134 results about "Matrix factorisation" patented technology

The invention discloses a traffic flow prediction method based on adaptive dynamic multi-scale space-time hypergraph convolution. The method comprises the following steps: S1, collecting traffic data; s2, forming space-time enhancement data from the traffic data; s3, a multi-scale adaptive causal convolution module extracts multi-scale traffic flow change features; s4, constructing a dynamic hypergraph structure, defining a hypergraph incidence matrix, and generating a self-adaptive hypergraph by adopting an attention enhancement matrix decomposition method; s5, fusing the time features in the S3 and the hypergraph structure in the S4, designing a multi-scale fusion homogeneous convolution module, and realizing fusion of multiple different-scale spatio-temporal features; s6, extracting topological node features through a graph convolutional network and a hypergraph convolutional network by using the multi-scale spatial-temporal features, and performing adaptive weighted fusion through a gating feature fusion unit; s7, performing multi-scale feature integration by a residual feature aggregation module; s8, generating traffic flow prediction results of a plurality of time steps in the future; the method has the advantages of extracting the traffic space-time dependency relationship, improving the prediction precision and generalization ability, and being more suitable for dynamic traffic.

A correlation-aware adaptive codebook compaction system for multi-modal data compression that preserves cross-modal relationships while providing enhanced reconstruction quality. The system analyzes temporal and spatial relationships between different data modalities to generate correlation maps that guide compression decisions. A virtual management layer performs stream characterization and adaptive routing, while a processing pipeline implements primary codebook compression with mismatch handling for novel data blocks. High-entropy data segments receive pre-compression processing before codebook compression. Sequential registration data is processed through matrix factorization and dedicated matrix codebooks. The system continuously monitors data distribution characteristics and automatically retrains codebooks when drift thresholds are exceeded. A neural upsampling subsystem uses correlation information to guide cross-modal enhancement processes through modality-specific networks and attention mechanisms. The unified output includes compressed data streams, correlation maps, synchronization metadata, neural model parameters, and updated codebooks, enabling synchronized reconstruction with preserved cross-modal relationships and enhanced quality through correlation-guided neural upsampling.

The invention relates to the field of environmental monitoring, and particularly discloses a non-negative matrix factorization and adaptive peak recognition fluorescence feature extraction and traceability system, which comprises a spectral data preprocessing module, a spectral data non-negative matrix factorization module, a component number automatic selection module, an adaptive peak recognition module, a feature library construction module and a similarity comparison module. An improved non-negative matrix factorization model is adopted to decompose the three-dimensional fluorescence spectrum matrix of a single sample, and an optimal component number K is automatically determined through multiplicative update rule iterative optimization; the self-adaptive peak identification module carries out selective filtering, accurately extracts the position and intensity of a fluorescence peak through multiple mechanisms, and carries out peak position calibration in a neighborhood; the Hungary algorithm is adopted to carry out characteristic peak matching to calculate the comprehensive similarity between the samples, and rapid and accurate identification of the pollution source is realized. The method has the advantages of high resolution, strong anti-interference capability, low requirement on the number of samples, automation and the like, and is suitable for water quality fingerprint feature extraction of a water sample in a complex environment and real-time source tracing of sewage.

The invention relates to an APT attack detection and machine learning technology, in particular to an APT attack detection method fusing comparative learning and cross-domain recommendation. A traceability graph is constructed based on a data set, and a bipartite graph is constructed according to the traceability graph; generating an r-ego network for all nodes in the bipartite graph; generating positive and negative sample pre-training graph encoders in the source domain, and transferring the pre-trained graph encoders to the target domain; generating initialization embedding in a target domain by using a pre-trained graph encoder; the matrix decomposition model is finely adjusted by using the initialized embedding, and the final embedding of each node in the target domain is obtained by using the finely-adjusted matrix decomposition model; and predicting whether the two nodes interact based on the final embedding. According to the method, the high-order connectivity is formed by using the side information of the system entities to predict the possibility of interaction between the entities. And meanwhile, a cross-domain recommendation method is used, so that the problem of data sparsity of APT attacks is relieved while the recommendation performance on a target domain is improved.

