Multi-device cooperation operation monitoring system based on operation data collection and analysis

Abstract

The application discloses a multi-device cooperation operation supervision system based on operation data collection and analysis, relates to the technical field of monitoring device operation supervision, and solves the technical problem that in the prior art, when each device independently operates, an effective correlation mechanism is lacked, and it is difficult to form a collaborative supervision network, specifically, a dynamic trust chain construction unit realizes multi-device collaborative supervision by precise device correlation analysis and differential trust chain construction, and cross-region monitoring capability is improved; a benchmark alignment control unit guarantees the space-time consistency and reliability of monitoring data by scientific space-time deviation judgment and calibration; a cross-validation unit improves the accuracy of device fault detection and reduces maintenance cost by multi-source data cross-analysis; overall, the system effectively solves the core technical problems of insufficient collaboration, space-time deviation, fault misjudgment and the like in current park security multi-device supervision, and significantly improves the comprehensiveness, accuracy and efficiency of park security monitoring.

Description

Technical Field

[0001] This invention relates to the field of monitoring equipment operation and supervision technology, specifically a multi-device operation and supervision system based on operation data acquisition and analysis. Background Technology

[0002] The current park security system is developing towards multi-device and full-coverage, but there are still many bottlenecks in the coordinated operation and supervision of multiple devices;

[0003] In existing technologies, there are various types of monitoring and sensing equipment in the park. When each device operates independently, there is a lack of effective correlation mechanism, making it difficult to form a collaborative monitoring network. This results in low efficiency in cross-regional tracking of moving objects, especially with significant shortcomings in the connection of monitoring in non-adjacent areas.

[0004] Meanwhile, the clock references and spatial coordinates of devices in different areas are not consistent, which can easily lead to spatiotemporal reference deviations due to factors such as network fluctuations and deviations in device task execution time, resulting in asynchronous data recording and affecting the reliability of monitoring data.

[0005] Furthermore, equipment fault detection often relies on self-check data from a single device, lacking cross-validation from multiple data sources, which can easily lead to misjudgments and increase the blind spots and costs of equipment maintenance.

[0006] To address the aforementioned technical shortcomings, a solution is proposed. Summary of the Invention

[0007] The purpose of this invention is to solve the problems mentioned above by proposing a multi-device cooperative operation monitoring system based on operational data acquisition and analysis.

[0008] The objective of this invention can be achieved through the following technical solutions:

[0009] A multi-device collaborative operation monitoring system based on operational data acquisition and analysis, including a collaborative operation center, wherein the communication connections of the collaborative operation center include:

[0010] The dynamic trust chain construction unit constructs dynamic trust chains for various types of equipment required by the park security system, and collects and analyzes dynamic trust chain operation data to complete security protection measures for corresponding areas within the park.

[0011] The baseline alignment control unit performs baseline alignment control on the trust chain;

[0012] The cross-validation unit performs cross-validation on the monitoring equipment based on its own operational status assessment.

[0013] Furthermore, the process of building a dynamic trust chain unit is as follows:

[0014] The locations of monitoring devices in each area of ​​the park are marked and sorted according to the area order, and then correlation analysis is performed based on the sorting order;

[0015] Based on the monitoring devices in each sorting order, the corresponding coverage area is determined, and common features of the coverage area are identified in combination with the operating cycle of the monitoring devices. Common features are represented by overlapping coverage areas, the presence of the same object at the border of adjacent areas, and the presence of the same moving object in non-adjacent areas. If the corresponding coverage areas have common features, the corresponding monitoring device is marked as an associated device; otherwise, if the corresponding coverage areas do not have common features, the corresponding monitoring device is marked as a non-associated device.

[0016] Furthermore, a dynamic trust chain is constructed for associated devices; based on whether the associated devices are located in adjacent areas, a border trust chain and a connection trust chain are constructed.

[0017] The data types collected by associated devices in adjacent areas are determined, and a collection data set is constructed. A trust chain is constructed based on the region where the data of the associated devices in adjacent areas are located, and error weights are set according to the associated devices with different usage cycles.

[0018] Taking any data as an example, a trust chain identification and analysis is performed. If any associated device experiences data fluctuation, the data fluctuation of adjacent associated devices is used as a comparison object. If the data fluctuation characteristics of adjacent associated devices are consistent, the current associated device is marked as a false alarm point.

[0019] Based on changes in usage scenarios and increases in the corresponding device operating cycles, the number and frequency of each associated device in the trust chain of adjacent areas in each stage are recorded as false alarm points, and the trend analysis of associated devices within the stage is carried out based on the accumulation progress of the number of times and the increase progress of the frequency.

