218 results about "Information bottleneck method" patented technology

The invention provides a structured data modeling analysis method based on Transform, and relates to the technical field of data analysis, and the method comprises the steps: carrying out the piecewise linear transformation and adaptive quantum coding of numeric features and category features through a double-flow feature encoder, and carrying out the fusion through a gating mechanism to obtain fusion features; inputting the enhanced training sample into a feature extraction network comprising a hierarchical attention module and a self-calibration module, and extracting global feature representation through a feature affinity graph and a causal attention mechanism; and constructing an information bottleneck feature filter to select a key feature subset, performing prediction and reconstruction by adopting a double-branch network, and analyzing the feature contribution degree by using a structured gradient method. According to the method, heterogeneous features can be effectively processed, the model performance is improved, and meanwhile an interpretable feature importance evaluation mechanism is provided.

The invention relates to an endoscope image reflection restoration method based on detection network and filtering fusion, and belongs to the technical field of medical image computer processing. The method aims at improving detection and removal of specular reflection in an endoscope image, a variant of TransUnet is adopted in the detection stage, and U-Net and Transform architectures are combined; the method comprises Atrous spatial pyramid pooling (ASPP), information bottleneck (IB) and a convolutional block attention module (CBAM). The enhancement functions improve the identifiability of specular highlight and solve the problem of weak generalization in endoscope data concentration. In the removal stage, the invention designs an enhanced median filtering module for removing specular reflection. The module first applies Gaussian blur to the repaired region and then calculates color information from the non-reflective region. According to the method, mirror reflection is effectively eliminated from the endoscope image, clearer and more accurate visual information is provided for clinicians, and improvement of diagnosis precision is facilitated.

The invention provides an interpretable node classification prediction method based on adversarial causal graph learning. The method comprises the steps that a constructed prediction model comprises a redundancy filtering module and an adversarial causal graph learning module; a redundancy filtering module and an adversarial causal graph learning module realize a graph information bottleneck mechanism; the redundancy filtering module adopts a two-layer graph attention network GAT structure to carry out information aggregation, and node embedding is obtained; the confrontation causal graph learning module adopts a learnable sub-graph sampler based on an attention mechanism to generate a causal interpretation sub-graph for node embedding, performs gradient disturbance optimization on interpretation sub-graph embedding based on a PGD confrontation training strategy of a causal enhancement mechanism, generates confrontation embedding, and obtains final disturbance interpretation sub-graph embedding through multiple rounds of disturbance iteration; performing end-to-end prediction model training through multi-target loss joint optimization; and after training is completed, embedding of the nodes is input into a classifier, and a prediction result is output. According to the method, the structural transparency and interpretability of the model are remarkably improved.

The invention provides a frequency difference compressor based on precision perception, a gradient compression method, equipment and a medium, which are used for carrying out data compression and transmission between a server and a client so as to reduce communication overhead in personalized federated learning, and relates to the technical field of data compression. The frequency difference compressor comprises an information bottleneck rarefaction unit, a frequency domain compression unit, a dynamic quantization unit and a differential coding unit. Non-key gradient redundant components of the original gradient data are removed through an information bottleneck rarefaction unit to generate sparse gradient data; generating a metadata packet containing the first N high-energy frequency domain coefficients and the positions and the number of the first N high-energy frequency domain coefficients through a frequency domain compression unit; performing adaptive bit width mapping on the high-precision floating point gradient data into low-order integer representation through a dynamic quantization unit to generate dynamic quantization gradient data; and the differential gradient is transmitted to the client through the differential coding unit, so that data compression and transmission are completed. The method solves the problems that the communication overhead is large and gradient information cannot be reserved as far as possible in gradient transmission.

The invention relates to the technical field of data processing, and discloses a multi-modal relation extraction method based on large model generation and knowledge graph integration, which comprises the following steps of: firstly, generating description for an image by using a large language model, constructing an image graph, analyzing a text, constructing a text graph, linking a knowledge graph based on a tagged entity, and extracting a multi-modal relation between the tagged entity and the knowledge graph; and constructing a knowledge graph sub-graph. And then, taking the labeled entity as an anchor point, splicing the three through similarity calculation to form a unified combined graph, and extracting and fusing multi-modal features by utilizing a graph information bottleneck technology and a GCN optimization graph structure, so that the accuracy and the processing efficiency of relation extraction are improved. And through multi-modal data fusion, the accuracy and the processing speed of relation extraction are remarkably improved. A graph structure is optimized by using a graph information bottleneck technology and a graph convolutional network, and redundant information is eliminated, so that semantic features in multi-modal data are effectively extracted and fused.

