Laboratory data analysis method

Abstract

The invention discloses a laboratory data analysis method, and relates to the technical field of laboratory data, and the method comprises the steps: obtaining the identification information of operators in a laboratory and the experiment time information of each operator; acquiring instrument names of instruments which are sequentially contacted by operation of each experimenter and sample names of samples which are sequentially contacted by operation of each experimenter; acquiring sensor data of an experiment process according to the experiment time information; inputting the identification information of the operator, the experiment time information, the instrument name, the sample name and the sensor data into a pre-trained analysis model to obtain a stress value of the laboratory; and outputting alarm information according to the stress value. According to the invention, the operation of the operator is tracked, and the risk degree possibly brought to the laboratory by the operation is quantified, so that the safety of the laboratory is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of laboratory data, and in particular to a laboratory data analysis method. Background Art

[0002] In a laboratory setting, the conclusion of an experiment is far from the end of safety work. The inherent difficulty in identifying safety hazards left behind after an experiment presents a very real and challenging problem in laboratory safety management. This difficulty is not accidental, but rather stems from the interplay of multiple factors.

[0003] Safety hazards at the end of a laboratory's operation are often difficult to detect due to their concealed and latent nature. On the one hand, trace chemical residues after an experiment (such as uncleaned organic solvents) may slowly react with changes in ambient temperature and humidity, generating toxic gases or explosives. However, initial concentrations are extremely low and cannot be detected by the senses. On the other hand, static risks after equipment shutdown are equally hidden, such as unreleased residual pressure in a high-pressure reactor or microcracks in a centrifuge rotor. These may appear static but may suddenly malfunction upon restart. Even more complex are waste risks—mixed waste liquids (such as those containing cyanide and acidic solutions) may not show any signs of activity initially, but may quietly react during storage to generate highly toxic gases. These hazards are impossible to predict with the naked eye.

[0004] The difficulty of human judgment stems primarily from the natural limitations of the senses: colorless and odorless harmful gases (such as carbon monoxide), trace radiation, or volatile chemicals are completely beyond human perception, and conventional detection tools (such as test strips) often give "false safety" signals due to insufficient sensitivity. Secondly, cognitive biases and operational inertia also become obstacles: experimenters tend to focus on the main reaction and ignore the accumulation of byproducts (such as the slow enrichment of organic peroxides), and fatigue is more likely to simplify the final process (such as leaving the fume hood open). More importantly, the complexity of modern laboratories far exceeds individual experience: the dynamic correlation of multiple hidden dangers (such as circuit aging combined with ventilation failure) or sudden environmental interference (such as vibration causing gas cylinders to tip over) is almost impossible to predict manually.

[0005] Therefore, how to improve laboratory safety has become a technical problem that needs to be solved urgently. Summary of the Invention

[0006] The technical problem solved by the present invention is that it is difficult to timely monitor safety hazards in a laboratory.

[0007] To solve the above technical problems, the present invention provides the following technical solutions: a laboratory data analysis method, comprising: obtaining identification information of operators in the laboratory and experimental time information of each operator; obtaining the instrument name of the instrument that each experimenter sequentially contacts, and the sample name of the sample that each experimenter sequentially contacts; obtaining sensor data of the experimental process based on the experimental time information; inputting the identification information of the operator, the experimental time information, the instrument name, the sample name and the sensor data into a pre-trained analysis model to obtain the stress value of the laboratory; and outputting alarm information based on the stress value.

[0008] Preferably, before obtaining the identification information of the operator in the laboratory, the method also includes: in response to a person entering the laboratory, tracking the movement trajectory of the person through a behavior recording device and detecting the posture information of the person; if the posture information of the person switches from standing to sitting, obtaining the workstation identification where the person is seated; controlling the start of the experimental recording device at the workstation according to the workstation identification; performing facial recognition on the person through the experimental recording device to obtain the identification information of the person; capturing the eye focus and hand movements of the person through the experimental recording device; if the person's eyes are focused on the experimental sample on the workstation and the person's hands are in contact with the experimental instrument, determining that the person is an operator.

