Electrocatalytic oxidation experiment auxiliary method and system based on artificial intelligence

Abstract

The invention provides an electrocatalytic oxidation experiment auxiliary method and system based on artificial intelligence, and the method comprises the steps: recognizing experiment problems encountered by a user and other users when the user and other users carry out an electrocatalytic oxidation experiment in an online combined manner; determining problem solving auxiliary knowledge based on the experimental problem and an artificial intelligence library; and assisting the user and other users to solve the experiment problem based on the problem solving auxiliary knowledge. When a user and other users are combined on line to carry out an electrocatalytic oxidation experiment, experiment problems encountered by the user and other users are identified, problem solving auxiliary knowledge is determined based on the experiment problems and an artificial intelligence library, and the experiment problems are solved in an auxiliary manner based on the problem solving auxiliary knowledge. According to the method, two parties are assisted by artificial intelligence to solve experiment problems encountered during online combined electrocatalytic oxidation experiment, the convenience of online combined electrocatalytic oxidation experiment is improved, the experiment efficiency is improved, and the applicability of online combined electrocatalytic oxidation experiment is further improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and particularly relates to an electrocatalytic oxidation experiment assistance method and system based on artificial intelligence. Background Art

[0002] Currently, to break through the limitation that joint electrocatalytic oxidation experiments need to be carried out at the same site, the two parties that can jointly conduct electrocatalytic oxidation experiments can conduct them online, that is, the two parties can each conduct electrocatalytic oxidation experiments and conduct experimental communication, experimental task division, etc. online.

[0003] However, when jointly conducting electrocatalytic oxidation experiments online, experimental problems may be encountered. When encountering experimental problems, the two parties communicate online to solve the experimental problems. However, since the two parties are not at the same site, there will still be inconvenience in the process of solving experimental problems, resulting in a possible decrease in the efficiency of solving experimental problems and also reducing the applicability of the two parties' online joint electrocatalytic oxidation experiments.

[0004] Therefore, there is an urgent need for an intelligent auxiliary solution means when experimental problems are encountered during the online joint electrocatalytic oxidation experiments of two parties, so that the convenience of the joint experiment during the online joint electrocatalytic oxidation experiment is closer to that of the experiment at the same site. Summary of the Invention

[0005] One of the purposes of the present invention is to provide an electrocatalytic oxidation experiment assistance method based on artificial intelligence. When a user jointly conducts an electrocatalytic oxidation experiment online with other users, identify the experimental problems encountered by the user and other users, determine problem-solving auxiliary knowledge based on the experimental problems and the artificial intelligence library, and based on the problem-solving auxiliary knowledge, assist the user and other users to solve the experimental problems, so as to realize the artificial intelligence-assisted solution of the experimental problems encountered during the online joint electrocatalytic oxidation experiment by two parties, improve the convenience of the online joint electrocatalytic oxidation experiment, improve the experimental efficiency, and further improve the applicability of the online joint electrocatalytic oxidation experiment.

[0006] An electrocatalytic oxidation experiment assistance method based on artificial intelligence provided by an embodiment of the present invention includes:

[0007] When a user jointly conducts an electrocatalytic oxidation experiment online with other users, identify the experimental problems encountered by the user and other users;

[0008] Determine problem-solving auxiliary knowledge based on the experimental problems and the artificial intelligence library;

[0009] Based on the problem-solving auxiliary knowledge, assist the user and other users to solve the experimental problems.