The invention discloses a financial data intelligent auditing analysis method based on deep learning, and the method comprises the following steps: S1, collecting enterprise financial data, constructing a dynamic memory adaptive attention network, and generating weighted transaction data; s2, calculating a weight factor of each transaction, and mapping the weighted transaction data to an attention weight distribution space; s3, screening transaction features by using variational information bottlenecks, and extracting key transaction features; s4, optimizing hyper-parameters of the dynamic memory adaptive attention network by using a whale optimization algorithm according to the key transaction characteristics; s5, processing the newly input financial transaction data, and judging an abnormal transaction based on a preset threshold value; and S6, generating an audit analysis result according to the abnormal transaction, and performing comparative analysis in combination with a historical audit record. According to the method, deep learning, machine learning, a statistical method and an intelligent optimization algorithm technology are combined, and financial data intelligent auditing analysis based on deep learning is realized.

The embodiment of the invention discloses a discrete voice coding method, electronic equipment and a storage medium, and the method comprises the steps: constructing a voice input and frequency spectrum output VAE, enabling the input voice to have speaker tone disturbance, and enabling the VAE structure to be used for multi-task learning; vector quantization is carried out on the VAE, and a VQ-VAE is initialized, so that a quantization layer is added to continue to reduce an information bottleneck; and additionally training a vocoder, and carrying out waveform reconstruction by starting from the code obtained in the VQ-VAE.

The invention discloses a multi-modal multi-scale retrieval enhancement generation method, system and device applied to external knowledge questions and answers and a medium. The method comprises question perception, multi-modal multi-scale query fusion coding, dense recall and answer generation. Analyzing a key query phrase from the question through a fine-tuned instruction language model, and accurately positioning a region of interest corresponding to the phrase in an image by using an open set visual positioning model; multi-source information is compressed and distilled into an optimal query vector through a deep fusion network integrating multi-head self-attention and an information bottleneck theory; executing a maximum inner product search to recall related knowledge; guiding the large language model to synthesize all information to generate a final answer; the system, the equipment and the medium directly perform feature fusion in the vector space based on the method, so that challenges such as information loss and cascading errors caused by a traditional normal form can be effectively dealt with, high correlation and high accuracy of retrieval knowledge are ensured, and accurate and reliable image-text questions and answers are realized.

The invention relates to the technical field of network communication, and discloses a network load balancing evaluation method based on a deep learning model, which comprises the following steps: S1, data preprocessing: collecting flow data, and carrying out normalization, noise reduction and enhancement processing; s2, manifold modeling: dimension reduction is performed on high-dimensional flow data, and a local structure is reserved; s3, feature extraction: extracting optimized low-dimensional features, and reducing redundancy; s4, performance evaluation: comprehensively evaluating throughput, delay and balance; s5, anomaly detection: detecting abnormal traffic and outputting a result; s6, feedback optimization: dynamically adjusting a load strategy, and improving the performance. Through deep learning, variational information bottleneck and manifold learning, accurate modeling and optimization of dynamic network traffic features are realized, the extracted features accurately reflect the traffic change trend, the adaptive capacity of the model to sudden and abnormal traffic is enhanced, performance reduction caused by feature distortion in a traditional method is effectively avoided, and the method has a good application prospect. And reliable support is provided for a load balancing strategy.

The invention belongs to the technical field of graph classification, discloses a graph classification method based on subgraph integration and position sensing, and relates to a graph classification method SIPA combining substructure embedding and node position sensing. The SIPA firstly extracts sub-graphs through two different strategies so as to capture multi-sample sub-structures in the graphs, the structural features of the sub-structures are coded by adopting a graph convolutional network, and information of different sub-graphs is effectively fused through an attention mechanism. Then, anchor nodes are introduced to calculate relative position information of nodes, and the information is embedded into node representation to better capture global position features. And finally, a graph information bottleneck mechanism is used for optimizing node representation and removing redundant information irrelevant to a classification task. The method not only effectively learns the local structure information, but also enhances the perception capability of the relative position information of the nodes. Experimental results show that SIPA is superior to an existing baseline model in five data sets, and the superiority of SIPA in a graph classification task is verified.