[0020] If the rate at which the number of associated devices accumulates exceeds the set acceleration threshold, or the rate at which the frequency increases exceeds the set frequency increase threshold, then the current associated device is set to low-weight trust. Conversely, if the rate at which the number of associated devices accumulates does not exceed the set acceleration threshold, and the rate at which the frequency increases does not exceed the set frequency increase threshold, then the current associated device is set to high-weight trust.

[0021] Trust chains are constructed based on the trust weights of associated devices. When the values ​​fluctuate, the trust chain of the associated device with the higher trust weight is used as the dynamic trust chain. Meanwhile, the associated devices with the lower trust weight continue to collect data and are aggregated in the order of collection. When data collection fluctuates, the dynamic trust chain is used as the decision criterion. The dynamic trust chain of the current adjacent area is set as the border trust chain, and the corresponding location and associated device number are sent to the coordination operation center.

[0022] Furthermore, the mobile subject identification analysis is performed on the associated devices in non-adjacent areas. Any type of mobile subject is taken as the mobile object in the current stage, and it moves in the corresponding non-adjacent areas in the corresponding order. The first position of the movement is taken as the starting point of the movement, and the associated device in the corresponding area is set as the starting point of the trust chain. Based on the irregularity of the corresponding position in the non-adjacent areas, the mobile object moves in any direction. The mobile object is identified by combining the collection cycle or collection angle of the associated device in the non-adjacent area.

[0023] If the time when a moving object enters the area coincides with the time when the associated device in the corresponding area is identified, it is inferred that the acquisition cycle or acquisition angle of the associated device in the current non-adjacent area is adapted to the corresponding trust chain point, and the current area is marked as the end point of the trust chain. The set speed range is adjusted according to the speed of the moving object, and the deviation of the identification time corresponding to the end point of the trust chain is used to determine whether the current area is marked as the end point of the trust chain corresponding to the starting point of the trust chain. If the time deviation is within the set deviation range, the trust chain is established. That is, the end point of the trust chain is determined based on any position of the current non-adjacent area as the starting point of the trust chain, the trust chain is constructed, and the trust chain is connected end to end. At the same time, different trust chains are determined for different moving objects with different movement speeds in order to complete the monitoring of the current area.

[0024] The trust chains between non-adjacent areas are marked as connecting trust chains, and the connecting trust chains cover multiple trust chain start points and trust chain end points, which are then sent to the coordination operation center.

[0025] Furthermore, if a moving object appears within the park, in conjunction with the monitoring of the adjacent trust chain area, the trust chain is contacted to immediately identify the moving object based on the trust chain of the corresponding area. This facilitates the rapid identification of the moving object's location and overcomes the limitations of continuous monitoring of adjacent areas. At the same time, when the trust chain confirms the identification of the moving object, the data collected by the monitoring equipment in the non-endpoint area is quickly uploaded to the coordination operation center. Non-endpoints refer to the non-trust chain start point and non-trust chain end point.

[0026] Furthermore, the process of the reference alignment control unit is as follows:

[0027] Joint analysis is performed on the border trust chain and the connection trust chain; the departure and entry time deviation values ​​of the same mobile subject in adjacent areas of the border trust chain are obtained, that is, the time when the mobile subject leaves the current area and enters the adjacent area.

[0028] When the same moving entity appears in a non-adjacent area in the trust chain, the distance between the non-adjacent areas and the duration of the interval are collected, and the monitoring moving speed is calculated. The moving speed at each moment is obtained based on the cumulative moving distance of the moving entity in the non-adjacent area and the moving time. The range of moving speed is obtained by increasing the moving time. The deviation between the monitored moving speed and the boundary value of the moving speed range is obtained.

[0029] Furthermore, if the deviation value of the departure and entry recording time at the border boundary exceeds the time deviation threshold, or the deviation between the monitored moving speed and the moving speed range boundary exceeds the speed deviation threshold, it is inferred that there is a spatiotemporal reference deviation in various types of trust chains within the monitoring area, that is, there is a recording deviation in time and space. The main reason is the network fluctuation of the equipment in each area or the deviation of the task execution time of the monitoring equipment; a spatiotemporal reference adjustment signal is generated and sent to the coordination operation center.