[0010] Preferably, identifying experimental problems encountered by the user and other users includes:

[0011] When the user or other users request greater than or equal to N active experimental perspectives within a first time period, respectively obtain the first experimental content under each of the active experimental perspectives and the conversation content generated by the user and other users within a second time period; wherein, the first time period includes: any time period with a first duration threshold when the user and other users jointly conduct an electrocatalytic oxidation experiment online; the second time period includes: the time period between the earliest generation moment of the active experimental perspective and the moment after the latest generation moment of the active experimental perspective with a second duration threshold;

[0012] Match the content feature vectors of the first experimental content and the conversation content with the standard content feature vectors in the standard content feature vector library to obtain the maximum matching degree and the indicated content of the standard content feature vector that generates the maximum matching degree with the content feature vector; the indicated content includes: a matching degree threshold, a problem item, and an effective condition;

[0013] When the maximum matching degree is greater than or equal to the matching degree threshold, use the problem item as the experimental problem; otherwise, determine whether the user or other users meet the effective condition within a third time period; wherein, the third time period includes: the time period between the latest generation moment of the active generation perspective and the moment after the latest generation moment of the active experimental perspective with a third duration threshold;

[0014] When meeting the condition, use the problem item as the experimental problem;

[0015] Wherein, the first duration threshold is greater than the third duration threshold which is greater than the second duration threshold.

[0016] Preferably, assisting the user and other users in solving the experimental problem based on the problem-solving auxiliary knowledge includes:

[0017] Analyze the problem-solving auxiliary knowledge to determine multiple solution logic nodes and the node sequence of each of the solution logic nodes;

[0018] Traverse each of the solution logic nodes in sequence according to the node sequence;

[0019] Each time during traversal, obtain the prompt object, passive generation perspective requirement, passive generation perspective party, and traversal continuation condition of the traversed solution logic node; wherein, the prompt object includes: the user and / or the other user; the passive generation perspective party includes: the user or the other user;

[0020] Send the traversed solution logic node to the prompt object;

[0021] Create the passive generation perspective of the passive generation perspective party based on the passive generation perspective requirement.

[0022] Obtain the second experimental content under the passive generation perspective.

[0023] Send the second experimental content to the user and the other party other than the passive generation perspective party among other users.

[0024] When the prompt object meets the traversal continuation condition, continue to traverse each of the solution logic nodes in sequence.

[0025] After traversing each of the solution logic nodes, complete assisting the user and other users in solving the experimental problem.

[0026] Preferably, the electrocatalytic oxidation experiment assistance method based on artificial intelligence further includes:

[0027] When a requester inputs an artificial intelligence library access request, determine the content in the library corresponding to the artificial intelligence library access request from the artificial intelligence library; wherein, the user and / or the other user;

[0028] Generate a visualization model based on the content in the library.

[0029] Display the visualization model to the requester.

[0030] When the requester inputs a model operation instruction based on the visualization model, control the visualization model to respond to the model operation instruction.

[0031] Preferably, the electrocatalytic oxidation experiment assistance method based on artificial intelligence further includes:

[0032] Update the library of the artificial intelligence library at intervals of a time interval threshold.

[0033] An electrocatalytic oxidation experiment assistance system based on artificial intelligence provided by an embodiment of the present invention includes:

[0034] An identification module, configured to identify an experimental problem encountered by a user and other users when the user and other users jointly conduct an electrocatalytic oxidation experiment online;

[0035] A determination module, configured to determine problem-solving assistance knowledge based on the experimental problem and an artificial intelligence library;

[0036] An assistance module, configured to assist the user and other users in solving the experimental problem based on the problem-solving assistance knowledge.

[0037] Preferably, the identification module identifying the experimental problem encountered by the user and other users includes:

[0038] When the user or other users request greater than or equal to N active experiment perspectives within the first time period, obtain the first experimental content under each of the active experiment perspectives and the conversation content generated by the user and other users within the second time period; wherein, the first time period includes: any time period with a first duration threshold when the user and other users jointly conduct an electrocatalytic oxidation experiment online; the second time period includes: the time period between the earliest generation moment of the active experiment perspective and the moment after the latest generation moment of the active experiment perspective plus a second duration threshold;

[0039] Match the content feature vectors of the first experimental content and the conversation content with the standard content feature vectors in the standard content feature vector library to obtain the maximum matching degree and the indicated content of the standard content feature vector that generates the maximum matching degree with the content feature vector; the indicated content includes: a matching degree threshold, problem items, and effective conditions;

[0040] When the maximum matching degree is greater than or equal to the matching degree threshold, use the problem items as the experimental problems; otherwise, determine whether the user or other users meet the effective conditions within the third time period; wherein, the third time period includes: the time period between the latest generation moment of the active generation perspective and the moment after the latest generation moment of the active experiment perspective plus a third duration threshold;

[0041] When meeting the conditions, use the problem items as the experimental problems;

[0042] Wherein, the first duration threshold is greater than the third duration threshold which is greater than the second duration threshold.

