Sequence data modeling method and system based on recurrent neural network

Abstract

The invention discloses a sequence data modeling method and system based on a recurrent neural network, and belongs to the technical field of sequence data modeling, and the method comprises the steps: determining each reserve demand in real time, and arranging training data corresponding to each reference model according to each reserve demand and a reference model corresponding to the recurrent neural network; setting function introduction data corresponding to each reference model; establishing a model library, and establishing a training adjustment model according to the model library; analyzing the user demand data uploaded by the user, determining a user application model, and loading and installing the user application model in the user side; identifying each piece of sequence data, analyzing each piece of sequence data through a user application model to obtain an analysis result, and displaying the analysis result to a user; when the user adjusts the analysis result, identifying an optimization result adjusted by the user, and integrating the optimization result into application optimization data; and optimizing and adjusting the user application model through the application optimization data.

Description

Technical Field

[0001] The present invention belongs to the technical field of sequence data modeling, and specifically relates to a sequence data modeling method and system based on recurrent neural network. Background Art

[0002] In today's information society, sequence data is everywhere, such as stock prices, weather data, human health monitoring data, etc. The analysis and modeling of these data are of great value to individual users and enterprises. However, the existing sequence data modeling technology mainly relies on manual establishment by professionals, which not only consumes a lot of time and energy, but also requires the modeler to have deep professional knowledge and practical experience.

[0003] For most individual users, although they have a strong demand for sequence data analysis and modeling, they often find it difficult to build the corresponding models themselves due to lack of professional knowledge and skills. At the same time, individual users are often unwilling to invest a lot of time and money for an unnecessary model, which further limits the popularization, promotion and application of sequence data modeling technology.

[0004] In view of this situation, the market is in urgent need of a technical solution that can lower the threshold of sequence data modeling and improve modeling efficiency. However, most existing solutions still focus on providing advanced modeling tools for professionals, but fail to fully consider the needs and characteristics of individual users.

[0005] Therefore, the present invention proposes a sequence data modeling system based on recurrent neural network, aiming to solve the above problems. Summary of the invention

[0006] In order to solve the problems existing in the above scheme, the present invention provides a sequence data modeling method and system based on recurrent neural network.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] A sequence data modeling system based on recurrent neural network, including a platform end and a user end;

[0009] The platform end includes a model module, a demand analysis module and an upgrade module;

[0010] The model module is used to determine each reserve demand in real time, and according to each reserve demand and the corresponding benchmark model of the recurrent neural network, the benchmark model is used to analyze the corresponding sequence data; organize the training data corresponding to each benchmark model; set the function introduction data corresponding to each benchmark model;

[0011] Establish a model library, input various reserve requirements, function introduction data, benchmark models and training data into the model library for storage;

[0012] A training adjustment model is established according to the model library, and the training adjustment model is used to adjust the training data of the corresponding benchmark model according to the user's sequence material data.

[0013] Furthermore, the reserve requirement is determined as follows:

[0014] Identify each type of sequence data in real time; the platform sets the conversion coefficient of each type of sequence data for different users;

[0015] Screening each type of sequence data to determine each type of sequence to be screened;

[0016] Identify in real time the potential user range corresponding to each type of sequence to be screened, and count the potential number of each potential user within the potential user range;

[0017] Mark each potential user within the potential user range as i, where i=1, 2, ..., n, and n is a positive integer; mark the potential number of each potential user as Li;

[0018] According to the formula Calculate the screening value of each type of sequence to be screened;

[0019] Where: PA is the screening value; λi represents the conversion coefficient corresponding to the corresponding potential user;

[0020] The reserve requirement is set according to the type of the sequence to be screened whose screening value is greater than the threshold X1.

[0021] The demand analysis module is used to analyze the user demand data uploaded by the user and determine the user application model, wherein the user application model is obtained by optimizing and adjusting the corresponding benchmark model according to the user demand data; and the user application model is loaded and installed in the user terminal.