[0030] If the deviation value of the departure and entry time recorded at the boundary does not exceed the time deviation threshold, and the deviation between the monitored moving speed and the boundary of the moving speed range does not exceed the speed deviation threshold, it is inferred that there is no spatiotemporal reference deviation in the trust chains of each type within the monitoring area. A continuous monitoring signal is generated and sent to the operation coordination center. After receiving the signal, the operation coordination center will monitor and coordinate the various types of equipment according to the original coordination logic.

[0031] Furthermore, the process of cross-validation is as follows:

[0032] During the operation of the monitoring equipment, the operating parameters of the monitoring equipment are uploaded in real time and divided into self-checking data and observable data according to the type of operating parameters; self-checking data includes observable data; threshold comparison is performed on the uploaded operating parameters, and if the operating parameters exceed the set threshold, they are marked as abnormal data; otherwise, they are marked as normal data.

[0033] The self-check data in the operating parameters are compared one by one and divided into normal data set and abnormal data set, and a timestamp is attached; in the normal data set, the observable data in the self-check data is obtained. If the observable data is abnormal, the current time is marked as the observation contradiction time; in the abnormal data set, the observable data in the self-check data is obtained. If the observable data is normal, the current time is marked as the self-check contradiction time.

[0034] Obtain the historical data acquisition deviation frequency of the observable data acquisition device at the time of the observation contradiction, and at the same time obtain the historical data fluctuation trend of the self-checking data upload device at the time of the self-check contradiction.

[0035] Furthermore, if the historical data acquisition deviation frequency of the corresponding observable data acquisition device at the time of the observation discrepancy exceeds the acquisition deviation frequency threshold, it is inferred that the data of the current observable data acquisition device is inaccurate, and the observable data acquisition device is subjected to equipment maintenance; if the historical data acquisition deviation frequency of the corresponding observable data acquisition device at the time of the observation discrepancy does not exceed the acquisition deviation frequency threshold, it is inferred that the data of the current observable data acquisition device is accurate, and the self-checking data upload device is subjected to equipment maintenance.

[0036] Furthermore, if the historical data fluctuation trend of the self-inspection data upload device at the time of the self-inspection contradiction is consistent with the current abnormal data fluctuation trend, it is inferred that the self-inspection data upload device has an operational risk, and the device should be maintained; if the historical data fluctuation trend of the self-inspection data upload device at the time of the self-inspection contradiction is inconsistent with the current abnormal data fluctuation trend, it is inferred that the self-inspection data upload device does not have an operational risk, and the device for collecting observable data should be maintained.

[0037] Based on the cross-validation results, the operation and maintenance of the corresponding monitoring equipment will be carried out in coordination with the operation center.

[0038] Compared with the prior art, the beneficial effects of the present invention are:

[0039] 1. When building dynamic trust chains for related devices, border trust chains and connection trust chains are built according to whether the regions are adjacent or not, realizing differentiated collaborative management of related devices in different regions;

[0040] For devices in adjacent areas, the data types are determined and a dataset is constructed. Error weights are set for each area, and false alarm points are marked by comparing the fluctuation characteristics (span, frequency) of any data fluctuation with those of adjacent devices. This can accurately identify false alarms of individual devices and reduce the interference of false alarms on monitoring decisions. Furthermore, based on changes in usage scenarios and device operating cycles, the number and frequency of false alarms are recorded and trend analysis is performed. High and low weight trust levels are set, and the trust chain is dynamically adjusted to use data from high-weight devices as the decision standard, while retaining the aggregated data from low-weight devices. This ensures the accuracy of decisions without wasting data resources.

[0041] For devices in non-adjacent areas, the system identifies and analyzes moving entities, using the starting point of the movement as the starting point of the trust chain. It then determines the endpoint of the trust chain by combining the collection cycle, angle, and movement speed deviation, thus constructing a connecting trust chain. This overcomes the limitations of continuous monitoring in adjacent areas and enables rapid identification and location tracking of moving objects in non-adjacent areas. When a moving object appears in the park, it can quickly locate the object by linking the adjacent trust chain, improving the comprehensiveness and response speed of the entire park's monitoring.

[0042] 2. By jointly analyzing the border and the trust chain, the deviation values ​​of the entry and exit times of the border boundary and the deviation of the movement speed and speed range boundary of the non-adjacent area are obtained. This allows for a scientific determination of whether there is a deviation in the spatiotemporal reference. When the deviation exceeds the threshold, the original timestamp, location information, and business data of the equipment are collected. The timestamp is calibrated by introducing a network latency estimation algorithm based on the intranet time server. A unified high-precision map of the park is established, and the observation data is converted to a unified coordinate system through feature point matching. This effectively eliminates the spatiotemporal recording deviation caused by network fluctuations and equipment task execution time deviations, ensuring the spatiotemporal consistency of the monitoring data. If the deviation does not exceed the threshold, the original coordination logic is maintained to ensure the stability and efficiency of the system operation.

