AI-based laboratory equipment scheduling optimization method and system

By acquiring real-time equipment status monitoring data and dynamic resource allocation models, a laboratory equipment scheduling strategy is generated, which solves the problems of resource fragmentation and task conflict in traditional scheduling methods, and realizes efficient utilization of laboratory resources and optimization of task response.

CN121212663APending Publication Date: 2025-12-26SHANGHAI SUNGIANT INFORMATION TECH CO LTD
View PDF 0 Cites 12 Cited by

Patent Information

Application Number
CN202511339155.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-09-18
Publication Date
2025-12-26

AI Technical Summary

Technical Problem

Traditional laboratory equipment scheduling methods cannot be optimized in real time based on dynamic constraints such as equipment load fluctuations, maintenance cycles, and compatibility, resulting in frequent resource fragmentation and task conflicts, and scheduling efficiency drops significantly with environmental changes.

Method used

By acquiring real-time equipment status monitoring data, we generate equipment availability assessment indicators and experimental task priority queues. We then use a dynamic resource allocation model to perform cross-decision analysis, generate equipment scheduling strategies, and calibrate and iteratively update them in real time to adapt to changes in the laboratory environment.

Benefits of technology

It has improved the efficiency of laboratory resource utilization, optimized task execution performance, and enabled equipment scheduling strategies to evolve adaptively, maximizing resource utilization, optimizing task response time, and reducing equipment wear and tear.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121212663A_ABST
    Figure CN121212663A_ABST
Patent Text Reader

Abstract

The invention provides an AI-based laboratory equipment scheduling optimization method and system, and the method comprises the steps: firstly obtaining a state monitoring data set containing the characteristics of equipment operation power consumption, idle time length, environment interference factors and the like in real time, and then carrying out the multi-dimensional analysis of the state monitoring data set; generating an availability evaluation index set containing characteristics of equipment load fluctuation, maintenance period prediction, compatibility matching and the like, and an experiment task priority queue, performing cross decision analysis on the availability evaluation index set and the experiment task priority queue based on a preset dynamic resource allocation model, and obtaining a scheduling strategy set containing a task allocation path, a cooperative operation rule and a conflict resolution mechanism; scheduling strategy parameters are calibrated according to experimental task operation log data, an optimized execution instruction set is generated, instructions are fed back to an equipment control system to adjust the equipment state, a dynamic resource allocation model is iteratively updated according to execution feedback data, and efficient scheduling optimization of laboratory equipment is achieved.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, in particular to a laboratory equipment scheduling optimization method and system based on AI. BACKGROUND

[0002] In the field of laboratory management, with the continuous improvement of the complexity of scientific research experiments and the rapid development of equipment intelligence, the traditional laboratory equipment scheduling method has been difficult to meet the efficient, accurate and adaptive scheduling requirements.

[0003] In the prior art, laboratory equipment scheduling mainly relies on manual experience or static allocation strategies based on simple rules, which has significant technical limitations: first, the task and resource matching mechanism is rigid, traditional methods mostly use fixed priority allocation or polling scheduling mode, which cannot be optimized in real time according to dynamic constraint conditions such as device load fluctuation characteristics, maintenance cycle prediction and device compatibility, which is easy to cause resource fragmentation and frequent task conflicts; second, the scheduling strategy lacks dynamic evolution ability, and once the existing scheduling scheme is generated, it is fixedly executed, and cannot be combined with the actual progress of the experimental task and the device execution feedback to perform parameter calibration and strategy iteration, resulting in a significant decrease in scheduling efficiency with changes in the experimental environment. SUMMARY

[0004] In view of the above-mentioned problems, in combination with the first aspect of the present application, the embodiments of the present application provide a laboratory equipment scheduling optimization method based on AI, which comprises: real-time acquisition of a set of state monitoring data of laboratory equipment, the set of state monitoring data comprising device running power consumption characteristics, device idle time characteristics and device environmental interference factor characteristics; multi-dimensional demand analysis processing of the set of state monitoring data to generate a set of device availability evaluation indexes and a priority queue of experimental tasks, the set of device availability evaluation indexes comprising device load fluctuation characteristics, device maintenance cycle prediction characteristics and device compatibility matching characteristics; based on a preset dynamic resource allocation model, cross-decision analysis processing of the set of device availability evaluation indexes and the priority queue of experimental tasks to generate a set of laboratory equipment scheduling strategies, the set of laboratory equipment scheduling strategies comprising device task allocation path, device cooperative operation rule and device conflict resolution mechanism; dynamic parameter calibration processing of the set of laboratory equipment scheduling strategies according to a set of real-time updated experimental task operation log data to generate a set of optimized device scheduling execution instructions; feedback of the set of optimized device scheduling execution instructions to a laboratory equipment control system to trigger device running state adjustment operations, and iterative updating of the dynamic resource allocation model based on a set of device execution feedback data.

[0005] In still another aspect, the embodiments of the present application also provide a laboratory equipment control system, comprising a processor, a machine readable storage medium, the machine readable storage medium being connected with the processor, the machine readable storage medium being used for storing programs, instructions or codes, and the processor being used for executing the programs, instructions or codes in the machine readable storage medium to realize the method described above.

[0006] Based on the above aspects, the embodiments of the present application realize intelligent management of the whole link from data acquisition to policy execution, and significantly improve the utilization efficiency of laboratory resources and the execution performance of tasks. Specifically, by collecting multi-dimensional state data such as equipment running power consumption, idle time and environmental interference in real time, combined with multi-dimensional demand analysis algorithm, not only the dynamic characteristics of equipment load, maintenance cycle law and cross-platform compatibility are accurately described, but also a scientific and quantitative experimental task priority sequence is generated, providing a two-dimensional decision benchmark for resource allocation. On this basis, the dynamic resource allocation model analyzes the coupling of equipment availability index and task priority through cross decision mechanism, generates a three-dimensional scheduling scheme including task allocation path planning, multi-device collaboration rules and conflict resolution strategy, effectively solving the problems of resource fragmentation and frequent task conflicts in traditional scheduling methods. Further, the real-time log-driven dynamic calibration mechanism can automatically correct the scheduling parameters according to the actual progress of the experimental process, ensuring the high adaptation of the policy and the execution environment. Finally, through the closed-loop feedback and model iterative update of the equipment control system, a data-driven policy optimization flywheel effect is formed, so that the equipment scheduling policy can adaptively evolve with the laboratory running situation, realizing the maximization of resource utilization, the optimization of task response time and the minimization of equipment loss in the global level. BRIEF DESCRIPTION OF DRAWINGS

[0007] Figure 1 is the execution flow diagram of the AI-based laboratory equipment scheduling optimization method provided by the embodiments of the present application.

[0008] Figure 2 is a schematic diagram of exemplary hardware and software components of the laboratory equipment control system provided by the embodiments of the present application. DETAILED DESCRIPTION

[0009] The present application will be described in detail below with reference to the accompanying drawings, Figure 1 is a flow diagram of the AI-based laboratory equipment scheduling optimization method provided by an embodiment of the present application, which will be described in detail below.

[0010] Step S110: Real-time acquisition of a set of state monitoring data of the laboratory equipment, the set of state monitoring data comprising equipment running power consumption features, equipment idle duration features, and equipment environmental interference factor features.

[0011] In the biochemical laboratory scenario, to achieve intelligent scheduling optimization of laboratory equipment, the first step is to comprehensively and continuously collect data on the real-time running state of the equipment. The set of state monitoring data needs to cover equipment running power consumption features that can reflect the power consumption of the equipment, equipment idle duration features that reflect the regularity of the time period when the equipment is not used, and equipment environmental interference factor features that affect the normal operation of the equipment.

[0012] Step S111: Deploy a multi-modal sensor group in each laboratory equipment to real-time collect equipment current fluctuation data, equipment temperature change data, and equipment mechanical vibration data.

[0013] For various types of key equipment in the biochemical laboratory, such as high-performance liquid chromatographs, polymerase chain reaction instruments, high-speed refrigerated centrifuges, and biological safety cabinets, a multi-modal sensor group is deployed at a specific functional module of each equipment. A current sensor is installed at the input end of the main power supply line of the equipment to monitor the current fluctuation of the equipment in different working stages (such as starting, running, standby, and shutdown); a temperature sensor is arranged in the core working area of the equipment, such as the heating module of the polymerase chain reaction instrument, the column oven of the high-performance liquid chromatograph, and the rotor warehouse of the high-speed refrigerated centrifuge, to capture the temperature change during the operation of the equipment; a mechanical vibration sensor is fixed at the position of the equipment with moving parts, such as the motor seat of the high-speed refrigerated centrifuge and the pump head of the liquid pump of the high-performance liquid chromatograph, to collect the mechanical vibration signals generated during the operation of the equipment. The above sensors are connected to the distributed data acquisition system inside the laboratory through a dedicated data transmission line to ensure the real-time and stability of the collected data.

[0014] Step S112: Power consumption mode recognition processing is performed on the equipment current fluctuation data to extract equipment running power consumption features, the equipment running power consumption features comprising equipment startup phase power consumption peak, equipment steady-state running power consumption mean, and equipment abnormal power consumption fluctuation period.

[0015] The collected equipment current fluctuation data is first preprocessed, including removing noise and outliers introduced in the data transmission process. Subsequently, based on time series analysis method, the power consumption mode of the preprocessed current fluctuation data is identified. The entire running cycle of the equipment is divided into different stages. In the starting stage, by analyzing the current change curve with time, the power consumption value corresponding to the maximum current in this stage is determined, that is, the power consumption peak value in the starting stage of the equipment; when the equipment enters the stable running stage, the average value of the current fluctuation data in this stage is calculated, and combined with the rated working voltage of the equipment, the average power consumption of the equipment in the stable running state is converted, that is, the average power consumption of the equipment in the stable running state; for the extraction of the abnormal power fluctuation period of the equipment, the long-time-scale current fluctuation data is analyzed by spectrum analysis, the abnormal fluctuation signals with non-periodic and amplitude exceeding the normal fluctuation range are identified, and the time interval law of the appearance of these abnormal fluctuation signals is determined, that is, the abnormal power fluctuation period of the equipment.

