicates that the first current leak detection data does not have abnormal detection in the spatial detection dimension.

[0063] In the above embodiments, by using a dynamic historical spatial fingerprint with historical consistency as a benchmark and combining it with a preset distance threshold for judgment, wall penetration detection or other anomalies can be performed, while simplifying the calculation and ensuring accurate and efficient spatial detection.

[0064] In step S2013, a similarity detection is performed on the first current leakage detection data and the first historical leakage detection data to obtain the first similarity detection result of the first current leakage detection data; In one specific embodiment, the first similarity detection result can characterize the abnormal detection result of the first current leakage detection data in the similarity detection dimension.

[0065] In an optional embodiment, the first historical leakage detection data may include multiple historical leakage detection data sets. The above-mentioned similarity detection of the first current leakage detection data and the first historical leakage detection data to obtain the first similarity detection result of the first current leakage detection data may include: The first current leak detection data and multiple historical leak detection data are classified and processed to obtain multiple current leak detection datasets; Determine the target leak detection dataset where the first current leak detection data is located; Perform similarity estimation on any two leakage detection data in the target leakage detection dataset to obtain the first similarity estimation result between the first current leakage detection data and the leakage detection data in the target leakage detection dataset excluding the first current leakage detection data; Based on the first similarity estimation result, the first similarity detection result is obtained.

[0066] In one specific embodiment, multiple current leak detection datasets can be leak detection datasets obtained by classifying multiple historical leak detection data based on similarity. The leak detection dataset can include at least one of the following: sealing point identifier, spatial location coordinates, detection timestamp, detection personnel ID, detection value, etc. Optionally, multiple current leak detection datasets can include target leak detection datasets. The multiple current leak detection datasets can be obtained by classifying the first current leak detection data and multiple historical leak detection data. This can be achieved by generating multiple hash signatures from multiple historical leak detection data using the MinHash algorithm, and then classifying similar historical leak detection data using the LSH algorithm.

[0067] In a specific embodiment, the first similarity estimation result can characterize the similarity between the first current leak detection data and the leak detection data in the target leak detection dataset other than the first current leak detection data. Specifically, the first similarity estimation result can be the similarity Jaccard. The closer the similarity Jaccard is to 1, the higher the similarity between any two leak detection data.

[0068] In a specific embodiment, for example, the first similarity estimation result can be similarity J, and the first similarity detection result can be determined by... This indicates that it can be detected in the first similarity detection result. When the preset similarity threshold is reached, it is determined that there is an anomaly in the current leakage detection data in the first similarity detection dimension.

[0069] In the above embodiments, by classifying the target sealing point into multiple historical leakage detection data, multiple current leakage detection datasets are obtained. The similarity between the first current leakage detection data and other leakage detection data is calculated in the leakage detection dataset where the first current leakage detection data is located, thereby obtaining the first similarity detection result of the first current leakage detection data. This can narrow the comparison range, reduce the amount of computation, and improve the detection speed in big data scenarios.

[0070] In step S2015, the first spatial detection result, the second spatial detection result, the first time detection result, the second time detection result, and the first similarity detection result are subjected to multi-factor nonlinear fusion processing to obtain the operation detection result of the first current leakage detection data.

[0071] In a specific embodiment, auxiliary verification can be performed by combining the second spatial detection result and the second temporal detection result to obtain an auxiliary verification result. If the auxiliary verification result indicates that the first current leakage detection data needs auxiliary verification, the first spatial detection result, the first temporal detection result, and the first similarity detection result are subjected to multi-factor nonlinear fusion processing using the following formula to obtain the operation detection result of the first current leakage detection data. Specifically, the auxiliary verification result can be used to characterize whether the first current leakage detection data needs auxiliary verification. If both the second spatial detection result and the second temporal detection result indicate that the first current leakage detection data does not have abnormal detection, an auxiliary verification result indicating that the first current leakage detection data needs auxiliary verification is obtained. If either the second spatial detection result or the second temporal detection result indicates that the first current leakage detection data has abnormal detection, an auxiliary verification result indicating that the first current leakage detection data does not need auxiliary verification is obtained. Optionally, if the auxiliary verification result indicates that the first current leakage detection data does not need auxiliary verification, the operation detection result of the first current leakage detection data is obtained based on the second spatial detection result and the second temporal detection result.