[0043] 3. Based on the equipment's own operational status assessment, cross-validation is performed. Operating parameters (heat dissipation temperature, stuttering frequency, rotation limit angle) are divided into self-check data and observable data. By comparing thresholds, normal and abnormal data sets are marked, achieving a preliminary assessment of the equipment's operational status. Further, the moments of observational discrepancies (observable data in the normal data set is abnormal) and self-check discrepancies (observable data in the abnormal data set is normal) are obtained. Combined with the analysis of the historical data acquisition deviation frequency and historical data fluctuation trend of the corresponding equipment, the responsible party for the fault can be accurately determined: when there is an observational discrepancy, the maintenance needs of observable or self-checked equipment are determined based on the historical deviation frequency; when there is a self-check discrepancy, the risk of self-checked equipment is judged by comparing historical fluctuation trends. This multi-source data cross-validation method significantly improves the accuracy of fault detection, avoids misjudgment based on single data, reduces ineffective maintenance costs, and improves the targeting of equipment maintenance. Attached Figure Description

[0044] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0045] Figure 1 This is a system principle block diagram of the present invention;

[0046] Figure 2 This is a flowchart of the method for constructing a dynamic trust chain in this invention;

[0047] Figure 3 This is a flowchart of the reference alignment control unit method in this invention. Detailed Implementation

[0048] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0049] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0050] The security system of a modern industrial park (including factories, R&D bases, logistics parks, etc.) typically consists of multiple subsystems such as perimeter intrusion detection, video surveillance, access control, patrol, fire protection, and lighting; these devices need to work together.

[0051] Please see Figure 1 As shown, the multi-device cooperative operation monitoring system based on operation data collection and analysis includes a cooperative operation center, wherein the cooperative operation center is connected to a dynamic trust chain building unit, a benchmark alignment control unit, and a cross-validation unit.

[0052] The operation center generates a dynamic trust chain construction signal and sends it to the dynamic trust chain construction unit.

[0053] After receiving the dynamic trust chain construction signal, the dynamic trust chain construction unit constructs dynamic trust chains for various types of equipment required by the park security system, and collects and analyzes dynamic trust chain operation data to complete the security protection measures for the corresponding areas within the park.

[0054] Please see Figure 2 As shown, the location of the monitoring equipment in each area of ​​the park is marked and sorted according to the area order, and then the correlation analysis is performed according to the sorting order.

[0055] Based on the monitoring devices in each sorting order, the corresponding coverage areas are determined. Then, combined with the operating cycle of the monitoring devices, common features of the coverage areas are identified. Common features include overlapping coverage areas, the presence of the same object at the boundary of adjacent areas, and the presence of the same moving object in non-adjacent areas. If corresponding coverage areas share common features, the corresponding monitoring device is marked as an associated device; conversely, if corresponding coverage areas do not share common features, the corresponding monitoring device is marked as an unassociated device. By marking the locations of monitoring devices in each area of ​​the park and sorting them by area order to conduct correlation analysis, the system can clearly grasp the spatial distribution logic of each device, laying the foundation for subsequent identification of associated devices. This avoids biases in correlation analysis caused by chaotic device location information and improves the orderliness and accuracy of correlation judgment.

[0056] Build dynamic trust chains for associated devices; build border trust chains and connection trust chains based on whether the associated devices are located in adjacent areas;

[0057] The data types collected by the associated devices in adjacent areas are determined, and a collection of data such as temperature, time, and video is constructed. A trust chain is constructed based on the region where the data of the associated devices in adjacent areas are located, and error weights are set according to the associated devices with different usage cycles.

[0058] Taking any data as an example, a trust chain identification and analysis is performed. If any associated device experiences data fluctuation, the data fluctuation of adjacent associated devices is used as a comparison object. If the data fluctuation characteristics of adjacent associated devices are consistent, the current associated device is marked as a false alarm point. It should be explained that the fluctuation characteristics refer to the data fluctuation span and the data fluctuation frequency. If the data fluctuation characteristics of adjacent associated devices are inconsistent, the historical adjacent first-float associated device of the current associated device is marked as a false alarm point.