The invention provides an educational resource sequence recommendation method and a related device, and relates to the technical field of resource recommendation. After student learning behavior data, learning resource attribute data and knowledge graph structure information are obtained, a regularization matrix decomposition technology is adopted to carry out potential factorization modeling on a student-resource interaction scoring matrix, and basic preference embedding features of students and resources are extracted. Aiming at diversity and complexity of student learning behaviors, a multi-view feature coding module is designed, learning sequence and short-term interest features are extracted from a behavior sequence view, static attribute features of students and courses are extracted from an attribute information view, and knowledge point pre-correction dependence and association relationship features between courses are extracted from a knowledge structure view. In order to improve the consistency and discrimination of feature representation, on the basis of multi-view fusion features, a comparative learning mechanism is introduced, and the discrimination and migration modeling ability of the model to student interests and preferences is enhanced by constructing a positive and negative sample comparison loss function.

A hybrid recommendation system for generating personalized film recommendations, the system comprising the following: a processing unit for receiving metadata, configured to receive descriptive data related to films, the descriptive data including plot summaries, genre identifiers, cast lists and director names; a text preprocessing module that is communicatively coupled with the metadata ingestion processing unit and is configured to perform tokenization, stopword removal, stemming, and lemmatization on the descriptive data to obtain a processed corpus; a TF-IDF vectorization unit configured to encode the processed corpus into high-dimensional semantic feature vectors by calculating TF-IDF inverse document frequency values ​​over the entire film dataset, with the semantic feature vectors representing the contextual meaning of terms for individual films; a collaborative filter engine comprising a user-element interaction matrix, wherein the engine is configured to compute latent preference signals using one or more techniques selected from the group consisting of cosine similarity, k-nearest neighbor similarity, and matrix factorization; a score fusion controller coupled to both the TF-IDF vectorization unit and the collaborative filter engine, wherein the module is configured to normalize the semantic feature vectors and the collaborative preference scores and dynamically combine them according to an adaptive weighting coefficient, the coefficient being determined as a function of data density, interaction sparsity, and user history length; and a recommendation output module configured to evaluate candidate films for each user based on the combined score and generate a top-N recommendation list.

The invention relates to a disturbance source positioning method based on dynamic mode decomposition, which belongs to the technical field of power system operation and analysis and comprises the following steps of: accurately extracting oscillation mode characteristics of a system by performing matrix decomposition on actually measured data; furthermore, a participation factor analysis model fusing time-space characteristics is constructed, and the spatial distribution characteristics and the time evolution characteristics of the modal are comprehensively considered, so that accurate positioning of the oscillation source is realized. Compared with a traditional method, the method has the advantages of no dependence on a detailed system model, high positioning precision and the like, is realized completely based on measurement data calculation, avoids complex system modeling, and has relatively high practical application value and popularization potential.

The invention relates to a matrix decomposition device and method based on a memristor cross array, which are suitable for efficient hardware implementation of singular value decomposition (SVD), the memristor cross array receives a conductance value mapped by a Grubrum matrix constructed by a to-be-decomposed matrix and a bit line input voltage converted by a bit line column vector, and outputs a corresponding current; converting the corresponding current into a voltage vector; performing normalization processing on the voltage vector to obtain a normalized vector; judging whether convergence occurs or not; performing normalization processing on the steady-state voltage vector to obtain a final output vector; and according to the final output vector, main characteristic values are extracted based on a first normalization circuit, and main singular values and corresponding singular matrixes are calculated. Compared with the prior art, the high parallel computing characteristic of the memristor cross array is utilized, efficient operation and hardware acceleration of matrix decomposition are achieved, the method has the advantages of being low in power consumption, high in speed and good in expansibility, and the method is suitable for application scenes such as artificial intelligence, signal processing and large-scale matrix operation.