[0043] Preferably, the auxiliary module assists the user and other users in solving the experimental problems based on the problem-solving auxiliary knowledge, including:

[0044] Analyze the problem-solving auxiliary knowledge to determine multiple solution logic nodes and the node sequence of each of the solution logic nodes;

[0045] Traverse each of the solution logic nodes in sequence according to the node sequence;

[0046] Each time during traversal, obtain the prompt object, passive generation perspective requirements, passive generation perspective party, and traversal continuation conditions of the traversed solution logic node; wherein, the prompt object includes: the user and / or the other users; the passive generation perspective party includes: the user or the other users;

[0047] Send the traversed solution logic node to the prompt object;

[0048] Create the passive generation perspective of the passive generation perspective party based on the passive generation perspective requirement;

[0049] Obtain the second experimental content under the passive generation perspective;

[0050] Send the second experimental content to the user and the other party other than the passive generation perspective party among other users;

[0051] When the prompt object meets the traversal continuation condition, continue to traverse each of the solution logic nodes in sequence;

[0052] After traversing each of the solution logic nodes, complete assisting the user and other users in solving the experimental problem.

[0053] Preferably, the electrocatalytic oxidation experiment assistance system based on artificial intelligence further includes:

[0054] A visualization module, which is used to include:

[0055] When the requester inputs an artificial intelligence library access request, determine the content in the library corresponding to the artificial intelligence library access request from the artificial intelligence library; wherein, the user and / or the other user;

[0056] Generate a visualization model based on the content in the library;

[0057] Display the visualization model to the requester;

[0058] When the requester inputs a model operation instruction based on the visualization model, control the visualization model to respond to the model operation instruction.

[0059] Preferably, the electrocatalytic oxidation experiment assistance system based on artificial intelligence further includes:

[0060] A library update module, which is used to include:

[0061] Perform library update on the artificial intelligence library at intervals of a time interval threshold.

[0062] Other features and advantages of the present invention will be described in the subsequent specification, and part of them will become obvious from the specification, or be understood by implementing the present invention. The objectives and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in the written specification and the accompanying drawings.

[0063] The technical solutions of the present invention will be further described in detail below through the accompanying drawings and embodiments. Description of the Drawings

[0064] The accompanying drawings are used to provide a further understanding of the present invention and form a part of the specification. They are used together with the embodiments of the present invention to explain the present invention, but do not constitute a limitation to the present invention. In the accompanying drawings:

[0065] Figure 1 is a flowchart of an artificial intelligence-based electrocatalytic oxidation experiment assistance method in an embodiment of the present invention;

[0066] Figure 2 is a schematic diagram of an artificial intelligence-based electrocatalytic oxidation experiment assistance system in an embodiment of the present invention. Detailed implementation manners

[0067] The following describes the preferred embodiments of the present invention with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0068] An embodiment of the present invention provides an artificial intelligence-based electrocatalytic oxidation experiment assistance method, as Figure 1 shown, including:

[0069] S1. When a user conducts an electrocatalytic oxidation experiment online jointly with other users, identify the experimental problems encountered by the user and other users;

[0070] S2. Based on the experimental problems and the artificial intelligence library, determine the problem-solving assistance knowledge;

[0071] S3. Based on the problem-solving assistance knowledge, assist the user and other users in solving the experimental problems.

