Experiment design and supervision system and method

Abstract

The invention discloses an experiment design and supervision system and method, and belongs to the field of artificial intelligence. According to experiment requirements and sample characteristics, an experiment scheme is generated by adopting an experiment model and combining a local knowledge base and internet retrieval content; according to the experiment scheme, an experiment target is disassembled into specific equipment operation instructions, and instrument equipment and a robot are controlled to complete an action sequence; constructing a structured security rule base, processing unstructured information by using a large model, and checking whether the experimental scheme and the operation instruction violate security rules or not; the method comprises the steps of constructing a multi-field ethical rule base, extracting ethical related elements in an experiment scheme, and examining whether the ethical related elements conform to rules or not based on the ethical rule base, so that an experiment task is automatic and intelligent, the experiment efficiency is improved, and the experiment safety and compliance are guaranteed.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence, and in particular to an experimental design and monitoring system and method. Background Technology

[0002] Traditional experimental tasks are designed and supervised largely by manual labor. As experimental tasks become increasingly complex and involve more interdisciplinary knowledge, the requirements for the standardization, safety, and ethical compliance of experimental operations are becoming more stringent, and traditional manual methods are gradually revealing many problems.

[0003] When designing experimental protocols manually, a significant amount of time is often required to review materials and consider various factors. Furthermore, due to insufficient personal experience or inadequate planning, the protocols may suffer from scientific flaws and inefficiency. During experimental supervision, because it involves multiple aspects such as equipment operation safety, experimental environment safety, and adherence to ethical standards, manual supervision struggles to achieve comprehensive, real-time, and precise monitoring, easily leading to safety hazards or violations of ethical norms.

[0004] Furthermore, the lack of effective coordination and collaboration between various stages of the experiment, from planning to execution, and the untimely and inaccurate transmission of information may lead to consequences such as interruption of the experimental process and unreliable results. Summary of the Invention

[0005] In order to overcome the shortcomings of the prior art, one of the objectives of this invention is to provide a system for the automated and intelligent design and supervision of experimental tasks, so as to improve experimental efficiency and ensure experimental safety and compliance.

[0006] To overcome the shortcomings of the existing technology, the second objective of this invention is to provide a method for the automated and intelligent design and supervision of experimental tasks, so as to improve experimental efficiency and ensure experimental safety and compliance.

[0007] One of the objectives of this invention is achieved through the following technical solution: An experimental design and monitoring method, comprising the following steps: Design experimental procedures and parameters: Based on experimental requirements and sample characteristics, adopt experimental models and combine local knowledge bases with Internet search content to generate experimental plans; Motion design: Based on the experimental plan, the experimental objective is broken down into specific equipment operation instructions, and the instruments and robots are controlled to complete the motion sequence; Security Detection: Construct a structured security rule base, process unstructured information with a large model, and check whether the experimental scheme and operation instructions violate security rules; Ethical review: Construct a multi-domain ethical rule base, extract ethically relevant elements from the experimental design, and review whether the ethically relevant elements comply with the rules based on the ethical rule base.

[0008] Furthermore, the design experimental procedure and parameter steps specifically include the following steps: Requirements Analysis: Using natural language processing technology, the system receives user input in natural language, extracts core elements, and outputs structured requirements. Sample feature modeling: Integrate local knowledge base sample data, construct sample features, and combine local knowledge graph and network information to generate association rules between samples and experiments; Generate experimental plan: Based on the standard process template in the knowledge graph of experimental type matching, adjust the step details according to the sample characteristics, and output the optimal experimental plan.

[0009] Furthermore, the motion design step specifically includes the following steps: Construction of Step and Action Mapping: Constructing an experimental step-device action mapping library, defining action logic based on a state machine model; Generate device instructions: For different devices' communication protocols, build a protocol adaptation layer to convert actions into instructions that the devices can recognize; Correction instructions: Receive the real-time execution status of the device / robot, correct subsequent actions through closed-loop control, report the operation status in real time, and receive safety correction instructions.

[0010] Furthermore, the security detection step specifically includes the following steps: Security checks: Build a structured security rule base and use a rule engine to check in real time whether experimental plans and operation instructions violate the rules; Anomaly Response: Acquire laboratory sensor data, monitor real-time data through time series analysis, identify hidden risks using anomaly detection models, and trigger corresponding responses to anomalies; Output results: Outputs the schemes, instructions, and abnormal situations that violate security rules; Solution optimization: When there are schemes, instructions or abnormal situations that violate safety rules, the experimental procedures and parameters are redesigned based on the output results.

