51 results about "Loss function" patented technology

The invention relates to a method for improving the reasoning ability of a large language model based on Monte Carlo tree search. The method comprises the following steps that S1, a mathematical question set and corresponding standard answers are preset; s2, taking each step for solving a mathematical problem as a tree node, and generating a Monte Carlo tree in the whole problem solving process; s3, generating training data based on Monte Carlo tree search; s4, scoring the generated training data; and S5, constructing a loss function according to scores obtained by scoring, optimizing the loss function and updating parameters of the large language model. The reasoning ability of the large language model can be improved.

The embodiment of the invention provides a training method, a reasoning method and a related device for a stream matching generation model, which are used for improving the accuracy of an action sequence predicted by the trained stream matching generation model. The method provided by the embodiment of the invention comprises the following steps: acquiring noise, a moment t and an environment characteristic of a first action, wherein the environment characteristic of the first action at least comprises an observation value of the first action; inputting the noise, the moment t and the environment characteristics into an initialized flow matching generation model to obtain an output predicted velocity field vector of the conditional probability path at the moment t + 1; calculating the loss between the predicted velocity field vector and the real velocity field vector by using a preset loss function, wherein the preset loss function comprises at least one of a first loss function and a second loss function, and a third loss function; and training the initialized stream matching generation model by using a loss and back propagation algorithm until the stream matching generation model converges to obtain a trained stream matching generation model.

The invention specifically discloses a lithium carbonate price prediction method and device based on a large language model, and a medium, and relates to the technical field of financial prediction and intelligent decision support. The method comprises the following steps: firstly, collecting and processing numerical type and text type data, constructing a causal graph network by the numerical type data, and extracting factual abstracts by the text type data to construct a news event library; then designing a three-layer progressive prompt template, and driving the large language model to generate a prediction result with explanation; then, implementing a dual-verification self-optimization reflection mechanism, and triggering an reflection generation improvement strategy when misjudgment is carried out or an error exceeds a threshold value; using a KTO algorithm to construct asymmetric loss function fine tuning model parameters; and finally, deploying the optimized model to a production system. According to the method, the dynamic adaptability and robustness of the model are improved through a'prediction-reflection-optimization 'closed-loop optimization architecture and a KTO algorithm driven by a foreground theory, prediction precision and interpretability are considered, and multi-dimensional decision support is provided for lithium carbonate price prediction.

The invention relates to a dynamic concept cognitive anomaly detection method and system under an unbalanced condition, and the method comprises the steps: collecting the related feature data of a sample set in a scene facing a specific extreme event, and dividing an initial data set and a test set; constructing an initial learning model; performing dynamic event type prediction based on the test set, and classifying the event as an extreme event or a non-extreme event; constructing an active three-way concept learning module to form a positive concept space and a negative concept space based on a three-way decision idea and prediction probability values of extreme events and non-extreme events; according to the positive concept space and the negative concept space, introducing a concept center domain strategy for dynamic updating; and adopting a loss function minimization strategy to obtain an optimal learning model. The effectiveness of dynamic detection is improved by utilizing an active three-way concept learning method, a concept center field and a concept dynamic optimization strategy, and the capability of identifying extreme events under the extremely unbalanced scene condition is realized.

A process for optimizing loss functions includes progressively building better sets of parameters for loss functions represented as multivariate Taylor expansions in accordance with an iterative process. The optimization process is built upon CMA-ES. At each generation (i.e., each CMA-ES iteration), a new set of candidate parameter vectors is sampled. These candidate parameter vectors are sampled from a multivariate Gaussian distribution representation that is modeled by the CMA-ES covariance matrix and the current mean vector. The candidates are then each evaluated by training a model (neural network) using the candidates and determining a fitness value for each candidate against a validation data set.

The invention discloses a decoupling adversarial sample generation method. The method comprises the following steps: decoupling an adversarial sample by taking a condition of decoupling the adversarial sample and obtaining a sum of a clean sample and adversarial disturbance as a decoupling principle; constructing a multi-objective optimization function, wherein the multi-objective optimization function comprises a plurality of constraint conditions; constructing a plurality of loss functions to enable the constructed plurality of loss functions to correspond to a plurality of constraint conditions, and training and updating the generative model by using the weighted sum of the plurality of loss functions as a final loss function to obtain a generative model meeting a decoupling principle confrontation sample; evaluating the obtained generative model meeting the decoupling principle confrontation sample by using an evaluation index until the evaluation result meets the decoupling principle and successfully attacks the target model at the same time; and generating a confrontation sample which can simultaneously meet the decoupling principle and aggressiveness by using the trained generative model. According to the invention, the problem that the adversarial sample cannot be decoupled, especially the problem that the adversarial sample cannot be decoupled at the model side, can be solved.