[0059] Based on changes in usage scenarios and the increase in the corresponding device operating cycles, the number and frequency of each associated device in the trust chain of adjacent areas in each stage are recorded as a false alarm point. The trend analysis of associated devices within a stage is performed based on the accumulation rate of the number of false alarms and the increase rate of the frequency. If the accumulation rate of the number of false alarms of associated devices in the current stage exceeds the set acceleration threshold, or the increase rate of the frequency exceeds the set frequency increase rate threshold, then the current associated device is set to a low-weight trust level. Conversely, if the accumulation rate of the number of false alarms of associated devices in the current stage does not exceed the set accumulation rate threshold, and the increase rate of the frequency does not exceed the set frequency increase rate threshold, then the current associated device is set to a high-weight trust level.

[0060] Trust chains are constructed based on the trust weights of associated devices. When the values ​​fluctuate, the trust chain of the associated device with the higher trust weight is used as the dynamic trust chain. Meanwhile, the associated devices with the lower trust weight continue to collect data and are aggregated in the order of collection. When data collection fluctuates, the dynamic trust chain is used as the decision criterion. The dynamic trust chain of the current adjacent area is set as the border trust chain, and the corresponding location and associated device number are sent to the coordination and operation center.

[0061] Moving entity identification analysis is performed on associated devices in non-adjacent areas. Any type of moving entity is taken as the moving object in the current stage, moving within the corresponding sequence of non-adjacent areas. The first position of movement is taken as the starting point, and the associated device in the corresponding area is set as the starting point of the trust chain. Due to the irregularity of the corresponding positions in non-adjacent areas, the moving object moves in any direction. Combining the acquisition cycle or acquisition angle of the associated device in the non-adjacent area, moving object identification is performed. If the time when the moving object enters the area coincides with the identification time of the associated device in the corresponding area, it is inferred that the acquisition cycle or acquisition angle of the associated device in the current non-adjacent area is compatible with the corresponding trust chain point, and the current area is marked as the end point of the trust chain. The speed range is adjusted according to the moving object's speed, and the deviation from the identification time corresponding to the end point of the trust chain determines whether the current area is marked as the end point of the trust chain corresponding to the starting point. If the time deviation is within the set deviation range, the trust chain is established. In other words, the trust chain end point is determined based on any position in the current non-adjacent area as the starting point, a trust chain is constructed, and the trust chains are connected end-to-end. Different trust chains are determined based on the movement speed of different moving objects to facilitate the monitoring of the current area.

[0062] The trust chains between non-adjacent areas are marked as connecting trust chains. These connecting trust chains encompass multiple trust chain start points and end points, and are sent to the coordination and operation center. If a moving object appears within the park, the connecting trust chains, in conjunction with the monitoring of adjacent trust chain areas, will immediately identify the moving object based on the corresponding trust chain. This facilitates rapid identification of the moving object's location and overcomes the limitations of continuous monitoring of adjacent areas. Simultaneously, when the connecting trust chain identifies a moving object, the data collected by the monitoring equipment in the non-endpoint area is rapidly uploaded to the coordination and operation center. Non-endpoints are defined as neither the start nor end point of a trust chain.

[0063] After receiving the trust chain, the operation center performs regional monitoring and generates a reference alignment control signal, which is then sent to the reference alignment control unit.

[0064] Please see Figure 3 As shown, after receiving the reference alignment control signal, the reference alignment control unit performs reference alignment control on the trust chain;

[0065] Joint analysis is performed on the border trust chain and the connection trust chain; the departure and entry time deviation values ​​of the same mobile subject in adjacent areas of the border trust chain are obtained, that is, the time when the mobile subject leaves the current area and enters the adjacent area.

[0066] When the same moving entity appears in a non-adjacent area in the trust chain, the distance between the non-adjacent areas and the duration of the interval are collected, and the monitored moving speed is calculated. The moving speed at each moment is obtained based on the cumulative moving distance of the moving entity in the non-adjacent area and the moving time. The range of moving speed is obtained by increasing the moving time. The deviation between the monitored moving speed and the boundary value of the moving speed range is obtained.

[0067] If the deviation value of the departure and entry recording time at the border exceeds the time deviation threshold, or the deviation of the monitored movement speed from the boundary of the movement speed range exceeds the speed deviation threshold, it is inferred that there is a spatiotemporal reference deviation in each type of trust chain within the monitored area, that is, there is a recording deviation in time and space. The main reason is the network fluctuation of the devices in each area or the deviation of the task execution time of the monitoring devices. A spatiotemporal reference adjustment signal is generated and sent to the coordination operation center. After receiving the spatiotemporal reference adjustment signal, the coordination operation center collects the original timestamps, location information (if any), and business data (such as video streams and card swipe records) of all monitoring devices according to each type of trust chain. The system does not use the device's own clock as the reference, but uses the internal network time server as the reference, and introduces a network latency estimation algorithm to mark each data packet with a "calibrated timestamp". For spatial data, a unified high-precision map of the park is established as the reference surface. Through feature point matching (such as aligning the corners of buildings in the camera image with the map coordinates) algorithm, all device observation data are converted to this unified coordinate system in real time.