[0022] Furthermore, the method for analyzing the user demand data uploaded by the user includes:

[0023] Identify the sequence material data and functional requirements in the user requirement data, and match the corresponding benchmark model and training data from the model library according to the functional requirements;

[0024] Performing adjustment analysis on the sequence material data and the training data by using the training adjustment model to obtain adjusted training data, which is marked as training adjustment data;

[0025] The training adjustment data is displayed to the user, and the user verifies the displayed training adjustment data to obtain training optimization data;

[0026] The benchmark model is optimized and adjusted using the training optimization data to obtain a user application model.

[0027] The upgrade module is used to perform model upgrade and adjustment, receive the user's upgrade requirements in real time, and upgrade and adjust the user application model of the user according to the upgrade requirements.

[0028] The user end includes a demand module, a data analysis module and an upgrade demand module;

[0029] The requirement module is used for users to set and upload user requirement data, and the user requirement data includes sequence material data and functional requirements.

[0030] Furthermore, the method for the user to set the user demand data includes:

[0031] The platform presets a demand tutorial, and the user determines the type of sequence data that needs to be analyzed according to the demand tutorial. The sequence data is counted according to the type of sequence data, and the user marks the corresponding processing result for each sequence data, and integrates them into sequence material data;

[0032] Set functional requirements; integrate functional requirements and sequence material data into user requirement data.

[0033] Furthermore, before the user marks the processing result for each sequence data, each sequence data is checked and analyzed, and a corresponding rejection mark is set for the sequence data that fails the check.

[0034] Furthermore, the method for checking and analyzing each sequence data includes:

[0035] A data verification model is established, and the expression of the data verification model is:

[0036]

[0037] In the formula: (s, f) is the input data, s is the sequence data; f is the type of sequence data; the output data is the data calibration value NH(s, f), and the data calibration value is 1 or 0;

[0038] Identify each sequence data and sequence data type, analyze each sequence data and sequence data type by using the data verification model, and obtain a data verification value for each sequence data;

[0039] When the data verification value is 0, the corresponding sequence data verification is evaluated as failed;

[0040] When the data verification value is 1, the corresponding sequence data verification is evaluated to be passed.

[0041] The data analysis module is used to analyze the sequence data, identify each sequence data, analyze each sequence data through the user application model, obtain corresponding analysis results, and display the analysis results to the user;

[0042] When the user adjusts the analysis result, the analysis result adjusted by the user is identified, marked as an optimization result, and the corresponding sequence data, analysis result and optimization result are integrated into application optimization data; and the user application model is optimized and adjusted through the application optimization data;

[0043] When the user does not adjust the analysis results, no corresponding operation is performed.

[0044] Furthermore, the method for optimizing and adjusting the user application model by applying the optimization data includes:

[0045] Establish an optimization library, and send each of the application optimization data to the optimization library for storage; identify the number of application optimization data stored in the optimization library in real time, and when the number of application optimization data reaches a threshold value X2, perform similar expansion on each of the application optimization data stored in the optimization library to obtain equivalent expansion data corresponding to each of the application optimization data;

[0046] Send optimization and expansion information to the user, and when the preset time is reached, optimize and adjust the user application model through each application optimization data and equivalent expansion data; delete the application optimization data and equivalent expansion data in the optimization library.

[0047] The upgrade requirement module is used to set corresponding upgrade requirements when the user has upgrade requirements and send the upgrade requirements to the platform end.

[0048] A sequence data modeling method based on a recurrent neural network, the method comprising:

[0049] Determine each reserve requirement in real time, and organize the training data corresponding to each benchmark model according to each reserve requirement and the corresponding benchmark model of the recurrent neural network; set the function introduction data corresponding to each benchmark model;

[0050] Establish a model library, input various reserve requirements, function introduction data, benchmark models and training data into the model library for storage; establish a training adjustment model based on the model library;

[0051] Analyze the user demand data uploaded by the user, determine the user application model, and load and install the user application model on the user terminal;

[0052] Identify each sequence data, analyze each sequence data through the user application model, obtain the analysis results, and display the analysis results to the user;

[0053] When the user adjusts the analysis result, the analysis result after the user's adjustment is identified and marked as an optimization result, and the corresponding sequence data, analysis result and optimization result are integrated into application optimization data; the user application model is optimized and adjusted through the application optimization data;

[0054] When the user has an upgrade requirement, the corresponding upgrade requirement is set, and the platform upgrades and adjusts the user's user application model according to the upgrade requirement.