The invention discloses an emotion recognition method based on multi-modal signal fusion, and relates to the technical field of emotion recognition, and the method comprises the steps: obtaining an electroencephalogram signal and a peripheral physiological signal to form a multi-modal signal, and carrying out the preprocessing of down-sampling, baseline correction and band-pass filtering on the multi-modal signal; based on the preprocessed signal, extracting a difference entropy feature and a power spectrum density feature; mapping the extracted features into a standardized space grid to generate a feature tensor with a uniform structure; performing adaptive weighting on the mapped feature tensor by using a frequency band fusion attention mechanism, and generating a frequency band weight through global average pooling and a full connection layer; inputting the weighted features into a full connection layer of the parameterized hypermatrix, and performing feature compression and modeling through matrix decomposition and reconstruction; a multi-task learning framework is adopted, classification results of emotion titer and awakening degree are output at the same time based on compressed features, and multi-task collaboration is optimized through a shared feature layer and a dynamic loss weight.

The invention discloses an anonymous vehicle matching method based on depth features, and relates to the technical field of vehicle matching methods. Firstly, a multi-branch network containing different modules and loss functions is built, and global and local features of a vehicle image are extracted at the same time; fusing the multi-branch features by using a tensor rank constraint non-negative matrix factorization model integrated with singular value saliency difference information; in the process, a self-adaptive illumination normalization module is added in front of an input layer, and a feature importance evaluation mechanism is introduced during fusion, so that the matching precision and robustness are improved, and anonymous vehicle matching is completed. According to the method, anonymous vehicles can be accurately matched, the matching precision is improved through multi-branch network and feature fusion, the adaptability to the complex environment is high, illumination and view angle change are avoided, the reasoning speed is high, and the real-time requirement is met. And the system also has good generalization ability, can work stably and reliably in different scenes, and effectively solves the existing technical problems.

The invention relates to the technical field of ecological environment data monitoring, and further relates to a mine greening supervision method based on remote sensing image semantic segmentation. The method comprises the following steps: step 1, based on original ecological indexes of a mine, establishing a six-column time sequence matrix for each mine landscape patch; 2, at each monitoring moment, constraint non-negative matrix factorization is completed on the time sequence matrix through minimum K-L divergence iteration, and the target is to disassemble the time sequence matrix into a product of a potential ecological function module weight matrix and a potential ecological function module index contribution matrix; and 3, carrying out weighted average on the resource-liability balance degree by using the area of each mine landscape patch so as to evaluate the ecological restoration effect of the mine. According to the invention, dynamic, fine and structured monitoring and evaluation of the mine ecological restoration process are realized.

The invention aims to provide a teaching-assisting knowledge graph and a construction method thereof, and relates to the technical field of education data processing. The method comprises the following steps: constructing a teaching aid evaluation matrix according to learning behavior data, teaching aid resource data and learning stage data of a user; decomposing the teaching-assistant evaluation matrix into an educational knowledge mastery degree matrix and an educational knowledge association degree matrix through a non-negative matrix factorization algorithm; and constructing a knowledge graph according to the teaching aid evaluation matrix, the educational knowledge mastery degree matrix and the educational knowledge association degree matrix. According to the knowledge graph construction method, the relationship among the educational knowledge nodes, the learning stage nodes and the teaching-assisted resource nodes is integrated, the influence degrees of different teaching-assisted resources on the educational knowledge nodes in different learning stages of the user can be distinguished by analyzing knowledge mastering and resource use conditions, the teaching-assisted resources can be efficiently screened, and the teaching-assisted resources can be conveniently and rapidly screened. A user is helped to discover weak links in a learning process, and a learning plan and a learning method are optimized.

