69 results about "Similarity relation" patented technology

The invention relates to the technical field of knowledge graph completion, provides an implicit relation perception time sequence knowledge graph completion method based on dynamic embedding and self-attention, and aims to improve the inference and completion capability of missing facts in a time sequence knowledge graph. According to the method, time evolution modeling, a graph neural network and semantic similarity calculation are combined, and dynamic embedding representation fusing static, trend and periodic characteristics is constructed. Explicit structure information is extracted through a multilayer relational graph convolutional network, and meanwhile, an implicit semantic similarity relationship under synchronous and asynchronous time is introduced to construct a sparse semantic graph. Structural information and semantic information are fused through GRU, multi-time step features are aggregated by adopting a time perception self-attention mechanism, and key time information is highlighted. And finally, entity prediction is completed by using a ConvTransE decoder, and the model is optimized through cross entropy loss. According to the method, a static structure and implicit semantics can be modeled at the same time, the time sensitivity is enhanced, and the method is suitable for large-scale dynamic graph completion and has better reasoning ability and generalization performance.

The invention discloses a rule and regulation management method and device and a storage medium, and relates to the technical field of enterprise operation. In the application, actual internal rules and regulations and actual external rules and regulations of an organization are disassembled; performing semantic recognition on a disassembly result through a direct relation extraction agent and a similar or conflict relation extraction agent which are obtained based on a law field fine-tuning large language model, and extracting system relations, including an upgrading relation, a reference relation, an internalization relation, a similar relation and a conflict relation, between rules and regulations; the method comprises the following steps: firstly, extracting a system relationship, and constructing a system blood relationship map according to a disassembling relationship obtained by disassembling and a system relationship obtained by extracting, so as to improve a traditional knowledge map construction method, and managing rules and regulations of an organization on the basis of the system blood relationship map obtained by the improved latest knowledge map construction method.

The invention provides an automatic evidence obtaining method and system for software copyright infringement. The method comprises the following steps: firstly, acquiring a multi-language interface calling sequence based on a target software running process to form unified semantic expression data; meanwhile, recording a sound signal of the mainboard of the electronic equipment by using a high-sensitivity sound sensor, and generating an equipment sound feature; performing joint coding on the semantic data and the sound features through a cross-modal alignment mechanism to generate multi-modal associated data; a memory enhancement unit and a machine learning technology are used to automatically learn a corresponding relation between a multi-language interface and sound features, and a cross-modal mapping relation is established; finally, cross-language plagiarism behaviors are matched based on the mapping relation, and software similarity relation data are automatically output. According to the method, code semantic analysis and hardware voiceprint features are combined, so that the cross-language software plagiarism behavior is automatically and accurately detected.

The invention discloses an evaluation data recommendation method based on a heterogeneous graph neural network, and relates to the technical field of computer application, and the method comprises the following steps: S1, employing historical evaluation data and user information in a system, and based on a user set, a user-data interaction set and an evaluation data set, carrying out the recommendation of evaluation data; constructing a heterogeneous graph neural network fusing the user-user similarity relationship, the user-data interaction relationship and the data-data similarity; s2, score calculation between the user and the data is achieved based on a graph learning device of the optimized sub-graph and a factorization machine, and sorting recommendation is completed; according to the evaluation data recommendation method based on the heterogeneous graph neural network, the BERT and the convolutional neural network are adopted to analyze two evaluation statements into semantic vectors respectively in evaluation text similarity calculation based on BERT, then the similarity is interactively calculated, and compared with evaluation text similarity calculation based on cosine similarity, the evaluation data recommendation efficiency is improved. And similarity calculation is performed from the perspective of evaluating the semantic information of the text, so that the interpretability is higher.

The invention relates to the technical field of regulation and control operation simulation training, in particular to a regulation and control operation simulation training method, system and device based on a collaborative filtering recommendation algorithm and a medium. Collecting regulation and control operation data, and preprocessing the regulation and control operation data; a recommendation algorithm is adopted to analyze the regulation and control operation data and the project features, the similarity relation of the regulation and control tasks is mined, and a recommendation training scheme is generated according to the similarity relation; generating a task recommendation report according to the recommendation scheme, collecting user feedback information and constructing a closed-loop optimization mechanism; and fusing the feedback information into a model incremental learning process, so that the model is iteratively updated on new data. Continuous online learning of the model is realized through a feedback mechanism, and recommendation results are continuously optimized along with changes of tasks and user behaviors.

