Material experiment optimization method and device based on massive user data and computer equipment
By using a four-dimensional logical partitioning and cross-domain correlation analysis model, combined with current scenario information, an optimized experimental scheme for the target material is generated. This solves the problem of underutilization of massive user data, improves the accuracy and efficiency of material experiments, and adapts to the needs of different scenarios.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-10
- Publication Date
- 2026-04-14
AI Technical Summary
Existing technologies have failed to fully tap the correlation value of massive user data, resulting in poor experimental optimization effects in materials experiments, failing to meet the requirements for accuracy and efficiency, and especially lacking in adaptability to different regions and equipment.
By employing a four-dimensional logical partitioning strategy and a cross-domain correlation analysis model, experimental characteristic analysis results are generated. Combined with current scenario information, optimized experimental schemes for target materials are recommended, including experimental procedures and equipment supplement recommendations, to adapt to the needs of different scenarios.
It improves the comprehensiveness and accuracy of integrated analysis in materials experiments, increases experimental efficiency and success rate, meets differentiated solutions for different needs, and enhances user adaptability and satisfaction.
Smart Images
Figure CN121860116A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of materials experiment optimization technology, and in particular to a materials experiment optimization method, apparatus and computer equipment based on massive user data. Background Technology
[0002] Materials science experiments exhibit a significant "scenario sensitivity" characteristic: experimental results not only depend on equipment parameters and process design, but are also strongly correlated with the regional environment (such as humidity, air pressure, and temperature), equipment model characteristics, and experimental objectives (such as developing novel thin films versus optimizing mass production processes). With the widespread adoption of cloud-based collaborative R&D models, a massive accumulation of experimental data (processes, parameters, results), environmental data, and equipment data from users in various regions has emerged. However, current technologies have not fully explored the correlation value of this data. Furthermore, the industry's demand for "precisely adapted experimental solutions" is increasingly urgent: users in different regions require differentiated process parameters and equipment configurations when conducting the same materials experiment; different experimental needs also place drastically different demands on equipment adaptability. Traditional solutions relying on manual experience can no longer meet the demands for efficiency and accuracy. Therefore, how to fully utilize massive user data to optimize the processes and equipment for materials science experiments is a current research focus.
[0003] Existing technologies achieve intelligent guidance and teaching feedback for experimental procedures by collecting user data (such as operation records and experimental results) in experimental teaching. However, this method has limitations in the analysis of user data and the data dimensions are singular, which limits the degree of intelligent guidance for experimental procedures and results in poor experimental optimization effects for materials experiments. Summary of the Invention
[0004] Therefore, it is necessary to provide a material experiment optimization method, apparatus, and computer equipment based on massive user data to address the above-mentioned technical problems.
[0005] Firstly, this application provides a material experiment optimization method based on massive user data, including:
[0006] The experiment acquires user experimental data, experimental association data, and current scenario information of the material experiment. Based on the user experimental data and experimental association data, an experimental group corresponding to each logical dimension is generated using a four-dimensional logical partitioning strategy. The experimental group includes the user experimental data.
[0007] Based on the experimental groups of each logical dimension, the experimental characteristic analysis results of the material experiments are generated through a cross-domain correlation analysis model.
[0008] Based on the experimental characteristic analysis results and the current scene information, an optimized experimental scheme for the target material that is adapted to the current scene information is generated through a scene recommendation model.
[0009] Optionally, based on the user experiment data and the experiment-related data, an experiment group corresponding to each logical dimension is generated using a four-dimensional logical partitioning strategy; the experiment group includes the user experiment data, including:
[0010] Based on the user experiment data mentioned above, identify the experimental process data, equipment data, and user requirement data for each experiment;
[0011] Based on the equipment data, user demand data, and experimental association data for each experiment, the user experiment data is divided into sub-experiment groups at each logical level of each logical dimension through a data partitioning strategy for each logical dimension.
[0012] Each logical dimension is divided into sub-experimental groups of all logical levels, which are used as the experimental groups for each logical dimension.
[0013] Optionally, the experimental groups based on each of the aforementioned logical dimensions generate experimental characteristic analysis results for the material experiments through a cross-domain correlation analysis model, including:
[0014] The cross-domain association analysis model is broken down into sub-cross-domain association analysis models for each of the logical dimensions.
[0015] For each sub-cross-domain association analysis model, through the experimental groups of each logical dimension associated with the sub-cross-domain association analysis model, and through the association analysis strategy of each sub-cross-domain association analysis model, the explicit change patterns and implicit change patterns between each logical dimension are identified.
[0016] The explicit and implicit variation patterns between the logical dimensions are used as the experimental characteristic analysis results of the material experiment.
[0017] Optionally, before generating the target material experiment optimization scheme adapted to the current scene information through a scene recommendation model based on the experimental characteristic analysis results and the current scene information, the method further includes:
[0018] Based on the current scene information, identify the current experimental requirements of the material experiment, the current environmental data of the material experiment, the current geographical information of the material experiment, and the current equipment information of the material experiment;
[0019] Based on the current experimental requirements information, the process requirements information and equipment requirements information of the material experiment are identified, and based on the equipment requirements information and the current equipment information of the material experiment, the equipment requirements information of the material experiment is identified.