The invention discloses a method and device for constructing a volatile organic compound emission list, and the method comprises the steps: obtaining observation data based on a preset observation point, and obtaining the concentration data of volatile organic compounds in a boundary layer based on the observation data; constructing a box model, and calculating the discharge flux in the boundary layer based on the box model and the concentration data; matrix decomposition is carried out on the concentration data and the emission flux based on an orthogonal matrix factor model, and a target factor contribution matrix and a target factor spectrum matrix are obtained; and determining an emission source and a contribution ratio thereof based on the target factor contribution matrix and the target factor spectrum matrix, and constructing a volatile organic compound emission list based on the emission flux, the emission source and the contribution ratio thereof. According to the method, the observation data is obtained based on the preset observation point, the concentration data of the VOCs in the boundary layer is obtained, the emission flux in the boundary layer is evaluated through the box model and the orthogonal matrix factor model, the reliability and accuracy of the evaluation result are ensured, and then the volatile organic compound emission list is accurately constructed.

The invention relates to a gradient perturbation optimization method for implicit matrix decomposition based on differential privacy, and belongs to the field of computer recommendation systems and the field of information security. An implicit feedback matrix composed of 0 and 1 is used for representing feedback data of a user to an item, 0 represents negative feedback, and 1 represents positive feedback. Randomly initializing a user implicit factor matrix W and a project implicit factor matrix H; a data set and a target function L (W, H) are constructed, W and H are optimized and solved by adopting a matrix decomposition method based on Bayesian personalized sorting, and a result W is stored. Randomly initializing a noise adding item implicit factor matrix # imgabs0 # and an initial record matrix # imgabs1 # by using the trained W, substituting the W into L (W, H), constructing a target function # imgabs3 # about # imgabs2 #, calculating a gradient # imgabs6 # of # imgabs4 # about # imgabs5 #, cutting the gradient by using a cutting threshold C, and obtaining an optimal privacy budget size lambda t in each round of training by using an overall mse calculation formula, then, the gradient is disturbed by using lambda t and the sensitivity of the gradient to obtain # imgabs7, the # imgabs8 is aggregated to obtain a cumulative gradient, and # imgabs9 is used for updating an item implicit factor matrix by using the cumulative gradient and # imgabs10; # imgabs11 is repeatedly updated to obtain a final item implicit factor matrix # imgabs12, and the final item implicit factor matrix # imgabs12 is distributed to each user; and the user u calculates a predicted value # imgabs13 on the equipment of the user u according to the predicted value, sorts unobserved interaction items in a descending order, and finally selects the first K items from the interaction items to recommend to the user u. The method has good privacy protection and model accuracy.

The invention discloses a deep network video saliency detection method based on RPCA, and aims to solve the problems of high singular value decomposition (SVD) calculation complexity and tedious parameter selection in a traditional RPCA method. By introducing the Schatten-p norm constraint in a matrix decomposition form, the bottleneck of SVD calculation is avoided; designing a piecewise linear threshold function with a learnable parameter set, and realizing adaptive learning of sparse regularization terms; and constructing an end-to-end deep network framework, and optimizing all parameters in a data-driven manner. Experimental results show that the method shows higher detection precision and efficiency in a video saliency detection task, and has a wide application prospect.

The invention discloses an unbalanced classification method for electroencephalogram data in epilepsy detection, and relates to the technical field of data optimization and big data processing. According to the method, firstly, covariance matrixes of majority class samples and minority class samples are calculated, linear transformation is achieved through matrix decomposition, and the minority class samples inherit global distribution characteristics of the majority class samples; and then, in the transformed feature space, sorting samples based on mahalanobis distance and performing partition pairing, selecting sample pairs with large difference to generate convex combination synthesis samples, and ensuring sample diversity and boundary consistency. Experimental results show that on a CHB-MIT electroencephalogram data set, the method effectively solves the problems that a traditional oversampling technology is prone to expanding minority class decision boundaries and generated samples are lack of diversity, and the reliability of epileptic seizure detection is remarkably improved.