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] First, the present invention greatly reduces the threshold for sequence data modeling, allowing non-professional users to easily analyze and model sequence data. Traditionally, model building requires professionals to spend a lot of time and energy, which is unrealistic for most individual users. However, the present invention can intelligently generate models for personal applications based on the sequence data selected by the user through the platform's intelligent services, without the need for users to have deep professional knowledge and practical experience, thereby greatly expanding the scope of application of sequence data modeling technology.

[0057] Secondly, the present invention improves the efficiency of sequence data modeling. Since the platform has pre-trained models for various sequence data, users can obtain models that meet their needs in a short time without having to build them from scratch. This not only saves users' time, but also improves the accuracy and reliability of modeling.

[0058] In addition, the present invention also provides a flexible optimization and adjustment scheme. When users have higher requirements for the accuracy of the model, the platform can dispatch professionals to perform optimization and adjustment. This method of providing users with free or low-cost transitional use and experience in the early stage not only reduces the threshold and cost of users, but also facilitates the promotion and popularization of technology. At the same time, since users will accumulate a large amount of training materials that truly reflect their needs during long-term use, this provides rich data support for the optimization and adjustment of professionals in the later stage, further improving the accuracy and practicality of the model.

[0059] Finally, the implementation of the present invention can also help promote the sustainable development of sequence data modeling technology. Through the intelligent services of the platform and the optimization and adjustment of professionals, the model library can be continuously accumulated and optimized to improve the adaptability and generalization ability of the model. At the same time, the present invention can also stimulate more users' interest and enthusiasm in sequence data modeling technology and promote technological innovation and development. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0061] Figure 1 This is a principle block diagram of the present invention. DETAILED DESCRIPTION

[0062] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] like Figure 1 As shown, a sequence data modeling system based on recurrent neural network includes a platform end and a user end;

[0064] The platform end is used by the platform party and includes a model module, a demand analysis module and an upgrade module;

[0065] The model module is used for intelligent analysis of various possible sequence data modeling requirements, which are marked as reserve requirements;

[0066] Establish corresponding benchmark models according to each reserve demand and recurrent neural network, and organize the training data corresponding to each benchmark model; the establishment of benchmark models and the setting of training data are all established and set by the platform's professionals; set the functional introduction data of each benchmark model, that is, introduce how the benchmark model analyzes sequence data and what results are obtained;

[0067] Establish a model library, input various reserve requirements, function introduction data, benchmark models and training data into the model library for storage;

[0068] A training adjustment model is established through existing intelligent technology, and the training adjustment model is used to subsequently perform intelligent adjustment on the training data of the corresponding benchmark model according to the sequence material data received from the user; that is, the adjustment is performed according to the rules, requirements, etc. corresponding to the sequence material data of the user, and the corresponding training adjustment model can be established through the professional capabilities of the platform; it can be established manually by the platform; illustratively, the training adjustment model can be established based on neural networks such as CNN networks and DNN networks, and the corresponding training sets are established manually for training, and the training set includes input data and output data, the input data is the sequence material data and the training data of the corresponding benchmark model; the output data is the adjusted training data.

[0069] In one embodiment, the reserve requirement is determined based on existing methods.

[0070] In one embodiment, the method for determining the reserve requirement is:

[0071] Identify various sequence data in real time and mark them as sequence data types; the platform estimates the possible conversion rate of each sequence data type for different users and marks them as conversion coefficients, that is, the platform estimates the conversion rate of each sequence data type for various users;

[0072] Determine the types of sequences to be screened by combining the corresponding established benchmark models;

[0073] Real-time identification of the potential user range corresponding to each type of sequence to be screened, that is, the range of people who will be applied to this type of sequence data; real-time statistical estimation of the number of each potential user within the potential user range, marked as potential number;

[0074] Each potential user within the potential user range is marked as i, where i=1, 2, ..., n, and n is a positive integer; the potential number of each potential user is marked as Li;

[0075] According to the formula Calculate the screening value of each type of sequence to be screened;

[0076] Where: PA is the screening value; λi represents the conversion coefficient corresponding to the corresponding potential user;

[0077] The reserve requirement is set according to the types of sequences to be screened whose screening values ​​are greater than the threshold X1.