[0020] Optionally, the step of generating a target material experiment optimization scheme adapted to the current scene information based on the experimental characteristic analysis results and the current scene information through a scene recommendation model includes:
[0021] Based on the current experimental requirements, process requirements, and equipment requirements of the material experiment, the range of optimization schemes suitable for the material experiment is identified through the experimental characteristic analysis results.
[0022] Based on the current environmental data and the current geographical information of the material experiment, the scene intelligent recommendation module filters the current target experimental process and the current equipment supplementary recommendation information of the material experiment within the scope of the optimization scheme.
[0023] The current target experimental procedure of the material experiment and the supplementary recommended information of the current equipment of the material experiment are used as the target material experiment optimization scheme for the current scenario information adaptation.
[0024] Optionally, after generating the target material experiment optimization scheme adapted to the current scene information through a scene recommendation model based on the experimental characteristic analysis results and the current scene information, the method further includes:
[0025] Collect user recommendation feedback information, and based on the recommendation feedback information, identify abnormal evaluation information of the user;
[0026] Based on the aforementioned abnormal evaluation information, each sample of experimental data is selected from the user experimental data.
[0027] Based on the experimental data of each sample, the scene recommendation model is trained to obtain a new scene recommendation model. The new scene recommendation model is then used to replace the original scene recommendation model. The process then returns to the step of generating a target material experimental optimization scheme that is adapted to the current scene information based on the experimental characteristic analysis results and the current scene information through the scene recommendation model.
[0028] Secondly, this application also provides a material experiment optimization device based on massive user data, comprising:
[0029] The acquisition module is used to acquire user experimental data, experimental association data, and current scenario information of the material experiment. Based on the user experimental data and experimental association data, it generates experimental groups corresponding to each logical dimension through a four-dimensional logical partitioning strategy. The experimental groups include the user experimental data.
[0030] The analysis module is used to generate experimental characteristic analysis results of the material experiments based on the experimental groups of each logical dimension through a cross-domain correlation analysis model.
[0031] The recommendation module is used to generate an optimized experimental scheme for the target material that is adapted to the current scene information based on the experimental characteristic analysis results and the current scene information through a scene recommendation model.
[0032] Optionally, the acquisition module is specifically used for:
[0033] Based on the user experiment data mentioned above, identify the experimental process data, equipment data, and user requirement data for each experiment;
[0034] Based on the equipment data, user demand data, and experimental association data for each experiment, the user experiment data is divided into sub-experiment groups at each logical level of each logical dimension through a data partitioning strategy for each logical dimension.
[0035] Each logical dimension is divided into sub-experimental groups of all logical levels, which are used as the experimental groups for each logical dimension.
[0036] Optionally, the analysis module is specifically used for:
[0037] The cross-domain association analysis model is broken down into sub-cross-domain association analysis models for each of the logical dimensions.
[0038] For each sub-cross-domain association analysis model, through the experimental groups of each logical dimension associated with the sub-cross-domain association analysis model, and through the association analysis strategy of each sub-cross-domain association analysis model, the explicit change patterns and implicit change patterns between each logical dimension are identified.
[0039] The explicit and implicit variation patterns between the logical dimensions are used as the experimental characteristic analysis results of the material experiment.
[0040] Optionally, the device further includes:
[0041] The first identification module is used to identify the current experimental requirements of the material experiment, the current environmental data of the material experiment, the current geographical information of the material experiment, and the current equipment information of the material experiment based on the current scene information.
[0042] The second identification module is used to identify the process requirements of the material experiment and the equipment requirements of the material experiment based on the current experimental requirements information, and to identify the equipment requirements of the material experiment based on the equipment requirements of the material experiment and the current equipment information of the material experiment.
[0043] Optionally, the recommendation module is specifically used for:
[0044] Based on the current experimental requirements, process requirements, and equipment requirements of the material experiment, the range of optimization schemes suitable for the material experiment is identified through the experimental characteristic analysis results.
[0045] Based on the current environmental data and the current geographical information of the material experiment, the scene intelligent recommendation module filters the current target experimental process and the current equipment supplementary recommendation information of the material experiment within the scope of the optimization scheme.
[0046] The current target experimental procedure of the material experiment and the supplementary recommended information of the current equipment of the material experiment are used as the target material experiment optimization scheme for the current scenario information adaptation.
[0047] Optionally, the device further includes:
[0048] The data collection module is used to collect user recommendation feedback information and, based on the recommendation feedback information, identify abnormal evaluation information of the user.
[0049] The filtering module is used to filter each sample experimental data from each of the user experimental data based on the abnormal evaluation information.
[0050] The iterative module is used to train the scene recommendation model based on the experimental data of each sample, obtain a new scene recommendation model, replace the scene recommendation model with the new scene recommendation model, and return to the step of generating a target material experimental optimization scheme adapted to the current scene information based on the experimental characteristic analysis results and the current scene information through the scene recommendation model.
[0051] Thirdly, this application provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described in any one of the first aspects.