[0016] Step S113: idle interval analysis processing is performed on the laboratory equipment operation record data to extract equipment idle duration features, and the equipment idle duration features include equipment single idle start time stamp, equipment continuous idle interval duration and equipment historical idle frequency distribution.

[0017] The equipment operation record data is called from the laboratory equipment management system, which records the start time and end time of each use of each equipment. The operation record data of a single equipment is sorted in chronological order, and then the sorted record is traversed to identify the time interval between the adjacent two use records. When the length of a certain time interval exceeds the set threshold value (which is determined according to the type of equipment and the routine operation process of the laboratory), it is determined that the equipment is in an idle state. The specific time point when the idle state starts, i.e. the equipment single idle start time stamp, is recorded; the duration from the start of the idle state to the start of the next use, i.e. the equipment continuous idle interval duration, is calculated. In order to extract the equipment historical idle frequency distribution, all idle interval duration data of the equipment in the past period (such as one month) is collected, and the above data is grouped according to certain time interval, and the number of idle events in each interval is counted, so as to form the equipment historical idle frequency distribution.

[0018] Step S114: calling the environment monitoring device to obtain the temperature and humidity data, electromagnetic interference data and equipment spacing data in the laboratory space, extracting the equipment environment interference factor features, and the equipment environment interference factor features include the influence coefficient of temperature and humidity on equipment precision, the electromagnetic interference intensity threshold and the equipment signal conflict probability.

[0019] The distributed environment monitoring devices are pre-deployed in the laboratory space, including an array of temperature and humidity sensors, an electromagnetic interference detector, and a device positioning system based on ultrasonic ranging. By calling the interfaces of these environment monitoring devices, real-time temperature and humidity data in different areas of the laboratory, electromagnetic interference data in different frequency bands, and relative position data (i.e., device spacing data) between devices are obtained. For the influence coefficient of temperature and humidity on device accuracy, the function relationship between temperature and humidity and measurement results provided in the device technical manual is analyzed, and the current collected temperature and humidity data are combined to calculate the influence coefficient; the electromagnetic interference strength threshold is determined according to the electromagnetic environment requirements for normal operation of the device, referring to relevant national standards and parameters provided by the device manufacturer; the calculation of the device-to-device signal conflict probability considers the communication mode (such as wireless, wired), working frequency, transmission power, and device spacing data of the device, and estimates through the establishment of a device-to-device signal propagation model.

[0020] Step S115: Align and merge the device running power consumption features, the device idle duration features, and the device environmental interference factor features according to the time window to generate a state monitoring data set.

[0021] The extracted device running power consumption features, device idle duration features, and device environmental interference factor features are uniformly aligned in the time dimension. A fixed-length time window (such as 10 minutes as a time window) is set, and each feature data is divided into the corresponding time window. For the device startup phase power consumption peak value and the device abnormal power consumption fluctuation period in the device running power consumption feature, record whether it appears in each time window and the specific feature value when it appears; for the device steady-state running power consumption average value, calculate the average value in each time window; the data in the device idle duration feature is attributed to the corresponding time window according to its timestamp; the device environmental interference factor feature takes the average value or feature value in each time window. After completing the time window alignment, the three types of feature data in the same time window are merged according to the preset data structure to form the state monitoring data segment corresponding to the time window. All time window state monitoring data segments are arranged in chronological order to finally generate a complete state monitoring data set.

[0022] Step S120: Perform multi-dimensional demand analysis processing on the state monitoring data set to generate a device availability evaluation index set and an experimental task priority queue, the device availability evaluation index set including device load fluctuation features, device maintenance cycle prediction features, and device compatibility matching features.

[0023] After obtaining the state monitoring data set, the current and to-be-executed experimental task information of the laboratory is combined for comprehensive analysis and processing from multiple dimensions such as equipment capacity, task demand, environmental influence, etc. On the one hand, based on the state monitoring data set, the availability of the equipment in the current and future period of time is evaluated, and a set of equipment availability evaluation indexes including equipment load fluctuation characteristics, equipment maintenance cycle prediction characteristics, and equipment compatibility matching characteristics are generated. On the other hand, according to the emergency degree, importance, resource demand and other factors of the experimental task, all to-be-executed experimental tasks are sorted, and an experimental task priority queue is generated.

[0024] Step S121: Analyzing the task attribute parameters in the experimental task request data set, extracting task device dependency characteristics, task emergency level labels and task resource consumption estimation characteristics.

[0025] The experimental task request data set from the laboratory information management system is received, which contains detailed information of multiple to-be-executed experimental tasks. Each experimental task request data is parsed to extract the task attribute parameters. The task device dependency characteristics are determined by analyzing the experimental scheme and operation process of the experimental task, which clearly indicates the type, quantity and usage order and dependency relationship of the equipment needed in the task execution process; the task emergency level label is divided according to the deadline of the experimental task, the priority of the project, whether it is an emergency repair or an emergency experiment, etc. Factors, usually divided into multiple levels (such as very high, high, medium, low); the task resource consumption estimation characteristics are based on the execution data of the historical similar experimental tasks, combined with the scale and experimental scheme of the current experimental task, to estimate the power resources, consumable resources and time resources consumed in the execution process of the task.

[0026] Step S122: According to the matching degree calculation of the equipment running power consumption characteristics and the task resource consumption estimation characteristics, the equipment load fluctuation characteristics are generated, which include the power consumption increment prediction value of the task superposition execution, the maximum load safety threshold of the equipment and the task interruption risk level.

[0027] The device steady-state running power consumption mean value in the device running power consumption feature is matched with the power resource consumption estimation in the task resource consumption estimation feature. First, the power consumption demand curve during execution of a single task is determined according to the task resource consumption estimation feature. When multiple tasks need to be executed on the same device (such as serial execution or parallel execution), the power consumption demand curves of the tasks are superimposed to predict the total power consumption after superposition and the change of the total power consumption with time, and the power consumption increment prediction value during execution of the tasks in superposition is extracted, that is, the power consumption increment prediction value. The device maximum load safety threshold is determined according to the hardware parameters, heat dissipation capacity and safety operation procedures of the device, so as to ensure that the device does not break down or cause safety accidents when running within the load range. The relationship between the power consumption increment prediction value during execution of the tasks in superposition and the device maximum load safety threshold, the frequency of occurrence of the device abnormal power fluctuation period and the historical running stability data of the device are comprehensively considered to evaluate the task interruption risk level, and the task interruption risk level is divided into different grades.

[0028] Step S123: Maintenance cycle prediction is performed based on the device maintenance historical data and the device idle duration feature, and a device maintenance cycle prediction feature is generated, which includes a remaining maintenance time window, a maintenance operation time consumption estimation and a maintenance period task migration path.

[0029] The maintenance historical data of the device is obtained from the device management system, including the time, type, content and duration of each past maintenance. The relationship between the use frequency, use intensity and maintenance cycle of the device is analyzed in combination with the device idle duration feature in the state monitoring data set. A time series prediction model is used to predict the time point of the next preventive maintenance of the device based on the historical maintenance records of the device and the recent idle duration feature data. The time interval between the current time and the predicted time point is the remaining maintenance time window. The maintenance operation time consumption estimation is estimated according to the time consumption data of the same type of historical maintenance operation in combination with the running state of the current device and the possible maintenance content. For the experimental tasks originally planned to be executed on the device during the maintenance period, the paths of these tasks to be transferred to other available devices for execution, i.e. the maintenance period task migration path, are planned according to the remaining maintenance time window and the time requirements of the tasks, as well as the idle duration features of other devices and the device availability evaluation indexes.

[0030] Step S124: Compatibility matching analysis is performed according to the device environment interference factor feature and the task precision requirement data to generate a device compatibility matching feature, which includes an environmental interference tolerance score, a device precision calibration capability index and a task result error estimation range.

[0031] Task precision requirement data of each experimental task is acquired, which specifies precision indexes of the experimental task on measurement results, reaction conditions, etc. The influence coefficient of temperature and humidity in the equipment environment interference factor feature on equipment precision, the electromagnetic interference intensity threshold, and the task precision requirement data are compared and analyzed. The environmental interference tolerance score is determined by calculating the ratio between the influence degree of the current environmental interference factor (temperature and humidity, electromagnetic interference) on the equipment precision and the task precision requirement. The higher the score, the stronger the ability of the equipment to meet the task precision requirement under the current environment. The equipment precision calibration capability index is evaluated according to the precision calibration function, calibration frequency, and accuracy of historical calibration data possessed by the equipment, reflecting the ability of the equipment to maintain precision by self-calibration when affected by environmental interference. The task result error estimation range is based on the environmental interference tolerance score and the equipment precision calibration capability index, combined with the result error data of the equipment executing similar tasks under similar environmental conditions in historical experiments, and the result error interval that may be generated in the execution of the task under the current environmental conditions is estimated by statistical analysis method.

[0032] Step S125: Based on the task urgency label and the laboratory task scheduling rule, priority sorting is performed to generate an experimental task priority queue, and the equipment load fluctuation feature, the equipment maintenance cycle prediction feature, and the equipment compatibility matching feature are merged into a set of equipment availability evaluation indexes.

[0033] According to the task urgency label of the experimental task, all to-be-executed experimental tasks are preliminarily sorted. Then, combined with the task scheduling rules formulated by the laboratory (such as task submission time, task project, task resource demand conflict resolution rules, etc.), the preliminary sorting result is adjusted and optimized. For example, for tasks with the same urgency label, the tasks are sorted according to the order of task submission time; for tasks with resource conflicts, the tasks are coordinated according to the priority and resource demand of the tasks. After sorting, an experimental task priority queue is formed, and the order of the tasks in the queue represents the execution priority of the tasks. At the same time, the generated equipment load fluctuation feature, equipment maintenance cycle prediction feature, and equipment compatibility matching feature are integrated according to a preset data format to form a set of equipment availability evaluation indexes, which comprehensively reflect the availability of the equipment in terms of load capacity, maintenance demand, and environmental compatibility.