The invention discloses a mathematical problem data enhancement method and system based on semantic retrieval. The method comprises the following steps: loading a mathematical problem data set, calculating features of each mathematical problem by using a preset neural network model encoder, and outputting an original feature set; for one feature in the set, the other feature closest to the feature in the whole feature set is screened out by calculating semantic similarity, and the screened feature is obtained; performing mixed enhancement on the original features and the screened features to obtain enhanced features; inputting the original features and the enhanced features into a preset neural network model decoder to obtain a structured solution; and repeating the above processes, and iteratively training parameters of the model by using a loss function with a gradient stopping strategy to obtain an optimized mathematical problem and a solution thereof. According to the method, the adaptability of the model to different question types can be effectively improved, language barriers can be overcome, and the method is also suitable for mathematical problems of Chinese and English.

The invention discloses a two-stage label noise learning classification method and system, and the method comprises the following steps: constructing a relative similarity filter through the comprehensive measurement of relative similarity and Euclidean distance, inputting an original data set into the relative similarity filter, screening out noise samples through the calculation of the relative similarity of the samples, and carrying out the classification of the noise samples. Outputting the filtered data set; inputting the filtered data set into a robust sorting support vector machine model based on a non-convex slope loss function and a local label weighting strategy for training, and converting the non-convex loss function into a convex optimization problem through a convex-concave process for solving to obtain an optimal model parameter; and updating a model threshold by using the optimal model parameter, and classifying a to-be-classified sample by using the updated model. According to the method, data-level screening and model-level noise suppression are both considered, the problem of unstable performance under a single processing path in a traditional method is solved, and the method is particularly suitable for stable learning tasks under high-dimensional and high-noise scenes.

The invention provides a training method and device of a scheme generation and optimization model based on a large model. The training method of the scheme generation and optimization model based on the large model comprises the steps of obtaining a sample experiment scheme and a sample demand thereof; training by taking the sample experiment scheme and the sample demand as training samples and taking the first autoregression loss as a loss function to obtain a scheme generation model; processing and training the second language by taking the historical optimization trajectory and the target scheme as training samples and taking the improved opinion loss as a loss function to obtain a feedback model; taking a sample requirement, a historical optimization track and a sample improvement opinion output by the feedback model in a historical training process as a training sample, and taking a second autoregression loss as a loss function for training to obtain an optimization model; obtaining a scheme generation and optimization model based on the scheme generation model, the feedback model and the optimization model; according to the method provided by the invention, the automatic design and optimization of the scheme for the special equipment or system are realized, and the generation efficiency and accuracy of the experimental scheme are improved.

The application provides a large model-based scheme generation and optimization model training method and device, the large model-based scheme generation and optimization model training method comprises the following steps: obtaining a sample experiment scheme and sample requirements thereof; taking the sample experiment scheme and the sample requirements as training samples, and training a scheme generation model by taking a first autoregressive loss as a loss function; taking a historical optimization trajectory and a target scheme as training samples, and training a feedback model by taking an improved opinion loss as a loss function; taking the sample requirements, the historical optimization trajectory, and sample improved opinions output by the feedback model in a historical training process as training samples, and training an optimization model by taking a second autoregressive loss as a loss function; and obtaining a scheme generation and optimization model based on the scheme generation model, the feedback model, and the optimization model; the method realizes automatic design and optimization of a scheme for a special device or system, and improves experiment scheme generation efficiency and accuracy.