[0052] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in any one of the first aspects.
[0053] Fifthly, this application provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described in any one of the first aspects.
[0054] The aforementioned material experiment optimization method, apparatus, and computer equipment based on massive user data acquire user experiment data, related data of each experiment, and current scenario information of the material experiment. Based on the user experiment data and related data, a four-dimensional logical partitioning strategy is used to generate experimental groups corresponding to each logical dimension. Each experimental group includes the user experiment data. Based on the experimental groups of each logical dimension, a cross-domain correlation analysis model is used to generate experimental characteristic analysis results for the material experiment. Based on the experimental characteristic analysis results and the current scenario information, a scenario recommendation model is used to generate a target material experiment optimization scheme adapted to the current scenario information. This scheme, through multi-dimensional data integration and classification analysis, focuses on adapting to fixed external factors such as regional environment and equipment characteristics, and the recommended scheme is more in line with the scenario-sensitive needs of the material experiment. The target material experiment optimization scheme generated by this solution includes the current target experimental process for the material experiment and supplementary equipment recommendation information. This not only provides optimized experimental processes for different material experiments based on a large amount of user data, but also offers recommended experimental equipment, ensuring the accuracy and suitability of the user's material experiments. Furthermore, when analyzing user experimental data, this solution uses a four-dimensional logical partitioning strategy and a cross-domain correlation analysis model for segmentation and analysis. This allows for multi-angle, multi-level, and multi-dimensional analysis of user experimental data. It also comprehensively analyzes the experimental characteristics of the material experiment from different logical dimensions, thereby improving the comprehensiveness and accuracy of the integrated analysis of various material experiments, effectively increasing experimental efficiency and success rate. Moreover, it can differentiate between different needs such as R&D / mass production and performance / cost, recommending differentiated solutions to improve user suitability and satisfaction, thus comprehensively improving the experimental optimization effect of material experiments. Attached Figure Description
[0055] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0056] Figure 1 This is a flowchart illustrating a material experiment optimization method based on massive user data in one embodiment.
[0057] Figure 2 This is a flowchart illustrating an example of material experiment optimization based on massive user data in one embodiment;
[0058] Figure 3 This is a structural block diagram of a material experiment optimization device based on massive user data in one embodiment;
[0059] Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation
[0060] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0061] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.
[0062] The material experiment optimization method based on massive user data provided in this application embodiment can be applied to a material experiment optimization system based on massive user data. This system can be applied to terminals, which can be, but are not limited to, various personal computers, laptops, mid-range computers, etc. The terminal, through multi-dimensional data integration and classification analysis, focuses on adapting to fixed external factors such as regional environment and equipment characteristics, recommending solutions that better meet the scenario-sensitive needs of material experiments. The target material experiment optimization solution generated by this method includes the current target experimental procedure for the material experiment and supplementary equipment recommendation information for the current material experiment. Therefore, it can not only combine a large amount of user data to provide optimized experimental procedures for different material experiments, but also provide recommended experimental equipment, ensuring the accuracy and suitability of the user's material experiments. Furthermore, when analyzing user experimental data, this solution employs a four-dimensional logical partitioning strategy and a cross-domain correlation analysis model to perform partitioning and analysis. This allows for multi-angle, multi-level, and multi-dimensional analysis of user experimental data. It also comprehensively analyzes the experimental characteristics of the material experiments from different logical dimensions, thereby improving the comprehensiveness and accuracy of the integrated analysis of various material experiments. This effectively enhances the experimental efficiency and success rate of material experiments. Additionally, it differentiates between different needs such as R&D / mass production and performance / cost, recommending differentiated solutions to improve user adaptability and satisfaction, ultimately enhancing the overall optimization effect of material experiments.
[0063] In one exemplary embodiment, such as Figure 1 As shown, a material experiment optimization method based on massive user data is provided. Taking the application of this method to a terminal as an example, the method includes the following steps S101 to S103. Wherein:
[0064] Step S101: Obtain the experimental data of each user in the material experiment, the experimental association data of each material experiment, and the current scenario information of the material experiment. Based on the experimental data of each user and the experimental association data, generate the experimental group corresponding to each logical dimension through a four-dimensional logical division strategy.
[0065] This experimental group includes experimental data from various users.
[0066] In this embodiment, after obtaining authorization from each user to use experimental data, the terminal collects experimental and equipment data through the device interface (Modbus / OPC UA) of the edge client, and collects environmental data through positioning and sensors. Each user inputs requirement data and current scene data through the client. This data is then anonymized and uploaded to the cloud, stored in a hybrid storage architecture of "relational database (user and environment data) + time-series database (experimental parameter data) + graph database (device-experiment association data)". The terminal obtains historical experimental data, environmental data, and equipment usage data for each user's current material experiment. It then retrieves the environmental information, equipment information, process requirements, and equipment requirements entered by the user who needs to optimize the material experiment, thus obtaining the current scene information of the material experiment. This material experiment is the one the user currently needs to perform. Based on the user's experimental data and the associated experimental data, the terminal generates experimental groups corresponding to each logical dimension using a four-dimensional logical partitioning strategy; each experimental group includes the user's experimental data. The four-dimensional logical partitioning strategy involves dividing each experimental data point into experimental groups with different ranges based on different logical dimensions. These logical dimensions include, but are not limited to, regional environment, experimental requirements, equipment type, and experiment type. The specific partitioning process will be explained in detail later.