[0009] Preferably, in response to a person entering the laboratory, the movement trajectory of the person is tracked by a behavior recording device, and the posture information of the person is detected, including: in response to the person entering the laboratory, recording the start time of the person entering the laboratory; tracking the movement trajectory of the person by a behavior recording device, and detecting the posture information of the person; obtaining the identification information of the operators in the laboratory and the experimental time information of each operator, including: if the person is an operator, sending the identification information of the operator by the experimental recording device; tracking the movement trajectory of the operator by the behavior recording device until the movement trajectory of the operator is lost for more than a preset time, then determining the last time the operator appears by the behavior recording device; determining the last time as the end time; and determining the experimental time information of the operator based on the start time and the end time.

[0010] Preferably, the behavior recording device includes a camera module, a processing module, a communication module and a radio frequency information module.

[0011] Preferably, electronic tags are provided on the instruments in the laboratory; the obtaining of the instrument name of the instrument that each experimenter sequentially contacts and the sample name of the sample that each experimenter sequentially contacts includes: if the behavior recording device recognizes that the operator enters the instrument area, controlling the radio frequency signal transmission module to start; reading the electronic tag information of the instrument through multiple radio frequency signal modules; comparing the electronic tag information read last time with the electronic tag information currently read, and determining the electronic tag that exists in the currently read electronic tag information and does not exist in the electronic tag information read last time as the operator's current contact instrument; determining the instrument name according to the electronic tag of the operator's current contact instrument.

[0012] Preferably, the container of the sample in the laboratory is provided with an electronic tag; the obtaining of the instrument name of the instrument that each experimenter contacts in sequence and the sample name of the sample that each experimenter contacts in sequence also includes: if the behavior recording device recognizes that the operator enters the sample area, the radio frequency signal transmission module is controlled to start; the electronic tag information of the sample is read through multiple radio frequency signal modules; the electronic tag information read last time and the electronic tag information currently read are compared, and the electronic tag that exists in the currently read electronic tag information and does not exist in the electronic tag information read last time is determined as the current contact sample of the operator; the sample name is determined according to the electronic tag of the current contact sample of the operator.

[0013] Preferably, the analysis model is a neural network model; the method for generating training samples of the analysis model includes: searching the monitoring records, dangerous event handling records and sensor sensing data records of the laboratory; obtaining the monitoring records corresponding to the dangerous event handling records, and extracting the identification information, experimental time information, instrument name, and sample name of the operator corresponding to the dangerous event handling records from the monitoring records; obtaining the sensor data records corresponding to the dangerous event handling records, and extracting sensor data from the sensor data records; and determining the duress value corresponding to the dangerous event handling record based on the accident information in the dangerous event handling record.

[0014] Preferably, before outputting the alarm information according to the duress value, the method further includes: determining the experimental project of each experimenter according to the instrument name of the instrument that each experimenter sequentially contacts and the sample name of the sample that each experimenter sequentially contacts; obtaining standard process specification information from a preset standard process library according to the experimental project of each experimenter; scoring the operation of the experimenter according to the standard process specification information; outputting the alarm information according to the duress value includes: outputting the alarm information according to the score of each experimenter and the duress value.

[0015] Preferably, outputting the alarm information according to the score of each experimenter and the stress value includes: generating alarm details according to the score of each experimenter, the experiment item and the stress value; and outputting the alarm details.

[0016] Preferably, the outputting of the alarm details comprises: acquiring the communication address of the operator according to the identification information of the operator; and pushing the alarm details to the operator according to the communication address.

[0017] The beneficial effects of the present invention are as follows: the identification information of the operators in the laboratory and the experimental time information of each operator are obtained, the instrument names of the instruments that each experimenter sequentially contacts and the sample names of the samples that each experimenter sequentially contacts are obtained, the sensor data of the experimental process is obtained according to the experimental time information, the operator's identification information, experimental time information, instrument name, sample name and sensor data are input into a pre-trained analysis model to obtain the duress value of the laboratory; alarm information is output according to the duress value, so as to track the operator's operation and quantify the degree of risk that the operation may bring to the laboratory, thereby improving the safety of the laboratory. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of the basic flow of a laboratory data analysis method provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0020] Example 1, reference Figure 1 , an embodiment of the present invention, provides a laboratory data analysis method, including S110~S150: S110, obtaining identification information of operators in the laboratory and experimental time information of each operator.