The invention discloses a multi-modal cancer survival prediction method based on a potential differentiation variational auto-encoder, and the method comprises the following steps: carrying out the tissue region segmentation of an input full-view digital slice, extracting the pathological features, and carrying out the grouping extraction of the grouping features of input genome data according to the function category; generating compressed pathological feature potential distribution through an information bottleneck theory and an attention mechanism; potential distribution of genome data is learned through global posteriori, specific potential variables are generated through a functional differentiation network, and missing genome features are reconstructed; integrating pathology and genome posteriori based on an expert product technology, and introducing alignment loss to constrain consistency of posteriori distribution; and screening survival related features through a co-attention mechanism, and outputting a survival probability and risk layering result. By adopting the multi-modal cancer survival prediction method based on the potential differentiation variational auto-encoder, the problem of calculation redundancy is solved, multi-modal joint distribution estimation under missing data is realized, and the clinical applicability is improved.

The invention discloses a concept bottleneck model construction method based on variational information bottleneck guidance, and the method comprises the steps: generating a basic concept pool directly related to the content of an input image through a visual language model, generating a descriptive supplementary concept pool through a large language model, and covering the diversified attribute features of a target category; on the basis of a variational information bottleneck principle, concept importance scores are calculated through a cross-modal aligned image-text embedding space, and high-relevance concepts are screened; the basic concept classifier and the supplementary concept classifier form a double-branch concept bottleneck network, and prediction results of the basic concept classifier and the supplementary concept classifier are fused through a classification fusion device; and an interpretability efficiency index optimization model is adopted to balance classification accuracy and concept interpretation efficiency. According to the method, deep alignment is carried out on image text embedding subjected to CLIP coding by utilizing the variational information bottleneck, and the classification accuracy is further improved by utilizing the supplementary concept bottleneck.

The invention discloses a source load risk management and control method for cooperative operation of multiple types of adjusting power supplies and new energy, and the method comprises the steps: depicting a prediction error tail dependency relationship through employing an extreme value theory and a Copula function, constructing a distribution robust optimization model in combination with a Wasserstein distance, and obtaining the standby capacity sharing, triggering threshold and risk index of the multiple types of adjusting power supplies; performing conformal prediction based on the prediction residual error to generate a dynamic confidence interval, and mapping the dynamic confidence interval into a pipeline radius of model prediction control; executing rolling MPC containing information bottleneck regularization under the constraint of the reserve capacity and the pipeline, and generating a robust scheduling strategy; and constructing a polyhedral feasible region model of the flexible load group according to the scheduling strategy and the risk index, and performing scaling to obtain a group control action. And the new energy consumption level and the system operation safety are obviously improved.

The invention discloses a false information detection method and device based on a cross-social media communication network. The method comprises the following steps: taking news data as an initial key node of a communication structure in a network graph; a learnable node selector is set for the network graph, a multi-expert model framework is introduced, each expert model obtains a key propagation sub-graph based on the importance weight of nodes output by the node selector, the nodes of the key propagation sub-graph are aggregated by adopting an aggregation network, and the key propagation sub-graph is obtained. Calculating mutual information loss of the key propagation sub-graphs based on a graph information bottleneck theory, introducing a gating network to output a distribution weight for each expert model, aggregating node aggregation results, and performing false information detection classification; according to the method, classification loss is constructed, meanwhile, comprehensive loss and diversity loss for a multi-expert model framework are introduced, and a node selector, a gating network and an aggregation network are jointly optimized in combination with mutual information loss, so that the accuracy and effectiveness of false information detection are improved.

The invention discloses a data analysis and prediction method and system based on multi-modal data fusion, and the method comprises the steps: collecting multi-modal original data, and carrying out the preprocessing of the multi-modal original data, and generating normalized data; setting sliding window parameters, and performing sliding fragmentation on each modal data to obtain sliding window fragment data; extracting modal features, and fusing the modal features into sliding window level fusion feature representation; inputting the improved variational information bottleneck model, and performing feature compression and reconstruction; all fusion features are aggregated, a prediction result is output through modeling reasoning, and the model is optimized. According to the method, the improved sliding window algorithm and the variational information bottleneck model are fused, so that efficient analysis and accurate prediction of multi-modal data are realized.