The invention discloses a fitness quality evaluation method based on myoelectricity and images, which comprises the following steps: step 1, data acquisition: the acquired data comprises original myoelectricity data with time sequence information and time sequence image data of fitness actions; step 2, preprocessing the collected data; step 3, for the preprocessed myoelectricity data, extracting myoelectricity characteristics through a sliding window by adopting a time domain intermediate frequency value model, and then decomposing a muscle activation degree matrix into a collaborative structure factor matrix and an activation coefficient matrix through a non-negative matrix decomposition algorithm; for the preprocessed time sequence image data, adopting a BlazePose algorithm to extract 33 3D articulation points in the time sequence image data and calculating the Euler angles of the articulation points so as to obtain attitude angle features; and step 4, using a support vector machine to fuse the myoelectricity features and the attitude angle features to carry out action scoring. The method can effectively improve the fitness quality of the user.

The invention relates to the technical field of industrial process soft measurement and quality control, and discloses a paper quality prediction method based on multivariate statistical latent variable fusion and space-time transformation, which comprises the following steps: acquiring space-time sequence data of a multi-source sensor in a papermaking process, constructing a space-time diagram structure reflecting a topological relation of equipment, and preprocessing. Then, multi-view latent variables are extracted through non-negative matrix factorization, independent component analysis and robust principal component analysis, attention fusion is conducted on the latent variables through an LV fusion module, and fusion latent variables are obtained; and inputting the fusion latent variable and original node data into a multi-scale convolution auto-encoder to obtain spatial feature embedding, and inputting the spatial feature embedding and the fusion latent variable into a space-time Transform module together to realize joint modeling of space correlation and time dependence. And finally, outputting a paper quality predicted value through a linear regression module. The method can achieve the accurate prediction of the paper quality under a high-dimensional and multi-noise working condition, and is suitable for online monitoring and modeling updating.

The present invention discloses a deep learning knowledge point recommendation method and device based on learning demand perception, including: converting a plurality of different types of entity interaction data in the user's historical learning behavior into a heterogeneous knowledge network; initializing the features of the user and the features of the knowledge points to obtain the initial embedding expression vectors of the corresponding user and the initial embedding expression vectors of the knowledge points; initializing the meta-path features of the heterogeneous association relationships to obtain the initial feature matrices corresponding to different heterogeneous association relationships; obtaining the static learning demand embedding expression vector and the knowledge point embedding expression vector of the target user; obtaining the dynamic learning demand embedding expression vector of the target user, and obtaining the learning demand embedding expression vector of the target user; obtaining the knowledge point learning times according to the learning demand embedding expression vector of the target user and the knowledge point embedding expression vector, and performing matrix decomposition on the knowledge point learning times to obtain the recommendation result. The present invention can improve the accuracy of the recommendation result.

The invention discloses a multi-scene teaching management method and system based on AI assistance, and relates to the technical field of teaching management. The method comprises the steps of obtaining attribute parameters in a multi-scene teaching data stream, performing preprocessing, constructing a multi-source data stream feature, calculating an adaptive weight according to the attribute parameters and the multi-source data stream feature, and performing weighted fusion to obtain a feature space; obtaining a spatio-temporal feature tensor through matrix decomposition based on the feature space, minimizing a reconstruction error through optimizing an objective function, performing low-rank representation through a regularization method, and performing optimization reconstruction on the spatio-temporal feature tensor; and based on the optimized and reconstructed spatial-temporal feature tensor, strategy optimization is carried out through a deep Q network, an optimal teaching strategy is generated, and multi-scene teaching management is carried out according to the generated optimal teaching strategy. Through intelligent data processing and a deep reinforcement learning algorithm, teaching management is automatically optimized, a personalized teaching strategy is provided, dynamic adjustment is realized, and teaching efficiency and quality are significantly improved.

This application provides a cross-modal semantic alignment method, system, and storage medium. The method extracts multimodal carbon features and performs standardized preprocessing, then uses a projection algorithm to map them to a low-dimensional common semantic space. It combines matrix factorization and association learning models to construct cross-modal semantic associations, and finally generates alignment results through large-scale model fusion inference. This solves the problems of insufficient accuracy and poor semantic coherence in cross-modal semantic alignment of traditional methods.