[0072] In one specific embodiment, the job detection result can characterize whether there are any data anomalies in the first current leak detection data. For example, the job detection result can be... ,in, It can be the first test result. It could be the result of the first spatial detection. It can be the first similarity detection result. It can be information entropy, w1, w2, w3, w4 are weight coefficients, and w1+w2+w3+w4=1. Specifically, n is the total number of data anomaly detection points, and pi is the probability that the first current leakage detection data corresponding to the i-th sealing point is judged as similar data. Optionally, the probability that the first current leakage detection data is judged as similar data can be determined by the first similarity estimation result.

[0073] In a specific embodiment, the risk level of the first current leakage detection data can be determined by combining a preset low-risk threshold and a preset high-risk threshold. Specifically, if S is greater than or equal to the preset high-risk threshold, the first current leakage detection data is determined to be high-risk; if S is less than the preset high-risk threshold but greater than or equal to the preset low-risk threshold, the first current leakage detection data is determined to be medium-risk; and if S is less than the preset low-risk threshold, the first current leakage detection data is determined to be low-risk.

[0074] In an optional embodiment, the above method may further include: Obtain multiple historical detection locations corresponding to the target sealing point; Determine the first location distance between any two historical detection locations from a plurality of historical detection locations; If the distance to the first location is less than a preset distance threshold, a set of historical detection locations of the target is obtained based on multiple historical detection locations.

[0075] In a specific embodiment, multiple historical detection locations can be multiple historical detection times, which can be multiple detection locations corresponding to the target sealing point during the historical detection period. The first location distance can be the distance between any two historical detection locations. Specifically, it can be based on the first location distance to calculate the average distance between any two historical detection locations.

[0076] In one specific embodiment, the preset distance threshold can be a threshold of the average distance between any two historical detection locations. Optionally, if the average distance between any two historical detection locations is less than the preset distance threshold, multiple historical detection locations can be used as a target historical detection location set.

[0077] In the above embodiments, filtering historical coordinates that meet the requirements by using a distance threshold as dynamic spatial fingerprints can reduce false judgments, simplify computation, and provide reliable support for spatial verification.

[0078] In an optional embodiment, the first historical leakage detection data includes a first historical detection time set, and the above method may further include: Obtain multiple historical detection times corresponding to the target sealing point; Determine the detection time interval between two adjacent historical detection times from among multiple historical detection times; When the detection time interval is a preset detection time interval, a first historical detection time set is obtained based on multiple historical detection times.

[0079] In one specific embodiment, the multiple historical detection times can be multiple detection times corresponding to the target sealing point during the historical detection period, and the detection time interval can be the time interval between two adjacent historical detection times.

[0080] In a specific embodiment, the preset detection time interval can be the detection time interval corresponding to the target sealing point. Specifically, the preset detection time interval can be 90 days, 180 days, etc. When the detection time interval is the preset detection time interval, multiple historical detection times can be used as the first historical detection time set.

[0081] In the above embodiments, by selecting historical times that conform to the standard period as dynamic historical time fingerprints, and then performing spatial verification based on the dynamic historical time fingerprints, time dimension fraud can be accurately identified, false judgments can be reduced, and calculations can be simplified, providing reliable support for subsequent time series verification.

[0082] In an optional embodiment, the above method may further include: Acquire leakage detection data for each of the multiple detection objects; Similarity detection is performed on multiple leak detection data corresponding to multiple detection objects to obtain the second similarity estimation results for each of the multiple leak detection data; Based on the second similarity estimation results, the second similarity detection results corresponding to each of the multiple leakage detection data are determined.

[0083] In one specific embodiment, the multiple detection objects can be the detection objects corresponding to multiple sealing points. Specifically, the detection objects can be the detection personnel, and the multiple sealing points can be the sealing points located in the same area as the target sealing point.

[0084] In one specific embodiment, the leakage detection data can be leakage detection data corresponding to multiple detection objects, and the leakage detection data can include the current leakage detection data corresponding to multiple detection objects and multiple historical leakage detection data corresponding to multiple detection objects.

