Laboratory management and control scheduling system and method

Abstract

The invention discloses a laboratory management and control scheduling system and method, and belongs to the field of laboratory management, and the system comprises an Internet of Things equipment monitoring module, a cloud computing resource scheduling module, an experiment task distribution and progress monitoring module, a data analysis and report generation module, an early warning and exception handling module, and a data security and privacy protection module. Through linkage of the cloud computing resource scheduling module and the experiment task allocation module, accurate matching of equipment, personnel and tasks is realized through an intelligent algorithm, the tasks are automatically allocated based on equipment loads and personnel skills, a scheduling plan can be dynamically adjusted according to real-time progress, the problems of resource idleness and task backlog are solved from the source, and the task scheduling efficiency is improved. The cooperative effects of efficient equipment operation, personnel load balance and ordered task promotion are achieved; equipment and environment data are collected in real time through the Internet of Things equipment monitoring module, and the early warning and exception handling module synchronously monitors and responds to exceptions.

Description

Technical Field

[0001] This invention relates to the field of laboratory management technology, and in particular to a laboratory control and scheduling system and method. Background Technology

[0002] As scientific research activities become more complex and large-scale, laboratories, as the core locations for scientific research, face many management challenges: traditional management models rely on manual scheduling of equipment and allocation of tasks, which can easily lead to uneven resource allocation and excessive equipment idle rates; experimental data collection is delayed, making it difficult to support decision-making in real time; and the lack of a rapid response mechanism for equipment failures and task delays seriously affects experimental efficiency.

[0003] In existing technologies, some laboratory management systems only achieve static recording of equipment information or digitization of task processes, without achieving deep integration of real-time monitoring and intelligent scheduling; a few intelligent systems suffer from problems such as single algorithms, poor scalability, and insufficient data security.

[0004] Therefore, there is a need for a laboratory management and scheduling system and method that integrates multiple technologies and has dynamic scheduling, real-time analysis and intelligent decision-making capabilities. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a laboratory management and scheduling system and method that solves problems such as untimely resource scheduling, low equipment utilization, unreasonable task allocation, poor data real-time performance, and delayed anomaly handling in traditional laboratory management.

[0006] Technical Solution: To solve the above-mentioned technical problems, according to one aspect of the present invention, more specifically, a laboratory management and scheduling system, including an Internet of Things (IoT) device monitoring module, a cloud computing resource scheduling module, an experimental task allocation and progress monitoring module, a data analysis and report generation module, an early warning and anomaly handling module, and a data security and privacy protection module.

[0007] IoT device monitoring module: By using sensors (temperature, humidity, and air pressure sensors) deployed on experimental equipment (such as spectrometers and centrifuges), experimental benches, and the environment, the module collects the device's working status (running / idle / fault), usage time, and environmental parameters in real time using LoRaWAN or NB-IoT protocols. After preprocessing by edge computing nodes, the data is transmitted to the cloud platform.

[0008] The cloud computing resource scheduling module is based on a hybrid cloud architecture (private cloud for storing sensitive data, public cloud for processing elastic computing tasks). It integrates an improved genetic algorithm and a reinforcement learning model: the genetic algorithm is used to generate the initial scheduling scheme, with the objective function of maximizing equipment utilization, and the constraints of task priority, equipment load, and personnel skills; the reinforcement learning model dynamically optimizes the scheduling strategy through real-time feedback data to achieve dynamic matching of equipment, tasks, and personnel.

[0009] Experimental task allocation and progress monitoring module: Constructs a task-person-equipment association graph, and automatically allocates tasks based on personnel's historical task completion efficiency, current load, and equipment availability using the Hungarian algorithm; records task nodes (such as task reception, equipment activation, and data upload) timestamps using blockchain technology, updates progress in real time, and pushes it to personnel terminals (APP / web terminal).

[0010] Data analysis and report generation module: It uses a time-series database to store historical data, and uses machine learning models (such as random forest) to analyze equipment usage frequency, idle time periods, and personnel efficiency trends to generate equipment optimization scheduling schemes (such as cross-laboratory sharing suggestions), personnel performance reports, and personalized improvement suggestions (such as skills training directions).