[0078] The demand analysis module is used to analyze the user demand data uploaded by the user, identify the sequence material data and functional requirements in the user demand data, and match the corresponding benchmark model and training data from the model library according to the functional requirements; adjust and analyze the sequence material data and the training data through the training adjustment model to obtain the adjusted training data, mark it as training adjustment data, and display the training adjustment data to the user. The user verifies the displayed training adjustment data according to the needs, or does not need to verify it, but the accuracy after verification is higher. If not verified, the training optimization is performed according to the adjustment data of subsequent users; the verified training adjustment data is marked as training optimization data, the benchmark model is optimized and adjusted through the training optimization data, the adjusted benchmark model is marked as the user application model, and loaded at the user end.

[0079] The upgrade module is used to upgrade and adjust the user's user application model, that is, the platform's professionals perform targeted optimization and upgrades on the user's user application model to improve its analysis accuracy.

[0080] The user terminal is used by users and can be in the form of an app, a website, etc.; it includes a demand module, a data analysis module, and an upgrade demand module;

[0081] The demand module is used for users to set and upload user demand data, which includes sequence material data, functional requirements and other related data; the detailed process is as follows:

[0082] A corresponding user demand data template, i.e., a corresponding tutorial, is preset. The user determines the type of sequence data to be analyzed according to the demand tutorial. The user counts each sequence data according to the type of sequence data, marks the corresponding processing result for each sequence data, and integrates them into sequence material data; sets functional requirements; and integrates the functional requirements and sequence material data into user demand data.

[0083] In one embodiment, since in actual application, users often add sequence data of a type other than the sequence data to sequence material data, which affects the analysis accuracy of the subsequent benchmark model, in this embodiment, each sequence data determined by the user is checked, and the process is as follows:

[0084] A data verification model is established. The data verification model is used to determine whether the sequence data belongs to the corresponding sequence data type. The expression of the data verification model is: In the formula: (s, f) is the input data, s is the sequence data; f is the type of sequence data; the output data is the data calibration value NH(s, f), and the data calibration value is 1 or 0;

[0085] Analyze each sequence data and sequence data type through a data verification model to obtain a data verification value for each sequence data;

[0086] Each sequence data with a data calibration value of 0 was marked for removal.

[0087] The data analysis module is used to analyze the corresponding sequence data at the user, identify each sequence data, analyze each sequence data through the user application model, obtain the corresponding analysis result, and display the analysis result to the user;

[0088] When the user adjusts the analysis results, the analysis results adjusted by the user are identified and marked as optimization results, and the corresponding sequence data, analysis results and optimization results are integrated into application optimization data; the user application model is optimized and adjusted through the application optimization data.

[0089] When the user does not adjust the analysis results, no corresponding operation is performed.

[0090] In one embodiment, optimizing and adjusting the user application model by applying the optimization data is real-time adjustment, that is, adjusting the user application model in real time according to the obtained application optimization data.

[0091] In one embodiment, the method of optimizing and adjusting the user application model by applying the optimization data is to optimize and adjust the user application model according to the application optimization data based on the existing technology.

[0092] In one embodiment, the method for optimizing and adjusting the user application model by applying optimization data includes:

[0093] An optimization library is established, and each application optimization data is sent to the optimization library for storage, so that users can view the optimization in real time; the number of stored application optimization data is identified in real time, and when the number of application optimization data reaches a threshold value X2, the same type of application optimization data stored in the optimization library is expanded to obtain equivalent expanded data corresponding to each application optimization data, that is, expansion simulation is performed according to the sequence data in the application optimization data to form a sequence data that can be regarded as equivalent to it but has different data, and corresponding analysis results are generated according to the optimization results based on the generated sequence data; the above expansion steps can be implemented based on existing technologies, such as by the platform side. Establish a corresponding equivalent expansion model for a neural network such as a CNN network or a DNN network, and establish a corresponding training set for training by artificial means, wherein the training set includes input data and output data, wherein the input data is the optimization data of each application, and the output data is the equivalent expansion data corresponding to the optimization data of each application; perform analysis through the equivalent expansion model to obtain the equivalent expansion data corresponding to the optimization data of each application; send optimization expansion information to the user, indicating that the user application model will be optimized and adjusted after a preset time, during which the user can view the optimization data of each application and the equivalent expansion data, and can adjust the equivalent expansion data;

[0094] When the preset time is reached, the user application model is optimized and adjusted through each application optimization data and equivalent expansion data, and the corresponding equivalent expansion data can also be retained for verification; the application optimization data and equivalent expansion data in the optimization library are deleted.