[0021] S120, obtaining the instrument name of each instrument that each experimenter sequentially contacts and the sample name of each sample that each experimenter sequentially contacts.

[0022] S130: Acquire sensor data of the experiment process according to the experiment time information.

[0023] S140 , inputting the operator's identification information, experiment time information, instrument name, sample name, and sensor data into a pre-trained analysis model to obtain a stress value of the laboratory.

[0024] S150: Outputting warning information according to the duress value.

[0025] Safety hazards within the laboratory are embedded in the operations of laboratory personnel, so data related to safety hazards can be obtained from the laboratory personnel's operations. For example, if organic solvents are not cleaned up in a timely manner, they will slowly react with changes in ambient temperature and humidity, generating toxic gases or explosives.

[0026] For this, risk-related factors are extracted: number of operators, length of experimental time, instrument category, sample category and environmental data, so as to quantify the degree of risk that the operator's operation may bring to the laboratory based on the laboratory's risk-related factors.

[0027] Among them, the coercion value is a comprehensive multi-factor output of the pre-trained analysis model, which is used to reflect the quantitative indicator of the real-time risk of the laboratory, so as to convert the fuzzy safety status into quantifiable data and provide early warning; the sensor data is the environmental parameters collected in real time through the deployment of the Internet of Things sensor network, such as temperature, humidity, and gas concentration; further, the device status, such as current or device temperature data, can also be collected through sensors.

[0028] The operator's identification information, experiment time, instrument name, sample name, and sensor data are fed into a pre-trained analysis model to generate a laboratory stress score. Specifically, the relevant data on personnel, instruments, samples, and environmental parameters are fed into a pre-trained neural network model for multimodal fusion analysis. Specifically, the stress score is a dynamic risk score (typically ranging from 0 to 1) generated by a multimodal neural network model that fuses and analyzes heterogeneous data such as laboratory operator operations, equipment status, and environmental parameters. Its core design includes the following technologies: feature fusion mechanism, such as the VGG19 image style transfer model, which extracts image content and style features through convolutional layers, and designs content loss (Content Loss) and style loss (Style Loss) functions to achieve multi-source feature fusion. In a physical laboratory scenario, for example, personnel operation behavior (video stream, containing operator identification information, experimental time information, and sample name labeling information), equipment current signal (time series data, containing instrument name and instrument usage labeling information), and gas concentration (sensor stream) can be regarded as different modal inputs to construct a fusion loss function; dynamic weight allocation, setting the parameter update logic of the three-layer neural network (ThreeLayerNet), and the model automatically learns the weight ratio of each risk factor through back propagation (such as the weight of not wearing gloves > the weight of exceeding the temperature and humidity standards).

[0029] The neural network model outputs the duress value to generate warning information and accurately push risks to avoid false alarms and missed reports.

[0030] The method for generating training samples of the analysis model includes S210 to S240: S210, searching for laboratory monitoring records, dangerous incident handling records, and sensor data records; S220, obtaining a monitoring record corresponding to the dangerous event handling record, and extracting the identification information of the operator, experiment time information, instrument name, and sample name corresponding to the dangerous event handling record from the monitoring record; S230, obtaining a sensor data record corresponding to the dangerous event processing record, and extracting sensor data from the sensor data record; S240: Determine a duress value corresponding to the dangerous event processing record according to the accident information in the dangerous event processing record.

[0031] For dangerous event records, a historical accident report library is obtained, and sensor data and surveillance video timestamps are associated to obtain the real risk mapping of dangerous events and risk-related factors.

[0032] The duress value labeling is to label the risk level of historical data. Specifically, it can be graded according to the consequences of the accident, for example, minor = 30, fire = 90, explosion = 100.

[0033] When building a risk prediction neural network, you can use the LSTM+Attention network to process time series data (operation sequence + sensor stream) to capture the dynamic risk evolution patterns.