[0011] Early warning and anomaly handling module: Set three-level early warning thresholds (minor / moderate / severe). When equipment vibration exceeds the standard (such as centrifuge) or the ambient temperature and humidity deviate from the threshold, an early warning is triggered through audible and visual alarms (local in the laboratory) and SMS / APP push (management personnel). For severe anomalies (such as equipment failure), the emergency plan library is automatically called (such as switching to backup equipment and assigning maintenance personnel), and the related task scheduling plan is adjusted simultaneously.

[0012] Data security and privacy protection module: Data is transmitted using AES-256 encryption, and permissions are assigned based on the RBAC (Role-Based Access Control) model (e.g., researchers can only view their own task data, while administrators can access all data); federated learning technology is used to achieve joint analysis of data from multiple laboratories to avoid leakage of raw data.

[0013] According to one aspect of the present invention, and more specifically a laboratory management and scheduling method, the method includes the following steps:

[0014] Step S1: The IoT device monitoring module collects the working status, usage time, and environmental parameters such as temperature and humidity of the experimental equipment. After preprocessing by the edge computing node of the module, the data is uploaded to the cloud platform. At the same time, the data security and privacy protection module uses AES-256 encryption technology to encrypt and protect the data during transmission.

[0015] Step S2: The cloud computing resource scheduling module receives real-time data from the cloud platform, calls the improved genetic algorithm and reinforcement learning model integrated in the module, and generates an initial scheduling plan by combining the historical data of the laboratory. The genetic algorithm takes maximizing equipment utilization as the objective function, and the reinforcement learning model dynamically optimizes the scheduling plan based on real-time feedback data.

[0016] Step S3: The experimental task allocation and progress monitoring module automatically allocates tasks based on the scheduling plan generated by the cloud computing resource scheduling module, combined with the personnel's historical task completion efficiency, current load and equipment availability, using the Hungarian algorithm. At the same time, it records the task node timestamps through blockchain technology, updates the task progress in real time and pushes it to the personnel's terminal. The data security and privacy protection module controls the personnel's terminal access to task data based on the RBAC model.

[0017] Step S4: The data analysis and report generation module calls a machine learning model (such as random forest) to analyze the historical data collected by the IoT device monitoring module and the task data recorded by the experimental task allocation and progress monitoring module, and outputs optimization reports such as device optimization scheduling schemes and personnel performance reports. The data security and privacy protection module uses federated learning technology when conducting joint analysis of data from multiple laboratories to avoid leakage of raw data.

[0018] Step S5: The early warning and anomaly handling module receives real-time device and environmental data collected by the IoT device monitoring module and task progress data from the experimental task allocation and progress monitoring module. When the monitored data exceeds the set three-level early warning threshold, the corresponding early warning is triggered and the emergency handling plan is executed. In case of serious anomalies, the cloud computing resource scheduling module is notified simultaneously to adjust the scheduling plan.

[0019] Step S6: Throughout the entire process, the data security and privacy protection module ensures the security of data transmission and access, including data encryption and access control.

[0020] The beneficial effects of the laboratory management and scheduling system and method of the present invention are as follows:

[0021] (1) This invention links the cloud computing resource scheduling module and the experimental task allocation module, and achieves precise matching of equipment, personnel and tasks through intelligent algorithms: it can automatically allocate tasks based on equipment load and personnel skills, and can also dynamically adjust the scheduling plan according to real-time progress, thereby solving the problems of idle resources and backlog of tasks from the root and achieving the synergistic effect of "efficient equipment operation, balanced personnel load and orderly task progress".

[0022] (2) The present invention collects equipment and environmental data in real time through the Internet of Things device monitoring module, and the early warning and anomaly handling module monitors and responds to anomalies in sync. The two form a closed loop with the cloud computing scheduling module: when the equipment fails, the backup plan is automatically triggered and the task arrangement is adjusted. When the environmental parameters exceed the standard, the early warning is issued in time and the experimental task is suspended in linkage, ensuring that the experimental process is "monitorable, early warningable, and emergency-proof", minimizing the impact of accidents on the experiment.

[0023] (3) This invention integrates IoT monitoring data and task execution data through the data analysis module, and the generated optimization suggestions feed back into the scheduling module: optimize the scheduling strategy by analyzing the equipment usage patterns, adjust the task allocation based on the personnel efficiency trend, and shift management from "passive response" to "proactive optimization"; at the same time, federated learning technology supports joint analysis of data from multiple laboratories, providing data support for cross-institutional resource sharing and collaborative research.