A computational method (400) for training a meta-learned evolutionary strategy black-box optimization classifier to learn an actuator control command for actuating a computer-controlled machine, the method comprising: Receiving (402) one or more training functions F and one or more initial metalearning parameters Θ of the metalearning evolutionary strategy blackbox optimization classifier; Sampling (404) a generation of λ samples z1,...,z λ a sampled objective function f ∈ F of the one or more training functions F and an initial mean m (0) of the sampled objective function f ∈ F, where the generation of λ samples z1,...,z λ with a multivariate normal distribution N(m (0) = 0, e (0) C (0) = 1) with initial mean m (0) = 0 and an initial covariance matrix C (0) = 1 in samples x1,...,xλ is shifted and scaled using the equation: xi = m ( t ) + σ ( t ) C ( t ) 1 2 zi , where σ (t) a step size of a number T steps in t = 1,...,T; for the number of T steps in t = 1,...,T, calculating (406) a set of T means m (1) ,...,m (T) by running the meta-scholarly evolutionary strategy black-box optimization classifier on the sampled objective function f ∈ F using the initial mean m (0) ; Calculate (408) a loss function L(f(m 0 ), ..., f(m T )) of the set of T means m (1) ,...,m (T) ; and Updating (410) the one or more initial metalearning parameters Θ of the meta-learned evolutionary strategy black-box optimization classifier in response to a characteristic of the loss function L to obtain an updated meta-learned evolutionary strategy black-box optimization classifier that includes a weighted combination of the generation of λ samples with larger weights for samples with smaller values ​​for the objective function f ∈ F; Sending input signals received from a sensor into the updated meta-scholarly evolutionary strategy black-box optimization classifier to obtain output signals designed to characterize a classification of the input signals; and Sending an actuator control command to an actuator (14) of the computer-controlled machine in response to the output signals; and Actuating the computer-controlled machine in response to the actuator control command.

This improves the accuracy and speed of solving large-scale combinatorial optimization problems by dividing them into subproblems. [Solution] The information processing device 100 for processing combinatorial optimization problems includes: a graph creation unit 112 that creates one or more subgraphs from a main graph; a mathematical optimization unit 115 that solves the combinatorial optimization problem for each subgraph using a mathematical optimization solver; a machine learning unit 117 that trains each subGNN so that the output of the subGNN corresponding to each subgraph is close to the solution of the mathematical optimization solver; a feature vector assignment unit 118 that assigns the feature vectors at each vertex of the subGNN obtained as a result of training to the corresponding vertices of the main GNN as input to the feature vectors of the main GNN corresponding to the graph data of the main graph; and a solution output unit 119 that outputs the solution obtained as a result of training the main GNN by setting a loss function so that the machine learning unit 117 solves the combinatorial optimization problem for the main graph.

The present invention proposes an optimization method for a cosine optimal loss function based on global information, including: S1. Combining the advantages of existing loss functions with some important new attributes and applying L2 weight normalization; S2. Clearly following the two objectives of minimizing intra-class variation and maximizing inter-class variation, relying on a new algorithm to learn the cosine similarity between class centers and class margins, and respectively proposing two lightweight versions of the cosine optimal loss function; S3. Integrating the above two lightweight versions to create a standard version of the cosine optimal loss function. The present invention mainly aims at the problems that existing loss functions do not apply weight and feature normalization or do not clearly follow the objectives of minimizing intra-class variation and maximizing inter-class variation. By using global information as the feedback for face recognition, a cosine optimal loss function based on global information is proposed. Compared with existing loss functions, this loss function is more effective and achieves more advanced performance.

The invention discloses a model loss optimization method and system for an event detection data long tail problem. The method comprises the steps that a basic model is obtained, and the basic model is a BERT-BiLSTM-CRF model; constructing an optimization loss function of the basic model; taking the optimization loss function as a training parameter of the basic model, training the basic model, and obtaining a trained model; and performing event detection on the input data by using the trained model. According to the scheme provided by the invention, the optimization loss function is adopted for model training, so that the performance of the model on a long-tail data set can be remarkably improved, and the effectiveness of the model in processing a data imbalance problem is displayed.

This application discloses a retrieval model training method, a retrieval-enhanced generation-based Bert-Hogg-Dubbs syndrome (BHD) identification method and system, relating to the field of rare disease identification. The training method includes acquiring positive and negative sample pairs; inputting the positive and negative sample pairs into an initial retrieval model; calculating the loss function of the initial retrieval model; and dynamically adjusting the angle margin of the loss function in real time according to a metric variance adaptive mechanism. The initial retrieval model is then optimized based on the loss function calculation results. This application forcibly expands the angle interval between BHD and non-BHD by using the angle margin of the loss function, and uses a metric variance adaptive mechanism to dynamically adjust the angle margin based on the statistical variance of the cosine similarity among all positive sample pairs in the current training batch. This solves the problem of weak image differences and blurred category decision boundaries in DCLDs caused by the highly similar imaging features of various rare diseases, thus improving the recognition accuracy of large models for query information.