[0034] Preferably, before S110, the method further includes S101 to S106: S101 , in response to a person entering a laboratory, tracking the person's movement trajectory through a behavior recording device and detecting the person's posture information.

[0035] S102: If the posture information of the person is switched from standing to sitting, the workstation identification of the seat where the person is seated is obtained.

[0036] S103, controlling the start-up of the experimental recording equipment at the workstation according to the workstation identification.

[0037] S104, performing facial recognition on the person through the experimental recording device to obtain the identification information of the person.

[0038] S105, capturing the eye focus and hand movements of the person through an experimental recording device.

[0039] S106: If the person's eyes are focused on the experimental sample on the workstation and the person's hands are in contact with the experimental instrument, the person is determined to be an operator.

[0040] Among them, the behavior recording device is an AI camera with posture tracking, which can identify the switching between standing and sitting postures through the OpenPose algorithm and automatically bind people to workstations; the experimental recording device is a terminal that integrates facial recognition, eye movement and hand tracking, and deploys a depth camera at the workstation to capture movements.

[0041] Eye focus detection can be used to determine whether the line of sight is locked on the experimental sample. Specifically, the YOLOv5 target detection model can be used to frame the sample area and calculate the line of sight intersection to avoid misjudgment of non-operational states. Hand contact detection can identify the interaction between human hands and instruments. Specifically, MediaPipe gesture recognition and instrument contour matching can be used to ensure the validity of the recording.

[0042] Preferably, S101 includes: in response to a person entering the laboratory, recording the start time of the person entering the laboratory; tracking the movement trajectory of the person through a behavior recording device, and detecting the posture information of the person; S110 also includes: if the person is an operator, sending the identification information of the operator through the experimental recording device; tracking the movement trajectory of the operator through the behavior recording device until the operator's movement trajectory is lost for more than a preset time, and determining the last time the operator appeared through the behavior recording device; determining the last time as the end time; and determining the experimental time information of the operator based on the start time and the end time.

[0043] Preferably, the behavior recording device includes a camera module, a processing module, a communication module and a radio frequency information module; an electronic tag is provided on the instrument in the laboratory, and an electronic tag is provided on the container of the sample in the laboratory; S120 includes: if the behavior recording device recognizes that the operator enters the instrument area, the radio frequency signal transmission module is controlled to start; the electronic tag information of the instrument is read through multiple radio frequency signal modules; the electronic tag information of the instrument is compared with the electronic tag information read last time and the electronic tag information currently read, and the electronic tag that exists in the electronic tag information currently read and does not exist in the electronic tag information read last time is determined as the operator's current contact instrument; the instrument name is determined according to the electronic tag of the operator's current contact instrument; similarly, if the behavior recording device recognizes that the operator enters the sample area, the radio frequency signal transmission module is controlled to start; the electronic tag information of the sample is read through multiple radio frequency signal modules; the electronic tag information of the sample is compared with the electronic tag information read last time and the electronic tag information currently read, and the electronic tag that exists in the electronic tag information currently read and does not exist in the electronic tag information read last time is determined as the operator's current contact sample; the sample name is determined according to the electronic tag of the operator's current contact sample.

[0044] The radio frequency signal module can be a UHF RFID reader / writer, which deploys a multi-antenna array in the laboratory to cover the operating area and accurately identify through obstructions; the electronic tag is a passive RFID tag affixed to the instrument. The tag stores a unique ID mapping the instrument name to achieve zero-contact automatic identification.

[0045] The label difference comparison can dynamically update the contact instrument list. For example, it can scan once every 0.5 seconds and compare the difference between the previous and next label sets to accurately record the operation sequence (such as taking out the centrifuge first and then putting it back).

[0046] Preferably, before S150, the method also includes: determining the experimental project of each experimenter based on the instrument name of the instrument that each experimenter sequentially contacts and the sample name of the sample that each experimenter sequentially contacts; obtaining standard process specification information from a preset standard process library based on the experimental project of each experimenter; and scoring the experimenter's operation based on the standard process specification information.