The embodiment of the application belongs to the field of artificial intelligence, and relates to a data analysis method based on artificial intelligence, comprising the following steps: acquiring voice dialogue data of a user and an agent in a business conversation process; converting the voice dialogue data into text data, and obtaining dialogue text by converting the text data; performing classification processing on the dialogue text according to a preset rule to obtain a theme label corresponding to the dialogue text; constructing a corresponding directed graph based on the dialogue text and the theme label; and performing similarity analysis processing on the directed graph based on a preset similarity analysis model to generate a similarity result between each directed graph. The application also provides a data analysis device based on artificial intelligence, a computer device and a storage medium. In addition, the application also relates to blockchain technology, and the similarity result can be stored in the blockchain. The application analyzes the similarity relationship of the theme path of the dialogue technique based on the use of the similarity analysis model to quickly and accurately obtain the corresponding similarity result.

The application discloses a video search method and device and a computer readable storage medium. The method comprises the following steps: obtaining a video search text, and performing text feature extraction on the video search text to obtain first text features; mapping the first text features to a video feature space corresponding to video information to obtain second text features; performing video feature extraction on each candidate video in a candidate video library to obtain first video features of each candidate video; mapping the first video features to a text feature space corresponding to text information to obtain second video features of each candidate video; and searching for a target candidate video corresponding to the video search text in the candidate video library based on a first similarity relationship between the first text features and the second video features and a second similarity relationship between the first video features and the second text features. The method can greatly improve the accuracy of searching for videos based on text.

The present invention discloses a method for calculating image similarity based on neighborhood similarity relationship, which includes the following steps: dividing a target image into multiple image blocks of the same size; calculating the structural similarity S between the target image and the image in the database based on four neighborhoods; structure ; The structural similarity S structure Compare with the threshold Ts; if S structure ≥Ts, calculate the characteristic similarity S between the target image and the image in the database based on the four neighborhoods feature , calculate the structural similarity S structure and characteristic similarity S feature The weighted average of the target image and the image in the database is obtained to obtain the overall similarity S; if S structure <Ts, the target image has no similarity with the images in the database. The present invention determines similarity through neighborhood relations, is not easily affected by salt and pepper noise and local uneven illumination, and can maximize the stability of the image similarity relationship in local structure.

This application provides a method, apparatus, and computer device for constructing training samples for a recall model. The method is applicable to shopping platforms and includes: obtaining at least one second product displayed after a user triggers a preset behavior for a first product on a preset page of the shopping platform; the first product and any second product have a similarity relationship; obtaining at least one third product in the shopping platform that matches the attribute information of the first product; constructing any product pair based on at least one second product and at least one third product, inputting the product pair and a prompt word into a large language model to obtain the similarity corresponding to the product pair; the prompt word is used to instruct the large language model to determine the similarity corresponding to the product pair from the product name and the ingredient list of the product pair; removing product pairs with similarity less than a second threshold to obtain similar product samples, the similar product samples are used to train the model to obtain a first recall model, and the first recall model is used to recall products with substitution relationships.

The invention provides a knowledge graph construction method and device, equipment, a medium and a product, and relates to the field of data processing, and the method comprises the steps: constructing a financial knowledge base through a financial knowledge platform frame, and enabling the financial knowledge base to provide a multi-modal feature vector and structured relation data corresponding to multi-modal financial data; performing knowledge annotation on the multi-modal feature vector and the structured relation data to obtain annotated data; inputting the annotation data into the domain model, and obtaining summary information of text blocks output by the domain model and semantic similarity relationships of different text blocks; the domain model is related to the financial domain; the text blocks are obtained by slicing the annotation data, and the semantic similarity relationship is determined according to the summary information; performing entity relationship analysis on the multi-granularity hierarchical structure and the semantic similarity relationship of the annotated data to generate maps of different levels; and performing optimization processing on entities corresponding to the maps of different levels to construct the financial knowledge map. And the dependence on manpower and the cost are reduced.

The invention discloses an intention-aware personalized news content recommendation method based on heterogeneous feature collaborative fusion, and belongs to the technical field of news recommendation. Aiming at the problem that current personalized news recommendation mainly depends on semantic interest representation modeling of a user, heterogeneous semantic features of headline contents and abstract contents of news clicked by the user are considered, and a global semantic correlation graph of a similar relationship of the headline contents and a global semantic correlation graph of a similar relationship of the abstract contents are constructed; a graph convolutional network is used for capturing collaborative title semantic features and collaborative abstract semantic features of similar news, and meanwhile heterogeneous type semantic features of the similar news are subjected to collaborative fusion, so that user interest representation is achieved; and finally, calculating an interest score for the intention news, and generating a personalized recommendation list. According to the method, the collaborative characteristics of similar news titles and abstracts related to semantics are fused, modeling representation of user interests is achieved, the accuracy of collaborative recommendation is improved, and the method has application value in the aspect of personalized content recommendation.

