Infrared camera equipment operation management method based on intelligent scheduling

Abstract

The invention discloses an infrared camera equipment operation management method based on intelligent scheduling, and relates to the technical field of infrared camera equipment operation management. Obtaining a time offset relationship and a behavior difference relationship between the operation behavior data and the last state reporting data, and generating a state synchronization offset based on the time offset relationship and the behavior difference relationship, so as to determine a state reporting delay feature under the condition that the infrared camera equipment enters a standby transition state after the task is completed; the state reporting delay feature is mapped into a delay evaluation vector including delay amplitude, delay persistence and behavior stability, and a scheduling confidence score is calculated based on the delay evaluation vector. According to the method, the problem of scheduling misjudgment caused by state reporting delay of the infrared camera in the transition stage from task completion to standby is solved, and accurate identification and intelligent hierarchical scheduling of the real schedulable state of the equipment are realized.

Description

Technical Field

[0001] This invention relates to the field of infrared camera equipment operation management technology, and specifically to an infrared camera equipment operation management method based on intelligent scheduling. Background Technology

[0002] Intelligent scheduling-based infrared camera equipment operation management refers to an operation optimization method that utilizes artificial intelligence algorithms or rule engines to uniformly plan and dynamically control multiple infrared camera devices deployed in a specific environment. This management approach primarily aims to improve equipment operating efficiency, reduce energy consumption, and enhance the accuracy of data acquisition. It typically receives real-time data from infrared cameras or external sensors (such as temperature, humidity, light, and motion detection) through a central management platform. Based on preset scheduling strategies or machine learning models, it intelligently judges the current environmental state and monitoring needs, thereby dynamically adjusting the operating parameters of each camera, including shooting time, frequency, resolution, angle, and on / off status. Most existing intelligent scheduling technologies employ rule-priority-based task scheduling models, combined with time window control and event-driven response mechanisms to optimize the infrared camera workflow. Its specific operational stages include: a data acquisition layer (front-end perception and image acquisition), a decision-making scheduling layer (intelligent analysis and scheduling strategy generation), an equipment control layer (issuing control commands to terminal cameras), and an operational feedback layer (uploading acquisition results and transmitting operational status). These stages form a closed-loop management system, achieving refined, automated, and intelligent control of the infrared camera equipment.

[0003] The existing technology has the following shortcomings: In the process of managing the operation of infrared camera equipment based on intelligent scheduling, when an infrared camera completes its shooting task and enters the transition phase from running to standby mode, there is a certain reporting delay due to the reliance on firmware feedback for device status information. During this transition phase, the scheduling system receives the running status information corresponding to the previous task cycle, causing a discrepancy between the actual operating status of the device and the status recorded by the system. In this situation, existing intelligent scheduling-based infrared camera equipment operation management technologies cannot accurately determine whether an infrared camera is eligible to participate in the next round of intelligent scheduling based on the status reporting delay characteristics when the infrared camera enters the standby transition state after completing its task. This leads the scheduling system to mistakenly classify infrared cameras that have completed their tasks and are available as unschedulable in subsequent operation management processes, resulting in available equipment resources being skipped or left idle. This further leads to adverse effects such as concentrated operating loads on other infrared camera equipment, uneven energy consumption distribution, and reduced overall operation management coordination and scheduling efficiency.

[0004] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The purpose of this invention is to provide an intelligent scheduling-based method for the operation and management of infrared camera equipment, in order to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: an infrared camera equipment operation management method based on intelligent scheduling, specifically including the following steps: S1. Collect the operation behavior data of the infrared camera device before and after the shooting task ends, construct a task convergence feature set based on the operation behavior data, and use the task convergence feature set to determine whether the infrared camera device enters the standby transition state from the running state to the standby state after the task is completed. S2. After confirming that the infrared camera device has entered the standby transition state, obtain the time offset relationship and behavior difference relationship between the running behavior data and the most recent status reporting data, and generate a status synchronization offset based on the time offset relationship and behavior difference relationship to determine the status reporting delay characteristics when the infrared camera device enters the standby transition state after completing the task. S3. Map the status reporting delay features into a delay evaluation vector that includes delay magnitude, delay persistence and behavior stability, and calculate the scheduling confidence score based on the delay evaluation vector; S4. Based on the scheduling confidence score, the infrared camera equipment is divided into different scheduling levels, and the scheduling level is used to determine whether the infrared camera equipment is qualified to participate in the next round of intelligent scheduling. S5. After completing intelligent scheduling, collect subsequent operational behavior data of the infrared camera equipment, compare the deviation relationship between the scheduling confidence score and the actual operational behavior, and update the task convergence feature set and state synchronization offset for dynamic control in the subsequent intelligent scheduling process.

[0007] Preferably, S1 is as follows: Before and after the shooting mission ends, the operation behavior data of the infrared camera device is continuously collected. The operation behavior data includes changes in shooting command response time, changes in data interaction frequency per unit time, and energy consumption change trajectory. The operation behavior data forms a behavior data sequence in chronological order. Based on the behavioral data sequence, the operation behavior at the end stage of the shooting task is analyzed in a time series. The magnitude, direction and duration of the change in the operation behavior before and after the end of the shooting task are extracted. Based on the magnitude, direction and duration of the change, a task convergence feature set is constructed. The task convergence feature set is used to characterize the behavioral features of the shooting task transitioning from the execution state to the non-execution state. Each feature parameter in the task convergence feature set is compared with the preset judgment conditions. When the direction of change is consistent, the magnitude of change decreases continuously, and the duration of change reaches the preset time interval, it is determined that the infrared camera device enters the standby transition state from the running state to the standby state after the task is completed.

[0008] Preferably, S2 specifically includes the following steps: S201. After confirming that the infrared camera device has entered the standby transition state, obtain the behavior occurrence time information corresponding to the running behavior data, and obtain the status reporting time information corresponding to the most recent status reporting data. By performing time alignment and difference calculation on the behavior occurrence time information and status reporting time information, a time offset relationship between the running behavior data and the most recent status reporting data is formed. S202. Based on the behavioral features in the operational behavior data that reflect the completion status of the shooting task, compare them with the status indicators in the most recent status report data that reflect the operational status, extract the degree of difference between the behavioral features and the status indicators, and form a behavioral difference relationship between the operational behavior data and the most recent status report data. S203. Based on the time offset relationship and behavior difference relationship, perform combined calculations to generate a state synchronization offset, and determine the state reporting delay characteristics of the infrared camera device when it enters a standby transition state after completing the task based on the numerical distribution range of the state synchronization offset.

[0009] Preferably, S203 is as follows: The time offset relationship is processed into intervals, mapping the time offset value between the running behavior data and the most recent status report data to a preset time offset interval, and forming a corresponding time offset interval identifier. The behavioral differences are hierarchically processed, mapping the degree of difference between the behavioral features reflecting the task completion status in the operational behavior data and the status identifiers reflecting the operational status in the status reporting data to a preset difference level range, and forming corresponding difference level identifiers. The state synchronization offset is generated by combining the time offset interval identifier and the difference level identifier. Based on the state synchronization offset's location in the preset value distribution interval, the state reporting delay characteristics of the infrared camera device when it enters the standby transition state after completing the task are determined.