[0024] (4) The present invention uses a data security module to cover the entire process of data acquisition, transmission and storage. AES-256 encryption and RBAC permission management ensure that experimental data (especially classified scientific research data) are not leaked. The hybrid cloud architecture and modular design support the smooth expansion from small laboratories to cross-regional scientific research platforms. It can meet the current management needs and adapt to the future expansion of experimental scale and technology upgrades, achieving a two-way balance between "security and development". Attached Figure Description

[0025] The present invention will now be described in further detail with reference to the accompanying drawings and specific implementation methods.

[0026] Figure 1 This is a schematic diagram of the laboratory management and scheduling system of the present invention. Detailed Implementation

[0027] The present invention will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the present application can be combined with each other.

[0028] To make the technical solution of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0029] Example 1

[0030] Reference Figure 1 An application of a laboratory management and scheduling system and method in university chemistry laboratories:

[0031] A university chemistry laboratory is equipped with 10 gas chromatographs, 5 centrifuges, 8 fume hoods, and corresponding reagent storage cabinets, and routinely undertakes experimental tasks such as organic compound detection and sample separation. After the deployment of this system, intelligent management and scheduling of experimental resources have been achieved. The specific operation process is as follows:

[0032] Equipment and Environmental Monitoring

[0033] The IoT device monitoring module has built-in status sensors in each instrument (gas chromatograph, centrifuge) to collect real-time data on the equipment's operating status (running / idle / fault), cumulative usage time, and current experimental parameters (such as column temperature and centrifugation speed). Temperature and humidity sensors are deployed in the experimental area, and wind speed sensors are installed in the fume hood. Data is transmitted to edge computing nodes via the LoRaWAN protocol. After preprocessing (such as outlier filtering), the data security and privacy protection module uploads the data to the hybrid cloud platform (experimental data is stored in the private cloud and processed and scheduled on the public cloud) using AES-256 encryption technology.

[0034] Task scheduling and allocation

[0035] When 5 sets of organic sample testing tasks are received (including 3 expedited tasks), the cloud computing resource scheduling module starts working:

[0036] Based on real-time data collected by the IoT device monitoring module, it was confirmed that the currently idle devices are gas chromatographs No. 3 and No. 7, and centrifuge No. 2.

[0037] An improved genetic algorithm is invoked to maximize equipment utilization. This is combined with task priority (urgent tasks take priority), researcher skills (researcher A is good at separating complex samples), and equipment load (chromatograph No. 7 has a shorter cumulative usage time on the day) to generate an initial scheduling plan.

[0038] According to the plan, the experimental task allocation and progress monitoring module assigns 3 sets of urgent tasks to researcher A (using chromatograph No. 7) and 2 sets of regular tasks to researcher B (using chromatograph No. 3) through the task-person-equipment association graph. At the same time, it records the task receipt timestamp through blockchain and pushes it to the mobile APP of both researchers.

[0039] Experimental process control

[0040] After receiving the task, Researcher A starts the No. 7 chromatograph, and the system automatically records the equipment activation timestamp. During the experiment, the IoT device monitoring module updates the equipment operating parameters and fume hood wind speed every 30 seconds (ensuring ≥1.2m / s), and the experimental task allocation and progress monitoring module synchronizes the task progress in real time (e.g., "Sample 1 detection completed, Sample 2 in progress").

[0041] The early warning and anomaly handling module monitors data in real time: when the column temperature fluctuation of chromatograph No. 7 exceeds ±2℃ (triggering a moderate warning), it immediately alerts the administrator through the laboratory's audible and visual alarm device and sends a text message to the administrator; at the same time, it automatically retrieves the emergency plan library and suggests switching to the backup chromatograph No. 5.

[0042] After researcher A selects to switch devices, the cloud computing resource scheduling module dynamically updates the scheduling plan, and the experimental task allocation and progress monitoring module synchronously corrects the task node timestamps to ensure task continuity.

[0043] After the day's experiments concluded, the data analysis and report generation module invoked the random forest model to analyze the historical data.