[0072] The user and another user are two parties for an online joint electrocatalytic oxidation experiment; when the user and another user conduct an online joint electrocatalytic oxidation experiment, identify the experimental problems they encounter. The experimental problems are the experimental difficulties, auxiliary requirements, etc. when the user and another user conduct an online joint electrocatalytic oxidation experiment. For example: not understanding a certain electrocatalytic oxidation related principle, needing to retrieve experimental data from previous electrocatalytic oxidation experiments, etc.; there is problem-solving auxiliary knowledge corresponding to different experimental problems in the artificial intelligence library. The problem-solving auxiliary knowledge is the knowledge content that conforms to the user and another user to solve the experimental problems. For example: if the experimental problem is not understanding a certain electrocatalytic oxidation related principle, then the problem-solving auxiliary knowledge is the specific explanation of the unclear electrocatalytic oxidation related principle; based on the problem-solving auxiliary knowledge, assist the user and another user to solve the experimental problems. In this application, when the user and another user conduct an online joint electrocatalytic oxidation experiment, identify the experimental problems encountered by the user and another user, determine the problem-solving auxiliary knowledge based on the experimental problems and the artificial intelligence library, and based on the problem-solving auxiliary knowledge, assist the user and another user to solve the experimental problems, realizing the use of artificial intelligence to assist the two parties to solve the experimental problems encountered during the online joint electrocatalytic oxidation experiment, improving the convenience of the online joint electrocatalytic oxidation experiment, improving the experimental efficiency, and further improving the applicability of the online joint electrocatalytic oxidation experiment.

[0073] In one embodiment, the identifying the experimental problems encountered by the user and another user includes:

[0074] When the user or another user requests greater than or equal to N active experimental perspectives within a first time period, respectively obtain the first experimental content under each of the active experimental perspectives and the conversation content generated by the user and another user within a second time period; wherein, the first time period includes: any time period with a first duration threshold when the user and another user conduct an online joint electrocatalytic oxidation experiment; the second time period includes: the time period between the earliest generation time of the active experimental perspective and the time after the latest generation time of the active experimental perspective plus a second duration threshold.

[0075] Match the content feature vectors of the first experimental content and the conversation content with the standard content feature vectors in the standard content feature vector library to obtain the maximum matching degree and the indication content of the standard content feature vector that generates the maximum matching degree with the content feature vector; the indication content includes: a matching degree threshold, a problem item, and an effective condition.

[0076] When the maximum matching degree is greater than or equal to the matching degree threshold, the problem item is taken as the experimental problem; otherwise, it is determined whether the user or other users meet the effectiveness condition within the third time period; wherein, the third time period includes: the time period between the latest generation moment of the actively generated perspective and the moment after the third time threshold from the latest generation moment of the actively experimental perspective;

[0077] When meeting the condition, the problem item is taken as the experimental problem;

[0078] Wherein, the first time threshold is greater than the third time threshold which is greater than the second time threshold.

