Experiment information processing method, electronic equipment, storage medium and computer program product
Through the intelligent collaboration system and large model technology, the experimental information is automatically processed, which solves the problem that existing laboratory teaching methods cannot be batched or automated, and efficient and automated experimental teaching is achieved.
Patent Information
- Application Number
- CN202411829327.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-12
- Publication Date
- 2025-04-11
AI Technical Summary
The existing laboratory teaching methods rely on the time investment of teachers or senior staff, and cannot achieve batch or automated laboratory operation teaching.
Through the agent collaboration system, including experimental planning agents, step control agents and teaching interactive agents, the experimental information is automatically processed. The system uses a large model to carry out experimental step planning, result evaluation and experimental prompts to realize automated experimental teaching.
The automation and batchization of experimental teaching has been realized, labor costs have been reduced, and the efficiency and benefits of experimental teaching have been improved.
Smart Images
Figure CN119809192A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of large model application technology, and in particular to a method for processing experimental information, an electronic device, a computer-readable storage medium, and a computer program product. Background Art
[0002] At present, laboratory teaching mainly adopts manual teaching methods, for example, teachers guide students on experimental methods offline or online, students practice, and then teachers manually evaluate the results and correct errors and answer questions. This method relies on the time investment of teachers or senior staff, and cannot achieve batch or automated laboratory operation teaching. Summary of the invention
[0003] The purpose of the embodiments of the present application is to provide a method for processing experimental information and an electronic device, a storage medium, and a computer program product for automated and batch laboratory operation teaching.
[0004] On the one hand, the present application provides a method for processing experimental information, comprising:
[0005] Obtaining experimental content information through the experimental planning agent, and outputting an experimental step list based on the experimental content information;
[0006] Obtaining, by means of a step control agent, an experimental result corresponding to any experimental step in the experimental step list, and determining an evaluation result corresponding to the experimental result;
[0007] The teaching interactive agent outputs experimental prompt information based on the evaluation results.
[0008] In one embodiment, the step of obtaining the experiment content information through the experiment planning agent and outputting the experiment step list based on the experiment content information includes:
[0009] The experiment planning agent uses the experiment content information to recall a number of related documents in a preset knowledge base as context information, and constructs an experiment planning instruction with the context information;
[0010] The experiment planning agent delivers the experiment planning instructions to the first large model, so that the first large model returns the experiment step list.
[0011] In one embodiment, the method further comprises:
[0012] The experimental planning agent determines whether the experimental steps are successfully executed based on the evaluation results of the experimental steps, updates the experimental step list based on the determination results, and outputs the updated experimental step list.
[0013] In one embodiment, the step of controlling the intelligent agent to obtain the experimental result corresponding to any experimental step in the experimental step list includes:
[0014] Control the intelligent agent through the steps to obtain the experimental photos corresponding to any experimental step, and determine the experimental results based on the experimental photos; or
[0015] The steps are used to control the intelligent agent to obtain the voice input result corresponding to any experimental step, and to determine the experimental result based on the voice input result.
[0016] In one embodiment, determining the evaluation result corresponding to the experimental result includes:
[0017] Through the steps, the intelligent agent is controlled to recall a number of relevant documents in a preset knowledge base using the experimental results as context information, and an evaluation instruction is constructed using the context information;
[0018] Through the steps, the intelligent agent is controlled to hand over the evaluation instruction to the second large model, so that the second large model returns the evaluation result.
[0019] In one embodiment, the teaching interactive agent outputs experimental prompt information based on the evaluation result, including:
[0020] The teaching interactive agent uses the evaluation result to recall a number of relevant documents in a preset knowledge base as context information, and constructs an experimental prompt instruction with the context information;
[0021] The teaching interactive agent delivers the experimental prompt instructions to the third model, so that the third model returns the experimental prompt information.