[0010] Preferably, S3 specifically includes the following steps: S301. The status reporting delay feature is deconstructed in multiple dimensions, and three types of indicators are extracted: delay amplitude, delay persistence and behavior stability. Among them, delay amplitude represents the maximum time span of the status synchronization offset, delay persistence represents the number of times the status asynchrony phenomenon is maintained in the continuous sampling period, and behavior stability represents the degree of fluctuation of the device operation behavior during the delay period. S302. Normalize the three indicators of delay amplitude, delay duration and behavior stability, and combine the parameters according to the preset fixed vector order to construct a delay evaluation vector containing delay amplitude, delay duration and behavior stability, which is used to uniformly express the strength level of the current state reporting delay feature. S303. Based on the components of each indicator in the delay evaluation vector, a weighted calculation is performed using preset weight coefficients to generate a scheduling confidence score. The scheduling confidence score is used to evaluate the credibility of the infrared camera device's participation in intelligent scheduling under different state reporting delay characteristics.

[0011] Preferably, S301 is as follows: Based on the changes in the state synchronization offset within a continuous sampling period, the maximum time span of the state synchronization offset is extracted to determine the delay magnitude index. The delay magnitude index is used to characterize the extreme range of the state reporting delay in the time dimension. Based on the number of times the state synchronization offset remains non-zero within a continuous sampling period, the number of times the state asynchrony phenomenon is maintained is counted to determine the delay persistence index. The delay persistence index is used to characterize the persistence feature of the state reporting delay in the time series. Based on the changes in operational behavior data during the period of state synchronization offset, the fluctuation of operational behavior parameters in adjacent sampling periods is analyzed to determine the behavior stability index. The behavior stability index is used to characterize the changes in equipment operational behavior during the state reporting delay period.

[0012] Preferably, S4 is as follows: Construct a scheduling level mapping table, set multiple scheduling level intervals, each scheduling level interval corresponds to a continuous range of scheduling confidence score values, and assign a unique scheduling level identifier to each scheduling level interval to distinguish the priority category of infrared camera devices in the scheduling process; The scheduling confidence score of the infrared camera equipment is matched with each scheduling level interval in the scheduling level mapping table. By comparing the numerical values ​​of the scheduling confidence scores, the scheduling level of the infrared camera equipment is determined, and a corresponding scheduling level identifier is assigned to it, thus forming a scheduling level classification result. Based on the scheduling level classification results, a scheduling level threshold is set for participating in the next round of intelligent scheduling. Infrared camera devices with a scheduling level higher than or equal to the scheduling level threshold are identified as qualified to participate in the next round of intelligent scheduling.

[0013] Preferably, S5 is as follows: After completing intelligent scheduling, the system continuously collects subsequent operational behavior data of the infrared camera device during the scheduling process. The subsequent operational behavior data includes scheduling task response time, task completion confirmation time, energy consumption change parameters and status reporting interval data, and forms a subsequent operational behavior data sequence. Based on the subsequent operational behavior data sequence, actual operational behavior features reflecting the scheduling execution quality are extracted. The actual operational behavior features are then matched and compared item by item with the scheduling confidence score calculated before intelligent scheduling to determine the deviation relationship between the scheduling confidence score and the actual operational behavior. Based on the deviation relationship results, the parameters of the behavioral change amplitude, direction and persistence characteristics in the task convergence feature set are corrected, and the time offset interval and difference level identifier of the state synchronization offset are updated at the same time to realize the dynamic control of the task convergence feature set and the state synchronization offset in the subsequent intelligent scheduling process.

[0014] The technical effects and advantages provided by the present invention in the above technical solution are as follows: 1. This invention comprehensively establishes a full-link state perception and evaluation mechanism for infrared camera equipment, from task completion to standby transition and then to scheduling eligibility determination, by constructing a key parameter system including a task convergence feature set, state synchronization offset, delay evaluation vector, and scheduling confidence score. This significantly improves the accuracy of equipment operating status judgment. Compared to existing technologies that cannot identify scheduling misjudgments caused by state reporting delays, this solution, through two-factor modeling of time offset and behavioral difference relationships, can identify the true state of the equipment after the shooting task ends. Furthermore, based on the state synchronization offset, a delay feature expression model is constructed, ensuring that the scheduling system has accurate perception capabilities of the equipment's available state, reducing the probability of resource idleness and scheduling imbalance.

[0015] 2. This invention introduces a scheduling confidence score and scheduling level mapping mechanism to achieve quantitative assessment and hierarchical control of equipment schedulability. Combined with real-time feedback of subsequent operational behavior and a model adaptive update mechanism, a dynamically learning and self-correcting scheduling decision-making system is constructed. By incorporating characteristics such as behavioral amplitude, direction of change, and persistence into task convergence modeling, and optimizing the computation path through algorithms such as normalization and weighted averages, this technical solution not only improves the flexibility and controllability of scheduling decisions but also enhances the system's fault tolerance and adaptability under conditions of inconsistent states and data lag. Therefore, in practical applications, it can significantly improve the intelligent scheduling efficiency, resource utilization, and operational stability of infrared camera equipment. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0017] Figure 1 This is a flowchart illustrating the operation management method for infrared camera equipment based on intelligent scheduling according to the present invention. Detailed Implementation

[0018] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that the description of this disclosure will be more complete and fully convey the concept of the exemplary embodiments to those skilled in the art.

[0019] This invention provides, for example Figure 1 The infrared camera equipment operation management method based on intelligent scheduling shown includes the following steps: S1. Collect the operation behavior data of the infrared camera device before and after the shooting task ends, construct a task convergence feature set based on the operation behavior data, and use the task convergence feature set to determine whether the infrared camera device enters the standby transition state from the running state to the standby state after the task is completed. In this embodiment, S1 specifically refers to: Before and after the shooting mission ends, the operation behavior data of the infrared camera device is continuously collected. The operation behavior data includes changes in shooting command response time, changes in data interaction frequency per unit time, and energy consumption change trajectory. The operation behavior data forms a behavior data sequence in chronological order. During the period from the imminent completion of a shooting task to its completion, continuous acquisition of operational behavior data from the infrared camera device can capture the entire process of the device transitioning from a task execution state to an idle state. The acquisition of operational behavior data is achieved through an internally embedded command execution recording interface, a data transmission logger, and a power consumption detection chip. Specifically, changes in shooting command response time can be determined by the control unit recording the time interval between issuing the command and the camera's execution feedback; changes in data interaction frequency per unit time can be identified by the communication module counting the number of data packets sent and received during that period; and energy consumption changes are tracked by the power management chip detecting instantaneous power consumption and generating energy consumption recording curves at continuous time points. Organizing this data chronologically forms a behavioral data sequence, allowing subsequent processing algorithms to determine the convergence trend of operational behavior on a unified time axis. The technical significance of this acquisition method lies in its ability to not only provide quantitative evidence of task execution boundaries but also to provide precise temporal behavioral data support for determining whether the device is entering a standby transition state, effectively avoiding scheduling misjudgments caused by information delays.

[0020] Infrared camera equipment operational behavior data refers to a set of key performance parameters that reflect the current or historical changes in the equipment's operational status. These parameters are typically presented as a continuous data set with time-series attributes. The change in shooting command response time refers to the time difference between the triggering of a task command and the completion of the device's response, revealing the device's response efficiency and load changes. The change in data interaction frequency per unit time reflects the device's activity level in network communication; higher interaction frequencies usually correspond to data uploads or task feedback, while a decrease in frequency may indicate that the task is nearing completion or is about to become idle. The energy consumption change trajectory is a power consumption curve depicted over time, which can be used to analyze whether task execution is nearing completion, as most shooting tasks exhibit a power consumption slowdown trend towards the end of execution. Behavioral data sequences refer to the three types of behavioral data organized into a continuous, ordered data set according to a unified timestamp, facilitating subsequent behavioral trend identification and status judgment through algorithmic models. Each technical feature possesses data collectability, temporal relevance, and behavioral representativeness, forming the foundational elements for constructing task completion judgment logic.