[0011] Furthermore, the safety rule base includes any one or more of equipment safety rules, environmental safety rules, and operating procedure rules.

[0012] Furthermore, the ethical review process specifically includes the following steps: Constructing ethical rules: Building a multi-domain ethical rule base and using knowledge graphs to represent the logical relationships between rules; Review: Extract ethically relevant elements from the experimental design through semantic parsing, and check whether the elements conform to the ethical rule base based on the rule reasoning engine; Solution optimization: When elements that do not comply with the ethical rule base exist, the experimental procedures and parameters are redesigned based on the review results.

[0013] The second objective of this invention is achieved by the following technical solution: An experimental design and monitoring system is provided for implementing any of the above-described experimental design and monitoring methods. The system includes an experimental scheme generation module, an action design module, a safety detection module, and an ethics review module. The experimental scheme generation module is communicatively connected to the action design module, the safety detection module, and the ethics review module. The experimental scheme generation module generates an experimental scheme based on experimental requirements and sample characteristics, using an experimental model and combining local knowledge base and internet search content. The action design module, based on the experimental scheme, breaks down the experimental objective into specific equipment operation instructions, controlling instruments and robots to complete action sequences. The safety detection module constructs a structured safety rule base, processes unstructured information using a large model, and checks whether the experimental scheme and operation instructions violate safety rules. The ethics review module constructs a multi-domain ethics rule base, extracts ethically relevant elements from the experimental scheme, and reviews whether the ethically relevant elements comply with the rules based on the ethics rule base.

[0014] Furthermore, the experimental scheme generation module includes a requirement analysis module, a sample characteristic modeling module, and a generation module. The requirement analysis module uses natural language processing technology to receive natural language requirements input by the user, extract core elements, and output structured requirements. The sample characteristic modeling module integrates sample data from the local knowledge base, constructs sample features, and combines local knowledge graphs and network information to generate association rules between samples and experiments. The generation module, based on the standard process template in the experiment type matching knowledge graph, adjusts the step details according to sample characteristics and outputs the optimal experimental scheme.

[0015] Furthermore, the action design module includes a mapping module, a command generation module, and a command correction module. The mapping module is communicatively connected to the command generation module. The mapping module constructs an experimental step-device action mapping library and defines action logic based on a state machine model. The command generation module constructs a protocol adaptation layer for different device communication protocols, converting actions into device-recognizable commands. The command correction module receives the real-time execution status of the device / robot, corrects subsequent actions through closed-loop control, reports the operation status in real time, and receives safety correction commands.

[0016] Furthermore, the safety detection module includes an inspection module, an anomaly response module, an output module, and a scheme optimization module. The inspection module constructs a structured safety rule base and uses a rule engine to check in real time whether experimental schemes and operating instructions violate the rules. The anomaly response module acquires laboratory sensor data, monitors real-time data through time series analysis, identifies hidden risks using an anomaly detection model, and triggers corresponding responses to anomalies. The output module outputs schemes, instructions, and anomalies that violate safety rules. When schemes, instructions, or anomalies that violate safety rules exist, the scheme optimization module redesigns the experimental process and parameters based on the output results.

[0017] Compared to existing technologies, the experimental design and monitoring system of this invention generates experimental plans based on experimental requirements and sample characteristics, using experimental models and combining local knowledge bases with internet search content. According to the experimental plans, the experimental objectives are broken down into specific equipment operation instructions, controlling instruments and robots to complete action sequences. A structured safety rule base is constructed to process unstructured information using a large model, checking whether the experimental plans and operation instructions violate safety rules. A multi-domain ethics rule base is constructed to extract ethically relevant elements from the experimental plans, reviewing whether these elements comply with the rules based on the ethics rule base. This automates and intelligentizes experimental tasks, improving experimental efficiency and ensuring experimental safety and compliance. Attached Figure Description