[0022] In one embodiment, the method further comprises:
[0023] Acquire experimental inquiry information through the teaching interactive agent, and recall a number of related documents in a preset knowledge base with the experimental step list;
[0024] Constructing an experiment feedback instruction by the teaching interactive agent based on the experiment inquiry information, the evaluation results of the completed steps in the experiment step list and the several related documents;
[0025] The experimental feedback instruction is handed over to the third large model through the teaching interactive intelligent agent, so that the third large model returns the experimental feedback information corresponding to the experimental inquiry information and outputs the experimental feedback information.
[0026] On the other hand, the present application provides an electronic device, the electronic device comprising:
[0027] processor;
[0028] a memory for storing processor-executable instructions;
[0029] Wherein, the processor is configured to execute the above-mentioned method for processing experimental information.
[0030] Furthermore, the present application provides a computer-readable storage medium, which stores a computer program, and the computer program can be executed by a processor to complete the above-mentioned experimental information processing method.
[0031] In addition, the present application provides a computer program product, including a computer program / instruction, which implements the above-mentioned method for processing experimental information when executed by a processor.
[0032] This application scheme, with the help of a collaboration and control system built by multiple intelligent agents, can effectively plan the experimental process, evaluate the experimental results, and provide prompts for the experimental implementation process based on the evaluation results. It can efficiently and automatically complete the experimental teaching and training work through interaction with users, without the need for intervention by teachers or senior staff, thus reducing labor costs and realizing batch laboratory operation teaching. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] In order to more clearly illustrate the technical solution of the embodiments of the present application, the drawings required for use in the embodiments of the present application are briefly introduced below.
[0034] Figure 1 A schematic diagram of an application scenario of a method for processing experimental information provided in an embodiment of the present application;
[0035] Figure 2 A schematic diagram of the structure of an electronic device provided in one embodiment of the present application;
[0036] Figure 3 A flowchart of a method for processing experimental information provided in an embodiment of the present application;
[0037] Figure 4 A flowchart of a method for generating a list of experimental steps provided in an embodiment of the present application;
[0038] Figure 5 A schematic diagram of a flow chart of a method for evaluating experimental results provided in one embodiment of the present application;
[0039] Figure 6 A schematic diagram of a flow chart of an experimental prompting method provided in an embodiment of the present application;
[0040] Figure 7 A schematic diagram of a flow chart of an experimental feedback method provided in one embodiment of the present application;
[0041] Figure 8 A schematic diagram of the overall process of a method for processing experimental information provided in an embodiment of the present application;
[0042] Fig. 9 A block diagram of a device for processing experimental information provided in one embodiment of the present application. DETAILED DESCRIPTION
[0043] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.
[0044] Similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.
[0045] Figure 1 Schematic diagram of an application scenario of the method for processing experimental information provided in the embodiment of the present application. Figure 1 As shown, the application scenario includes a client 20 and a server 30; the client 20 can be a user terminal equipped with an intelligent agent, such as a host, a mobile phone, a tablet computer, etc., for interacting with the user; the server 30 can be a host, a server, a server cluster or a cloud computing center equipped with a large model, which can be used to respond to the instructions issued by the intelligent agent on the user terminal and return the corresponding experimental information.
[0046] like Figure 2 As shown, this embodiment provides an electronic device 1, including: at least one processor 11 and a memory 12, Figure 2 A processor 11 is taken as an example. The processor 11 and the memory 12 are connected via a bus 10. The memory 12 stores instructions that can be executed by the processor 11. The instructions are executed by the processor 11 so that the electronic device 1 can execute all or part of the process of the method in the following embodiment. In one embodiment, the electronic device 1 can be the above-mentioned client 20, which is used to execute the method for processing experimental information.
[0047] The memory 12 can 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 red-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, disk or optical disk.
[0048] The present application also provides a computer-readable storage medium, which stores a computer program. The computer program can be executed by the processor 11 to complete the method for processing experimental information provided in the present application.
[0049] The present application also provides a computer program product, including a computer program / instruction, which implements the method for processing experimental information provided in the present application when the computer program / instruction is executed by a processor.