[0021] Based on the behavioral data sequence, the operation behavior at the end stage of the shooting task is analyzed in a time series. The magnitude, direction and duration of the change in the operation behavior before and after the end of the shooting task are extracted. Based on the magnitude, direction and duration of the change, a task convergence feature set is constructed. The task convergence feature set is used to characterize the behavioral features of the shooting task transitioning from the execution state to the non-execution state. Time-series analysis of the operational behavior at the end of a shooting task is the core operation for dynamic feature extraction based on behavioral data sequences. Specifically, a sliding time window is constructed to select multiple consecutive data segments before and after the end of the shooting task from the behavioral data sequence. The shooting command response time, data interaction frequency, and energy consumption trajectory in each segment are compared item by item. For each dimension, the magnitude, direction, and duration of the change in behavioral parameters over time are calculated. For example, does the shooting command response time show an increasing trend over a period of time? Does the data interaction frequency show a stable decrease? Does energy consumption continuously slow down? When the behavioral changes in multiple dimensions show a synchronous trend of decay, it can be considered that the task behavior is converging. Based on these trend parameters, a task convergence feature set is constructed to accurately describe the transition process from the execution state to the non-execution state. This processing method can effectively capture device behavior convergence signals, providing accurate evidence for determining whether the device is in a standby transition state after task termination, significantly reducing judgment errors caused by information delays or abnormal fluctuations.

[0022] The magnitude of change in operational behavior before and after the completion of a shooting task refers to the numerical change in key behavioral parameters of the device, such as the difference formed by a sudden drop in unit power consumption from a high level to a low level, reflecting the strength of task convergence. The direction of change refers to whether the change is an increase, a decrease, or a constant, used to determine the trend of behavior. The duration of change refers to the total length of time that the behavioral change maintains the same direction of change in a continuous time segment, used to measure the coherence and stability of the convergence process. The task convergence feature set is a multi-dimensional feature set composed of multiple magnitudes, directions, and durations of change, possessing high temporal correlation and state discrimination capabilities. This feature set is not a response to single-point data, but rather a model of a behavioral trend, capable of truly reflecting whether the device is leaving the task-active state and entering a scheduling idle period. By constructing the task convergence feature set, the system can transform originally discrete behavioral data into structural judgment criteria with trend and temporal significance, providing standardized input for subsequent state reasoning and scheduling hierarchy.

[0023] Each feature parameter in the task convergence feature set is compared with the preset judgment conditions. When the direction of change is consistent, the magnitude of change decreases continuously, and the duration of change reaches the preset time interval, it is determined that the infrared camera device enters the standby transition state from the running state to the standby state after the task is completed.

[0024] The core operation for constructing accurate state judgment logic is to compare each feature parameter in the task convergence feature set with preset judgment conditions. This process can be achieved by setting a standardized judgment template and comparing the change direction, change amplitude, and change duration extracted from the task convergence feature set with the corresponding thresholds in the template. Specifically, a time sliding window mechanism can be used to identify features in continuous behavioral data segments and use logical rules to determine whether the change direction is consistent, whether the change amplitude is within a continuously decreasing range, and whether the change duration reaches a set time limit. When all comparison conditions are met, the time period can be determined as the infrared camera device having completed its task and is in a standby transition state, switching from running to standby. This judgment process transforms quantitative behavioral trends into state recognition criteria, avoiding misjudgments caused by relying solely on a single reported state, providing the scheduling system with more accurate operational state judgment results, and effectively improving the timeliness and accuracy of resource scheduling.

[0025] Preset judgment criteria are a set of standards for evaluating the trend of task behavior changes, constructed based on historical data training, experimental optimization, or manual setting. These criteria typically include explicit threshold settings for the direction, magnitude, and duration of change. Consistent change direction and continuously decreasing magnitude indicate that multiple key behavioral parameters exhibit a uniform downward trend within the same time window; for example, a continuous increase in response time, a continuous decrease in communication frequency, and a continuous decrease in power consumption. This trend signifies that task execution activity is systematically converging. The preset time interval refers to the minimum duration window of behavioral change required to determine whether task behavior has entered a transitional state. For example, it may be set to ensure that the behavioral trend remains stable within a certain number of seconds or sampling periods. This time window setting avoids misjudgments caused by occasional fluctuations or anomalies, helping the system make robust judgments under the premise that the behavioral trend has a certain degree of continuity. These technical features work together to achieve a precise mapping of the operational behavior change trend to the scheduling status judgment logic, ensuring that the equipment scheduling process has high robustness and adaptability in the status judgment stage.

[0026] S2. After confirming that the infrared camera device has entered the standby transition state, obtain the time offset relationship and behavior difference relationship between the running behavior data and the most recent status reporting data, and generate a status synchronization offset based on the time offset relationship and behavior difference relationship to determine the status reporting delay characteristics when the infrared camera device enters the standby transition state after completing the task. In this embodiment, S2 specifically includes the following steps: S201. After confirming that the infrared camera device has entered the standby transition state, obtain the behavior occurrence time information corresponding to the running behavior data, and obtain the status reporting time information corresponding to the most recent status reporting data. By performing time alignment and difference calculation on the behavior occurrence time information and status reporting time information, a time offset relationship between the running behavior data and the most recent status reporting data is formed. After an infrared camera completes its shooting task, to determine whether the device has switched from task execution to standby mode, it's necessary to compare the actual action time of the device with the status reporting time recorded by the system. First, the camera's operational behavior data is obtained through log recording or a low-level behavior monitoring mechanism. This includes actions such as starting data writing after image acquisition and a decrease in sensor current load. Each action is associated with a specific time of occurrence, indicating the exact moment the action occurred on the timeline. Simultaneously, the most recent status reporting data received by the system backend is retrieved, containing the device's current operating status returned via network communication and the corresponding status reporting time. To determine if there is a delay or inconsistency between these two types of data, time alignment is required. This involves synchronizing the action occurrence time and status reporting time using a unified clock reference to ensure the accuracy of the comparison timing. Then, the time difference between the two is calculated based on the unified timing. For example, if the action occurrence time is 12:00:03 and the status reporting time is 12:00:08, the time offset is 5 seconds. This difference constitutes the initial quantification of the time offset relationship. This calculation method can accurately reflect whether there is a delay or deviation between the actual behavior of the equipment and the perceived state of the system, which facilitates further state assessment and scheduling decisions.

[0027] The behavior occurrence time information corresponding to the operational behavior data refers to the precise time stamps attached to all behavioral events related to task execution actively or passively collected from the infrared camera device, such as the time when shooting ends, the time when power load changes, and the time when buffer release is completed. This time information is usually generated by a high-precision timer inside the device. The most recent status report data refers to the status information packet reported by the infrared camera device to the superior management platform through a network interface or serial communication. This information includes the device operating mode identifier, task completion flag, and status report time information, where the status report time information represents the time record when the system received the device's current status. Time alignment is the process of unifying time information from two different sources to the same time base, usually requiring consideration of error corrections such as clock skew or network latency. Difference calculation is based on the numerical difference between the aligned behavior occurrence time information and the status report time information, reflecting the degree of synchronization between the two in the time dimension. The resulting time offset relationship is a quantitative indicator used to characterize the time difference between device behavior and system perception, providing a core reference for subsequent judgment of status report delay.