[0034] Step S130: Based on a preset dynamic resource allocation model, cross-decision analysis processing is performed on the set of equipment availability evaluation indexes and the experimental task priority queue to generate a set of laboratory equipment scheduling strategies, which includes equipment task allocation path, equipment cooperative operation rule, and equipment conflict resolution mechanism.

[0035] The preset dynamic resource allocation model is a deep learning-based decision model, which has been trained by historical scheduling data and simulation data. The device availability evaluation index set and the experimental task priority queue are input into the dynamic resource allocation model as input data. The model first performs feature fusion on the two types of input data, then performs cross-decision analysis through a multi-layer neural network, and comprehensively considers the priority of the task, the availability of the device, the load fluctuation, the maintenance period, the compatibility and other factors, and finally generates a laboratory device scheduling strategy set containing device task allocation path, device cooperative operation rule and device conflict resolution mechanism.

[0036] Step S131: Bidirectional matching degree calculation is performed between each task in the experimental task priority queue and the corresponding device in the device availability evaluation index set, and a task-device matching matrix is generated, which contains task execution success rate score, device utilization rate improvement coefficient and task conflict detection result.

[0037] For each task in the experimental task priority queue, bidirectional matching degree calculation is performed with each device in the device availability evaluation index set. In the calculation process, multiple dimensional factors are considered. The task execution success rate score is obtained by analyzing the matching degree between the device compatibility matching characteristics of the device (environmental interference tolerance score, device precision calibration ability index), the device load fluctuation characteristics (power consumption increment prediction value when the task is executed in a stacked manner, device maximum load safety threshold) and the task resource consumption estimation characteristics, task precision requirement data, and combining the success rate data of the device in executing similar tasks; the device utilization rate improvement coefficient is calculated according to the time resource estimation in the device idle time characteristics (continuous idle interval time of the device, historical idle frequency distribution of the device) and the task resource consumption estimation characteristics, and the reduction proportion of the idle time of the device and the increase proportion of the use time of the device after the task is allocated to the device, so as to obtain the improvement degree of the utilization rate of the device; the task conflict detection result is determined by checking whether the execution time window of the task overlaps with the time window of the device allocated task, whether the load capacity of the device can meet the power consumption increment prediction value when the task is executed in a stacked manner, etc. The bidirectional matching degree calculation results of all tasks and devices are organized in matrix form, with rows representing experimental tasks and columns representing devices. Each element in the matrix contains the corresponding task execution success rate score, device utilization rate improvement coefficient and task conflict detection result, i.e. a task-device matching matrix is generated.

[0038] Step S132: According to the device maintenance period prediction characteristics, the maintenance window constraint processing is performed on the task-device matching matrix, and the device task allocation path is generated, which contains the task execution sequence before maintenance, the task migration path during maintenance and the device restart strategy after maintenance.

[0039] On the basis of the task-device matching matrix, the maintenance window constraint processing is performed in combination with the device maintenance period prediction features in the device availability evaluation index set. For each device, according to the remaining maintenance time window, the tasks that can be performed before the start of the maintenance operation are determined. From the task-device matching matrix, the tasks that have a higher matching degree with the device and can be completed within the remaining maintenance time window are selected, and are sorted according to the order of the experimental task priority queue and the execution time requirement of the tasks to generate a pre-maintenance task execution sequence. For those tasks that are originally planned to be executed on the device during the device maintenance, according to the task migration path during the maintenance, other available devices with a higher matching degree are selected from the task-device matching matrix for reallocation. At the same time, a post-maintenance device restart strategy is formulated, including the start time point, start sequence, self-checking process of the device after the completion of the maintenance, and the sequence and manner of task recovery execution, to ensure that the device can quickly and accurately recover to the normal working state after the maintenance and continue to execute the unfinished tasks. Through the above processing, a complete device task allocation path is finally generated.

[0040] Step S133: performing resource conflict detection on multiple tasks executed in the same period based on the device compatibility matching features, generating a device collaborative operation rule, the device collaborative operation rule including a device shared use time slice rule, a device mutual exclusion use condition judgment rule, and a device grouping collaborative operation protocol.

[0041] The environmental interference tolerance score and the signal conflict probability between devices in the device compatibility matching features are analyzed, and the possible resource conflict situations when multiple tasks executed in the same time period use devices are identified. For devices that can be shared (such as some public detection instruments), according to the execution time and resource requirements of the tasks, the use time of the device is divided into multiple time slices, each time slice is allocated to a task for use, and a device shared use time slice rule is generated to clearly define the use time period and length of each task. For devices that cannot be used at the same time due to working principle or accuracy requirements, a device mutual exclusion use condition judgment rule is formulated to specify the conditions under which the device cannot be used by multiple tasks at the same time, as well as the conflict judgment standard and priority order when a task applies for using the device. For complex tasks that require multiple devices to work collaboratively, a device grouping collaborative operation protocol is formulated, which clearly defines the composition of the device group participating in collaborative work, the roles and responsibilities of each device, the data transmission method and protocol between devices, the synchronization mechanism of the working state, and the error handling and recovery mechanism during the collaborative work process, to ensure that the devices can efficiently and orderly collaborate.

[0042] Step S134: When a task resource conflict is detected, a conflict resolution strategy is generated according to the task urgency label and the device load fluctuation feature, and a device conflict resolution mechanism is generated, which includes a task execution order adjustment strategy, a device backup node switching strategy, and a task resource dynamic reallocation strategy.

[0043] In the task execution process, by monitoring the resource usage of the task and the state of the device in real time, when a task resource conflict (such as multiple tasks simultaneously applying for the use of the same device, the device load exceeding the maximum load safety threshold, etc.) is detected, the conflict resolution strategy process is started. First, according to the task urgency label of the conflict task, the priority order of the task is determined. For tasks with high priority, the task execution order adjustment strategy can be used to suspend or delay the execution of tasks with low priority, and after the high-priority task is completed, the execution is resumed, and the execution time window of the related task needs to be updated. If the conflict is caused by high device load, and there is a backup device node (other devices with the same or similar functions as the conflict device), the device backup node switching strategy is used to switch part of the task to the backup device for execution, and the load capacity and task matching degree of the backup device need to be re-evaluated. For some tasks that can dynamically adjust resource requirements, the task resource dynamic reallocation strategy is used to reallocate the resources of the device (such as adjusting the execution parameters of the task to reduce power consumption) according to the current load of the device and the actual requirements of the task, in order to alleviate the resource conflict. Through the above decision-making process, a device conflict resolution mechanism containing multiple strategies is generated.

[0044] Step S135: The device task allocation path, the device cooperative operation rule, and the device conflict resolution mechanism are encapsulated according to the decision-making level to generate a laboratory device scheduling strategy set.

[0045] The generated device task allocation path, device cooperative operation rule, and device conflict resolution mechanism are encapsulated according to the decision-making level. The device task allocation path serves as the basic level, which specifies the specific execution path and time arrangement of each task on the device; the device cooperative operation rule serves as the intermediate level, which is used to standardize the behavior and interaction mode of multiple devices when working cooperatively; and the device conflict resolution mechanism serves as the highest level, which provides solutions and decision-making basis when resource conflicts occur. In the encapsulation process, each level of strategy is given corresponding priority and execution conditions to ensure that in the actual execution process, the corresponding strategy can be triggered in the correct order and condition. The above encapsulated strategies are integrated into a unified data structure to generate a laboratory device scheduling strategy set, which can completely guide the scheduling and operation of laboratory devices.

[0046] Step S140: According to the real-time updated experimental task operation log data set, the dynamic parameter calibration processing is performed on the laboratory equipment scheduling strategy set, and an optimized equipment scheduling execution instruction set is generated.

[0047] In the execution process of the laboratory equipment scheduling strategy set, the laboratory information management system records the operation log data of the experimental task in real time to form a real-time updated experimental task operation log data set. The experimental task operation log data set contains the actual start time, actual end time, actual running parameters of the equipment, and abnormal event records during task execution. According to these real-time updated data, the parameters in the laboratory equipment scheduling strategy set are dynamically calibrated. By comparing the deviation between the actual execution result and the expected result of the strategy, the causes of the deviation (such as inaccurate task execution time estimation, equipment load capacity estimation deviation, environmental interference factor change, etc.) are analyzed, and the related parameters in the strategy (such as task execution time window, equipment load threshold, equipment matching degree weight, etc.) are adjusted and optimized, and finally an optimized equipment scheduling execution instruction set is generated.

[0048] Step S141: Real-time collection of equipment response delay data, task progress deviation data and equipment abnormal alarm data during task execution, and generation of task execution state monitoring data stream.

[0049] In the process of task execution, through the deployment of monitoring nodes in the equipment control system and laboratory network, a variety of state data are collected in real time. The equipment response delay data is the time interval from sending the task execution instruction to the equipment starting to execute the instruction, which is calculated by recording the instruction sending time and the actual start time of the equipment; the task progress deviation data is the difference between the current actual execution progress and the planned execution progress of the task, which is calculated by comparing the actual completed work quantity with the planned completed work quantity, and the work quantity can be measured by the number of completed key steps, the proportion of consumed time, etc.; the equipment abnormal alarm data is various abnormal signals generated by the equipment during operation, such as temperature exceeding the set range, pressure abnormality, motor failure, communication interruption, etc., which are directly generated by the built-in sensors and monitoring system of the equipment. The collected equipment response delay data, task progress deviation data and equipment abnormal alarm data are continuously transmitted to the data processing center in chronological order to form a continuous task execution state monitoring data stream.

[0050] Step S142: Deviation comparison between the task execution state monitoring data stream and the preset execution parameters in the laboratory equipment scheduling strategy set to identify the equipment scheduling deviation type, which includes equipment response timeout deviation, task resource allocation insufficient deviation and equipment performance degradation deviation.