[0018] Figure 1 This is a flowchart of the experimental design and monitoring method of the present invention; Figure 2 This is a framework diagram of the experimental design and monitoring system of this invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] It should be noted that when a component is said to be "fixed to" another component, it can be directly on the other component or fixed through another intermediate component. When a component is said to be "connected to" another component, it can be directly connected to the other component or may also have another intermediate component present. When a component is said to be "set to" another component, it can be directly set on the other component or may also have another intermediate component present.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0022] Please see Figure 1 This application discloses an experimental design and monitoring method, comprising the following steps: Design experimental procedures and parameters: Based on experimental requirements and sample characteristics, adopt experimental models and combine local knowledge bases with Internet search content to generate experimental plans; Motion design: Based on the experimental plan, the experimental objective is broken down into specific equipment operation instructions, and the instruments and robots are controlled to complete the motion sequence; Security Detection: Construct a structured security rule base, process unstructured information with a large model, and check whether the experimental scheme and operation instructions violate security rules; Ethical review: Construct a multi-domain ethical rule base, extract ethically relevant elements from the experimental design, and review whether the ethically relevant elements comply with the rules based on the ethical rule base.

[0023] The specific steps for designing the experimental procedure and parameters are as follows: Requirements Analysis: Using natural language processing technology, the system receives user input in natural language, extracts core elements, and outputs structured requirements. Sample feature modeling: Integrate local knowledge base sample data, construct sample features, and combine local knowledge graph and network information to generate association rules between samples and experiments; Generate experimental plan: Based on the standard process template in the knowledge graph of experimental type matching, adjust the step details according to the sample characteristics, and output the optimal experimental plan.

[0024] In the requirements analysis step, the natural language requirements input by the user include one or more of the following: text, voice, video, or files.

[0025] The motion design process specifically includes the following steps: Construction of Step and Action Mapping: Constructing an experimental step-device action mapping library, defining action logic based on a state machine model; Generate device instructions: For different devices' communication protocols, build a protocol adaptation layer to convert actions into instructions that the devices can recognize; Correction instructions: Receive the real-time execution status of the device / robot, correct subsequent actions through closed-loop control, report the operation status in real time, and receive safety correction instructions.

[0026] The safety inspection process specifically includes the following steps: Security checks: Build a structured security rule base and use a rule engine to check in real time whether experimental plans and operation instructions violate the rules; Anomaly Response: Acquire laboratory sensor data, monitor real-time data through time series analysis, identify hidden risks using anomaly detection models, and trigger corresponding responses to anomalies; Output results: Outputs the schemes, instructions, and abnormal situations that violate security rules; Solution optimization: When there are schemes, instructions or abnormal situations that violate safety rules, the experimental procedures and parameters are redesigned based on the output results.

[0027] In the safety inspection process, the safety rule base includes any one or more of the following: equipment safety rules, environmental safety rules, and operating procedure rules.

[0028] The ethical review process specifically includes the following steps: Constructing ethical rules: Building a multi-domain ethical rule base and using knowledge graphs to represent the logical relationships between rules; Review: Extract ethically relevant elements from the experimental design through semantic parsing, and check whether the elements conform to the ethical rule base based on the rule reasoning engine; Solution optimization: When elements that do not comply with the ethical rule base exist, the experimental procedures and parameters are redesigned based on the review results.

[0029] Please continue reading. Figure 2 This application also discloses an experimental design and monitoring system for implementing the above-mentioned experimental design and monitoring methods.

[0030] The experimental design and monitoring system includes modules for generating experimental plans, motion design, safety detection, and ethics review. The experimental plan generation module communicates with these modules. The experimental plan generation module generates experimental plans based on experimental requirements and sample characteristics, using an experimental model and combining local knowledge base and internet search results. The motion design module breaks down the experimental objectives into specific equipment operation instructions based on the experimental plan, controlling the instruments and robots to complete the action sequence. The safety detection module constructs a structured safety rule base, uses a large model to process unstructured information, and checks whether the experimental plan and operation instructions violate safety rules. The ethics review module constructs a multi-domain ethics rule base, extracts ethically relevant elements from the experimental plan, and reviews whether these elements comply with the rules based on the ethics rule base.

[0031] Specifically, the experimental design and monitoring system uses a user interface for input and output. Input and output can be one or more of text, voice, video, or files.