[0079] Generally, in order for both parties conducting electrocatalytic oxidation experiments online jointly to see each other's experimental operation screens, cameras can be set up beside their respective test benches to capture the experimental operation screens and then send the experimental operation screens to each other. When a user or another user wants the camera to capture the screen of their experimental operation from a specific angle, they can request an active experimental perspective from the camera, for example: Take a close-up shot of my hand operation. N is a positive integer, for example, 3. When a user or another user requests greater than or equal to N active experimental perspectives within the first time period, it indicates that the user or another user has multiple experimental operation screens that they want the other party to see, and the two parties may have encountered experimental problems. If the two parties have indeed encountered experimental problems, they will explain it in the subsequent conversation, and of course, it will also be reflected in the experimental operation screens captured from the active experimental perspectives. Therefore, the first experimental content under each active experimental perspective and the conversation content generated by the user and other users within the second time period are respectively obtained, and the content feature vectors of the first experimental content and the conversation content are constructed. Multiple groups of corresponding standard content feature vectors and indication contents are preset. The standard content feature vectors reflect a situation where further determination of experimental problems is required, and are constructed from the experimental content and conversation reflecting this situation. For example, if the experimental content and conversation reflecting this situation are the experimental indicators of the electrocatalytic oxidation experiment and "Are the experimental indicators too high?", then the reflected situation is that the user or another user believes that the experimental indicator settings are unreasonable. The corresponding indication content is used to indicate how to further determine the experimental problem. Among them, the problem item is the experimental problem reflected by the standard content feature vector. The matching degree threshold can be, for example, 80. When the maximum matching degree is greater than this matching degree threshold, it indicates that the situation reflected by the content feature vector has a high matching degree with the corresponding standard content feature vector, and the problem item can be directly used as the experimental problem. Otherwise, that is, when the maximum matching degree is less than this matching degree threshold, it indicates that the experimental problem needs to be determined in depth. An effective condition is set, for example: The effective condition is that the user or another user adjusts the experimental indicators of the electrocatalytic oxidation experiment multiple times. When the user or another user meets the effective condition within the third time period, it indicates that the problem item is further confirmed and can be used as the experimental problem. The first time threshold can be 200 seconds; the second time threshold can be 100 seconds; the third time threshold can be 60 seconds. In the embodiments of the present invention, first, based on the request for the active experimental perspective, it is determined whether the user may encounter experimental problems, and subsequent confirmation operations are triggered, reducing the recognition resources and improving the recognition efficiency; the first time period, the second time period, and the third time period are set to obtain data specifically, further reducing the recognition resources; secondly, by introducing the standard content feature vector library and the indication content, the experimental problems encountered by the user and other users are quickly determined, improving the efficiency and accuracy of experimental problem recognition. At the same time, it is also very intelligent.

[0080] In one embodiment, assisting the user and other users in solving the experimental problem based on the problem-solving assistance knowledge includes:

[0081] Analyze the problem-solving assistance knowledge to determine a plurality of solution logic nodes and the node sequence order of each of the solution logic nodes;

[0082] Traverse each of the solution logic nodes in sequence according to the node sequence order;

[0083] Each time during traversal, obtain the hint object, passively generated perspective requirement, passively generated perspective party, and traversal continuation condition of the traversed solution logic node; wherein, the hint object includes: the user and / or the other user; the passively generated perspective party includes: the user or the other user;

[0084] Send the traversed solution logic node to the hint object;

[0085] Create a passively generated perspective of the passively generated perspective party based on the passively generated perspective requirement;

[0086] Obtain the second experimental content under the passively generated perspective;

[0087] Send the second experimental content to the other party among the user and the other users except the passively generated perspective party;

[0088] When the hint object meets the traversal continuation condition, continue to traverse each of the solution logic nodes in sequence;

[0089] After traversing each of the solution logic nodes, complete assisting the user and other users in solving the experimental problem.

[0090] The problem-solving assistance knowledge indicates how the system assists the user and other users. It has an assistance logic and consists of multiple solution logic nodes with a sequential order of nodes. Each solution logic node represents what assistance means the system needs to execute. For example, it guides the user on how to judge whether the experimental index settings are reasonable, etc. Each solution logic node has a prompt object, which is the object that the solution logic node needs to prompt. The passive generation perspective requirement is how the camera beside the operation console of the passive generation perspective side needs to obtain the second experimental content. During specific assistance, the traversed solution logic node is sent to the prompt object, and the second experimental content under the passive generation perspective is sent to the other party among the user and other users except the passive generation perspective side. After traversing all the solution logic nodes, the assistance in solving the experimental problem for the user and other users is completed. When the prompt object meets the condition for continuing traversal, continue to traverse each of the solution logic nodes in sequence. For example, if the prompt object has read the solution logic node, it means the prompt object has received the prompt and can continue traversing, and continue to assist using the remaining solution logic nodes. The embodiments of the present invention introduce solution logic nodes, prompt objects, passive generation perspective requirements, passive generation perspective sides, and traversal continuation conditions, and orderly assist the user and other users in solving experimental problems, improving the accuracy of assistance and being very intelligent at the same time.