[0051] The real-time data in the task execution state monitoring data stream is compared with the preset execution parameters in the laboratory equipment scheduling strategy set one by one. For the equipment response delay data, it is compared with the preset equipment response delay threshold value, and if the actual response delay exceeds the threshold value, it is identified as an equipment response timeout deviation; for the task progress deviation data, it is compared with the preset task progress deviation allowed range, and if the actual progress deviation exceeds the range, the deviation reason is further analyzed, and if the progress lags due to the fact that the resources (such as power, time, and consumables) allocated during the task execution process cannot meet the task demand, it is identified as a task resource allocation insufficient deviation; and the equipment abnormal alarm data and the long-term running data of the equipment are analyzed, and if the running performance indicators (such as processing speed, accuracy, and stability) of the equipment gradually decrease with the increase of the use time, resulting in the decrease of the task execution efficiency or the decrease of the task result quality, it is identified as an equipment performance degradation deviation. Through the above comparison and analysis, the deviation types occurring in the equipment scheduling process are accurately identified.

[0052] Step S143: According to the equipment maintenance period prediction feature, the root cause of the equipment performance degradation deviation is analyzed, and equipment performance calibration parameters are generated, which include equipment driving parameter adjustment amplitude, equipment working mode switching threshold, and equipment standby component enabling condition.

[0053] For the identified equipment performance degradation deviation, the root cause analysis is performed in combination with the equipment maintenance period prediction features in the equipment availability evaluation index set. The maintenance history data of the equipment is consulted, the performance change law of the equipment at different use stages is analyzed, and the specific reasons (such as key component wear, circuit aging, and software parameter drift) causing the performance degradation are determined in combination with the current equipment performance degradation performance. According to the root cause analysis result, the equipment performance calibration parameters are generated. The equipment driving parameter adjustment amplitude is determined according to the degree of equipment performance degradation and the control model of the equipment, such as adjusting the driving current of the motor and adjusting the power output of the heating module, so as to compensate for the influence of performance degradation; the equipment working mode switching threshold is determined according to the best working range after the performance degradation of the equipment, and when the load or running environment parameter of the equipment reaches the threshold value, the working mode is automatically switched to the working mode (such as from high-speed mode to medium-speed mode) more suitable for the current performance state; and the equipment standby component enabling condition is used to determine that the standby component (such as a standby sensor and a standby motor) of the equipment needs to be enabled under a certain degree of performance degradation or a certain fault mode, so as to restore the normal performance of the equipment.

[0054] Step S144: Based on the task progress deviation data, the equipment task allocation path is real-time re-planned, and a dynamic task allocation patch is generated, which includes task execution time window adjustment instructions, equipment load rebalancing strategies, and task dependency relationship reconstruction rules.

[0055] According to the task execution state monitoring data flow, the task progress deviation data is monitored, and real-time re-planning processing is performed on the device task allocation path. If the task progress lags behind the planned progress, and the lagging reason is that the task execution time estimation is insufficient, a task execution time window adjustment instruction is generated, the execution time window of the task is extended, and the time arrangement of the subsequent tasks is adjusted accordingly; if the task progress deviation is caused by uneven device load allocation, which leads to excessive load on part of the devices and idle on part of the devices, a device load rebalancing strategy is developed, part of the tasks on the heavily loaded devices are migrated to the idle devices for execution, and the migration needs to refer to the task-device matching matrix and the device availability evaluation index; for the case where there is a task dependency relationship (such as task B must start after task A is completed), if the progress of the preceding task A deviates, affecting the execution of the subsequent task B, the task dependency relationship is reconstructed, and a task dependency relationship reconstruction rule is generated, such as allowing task B to start in advance after a certain percentage of task A is completed, or adjusting the execution device of task B to avoid waiting. The above re-planning processing results are integrated to generate a dynamic task allocation patch.

[0056] Step S145: The device performance calibration parameters and the dynamic task allocation patch are classified and integrated according to the device nodes to generate an optimized device scheduling execution instruction set, and a laboratory device control system execution instruction verification operation is triggered.

[0057] The generated device performance calibration parameters and dynamic task allocation patch are classified and integrated according to the device nodes. For each device, collect the device driving parameter adjustment amplitude, the device working mode switching threshold, the device standby component enabling condition (device performance calibration parameters) related to it, and the part of the task execution time window adjustment instruction involving the device, the new task allocated to the device or the task migrated out of the device in the device load rebalancing strategy, and the task dependency adjustment related to the device in the task dependency relationship reconstruction rule (dynamic task allocation patch). Convert the above information into an instruction format that can be recognized and executed by the device, and each instruction contains information such as instruction type, target parameter, adjustment value, execution time, etc. Organize the instructions of all devices according to the device number and the instruction execution order to generate an optimized device scheduling execution instruction set. Before the instruction set is issued to the laboratory device control system, trigger the instruction verification operation to check the integrity, correctness, rationality of the instructions and whether there is a conflict between the instructions, to ensure that the instructions can be accurately and safely executed by the device.

[0058] Step S150: The optimized device scheduling execution instruction set is fed back to the laboratory device control system to trigger a device running state adjustment operation, and the dynamic resource allocation model is iteratively updated based on the device execution feedback data set.

[0059] The optimized device scheduling execution instruction set is transmitted to the laboratory device control system through a secure communication protocol. After receiving the instruction set, the laboratory device control system parses and verifies each instruction, and then controls the corresponding device to perform the operation state adjustment operation according to the instruction requirements, such as adjusting the operating parameters of the device, changing the working mode of the device, starting or stopping a certain functional module of the device, migrating tasks between devices, etc. During the execution of the adjustment operation of the device, the actual execution data of the device, the completion of the task, the change of the running state of the device, etc. are continuously collected to form a device execution feedback data set. The preset dynamic resource allocation model is iteratively updated using the device execution feedback data set, the actual execution result is compared with the model prediction result, the prediction error is calculated, and the weight parameters and decision logic of the model are adjusted through the back propagation algorithm, so that the model can better adapt to the actual situation of the laboratory device and task, and the accuracy and optimization degree of the subsequent scheduling strategy are improved.

[0060] Step S151: Analyzing the device driving parameter adjustment instructions in the optimized device scheduling execution instruction set, generating a device control signal sequence, the device control signal sequence including motor speed regulation instructions, temperature control module set value update instructions, and safety protection device trigger conditions.

[0061] The optimized device scheduling execution instruction set is parsed, and the instructions related to device driving parameter adjustment are extracted. According to the type and control mode of the device, the above instructions are converted into specific device control signals. For devices containing motors (such as centrifuges, mixers, pumps), according to the motor speed adjustment amplitude in the device driving parameter adjustment instruction, a motor speed regulation instruction is generated to clearly define the target speed, speed change rate, and holding time after reaching the target speed of the motor; for devices with temperature control modules (such as PCR instruments, incubators, column temperature boxes), according to the adjustment requirements of the temperature control parameters, a temperature control module set value update instruction is generated, including target temperature value, temperature rise / drop rate, temperature stabilization time, etc. parameters; at the same time, in order to ensure the safety of device operation, according to the safety operation procedures of the device and the safety threshold in the device driving parameter adjustment instruction, the safety protection device trigger conditions are generated, such as triggering the corresponding safety protection device (such as power off, stop heating, alarm) when the device temperature exceeds a certain upper limit value, the motor current is too large, or the pressure is abnormal. The above control signals are organized into a device control signal sequence according to the time sequence and logical relationship.

[0062] Step S152: According to the device cooperative operation rules, the control signals of multiple devices are processed in time sequence, and a device cooperative control time sequence table is generated, which includes device start interval duration, signal transmission delay compensation value, and device state verification time point.

[0063] For the case that multiple devices need to work together to complete an experimental task, the control signals of multiple devices participating in collaborative work are processed in time sequence according to the device collaborative operation rules in the laboratory device scheduling strategy set. First, the starting order of each device is determined, and the time interval between the start of adjacent devices, i.e. the device start interval, is calculated according to the dependence relationship between the devices and the task execution process, to ensure that the next device starts after the previous device is ready. Considering that there may be a delay in the transmission of control signals in the laboratory network, the transmission delay time of the signal from the sending end to the receiving end is calculated as the signal transmission delay compensation value according to the transmission speed of the network, the distance between the devices and the signal transmission protocol, and the transmission delay time of the signal from the sending end to the receiving end. The sending time of the control signal is adjusted to ensure that each device can receive the control signal at the predetermined time point and perform the corresponding operation. At the same time, the device state checking time point is set, and during the collaborative work, the running state of each device is checked regularly (such as every certain time or after the completion of a key operation step) to ensure that the actual state of the device is consistent with the requirements of the control signal. The device start interval, signal transmission delay compensation value and device state checking time point are integrated to generate a device collaborative control time sequence table.

[0064] Step S153: Before performing the device running state adjustment operation, the device pre-check module is called to perform compatibility check on the current state of the target device and the required state of the instruction, and a device instruction execution readiness state report is generated.

[0065] Before performing the device running state adjustment operation, the laboratory device control system calls the device pre-check module. The device pre-check module communicates with the control system of the target device to obtain the current state parameters of the target device, such as current temperature, pressure, speed, working mode, loaded program, available memory, consumable amount, etc. The obtained current state parameters are checked for compatibility with the required target state parameters in the optimized device scheduling execution instruction set. Check whether the current hardware conditions of the device meet the requirements of the instruction (such as whether the device model matches, whether the hardware configuration is sufficient), whether the current running state of the device allows state adjustment (such as whether it is in a busy state, whether there are unfinished tasks), whether the consumables and resources of the device are sufficient (such as whether the reagent is sufficient, whether the storage space is sufficient), whether the safety interlock device of the device is normal, etc. According to the results of the compatibility check, a device instruction execution readiness state report is generated to clearly indicate whether the target device is ready for the device running state adjustment operation, and if not, what incompatible problems and reasons exist.