[0028] S202. Based on the behavioral features in the operational behavior data that reflect the completion status of the shooting task, compare them with the status indicators in the most recent status report data that reflect the operational status, extract the degree of difference between the behavioral features and the status indicators, and form a behavioral difference relationship between the operational behavior data and the most recent status report data. To assess the accuracy of the current status information of infrared camera equipment, it is necessary to compare the behavioral features closely related to task completion in the equipment's operational behavior data with the status identifiers marking the running status in the status report data received by the system, thereby extracting the degree of difference between the two. Specifically, behavioral features are first extracted, such as data transmission completion rate, image cache clearing flag, and current load reaching a stable value. These features exhibit specific patterns after the equipment completes its task. Then, status identifiers are obtained, such as the "working" or "idle" flag carried in the report, and the equipment execution command status identifier. By setting a feature-identifier mapping model, each behavioral feature can be paired with its corresponding ideal status identifier, and the degree of matching can be calculated. When the actual behavioral feature shows a "task completed" state, but the status identifier still shows "running," the system determines that a difference exists. This difference can be quantified using a set similarity threshold model; for example, if the completion probability of a behavioral feature is 95%, and the status identifier corresponds to the running state, then the degree of difference is a deviation of 0.95 from 0. Finally, the difference values ​​of all feature-identifier pairs are summarized to form a behavioral difference relationship, which is used to further calculate the status synchronization offset.

[0029] Behavioral features refer to specific parameters extracted from infrared camera equipment that reflect the execution or completion status of a task, such as image processing completion signals, communication load stabilization, and battery voltage recovery. Each behavioral feature is closely related to a specific task stage. Status identifiers reflecting the operating status are preset operation marker fields in the device's status reporting data. These typically include enumerated types such as task in progress, standby, error status, and initialization, used by the system to identify the current working state. The degree of difference between behavioral features and status identifiers is calculated by setting the expected matching relationship between features and identifiers and then calculating their deviation value over the same time period. This is usually quantitatively evaluated using numerical methods or fuzzy matching functions. The behavioral difference relationship is the aggregated result of the degree of difference between multiple behavioral features and their corresponding status identifiers. It describes the overall synchronization deviation between the device's behavioral layer and state cognition layer and is a core indicator for judging the accuracy of state synchronization.

[0030] S203. Based on the time offset relationship and behavior difference relationship, perform combined calculations to generate a state synchronization offset, and determine the state reporting delay characteristics of the infrared camera device when it enters a standby transition state after completing the task based on the numerical distribution range of the state synchronization offset.

[0031] This method combines time offset and behavioral difference relationships to generate a state synchronization offset. The state reporting delay characteristic is then determined based on the numerical distribution range of this offset. This addresses the issue of firmware status reporting delays causing perception distortion in the scheduling system during the transition from running to standby mode after an infrared camera completes its shooting task. Since relying solely on either time offset or behavioral difference relationships can lead to misjudgments due to network fluctuations, short-term anomalies, or device heterogeneity, it's impossible to comprehensively and accurately identify whether a device has completed its task and is eligible for scheduling. Therefore, combining the two creates a more representative state synchronization offset that reflects the accuracy of state synchronization during this transition. By setting a reasonable numerical distribution range and mapping the state synchronization offset to specific delay levels, different degrees of state reporting lag can be effectively distinguished. This provides a stable and quantitative basis for subsequent scheduling decisions, improving the reliability and real-time performance of scheduling decisions, preventing available device resources from being misjudged as unschedulable, and enhancing the coordination and resource utilization of the entire intelligent scheduling system.

[0032] In this embodiment, S203 specifically refers to: The time offset relationship is processed into intervals, mapping the time offset value between the running behavior data and the most recent status report data to a preset time offset interval, and forming a corresponding time offset interval identifier. To accurately identify the delay characteristics of status reporting after infrared camera devices complete a task, it is necessary to perform interval processing on the time offset value between the operational behavior data and the most recent status report data. Specifically, the time offset value for each task cycle is first extracted from the preceding data analysis. This value reflects the time difference between the occurrence of the infrared camera device's behavior and the receipt of its status by the system. To avoid instability in subsequent analysis due to the direct use of discrete values, an interval mapping method is used to assign the time offset value to a pre-defined time offset interval. The pre-defined time offset intervals are several time periods divided based on historical data statistical analysis results, such as 0–2 seconds, 2–5 seconds, 5–10 seconds, etc., each corresponding to different levels of device synchronization capability. Whenever a new task's time offset value is generated, the system maps it to the corresponding time offset interval and records it using the interval's number or label as the time offset interval identifier. For example, when the time offset value is 3.4 seconds, it will be mapped to the 2–5 second interval, and the corresponding time offset interval will be labeled "Interval 2". This interval-based processing method effectively reduces the risk of misjudgment caused by data fluctuations and provides structured input support for subsequent combined analysis of behavioral differences. Interval-based processing is a technique that discretizes continuous variables to enhance model robustness. The time offset value refers to the difference between the time of the behavior occurrence and the time of status reporting. The preset time offset interval is a time division boundary set according to task characteristics and device response patterns. The time offset interval identifier is the discrete label to which the offset value belongs after mapping, facilitating structured classification and reference by scheduling logic.

[0033] The behavioral differences are hierarchically processed, mapping the degree of difference between the behavioral features reflecting the task completion status in the operational behavior data and the status identifiers reflecting the operational status in the status reporting data to a preset difference level range, and forming corresponding difference level identifiers. To improve the accuracy of identifying delays in infrared camera status reporting, it is necessary to classify the degree of difference between operational behavior data and status reporting data. This process first generates a difference degree value based on the numerical or sign deviation between behavioral features and status identifiers. This value reflects the synchronization consistency between the device's behavioral layer and perception layer. Since the degree of difference is a continuous variable, directly using it for intelligent scheduling decisions can lead to tolerance instability or misjudgment; therefore, a classification mechanism is required. Specifically, based on historical scheduling accuracy analysis and behavioral deviation statistics, the degree of difference is divided into several preset difference level intervals. Each interval represents a specific difference sensitivity level, such as "basically consistent interval," "moderate difference interval," and "significant deviation interval," corresponding to different risk thresholds for error accumulation. After each difference degree value is generated, it is matched with a preset level interval, mapped to the corresponding level, and assigned a difference level identifier, such as "Level 1," "Level 2," and "Level 3." For example, if the behavioral features indicate that the signal strength of the shooting task is 92% complete, but the status identifier is still "task in progress," the difference degree is calculated to be 0.92, matching the "moderate difference interval," and is marked as "Level 2." This discretized hierarchical processing method reduces the impact of error interference on scheduling decisions and enhances the stability and controllability of scheduling confidence assessment. Hierarchical processing is a strategy that transforms continuous differences into discrete classification labels. The preset difference level interval is a set of difference value ranges defined according to the scheduling tolerance strategy. The difference level identifier is the level number corresponding to the difference value after mapping, used to support the combined generation of subsequent state synchronization offsets.

[0034] The state synchronization offset is generated by combining the time offset interval identifier and the difference level identifier. Based on the state synchronization offset's location in the preset value distribution interval, the state reporting delay characteristics of the infrared camera device when it enters the standby transition state after completing the task are determined.