[0091] In one embodiment, the electrocatalytic oxidation experiment assistance method based on artificial intelligence further includes:

[0092] When the requester inputs an artificial intelligence library access request, determine the content in the library corresponding to the artificial intelligence library access request from the artificial intelligence library; where the user and / or the other user;

[0093] Generate a visualization model based on the content in the library;

[0094] Display the visualization model to the requester;

[0095] When the requester inputs a model operation instruction based on the visualization model, control the visualization model to respond to the model operation instruction.

[0096] When the requester inputs an artificial intelligence library access request, corresponding content in the artificial intelligence library can be scheduled to generate a visualization model for the requester to operate, realizing visual access.

[0097] In one embodiment, the electrocatalytic oxidation experiment assistance method based on artificial intelligence further includes:

[0098] At intervals of a time interval threshold, update the artificial intelligence library.

[0099] The time interval threshold can be, for example: 3 days; at every time interval threshold, the artificial intelligence library is updated to improve the real-time and comprehensiveness of the artificial intelligence library for determining problem-solving auxiliary knowledge.

[0100] An embodiment of the present invention provides an artificial intelligence-based electrocatalytic oxidation experiment assistance system, as Figure 2 shown, including:

[0101] An identification module 1, configured to identify experimental problems encountered by a user and other users when the user conducts an electrocatalytic oxidation experiment online jointly with other users;

[0102] A determination module 2, configured to determine problem-solving auxiliary knowledge based on the experimental problems and the artificial intelligence library;

[0103] An assistance module 3, configured to assist the user and other users in solving the experimental problems based on the problem-solving auxiliary knowledge.

[0104] The identification module identifying the experimental problems encountered by the user and other users includes:

[0105] When the user or other users request greater than or equal to N active experimental perspectives within a first time period, respectively obtain the first experimental content under each of the active experimental perspectives and the conversation content generated by the user and other users within a second time period; wherein, the first time period includes: any time period with a first duration threshold when the user conducts an electrocatalytic oxidation experiment online jointly with other users; the second time period includes: the time period between the earliest generation moment of the active experimental perspective and the moment after the latest generation moment of the active experimental perspective plus a second duration threshold;

[0106] Match the content feature vectors of the first experimental content and the conversation content with the standard content feature vectors in the standard content feature vector library to obtain the maximum matching degree and the indicated content of the standard content feature vector that generates the maximum matching degree with the content feature vector; the indicated content includes: a matching degree threshold, a problem item, and an effective condition;

[0107] When the maximum matching degree is greater than or equal to the matching degree threshold, use the problem item as the experimental problem; otherwise, determine whether the user or other users meet the effective condition within a third time period; wherein, the third time period includes: the time period between the latest generation moment of the active generation perspective and the moment after the latest generation moment of the active experimental perspective plus a third duration threshold;

[0108] When meeting the condition, use the problem item as the experimental problem;

[0109] Wherein, the first duration threshold is greater than the third duration threshold which is greater than the second duration threshold.

[0110] The auxiliary module, based on the problem-solving auxiliary knowledge, assists the user and other users in solving the experimental problem, including:

[0111] Parsing the problem-solving auxiliary knowledge to determine multiple solution logic nodes and the node sequence of each of the solution logic nodes;

[0112] Traversing each of the solution logic nodes in sequence according to the node sequence;

[0113] Each time during traversal, obtaining the hint object, passively generated perspective requirement, passively generated perspective party, and traversal continuation condition of the traversed solution logic node; wherein, the hint object includes: the user and / or the other user; the passively generated perspective party includes: the user or the other user;

[0114] Sending the traversed solution logic node to the hint object;

[0115] Based on the passively generated perspective requirement, creating the passively generated perspective of the passively generated perspective party;

[0116] Obtaining the second experimental content under the passively generated perspective;

[0117] Sending the second experimental content to the other party among the user and other users except the passively generated perspective party;

[0118] When the hint object meets the traversal continuation condition, continuing to traverse each of the solution logic nodes in sequence;

[0119] After traversing each of the solution logic nodes, completing the assistance to the user and other users in solving the experimental problem.