[0066] Step S154: When the device instruction execution readiness state report shows an abnormality, the standby device switching process is started according to the device conflict resolution mechanism, and a device fault emergency scheduling instruction is generated.

[0067] If the device instruction execution readiness state report shows that the target device has abnormal conditions (such as hardware failure, resource shortage, state incompatibility, etc.), and cannot perform the device running state adjustment operation, the laboratory equipment control system will start the standby device switching process according to the device conflict resolution mechanism in the laboratory equipment scheduling policy set. First, find a standby device with the same or similar function as the target device from the device availability evaluation index set, and which is currently in an idle or low load state. Perform a quick compatibility and availability check on the standby device to ensure that it can meet the execution requirements of the task. If a suitable standby device is found, generate a device failure emergency scheduling instruction, which contains detailed information such as task identification, task parameters, execution time window, and coordination relationship with other devices for transferring the task originally planned to be executed on the target device to the standby device. At the same time, update the device task allocation path and device coordination control timing table to ensure that the task can be executed smoothly on the standby device and minimize the impact on the experimental progress.

[0068] Step S155: The verified device control signal sequence and the device coordination control timing table are issued to the laboratory equipment control system to trigger the device running state adjustment operation.

[0069] When the device instruction execution readiness state report shows that the target device is ready, or the standby device switching process has been successfully completed, the verified device control signal sequence and the device coordination control timing table are issued to the laboratory equipment control system through a reliable communication link. The laboratory equipment control system sends each control signal in the device control signal sequence to the corresponding device in the order specified in the device coordination control timing table and according to the signal transmission delay compensation value. After receiving the control signal, the device performs the corresponding running state adjustment operation, such as adjusting the motor speed, updating the temperature control module set value, switching the working mode, starting or stopping a specific function, etc. During the device running state adjustment process, the laboratory equipment control system monitors the state changes of the device in real time to ensure that the device can accurately complete the state adjustment according to the instruction requirements.

[0070] Step S156: Collect the actual task completion data, device energy consumption change data, and device abnormal event records after the device executes the optimized device scheduling execution instruction set, and generate a device execution feedback data set.

[0071] After the device executes the optimized device scheduling execution instruction set, various feedback data is collected through the laboratory information management system and the device monitoring system. The actual task completion degree data includes the final completion of the task, such as whether the task is successfully completed, the proportion of the completed task amount to the total task amount, the quality indicators of the task results (such as the accuracy and repeatability of experimental data), and the like; the device energy consumption change data includes the actual power consumption curve of the device during the execution of the instruction, the total energy consumption, the energy consumption distribution of different working stages, and the like, which is calculated by analyzing the current and voltage data; the device abnormal event record includes all abnormal situations occurring during the execution of the instruction, such as slight parameter fluctuation, temporary communication interruption, generation and recovery of alarm signals, device failure shutdown, and the like, and records the time, type, duration, processing method and result of the abnormal event. The actual task completion degree data, device energy consumption change data and device abnormal event record collected above are summarized and arranged to generate a device execution feedback data set.

[0072] Step S1571: Time sequence alignment processing is performed on the device usage records generated during the execution process of the actual task execution path, and the actual device calling sequence, actual task duration and actual device cooperation mode are extracted. The device usage records generated during the execution process of the actual task execution path are exported from the database of the laboratory device management system, which contain the device identification involved in each task execution process, the device calling start time, the device calling end time, the operation steps of the device in the task execution, the data transmission record between devices and the like. Time sequence alignment processing is performed on the above-mentioned device usage records to calibrate all device usage records with a unified time reference (such as laboratory standard time). Then, the key information is extracted from the time sequence aligned device usage records: the actual device calling sequence refers to the order of device calling in the task execution process, which is obtained by arranging the device calling start time in time sequence; the actual task duration refers to the time interval between the calling of the first device and the calling of the last device in the task; the actual device cooperation mode refers to the cooperation mode of multiple devices in executing the same task or related tasks, which is determined by analyzing the calling relationship between devices, data transmission direction and time, operation step cooperation and the like, such as master-slave cooperation, parallel cooperation and pipeline cooperation. Step S1572: The actual device calling sequence is matched with the planned calling sequence in the preset device task allocation path to identify the sequence deviation type, which includes device early calling deviation, device alternative calling deviation and device parallel execution mode deviation. The actual device calling sequence is matched with the planned device calling sequence in the preset device task allocation path. The identification and position of the devices in the actual calling sequence and the planned calling sequence are compared element by element. If the calling time of a device in the actual calling sequence is earlier than the planned calling time of the device in the planned calling sequence and exceeds the allowed early time range, the device early calling deviation is identified. If a device appears in the actual calling sequence but not in the planned calling sequence, or a device in the planned calling sequence is replaced by another device and the replacement is not within the preset replacement rules, the device replacement calling deviation is identified. If some devices in the planned device calling sequence are required to be executed in series, but the devices are executed in parallel in the actual device calling sequence, or the devices that are required to be executed in parallel in the planned calling sequence are executed in series, and the change of the execution mode is not subject to the preset mode change approval process, the device parallel execution mode deviation is identified. Through the mode matching and deviation identification, the difference types between the actual device calling sequence and the plan are determined. Step S1573: The ratio of the actual task duration to the planned duration is calculated to generate a task execution efficiency coefficient, which includes a device preparation phase efficiency loss value, a task core phase acceleration ratio, and a task end phase redundancy time length. The actual task duration is divided by the planned task duration in the preset device task allocation path to obtain the overall value of the task execution efficiency coefficient. In order to analyze the task execution efficiency in more detail, the entire execution process of the task is divided into a device preparation phase, a task core phase, and a task end phase. The device preparation phase refers to the time between the calling of the device and the preparation of the device ready for core task execution; the task core phase refers to the time during which the device performs the main experimental operation; and the task end phase refers to the time between the completion of the core task and the end of the device calling. The actual time and the planned time of each phase are calculated respectively. The device preparation phase efficiency loss value is the difference between the actual preparation time and the planned preparation time, and if the actual time is greater than the planned time, it is a positive loss value. The task core phase acceleration ratio is the ratio of the planned core phase time to the actual core phase time, and if the ratio is greater than 1, it indicates that the execution speed is faster than the plan. The task end phase redundancy time length is the difference between the actual end time and the planned end time, and if the actual time is greater than the planned time, it is a redundancy time length. The efficiency indicators of the above phases are integrated into the task execution efficiency coefficient to comprehensively reflect the efficiency of each phase of the task execution. Step S1574: The compliance of the actual device cooperation mode with the preset device cooperation running rules is analyzed to generate a cooperation mode deviation index, which includes a device sharing time overlap degree, a device mutual exclusion use violation number, and a device grouping cooperation effectiveness score. The actual device collaboration mode extracted is compared in detail with the preset device cooperation operation rule, and the compliance of both is evaluated. The device sharing time overlap degree refers to the overlap proportion of actual sharing time when multiple devices share the same resource (such as a public database, network bandwidth, or a shared detection module). The device mutual exclusion usage violation times refer to the number of times that devices or resources specified as mutually exclusive in the preset device cooperation operation rule are used simultaneously in the actual device collaboration mode. The device grouping collaboration effectiveness score is a quantitative score (such as a percentage or a rating) of the effectiveness of device grouping collaboration based on the task completion efficiency, task result quality, device communication success rate, and collaboration error frequency in the actual device collaboration mode. The above evaluation results are integrated to generate a collaboration mode deviation index, which is used to measure the deviation degree between the actual device collaboration mode and the preset rule. Step S1575: The sequence deviation types, the task execution efficiency coefficients, and the collaboration mode deviation indexes are classified according to task numbers to generate the task path deviation analysis report.

[0073] The identified sequence deviation types (device early call deviation, device replacement call deviation, and device parallel execution mode deviation), the calculated task execution efficiency coefficients (device preparation stage efficiency loss value, task core stage acceleration ratio, and task end stage redundant time length), and the generated collaboration mode deviation indexes (device sharing time overlap degree, device mutual exclusion usage violation times, and device grouping collaboration effectiveness score) are classified and arranged according to task numbers. For each task number, all sequence deviation types, corresponding task execution efficiency coefficient values, and collaboration mode deviation index values generated during execution are summarized together. A sub-report is generated for each task to describe the deviation details of the task in terms of device call sequence, execution efficiency, and collaboration mode. The sub-reports of all tasks are arranged in order of task numbers to form a complete task path deviation analysis report, which can clearly show the deviation details of each task from the preset strategy in the execution path.

[0074] Step S158: The device energy consumption change data is compared with the predicted energy consumption data to generate a device energy consumption model error coefficient, which includes a steady-state operation error rate, a peak power consumption prediction deviation, and an abnormal power consumption detection sensitivity.

[0075] The device execution feedback data set is compared with the energy consumption data predicted by the dynamic resource allocation model in the scheduling strategy generation stage. The steady-state operation error rate refers to the error percentage between the actual energy consumption value and the predicted energy consumption value of the device in the steady-state operation stage, and the average value of the error percentage of multiple steady-state operation time periods is obtained; the peak power consumption prediction deviation refers to the difference between the actual peak power consumption and the predicted peak power consumption of the device in the startup stage or the load mutation stage; the abnormal power consumption detection sensitivity refers to the detection ability of the dynamic resource allocation model to abnormal power consumption fluctuations, and the detection rate and false positive rate of the model are calculated by comparing the number of abnormal power consumption events predicted by the model with the number of actual abnormal power consumption events, to comprehensively evaluate the abnormal power consumption detection sensitivity. According to the comparison and calculation results above, the device energy consumption model error coefficient is generated, which is used to evaluate the accuracy of the energy consumption prediction part of the dynamic resource allocation model.

[0076] Step S159: Based on the device abnormal event record, the device compatibility matching feature is verified in reverse, and an environmental interference factor correction parameter is generated, which includes a temperature and humidity compensation coefficient, an electromagnetic interference shielding effectiveness update value, and a device spacing optimization suggestion.