This invention discloses a multi-sensor fusion mapping method and apparatus for degraded scenarios, comprising: a front-end fusion odometry method: receiving multi-source data and obtaining initial pose through coordinate system alignment; performing point cloud distortion removal through IMU integration and extrinsic parameter transformation to generate a priori LiDAR pose; analyzing point pair contribution vectors based on ICP Hessian matrix decomposition to determine pose degradation; for non-degraded frames, constructing LiDAR point-to-surface residuals and RTK pose residuals, updating the state through ESIKF, and outputting keyframe pose, point cloud, and degradation labels; a back-end factor graph optimization method: filtering non-degraded keyframes through a sliding window, optimizing pose through point cloud beam adjustment; performing secondary verification of RTK pose to remove invalid values; constructing odometry, loop closure, and RTK factors, and fusing and optimizing to obtain a globally consistent high-precision point cloud map. This method enhances robustness through degradation detection and ensures global consistency through factor graph fusion, making it suitable for mapping complex scenarios.

A processing device (400) for performing non-negative matrix factorization on measured X-ray powder diffraction profiles comprises a measurement profile acquisition section (410) for acquiring a plurality of measured profiles, a decomposition section (420) for applying non-negative matrix factorization to the measured profiles and for calculating base profiles; an index calculation section (430) for acquiring the base profiles and for calculating indices based on a non-uniformity of the base profiles; a base profile classification section (440) for classifying the base profiles into a plurality of groups based on the indices; and a base profile correction section (450) for performing a correction based on the indices on at least one of the plurality of groups and for calculating a corrected base profile.

The application discloses an unsupervised hyperspectral image super-resolution method based on a matrix decomposition network and belongs to the technical field of hyperspectral image processing. The application is used for processing a hyperspectral image, generating a simulated low spatial resolution hyperspectral image Y and a high spatial resolution multispectral image Z; first, inputting the generated data pair (Y, Z) into a designed auto-encoder network, training iteration to obtain a point spread function and a spectral response function; for a target high spatial resolution hyperspectral image X, the target high spatial resolution hyperspectral image X can be assumed to be a linear combination of a terminal member matrix A and a corresponding abundance matrix S, that is, X = AS, a spectral and spatial degradation model is combined to model, a deep CP decomposition module is designed to calculate A, A and S are iteratively solved, and finally a fusion result is obtained. The application can obtain more rich spectral and spatial features, obtain a better fusion result, and has good performance in practice.

The invention discloses a remote sensing image sub-region rapid classification method based on dual-scale multi-graph regularization non-negative matrix factorization, and provides a dual-scale basis selection strategy and a multi-graph regularization non-negative matrix factorization model for overcoming the defects of complex scene adaptation, small sample learning and classification speed and accuracy balance in the prior art. Unsupervised subregion classification is realized through the steps of data preprocessing, double-scale seed set division, basis matrix construction, double information graph regularization item construction, model optimization solution and the like. According to the method, the classification number does not need to be predefined, the basis matrix representativeness is enhanced through dual-scale basis selection, and the classification precision and robustness are improved by combining a dual-graph regularization item and utilizing a manifold structure and discrimination information of data at the same time; the efficient optimization solution of the non-negative matrix factorization realizes the rapid classification of the sub-regions, and improves the accuracy and efficiency of the classification of the sub-regions of the remote sensing image.

This invention discloses a water pollution data monitoring method and system based on multi-objective analysis, belonging to the field of water pollution source tracing technology. The method includes: collecting a GIS map of the target watershed and time series data on rainfall, flow, and water quality; hydrologically segmenting the flow series according to the opening and closing status of dams to obtain surface runoff and baseflow components; constructing a two-dimensional water quality observation matrix, setting pulse and delay constraints in conjunction with rainfall and runoff components, and using a non-negative matrix factorization algorithm with ratio constraints for source analysis to obtain a source feature matrix and a source contribution time coefficient matrix; identifying pollution source emission attributes based on the ammonia nitrogen to total phosphorus ratio and the correlation between the source contribution coefficient and rainfall in the source feature matrix, and marking them on the GIS map. This invention integrates dam-controlled hydrological segmentation with matrix factorization based on physicochemical constraints to achieve refined source tracing, improving the accuracy and interpretability of pollution source identification.