The application discloses a multi-modal model object hallucination elimination method based on sharpness perception and target-oriented disturbance. In view of the hallucination suppression failure and index sharp rebound problem of the existing machine forgetting technology after parameter fine-tuning, the application firstly automatically constructs negative, positive and general sentence data sets based on alignment scores; then a target-oriented min-max optimization model is established, and the sensitive direction of the model on the loss function surface is locked by simulating the parameter disturbance in the worst case; finally, a sharpness perception parameter updating mechanism is used to force the model to converge to the flat extreme value region of the loss space. The application solves the problem that the hallucination rate of the model significantly increases when the model faces parameter disturbance or incremental training interference, realizes deep robust elimination of hallucination, and effectively maintains the general utility of the model on the regular task.

The application discloses a student mathematical ability evaluation method based on a time series regression and an incremental learning model, relates to the technical field of mathematical ability evaluation, and comprises the following steps: S1, establishing a mathematical question bank and performing ability dimension division, and recording the examination proportion of the ability dimension; S2, setting a dynamic data screening mechanism of a sliding window; S3, collecting student answering sequence data; S4, constructing a mathematical ability evaluation regression model based on the dynamic data screening mechanism of the sliding window and a time decay weight; S5, constructing a loss function of the mathematical ability evaluation regression model, and searching for the mathematical ability evaluation regression model parameters when the loss function reaches a minimum value by adopting a Bayesian optimization algorithm; and S6, performing real-time dynamic evaluation and diagnostic evaluation on the mathematical ability of students.The application has the characteristics of small calculation amount, low complexity, real-time incremental updating, strong interpretability and personalized analysis of learning paths, and can be applied to mobile terminal deployment under resource-limited conditions.

A data model modeling method based on mathematical data analysis operation processing comprises the steps that (a) dynamic feature screening is conducted on original data, feature importance is calculated based on information entropy and a covariance matrix, redundant features are removed by setting a dynamic threshold value, and the feature weight distribution proportion is adjusted in real time according to data distribution changes; (b) performing tensor decomposition dimension reduction on the screened high-dimensional data: decomposing three-dimensional or more tensors into a product of a low-rank core tensor and a factor matrix by adopting a CP decomposition or Tucker decomposition method, and extracting potential correlation features; (c) constructing a multi-objective optimization model: combining a least square loss function with an L1 / L2 regularization item, and adjusting model parameters in real time through a dynamic feedback mechanism which comprises an error back propagation algorithm and a self-adaptive learning rate strategy; and (d) adjusting and optimizing the hyper-parameters based on a Bayesian optimization algorithm, inspecting and evaluating the distribution consistency of the model by using Kolmogorov-Smirnov, and dynamically adjusting a training strategy according to an inspection result.

The invention discloses an electricity marketing language model reasoning optimization method and system based on chain thinking. The optimization method provided by the invention comprises the following steps: encoding initial information of power marketing multi-modal input by using a head module to generate an initial state; iteratively calculating and gradually optimizing the initial state through a recursion module to obtain a potential state, participating in a generation process of soft target distribution by the recursion module in each iteration, and supervising, training and reasoning the potential state in combination with a teacher model; meanwhile, corresponding soft target distribution is generated through a teacher model to serve as a reference standard, selection of the teacher model in each iteration stage and the generation quality of the soft target distribution are optimized by adopting a suitable distillation loss function, and adaptation of a dynamic supervision signal is achieved; and decoding the final potential state by using a tail module to generate prediction information. According to the invention, the reasoning capability and generalization performance of the power marketing language model in a complex power marketing business scene are enhanced.

The present application relates to a kind of knowledge distillation method based on inference step deconstruction and differentiating supervision, belong to artificial intelligence field.The structured thinking chain generated by acquiring teacher model is separated according to line, each inference step is deconstructed into independent unit;Each step is type labeled, according to the five-level classification system of basic calculation, basic fact, operation execution, logical reasoning, strategy planning, differentiating weight is distributed, and weight superposition is used to composite step;Weighted loss function is constructed, step weight is introduced into cross-entropy loss, and student model is distilled training.The present application focuses on key inference link in the learning process by step-level type perception and differentiating supervision, overcomes the problem of detail loss and global understanding damage caused by flat sequence supervision in traditional distillation.Experimental results show that, on mathematical reasoning task, compared with equal-weight step distillation method, accuracy is improved by 4.6 percentage points, and efficient migration of large model reasoning ability to lightweight model is realized.