[0032] The experimental plan generation module includes a requirements analysis module, a sample characteristic modeling module, and a generation module. The requirements analysis module uses natural language processing technology to receive natural language requirements input by the user, extract core elements, and output structured requirements. The sample characteristic modeling module integrates sample data from the local knowledge base, constructs sample features, and combines local knowledge graphs and online information to generate association rules between samples and experiments. The generation module adjusts the step details based on the standard process template in the experiment type matching knowledge graph, and outputs the optimal experimental plan.

[0033] The action design module includes a mapping module, a command generation module, and a command correction module. The mapping module and the command generation module are communicatively connected. The mapping module constructs an experimental step-device action mapping library and defines action logic based on a state machine model. The command generation module constructs a protocol adaptation layer for different device communication protocols, converting actions into device-recognizable commands. The command correction module receives the real-time execution status of the device / robot, corrects subsequent actions through closed-loop control, reports the operation status in real time, and receives safety correction commands. In this application, the device can be any one or more of experimental equipment, robots, centrifuges, pipettes, and spectrometers.

[0034] The safety detection module includes an inspection module, an anomaly response module, an output module, and a scheme optimization module. The inspection module constructs a structured safety rule base and uses a rule engine to check in real time whether experimental schemes and operating instructions violate the rules. The anomaly response module acquires laboratory sensor data, monitors real-time data through time series analysis, identifies hidden risks using an anomaly detection model, and triggers corresponding responses to anomalies. The output module outputs schemes, instructions, and anomalies that violate safety rules. When schemes, instructions, or anomalies that violate safety rules are found, the scheme optimization module redesigns the experimental process and parameters based on the output results. Sensors include temperature sensors, humidity sensors, gas concentration sensors, equipment vibration sensors, and pressure sensors.

[0035] The ethics review module includes an ethics rule construction module, a review module, and a scheme optimization module. The ethics rule construction module builds a multi-domain ethics rule base and uses a knowledge graph to represent the logical relationships between rules. The review module extracts ethics-related elements from the experimental scheme through semantic parsing and checks whether the elements conform to the ethics rule base based on a rule reasoning engine. When there are elements that do not conform to the ethics rule base, the scheme optimization module redesigns the experimental process and parameters based on the review results.

[0036] Compared to existing technologies, the experimental design and monitoring system of this invention generates experimental plans based on experimental requirements and sample characteristics, using experimental models combined with local knowledge bases and internet search content. According to the experimental plan, the experimental objectives are broken down into specific equipment operation instructions, controlling instruments and robots to complete action sequences. A structured safety rule base is constructed to process unstructured information using a large model, checking whether the experimental plan and operation instructions violate safety rules. A multi-domain ethics rule base is constructed to extract ethically relevant elements from the experimental plan, reviewing whether these elements comply with the rules, thus automating and intelligentizing experimental tasks to improve experimental efficiency and ensure experimental safety and compliance.

[0037] The above embodiments merely illustrate several implementation methods of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be noted that, for those skilled in the art, several modifications and improvements can be made without departing from the concept of the present invention. These are all equivalent modifications and improvements made to the above embodiments based on the essential technology of the present invention, and all of these fall within the protection scope of the present invention.

Claims

1. An experimental design and monitoring method, characterized in that, Includes the following steps: Design experimental procedures and parameters: Based on experimental requirements and sample characteristics, adopt experimental models and combine local knowledge bases with Internet search content to generate experimental plans; Motion design: Based on the experimental plan, the experimental objective is broken down into specific equipment operation instructions, and the instruments and robots are controlled to complete the motion sequence; Security Detection: Construct a structured security rule base, process unstructured information with a large model, and check whether the experimental scheme and operation instructions violate security rules; Ethical review: Construct a multi-domain ethical rule base, extract ethically relevant elements from the experimental design, and review whether the ethically relevant elements comply with the rules based on the ethical rule base.

2. The experimental design and monitoring method according to claim 1, characterized in that: The experimental design process and parameter steps specifically include the following steps: Requirements Analysis: Using natural language processing technology, the system receives user input in natural language, extracts core elements, and outputs structured requirements. Sample feature modeling: Integrate local knowledge base sample data, construct sample features, and combine local knowledge graph and network information to generate association rules between samples and experiments; Generate experimental plan: Based on the standard process template in the knowledge graph of experimental type matching, adjust the step details according to the sample characteristics, and output the optimal experimental plan.