[0085] In a specific embodiment, the second similarity estimation result can characterize the similarity between any two leak detection data in the leak detection data. The second similarity estimation result can include the current similarity estimation result and the historical similarity estimation result. The current similarity estimation result can characterize the similarity between the current leak detection data corresponding to each of the multiple detection objects, and the historical similarity estimation result can characterize the similarity between multiple historical leak detection data corresponding to each detection object. Optionally, the above-mentioned similarity detection of multiple leak detection data corresponding to multiple detection objects to obtain the second similarity estimation result corresponding to each of the multiple leak detection data can include: performing similarity detection on the current leak detection data corresponding to the multiple detection objects to obtain the current similarity estimation result corresponding to the current leak detection data; and performing similarity detection on multiple historical leak detection data corresponding to each of the multiple detection objects to obtain the historical similarity estimation result corresponding to each detection object.

[0086] In a specific embodiment, the second similarity detection result can characterize whether there are any anomalies in the similarity detection dimension of the leakage detection data corresponding to each detection object. Specifically, the second similarity detection result can include historical similarity detection results and current similarity detection results. The current similarity detection result can characterize whether there are any anomalies in the current leakage detection data corresponding to each detection object in the similarity detection dimension, and the historical similarity detection result can characterize whether there are any anomalies in the similarity detection dimension of multiple historical leakage detection data corresponding to each detection object. Optionally, the second similarity estimation result can be a Jaccard similarity estimate. If the Jaccard similarity estimate exceeds a preset similarity threshold, the leakage detection data is suspected of being falsified. If the number and / or proportion of suspected falsified leakage detection data pairs exceed a preset aggregation threshold, a second similarity detection result characterizing the leakage detection data having anomaly detection in the similarity detection dimension can be obtained.

[0087] In a specific embodiment, the second similarity estimation result can be the current similarity estimation result, which can be the Jaccard similarity estimate between the current leakage detection data corresponding to multiple detection objects. The above-mentioned determination of the second similarity detection result corresponding to each of the multiple leakage detection data based on the second similarity estimation result can include: for the current leakage detection data corresponding to multiple detection objects, if the Jaccard similarity estimate exceeds a preset similarity threshold, it is determined that the current leakage detection data pair is suspected of being fraudulent; if the number and / or proportion of the current leakage detection data pairs suspected of being fraudulent exceeds a preset aggregation threshold, a current similarity detection result can be obtained that characterizes the current leakage detection data corresponding to the detection object as having abnormal detection in the similarity detection dimension.

[0088] In a specific embodiment, the second similarity estimation result can be a historical similarity estimation result, which can be a Jaccard similarity estimate between multiple historical leakage detection data corresponding to each detection object. The above-mentioned determination of the second similarity detection result corresponding to each of the multiple leakage detection data based on the second similarity estimation result can include: for multiple historical leakage detection data corresponding to each detection object, if the Jaccard similarity estimate exceeds a preset similarity threshold, it is determined that the historical leakage detection data pair is suspected of being falsified; if the number and / or proportion of historical leakage detection data pairs suspected of being falsified exceeds a preset aggregation threshold, a historical similarity detection result can be obtained that characterizes the multiple historical leakage detection data corresponding to the detection object as having abnormal detection in the similarity detection dimension.

[0089] As can be seen from the technical solutions provided in the embodiments of this specification above, this specification acquires first current leakage detection data corresponding to the target sealing point, first historical leakage detection data corresponding to the target sealing point, second current leakage detection data corresponding to adjacent sealing points adjacent to the target sealing point, a preset detection confidence interval, and a moving time threshold. The preset detection confidence interval represents a reasonable range of time detection intervals between the target sealing point and adjacent sealing points; the moving time threshold represents the shortest time required for adjacent sealing points to travel to the target sealing point for detection. Based on the detection time in the first current leakage detection data and the detection time in the second current leakage detection data, a first detection interval between the target sealing point and adjacent sealing points is determined. Based on the first detection interval and the preset detection confidence interval, time detection is performed on the first current leakage detection data to obtain a first time detection result of the first current leakage detection data. The first detection interval and the moving time threshold are compared to obtain a first spatial detection result of the first current leakage detection data. Similarity detection is performed on the first current leakage detection data and the first historical leakage detection data to obtain a first similarity detection result of the first current leakage detection data. Multi-factor nonlinear fusion processing is performed on the spatial detection result, the time detection result, and the first similarity detection result to obtain the operational detection result of the first current leakage detection data. It can integrate logical verification of three independent dimensions: time, space, and data similarity, and use a multi-factor nonlinear fusion model for comprehensive scoring. Each dimension complements and cross-verifies each other. Even if the fraudster evades the detection of a single dimension, the overall score can still effectively identify anomalies, significantly improving the detection rate and accuracy of fraudulent behavior.