[0067] Step S102: Based on the experimental groups of each logical dimension, the experimental characteristics analysis results of the material experiment are generated through the cross-domain correlation analysis model.
[0068] In this embodiment, the terminal generates experimental characteristic analysis results for materials experiments based on experimental groups across various logical dimensions using a cross-domain correlation analysis model. This cross-domain correlation analysis model includes sub-cross-domain correlation analysis models between different logical dimensions, such as an environment-experimental process correlation model, a demand-process matching model, and an equipment-experiment adaptation model. The experimental characteristic analysis results include explicit patterns of "environment-parameter-results" and implicit patterns of multi-factor coupling (such as the synergistic effect of equipment aging and environmental humidity). The specific generation process will be explained in detail later.
[0069] Step S103: Based on the experimental characteristic analysis results and the current scene information, generate an optimized experimental scheme for the target material that is adapted to the current scene information through a scene recommendation model.
[0070] In this embodiment, based on the experimental characteristic analysis results and current scene information, the terminal generates a target material experiment optimization scheme adapted to the current scene information through a scene recommendation model. This scene recommendation model includes an optimization model for the experimental process and a recommendation model for equipment. The target material experiment optimization scheme includes the current target experimental process for the material experiment and supplementary equipment recommendation information for the current material experiment. The specific generation process will be explained in detail later.
[0071] Based on the above scheme, through multi-dimensional data integration and classification analysis, and focusing on adapting to fixed external factors such as regional environment and equipment characteristics, the recommended scheme is more in line with the scenario-sensitive needs of materials experiments. Specifically, the target materials experiment optimization scheme generated by this scheme includes the current target experimental procedure and supplementary equipment recommendations for the current materials experiment. This not only combines a large amount of user data to provide optimized experimental procedures for different materials experiments, but also provides recommended experimental equipment, ensuring the accuracy and suitability of users' materials experiments. Furthermore, when analyzing user experimental data, this solution employs a four-dimensional logical partitioning strategy and a cross-domain correlation analysis model to perform partitioning and analysis. This allows for multi-angle, multi-level, and multi-dimensional analysis of user experimental data. It also comprehensively analyzes the experimental characteristics of the material experiments from different logical dimensions, thereby improving the comprehensiveness and accuracy of the integrated analysis of various material experiments. This effectively enhances the experimental efficiency and success rate of material experiments. Additionally, it differentiates between different needs such as R&D / mass production and performance / cost, recommending differentiated solutions to improve user adaptability and satisfaction, ultimately enhancing the overall optimization effect of material experiments.
[0072] Optionally, based on the experimental data of each user and the associated data of each experiment, an experimental group corresponding to each logical dimension is generated through a four-dimensional logical partitioning strategy. The experimental group includes the experimental data of each user, including: based on the experimental data of each user, the experimental process data of each experiment, the equipment data of each experiment, and the user requirement data of each experiment are identified. Based on the equipment data of each experiment, the user requirement data of each experiment, and the associated data of each experiment, the experimental data of each user is divided into sub-experimental groups of each logical level of each logical dimension through the data partitioning strategy of each logical dimension. All sub-experimental groups of each logical level of each logical dimension are taken as the experimental group of each logical dimension.
[0073] In this embodiment, the terminal identifies the experimental process data, equipment data, and user requirements data for each experiment based on the experimental data of each user. The experimental process data includes the experiment type (e.g., CVD thin film preparation, high-temperature heat treatment), experimental objective (R&D / mass production / performance optimization), process steps, equipment operating parameters (time-series data), control command sequence, experimental results (material performance testing data), and failure case records. The equipment data includes the user's existing equipment model, manufacturer, service life (aging coefficient), parameter accuracy range, historical fault records, and the experimental types the equipment is compatible with. The user requirements data includes experimental priority (efficiency / cost / performance), adjustable resources (e.g., whether equipment can be replaced, whether the environment can be optimized), and special requirements (e.g., low-temperature experiments, high-purity requirements).
[0074] Then, based on the device data, user demand data, and associated data for each experiment, the terminal divides the user experiment data into sub-experiment groups at each logical level of each logical dimension using a data partitioning strategy for each logical dimension. The data partitioning strategy for each logical dimension can employ a four-dimensional clustering algorithm to classify users and output user cluster labels. The specific data partitioning strategies for each logical dimension are shown in Table 1.
[0075] Table 1: Data partitioning strategies for each logical dimension
[0076]
[0077] Finally, the terminal uses all the sub-experimental groups of all logical levels of each logical dimension as the experimental group for each logical dimension.