The invention relates to the technical field of data analysis, and discloses a comment viewpoint analysis method and device, computer equipment and a storage medium. Incremental comment data is split into incremental short sentences, and the word vector similarity relation between the original short sentences and the incremental short sentences is utilized to perform first clustering; and the core sentences in each first clustering cluster are selected, so that partial clustering of the incremental short sentences is realized, and the processing efficiency is improved. And after the first clustering, labels of the core sentences are labeled by utilizing a large language model, so that the waste of computing resources caused by labeling all data in the early stage is avoided. And then, carrying out secondary clustering by utilizing the labels of the core sentences and the previously stored clustering results of the core sentences, and carrying out clustering and merging comments with complex grammar structures on the basis of sentence vectors. And combining the results of the first clustering and the second clustering to obtain the short sentences under each viewpoint dimension, so that rapid processing of incremental data is realized, consumption of computing resources is reduced, and the computing speed is improved.

The embodiment of the application discloses a data deduplication method and device, a computing device cluster and related products, and belongs to the technical field of big data. In the embodiment of the application, a similarity relationship between a plurality of data in a first data set is generated according to the similarity between the plurality of data; a first deduplicated data is determined according to the similarity relationship, the first deduplicated data being the data with the largest number of similarity relationships with other data in the first data set; and the first deduplicated data is deleted from the first data set. On the one hand, data deduplication is achieved, and on the other hand, compared with a deduplication scheme that only retains the data with the largest number of similarity relationships, the data deduplication scheme provided by the embodiment of the application can also retain a larger number of representative data. Therefore, compared with the deduplication scheme that only retains the data with the largest number of similarity relationships, the method provided by the embodiment of the application not only achieves data deduplication but also achieves data expansion, thereby improving the quality of the deduplicated data set.

The embodiment of the application discloses a vector retrieval method, a method for determining an authorized vector graph, a device and related products, and belongs to the technical field of artificial intelligence. In the embodiment of the application, an authorized vector graph is configured. For an edge connected between two vertices corresponding to two vectors with a similar relationship in the authorized vector graph, the edge corresponds to a weight. In this way, when the vector most similar to a query vector is retrieved through the authorized vector graph, for the edge connected to the retrieval starting point, part of the edges can be filtered through the weight corresponding to the edge to determine the next retrieval starting point. Thus, it is not necessary to calculate the distance between the vectors indicated by all neighbor vertices of the retrieval starting point and the query vector, thereby saving the calculation amount in the vector retrieval process. Accordingly, it is also not necessary to access the vectors indicated by all neighbor vertices of the retrieval starting point from a storage system, and thus the number of times of accessing the stored vectors in the storage system in the vector retrieval process can be reduced.

A low-quality multi-view news data anchor graph regular division method based on diffusion completion belongs to the field of data division in low-quality multi-view news data, and comprises the following steps: firstly, inputting low-quality news data of each view and a corresponding similarity relation matrix into a heterogeneous relation convolutional network; to obtain a low-dimensional embedded representation of each view. Then, the low-dimensional embedded representation uses forward noise adding and reverse noise reduction processes of a conditional diffusion model to obtain predicted noise, and missing samples are complemented through the predicted noise; and then, an anchor point diagram is constructed by using the similarity between the complemented embedded sample and the anchor points, soft clustering distribution is obtained for the constructed anchor point diagram through an orthogonal normalization layer, and discriminative feature representation is obtained through anchor graph regularization constraint. And finally, soft clustering distribution is constrained by using a tensor Schatten p-norm so as to fully mine complementarity information and a sparse structure between the views.