[0090] Figure 3 This is a block diagram of an LDAR-based authentication device for spatiotemporal fingerprinting, illustrating an exemplary embodiment. (Refer to...) Figure 3 The device includes: The first acquisition module 310 is used to acquire first current leakage detection data corresponding to the target sealing point, first historical leakage detection data corresponding to the target sealing point, second current leakage detection data corresponding to adjacent sealing points of the target sealing point, a preset detection confidence interval, and a movement time threshold; the adjacent sealing points are sealing points adjacent to the target sealing point; the preset detection confidence interval represents a reasonable range of time detection intervals between the target sealing point and adjacent sealing points; the movement time threshold represents the shortest time required for the adjacent sealing point to travel to the target sealing point for detection; The first detection interval determination module 330 is used to determine the first detection interval between the target sealing point and the adjacent sealing point based on the detection time in the first current leakage detection data and the detection time in the second current leakage detection data; The first-time detection module 350 is used to perform time detection on the first current leakage detection data based on the first detection interval and the preset detection confidence interval, and obtain the first-time detection result of the first current leakage detection data; The second time detection module 370 is used to perform time detection on the detection time in the first current leakage detection data based on the first historical detection time set in the first historical leakage detection data, and obtain a second time detection result; the first historical detection time set includes multiple historical detection times that characterize the detection time interval of the target sealing point as having historical periodicity. The first spatial detection module 390 is used to compare the first detection interval with the movement time threshold to obtain the first spatial detection result of the first current leakage detection data. The second spatial detection module 3110 is used to perform spatial detection on the detection positions in the first current leakage detection data based on the target historical detection position set in the first historical leakage detection data, and obtain a second spatial detection result; the target historical detection position set includes multiple historical detection positions that characterize the spatial position of the target sealing point as having historical consistency; The first similarity detection module 3130 is used to perform similarity detection on the first current leakage detection data and the first historical leakage detection data to obtain the first similarity detection result of the first current leakage detection data. The fusion processing module 3150 is used to perform multi-factor nonlinear fusion processing on the first spatial detection result, the second spatial detection result, the first time detection result, the second time detection result, and the first similarity detection result to obtain the operation detection result of the first current leakage detection data.

[0091] In an optional embodiment, the first historical leakage detection data includes multiple historical leakage detection data, and the first similarity detection module 3130 includes: The classification processing unit is used to classify the first current leak detection data and multiple historical leak detection data to obtain multiple current leak detection datasets; The target leak detection dataset determination unit is used to determine the target leak detection dataset in which the first current leak detection data is located; multiple current leak detection datasets include the target leak detection dataset. The similarity estimation unit is used to perform similarity estimation on any two leakage detection data in the target leakage detection dataset to obtain the first similarity estimation result between the first current leakage detection data and the leakage detection data in the target leakage detection dataset other than the first current leakage detection data; The first similarity detection result acquisition unit is used to obtain the first similarity detection result based on the first similarity estimation result.

[0092] In an optional embodiment, the above-described apparatus further includes: The second acquisition module is used to acquire multiple historical detection locations corresponding to the target sealing point; The first position distance determination module is used to determine the first position distance between any two historical detection positions among a plurality of historical detection positions; The third acquisition module is used to obtain a set of historical detection locations of the target based on multiple historical detection locations when the distance to the first location is less than a preset distance threshold.

[0093] In an optional embodiment, the second space detection module 3110 includes: The second location distance determination module is used to determine the second location distance between the detection location in the first current leakage detection data and multiple historical detection locations in the target historical detection location set; The second spatial detection result acquisition module is used to obtain the second spatial detection result based on the second position distance and the preset distance threshold.

[0094] In an optional embodiment, the above-described apparatus further includes: The fourth acquisition module is used to acquire multiple historical detection times corresponding to the target sealing point; The detection time interval determination module is used to determine the detection time interval between two adjacent historical detection times among multiple historical detection times; The fifth acquisition module is used to obtain a first historical detection time set based on multiple historical detection times when the detection time interval is a preset detection time interval.