[0035] To accurately identify the status reporting delay characteristics of infrared camera devices entering a standby transition state after completing a task, it is necessary to combine the time offset interval identifier and the difference level identifier to generate a status synchronization offset that characterizes the degree of status synchronization offset. This combination operation can be implemented using weighted averages, encoded superposition, or multi-dimensional mapping. For example, different numerical weights can be set for different offset intervals and difference levels, and the status synchronization offset can be generated through linear combination or hash mapping. The status synchronization offset is essentially a multi-dimensional fusion result used to uniformly measure the coupling strength between time response lag and behavioral response difference. To improve the discrimination efficiency of this parameter in evaluation, the status synchronization offset needs to be mapped to a preset numerical distribution interval based on the delay characteristics in historical task cycles. Different intervals represent different levels of delay characteristic stability and impact. For example, the offset range can be divided into "low delay interval," "medium delay interval," and "high delay interval." When the status synchronization offset generated by a device in a task cycle falls within the "medium delay interval," it can be determined that it currently has a medium level of status reporting delay. This processing method not only improves the ability to identify different behaviors in non-obvious states but also provides standardized input for the subsequent generation of scheduling confidence scores. Among them, the combination operation is an operation method that integrates and analyzes two heterogeneous indicators. The state synchronization offset is an evaluation parameter generated by the combination result, which is used to measure the degree of lag in the state report. The preset numerical distribution range is a standard for dividing the offset parameters in advance based on the scheduling history and evaluation error, which is used to classify and identify the offset.

[0036] S3. Map the status reporting delay features into a delay evaluation vector that includes delay magnitude, delay persistence and behavior stability, and calculate the scheduling confidence score based on the delay evaluation vector; In this embodiment, S3 specifically includes the following steps: S301. The status reporting delay feature is deconstructed in multiple dimensions, and three types of indicators are extracted: delay amplitude, delay persistence and behavior stability. Among them, delay amplitude represents the maximum time span of the status synchronization offset, delay persistence represents the number of times the status asynchrony phenomenon is maintained in the continuous sampling period, and behavior stability represents the degree of fluctuation of the device operation behavior during the delay period. S302. Normalize the three indicators of delay amplitude, delay duration and behavior stability, and combine the parameters according to the preset fixed vector order to construct a delay evaluation vector containing delay amplitude, delay duration and behavior stability, which is used to uniformly express the strength level of the current state reporting delay feature. In actual operation, the three indicators—delay magnitude, delay persistence, and behavioral stability—have different dimensions and numerical ranges. Directly combining them can lead to one dimension dominating the overall evaluation result due to scale differences. To avoid this problem, the three indicators must first be normalized. Min-max scaling or Z-score normalization methods can be used to map the original values ​​of each indicator to a uniform numerical range, such as 0 to 1, ensuring the comparability of the weights of each dimension in the calculation. After normalization, according to a pre-defined fixed order (e.g., delay magnitude first, delay persistence second, and behavioral stability third), the three indicators are combined as a vector to form a delay evaluation vector. This vector is a three-dimensional ordered set of values ​​that uniformly reflects the intensity of the current status reporting delay characteristics of the infrared camera equipment, supporting quantitative evaluation in subsequent scheduling decisions.

[0037] During normalization, latency amplitude refers to the maximum time span in the state synchronization offset, and its value needs to be standardized using the maximum and minimum values ​​in the full sample. Latency persistence represents the number of times the state desynchronization phenomenon persists in a continuous sampling period, and is an integer indicator. Behavioral stability represents the degree of fluctuation in operational behavior, usually expressed by variance or mean absolute deviation. Combining these three indicators in a fixed vector order ensures the structural consistency of the latency evaluation vector, facilitating subsequent quantitative comparisons of latency states between different devices. The latency evaluation vector not only preserves the independence of the three dimensions but also provides a compact expression structure, enabling it to be used as an input parameter in the calculation of scheduling confidence scores in intelligent scheduling strategies, thereby achieving an accurate characterization of the current schedulability of devices.

[0038] S303. Based on the components of each indicator in the delay evaluation vector, a weighted calculation is performed using preset weight coefficients to generate a scheduling confidence score. The scheduling confidence score is used to evaluate the credibility of the infrared camera device's participation in intelligent scheduling under different state reporting delay characteristics.

[0039] To quantitatively assess the schedulability of infrared camera equipment, a scheduling confidence score is generated by weighting the various indicator components in the delay assessment vector with preset weighting coefficients. Specifically, weighting coefficients are first assigned to the three indicators: delay amplitude, delay persistence, and behavioral stability, for example, 0.4, 0.3, and 0.3 respectively, reflecting their influence on the overall scheduling judgment. Then, the three normalized indicators are multiplied one-to-one with their corresponding weighting coefficients, and all product values ​​are summed to obtain the final scheduling confidence score. The score is typically limited to between 0 and 1, with higher values ​​indicating greater reliability in scheduling the equipment in its current state. The advantage of this method is that it fully reflects the contribution of various delay characteristics to scheduling reliability through a weighting mechanism and enables accurate comparison and filtering of state differences between different devices.

[0040] In this process, preset weighting coefficients are set in advance based on historical operational data statistics, expert experience, or machine learning training results to balance the impact of various dimensional indicators on scheduling evaluation. Weighted calculation uses a linear combination method, multiplying each value in the delay evaluation vector by its corresponding weight and then summing the results to ensure continuity and discriminability. The scheduling confidence score is a single numerical value used to comprehensively reflect the schedulable reliability of the current infrared camera equipment under conditions of delayed status reporting. It is typically used as an input parameter for sorting, prioritization, or scheduling strategy selection, and is a core reference indicator in the intelligent scheduling decision chain.

[0041] In this embodiment, S301 specifically refers to: Based on the changes in the state synchronization offset within a continuous sampling period, the maximum time span of the state synchronization offset is extracted to determine the delay magnitude index. The delay magnitude index is used to characterize the extreme range of the state reporting delay in the time dimension. Within a continuous sampling period, the state synchronization offset generated in each sampling result can be timestamped and arranged according to time sequence. The length of the continuous time period from the first offset to the offset value returning to zero is statistically analyzed, and this length is the maximum time span of the state synchronization offset. By extracting this time span as a delay magnitude index, the longest duration of asynchrony between the infrared camera device's operational behavior and status reporting after completing the shooting task can be quantified. This is used to assess the severity of potential scheduling information misjudgments at task switching nodes. For example, if a device's state synchronization offset is continuously non-zero for five sampling periods, with start and end times t1 and t6 respectively, then its maximum time span is t6 minus t1, denoted as the delay magnitude index of the device during this task switching process. The larger the delay magnitude index, the stronger the lag in the device's status reporting, and the more significant the impact on intelligent scheduling judgment. Therefore, this index is an important parameter for evaluating the scheduling feasibility of infrared camera devices. Extracting the delay magnitude index in this way provides basic data support for subsequent construction of delay evaluation vectors and scheduling confidence scores.

[0042] Based on the number of times the state synchronization offset remains non-zero within a continuous sampling period, the number of times the state asynchrony phenomenon is maintained is counted to determine the delay persistence index. The delay persistence index is used to characterize the persistence feature of the state reporting delay in the time series. Within a continuous sampling period, the state synchronization offset generated at each time point is analyzed item by item. The number of periods where the offset value is not zero is recorded, and the cumulative frequency of this non-zero offset is counted. This frequency represents the number of times the state asynchrony phenomenon persists. Based on this number of persistences, a delay persistence index is constructed. The delay persistence index measures the continuity of state reporting delay on the time axis. If the device consistently exhibits a non-zero state synchronization offset across multiple sampling periods, it indicates that its state reporting delay is not an isolated phenomenon but rather has a certain degree of continuity and stability, potentially affecting the scheduling system's judgment of the device's operating status in the long term. For example, if the state synchronization offset is not zero in seven out of ten consecutive sampling periods, the number of persistences is seven, and the delay persistence index is seven. This index reflects the degree of disconnect between the device's state synchronization and actual operating behavior during the standby transition period after task completion. The higher the delay persistence index, the more likely the device is to be in a state of scheduling misjudgment for a long time, thus affecting its reliability in participating in subsequent task allocation. Therefore, extracting delay persistence indicators is of great reference value for further calculating scheduling confidence scores, and helps to improve the accuracy and robustness of the scheduling system.