[0050] See also Figure 3 , is a flow chart of a method for processing experimental information provided in an embodiment of the present application, such as Figure 3 As shown, the method may include the following steps 310 to 330.
[0051] Step 310: Acquire the experiment content information through the experiment planning agent, and output the experiment step list based on the experiment content information.
[0052] The experiment planning agent is used to interact with the user to plan the experiment process and generate a list of experimental steps. The experiment content information describes the content and purpose of the experiment and is input by the user to the terminal device equipped with the experiment planning agent.
[0053] See also Figure 4 , is a flow chart of a method for generating an experimental step list provided in an embodiment of the present application, such as Figure 4 As shown, when executing step 310, the following steps 410 to 420 may be executed.
[0054] Step 410: The experiment planning agent uses the experiment content information to recall a number of related documents in a preset knowledge base as context information, and constructs the experiment planning instructions with the context information.
[0055] Among them, according to the field to which the experiment belongs, a knowledge base can be preconfigured, and the knowledge base includes a large amount of information in the field. For example, the knowledge base in the medical field contains a large number of documents on medical experiments and medical knowledge. The knowledge base in the physics field includes a large number of documents on physics experiments and physics knowledge.
[0056] The experimental planning agent can vectorize the experimental content information, and then use the processed feature vectors to search for multiple related documents with the highest vector similarity in the knowledge base as context information. The experimental planning agent constructs the experimental planning instructions based on the first template for constructing the experimental planning instructions.
[0057] Exemplarily, the first template may be:
[0058] Combined with the experimental document content in the following {context information}, construct the experimental planning steps with {experimental purpose} as the goal. Each step needs to include the step name, step execution method, step assessment point, step estimated execution time, and step preparation conditions as content. Make sure that the preparation conditions of each step have been met in the previous steps. If there are additional experimental conditions {additional experimental conditions}, please follow the above conditions.
[0059] Fill in {context information}, {experimental purpose}, and {additional experimental conditions} in the first template to construct the experimental planning instructions.
[0060] Step 420: The experiment planning agent delivers the experiment planning instructions to the first large model, so that the first large model returns a list of experiment steps.
[0061] In this solution, each agent (experiment planning agent, step control agent, teaching interaction agent) corresponds to a big model. The big models connected to different agents can be the same or different. The big model can be ChatGPT (Chat Generative Pre-trained Transformer), Tongyi Qianwen, Wenxin Big Model, Doubao, etc.
[0062] After constructing the experimental planning instructions through the experimental planning agent, the experimental planning instructions can be sent to the first large model, so that the first large model can output the experimental step list according to the experimental planning instructions and return it to the experimental planning agent.
[0063] After the experiment planning agent obtains the experiment step list, it can output the experiment step list on the user terminal where it is located or the user terminal connected to it, so as to guide the user to implement the experiment through the experiment step list.
[0064] Step 320: The step control agent obtains the experimental result corresponding to any experimental step in the experimental step list, and determines the evaluation result corresponding to the experimental result.
[0065] After each experimental step in the experimental step list is implemented, the experimental result corresponding to the currently implemented experimental step can be obtained through the step control agent.
[0066] In one embodiment, the step control agent obtains the experimental photo corresponding to any experimental step, and determines the experimental result with the experimental photo. Here, the experimental photo can be manually taken and uploaded by the user, or it can be automatically taken by a preset camera in the experimental site.
[0067] After obtaining the experimental photos, the experimental photos can be directly used as the experimental results through the step-controlled intelligent agent, or the experimental photos can be classified through the step-controlled intelligent agent, and the classification results can be used as the experimental results.
[0068] In one embodiment, after any experimental step is completed, the user can explain the experimental result by voice input. The step control agent can obtain the voice input result corresponding to any experimental step and determine the experimental result with the voice input result.
[0069] After obtaining the voice input result, the step can be used to control the intelligent agent to directly use the voice input result as the experimental result, or the step can be used to control the intelligent agent to recognize the text information in the voice input result as the experimental result.