[0077] According to the device abnormal event record in the device execution feedback data set, whether the cause of the abnormal event is related to the working environment of the device is analyzed. If the abnormal event (such as device precision decline, communication interference, data acquisition error) is caused by laboratory environmental factors (temperature and humidity, electromagnetic interference, device spacing), the device compatibility matching feature in the device availability evaluation index set is verified in reverse based on these abnormal event records. Check whether the temperature and humidity influence coefficient on device precision, electromagnetic interference intensity threshold, and device-to-device signal conflict probability in the device compatibility matching feature accurately reflect the actual environmental interference situation. According to the results of the reverse verification, an environmental interference factor correction parameter is generated. The temperature and humidity compensation coefficient is adjusted according to the correlation between the actual temperature and humidity data and the device abnormal event, to more accurately reflect the influence of temperature and humidity on device performance; the electromagnetic interference shielding effectiveness update value re-evaluates and updates the effectiveness of the original electromagnetic interference shielding measures according to the actual electromagnetic interference intensity and the occurrence of device abnormal events; and the device spacing optimization suggestion is based on the actual occurrence of device-to-device signal conflicts and the communication needs of the device, to make specific suggestions for adjusting the device placement position and spacing, to reduce environmental interference.

[0078] Step S160: The task path deviation analysis report, the device energy consumption model error coefficient, and the environmental interference factor correction parameter are input into the dynamic resource allocation model for incremental training, to update the device task allocation path generation rule and the device conflict resolution mechanism trigger condition.

[0079] The generated task path deviation analysis report, device energy consumption model error coefficient and environmental interference factor correction parameter are input into the preset dynamic resource allocation model for incremental training. During the incremental training process, the dynamic resource allocation model uses these new feedback data to adjust the neural network weights, decision tree node parameters, rule base threshold values, etc. inside it. For the device task allocation path generation rule, according to the unexpected device downtime influence range, task resource reallocation frequency and path adjustment effectiveness score in the task path deviation analysis report, the matching degree calculation weight of the task and the device, the task sorting algorithm parameter, the time window allocation strategy, etc. are adjusted to improve the accuracy and robustness of the device task allocation path; for the device conflict resolution mechanism trigger condition, combined with the device energy consumption model error coefficient (steady-state operation error rate, peak power consumption prediction deviation) and the environmental interference factor correction parameter (temperature and humidity compensation coefficient, electromagnetic interference shielding effectiveness update value), the sensitivity threshold of resource conflict detection, the weight of task priority determination, the trigger condition of standby device switching, etc. are adjusted, so that the device conflict resolution mechanism can respond and handle the conflict situation in actual operation more timely and accurately. Through incremental training, the dynamic resource allocation model can continuously adapt to the changes of laboratory devices and tasks, and improve the effect of scheduling optimization.

[0080] Step S161: Perform time sequence alignment processing on the device usage records generated during the execution of the actual task execution path, and extract the actual device calling sequence, actual task duration and actual device cooperation mode.

[0081] The device usage records generated during the execution of the actual task execution path are exported from the database of the laboratory device management system. These records contain information such as the device identifier involved in each task execution process, the device calling start time, the device calling end time, the operation steps of the device in the task execution, and the data transmission records between devices. The above-mentioned device usage records are subjected to time sequence alignment processing to calibrate all device usage records with a unified time reference (such as laboratory standard time). Then, the key information is extracted from the time sequence aligned device usage records: the actual device calling sequence refers to the order in which the devices are called during task execution, which is obtained by arranging the device calling start times in chronological order; the actual task duration refers to the time interval between the calling of the first device and the calling of the last device; the actual device cooperation mode refers to the cooperation mode of multiple devices in executing the same task or related tasks, which is determined by analyzing the calling relationship between devices, data transmission direction and time, operation step coordination, etc. such as master-slave cooperation, parallel cooperation, pipeline cooperation, etc.

[0082] Step S162: Pattern matching the actual device calling sequence with the planned calling sequence in the preset device task allocation path, identifying the sequence deviation type, which includes device early calling deviation, device alternative calling deviation and device parallel execution mode deviation.

[0083] The extracted actual device calling sequence is pattern matched with the planned device calling sequence in the preset device task allocation path. The identification and position of devices in the actual calling sequence and the planned calling sequence are compared element by element. If the calling time of a device in the actual calling sequence is earlier than the planned calling time of the device in the planned calling sequence, and exceeds the allowed early time range, it is identified as device early calling deviation; if a device appears in the actual calling sequence that does not appear in the planned calling sequence, or a device in the planned calling sequence is replaced by another device, and such replacement is not within the preset replacement rules, it is identified as device alternative calling deviation; if some devices in the planned device calling sequence are specified to be executed in series, but these devices are called in parallel in the actual device calling sequence, or the devices that are planned to be executed in parallel are executed in series, and such change in execution mode is not subject to the preset mode change approval process, it is identified as device parallel execution mode deviation. Through pattern matching and deviation identification, the difference type between the actual device calling sequence and the plan is determined.

[0084] Step S163: Calculate the ratio of the actual task duration to the planned duration to generate a task execution efficiency coefficient, which includes device preparation phase efficiency loss value, task core phase acceleration ratio and task tail phase redundant time length.

[0085] The actual task duration is divided by the planned task duration in the preset device task allocation path to obtain the overall value of the task execution efficiency coefficient. In order to analyze the task execution efficiency in more detail, the entire execution process of the task is divided into device preparation phase, task core phase and task tail phase. The device preparation phase refers to the time between the calling of the device and the preparation of the device ready for core task execution; the task core phase refers to the time during which the device performs the main experimental operation; the task tail phase refers to the time between the completion of the core task and the end of the device calling. The actual time and the planned time of each phase are calculated respectively: the device preparation phase efficiency loss value is the difference between the actual preparation time and the planned preparation time, if the actual time is greater than the planned time, it is a positive loss value; the task core phase acceleration ratio is the ratio of the planned core phase time to the actual core phase time, if the ratio is greater than 1, it means that the execution speed is faster than planned; the task tail phase redundant time length is the difference between the actual tail time and the planned tail time, if the actual time is greater than the planned time, it is a redundant time length. The efficiency indicators of the above phases are integrated into the task execution efficiency coefficient to comprehensively reflect the efficiency of each phase of task execution.

[0086] Step S164: Analyze the compliance of the actual device collaboration mode with the preset device cooperation rule, generate a collaboration mode deviation index, and the collaboration mode deviation index includes device sharing time overlap degree, device mutual exclusion use violation times, and device grouping collaboration effectiveness score.

[0087] The extracted actual device collaboration mode is compared and analyzed in detail with the preset device cooperation rule, and the compliance of the two is evaluated. The device sharing time overlap degree refers to the overlap proportion of the actual sharing time when multiple devices share the same resource (such as a public database, network bandwidth, and a shared detection module). The overlap interval length of each device using the shared resource is calculated, and the ratio of the total sharing time is obtained. The device mutual exclusion use violation times refers to the number of times that the devices or resources specified as mutual exclusion in the preset device cooperation rule are used simultaneously in the actual device collaboration mode. The calling time of the mutual exclusion device in the device usage record is checked to obtain the statistics. The device grouping collaboration effectiveness score is a quantitative score (such as a percentage or a rating system) of the effectiveness of device grouping collaboration based on the task completion efficiency, task result quality, device communication success rate, and collaboration error frequency in the actual device collaboration mode. The evaluation results are integrated to generate a collaboration mode deviation index, which is used to measure the deviation degree between the actual device collaboration mode and the preset rule.

[0088] Step S165: Classify the sequence deviation type, the task execution efficiency coefficient, and the collaboration mode deviation index according to the task number, and generate the task path deviation analysis report.

[0089] The identified sequence deviation types (device early call deviation, device replacement call deviation, and device parallel execution mode deviation), the calculated task execution efficiency coefficients (device preparation stage efficiency loss value, task core stage acceleration ratio, and task tail stage redundancy time length), and the generated collaboration mode deviation index (device sharing time overlap degree, device mutual exclusion use violation times, and device grouping collaboration effectiveness score) are classified and arranged according to the task number. For each task number, all the sequence deviation types, the corresponding task execution efficiency coefficients, and the collaboration mode deviation index values generated during the execution process are summarized together. A sub-report is generated for each task to describe the deviation details of the task in terms of device call sequence, execution efficiency, and collaboration mode. The sub-reports of all tasks are arranged in order according to the task number, and are integrated to form a complete task path deviation analysis report. The task path deviation analysis report can clearly show the deviation details of each task in the execution path from the preset strategy.

[0090] Step S166: Recalculating the device call priority weight in the device task allocation path according to the sequence deviation type, generating an updated device priority matrix.

[0091] According to the sequence deviation type identified in the task path deviation analysis report, the causes of different types of deviations and the relationship between the device call priority setting are analyzed. For the device call deviation, if it is due to the call priority setting of a certain type of device being too high, causing it to be called too early in task execution, the call priority weight of this type of device is reduced; for the device alternative call deviation, if the actual execution effect of the alternative device is better than the original planned device, the call priority weight of the alternative device is appropriately increased; for the device parallel execution mode deviation, if parallel execution leads to resource conflict or efficiency decline, the call priority weight of the devices participating in parallel execution is adjusted to make it more meet the needs of serial execution, otherwise, if parallel execution improves efficiency and does not produce conflict, the priority of related devices is maintained or adjusted to encourage reasonable parallel. Based on the above analysis, the device call priority weight in the device task allocation path generation rule is recalculated, the priority values of each device in the matrix are adjusted, and an updated device priority matrix is generated.

[0092] Step S167: Adjusting the time window allocation strategy in the device task allocation path based on the task execution efficiency coefficient, generating a dynamic time margin compensation rule, which includes device startup phase buffer duration, task transition phase overlap allowance threshold and task latest completion time flexibility coefficient.