[0078] Based on the above scheme, this scheme uses a four-dimensional logical partitioning strategy and a cross-domain correlation analysis model to partition and analyze user experimental data, thereby analyzing user experimental data from multiple angles, levels, and dimensions. It can also comprehensively analyze the experimental characteristics of the material experiment from different logical dimensions, thereby improving the comprehensiveness and accuracy of the integrated analysis of various material experiments, and effectively improving the experimental efficiency and success rate of material experiments.
[0079] Optionally, based on the experimental groups of each logical dimension, the experimental characteristic analysis results of the material experiment are generated through a cross-domain correlation analysis model, including: splitting the cross-domain correlation analysis model into sub-cross-domain correlation analysis models for each logical dimension; for each sub-cross-domain correlation analysis model, through the experimental groups of each logical dimension associated with the sub-cross-domain correlation analysis model, identifying the explicit change patterns and implicit change patterns between each logical dimension through the correlation analysis strategy of each sub-cross-domain correlation analysis model; and using the explicit change patterns and implicit change patterns between each logical dimension as the experimental characteristic analysis results of the material experiment.
[0080] In this embodiment, the terminal breaks down the cross-domain association analysis model into sub-cross-domain association analysis models for each logical dimension.
[0081] For each sub-cross-domain correlation analysis model, the terminal, based on the experimental groups of each logical dimension associated with the sub-cross-domain correlation analysis model, identifies the explicit and implicit change patterns between each logical dimension through the correlation analysis strategy of each sub-cross-domain correlation analysis model.
[0082] Specifically, the association analysis strategy for each sub-domain association analysis model is as follows:
[0083] 1. Environment-Experimental Process Correlation Model: Analyze the influence of different regional environments on process parameters under the same experimental type (e.g., the gas flow rate of CVD experiments under high humidity needs to be increased to suppress water vapor interference, and the temperature control rate needs to be reduced under low pressure to avoid material cracking).
[0084] 2. Demand-Process Matching Model: Matching the optimal process based on user experimental goals (R&D / mass production) (e.g., recommending multi-parameter gradient experimental processes for R&D users, and recommending fixed-parameter efficient processes for mass production users).
[0085] 3. Equipment-Experiment Adaptation Model: Analyze the range of suitable experimental parameters based on equipment model and aging level (e.g., older temperature control furnaces need to have their temperature fluctuation threshold reduced, while new equipment can support higher precision parameter adjustment).
[0086] The method for identifying explicit change patterns is to use a combination algorithm of "association rule mining + deep learning". Association rule mining extracts explicit patterns of "environment-parameter-result". The method for identifying implicit change patterns is to learn implicit patterns of multi-factor coupling (such as the synergistic effect of equipment aging and environmental humidity) through deep learning models (such as GraphSAGE).
[0087] The terminal uses the explicit and implicit patterns of change between the logical dimensions as the results of the experimental characteristic analysis of the materials experiment.
[0088] Based on the above scheme, this scheme uses a four-dimensional logical partitioning strategy and a cross-domain correlation analysis model to partition and analyze user data, thereby analyzing user experimental data from multiple angles, levels, and dimensions. It can also comprehensively analyze the experimental characteristics of the material experiment from different logical dimensions, thereby improving the comprehensiveness and accuracy of the integrated analysis of various material experiments, and effectively improving the experimental efficiency and success rate of material experiments.
[0089] Optionally, before generating the target material experiment optimization scheme adapted to the current scenario information through the scenario recommendation model based on the experimental characteristic analysis results and current scenario information, the following steps are also included: based on the current scenario information, identifying the current experimental requirements information, current environmental data, current geographical information, and current equipment information of the material experiment; based on the current experimental requirements information, identifying the process requirements information and equipment requirements information of the material experiment; and based on the equipment requirements information and current equipment information of the material experiment, identifying the equipment requirements information of the material experiment.
[0090] In this embodiment, the terminal identifies the current experimental requirements, current environmental data, current geographical location, and current equipment information of the materials experiment based on the current scene information. The current environmental data includes, but is not limited to, meteorological data, temperature data, air pressure data, humidity data, and other environmental data that may affect the materials experiment. The current geographical location information is the user's latitude and longitude. The current equipment information includes the model, age, and functions of each device currently owned by the user.
[0091] Then, based on the current experimental requirements, the terminal identifies the process requirements and equipment requirements for the materials experiment. Furthermore, based on the equipment requirements and the current equipment information, the terminal identifies the specific equipment requirements for the materials experiment. These equipment requirements include the model, service life, and functional scope of the equipment the user needs to replace, as well as the model, service life, and functional scope of the equipment the user needs to purchase.
[0092] Based on the above solution, by analyzing user needs and current scenario information, the comprehensiveness of the analysis of users' actual experiments and equipment is improved.
[0093] Optionally, based on the experimental characteristic analysis results and current scenario information, a scenario recommendation model is used to generate a target material experiment optimization scheme adapted to the current scenario information. This includes: based on the current experimental requirements, process requirements, and equipment requirements of the material experiment, the scope of optimization schemes adapted to the material experiment is identified through the experimental characteristic analysis results; based on the current environmental data and geographical information of the material experiment, a scenario intelligent recommendation module is used to filter the current target experimental process and supplementary equipment recommendations for the material experiment within the scope of optimization schemes; and the current target experimental process and supplementary equipment recommendations for the material experiment are used as the target material experiment optimization scheme adapted to the current scenario information.