[0047] The standard process library is a digital knowledge base of experimental SOPs, which is used to store operational specifications in a structured manner (such as "weights must be balanced before centrifugation") to provide a basis for judgment.

[0048] Operational scoring can compare actual behavior with the standard deviation and be used to deduct points based on the rule engine. For example, 20 points will be deducted for unbalanced weights to quantify human errors.

[0049] S150 includes: generating alarm details according to the score, experimental items and duress value of each experimenter; obtaining the communication address of the operator according to the identification information of the operator; and pushing the alarm details to the operator according to the communication address.

[0050] Alarm details are generated, including combining the duress value and the operation score. For example, the formula is: risk index = duress value × 0.7 + operation deviation × 0.3, where the operation deviation can be determined based on the experimental score. For example, after determining the actual experimental score through the method disclosed in the patent with publication number "CN112036840A", the degree of deviation is determined according to the actual experimental score and the full score of the preset experimental score. The settings of 0.7 and 0.3 in the formula are both empirical parameters, which can be set according to actual usage needs to distinguish between environmental risks and human errors. For example, if the duress value is 70 and the operation score is 50, the alarm is "high-risk operation: unprotected + ethanol leakage"; in another optional method, the duress value can be directly output together with the operation score. For example, the alarm information is output, the duress value is 70, and it is suspected that "unprotected leads to ethanol leakage".

[0051] Explain the whole process: Step 1: Experiment initiation: Researcher A swipes their card to enter the lab, and the behavior recording system tracks their movements. A sits down at workstation 3, triggering posture recognition, which automatically activates the workstation camera. Facial recognition confirms their identity, and their gaze is focused on the concentrated sulfuric acid sample, while they are holding a pipette, signaling the start of the experiment.

[0052] Step 2: Operation tracking: A walks towards the centrifuge area. The RFID reader scans the newly added tag Centrifuge-05, records the contact with the instrument, and collects environmental data in real time. The temperature and humidity sensor detects that the volatilization of H2SO4 causes a sharp increase in humidity.

[0053] Step 3: Risk analysis; the analysis model inputs include: Personnel: Researcher_A, Operation sequence: [Take H2SO4 sample, use Centrifuge-05], Sensors: Humidity +60%, Temperature +2°C; The model matches historical accident patterns and outputs a stress value of 85.

[0054] Step 4: Alarm generation; the process library detects that goggles are required for centrifugal operation, but video analysis A does not wear them, and the operation score is 40. The alarm details are generated: "[Emergency Alarm] Duress value 85 + Operation violation 40 ● Risk point: Centrifuge vibration accelerates acid volatilization ● Measures: Ventilate immediately + wear goggles” and push it to A’s mobile phone via WeChat for Business.

[0055] The embodiment of the present application obtains the identification information of the operators in the laboratory and the experimental time information of each operator, obtains the instrument name of the instrument that each experimenter sequentially contacts, and the sample name of the sample that each experimenter sequentially contacts, obtains the sensor data of the experimental process according to the experimental time information, inputs the operator's identification information, experimental time information, instrument name, sample name and sensor data into a pre-trained analysis model to obtain the duress value of the laboratory; outputs alarm information according to the duress value, so as to track the operator's operation and quantify the degree of risk that the operation may bring to the laboratory, thereby improving the safety of the laboratory.

[0056] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. The storage medium may be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0057] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A laboratory data analysis method, characterized in that: include: Obtain identification information of operators in the laboratory and experimental time information of each operator; Obtain the instrument name of each instrument that each experimenter sequentially touches, and the sample name of each sample that each experimenter sequentially touches; Acquire sensor data of the experimental process according to the experimental time information; Inputting the identification information of the operator, the experimental time information, the instrument name, the sample name and the sensor data into a pre-trained analysis model to obtain a stress value of the laboratory; Outputting warning information according to the stress value.