[0044] Output equipment optimization suggestions: The column temperature of chromatograph No. 7 was abnormal 3 times this month, and calibration is recommended; the fume hood utilization rate reached 100% between 14:00 and 16:00, and it is recommended to schedule experiments during off-peak hours;

[0045] Generate personnel performance reports: Researcher A's efficiency in completing urgent tasks is 15% higher than the average, and Researcher B's error rate in routine tasks is low. Provide targeted skill improvement suggestions for each.

[0046] When multiple laboratories conduct joint analysis, the data security module uses federated learning technology to share equipment scheduling optimization experience with other chemistry laboratories on campus without disclosing the original data.

[0047] Example 2

[0048] Reference Figure 1 A laboratory management and scheduling system and method, applied in a biomedical laboratory:

[0049] A biomedical laboratory specializes in cell culture and molecular biology experiments, equipped with biosafety cabinets, CO2 incubators, PCR instruments, and other equipment. It has stringent requirements for the cleanliness and temperature stability of the experimental environment. The application workflow of this system is as follows:

[0050] The environmental and equipment monitoring IoT module installs differential pressure sensors in biosafety cabinets, temperature, humidity, and CO2 concentration sensors in CO2 incubators, and thermal cycling status sensors in PCR instruments. Data is collected in real-time and transmitted encrypted to the cloud platform. The data security and privacy protection module, based on the RBAC model, allows researchers to view only the incubator data they operate, while administrators can view the status of all devices.

[0051] The complex task scheduling laboratory receives a batch task of "COVID-19 nucleic acid testing" (containing 100 samples). The cloud computing resource scheduling module combines historical data (the PCR instrument's maximum daily processing capacity is 24 samples) and real-time equipment status to generate a scheduling plan:

[0052] Samples were processed in four batches, and two PCR instruments (No. 1 and No. 3) were used in parallel.

[0053] Researcher C was assigned to be responsible for sample preparation (using biosafety cabinet #2), while researchers D and E were responsible for PCR amplification and result analysis, ensuring a balanced workload for personnel. The experimental task allocation module breaks down tasks into nodes of "sample reception - nucleic acid extraction - amplification - data analysis," and records the timestamps of each node through blockchain, pushing them to the team's shared terminal in real time.

[0054] Abnormal handling and emergency response

[0055] When PCR instrument No. 1 experiences temperature runaway during the amplification phase (triggering a critical warning), the warning and anomaly handling module immediately activates the emergency plan: suspending the operation of the device and locking the internal samples; simultaneously notifying the cloud computing resource scheduling module to adjust the plan and allocate the unfinished samples to the backup PCR instrument No. 5;

[0056] Meanwhile, through the linkage control of the biosafety cabinet, the exhaust efficiency of biosafety cabinet No. 2 is automatically enhanced to prevent potential biological contamination.

[0057] Data traceability and optimization

[0058] All experimental data (such as incubator temperature curves and PCR amplification curves) are encrypted and stored by the IoT device monitoring module, and the data analysis module generates traceability reports. It supports querying the entire process data by sample number and operation time, which meets the traceability requirements of biological experiments.

[0059] Monthly analysis showed that the CO2 incubator was only used at night (22:00-6:00), with a utilization rate of only 5%. The system suggested adjusting some cell passage experiments to this time period to improve equipment utilization. Researcher C's sample preparation efficiency fluctuated greatly, and it was recommended to conduct standardized operation training.

[0060] The above embodiments are all based on the modular architecture defined in this invention. Through equipment scheduling, task allocation, environmental monitoring and anomaly handling processes in laboratory scenarios, the practicality and relevance of the system are fully demonstrated.

[0061] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

Claims

1. A laboratory management and scheduling system, characterized in that, include: The IoT device monitoring module is used to collect device operating status, usage time, and environmental parameters through sensors deployed in experimental equipment, experimental benches, and environments, using LoRaWAN or NB-IoT protocols. After preprocessing by edge computing nodes, the data is transmitted to the cloud platform. The cloud computing resource scheduling module, based on a hybrid cloud architecture, integrates an improved genetic algorithm and a reinforcement learning model. With maximizing equipment utilization as the objective function, it combines task priority, equipment load, and personnel skills to generate and dynamically optimize the scheduling scheme for equipment, tasks, and personnel. The experimental task allocation and progress monitoring module constructs a task-personnel-equipment association graph, uses the Hungarian algorithm to automatically allocate tasks, records task node timestamps through blockchain technology, and pushes progress to personnel terminals in real time. The data analysis and report generation module uses a time-series database to store historical data, analyzes the data through machine learning models, and outputs optimization suggestions for equipment scheduling and personnel performance reports. The early warning and anomaly handling module sets three levels of early warning thresholds. When equipment, environmental or task data is abnormal, an early warning is triggered and an emergency handling plan is executed. In the event of a serious anomaly, the scheduling plan is adjusted synchronously. The data security and privacy protection module uses AES-256 encryption to transmit data, assigns permissions based on the RBAC model, and achieves joint analysis of data from multiple laboratories through federated learning technology.