The invention discloses an optimization method for solving a mixed integer linear programming problem, and the method comprises the steps: employing a bipartite graph structure composed of variable nodes and constraint nodes for the modeling of the MILP problem, and the bipartite graph structure comprises variable node features, constraint node features and edge features; variables of the bipartite graph structure are divided into stable variables and unstable variables, a corresponding total loss function is determined, and the total loss function is determined based on a cross entropy loss function and a comparison loss function; carrying out label learning on the stable variables by adopting a cross entropy loss function, and carrying out comparative learning on the unstable variables by adopting a comparative loss function; based on the total loss function, training learning of the corresponding relation of the MILP problem and the solution is carried out to obtain a corresponding prediction model, and based on the prediction model, the MILP problem is solved. According to the method, prediction precision and solution feasibility can be considered in the MILP problem solving process, and good stability and practicability are shown in various types of actual problems.

Systems and methods are disclosed herein for training a model with a learned loss function. In an example system, a first trained neural network is generated based on application of a first loss function, such as a predefined loss function. A set of values is extracted from one or more of the layers of the neural network model, such as the weights of one of the layers. A separate machine learning model is trained using the set of values and a set of labels (e.g., ground truth annotations for a set of data). The machine learning model outputs a symbolic equation based on the training. The symbolic equation is applied to the first trained neural network to generate a second trained neural network. In this manner, a learned loss function can be generated and used to train a neural network, resulting in improved performance of the neural network.

The invention relates to the technical field of computer-aided solution of physical fields or mathematical equations, and discloses a physical scene multi-region cooperative computing method based on an adaptive guaranteed structure. The method comprises the following steps: firstly, dividing a global solution domain into a plurality of mutually connected and partially overlapped sub-domains through domain decomposition, and configuring an independent physical information neural network model for each sub-domain; then circularly executing the following steps: performing multi-dimensional feature extraction in each sub-domain based on the composite feature index; constructing a probability function according to the characteristic indexes, and implementing adaptive sampling to dynamically update a training set; after each round of training is finished, dynamically optimizing the weight of the loss function according to the change trend of different loss items, and adding a physical structure retention constraint item into the total loss function; and circularly executing until a convergence condition is met, and outputting a physical field numerical solution. According to the method, precise capture of the local high-gradient region of the physical field is realized, and the stability and physical conservation of the model are ensured while the calculation precision and efficiency are improved.

The invention belongs to the technical field of strategy search, and relates to a strategy search method and device for multi-participant resource allocation, equipment and a medium. The method comprises the following steps: acquiring a multi-participant resource allocation scene and modeling a Markov model to obtain an expected function value vector of a state; constructing approximate Nash equilibrium to serve as a constraint condition of an expected function value vector of the state; establishing an updating rule of the strategy in a time step, and establishing a utility function of a participant in the strategy to obtain an iteration mode of the strategy; an iteration mode of the strategy is simplified and solved, and an equilibrium solution is obtained; according to the equilibrium solution, calculating a target value function of each participant, and calculating a response of approximate Nash equilibrium; obtaining a state value function by combining the expected function value vector of the state; and taking minimization of the loss function as a target, carrying out iterative search on the strategy until stopping, and outputting the current strategy as an optimal solution of the Markov model. According to the invention, the strategy can be accurately and quickly searched.

The embodiment of the invention provides a training method and a reasoning method of a stream matching generation model and a related device, which are used for improving the efficiency of a stream matching generation model training process. The method provided by the embodiment of the invention comprises the following steps: acquiring noise, a moment t, a first modal object acquired from the noise and environment characteristics of the first modal object; inputting the noise, the moment t, the first modal object and the environmental characteristics into an initialized flow matching generation model to obtain a predicted velocity field vector of a conditional probability path at a (t + 1) moment output by the initialized flow matching generation model; using a preset loss function to calculate loss between the predicted velocity field vector and the real velocity field vector, the preset loss function including at least one of a first loss function and a second loss function, and a third loss function; and training the initialized stream matching generation model by using a loss and back propagation algorithm until the stream matching generation model converges to obtain a trained stream matching generation model.