[0095] The upgrade requirement module is used to set corresponding upgrade requirements and send the corresponding upgrade requirements to the platform end when the user has a need to professionally upgrade the user application model.

[0096] Because the early user application models are basically free or low-cost for each user, when users have higher-precision analysis needs, they need to be optimized and upgraded by professionals on the platform.

[0097] A sequence data modeling method based on a recurrent neural network, the method comprising:

[0098] Determine each reserve requirement in real time, and organize the training data corresponding to each benchmark model according to each reserve requirement and the corresponding benchmark model of the recurrent neural network; set the function introduction data corresponding to each benchmark model;

[0099] Establish a model library, input various reserve requirements, function introduction data, benchmark models and training data into the model library for storage; establish a training adjustment model based on the model library;

[0100] Analyze the user demand data uploaded by the user, determine the user application model, and load and install the user application model on the user side.

[0101] Identify each sequence data, analyze each sequence data through the user application model, obtain the corresponding analysis results, and display the analysis results to the user;

[0102] When the user adjusts the analysis result, the analysis result after the user's adjustment is identified and marked as an optimization result, and the corresponding sequence data, analysis result and optimization result are integrated into application optimization data; the user application model is optimized and adjusted through the application optimization data;

[0103] When the user has an upgrade requirement, the corresponding upgrade requirement is set, and the platform upgrades and adjusts the user's user application model according to the upgrade requirement.

[0104] The above formulas are all calculated by removing dimensions and taking numerical values. The formula is a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data.

[0105] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A sequence data modeling system based on recurrent neural network, characterized in that: Including platform side and user side; The platform end includes a model module, a demand analysis module and an upgrade module; The model module is used to determine each reserve demand in real time, and according to each reserve demand and the corresponding benchmark model of the recurrent neural network, the benchmark model is used to analyze the corresponding sequence data; organize the training data corresponding to each benchmark model; Setting function introduction data corresponding to each of the benchmark models; Establish a model library, input various reserve requirements, function introduction data, benchmark models and training data into the model library for storage; Establishing a training adjustment model according to the model library, wherein the training adjustment model is used to adjust the training data of the corresponding benchmark model according to the user's sequence material data; The demand analysis module is used to analyze the user demand data uploaded by the user and determine the user application model, wherein the user application model is obtained by optimizing and adjusting the corresponding benchmark model according to the user demand data; and the user application model is loaded and installed in the user terminal; The upgrade module is used to perform model upgrade adjustment, receive the user's upgrade requirements in real time, and upgrade and adjust the user application model of the user according to the upgrade requirements; The user end includes a demand module, a data analysis module and an upgrade demand module; The requirement module is used for users to set and upload user requirement data, and the user requirement data includes sequence material data and functional requirements; The data analysis module is used to analyze the sequence data, identify each sequence data, analyze each sequence data through the user application model, obtain corresponding analysis results, and display the analysis results to the user; When the user adjusts the analysis result, the analysis result adjusted by the user is identified, marked as an optimization result, and the corresponding sequence data, analysis result and optimization result are integrated into application optimization data; Optimizing and adjusting the user application model through the application optimization data; When the user does not adjust the analysis results, no corresponding operation is performed; The upgrade requirement module is used to set corresponding upgrade requirements when the user has upgrade requirements and send the upgrade requirements to the platform end.