[0093] According to the device preparation phase efficiency loss value, task core phase acceleration ratio and task tail phase redundancy duration in the task execution efficiency coefficient, the time window allocation strategy in the device task allocation path is adjusted. If the device preparation phase efficiency loss value is large, it means that the device preparation process takes a long time, in order to avoid affecting the subsequent tasks, the device startup phase buffer duration is increased in the time window allocation, that is, a buffer time is additionally added based on the planned device preparation time; according to the task core phase acceleration ratio, if the actual execution speed of the task is faster than the plan (acceleration ratio is greater than 1), the task transition phase overlap allowance threshold can be appropriately increased, allowing the task to overlap with the subsequent task to a certain extent in the time window, in order to improve the utilization of the device, otherwise, if the acceleration ratio is less than 1, the overlap allowance threshold is reduced, increasing the interval between tasks; combined with the task tail phase redundancy duration, the task latest completion time flexibility coefficient is set, for the task with large tail phase redundancy duration, the latest completion time has a certain flexibility (such as multiplying a flexibility coefficient greater than 1 based on the planned completion time), in order to cope with possible delays. The above adjustment strategies are integrated to generate a dynamic time margin compensation rule, which is used to optimize the time window setting in the device task allocation path.

[0094] Step S168: According to the cooperation mode deviation index, reconstruct the constraint conditions in the device cooperative operation rules, generate an enhanced device cooperation protocol, which contains device state pre-check requirements, device inter-heartbeat signal exchange frequency and cooperation exception automatic rollback mechanism.

[0095] According to the device sharing time overlap, the number of device mutual exclusion violation and the device grouping cooperation effectiveness score in the cooperation mode deviation index, the constraint conditions in the device cooperative operation rules are reconstructed. In order to reduce the device sharing time overlap and the number of device mutual exclusion violation, the device state pre-check requirements are added in the enhanced device cooperation protocol, which clearly stipulates that before the start of device cooperation, the current state of all devices participating in cooperation (such as whether idle, whether sufficient resources, whether there is conflict) must be fully pre-checked, and only after the pre-check is passed can the cooperation start; according to the device grouping cooperation effectiveness score, if the score is low, it may be due to the state synchronization between devices not timely, therefore the device inter-heartbeat signal exchange frequency is increased, so that the devices can exchange their running state information more frequently (such as once every second), to ensure state synchronization; for the abnormal situations that may occur during cooperation (such as communication interruption, device failure, data error), the cooperation exception automatic rollback mechanism is added in the enhanced device cooperation protocol, which stipulates that when the cooperation exception is detected, the system can automatically restore the devices participating in cooperation to the state before the start of cooperation, and record the exception information, in order to troubleshoot and re-cooperate. Through the reconstruction of the above constraint conditions, the enhanced device cooperation protocol is generated, which improves the reliability and efficiency of device cooperative operation.

[0096] Step S169: Write the updated device priority matrix, the dynamic time margin compensation rule and the enhanced device cooperation protocol into the decision parameter library of the dynamic resource allocation model.

[0097] The updated device priority matrix, dynamic time margin compensation rules, and enhanced device collaboration protocol are stored in the decision parameter library of the dynamic resource allocation model. The decision parameter library is organized using a structured database table, including a device priority table, a time margin rule table, a collaboration protocol table, and the like. The updated device priority matrix is written into the device priority table, covering the original priority data; the device startup phase buffer duration, task transition phase overlap allowed threshold, and task latest completion time elasticity coefficient in the dynamic time margin compensation rules are written into the time margin rule table; the device state pre-check requirements, inter-device heartbeat signal exchange frequency, and collaboration exception automatic rollback mechanism in the enhanced device collaboration protocol are parsed into specific parameters and rule codes, and written into the collaboration protocol table. The decision parameter library supports version control and backtracking functions for parameters, recording the time, reason, and updater of each parameter update, for subsequent auditing and problem tracing. In the subsequent scheduling strategy generation process of the dynamic resource allocation model, these updated parameters and rules will be read from the decision parameter library to guide decision analysis.

[0098] Step S170: In the subsequent device scheduling strategy generation process, the updated device task allocation path generation rules are preferentially applied, and a new device conflict resolution mechanism is triggered when a collaboration mode deviation is detected.

[0099] After the dynamic resource allocation model completes incremental training and updates the decision parameter library, in the subsequent laboratory device scheduling strategy generation process, the dynamic resource allocation model will preferentially apply the updated device task allocation path generation rules. When calculating the task-device matching degree, the updated device priority matrix is used; when planning the device task allocation path, the dynamic time margin compensation rules are applied to set the time window; when generating the device collaborative operation rules, the enhanced device collaboration protocol is adopted. At the same time, the compliance of the actual device collaboration mode with the enhanced device collaboration protocol will be continuously monitored, and through real-time analysis of device usage records and task execution state monitoring data streams, whether a collaboration mode deviation (such as device sharing time overlap exceeding the threshold, device mutual exclusion use violation frequency increasing, device grouping collaboration effectiveness score decreasing, etc.) occurs will be detected. When a collaboration mode deviation is detected, the dynamic resource allocation model will trigger a new device conflict resolution mechanism (based on the updated trigger conditions), and take timely adjustment measures (such as task migration, resource reallocation, device mode switching, etc.) to ensure the effective execution of the device scheduling strategy and the efficient collaborative operation of the laboratory devices.

[0100] Figure 2 A schematic diagram of exemplary hardware and software components of a laboratory device control system 100 that can implement the ideas of the present application is shown. For example, a processor 120 can be used on the laboratory device control system 100 and used to perform the functions in the present application.

[0101] The laboratory equipment control system 100 can be a general server or a special-purpose server, both of which can be used to implement the AI-based laboratory equipment scheduling optimization method of the present application. The present application, although only shows one server, for the sake of convenience, the functions described in the present application can be implemented in a distributed manner on multiple similar platforms to balance the processing load.

[0102] For example, the laboratory equipment control system 100 can include a network port 110 connected to a network, one or more processors 120 for executing program instructions, a communication bus 130, and different forms of storage media 140, such as a disk, a ROM, or a RAM, or any combination thereof. Exemplarily, the laboratory equipment control system 100 can also include program instructions stored in a ROM, a RAM, or other types of non-transitory storage media, or any combination thereof. The method of the present application can be implemented according to the above-mentioned program instructions. The laboratory equipment control system 100 also includes an I / O interface 150 between the computer and other input / output devices.

[0103] For the sake of illustration, only one processor is described in the laboratory equipment control system 100. However, it should be noted that the laboratory equipment control system 100 in the present application can also include multiple processors, so the steps performed by one processor described in the present application can also be jointly performed or individually performed by multiple processors. For example, if the processor of the laboratory equipment control system 100 performs steps A and B, it should be understood that steps A and B can also be jointly performed by two different processors or individually performed in one processor. For example, a first processor performs step A, a second processor performs step B, or the first processor and the second processor jointly perform steps A and B.

[0104] In addition, the present application embodiment also provides a readable storage medium, wherein computer executable instructions are pre-set in the readable storage medium, and when the processor executes the computer executable instructions, the AI-based laboratory equipment scheduling optimization method described above is realized.

[0105] It should be noted that, in order to simplify the description of the present application disclosed, and to help the understanding of one or more embodiments of the present application, in the foregoing description of the embodiments of the present application, sometimes multiple features are incorporated into one embodiment, figure or description thereof.

Claims

1. An AI-based laboratory equipment scheduling optimization method, characterized in that, The method includes: Real-time acquisition of a set of status monitoring data for laboratory equipment, the set of status monitoring data including equipment operating power consumption characteristics, equipment idle time characteristics, and equipment environmental interference factor characteristics; The status monitoring data set is subjected to multi-dimensional requirement analysis processing to generate a set of equipment availability assessment indicators and an experimental task priority queue. The set of equipment availability assessment indicators includes equipment load fluctuation characteristics, equipment maintenance cycle prediction characteristics, and equipment compatibility matching characteristics. Based on a preset dynamic resource allocation model, cross-decision analysis is performed on the set of equipment availability assessment indicators and the priority queue of experimental tasks to generate a set of laboratory equipment scheduling strategies. The set of laboratory equipment scheduling strategies includes equipment task allocation paths, equipment collaborative operation rules and equipment conflict resolution mechanisms. Based on the real-time updated experimental task operation log data set, the laboratory equipment scheduling strategy set is dynamically calibrated to generate an optimized set of equipment scheduling execution instructions. The optimized set of equipment scheduling execution instructions is fed back to the laboratory equipment control system to trigger equipment operation status adjustment, and the dynamic resource allocation model is iteratively updated based on the set of equipment execution feedback data.

2. The AI-based laboratory equipment scheduling optimization method according to claim 1, characterized in that, The real-time acquisition of laboratory equipment status monitoring data set includes: Multimodal sensor arrays are deployed in each laboratory device to collect real-time data on device current fluctuations, device temperature changes, and device mechanical vibrations. The power consumption pattern recognition processing is performed on the current fluctuation data of the device to extract the operating power consumption characteristics of the device. The operating power consumption characteristics of the device include the peak power consumption during the device startup phase, the average power consumption during steady-state operation of the device, and the abnormal power consumption fluctuation cycle of the device. Idle interval analysis is performed on laboratory equipment operation record data to extract equipment idle duration features, which include the start timestamp of a single idle period, the duration of consecutive idle intervals, and the historical idle frequency distribution of the equipment. The environmental monitoring device is invoked to obtain temperature and humidity data, electromagnetic interference data and equipment spacing data in the laboratory space. The environmental interference factor characteristics of the equipment are extracted. The environmental interference factor characteristics of the equipment include the influence coefficient of temperature and humidity on equipment accuracy, electromagnetic interference intensity threshold and signal conflict probability between equipment. The device's operating power consumption characteristics, device idle time characteristics, and device environmental interference factor characteristics are aligned by time windows and then merged to generate a status monitoring data set.