[0043] Based on the changes in operational behavior data during the period of state synchronization offset, the fluctuation of operational behavior parameters in adjacent sampling periods is analyzed to determine the behavior stability index. The behavior stability index is used to characterize the changes in equipment operational behavior during the state reporting delay period.

[0044] During the state synchronization offset period, the operational behavior data sequence within the corresponding time period is extracted. Multiple dimensions of the operational behavior parameters are selected, such as the shooting command response interval, data interaction frequency, and power consumption change trajectory. The numerical differences of these parameters between adjacent sampling periods are statistically analyzed. A sliding window approach is used to calculate the variation amplitude between two adjacent time points period by period. The standard deviation or mean absolute deviation of these variation amplitudes is calculated to assess the degree of fluctuation in operational behavior, thereby generating a behavior stability index. A lower behavior stability index value indicates a more stable behavior change during the delay period, and is more likely to be in an idle or low-power phase after task completion. Conversely, a higher index value indicates that the device's behavior characteristics still fluctuate drastically during the state delay period, potentially indicating incomplete task completion or hardware malfunction. For example, if an infrared camera device exhibits minimal fluctuations in its response time and power consumption curves during the five consecutive sampling periods of the state synchronization offset, its behavior stability index will be low, indicating that the device's state is basically stable and has a high degree of reliability in participating in scheduling. This index enhances the system's perception of the persistence of device state anomalies and behavioral consistency, thereby improving the accuracy of state assessment.

[0045] S4. Based on the scheduling confidence score, the infrared camera equipment is divided into different scheduling levels, and the scheduling level is used to determine whether the infrared camera equipment is qualified to participate in the next round of intelligent scheduling. In this embodiment, S4 specifically refers to: Construct a scheduling level mapping table, set multiple scheduling level intervals, each scheduling level interval corresponds to a continuous range of scheduling confidence score values, and assign a unique scheduling level identifier to each scheduling level interval to distinguish the priority category of infrared camera devices in the scheduling process; Constructing a scheduling level mapping table can be achieved by setting multiple continuous and non-overlapping confidence score ranges, typically categorized according to scheduling capability strength. For example, in a scenario where the overall scheduling confidence score range is 0 to 100, it can be divided into five level ranges: 0-20, 21-40, 41-60, 61-80, and 81-100, corresponding to scheduling priorities from lowest to highest. Each range is assigned a specific scheduling level identifier, such as L1, L2, L3, L4, and L5. In practice, numerical comparison methods are used to determine which range a given infrared camera device's current scheduling confidence score belongs to, and the corresponding scheduling level identifier is assigned. The purpose of this is to transform continuous numerical scores into discrete levels, enabling tiered selection and priority scheduling of devices in subsequent scheduling decisions, thereby improving the controllability and stability of the scheduling strategy.

[0046] The scheduling level mapping table is a set of rules, its core consisting of scheduling level intervals and scheduling level identifiers. Scheduling level intervals are logical segments defined according to the numerical range of scheduling confidence scores. Each interval defines the upper and lower boundaries of a set of confidence scores, serving as boundary conditions for level determination. The scheduling level identifier is a unique label for each level interval, used to quickly identify the scheduling capability category of infrared camera equipment during the scheduling process. This mapping relationship ensures a stable mapping mechanism between score values ​​and scheduling priorities, helping to avoid inconsistencies in scheduling decisions caused by discrete fluctuations in score values, and improving the clarity of level classification and the consistency of scheduling strategy execution in the operation and management of infrared camera equipment.

[0047] The scheduling confidence score of the infrared camera equipment is matched with each scheduling level interval in the scheduling level mapping table. By comparing the numerical values ​​of the scheduling confidence scores, the scheduling level of the infrared camera equipment is determined, and a corresponding scheduling level identifier is assigned to it, thus forming a scheduling level classification result. Matching the scheduling confidence score of infrared camera devices with the scheduling level intervals in the scheduling level mapping table can be achieved using an interval lookup algorithm. Specifically, the scheduling confidence score corresponding to each infrared camera device is used as input, and its upper and lower boundaries are compared sequentially with multiple preset scheduling level intervals in the mapping table. When an interval satisfies the condition that the confidence score is greater than or equal to the lower boundary and less than or equal to the upper boundary, the scheduling level of the infrared camera device is determined, and a corresponding identifier is assigned to the device according to the predefined scheduling level identifier for that interval. For example, a device with a score of 68 successfully matches the interval 61–80, and is assigned L4 as its scheduling level identifier. This approach establishes a structured association between scheduling confidence scores and scheduling decisions, providing a clear standard for level judgment in subsequent task scheduling processes.

[0048] The scheduling confidence score is a numerical measure of the schedulability of an infrared camera device under conditions of status reporting delay. Comparing the numerical allocation of the scheduling confidence score involves matching the score with multiple preset scheduling level intervals to determine which interval it falls into within the entire scoring space. A scheduling level interval is a continuous segment divided according to a numerical range, with each segment representing an independent scheduling level. Once a match is successful, the system immediately assigns the device the scheduling level identifier corresponding to that interval. The scheduling level identifier is a discrete classification label used to indicate the device's scheduling priority category. The scheduling level classification result ultimately determines the device's availability and priority in the next round of intelligent scheduling, serving as a crucial bridge between the scoring evaluation results and the task allocation strategy.

[0049] Based on the scheduling level classification results, a scheduling level threshold is set for participating in the next round of intelligent scheduling. Infrared camera devices with a scheduling level higher than or equal to the scheduling level threshold are identified as qualified to participate in the next round of intelligent scheduling, while other devices are not qualified to participate in the next round of intelligent scheduling, so as to achieve controllable scheduling screening under the background of delay interference.

[0050] Based on the scheduling level classification results, infrared camera devices that meet the scheduling conditions can be selected by setting a scheduling level threshold. Specifically, after each round of scheduling level classification, a clear scheduling level threshold is set manually or by algorithm as the minimum qualification threshold for participating in the next round of intelligent scheduling. Then, the scheduling level of all infrared camera devices is compared with this threshold. Devices with a scheduling level higher than or equal to the threshold are considered to have stable operation and meet the conditions for participating in scheduling, and are included in the next round of scheduling pool; devices below the threshold are temporarily excluded to avoid potential uncertainties caused by status reporting delays. For example, if the scheduling levels are divided into L1 to L5, and the threshold is set to L3, then devices at levels L3, L4, and L5 can enter the scheduling process, while devices at levels L1 and L2 will be removed to ensure scheduling stability.

[0051] The scheduling level threshold is a numerical limit used to define the boundary of scheduling eligibility. Essentially, it is the lowest usable level set in the classification label formed by mapping the scheduling confidence score to a level. By filtering through this threshold, the operational stability and responsiveness of equipment can be controlled under different reporting delay backgrounds, thereby achieving controllability and accuracy of scheduling objectives. The scheduling level classification results provide the scheduling reliability distribution for each infrared camera device, while the scheduling level threshold acts as the logic controller at the scheduling entry point. This ensures that equipment scheduling is based not only on functional completion but also on the reliability of state feedback, effectively improving the adaptability and robustness of the scheduling process under delay interference.