2. A sequence data modeling system based on recurrent neural network according to claim 1, characterized in that: The reserve requirement is determined as follows: Identify each type of sequence data in real time; the platform sets the conversion coefficient of each type of sequence data for different users; Screening each type of sequence data to determine each type of sequence to be screened; Identify in real time the potential user range corresponding to each type of sequence to be screened, and count the potential number of each potential user within the potential user range; Mark each potential user within the potential user range as i, where i=1, 2, ..., n, and n is a positive integer; mark the potential number of each potential user as Li; According to the formula Calculate the screening value of each type of sequence to be screened; Where: PA is the screening value; λi represents the conversion coefficient corresponding to the corresponding potential user; The reserve requirement is set according to the type of the sequence to be screened whose screening value is greater than the threshold X1.

3. A sequence data modeling system based on recurrent neural network according to claim 1, characterized in that: Methods for analyzing user demand data uploaded by users include: Identify the sequence material data and functional requirements in the user requirement data, and match the corresponding benchmark model and training data from the model library according to the functional requirements; Performing adjustment analysis on the sequence material data and the training data by using the training adjustment model to obtain adjusted training data, which is marked as training adjustment data; The training adjustment data is displayed to the user, and the user verifies the displayed training adjustment data to obtain training optimization data; The benchmark model is optimized and adjusted using the training optimization data to obtain a user application model.

4. A sequence data modeling system based on recurrent neural network according to claim 1, characterized in that: The methods for users to set user demand data include: The platform presets a demand tutorial, and the user determines the type of sequence data that needs to be analyzed according to the demand tutorial. The sequence data is counted according to the type of sequence data, and the user marks the corresponding processing result for each sequence data, and integrates them into sequence material data; Set functional requirements; integrate functional requirements and sequence material data into user requirement data.

5. A sequence data modeling system based on recurrent neural network according to claim 4, characterized in that: Before the user marks the processing result for each sequence data, each sequence data is checked and analyzed, and a corresponding rejection mark is set for the sequence data that fails the check.

6. A sequence data modeling system based on recurrent neural network according to claim 5, characterized in that: Methods for checking and analyzing the data of each sequence include: A data verification model is established, and the expression of the data verification model is: In the formula: (s, f) is the input data, s is the sequence data; f is the type of sequence data; the output data is the data calibration value NH(s, f), and the data calibration value is 1 or 0; Identify each sequence data and sequence data type, analyze each sequence data and sequence data type by using the data verification model, and obtain a data verification value for each sequence data; When the data verification value is 0, the corresponding sequence data verification is evaluated as failed; When the data verification value is 1, the corresponding sequence data verification is evaluated to be passed.

7. A sequence data modeling system based on recurrent neural network according to claim 1, characterized in that: Methods for optimizing and adjusting user application models through application optimization data include: Establish an optimization library, and send each of the application optimization data to the optimization library for storage; identify the number of application optimization data stored in the optimization library in real time, and when the number of application optimization data reaches a threshold value X2, perform similar expansion on each of the application optimization data stored in the optimization library to obtain equivalent expansion data corresponding to each of the application optimization data; Send optimization and expansion information to the user, and when the preset time is reached, optimize and adjust the user application model through each application optimization data and equivalent expansion data; delete the application optimization data and equivalent expansion data in the optimization library.

8. A sequence data modeling method based on recurrent neural network, characterized in that: A sequence data modeling system based on a recurrent neural network as described in any one of claims 1 to 7, the method comprising: Determine each reserve requirement in real time, and organize the training data corresponding to each benchmark model according to each reserve requirement and the corresponding benchmark model of the recurrent neural network; set the function introduction data corresponding to each benchmark model; Establish a model library, input various reserve requirements, function introduction data, benchmark models and training data into the model library for storage; establish a training adjustment model based on the model library; Analyze the user demand data uploaded by the user, determine the user application model, and load and install the user application model on the user terminal; Identify each sequence data, analyze each sequence data through the user application model, obtain the analysis results, and display the analysis results to the user; When the user adjusts the analysis result, the analysis result after the user's adjustment is identified and marked as an optimization result, and the corresponding sequence data, analysis result and optimization result are integrated into application optimization data; the user application model is optimized and adjusted through the application optimization data; When the user has an upgrade requirement, the corresponding upgrade requirement is set, and the platform upgrades and adjusts the user's user application model according to the upgrade requirement.

Images