[0094] In this embodiment, the terminal, based on the current experimental requirements, process requirements, and equipment requirements of the materials experiment, identifies the range of suitable optimization schemes for the materials experiment through experimental characteristic analysis results. These experimental characteristic analysis results combine explicit and implicit patterns to filter user experimental data corresponding to each logical dimension.
[0095] Then, based on the current environmental data and geographical information of the materials experiment, the terminal uses the scene-based intelligent recommendation module to filter the current target experimental procedure and supplementary equipment information for the materials experiment within the scope of optimization solutions. The specific filtering method is as follows:
[0096] 1. Experimental procedure optimization scheme:
[0097] a) Basic optimization: Adjust core parameters according to user classification tags (e.g., for CVD experiments of users in high humidity environments, it is recommended to increase the methane flow rate to 1.2 times that of a dry plain environment).
[0098] b) Step optimization: Optimize the equipment startup sequence (e.g., for users of older vacuum pumps, it is recommended to pre-evacuate for 30 minutes before heating to avoid contamination of the chamber).
[0099] c) Risk avoidance: Mark the experimental risk points and countermeasures (e.g., for users in low-pressure environments, remind them "the temperature control rate should not exceed 3℃ / min to avoid material stress cracking").
[0100] 2. Recommended Equipment List:
[0101] a) Existing equipment adaptation: Provide parameter adjustment suggestions for users' existing equipment (e.g., for users of old flow meters, it is recommended to replace them with high-precision sensors to adapt to high humidity environments).
[0102] b) Selection of new equipment: Recommend suitable equipment based on experimental needs (e.g., for mass production users, recommend CVD equipment with automated feeding function to improve efficiency).
[0103] c) Region adaptation labeling: Label the environmental adaptability of the device.
[0104] Finally, the terminal will use the current target experimental procedure of the materials experiment and the supplementary recommended information of the current equipment of the materials experiment as the target materials experiment optimization scheme for the current scenario information adaptation.
[0105] Based on the above solution, the scenario-based intelligent optimization recommendation scheme designed in this solution can adapt to the user's experimental needs, target experimental procedures that meet the user's environment and location, and supplementary equipment recommendation information, thereby improving the accuracy and adaptability of the recommendations to the user.
[0106] Optionally, after generating the target material experimental optimization scheme adapted to the current scene information through the scene recommendation model based on the experimental characteristic analysis results and current scene information, the process further includes: collecting user recommendation feedback information and identifying abnormal user evaluation information based on the recommendation feedback information; filtering each sample experimental data from each user's experimental data based on the abnormal evaluation information; training the scene recommendation model based on each sample experimental data to obtain a new scene recommendation model, replacing the original scene recommendation model with the new scene recommendation model, and returning to the execution step of generating the target material experimental optimization scheme adapted to the current scene information through the scene recommendation model based on the experimental characteristic analysis results and current scene information.
[0107] In this embodiment, the terminal collects user recommendation feedback information and identifies abnormal user evaluation information based on this information. This abnormal evaluation information can include dissatisfaction with the experimental procedure and dissatisfaction with equipment recommendations.
[0108] Then, based on the abnormal evaluation information, the terminal filters user experimental data from each user's experimental data to select those that match user dissatisfaction with the experimental process and equipment recommendations, using these as sample experimental data. Next, based on these sample experimental data, the terminal trains a scenario recommendation model to obtain a new scenario recommendation model. This new model replaces the original scenario recommendation model, and the terminal returns the results of the experimental characteristic analysis and the current scenario information. Using the scenario recommendation model, it generates a target material experimental optimization scheme step adapted to the current scenario information. This allows for the re-recommendation of new experimental processes and equipment recommendations to the user.
[0109] Based on the above solution, by combining user feedback information to adjust the scenario recommendation model, the recommendation accuracy of the scenario recommendation model and the user experience effect of dynamic user needs are improved.
[0110] This application also provides an example of intelligent detection for railway overhead contact lines, such as... Figure 2 As shown, the specific processing procedure includes the following steps:
[0111] Step S201: Obtain the experimental data of each user in the material experiment, the experimental correlation data of each material experiment, and the current scene information of the material experiment.
[0112] Step S202: Based on the experimental data of each user, identify the experimental process data, equipment data, and user requirements data for each experiment.
[0113] Step S203: Based on the equipment data, user demand data, and experimental association data for each experiment, the user experiment data is divided into sub-experiment groups at each logical level of each logical dimension through the data partitioning strategy of each logical dimension.
[0114] Step S204: Take all the sub-experimental groups of all logical levels of each logical dimension as the experimental group of each logical dimension.
[0115] Step S205: The cross-domain association analysis model is split into sub-cross-domain association analysis models for association analysis of each logical dimension.
[0116] Step S206: For each sub-cross-domain correlation analysis model, through the experimental groups of each logical dimension associated with the sub-cross-domain correlation analysis model, and through the correlation analysis strategy of each sub-cross-domain correlation analysis model, identify the explicit change patterns and implicit change patterns between each logical dimension.