[0120] The electrocatalytic oxidation experiment assistance system based on artificial intelligence further includes:

[0121] A visualization module, which is used for including:

[0122] When the requester inputs an artificial intelligence library access request, determining the content in the library corresponding to the artificial intelligence library access request from the artificial intelligence library; wherein, the user and / or the other user;

[0123] Generating a visualization model based on the content in the library;

[0124] Displaying the visualization model to the requester;

[0125] When the requester inputs a model operation instruction based on the visualization model, controlling the visualization model to respond to the model operation instruction.

[0126] An artificial intelligence-based electrocatalytic oxidation experiment assistance system further includes:

[0127] A library update module, configured to include:

[0128] Performing a library update on the artificial intelligence library at every time interval threshold.

[0129] Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. An artificial intelligence-based electrocatalytic oxidation experimental auxiliary method, characterized in that: include: When a user conducts an electrocatalytic oxidation experiment online with other users, identify the experimental problems encountered by the user and other users; Determine problem-solving auxiliary knowledge based on experimental questions and artificial intelligence library; Based on problem-solving auxiliary knowledge, assist users and other users to solve experimental problems.

2. The artificial intelligence-based electrocatalytic oxidation experimental auxiliary method according to claim 1, characterized in that: Identify issues that users are experiencing with their experiments, including: When the user or other users request more than or equal to N active experimental perspectives within the first time period, the first experimental content under each active experimental perspective and the conversation content generated by the user and other users within the second time period are respectively obtained; wherein the first time period includes: any time period of the first time threshold when the user and other users jointly conduct an electrocatalytic oxidation experiment online; the second time period includes: the time period between the earliest generation time of the active experimental perspective and the second time threshold after the latest generation time of the active experimental perspective; Matching the content feature vectors of the first experimental content and the dialogue content with the standard content feature vectors in the standard content feature vector library, obtaining the maximum matching degree and the indicative content of the standard content feature vector that produces the maximum matching degree with the content feature vector; the indicative content includes: matching degree threshold, question item, and effective condition; When the maximum matching degree is greater than or equal to the matching degree threshold, the question item is used as an experimental question; otherwise, it is determined whether the user or other users meet the effective conditions within the third time period; wherein the third time period includes: the time period between the latest time when the perspective is actively generated and the time of the third time length threshold after the latest time when the perspective is actively generated; When it is consistent, the question item is used as an experimental question; Among them, the first duration threshold is greater than the third duration threshold and greater than the second duration threshold.

3. The electrocatalytic oxidation experiment auxiliary method based on artificial intelligence according to claim 1, characterized in that: Based on problem-solving auxiliary knowledge, assist users and other users to solve experimental problems, including: Analyze the problem-solving auxiliary knowledge to determine multiple solution logic nodes and the node sequence of each solution logic node; According to the order of nodes, traverse each solution logic node in turn; Each time the traversal is performed, the prompt object, the passively generated viewpoint requirement, the passively generated viewpoint party and the traversal continuation condition of the traversed solution logic node are obtained; wherein the prompt object includes: the user and / or other users; the passively generated viewpoint party includes: the user or other users; Send the traversed solution logic node to the prompt object; Based on the passive perspective generation requirements, create a passive perspective generation party's passive perspective generation; Obtain the second experimental content from the passive generation perspective; Sending the second experimental content to the user and another user other than the one who passively generates the viewpoint; When the prompt object meets the traversal continuation condition, continue to traverse each solution logic node in sequence; After traversing each solution logic node, the auxiliary user and other users are completed to solve the experimental problem.

4. The artificial intelligence-based electrocatalytic oxidation experimental auxiliary method according to claim 1, characterized in that: Also includes: When the requester inputs an AI library access request, the content in the library corresponding to the AI ​​library access request is determined from the AI ​​library; wherein the user and / or other users; Generate a visual model based on the content in the library; Displaying the visualization model to the requesting party; When the requester inputs a model operation instruction based on the visualization model, the visualization model is controlled to respond to the model operation instruction.