3. The AI-based laboratory equipment scheduling optimization method according to claim 1, characterized in that, The process of performing multi-dimensional requirement analysis on the status monitoring data set to generate a set of equipment availability assessment indicators and an experimental task priority queue includes: Analyze the task attribute parameters in the experimental task request dataset to extract task equipment dependency features, task urgency labels, and task resource consumption prediction features; Based on the matching degree calculation of the device operating power consumption characteristics and the task resource consumption prediction characteristics, the device load fluctuation characteristics are generated. The device load fluctuation characteristics include the power consumption increment prediction value when tasks are executed in combination, the device maximum load safety threshold, and the task interruption risk level. Based on historical equipment maintenance data and the idle time characteristics of the equipment, maintenance cycle prediction is performed to generate equipment maintenance cycle prediction features. The equipment maintenance cycle prediction features include the remaining maintenance time window, maintenance operation time estimation, and task migration path during maintenance. Based on the equipment environmental interference factor characteristics and task accuracy requirement data, a compatibility matching analysis is performed to generate equipment compatibility matching features. The equipment compatibility matching features include environmental interference tolerance score, equipment accuracy calibration capability index and task result error prediction range. Based on the task urgency labels and laboratory task scheduling rules, priority is sorted to generate an experimental task priority queue. The equipment load fluctuation characteristics, equipment maintenance cycle prediction characteristics, and equipment compatibility matching characteristics are then merged into a set of equipment availability evaluation indicators.

4. The AI-based laboratory equipment scheduling optimization method according to claim 3, characterized in that, The preset dynamic resource allocation model performs cross-decision analysis on the set of equipment availability assessment indicators and the priority queue of experimental tasks to generate a set of laboratory equipment scheduling strategies, including: Each task in the experimental task priority queue is matched bidirectionally with the corresponding device in the set of device availability evaluation indicators to generate a task-device matching matrix. The task-device matching matrix includes task execution success rate score, device utilization improvement coefficient and task conflict detection result. Based on the equipment maintenance cycle prediction features, the task-equipment matching matrix is ​​subjected to maintenance window constraint processing to generate an equipment task allocation path. The equipment task allocation path includes the task execution sequence before maintenance, the task migration path during maintenance, and the equipment restart strategy after maintenance. Based on the device compatibility matching features, resource conflict detection is performed on multiple tasks executed simultaneously to generate device collaborative operation rules. The device collaborative operation rules include device shared use time slicing rules, device mutual exclusion use condition determination rules, and device group collaborative operation protocols. When a task resource conflict is detected, a conflict resolution decision is made based on the task urgency label and the device load fluctuation characteristics, and a device conflict resolution mechanism is generated. The device conflict resolution mechanism includes a task execution order adjustment strategy, a device backup node switching strategy, and a task resource dynamic reallocation strategy. The equipment task allocation path, the equipment collaborative operation rules, and the equipment conflict resolution mechanism are encapsulated at the decision level to generate a set of laboratory equipment scheduling strategies.

5. The AI-based laboratory equipment scheduling optimization method according to claim 1, characterized in that, The step of dynamically calibrating the laboratory equipment scheduling strategy set based on the real-time updated experimental task operation log data set to generate an optimized set of equipment scheduling execution instructions includes: Real-time acquisition of equipment response delay data, task progress deviation data, and equipment abnormal alarm data during the execution of experimental tasks, generating a task execution status monitoring data stream; The deviation of the task execution status monitoring data stream is compared with the preset execution parameters in the laboratory equipment scheduling strategy set to identify the equipment scheduling deviation type, which includes equipment response timeout deviation, insufficient task resource allocation deviation, and equipment performance degradation deviation. Based on the predicted characteristics of the equipment maintenance cycle, a root cause analysis is performed on the equipment performance degradation deviation to generate equipment performance calibration parameters. The equipment performance calibration parameters include the adjustment range of equipment drive parameters, the equipment working mode switching threshold, and the activation conditions of equipment spare parts. Based on the task progress deviation data, the device task allocation path is replanned in real time to generate a dynamic task allocation patch. The dynamic task allocation patch includes task execution time window adjustment instructions, device load rebalancing strategy and task dependency reconstruction rules. The equipment performance calibration parameters and the dynamic task allocation patch are integrated according to equipment nodes to generate an optimized set of equipment scheduling execution instructions, and the laboratory equipment control system is triggered to perform instruction verification operations.

6. The AI-based laboratory equipment scheduling optimization method according to claim 1, characterized in that, The step of feeding back the optimized set of equipment scheduling execution instructions to the laboratory equipment control system to trigger equipment operating status adjustment operations includes: The optimized set of equipment scheduling execution instructions is parsed to generate a sequence of equipment control signals, which includes motor speed adjustment instructions, temperature control module setpoint update instructions, and safety protection device trigger conditions. According to the equipment collaborative operation rules, the control signals of multiple devices are processed for timing synchronization to generate a device collaborative control timing table. The device collaborative control timing table includes the device start interval duration, signal transmission delay compensation value and device status verification time point. Before performing the equipment operating status adjustment operation, the equipment pre-inspection module is called to perform a compatibility check between the current status of the target equipment and the required status of the instruction, and a equipment instruction execution readiness status report is generated. When the device instruction execution readiness status report shows an abnormality, the backup device switching process is initiated according to the device conflict resolution mechanism, and an emergency dispatch instruction for device failure is generated. The verified equipment control signal sequence and equipment collaborative control timing table are sent to the laboratory equipment control system to trigger a batch update operation of equipment operating parameters.

7. The AI-based laboratory equipment scheduling optimization method according to claim 1, characterized in that, The iterative update of the dynamic resource allocation model based on the device execution feedback data set includes: The system collects actual task completion data, equipment energy consumption change data, and equipment abnormal event records after the equipment executes the optimized set of equipment scheduling execution instructions, and generates a set of equipment execution feedback data. Extract the difference features between the actual task execution path and the preset device task allocation path from the device execution feedback data set, and generate a task path deviation analysis report. The task path deviation analysis report includes the scope of the impact of unexpected device downtime, the frequency of task resource reallocation, and the effectiveness score of path adjustment. Based on the comparison between the equipment energy consumption change data and the predicted energy consumption data, an equipment energy consumption model error coefficient is generated. The equipment energy consumption model error coefficient includes the steady-state operation error rate, peak power consumption prediction deviation, and abnormal power consumption detection sensitivity. Based on the abnormal event records of the equipment, the compatibility matching characteristics of the equipment are reverse-verified to generate environmental interference factor correction parameters. The environmental interference factor correction parameters include temperature and humidity compensation coefficients, electromagnetic interference shielding effectiveness update values, and equipment spacing optimization suggestions. The task path deviation analysis report, the equipment energy consumption model error coefficient, and the environmental interference factor correction parameters are input into the dynamic resource allocation model for incremental training, thereby updating the equipment task allocation path generation rules and the equipment conflict resolution mechanism triggering conditions.

8. The AI-based laboratory equipment scheduling optimization method according to claim 7, characterized in that, The step of extracting the difference characteristics between the actual task execution path and the preset device task allocation path from the device execution feedback data set, and generating a task path deviation analysis report, includes: The device usage records generated during the execution of the actual task execution path are time-series aligned to extract the actual device call order, actual task duration, and actual device collaboration mode. The actual device call order is matched with the planned call order in the preset device task allocation path to identify the type of order deviation. The type of order deviation includes device early call deviation, device alternative call deviation, and device parallel execution mode deviation. Calculate the ratio of the actual task duration to the planned duration to generate a task execution efficiency coefficient, which includes the efficiency loss value during the equipment preparation phase, the acceleration ratio during the core task phase, and the redundancy time during the task completion phase. The degree of conformity between the actual equipment collaboration mode and the preset equipment collaborative operation rules is analyzed to generate a collaboration mode deviation index. The collaboration mode deviation index includes the overlap of equipment sharing time, the number of violations of equipment mutual exclusion use, and the effectiveness score of equipment group collaboration. The sequence deviation type, the task execution efficiency coefficient, and the collaboration mode deviation index are categorized by task number to generate the task path deviation analysis report.

9. The AI-based laboratory equipment scheduling optimization method according to claim 8, characterized in that, The step of inputting the task path deviation analysis report, the equipment energy consumption model error coefficient, and the environmental interference factor correction parameters into the dynamic resource allocation model for incremental training, and updating the equipment task allocation path generation rules and equipment conflict resolution mechanism triggering conditions, includes: The device call priority weights in the device task allocation path are recalculated based on the order deviation type to generate an updated device priority matrix; Based on the task execution efficiency coefficient, the time window allocation strategy in the device task allocation path is adjusted to generate a dynamic time margin compensation rule. The dynamic time margin compensation rule includes the device startup phase buffer duration, the task transition phase overlap allowable threshold, and the task latest completion time elasticity coefficient. Based on the deviation index of the cooperation mode, the constraints in the equipment collaborative operation rules are reconstructed to generate an enhanced equipment cooperation protocol. The enhanced equipment cooperation protocol includes equipment status pre-inspection requirements, the frequency of heartbeat signal exchange between equipment, and an automatic rollback mechanism for cooperation anomalies. The updated device priority matrix, the dynamic time margin compensation rule, and the enhanced device collaboration protocol are written into the decision parameter library of the dynamic resource allocation model. In the subsequent equipment scheduling strategy generation process, the updated equipment task allocation path generation rules are applied first, and a new equipment conflict resolution mechanism is triggered when a deviation in the cooperation mode is detected.

10. A laboratory equipment control system, characterized in that, The laboratory equipment control system includes a processor and a memory, the memory and the processor being connected. The memory is used to store programs, instructions or code, and the processor is used to execute the programs, instructions or code in the memory to implement the AI-based laboratory equipment scheduling optimization method according to any one of claims 1-9.

Citation Information

Cited By

  • Semiconductor device feedforward and feedback cooperative control method, system, device and medium

    CN121478032A

  • Methods, systems, devices and media for feedforward and feedback coordinated control of semiconductor devices

    CN121478032B

  • Smart campus management method and system

    CN121684551A

  • A smart campus management method and system

    CN121684551B

  • Equipment state detection method and system for PCR (Polymerase Chain Reaction)

    CN121705871A