The invention relates to the technical field of knowledge maps, in particular to a few-sample knowledge map completion method and system fusing relation perception information bottleneck. The method comprises the following steps: S1, preprocessing an input triple; s2, building a global aggregation module, and updating entity embedding; s3, establishing a relationship aggregation module, and updating relationship embedding; s4, establishing a relationship-based information bottleneck module, filtering noise irrelevant to tasks, and meanwhile, retaining relationship-specific information; s5, building an EM attention pooling module, adaptively aggregating multi-path semantic representation, and highlighting the correlation between the entity and the relationship; and S6, establishing a score calculation module, calculating a triple score and outputting the triple score. The invention provides a few-sample knowledge graph completion method and a few-sample knowledge graph completion system fusing relation perception information bottleneck, which are used for solving the problems of insufficient relation and entity representation coupling, high redundant information interference and difficulty in modeling due to high-order relation dependence in a knowledge graph completion task, and realizing efficient inference of potential relation facts.

The invention relates to the technical field of intelligent decision making, can be applied to business system platforms of financial science and technology, medical health and the like, and discloses a behavior cloning model training method, device, equipment and medium, and the method comprises the steps: obtaining multi-modal input, carrying out the feature extraction and splicing of the multi-modal input, and obtaining an input representation; utilizing a preset decoder to extract a potential representation of the input representation, and utilizing a preset strategy head to decode the potential representation into action data; calculating a potential representation mutual information loss function value by using an information bottleneck principle, and calculating a mean square error loss value of the action data and preset real action data; iteratively updating parameters of a preset decoder and a preset strategy head according to the mutual information loss function value and the mean square error loss value to obtain an updated model; detecting whether a joint loss function value in the updating model is smaller than a preset threshold value or not in real time; and when the joint loss function value is smaller than a preset threshold value, stopping parameter iteration updating to obtain an optimization model.

The invention discloses a single-classification industrial control system anomaly detection method based on double-view information bottleneck fusion, which belongs to the technical field of industrial control system anomaly detection and comprises the following steps of: in a training stage, simultaneously constructing a time sequence view and a pseudo image view; respectively extracting characterization through a time dynamic encoder and a pre-trained visual backbone; performing cross-view compression in the variational information bottleneck fusion module and establishing projection branches only depending on sequence representation; a normal subspace is learned around a center vector, an accurate hypersphere is established to describe normal data, and a center distance is used as an abnormal score and a quantile threshold is used to complete discrimination; in the detection stage, online recognition can be performed only by inputting a time sequence view. According to the method, dual-view prior and variational information bottleneck are fused, end-to-end collaborative optimization is carried out on the dual-view prior and the variational information bottleneck and deep support vector data description, an accurate decision boundary can be established under the condition of a small number of samples, and a solution for industrial control system anomaly detection under the condition that the samples are limited is provided.

A robust multimedia recommendation method based on information bottleneck, including: a user representation matrix and an item representation matrix are learned based on a deep graph neural model; mutual information between multimedia content and representation information of the multimedia content is minimized based on an information bottleneck theory to compute a first loss function; a user-item interaction matrix is reconstructed based on the user representation matrix and the item representation matrix to compute a second loss function; and the first loss function and the second loss function are combined to perform multi-task learning to update parameters of the deep graph neural model until the deep graph neural model converges. A robust multimedia recommendation device and a robust multimedia recommendation medium are further provided.

The invention provides a service network function node identification method based on subgraph information bottleneck, and belongs to the technical field of networks. The method comprises the following steps: acquiring a topological graph of a to-be-tested service network, and acquiring a feature matrix and an adjacent matrix of the topological graph; the feature matrix and the adjacency matrix are input into a feature coding model, node features of the service network to be tested are obtained through the feature coding model according to the feature matrix and the adjacency matrix, and the feature coding model is obtained after training of an optimization function combining multi-order subgraph information bottleneck and a global topology constraint function; and obtaining a node identification result of the to-be-tested service network according to the node characteristics. Therefore, network node features with multi-scale constraint information in a hidden space are obtained in a data-driven form by combining the multi-level node semantic information and the multi-scale topological information of the sub-graph from the perspective of an information theory, and more accurate functional node features are captured, so that the accuracy of service network node identification is greatly improved.