[0068] If the departure and entry time deviation value at the border boundary does not exceed the time deviation threshold, and the deviation between the monitored moving speed and the moving speed range boundary does not exceed the speed deviation threshold, it is inferred that there is no spatiotemporal reference deviation in the trust chains of each type within the monitoring area, and a continuous monitoring signal is generated and sent to the operation coordination center. After receiving the signal, the operation coordination center will monitor and coordinate the various types of equipment according to the original coordination logic.

[0069] It coordinates with the operation center to control and monitor multiple types of equipment in the monitoring area, and generates cross-verification signals and sends them to the cross-verification unit;

[0070] After receiving the cross-validation signal, the cross-validation unit performs cross-validation on the monitoring equipment. It performs cross-validation based on its own operating status assessment to improve the accuracy of equipment fault detection.

[0071] During the operation of the monitoring equipment, the operating parameters of the monitoring equipment are uploaded in real time. Specifically, the operating parameters are represented as heat dissipation temperature, stuttering frequency, and rotation limit angle. The operating parameters are divided into self-checking data and observable data according to their type. Self-checking data includes observable data, which is the operating parameters obtained from the operating log of the monitoring equipment. Observable data is represented by data such as stuttering frequency and rotation limit angle in the operating parameters, which can be observed through adjacent monitoring equipment or the sensors equipped on the corresponding equipment.

[0072] The uploaded running parameters are compared with a threshold. If the running parameters exceed the set threshold, they are marked as abnormal data; otherwise, they are marked as normal data.

[0073] The self-check data in the operating parameters are compared one by one and divided into normal data set and abnormal data set, and a timestamp is attached; in the normal data set, the observable data in the self-check data is obtained. If the observable data is abnormal, the current time is marked as the observation contradiction time; in the abnormal data set, the observable data in the self-check data is obtained. If the observable data is normal, the current time is marked as the self-check contradiction time.

[0074] Obtain the historical data acquisition deviation frequency of the observable data acquisition device at the time of observation contradiction, and at the time of self-inspection contradiction, obtain the historical data fluctuation trend of the self-inspection data upload device.

[0075] If the historical data acquisition deviation frequency of the corresponding observable data acquisition device at the time of the observation contradiction exceeds the acquisition deviation frequency threshold, it is inferred that the data of the current observable data acquisition device is inaccurate, and the observable data acquisition device should be maintained.

[0076] If the historical data acquisition deviation frequency of the corresponding observable data acquisition device at the time of the observation contradiction does not exceed the acquisition deviation frequency threshold, it is inferred that the data of the current observable data acquisition device is accurate, and equipment maintenance is performed on the self-checking data upload device.

[0077] If the historical data fluctuation trend of the self-checking data upload device at the time of the self-checking contradiction is consistent with the current abnormal data fluctuation trend, it is inferred that there is an operational risk in the self-checking data upload device, and the self-checking data upload device should be maintained.

[0078] If the historical data fluctuation trend of the self-checking data upload device at the time of the self-check contradiction is inconsistent with the current abnormal data fluctuation trend, it is inferred that there is no operational risk to the self-checking data upload device, and equipment maintenance should be carried out on the observable data acquisition device.

[0079] Based on the cross-validation results, the operation and maintenance of the corresponding monitoring equipment will be carried out in coordination with the operation center.

[0080] Thresholds, preset values, preset ranges, etc. are set for result comparison and analysis to determine whether they are good or bad. The value of these thresholds is determined by a combination of large-scale model analysis of sample data and human experience. They can also be adjusted appropriately based on seasonal or common-sense influences.

[0081] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A multi-device collaborative operation monitoring system based on operational data acquisition and analysis, characterized in that: This includes the coordination and operation center, whose communication connections include: The dynamic trust chain construction unit constructs dynamic trust chains for various types of equipment required by the park security system, and collects and analyzes dynamic trust chain operation data to complete security protection measures for corresponding areas within the park. The baseline alignment control unit performs baseline alignment control on the trust chain; The cross-validation unit performs cross-validation on the monitoring equipment based on its own operational status assessment.