[0052] S5. After completing intelligent scheduling, collect subsequent operational behavior data of the infrared camera equipment, compare the deviation relationship between the scheduling confidence score and the actual operational behavior, and update the task convergence feature set and state synchronization offset for dynamic control in the subsequent intelligent scheduling process.

[0053] In this embodiment, S5 specifically refers to: After completing intelligent scheduling, the system continuously collects subsequent operational behavior data of the infrared camera device during the scheduling process. The subsequent operational behavior data includes scheduling task response time, task completion confirmation time, energy consumption change parameters and status reporting interval data, and forms a subsequent operational behavior data sequence. After intelligent scheduling is completed, to evaluate the effectiveness of the scheduling strategy, it is necessary to continuously track and collect the operating status of the infrared camera equipment during the scheduling process, forming subsequent operational behavior data. Specifically, this can be achieved through the data recording module built into the device, the edge computing unit, or real-time monitoring commands issued by the scheduling system, periodically recording scheduling task response time, task completion confirmation time, energy consumption change parameters, and status reporting interval data. The scheduling task response time can be obtained by detecting the timestamp of the device's first response after task allocation; the task completion confirmation time is obtained by identifying the termination flag of the shooting task or the file writing completion signal; the energy consumption change parameters are obtained by sampling from the power consumption sensor module; and the status reporting interval data is dynamically calculated based on the status feedback interval received by the system. The collected data is arranged in the order of sampling time to construct a subsequent operational behavior data sequence that can be used for analysis. This sequence is used to compare with the predicted behavior before scheduling to determine whether the current device status meets the expected performance, ultimately achieving closed-loop optimization of the scheduling logic.

[0054] Subsequent operational behavior data is crucial performance data for infrared camera equipment after receiving scheduling instructions, specifically encompassing four core technical characteristics. Scheduling task response time represents the equipment's ability to respond to delays from receiving a task to commencing execution; task completion confirmation time reflects the completeness of task execution and the degree of time closure in equipment response; energy consumption variation parameters are used to determine the actual consumption of equipment resources by scheduling tasks, reflecting their efficiency and stability; and status reporting interval data reveals the synchronization degree of equipment status feedback, serving as an indirect indicator of latency anomalies. This data is collected using a uniform sampling frequency and organized in a structured time series format, forming a subsequent operational behavior data sequence. This provides high-timeliness and high-resolution support for subsequent deviation identification and dynamic control. The completeness and accuracy of this data sequence are prerequisites for realizing the self-correction capability of the intelligent scheduling system.

[0055] Based on the subsequent operational behavior data sequence, actual operational behavior features reflecting the scheduling execution quality are extracted. The actual operational behavior features are then matched and compared item by item with the scheduling confidence score calculated before intelligent scheduling to determine the deviation relationship between the scheduling confidence score and the actual operational behavior. To evaluate the accuracy and robustness of intelligent scheduling strategies, after completing a scheduling task, it is necessary to extract actual operational behavior features reflecting the quality of scheduling execution based on subsequent operational behavior data sequences, and then compare and analyze these features with the scheduling confidence score. Specifically, this can be achieved by analyzing key behavioral indicators such as scheduling task response time, task completion confirmation time, energy consumption change parameters, and status reporting interval data to extract feature values ​​for dimensions such as stability, response efficiency, and energy consumption control during actual operation. Then, these actual operational behavior features are mapped one-to-one with the evaluation dimensions used in generating the scheduling confidence score, ensuring logical correspondence and dimensional consistency among the indicators. During the comparison process, a step-by-step matching strategy is used to calculate the numerical difference between each feature and its corresponding score component, and the overall degree of deviation is comprehensively evaluated using methods such as statistical offset, mean deviation, and maximum deviation. This process enables consistency analysis between scheduling predictions and actual execution results, provides feedback loop support for the intelligent scheduling model, and provides a basis for subsequent model correction and scheduling optimization.

[0056] Actual operational behavior characteristics are a quantitative expression of the equipment's performance after scheduling, mainly including scheduling task response latency, timeliness of task completion confirmation, energy consumption level change rate, and synchronization frequency of status information. These characteristics are respectively linked to three evaluation dimensions: latency magnitude, latency persistence, and behavioral stability, to construct a complete behavioral comparison benchmark. Item-by-item matching and comparison involves performing a one-to-one difference analysis between each actual operational behavior characteristic and its corresponding component in the scheduling confidence score vector. This process can be calculated using relative error, absolute error, or rate of change to ensure the results are comparable and quantifiable. The deviation relationship between the scheduling confidence score and actual operational behavior is an important parameter for measuring scheduling prediction capability. Its results can be used to calibrate the confidence interval of the prediction model and to determine whether a specific device has external interference or operational anomalies. Through this deviation analysis mechanism, the system can achieve dynamic adaptation and continuous iterative updates of the intelligent scheduling strategy.

[0057] Based on the deviation relationship results, the parameters of the behavioral change amplitude, direction and persistence characteristics in the task convergence feature set are corrected, and the time offset interval and difference level identifier of the state synchronization offset are updated at the same time to realize the dynamic control of the task convergence feature set and the state synchronization offset in the subsequent intelligent scheduling process.

[0058] To improve the accuracy and adaptability of subsequent intelligent scheduling, key parameters in the task convergence feature set can be specifically modified based on the deviation relationship between the scheduling confidence score and actual operational behavior. Specifically, this can be achieved by analyzing the operational behavior characteristics corresponding to various deviation components, such as the reflection of delay amplitude deviation on the magnitude of behavior change, delay persistence deviation on the persistence of behavior change, and behavior stability deviation on the uncertainty of behavior change direction. Adjustment directions and magnitudes matching the causes of deviations can then be extracted. Subsequently, the corresponding parameter items in the task convergence feature set are dynamically adjusted based on the deviation index values, such as reducing the change amplitude threshold, extending or shortening the duration limit, or adjusting the sensitivity setting to the direction of behavior change. Furthermore, the time offset interval boundary of the state synchronization offset is adjusted according to the new behavior pattern, and the difference level identifier is remapped to ensure consistency between the modeling structure of the state reporting delay and the actual operating performance of the equipment, thereby achieving real-time self-calibration of the scheduling model.

[0059] The magnitude, direction, and persistence of behavioral changes in the task convergence feature set are key parameters describing the behavioral evolution of infrared camera equipment as it transitions from an operational to a non-operational state. The magnitude of change measures the severity of the behavioral indicator, the direction of change indicates the directional nature of the behavioral trend, and the persistence of change measures the stability of the trend over time. Parameter correction refers to updating and adjusting these feature parameters after receiving a new round of behavioral data feedback, taking into account the deviation between prediction and reality. The state synchronization offset is a delayed state representation mechanism jointly modeled using a time offset interval and a difference level identifier. The time offset interval describes the time delay range of the equipment's state response, and the difference level identifier reflects the degree of content deviation between the operational state and the reported state. By updating these two components, the state representation model can achieve adaptive evolution, enabling the scheduling system to have stronger fault tolerance and predictive accuracy when facing changes in equipment behavior.

[0060] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions according to the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means (e.g., infrared, wireless, microwave, etc.). A computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. Semiconductor media can be solid-state drives.