The invention provides a metallurgical furnace working condition intelligent identification method fusing multi-modal data. A double-branch multi-level residual structure feature encoder is designed, and metallurgical furnace process variable data features and image data features are fully extracted. Aggregation and separation among modal features are carried out through a comparative learning method, feature semantic alignment is realized, and feature distribution is optimized. Under the constraint of orthogonal loss, a feature decomposer is utilized to effectively separate out inter-modal correlation features and modal private features, and an information bottleneck theory is utilized to promote redundancy removal of key correlation features of process variable data and image data. A multi-level and multi-dimensional feature fusion module is constructed, single-level feature interaction fusion and inter-level feature fusion are sequentially realized under the action of bidirectional cross attention, and fusion features rich in information content are obtained. And finally, the information is sent to the classifier, so that intelligent and accurate identification of the metallurgical furnace working condition under multi-modal data input is realized.

The invention relates to an incomplete multi-view multi-label classification method based on task enhancement and missing view completion. The method comprises the steps of obtaining to-be-classified multi-view data; inputting the to-be-classified multi-view data into the missing view completion and multi-label classification model, and outputting a multi-label classification result; wherein the missing view completion and multi-label classification model comprises a task-oriented feature selection module, a missing view recovery module, an adaptive learning fusion module and a multi-label classification module, and the missing view completion and multi-label classification model is obtained based on training of a training set, information bottleneck loss, reconstruction loss and target classification loss. The training set is incomplete multi-view multi-label data. According to the method, a new two-stage framework is provided, acquisition of task related information and complementation of missing views are combined, task related features are extracted in the first stage, and complete multi-view data are obtained in the second stage, so that the accuracy of the classification process is improved.

The invention belongs to the field of data detection, and provides a false news detection method and system based on fact-emotion dual uncertainty, and the method comprises the steps: obtaining a text and an image of each piece of news in a social network; the method comprises the following steps: performing feature extraction on a text and an image to obtain text embedding and image embedding, performing Gaussian reweighting on the text embedding and the image embedding respectively, then performing calculation to generate Gaussian uncertainty representations, and screening the Gaussian uncertainty representations based on a variational information bottleneck strategy to obtain multi-modal uncertainty representations; processing the multi-modal uncertainty representation to generate a fact inconsistent representation, and processing the multi-modal uncertainty representation based on an emotion manipulation graph convolutional network to generate an emotion inconsistent representation; and fusing the fact inconsistent representation and the emotion inconsistent representation to generate fusion features, and performing classification based on the fusion features to obtain a false news detection classification result. According to the method, the limitation of cross-modal complementarity caused by the uncertainty of multi-modal data is relieved.

The invention is applicable to the technical field of cell type annotation, and provides an interpretable single cell annotation method, which comprises the following steps: based on a source cancer data set, performing cell type label prediction on a target cancer data set through a first module of an annotation model to obtain a prediction label of each cell in the target cancer data set, the annotation model is constructed by adopting an information bottleneck-based graph interpretation technology, and based on the health data set and the prediction label, interpretability analysis is performed on the to-be-interpreted cancer data set through a second module of the annotation model to obtain an interpretation result, the to-be-explained cancer data set is composed of the cancer cell gene expression matrix and the prediction label of the target cancer data set, so that the explanatory mechanism is integrated into the model architecture, the prediction accuracy is ensured, the explanatory stability and reliability are improved, the inconsistency caused by dependence on a post explanatory method is avoided, and the prediction accuracy is improved. And the prediction logic of the model can be understood.

The invention discloses a hierarchical network topology estimation method based on an information bottleneck theory, and the method comprises the steps: carrying out the merging of end-to-end traffic time sequences, introducing comparative learning, generating random perturbation for the merged end-to-end traffic time sequences in a time domain and a frequency domain, and carrying out the estimation of the hierarchical network topology. The end-to-end traffic time sequence is comprehensively represented from the perspective of time-frequency consistency analysis through comparative learning, end-to-end traffic time sequence embedding is obtained, and finally, the length of a shared path is measured by adopting the Euclidean distance embedded by the end-to-end traffic time sequence, and the network topology is recovered from bottom to top. According to the method, an information bottleneck theory is adopted, information related to topology estimation is reserved, noise is compressed, end-to-end flow time sequences are combined based on confidence, time sequence data are effectively represented from a time domain and a frequency domain at the same time by adopting comparative learning, features capable of reflecting variation difference and consistency between different time sequence data are extracted, and the time sequence data are effectively represented. And the length of the shared path is better measured, so that the network topology structure is more accurately recovered.