3. The experimental design and monitoring method according to claim 1, characterized in that: The motion design process specifically includes the following steps: Construction of Step and Action Mapping: Constructing an experimental step-device action mapping library, defining action logic based on a state machine model; Generate device instructions: For different devices' communication protocols, build a protocol adaptation layer to convert actions into instructions that the devices can recognize; Correction instructions: Receive the real-time execution status of the device / robot, correct subsequent actions through closed-loop control, report the operation status in real time, and receive safety correction instructions.

4. The experimental design and monitoring method according to claim 1, characterized in that: The security testing process specifically includes the following steps: Security checks: Build a structured security rule base and use a rule engine to check in real time whether experimental plans and operation instructions violate the rules; Anomaly Response: Acquire laboratory sensor data, monitor real-time data through time series analysis, identify hidden risks using anomaly detection models, and trigger corresponding responses to anomalies; Output results: Outputs the schemes, instructions, and abnormal situations that violate security rules; Solution optimization: When there are schemes, instructions or abnormal situations that violate safety rules, the experimental procedures and parameters are redesigned based on the output results.

5. The experimental design and monitoring method according to claim 4, characterized in that: The safety rule base includes any one or more of the following: equipment safety rules, environmental safety rules, and operating procedure rules.

6. The experimental design and monitoring method according to claim 1, characterized in that: The ethical review process specifically includes the following steps: Constructing ethical rules: Building a multi-domain ethical rule base and using knowledge graphs to represent the logical relationships between rules; Review: Extract ethically relevant elements from the experimental design through semantic parsing, and check whether the elements conform to the ethical rule base based on the rule reasoning engine; Solution optimization: When elements that do not comply with the ethical rule base exist, the experimental procedures and parameters are redesigned based on the review results.

7. An experimental design and monitoring system for implementing the experimental design and monitoring method as described in any one of claims 1-6, characterized in that: The experimental design and monitoring system includes an experimental scheme generation module, an action design module, a safety detection module, and an ethics review module. The experimental scheme generation module is communicatively connected to the action design module, the safety detection module, and the ethics review module. The experimental scheme generation module generates an experimental scheme based on experimental requirements and sample characteristics, using an experimental model and combining local knowledge base and internet search content. The action design module, based on the experimental scheme, breaks down the experimental objective into specific equipment operation instructions, controlling instruments and robots to complete action sequences. The safety detection module constructs a structured safety rule base, uses a large model to process unstructured information, and checks whether the experimental scheme and operation instructions violate safety rules. The ethics review module constructs a multi-domain ethics rule base, extracts ethically relevant elements from the experimental scheme, and reviews whether these ethically relevant elements comply with the rules based on the ethics rule base.

8. The experimental design and monitoring system according to claim 7, characterized in that: The experimental scheme generation module includes a requirement analysis module, a sample characteristic modeling module, and a generation module. The requirement analysis module uses natural language processing technology to receive natural language requirements input by the user, extract core elements, and output structured requirements. The sample characteristic modeling module integrates sample data from the local knowledge base, constructs sample features, and combines local knowledge graphs and network information to generate association rules between samples and experiments. The generation module, based on the standard process template in the experiment type matching knowledge graph, adjusts the step details according to sample characteristics and outputs the optimal experimental scheme.

9. The experimental design and monitoring system according to claim 7, characterized in that: The action design module includes a mapping module, a command generation module, and a command correction module. The mapping module is communicatively connected to the command generation module. The mapping module constructs an experimental step-device action mapping library and defines action logic based on a state machine model. The command generation module constructs a protocol adaptation layer for different device communication protocols, converting actions into device-recognizable commands. The command correction module receives the real-time execution status of the device / robot, corrects subsequent actions through closed-loop control, reports the operation status in real time, and receives safety correction commands.

10. The experimental design and monitoring system according to claim 7, characterized in that: The safety detection module includes an inspection module, an anomaly response module, an output module, and a scheme optimization module. The inspection module constructs a structured safety rule base and uses a rule engine to check in real time whether experimental schemes and operating instructions violate the rules. The anomaly response module acquires laboratory sensor data, monitors real-time data through time series analysis, identifies hidden risks using an anomaly detection model, and triggers corresponding responses to anomalies. The output module outputs schemes, instructions, and anomalies that violate safety rules. When schemes, instructions, or anomalies that violate safety rules are found, the scheme optimization module redesigns the experimental procedures and parameters based on the output results.

Images