[0061] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0062] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0063] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0064] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0065] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0066] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for operating and managing infrared camera equipment based on intelligent scheduling, characterized in that, Specifically, the following steps are included: S1. Collect the operation behavior data of the infrared camera device before and after the shooting task ends, construct a task convergence feature set based on the operation behavior data, and use the task convergence feature set to determine whether the infrared camera device enters the standby transition state from the running state to the standby state after the task is completed. S2. After confirming that the infrared camera device has entered the standby transition state, obtain the time offset relationship and behavior difference relationship between the running behavior data and the most recent status reporting data, and generate a status synchronization offset based on the time offset relationship and behavior difference relationship to determine the status reporting delay characteristics when the infrared camera device enters the standby transition state after completing the task. S3. Map the status reporting delay features into a delay evaluation vector that includes delay magnitude, delay persistence and behavior stability, and calculate the scheduling confidence score based on the delay evaluation vector; S4. Based on the scheduling confidence score, the infrared camera equipment is divided into different scheduling levels, and the scheduling level is used to determine whether the infrared camera equipment is qualified to participate in the next round of intelligent scheduling. S5. After completing intelligent scheduling, collect subsequent operational behavior data of the infrared camera equipment, compare the deviation relationship between the scheduling confidence score and the actual operational behavior, and update the task convergence feature set and state synchronization offset for dynamic control in the subsequent intelligent scheduling process.

2. The method for operating and managing infrared camera equipment based on intelligent scheduling according to claim 1, characterized in that, S1 specifically refers to: Before and after the shooting mission ends, the operation behavior data of the infrared camera device is continuously collected. The operation behavior data includes changes in shooting command response time, changes in data interaction frequency per unit time, and energy consumption change trajectory. The operation behavior data forms a behavior data sequence in chronological order. Based on the behavioral data sequence, the operation behavior at the end stage of the shooting task is analyzed in a time series. The magnitude, direction and duration of the change in the operation behavior before and after the end of the shooting task are extracted. Based on the magnitude, direction and duration of the change, a task convergence feature set is constructed. The task convergence feature set is used to characterize the behavioral features of the shooting task transitioning from the execution state to the non-execution state. Each feature parameter in the task convergence feature set is compared with the preset judgment conditions. When the direction of change is consistent, the magnitude of change decreases continuously, and the duration of change reaches the preset time interval, it is determined that the infrared camera device enters the standby transition state from the running state to the standby state after the task is completed.

3. The method for operating and managing infrared camera equipment based on intelligent scheduling according to claim 1, characterized in that, S2 specifically includes the following steps: S201. After confirming that the infrared camera device has entered the standby transition state, obtain the behavior occurrence time information corresponding to the running behavior data, and obtain the status reporting time information corresponding to the most recent status reporting data. By performing time alignment and difference calculation on the behavior occurrence time information and status reporting time information, a time offset relationship between the running behavior data and the most recent status reporting data is formed. S202. Based on the behavioral features in the operational behavior data that reflect the completion status of the shooting task, compare them with the status indicators in the most recent status report data that reflect the operational status, extract the degree of difference between the behavioral features and the status indicators, and form a behavioral difference relationship between the operational behavior data and the most recent status report data. S203. Based on the time offset relationship and behavior difference relationship, perform combined calculations to generate a state synchronization offset, and determine the state reporting delay characteristics of the infrared camera device when it enters a standby transition state after completing the task based on the numerical distribution range of the state synchronization offset.

4. The method for operating and managing infrared camera equipment based on intelligent scheduling according to claim 3, characterized in that, S203 specifically refers to: The time offset relationship is processed into intervals, mapping the time offset value between the running behavior data and the most recent status report data to a preset time offset interval, and forming a corresponding time offset interval identifier. The behavioral differences are hierarchically processed, mapping the degree of difference between the behavioral features reflecting the task completion status in the operational behavior data and the status identifiers reflecting the operational status in the status reporting data to a preset difference level range, and forming corresponding difference level identifiers. The state synchronization offset is generated by combining the time offset interval identifier and the difference level identifier. Based on the state synchronization offset's location in the preset value distribution interval, the state reporting delay characteristics of the infrared camera device when it enters the standby transition state after completing the task are determined.

5. The method for operating and managing infrared camera equipment based on intelligent scheduling according to claim 1, characterized in that, S3 specifically includes the following steps: S301. The status reporting delay feature is deconstructed in multiple dimensions, and three types of indicators are extracted: delay amplitude, delay persistence and behavior stability. Among them, delay amplitude represents the maximum time span of the status synchronization offset, delay persistence represents the number of times the status asynchrony phenomenon is maintained in the continuous sampling period, and behavior stability represents the degree of fluctuation of the device operation behavior during the delay period. S302. Normalize the three indicators of delay amplitude, delay duration and behavior stability, and combine the parameters according to the preset fixed vector order to construct a delay evaluation vector containing delay amplitude, delay duration and behavior stability, which is used to uniformly express the strength level of the current state reporting delay feature. S303. Based on the components of each indicator in the delay evaluation vector, a weighted calculation is performed using preset weight coefficients to generate a scheduling confidence score. The scheduling confidence score is used to evaluate the credibility of the infrared camera device's participation in intelligent scheduling under different state reporting delay characteristics.

6. The method for operating and managing infrared camera equipment based on intelligent scheduling according to claim 5, characterized in that, S301 specifically refers to: Based on the changes in the state synchronization offset within a continuous sampling period, the maximum time span of the state synchronization offset is extracted to determine the delay magnitude index. The delay magnitude index is used to characterize the extreme range of the state reporting delay in the time dimension. Based on the number of times the state synchronization offset remains non-zero within a continuous sampling period, the number of times the state asynchrony phenomenon is maintained is counted to determine the delay persistence index. The delay persistence index is used to characterize the persistence feature of the state reporting delay in the time series. Based on the changes in operational behavior data during the period of state synchronization offset, the fluctuation of operational behavior parameters in adjacent sampling periods is analyzed to determine the behavior stability index. The behavior stability index is used to characterize the changes in equipment operational behavior during the state reporting delay period.

7. The method for operating and managing infrared camera equipment based on intelligent scheduling according to claim 1, characterized in that, S4 specifically refers to: Construct a scheduling level mapping table, set multiple scheduling level intervals, each scheduling level interval corresponds to a continuous range of scheduling confidence score values, and assign a unique scheduling level identifier to each scheduling level interval to distinguish the priority category of infrared camera devices in the scheduling process; The scheduling confidence score of the infrared camera equipment is matched with each scheduling level interval in the scheduling level mapping table. By comparing the numerical values ​​of the scheduling confidence scores, the scheduling level of the infrared camera equipment is determined, and a corresponding scheduling level identifier is assigned to it, thus forming a scheduling level classification result. Based on the scheduling level classification results, a scheduling level threshold is set for participating in the next round of intelligent scheduling. Infrared camera devices with a scheduling level higher than or equal to the scheduling level threshold are identified as qualified to participate in the next round of intelligent scheduling.

8. The method for operating and managing infrared camera equipment based on intelligent scheduling according to claim 1, characterized in that, S5 specifically refers to: After completing intelligent scheduling, the system continuously collects subsequent operational behavior data of the infrared camera device during the scheduling process. The subsequent operational behavior data includes scheduling task response time, task completion confirmation time, energy consumption change parameters and status reporting interval data, and forms a subsequent operational behavior data sequence. Based on the subsequent operational behavior data sequence, actual operational behavior features reflecting the scheduling execution quality are extracted. The actual operational behavior features are then matched and compared item by item with the scheduling confidence score calculated before intelligent scheduling to determine the deviation relationship between the scheduling confidence score and the actual operational behavior. Based on the deviation relationship results, the parameters of the behavioral change amplitude, direction and persistence characteristics in the task convergence feature set are corrected, and the time offset interval and difference level identifier of the state synchronization offset are updated at the same time to realize the dynamic control of the task convergence feature set and the state synchronization offset in the subsequent intelligent scheduling process.

Images