2. The multi-device cooperative operation monitoring system based on operational data acquisition and analysis according to claim 1, characterized in that, The process of building a dynamic trust chain unit is as follows: The locations of monitoring devices in each area of ​​the park are marked and sorted according to the area order, and then correlation analysis is performed based on the sorting order; Based on the monitoring devices in each sorting order, the corresponding coverage area is determined, and common features of the coverage area are identified in combination with the operating cycle of the monitoring devices. Common features are represented by overlapping coverage areas, the presence of the same object at the border of adjacent areas, and the presence of the same moving object in non-adjacent areas. If the corresponding coverage areas have common features, the corresponding monitoring device is marked as an associated device; otherwise, if the corresponding coverage areas do not have common features, the corresponding monitoring device is marked as a non-associated device.

3. The multi-device cooperative operation monitoring system based on operational data acquisition and analysis according to claim 2, characterized in that, Build a dynamic trust chain for associated devices; Based on whether the areas where the associated devices are located are adjacent, construct border trust chains and connection trust chains; The data types collected by associated devices in adjacent areas are determined, and a collection data set is constructed. A trust chain is constructed based on the region where the data of the associated devices in adjacent areas are located, and error weights are set according to the associated devices with different usage cycles. Taking any data as an example, a trust chain identification and analysis is performed. If any associated device experiences data fluctuation, the data fluctuation of adjacent associated devices is used as a comparison object. If the data fluctuation characteristics of adjacent associated devices are consistent, the current associated device is marked as a false alarm point. Based on changes in usage scenarios and increases in the corresponding device operating cycles, the number and frequency of each associated device in the trust chain of adjacent areas in each stage are recorded as false alarm points, and the trend analysis of associated devices within the stage is carried out based on the accumulation progress of the number of times and the increase progress of the frequency. If the rate at which the number of associated devices accumulates exceeds the set acceleration threshold, or the rate at which the frequency increases exceeds the set frequency increase threshold, then the current associated device is set to low-weight trust. Conversely, if the rate at which the number of associated devices accumulates does not exceed the set acceleration threshold, and the rate at which the frequency increases does not exceed the set frequency increase threshold, then the current associated device is set to high-weight trust. Trust chains are constructed based on the trust weights of associated devices. When the values ​​fluctuate, the trust chain of the associated device with the higher trust weight is used as the dynamic trust chain. Meanwhile, the associated devices with the lower trust weight continue to collect data and are aggregated in the order of collection. When data collection fluctuates, the dynamic trust chain is used as the decision criterion. The dynamic trust chain of the current adjacent area is set as the border trust chain, and the corresponding location and associated device number are sent to the coordination operation center.

4. The multi-device cooperative operation monitoring system based on operational data acquisition and analysis according to claim 3, characterized in that, Mobile entity identification analysis is performed on associated devices in non-adjacent areas. Any type of mobile entity is taken as the mobile object in the current stage. It moves in non-adjacent areas in the corresponding order and takes the first position of movement as the starting point of movement. The associated devices in the corresponding area are set as the starting point of the trust chain. Based on the irregularity of the corresponding positions in non-adjacent areas, the mobile object moves in any direction. The mobile object is identified by combining the collection cycle or collection angle of the associated devices in non-adjacent areas. If the time when the moving object enters the area is consistent with the time when the associated device in the corresponding area is identified, it is inferred that the collection cycle or collection angle of the associated device in the current non-adjacent area is adapted to the corresponding trust chain point, and the current area is marked as the end point of the trust chain. The speed range is adjusted according to the speed of the moving object, and the current area is marked as the end point of the trust chain corresponding to the identification time of the end point of the trust chain. If the time deviation is within the set deviation range, the trust chain is established. That is, the end point of the trust chain is determined based on any position of the current non-adjacent area as the start point of the trust chain, the trust chain is constructed, and the trust chain is connected end to end. At the same time, different trust chains are determined for the moving speed of different moving objects in order to complete the monitoring of the current area. The trust chains between non-adjacent areas are marked as connecting trust chains, and the connecting trust chains cover multiple trust chain start points and trust chain end points, which are then sent to the coordination operation center.

5. The multi-device cooperative operation monitoring system based on operational data acquisition and analysis according to claim 4, characterized in that, If a moving object appears within the park, in conjunction with the monitoring of the adjacent trust chain area, the trust chain is contacted to immediately identify the moving object based on the trust chain of the corresponding area. This facilitates the rapid identification of the moving object's location and overcomes the limitations of continuous monitoring of adjacent areas. At the same time, when the trust chain is contacted to confirm the identification of the moving object, the data collected by the monitoring equipment in the non-endpoint area is quickly uploaded to the coordination operation center. The non-endpoint refers to the non-trust chain start point and non-trust chain end point.