5. The artificial intelligence-based electrocatalytic oxidation experimental auxiliary method according to claim 1, characterized in that: Also includes: The artificial intelligence library is updated at every time interval threshold.

6. An artificial intelligence-based electrocatalytic oxidation experimental auxiliary system, characterized in that: include: An identification module, used to identify experimental problems encountered by the user and other users when the user conducts an electrocatalytic oxidation experiment online in conjunction with other users; A determination module, used to determine problem-solving auxiliary knowledge based on experimental questions and artificial intelligence library; The auxiliary module is used to assist users and other users in solving experimental problems based on problem-solving auxiliary knowledge.

7. The artificial intelligence-based electrocatalytic oxidation experiment auxiliary system according to claim 6, characterized in that: The Identification Module identifies experimental problems that users encounter with other users, including: When the user or other users request more than or equal to N active experimental perspectives within the first time period, the first experimental content under each active experimental perspective and the conversation content generated by the user and other users within the second time period are respectively obtained; wherein the first time period includes: any time period of the first time threshold when the user and other users jointly conduct an electrocatalytic oxidation experiment online; the second time period includes: the time period between the earliest generation time of the active experimental perspective and the second time threshold after the latest generation time of the active experimental perspective; Matching the content feature vectors of the first experimental content and the dialogue content with the standard content feature vectors in the standard content feature vector library, obtaining the maximum matching degree and the indicative content of the standard content feature vector that produces the maximum matching degree with the content feature vector; the indicative content includes: matching degree threshold, question item, and effective condition; When the maximum matching degree is greater than or equal to the matching degree threshold, the question item is used as an experimental question; otherwise, it is determined whether the user or other users meet the effective conditions within the third time period; wherein the third time period includes: the time period between the latest time when the perspective is actively generated and the time of the third time length threshold after the latest time when the perspective is actively generated; When it is consistent, the question item is used as an experimental question; Among them, the first duration threshold is greater than the third duration threshold and greater than the second duration threshold.

8. The artificial intelligence-based electrocatalytic oxidation experiment auxiliary system according to claim 6, characterized in that: The auxiliary module assists users and other users in solving experimental problems based on problem-solving auxiliary knowledge, including: Analyze the problem-solving auxiliary knowledge to determine multiple solution logic nodes and the node sequence of each solution logic node; According to the order of nodes, traverse each solution logic node in turn; Each time the traversal is performed, the prompt object, the passively generated viewpoint requirement, the passively generated viewpoint party and the traversal continuation condition of the traversed solution logic node are obtained; wherein the prompt object includes: the user and / or other users; the passively generated viewpoint party includes: the user or other users; Send the traversed solution logic node to the prompt object; Based on the passive perspective generation requirements, create a passive perspective generation party's passive perspective generation; Obtain the second experimental content from the passive generation perspective; Sending the second experimental content to the user and another user other than the one who passively generates the viewpoint; When the prompt object meets the traversal continuation condition, continue to traverse each solution logic node in sequence; After traversing each solution logic node, the auxiliary user and other users are completed to solve the experimental problem.

9. The artificial intelligence-based electrocatalytic oxidation experiment auxiliary system according to claim 6, characterized in that: Also includes: Visualization modules for: When the requester inputs an AI library access request, the content in the library corresponding to the AI ​​library access request is determined from the AI ​​library; wherein the user and / or other users; Generate a visual model based on the content in the library; Displaying the visualization model to the requesting party; When the requester inputs a model operation instruction based on the visualization model, the visualization model is controlled to respond to the model operation instruction.

10. The artificial intelligence-based electrocatalytic oxidation experiment auxiliary system according to claim 6, characterized in that: Also includes: Library update module to include: The artificial intelligence library is updated at every time interval threshold.

Images