The invention relates to the technical field of data processing, in particular to a large model reasoning optimization method based on context incremental updating, which comprises the following steps: processing a multi-modal data stream through timestamp alignment and a filtering algorithm, extracting features by adopting a shared encoder and a private encoder, and realizing feature decoupling through a depth information bottleneck principle. A dynamic emotion map is constructed by using Gaussian process regression and a random process algorithm, and self-adaptive updating control is realized by combining meta-learning and Bayesian optimization. Incremental state management is realized by adopting a neural Turing machine, reasoning consistency is guaranteed through a generative adversarial network, model parameters are optimized in combination with a digital twin system and reinforcement learning, and a mental health service response is finally generated through a conditional generation model and hierarchical reinforcement learning. According to the method, the problem of asynchronism of multi-modal emotion feature dynamic evolution and context increment updating is effectively solved, accumulated drift of emotion state tracking is eliminated, and the continuity of reasoning logic is guaranteed.

The invention provides a point cloud completion method and system based on a high-dimensional feature field and structured tensor decomposition, and belongs to the field of artificial intelligence. Comprising the following steps: encoding geometric information carried by sparse point clouds through a space geometric encoder, and distributing the geometric information to three mutually orthogonal two-dimensional feature planes and a three-dimensional feature grid to jointly form a high-dimensional feature field in which space local information is reserved; for any query point in the space, combining the space coordinates of the query point and the local features sampled in the high-dimensional feature field as input, driving a decoder based on structured tensor decomposition, and reconstructing the geometric attribute value of the query point; a continuous geometric field function implicitly defines a three-dimensional surface after completion, and point cloud completion is completed by sampling the function and extracting a zero contour surface of the function. The technical problems that when sparse and incomplete point cloud data are processed, due to information bottleneck and lack of geometric priori, the complementation quality is poor, and macrostructures and microscopic details are difficult to consider at the same time are solved.

The invention relates to the technical field of voice signal processing, and discloses a method for realizing personalized singing synthesis model training through multi-modal voice driving, and the method comprises the following steps: obtaining multi-modal input data, including text, reference audio, speaker and emotional features; processing the data to obtain coding features; the inter-modal redundant information is evaluated and suppressed through redundant perception coding; compressing coding features by using an information bottleneck model, and retaining effective information; fusing the compressed features to generate personalized singing features; the input decoding module generates Mel spectrum features; and converting the Mel spectrum into an audio waveform through a vocoder, and outputting the audio waveform. And converting the Mel spectrum into an audio waveform through a vocoder, and outputting the audio waveform. According to the method, multi-modal data can be effectively fused, the individuation and emotion expression ability of the singing sound is improved, redundant information interference is reduced, the quality and efficiency of singing sound synthesis are improved, and finally, high-fidelity individualized singing sound is output.

The invention discloses a forged image detection method, device and equipment. Comprising the steps of collecting images and description texts thereof, and constructing a training data set; extracting image features and text features in the training data set through a CLIP model; constructing constraints based on the image features and the text features, establishing an optimization target by adopting a conditional information bottleneck method, and training a forged image detection model to obtain a trained forged image detection model; inputting a to-be-identified image into the forged image detection model, and outputting a detection value; and under the condition that the detection value is greater than a preset threshold value, determining that the to-be-identified image is a forged image. On the basis of the strong feature expression ability of the pre-training model, the problem of feature redundancy is solved by using a conditional information bottleneck method, the enhancement effect of the text mode on the detection ability of the forged image is effectively utilized, the detection performance of balance and strong generalization ability on different types of forged images is realized, and meanwhile, the detection efficiency is improved. And the detection accuracy of the forged image is improved.

A method for performing robust multimedia recommendation on the basis of an information bottleneck, and a device and a medium. The method comprises: on the basis of a deep graph neural model, learning a user representation matrix and a product representation matrix; on the basis of an information bottleneck theory, minimizing mutual information between multimedia content and representation information of the multimedia content, and calculating a first loss function; reconstructing an interaction matrix on the basis of the user representation matrix and the product representation matrix, and calculating a second loss function; and performing multi-task learning by combining the loss functions, so as to update model parameters until a model converges.