6. The multi-device cooperative operation monitoring system based on operational data acquisition and analysis according to claim 1, characterized in that, The process of the reference alignment control unit is as follows: Joint analysis is performed on the border trust chain and the connection trust chain; the departure and entry time deviation values ​​of the same mobile subject in adjacent areas of the border trust chain are obtained, that is, the time when the mobile subject leaves the current area and enters the adjacent area. When the same moving entity appears in a non-adjacent area in the trust chain, the distance between the non-adjacent areas and the duration of the interval are collected, and the monitoring moving speed is calculated. The moving speed at each moment is obtained based on the cumulative moving distance of the moving entity in the non-adjacent area and the moving time. The range of moving speed is obtained by increasing the moving time. The deviation between the monitored moving speed and the boundary value of the moving speed range is obtained.

7. The multi-device cooperative operation monitoring system based on operational data acquisition and analysis according to claim 6, characterized in that, If the deviation value of the departure and entry recording time at the border exceeds the time deviation threshold, or the deviation between the monitored movement speed and the boundary of the movement speed range exceeds the speed deviation threshold, it is inferred that there is a spatiotemporal reference deviation in each type of trust chain within the monitored area, that is, there is a recording deviation in time and space. The main reason is the network fluctuation of the equipment in each area or the deviation of the task execution time of the monitoring equipment; a spatiotemporal reference adjustment signal is generated and sent to the coordination operation center. If the deviation value of the departure and entry time recorded at the boundary does not exceed the time deviation threshold, and the deviation between the monitored moving speed and the boundary of the moving speed range does not exceed the speed deviation threshold, it is inferred that there is no spatiotemporal reference deviation in the trust chains of each type within the monitoring area. A continuous monitoring signal is generated and sent to the operation coordination center. After receiving the signal, the operation coordination center will monitor and coordinate the various types of equipment according to the original coordination logic.

8. The multi-device cooperative operation monitoring system based on operational data acquisition and analysis according to claim 1, characterized in that, The process of cross-validation unit is as follows: During the operation of the monitoring equipment, the operating parameters of the monitoring equipment are uploaded in real time and divided into self-checking data and observable data according to the type of operating parameters; self-checking data includes observable data; threshold comparison is performed on the uploaded operating parameters, and if the operating parameters exceed the set threshold, they are marked as abnormal data; otherwise, they are marked as normal data. The self-check data in the operating parameters are compared one by one and divided into normal data set and abnormal data set, and a timestamp is attached; in the normal data set, the observable data in the self-check data is obtained. If the observable data is abnormal, the current time is marked as the observation contradiction time; in the abnormal data set, the observable data in the self-check data is obtained. If the observable data is normal, the current time is marked as the self-check contradiction time. Obtain the historical data acquisition deviation frequency of the observable data acquisition device at the time of the observation contradiction, and at the same time obtain the historical data fluctuation trend of the self-checking data upload device at the time of the self-check contradiction.

9. The multi-device cooperative operation monitoring system based on operational data acquisition and analysis according to claim 8, characterized in that, If the historical data acquisition deviation frequency of the corresponding observable data acquisition device at the time of the observation contradiction exceeds the acquisition deviation frequency threshold, it is inferred that the data of the current observable data acquisition device is inaccurate, and the observable data acquisition device should be maintained. If the historical data acquisition deviation frequency of the corresponding observable data acquisition device at the time of the observation discrepancy does not exceed the acquisition deviation frequency threshold, it is inferred that the data of the current observable data acquisition device is accurate, and equipment maintenance is performed on the self-checking data upload device.

10. The multi-device cooperative operation monitoring system based on operational data acquisition and analysis according to claim 9, characterized in that, If the historical data fluctuation trend of the self-checking data upload device at the time of the self-checking contradiction is consistent with the current abnormal data fluctuation trend, it is inferred that there is an operational risk in the self-checking data upload device, and the self-checking data upload device should be maintained. If the historical data fluctuation trend of the self-checking data upload device at the time of the self-check contradiction is inconsistent with the current abnormal data fluctuation trend, it is inferred that there is no operational risk to the self-checking data upload device, and equipment maintenance should be carried out on the observable data acquisition device. Based on the cross-validation results, the operation and maintenance of the corresponding monitoring equipment will be carried out in coordination with the operation center.

Images