2. The laboratory management and scheduling system according to claim 1, characterized in that, In the cloud computing resource scheduling module, the genetic algorithm is used to generate the initial scheduling scheme, and the reinforcement learning model dynamically optimizes the scheduling strategy through real-time feedback data to achieve dynamic matching of equipment, tasks and personnel. In the hybrid cloud architecture, the private cloud is used to store sensitive data, and the public cloud is used to process elastic computing tasks.

3. The laboratory management and scheduling system according to claim 2, characterized in that, The three-level warning threshold of the warning and anomaly handling module corresponds to three levels of anomaly: minor, moderate, and severe. For severe anomalies, the emergency solution library is automatically invoked. The emergency solution library includes solutions for switching to backup equipment and allocating maintenance personnel, and the cloud computing resource scheduling module is notified simultaneously to adjust the scheduling plan.

4. A laboratory management and scheduling method, using the laboratory management and scheduling system as described in claim 3, characterized in that, Includes the following steps: S1. The IoT device monitoring module collects device and environmental data through sensors, and uploads it to the cloud platform after preprocessing by the edge computing node. The data security and privacy protection module uses AES-256 encryption technology to encrypt the transmitted data. S2. The cloud computing resource scheduling module receives real-time data, calls the improved genetic algorithm and reinforcement learning model, and combines historical data to generate and dynamically optimize the scheduling plan. The genetic algorithm takes maximizing equipment utilization as its objective function. S3. The experimental task allocation and progress monitoring module allocates tasks according to the scheduling plan and uses the Hungarian algorithm. It records the task node timestamps and pushes the progress through blockchain technology. The data security and privacy protection module manages access permissions based on the RBAC model. S4. The data analysis and report generation module calls machine learning models to analyze historical and task data, and outputs optimization reports. Federated learning technology is used when multiple laboratories conduct joint analysis. S5. The early warning and anomaly handling module monitors data in real time. When the data exceeds the level three early warning threshold, it triggers an early warning and performs emergency handling. In case of serious anomalies, it notifies the cloud computing resource scheduling module to adjust the plan. S6. The data security and privacy protection module ensures the security of data transmission and access throughout the entire process, including but not limited to data encryption and access control.

5. The laboratory management and scheduling method according to claim 4, characterized in that, The genetic algorithm used in step S2 takes task priority, equipment load and personnel skills as constraints, and the reinforcement learning model dynamically optimizes the scheduling plan based on real-time feedback data to achieve the best match between equipment, tasks and personnel.

6. The laboratory management and scheduling method according to claim 4, characterized in that, In step S3, the task-person-equipment association graph constructed by the experimental task allocation and progress monitoring module comprehensively considers the historical task completion efficiency of personnel, current load, and equipment availability to ensure the rationality and efficiency of task allocation. Furthermore, the task nodes recorded by blockchain technology include timestamps of key nodes such as task reception, equipment activation, and data upload.

7. The laboratory management and scheduling method according to claim 4, characterized in that, The machine learning model used in the data analysis and report generation module in step S4 includes the random forest model. The analysis content includes equipment usage frequency, idle time period, and personnel efficiency trend. The output optimization report includes suggestions for cross-laboratory equipment sharing and personalized skills training directions for personnel.

8. The laboratory management and scheduling method according to claim 4, characterized in that, The emergency response plan of the early warning and anomaly handling module includes operations such as automatic equipment shutdown, environmental parameter adjustment and equipment linkage startup, and automatic task transfer to backup personnel. The operation records of the emergency handling process are stored using blockchain technology to ensure that the anomaly handling is traceable.

Images