The invention discloses a multi-model denoising method and system for a reinforcement learning recommendation system, and the method comprises the steps: obtaining noisy interaction data, and carrying out the prediction of the noisy interaction data through employing a generalized matrix decomposition model and other two matrix decomposition models as prediction models; predicting model parameters are optimized by minimizing KL divergence of fitting real user preference distribution among a plurality of predicting models and maximizing likelihood of observation data under given real user preference conditions; the optimized prediction model serves as a teacher model, and the teacher model is trained through the noise reduction positive sample noise and the noise reduction negative sample noise to obtain a de-noised teacher model; constructing a student model, and defining a target loss function; according to the method, the denoising algorithm is used for training the denoising user model, the denoising user model is used for interacting with an online reinforcement learning strategy, feedback better conforming to the real preference of the user is provided, and the noise robustness and the recommendation performance of the reinforcement learning recommendation method are improved.

In an example, a particular type of deep learning model is used in the global model of the GDMix model: a Factorization Machine. A Factorization Machine combines a Support Vector Machine (SVM) and Matrix Factorizations. It has the advantage of modeling data with huge sparsity well, while maintaining a linear time complexity. A modification may be further made to the Factorization Machine by introducing L2 norm reduction. This acts to divide calculations made by the Factorization Machine into a portion that can be precomputed and a portion that cannot be precomputed. The portion that can be precomputed is then precomputed in an offline manner. As such, when the model is operated in an online manner, the Factorization Machine only needs to compute the portion that cannot be precomputed, reducing the number of operations that need to performed at runtime and greatly improving processing speed over prior machine learned models.

The invention relates to the technical field of power customer service and automatic matching, in particular to an automatic matching method for power customer engineering. Comprising the following steps: screening out candidate service units meeting qualification conditions by using a multi-attribute decision analysis method; based on a content-based recommendation algorithm, extracting features of customer engineering, and recommending electric power engineering service units matched with the features; according to a recommendation algorithm based on matrix decomposition, power customer engineering and power engineering service units are expressed as rows and columns of a two-dimensional matrix respectively, and service units with potential matching are recommended by calculating the incidence relation between matrixes; the recommendation results of the two algorithms are fused, other factors are considered, sorting is carried out, and the final recommendation result is comprehensively generated. According to the design, automatic matching between the customer and the electric power engineering service unit can be realized, the matching success rate is improved, the transaction cost is reduced, and the operation efficiency of the electric power market is improved.

The invention relates to a railway communication interference elimination algorithm, and aims to realize interference elimination and symbol extraction. The algorithm comprises the following steps of: 1, randomly initializing # imgabs0 #; 2, performing tensor decomposition by using a multivariate decomposition interference elimination algorithm; 3, solving a rank-one matrix decomposition factor {h1, a1, s1} through a regular multivariate alternating least square algorithm of blind decomposition; and 4, estimating user information by using a singular value decomposition algorithm. The multivariate decomposition interference elimination algorithm comprises the following steps: step 1, obtaining a signal tensor # imgabs1 # through interference cancellation; step 2, decomposing a rank-one matrix factor {h1, a1, s1} by using a regular multivariate alternating least square algorithm of blind decomposition; step 3, reconstructing a signal # imgabs2 # and calculating a residual error # imgabs3 #; step 4, combining a rank 1 matrix factor of # imgabs4 # and a rank 1 matrix factor of # imgabs5 # to obtain a rank 2 initialization matrix factor H * = [h1, h '] and A * = [a1, a'], and # imgabs6 #; step 5, decomposing the rank matrix factors {Hr, Ar, Sr} by adopting a regular multiple alternating least square algorithm of blind decomposition, and finally reconstructing the signal and extracting information.