[0095] In an optional embodiment, the second time detection module 370 described above includes: The second detection interval determination module is used to determine the second detection interval between the detection time in the first current leakage detection data and multiple historical detection times in the first historical detection time set; The detection interval comparison module is used to compare the second detection interval with the preset detection time interval to obtain the second time detection result.

[0096] In an optional embodiment, the above-described apparatus further includes: The sixth acquisition module is used to acquire the historical detection interval features between the target sealing point and adjacent sealing points; The confidence interval determination module is used to determine a preset detection confidence interval based on historical detection interval characteristics.

[0097] In an optional embodiment, the sixth acquisition module includes: The first acquisition unit is used to acquire the second historical leakage detection data corresponding to adjacent sealing points; The second acquisition unit is used to obtain multiple historical detection intervals between the target sealing point and adjacent sealing points based on the first historical detection time set in the first historical leakage detection data and the second historical detection time set in the second historical leakage detection data. The third acquisition unit is used to fit multiple historical detection intervals to obtain historical detection interval features.

[0098] In an optional embodiment, the above-described apparatus further includes: The seventh acquisition module is used to acquire leakage detection data corresponding to each of the multiple detection objects; The second similarity detection module is used to perform similarity detection on multiple leakage detection data corresponding to multiple detection objects, and obtain the second similarity estimation results corresponding to each of the multiple leakage detection data. The second similarity detection result acquisition module is used to determine the second similarity detection result corresponding to each of the multiple leakage detection data based on the second similarity estimation result.

[0099] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0100] Figure 4 This is a block diagram illustrating a system for verifying the authenticity of LDAR detection operations based on spatiotemporal fingerprinting, according to an exemplary embodiment. The system can be a terminal, and its internal structure diagram can be as follows: Figure 4As shown, the system includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for verifying the authenticity of LDAR detection operations based on spatiotemporal fingerprinting. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the system casing, or an external keyboard, touchpad, or mouse. Figure 5 This is a block diagram illustrating a system for verifying the authenticity of LDAR detection operations based on spatiotemporal fingerprinting, according to an exemplary embodiment. The system can be a server, and its internal structure diagram can be as follows: Figure 5 As shown, the system includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for verifying the authenticity of LDAR detection jobs based on spatiotemporal fingerprinting. Those skilled in the art will understand that Figure 4 or Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present disclosure and does not constitute a limitation on the system to which the present disclosure is applied. A specific system may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements. In an exemplary embodiment, a system is also provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the spatiotemporal fingerprint-based LDAR detection job authenticity verification method as described in the embodiments of this disclosure.

[0101] In an exemplary embodiment, a computer-readable storage medium is also provided, which, when the instructions in the storage medium are executed by a system processor, enables the system to perform the spatiotemporal fingerprint-based LDAR detection job authenticity verification method in the embodiments of this disclosure.

[0102] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0103] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method for verifying the authenticity of LDAR detection operations based on spatiotemporal fingerprinting, characterized in that, include: The system acquires the first current leakage detection data corresponding to the target sealing point, the first historical leakage detection data corresponding to the target sealing point, the second current leakage detection data corresponding to the adjacent sealing points of the target sealing point, a preset detection confidence interval, and a moving time threshold; the adjacent sealing points are the sealing points adjacent to the target sealing point; the preset detection confidence interval represents a reasonable range of time detection intervals between the target sealing point and the adjacent sealing points. The movement time threshold represents the shortest time required for the adjacent sealing point to travel to the target sealing point for detection. Based on the detection time in the first current leak detection data and the detection time in the second current leak detection data, a first detection interval is determined between the target sealing point and adjacent sealing points; Based on the first detection interval and the preset detection confidence interval, time detection is performed on the first current leakage detection data to obtain the first time detection result; Based on the first historical detection time set in the first historical leakage detection data, time detection is performed on the detection time in the first current leakage detection data to obtain the second time detection result; The first historical detection time set includes multiple historical detection times that characterize the detection time interval of the target sealing point as having historical periodicity; The first detection interval is compared with the movement time threshold to obtain the first spatial detection result; Based on the target historical detection location set in the first historical leakage detection data, spatial detection is performed on the detection locations in the first current leakage detection data to obtain a second spatial detection result; the target historical detection location set includes multiple historical detection locations that characterize the spatial location of the target sealing point and have historical consistency; A similarity detection is performed on the first current leak detection data and the first historical leak detection data to obtain a first similarity detection result; The first spatial detection result, the second spatial detection result, the first time detection result, the second time detection result, and the first similarity detection result are subjected to multi-factor nonlinear fusion processing to obtain the operational detection result of the first current leakage detection data.