[0070] After obtaining the experimental results through the step control agent, the experimental results can be evaluated.
[0071] In one embodiment, an evaluation rule base may be preset on the step control agent, and the evaluation rule base includes a plurality of evaluation rules for experimental results. The step control agent evaluates the experimental results based on the evaluation rules in the evaluation rule base to obtain an evaluation result.
[0072] In one embodiment, the step control agent may be preconfigured with a calling interface of the evaluation tool, and the step control agent may process the experimental results by calling the evaluation tool through the calling interface to obtain the evaluation results.
[0073] Step 330: Outputting experimental prompt information based on the evaluation results through the teaching interactive agent.
[0074] After the step control agent obtains the evaluation result of the experimental result of any experimental step, the evaluation result can be handed over to the teaching interaction agent. The teaching interaction agent can determine the deficiencies of the user in implementing the experimental steps based on the evaluation result and output experimental prompt information so that the user can improve the experimental process based on the experimental prompt information.
[0075] Through the above measures, this solution, with the help of the collaboration and control system constructed by multiple intelligent agents, can effectively plan the experimental process, evaluate the experimental results, and provide prompts for the experimental implementation process based on the evaluation results. By interacting with users, it can efficiently and automatically complete the experimental teaching and training work without the intervention of teachers or senior staff, reducing labor costs and realizing batch laboratory operation teaching.
[0076] In one embodiment, after the step control agent obtains the evaluation result of the experimental result of any experimental step, the evaluation result can be sent to the experimental planning agent. The experimental planning agent can determine whether the experimental step is successfully executed based on the evaluation result of the experimental step.
[0077] Exemplarily, the evaluation result may include a step score. The experiment planning agent may determine whether the step score reaches a preset passing score. If so, the experiment step is determined to be successfully executed; if not, the experiment step is determined to be failed.
[0078] After obtaining the judgment result, the experimental step list is updated through the experimental planning agent, and the updated experimental step list is output. Exemplarily, if any experimental step fails to execute, the experimental planning agent determines that the experimental step needs to be redone, then the experimental step can be added to the experimental step list again. Alternatively, if any experimental step is successfully executed, the experimental planning agent determines that the next experimental step can be continued, then the experimental step list can be kept unchanged. Alternatively, if any experimental step fails to execute and the step score is too low, it can be considered that the experimental step is difficult for the user, and the experimental step can be replaced with another simpler experimental step, thereby updating the experimental step list.
[0079] Through this measure, the experiment planning agent can update the experimental step list according to the execution status of the experimental steps during the experiment, so that the user can conveniently implement the experiment according to the instructions of the experimental step list.
[0080] In one embodiment, see Figure 5 , is a flow chart of an evaluation method for experimental results provided in an embodiment of the present application, such as Figure 5 As shown, when step 320 is executed to evaluate the experimental results, the following steps 510 to 520 may be executed.
[0081] Step 510: Control the agent through the steps to recall a number of relevant documents in the preset knowledge base based on the experimental results as context information, and construct evaluation instructions based on the context information.
[0082] After the step control agent obtains the experimental results, the experimental results can be vectorized, and then the processed feature vectors are used to search for multiple documents with the highest vector similarity in the knowledge base as context information. The step control agent constructs the evaluation instruction based on the second template for constructing the evaluation instruction.
[0083] Exemplarily, the second template may be:
[0084] The step results and descriptions are evaluated according to the scoring items indicated by {context information}, and the step scores are given, and the reasons for the scores are also given. The evaluation process can be assisted by the image similarity tool {tool description}, the structured matching tool {tool description}, and the score calculation tool {tool description}.
[0085] By filling in {context information} and {tool description} of various tools in the second template, an assessment instruction can be constructed.
[0086] Step 520: The step controls the agent to pass the evaluation instruction to the second largest model, so that the second largest model returns the evaluation result.