The present invention discloses an autonomous driving decision-making method based on an adaptive discriminator. By restricting the volume of the information entropy flowing into the discriminator, the training difficulty of the discriminator is increased. At the same time, when the volume of the information entropy flowing into the discriminator is too small, the information flow restriction will be gradually weakened, so that the information obtained by the discriminator always remains at a reasonable level. To achieve the purpose of dynamic adjustment, the present invention adopts a method of threshold comparison, and the volume of the information entropy flowing in fluctuates near a certain threshold, and the threshold is selected based on statistics. When the information flowing into the discriminator is greater than the information threshold, the loss function will increase, and the volume of the information passing through will be reduced when updating the network; while when the information flowing into the discriminator is less than the threshold, this loss does not work, and the discriminator will automatically increase the volume of the information passing through in order to more accurately judge the data source. In this way, the purpose of dynamic adjustment can be achieved, and the problem of unbalanced game between the generator and the discriminator is solved.

The invention discloses a convexity self-learning size gear optimization method and system, and belongs to the technical field of metal calendaring, and the method comprises the steps: collecting actual production data in a preset production period of a production site, and integrating data required by gear optimization; determining an effective target size range of the plate strip, and dividing the effective target size range into a plurality of intervals; constructing a loss function for evaluating the reasonability of size gear division; and taking the gear number and the interval number contained in each gear as optimization objects, and based on the loss function, solving an optimal solution of the optimization objects by utilizing a swarm intelligence algorithm to realize convexity self-learning size gear optimization. By adopting the convexity self-learning size gear optimization method and system provided by the invention, the scientific reliability of optimization work can be improved, meanwhile, the optimization efficiency can be improved, the performance of a self-learning scheme in the aspects of precision and stability can be enhanced, and finally, the plate shape control effect can be effectively improved.

The present application discloses a method and apparatus for determining a search rearrangement model. An initial scoring and ranking model is used to perform initial ranking and scoring on multiple search result entries of a target search term to obtain their respective initial ranking scores. A scoring and evaluation model is used to evaluate the initial ranking scores according to the expected ranking and determine their respective reward scores. Further, a loss function of the multiple search result entries is determined based on the initial ranking scores and the reward scores, and the initial scoring and ranking model is trained for the ranking model according to the loss function to obtain a target scoring and ranking model for performing search rearrangement on the multiple search result entries. Since the reward scores are determined based on the expected ranking, training the initial scoring and ranking model for the ranking model using the loss function determined based on the initial ranking scores and the reward scores enables the initial scoring and ranking model to be optimized in the direction of outputting the expected ranking, obtaining the target scoring and ranking model and improving the accuracy of the ranking result.

The application belongs to the technical field of numerical control machine tools, and discloses a mathematical model parameter identification method for a machine tool feeding system based on gradient optimization. The method comprises the following steps: S1, establishing a mathematical model for the machine tool feeding system; S2, collecting actual operation data of the machine tool; setting initial parameters to be identified; constructing an update model for the parameters to be identified; S3, inputting a preset instruction position signal and the current parameters to be identified into the update model for the parameters to be identified to update the parameters to be identified, simulating and calculating a loss function by using the updated identification parameters, and judging the relationship between the current loss function and an optimal loss function; if the current loss function is smaller than the optimal loss function, the value of the current parameters to be identified is kept, otherwise, the number of times that the loss function increases is increased; S4, updating the number of iterations, and judging whether the current number of iterations reaches a preset maximum number of iterations; if yes, the current parameters to be identified are output; otherwise, the step S3 is returned. By the application, the identification efficiency of parameters with low sensitivity to the global loss function is improved.

The invention discloses a student mathematical ability assessment method based on a time sequence regression and incremental learning model, and relates to the technical field of mathematical ability assessment, and the method comprises the steps: S1, building a mathematical question bank, carrying out the ability dimension division, and recording the investigation proportion of the ability dimension; s2, setting a dynamic data screening mechanism of the sliding window; s3, collecting student answer sequence data; s4, constructing a mathematical ability assessment regression model based on a dynamic data screening mechanism of a sliding window and a time attenuation weight; s5, constructing a loss function of the mathematical ability assessment regression model, and searching by adopting a Bayesian optimization algorithm to obtain mathematical ability assessment regression model parameters when the loss function obtains a minimum value; and S6, carrying out real-time dynamic evaluation and diagnostic evaluation on the mathematical ability of the student. The method has the advantages of being small in calculation amount, low in complexity, capable of achieving real-time incremental updating, high in interpretability and capable of achieving personalized analysis of learning paths, and can adapt to mobile terminal application deployment under the condition that resources are limited.