[0117] Step S207: The explicit change patterns between each logical dimension and the implicit change patterns between each logical dimension are used as the experimental characteristic analysis results of the material experiment.
[0118] Step S208: Based on the current scene information, identify the current experimental requirements information of the materials experiment, the current environmental data of the materials experiment, the current geographical information of the materials experiment, and the current equipment information of the materials experiment.
[0119] Step S209: Based on the current experimental requirement information, identify the process requirement information and equipment requirement information of the material experiment, and based on the equipment requirement information and the current equipment information of the material experiment, identify the equipment requirement information of the material experiment.
[0120] Step S210: Based on the current experimental requirements, process requirements, and equipment requirements of the materials experiment, the range of optimization schemes suitable for the materials experiment is identified through the experimental characteristic analysis results.
[0121] Step S211: Based on the current environmental data and the current geographical information of the materials experiment, the current target experimental process and the current equipment of the materials experiment are selected from the optimization scheme range through the scene intelligent recommendation module.
[0122] Step S212: The current target experimental procedure of the material experiment and the supplementary recommended information of the current equipment of the material experiment are used as the target material experiment optimization scheme for the current scenario information adaptation.
[0123] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.
[0124] Based on the same inventive concept, this application also provides a material experiment optimization device based on massive user data for implementing the material experiment optimization method based on massive user data described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the material experiment optimization device based on massive user data provided below can be found in the limitations of the material experiment optimization method based on massive user data above, and will not be repeated here.
[0125] In one exemplary embodiment, such as Figure 3 As shown, a materials experiment optimization device based on massive user data is provided, including: an acquisition module 310, an analysis module 320, and a recommendation module 330, wherein:
[0126] The acquisition module 310 is used to acquire the experimental data of each user in the material experiment, the experimental association data of each experiment in the material experiment, and the current scene information of the material experiment, and based on the experimental data of each user and the experimental association data, generate experimental groups corresponding to each logical dimension through a four-dimensional logical partitioning strategy; the experimental group includes the experimental data of each user.
[0127] Analysis module 320 is used to generate experimental characteristic analysis results of the material experiment based on the experimental groups of each logical dimension through a cross-domain correlation analysis model;
[0128] The recommendation module 330 is used to generate a target material experiment optimization scheme that matches the current scene information based on the experimental characteristic analysis results and the current scene information through a scene recommendation model.
[0129] Optionally, the acquisition module 310 is specifically used for:
[0130] Based on the user experiment data mentioned above, identify the experimental process data, equipment data, and user requirement data for each experiment;
[0131] Based on the equipment data, user demand data, and experimental association data for each experiment, the user experiment data is divided into sub-experiment groups at each logical level of each logical dimension through a data partitioning strategy for each logical dimension.
[0132] Each logical dimension is divided into sub-experimental groups of all logical levels, which are used as the experimental groups for each logical dimension.
[0133] Optionally, the analysis module 320 is specifically used for:
[0134] The cross-domain association analysis model is broken down into sub-cross-domain association analysis models for each of the logical dimensions.
[0135] For each sub-cross-domain association analysis model, through the experimental groups of each logical dimension associated with the sub-cross-domain association analysis model, and through the association analysis strategy of each sub-cross-domain association analysis model, the explicit change patterns and implicit change patterns between each logical dimension are identified.
[0136] The explicit and implicit variation patterns between the logical dimensions are used as the experimental characteristic analysis results of the material experiment.
[0137] Optionally, the device further includes:
[0138] The first identification module is used to identify the current experimental requirements of the material experiment, the current environmental data of the material experiment, the current geographical information of the material experiment, and the current equipment information of the material experiment based on the current scene information.
[0139] The second identification module is used to identify the process requirements of the material experiment and the equipment requirements of the material experiment based on the current experimental requirements information, and to identify the equipment requirements of the material experiment based on the equipment requirements of the material experiment and the current equipment information of the material experiment.
[0140] Optionally, the recommendation module 330 is specifically used for:
[0141] Based on the current experimental requirements, process requirements, and equipment requirements of the material experiment, the range of optimization schemes suitable for the material experiment is identified through the experimental characteristic analysis results.
[0142] Based on the current environmental data and the current geographical information of the material experiment, the scene intelligent recommendation module filters the current target experimental process and the current equipment supplementary recommendation information of the material experiment within the scope of the optimization scheme.
[0143] The current target experimental procedure of the material experiment and the supplementary recommended information of the current equipment of the material experiment are used as the target material experiment optimization scheme for the current scenario information adaptation.
[0144] Optionally, the device further includes:
[0145] The data collection module is used to collect user recommendation feedback information and, based on the recommendation feedback information, identify abnormal evaluation information of the user.
[0146] The filtering module is used to filter each sample experimental data from each of the user experimental data based on the abnormal evaluation information.
[0147] The iterative module is used to train the scene recommendation model based on the experimental data of each sample, obtain a new scene recommendation model, replace the scene recommendation model with the new scene recommendation model, and return to the step of generating a target material experimental optimization scheme adapted to the current scene information based on the experimental characteristic analysis results and the current scene information through the scene recommendation model.