[0087] After the evaluation instruction is constructed by the step control agent, the evaluation instruction can be sent to the second largest model, so that the second largest model outputs the evaluation result according to the evaluation instruction and returns it to the step control agent.
[0088] In one embodiment, see Figure 6 , is a flow chart of an experimental prompt method provided in an embodiment of the present application, such as Figure 6 As shown, when step 330 is executed to output the experiment prompt information, the experiment prompt information can be obtained through the following steps 610 to 620.
[0089] Step 610: The teaching interactive agent uses the evaluation results to recall a number of relevant documents in the preset knowledge base as context information, and constructs experimental prompt instructions with the context information.
[0090] After the teaching interactive agent obtains the evaluation result, it can vectorize the evaluation result and use the processed feature vector to search for multiple documents with the highest vector similarity in the knowledge base as context information. The teaching interactive agent can construct the third template of the experimental prompt instruction based on the experimental prompt instruction.
[0091] Exemplarily, the third template may be:
[0092] Based on the evaluation results of the experimental steps and the correct way to execute the experiment indicated by the {context information}, experimental prompt information is given to assist the user in improving the implementation method of the experimental steps.
[0093] After the third template is filled with {context information}, the experimental prompt instructions can be constructed.
[0094] Step 620: The experimental prompt instructions are handed over to the third largest model through the teaching interactive intelligent agent, so that the third largest model returns the experimental prompt information.
[0095] After the teaching interactive agent constructs the experimental prompt instruction, the experimental prompt instruction can be handed over to the third model, so that the third model outputs the experimental prompt information according to the experimental prompt instruction and returns it to the teaching interactive agent. Figure 7 , is a flow chart of an experimental feedback method provided in an embodiment of the present application, such as Figure 7 As shown, the method may include the following steps 710 to 730.
[0096] Step 710: Acquire experimental inquiry information through the teaching interactive agent, and recall a number of related documents in the preset knowledge base with the experimental step list.
[0097] During the experiment, users can ask questions about the experiment at any time and input experimental query information to the teaching interactive agent through voice or text. After the teaching interactive agent obtains the experimental query information, it can vectorize the list of experimental steps and use the processed feature vectors to search for multiple related documents with the highest vector similarity in the knowledge base.
[0098] Step 720: The teaching interactive agent constructs an experiment feedback instruction based on the experiment inquiry information, the evaluation results of the completed steps in the experiment step list, and several related documents.
[0099] The teaching interactive agent constructs the experimental feedback instruction based on the fourth template with the experimental inquiry information, the evaluation results of the completed steps in the experimental step list and several related documents. Here, the fourth template is used to construct the experimental feedback instruction.
[0100] Exemplarily, the fourth template may be:
[0101] Based on the evaluation results of the completed steps {Step 1: evaluation results; Step 2: evaluation results; Step 3: evaluation results...} and the experiment-related documents {related documents}, answer the user's questions in {experimental inquiry information}.
[0102] After the fourth template is filled with {evaluation results}, {related documents} and {experimental inquiry information}, the experimental feedback instructions can be constructed.
[0103] Step 730: The experimental feedback instruction is delivered to the third largest model through the teaching interactive agent, so that the third largest model returns the experimental feedback information corresponding to the experimental query information and outputs the experimental feedback information.
[0104] After the teaching interaction agent constructs the experimental feedback instruction, the experimental feedback instruction can be sent to the third model, so that the third model generates experimental feedback information according to the experimental feedback instruction and returns it to the teaching interaction agent. The teaching interaction agent can output the experimental feedback information to provide feedback to the user.
[0105] See also Figure 8 , is a schematic diagram of the overall flow of a method for processing experimental information provided in an embodiment of the present application, such as Figure 8 As shown, during the experiment, users can exchange information with the experiment planning agent, step control agent, and teaching interaction agent, and multiple agents can interact with each other. With the help of agent reasoning and action coordination capabilities, the planning and updating of experimental steps, step operation evaluation, active step prompts, and real-time Q&A during the experiment can be achieved.