2. The method according to claim 1, wherein Before obtaining identification information of an operator in the laboratory, the method further includes: In response to a person entering the laboratory, tracking the person's movement trajectory through a behavior recording device and detecting the person's posture information; If the posture information of the person switches from standing to sitting, obtaining the workstation identification where the person is seated; Controlling the start of the experimental recording equipment at the workstation according to the workstation identification; Performing facial recognition on the person through the experimental recording device to obtain identification information of the person; Capturing the eye focus and hand movements of the person using the experimental recording equipment; If the eyes of the person are focused on the experimental sample on the workstation and the hands of the person are in contact with the experimental instrument, the person is determined to be an operator.

3. The method according to claim 2, wherein In response to a person entering the laboratory, tracking the person's movement trajectory by a behavior recording device and detecting the person's posture information includes: In response to a person entering the laboratory, recording a start time of the person entering the laboratory; Tracking the movement trajectory of the person through a behavior recording device and detecting the posture information of the person; The obtaining of identification information of operators in the laboratory and experimental time information of each operator includes: If the person is an operator, sending identification information of the operator through the experiment recording device; Tracking the operator's movement trajectory by the behavior recording device until the operator's movement trajectory is lost for a preset period of time, and then determining the last moment of the operator's appearance by the behavior recording device; determining the last moment as an end moment; The experiment time information of the operator is determined according to the start time and the end time.

4. The method according to claim 3, wherein The behavior recording device includes a camera module, a processing module, a communication module and a radio frequency information module.

5. The method according to claim 4, wherein The instruments in the laboratory are provided with electronic tags; the method of obtaining the instrument names of the instruments that each experimenter sequentially contacts and the sample names of the samples that each experimenter sequentially contacts includes: If the behavior recording device recognizes that the operator has entered the instrument area, the radio frequency signal transmission module is controlled to start; Reading electronic tag information of the instrument through multiple radio frequency signal modules; Comparing the electronic tag information read last time with the electronic tag information currently read, and determining the electronic tag that exists in the electronic tag information currently read but does not exist in the electronic tag information read last time as the current contact instrument of the operator; The name of the instrument is determined according to the electronic tag of the instrument currently in contact with the operator.

6. The method according to claim 5, wherein The containers of the samples in the laboratory are provided with electronic labels; the method of obtaining the names of the instruments that each experimenter sequentially contacts and the names of the samples that each experimenter sequentially contacts also includes: If the behavior recording device recognizes that the operator enters the sample area, the radio frequency signal transmission module is controlled to start; Reading the electronic tag information of the sample through multiple radio frequency signal modules; Comparing the electronic tag information read last time with the electronic tag information currently read, and determining the electronic tag that exists in the electronic tag information currently read but does not exist in the electronic tag information read last time as the current contact sample of the operator; The sample name is determined according to the electronic tag of the sample currently in contact with the operator.

7. The method according to claim 6, wherein The analysis model is a neural network model; The method for generating training samples of the analysis model includes: Searching for monitoring records, hazardous incident handling records, and sensor data records of the laboratory; Obtaining the monitoring record corresponding to the dangerous event handling record, and extracting the identification information of the operator corresponding to the dangerous event handling record, the experiment time information, the instrument name, and the sample name from the monitoring record; Acquire sensor data records corresponding to the dangerous event processing records, and extract sensor data from the sensor data records; The duress value corresponding to the dangerous event processing record is determined according to the accident information in the dangerous event processing record.

8. The method according to claim 7, wherein Before outputting the warning information according to the duress value, the method further includes: Determine the experimental project of each experimenter according to the name of the instrument that each experimenter sequentially contacts and the name of the sample that each experimenter sequentially contacts; Obtain standard process specification information from the preset standard process library according to each experimenter's experimental project; Scoring the experimenter's operation according to the standard process specification information; Outputting warning information according to the duress value includes: The warning information is output according to the score of each experimenter and the stress value.

9. The method according to claim 8, wherein Outputting the warning information according to the score of each experimenter and the stress value includes: Generate warning details based on each experimenter's score, experiment project and the stress value; Output the alarm details.

10. The method according to claim 9, wherein The outputting of the alarm details includes: Acquiring the communication address of the operator according to the identification information of the operator; Push the alarm details to the operator according to the communication address.

Images