[0148] The modules in the aforementioned material experiment optimization device based on massive user data can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.
[0149] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a material experiment optimization method based on massive user data. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.
[0150] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0151] In one exemplary embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of a beer warehouse inventory optimization method.
[0152] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of a beer warehouse inventory optimization method.
[0153] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of a beer warehouse inventory optimization method.
[0154] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.
[0155] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.
[0156] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.
[0157] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.
Claims
1. A method for optimizing material experiments based on massive user data, characterized in that, The method includes: The experiment acquires user experimental data, experimental association data, and current scenario information of the material experiment. Based on the user experimental data and experimental association data, an experimental group corresponding to each logical dimension is generated using a four-dimensional logical partitioning strategy. The experimental group includes the user experimental data. Based on the experimental groups of each logical dimension, the experimental characteristic analysis results of the material experiments are generated through a cross-domain correlation analysis model. Based on the experimental characteristic analysis results and the current scene information, an optimized experimental scheme for the target material that is adapted to the current scene information is generated through a scene recommendation model.
2. The method according to claim 1, characterized in that, Based on the user experiment data and the associated experiment data, a four-dimensional logical partitioning strategy is used to generate experiment groups corresponding to each logical dimension; each experiment group includes the user experiment data, including: Based on the user experiment data mentioned above, identify the experimental process data, equipment data, and user requirement data for each experiment; Based on the equipment data, user demand data, and experimental association data for each experiment, the user experiment data is divided into sub-experiment groups at each logical level of each logical dimension through a data partitioning strategy for each logical dimension. Each logical dimension is divided into sub-experimental groups of all logical levels, which are used as the experimental groups for each logical dimension.
3. The method according to claim 2, characterized in that, The experimental groups based on each of the aforementioned logical dimensions generate experimental characteristic analysis results for the material experiments through a cross-domain correlation analysis model, including: The cross-domain association analysis model is broken down into sub-cross-domain association analysis models for each of the logical dimensions. For each sub-cross-domain association analysis model, through the experimental groups of each logical dimension associated with the sub-cross-domain association analysis model, and through the association analysis strategy of each sub-cross-domain association analysis model, the explicit change patterns and implicit change patterns between each logical dimension are identified. The explicit and implicit variation patterns between the logical dimensions are used as the experimental characteristic analysis results of the material experiment.
4. The method according to claim 1, characterized in that, Before generating the target material experiment optimization scheme adapted to the current scene information through the scene recommendation model based on the experimental characteristic analysis results and the current scene information, the method further includes: Based on the current scene information, identify the current experimental requirements of the material experiment, the current environmental data of the material experiment, the current geographical information of the material experiment, and the current equipment information of the material experiment; Based on the current experimental requirements information, the process requirements information and equipment requirements information of the material experiment are identified, and based on the equipment requirements information and the current equipment information of the material experiment, the equipment requirements information of the material experiment is identified.
5. The method according to claim 4, characterized in that, Based on the experimental characteristic analysis results and the current scene information, the process of generating a target material experimental optimization scheme adapted to the current scene information through a scene recommendation model includes: Based on the current experimental requirements, process requirements, and equipment requirements of the material experiment, the range of optimization schemes suitable for the material experiment is identified through the experimental characteristic analysis results. Based on the current environmental data and the current geographical information of the material experiment, the scene intelligent recommendation module filters the current target experimental process and the current equipment supplementary recommendation information of the material experiment within the scope of the optimization scheme. The current target experimental procedure of the material experiment and the supplementary recommended information of the current equipment of the material experiment are used as the target material experiment optimization scheme for the current scenario information adaptation.
6. The method according to claim 1, characterized in that, After generating the target material experiment optimization scheme adapted to the current scene information through a scene recommendation model based on the experimental characteristic analysis results and the current scene information, the method further includes: Collect user recommendation feedback information, and based on the recommendation feedback information, identify abnormal evaluation information of the user; Based on the aforementioned abnormal evaluation information, each sample of experimental data is selected from the user experimental data. Based on the experimental data of each sample, the scene recommendation model is trained to obtain a new scene recommendation model. The new scene recommendation model is then used to replace the original scene recommendation model. The process then returns to the step of generating a target material experimental optimization scheme that is adapted to the current scene information based on the experimental characteristic analysis results and the current scene information through the scene recommendation model.
7. A material experiment optimization device based on massive user data, characterized in that, The device includes: The acquisition module is used to acquire the experimental data of each user in the material experiment, the experimental association data of each material experiment, and the current scene information of the material experiment, and based on the experimental data of each user and the experimental association data, generate experimental groups corresponding to each logical dimension through a four-dimensional logical partitioning strategy; the experimental group includes the experimental data of each user. The analysis module is used to generate experimental characteristic analysis results of the material experiments based on the experimental groups of each logical dimension through a cross-domain correlation analysis model. The recommendation module is used to generate an optimized experimental scheme for the target material that is adapted to the current scene information based on the experimental characteristic analysis results and the current scene information through a scene recommendation model.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.