2. The method for verifying the authenticity of LDAR detection operations based on spatiotemporal fingerprinting according to claim 1, characterized in that, The first historical leak detection data includes multiple historical leak detection data. The step of performing similarity detection on the first current leak detection data and the first historical leak detection data to obtain a first similarity detection result includes: The first current leak detection data and the multiple historical leak detection data are classified and processed to obtain multiple current leak detection datasets; Determine the target leak detection dataset where the first current leak detection data is located; the plurality of current leak detection datasets include the target leak detection dataset; A similarity estimate is performed on any two leakage detection data in the target leakage detection dataset to obtain a first similarity estimate result between the first current leakage detection data and the leakage detection data in the target leakage detection dataset excluding the first current leakage detection data; Based on the first similarity estimation result, the first similarity detection result is obtained.

3. The method for verifying the authenticity of LDAR detection operations based on spatiotemporal fingerprinting according to claim 1, characterized in that, The method further includes: Obtain multiple historical detection locations corresponding to the target sealing point; Determine the first position distance between any two historical detection positions among the plurality of historical detection positions; If the distance to the first location is less than a preset distance threshold, the target historical detection location set is obtained based on the multiple historical detection locations.

4. The method for verifying the authenticity of LDAR detection operations based on spatiotemporal fingerprinting according to claim 3, characterized in that, The step of performing spatial detection on the detection locations in the first current leak detection data based on the target historical detection location set in the first historical leak detection data to obtain the second spatial detection result includes: Determine the second location distance between the detection location in the first current leakage detection data and multiple historical detection locations in the target historical detection location set; The second spatial detection result is obtained based on the second location distance and the preset distance threshold.

5. The method for verifying the authenticity of LDAR detection operations based on spatiotemporal fingerprinting according to claim 1, characterized in that, The method further includes: Obtain multiple historical detection times corresponding to the target sealing point; Determine the detection time interval between two adjacent historical detection times among the plurality of historical detection times; When the detection time interval is a preset detection time interval, the first set of historical detection times is obtained based on the multiple historical detection times.

6. The method for verifying the authenticity of LDAR detection operations based on spatiotemporal fingerprinting according to claim 5, characterized in that, The step of performing time detection on the detection time in the first current leakage detection data based on the first historical detection time set in the first historical leakage detection data to obtain the second time detection result includes: Determine a second detection interval between the detection time in the first current leak detection data and multiple historical detection times in the first historical detection time set; The second detection interval is compared with the preset detection time interval to obtain the second time detection result.

7. The method for verifying the authenticity of LDAR detection operations based on spatiotemporal fingerprinting according to any one of claims 1-6, characterized in that, The method further includes: Obtain the historical detection interval characteristics between the target sealing point and adjacent sealing points; Based on the historical detection interval characteristics, the preset detection confidence interval is determined.

8. The method for verifying the authenticity of LDAR detection operations based on spatiotemporal fingerprinting according to any one of claims 1-6, characterized in that, The acquisition of historical detection interval features between the target sealing point and adjacent sealing points includes: Obtain the second historical leakage detection data corresponding to the adjacent sealing points; Based on the first historical detection time set in the first historical leakage detection data and the second historical detection time set in the second historical leakage detection data, multiple historical detection intervals between the target sealing point and adjacent sealing points are obtained. The historical detection intervals are fitted to obtain the historical detection interval features.

9. The method for verifying the authenticity of LDAR detection operations based on spatiotemporal fingerprinting according to any one of claims 1-6, characterized in that, The method further includes: Acquire leakage detection data for each of the multiple detection objects; Perform similarity detection on multiple leakage detection data corresponding to the multiple detection objects to obtain the second similarity estimation result corresponding to each of the multiple leakage detection data; Based on the second similarity estimation result, the second similarity detection result corresponding to each of the multiple leakage detection data is determined.

10. A system for verifying the authenticity of LDAR detection operations based on spatiotemporal fingerprinting, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to execute instructions to implement the method for verifying the authenticity of LDAR detection jobs based on spatiotemporal fingerprints as described in any one of claims 1-9.

Images