[0106] Fig. 9 is a block diagram of a device for processing experimental information according to an embodiment of the present invention. Fig. 9 As shown, the device may include:
[0107] Planning module 910, used to obtain experimental content information through an experimental planning agent, and output an experimental step list based on the experimental content information;
[0108] An evaluation module 920 is used to obtain, through a step control agent, an experimental result corresponding to any experimental step in the experimental step list, and determine an evaluation result corresponding to the experimental result;
[0109] The prompt module 930 is used to output experimental prompt information based on the evaluation results through the teaching interactive intelligent agent.
[0110] The implementation process of the functions and effects of each module in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned experimental information processing method, and will not be repeated here.
[0111] In several embodiments provided in the present application, the disclosed devices and methods may also be implemented in other ways. The device embodiments described above are merely schematic, for example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram may represent a module, a program segment or a part of a code, and a module, a program segment or a part of a code contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they may sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of boxes in the block diagram and / or the flowchart, can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.
[0112] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
[0113] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.
Claims
1. A method for processing experimental information, characterized in that: include: Obtaining experimental content information through the experimental planning agent, and outputting an experimental step list based on the experimental content information; Obtaining, by means of a step control agent, an experimental result corresponding to any experimental step in the experimental step list, and determining an evaluation result corresponding to the experimental result; The teaching interactive agent outputs experimental prompt information based on the evaluation results.
2. The method according to claim 1, characterized in that The step of obtaining the experimental content information through the experimental planning agent and outputting the experimental step list based on the experimental content information includes: The experiment planning agent uses the experiment content information to recall a number of related documents in a preset knowledge base as context information, and constructs an experiment planning instruction with the context information; The experiment planning agent delivers the experiment planning instructions to the first large model, so that the first large model returns the experiment step list.
3. The method according to claim 1, characterized in that The method further comprises: The experimental planning agent determines whether the experimental steps are successfully executed based on the evaluation results of the experimental steps, updates the experimental step list based on the determination results, and outputs the updated experimental step list.
4. The method according to claim 1, characterized in that: The step of controlling the intelligent agent to obtain the experimental result corresponding to any experimental step in the experimental step list includes: Control the intelligent agent through the steps to obtain the experimental photos corresponding to any experimental step, and determine the experimental results based on the experimental photos; or The steps are used to control the intelligent agent to obtain the voice input result corresponding to any experimental step, and to determine the experimental result based on the voice input result.
5. The method according to claim 1, characterized in that The determining the evaluation result corresponding to the experimental result includes: Through the steps, the intelligent agent is controlled to recall a number of relevant documents in a preset knowledge base using the experimental results as context information, and an evaluation instruction is constructed using the context information; Through the steps, the intelligent agent is controlled to hand over the evaluation instruction to the second large model, so that the second large model returns the evaluation result.
6. The method according to claim 1, characterized in that The teaching interactive agent outputs experimental prompt information based on the evaluation result, including: The teaching interactive agent uses the evaluation result to recall a number of relevant documents in a preset knowledge base as context information, and constructs an experimental prompt instruction with the context information; The teaching interactive agent delivers the experimental prompt instructions to the third model, so that the third model returns the experimental prompt information.
7. The method according to claim 1, characterized in that The method further comprises: Acquire experimental inquiry information through the teaching interactive agent, and recall a number of related documents in a preset knowledge base with the experimental step list; Constructing an experiment feedback instruction by the teaching interactive agent based on the experiment inquiry information, the evaluation results of the completed steps in the experiment step list and the several related documents; The experimental feedback instruction is handed over to the third large model through the teaching interactive intelligent agent, so that the third large model returns the experimental feedback information corresponding to the experimental inquiry information and outputs the experimental feedback information.
8. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to execute the method for processing experimental information described in any one of claims 1-7.
9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program can be executed by a processor to complete the method for processing experimental information described in any one of claims 1-7.
10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the method for processing experimental information described in any one of claims 1 to 7 is implemented.