The invention discloses an image version evolution path identification method and device based on atlas modeling. The method comprises the following steps: preprocessing a received original image; extracting image fingerprint data from the preprocessed image, performing fingerprint matching, if matching succeeds, determining that an original image and a historical image of a credit material uploaded by a user are candidate similar graphs, taking the candidate similar graphs as nodes, establishing directed edges for the candidate similar graphs according to a similarity relationship, and calculating weights of the directed edges; according to the method, a directed acyclic graph is constructed, a graph structure of the directed acyclic graph is constructed, an evolution path with the maximum possibility is calculated among nodes based on the constructed directed acyclic graph, a chain-level risk score of the evolution path with the maximum possibility is calculated, and a path graph with a current candidate similar graph as a starting point is output. According to the method, the path relation of the image in tampering, evolution and cross-user propagation can be intuitively described, and the crossing from single-point detection to full-link association tracking is realized.

The invention belongs to the technical field of radar radiation source identification. The invention provides a radar radiation source identification method based on relation perception and prototype optimization. According to the embodiment of the invention, through channel gating and a soft attention mechanism, invalid frequency band features are automatically inhibited, and the weight of a bad sample which deviates from the center is reduced. And a GCN is introduced to construct a sparse prototype graph, so that the model can perceive a similarity relationship between categories, and local consistency is enhanced through a graph propagation mechanism. And in cooperation with prototype comparison loss, centers of similar categories are forcibly pushed away, so that a clearer isolation strip is formed at a decision boundary, and the false identification rate is remarkably reduced. A residual mean fusion structure is also designed. When an attention mechanism may fail due to extremely small sample size, a mean value prototype on a residual path can play a role in guaranteeing the bottom, so that the stability of model training is ensured; and when the sample size is slightly large, the attention mechanism can provide finer feature expression, so that the universality of the model under different small sample settings is realized.

The application belongs to the technical field of e-commerce commodity cold start recommendation, and discloses a commodity recommendation method of multi-granularity attribute set cooperative neighbor attention, first, a user-user similarity relation graph is constructed by using the multi-granularity attribute set of the user, a commodity-commodity similarity relation graph is constructed by using the multi-granularity attribute set of the commodity, and the cooperative neighbor embedding representation of the user and the commodity on the multi-granularity attribute set is learned through a graph neural network; then the cooperative neighbor embedding representation on the multi-granularity attribute set is fused through an attention mechanism, and the user embedding representation and the commodity embedding representation are modeled; the score of the user to the commodity is calculated through inner product, the preference of the user attribute to the commodity attribute is learned, and a ranked commodity recommendation list is generated according to the score size. The application mines the personalized interest of the user from the multi-granularity attribute combination of the user and the multi-granularity attribute combination of the commodity, realizes the commodity recommendation of the interactive behavior cold start, and provides great support especially in the aspects of e-commerce new user and new commodity recommendation.

This information processing device: holds registered data and information indicating positions corresponding to the registered data; acquires data to be registered and information indicating registered data that has a hierarchical relationship with the data to be registered and shares at least some positions with the data to be registered; and assigns the data to be registered a corresponding position, on the basis of positions corresponding to the registered data having the hierarchical relationship with the data to be registered and positions corresponding to registered data having a similarity relationship with the data to be registered.

The application discloses a reciprocal interlayer-time discriminant target model for robust visual tracking, and belongs to the technical field of target tracking, and is used for solving the problem that traditional twin tracking algorithms rarely consider information interaction of templates and search regions, and that cumulative error of similar target interference influences tracking results. The application firstly constructs an interlayer target perception enhancement model, realizes interlayer feature information interaction by establishing pixel-by-pixel correlation between templates and search regions in a feature extraction process, reduces cumulative error caused by invisible target to search regions, and enhances target perception; meanwhile, in order to weaken the influence of interference, a time interference evaluation strategy is designed, similarity between multiple candidate positions in adjacent frames is established by using an interframe candidate propagation module, similar interference is eliminated according to the determined similarity score, a more reliable target position is obtained, and robust tracking is realized.

The invention discloses a cognitive diagnosis method for fine-grained knowledge level constraint perception, which relates to the technical field of cognitive diagnosis, and statically evaluates a knowledge mastering level through a knowledge proficiency evaluation module in combination with student answer records and a Q matrix; a student similarity construction method based on random grouping is adopted, and potential learning mode association is revealed; a multi-scale relation learning strategy and a Top-k attention-enhanced graph network mechanism are utilized to dynamically adjust a student similarity relation network and accurately model a complex learning relation between students, and finally, output of each module is comprehensively optimized through a joint training mechanism, so that the rationality, interpretability and accuracy of cognitive diagnosis are remarkably improved, and the learning efficiency is improved. And important support is provided for further development of personalized education and intelligent education systems.

The embodiment of the invention provides a coupling fault diagnosis method and system, and the method comprises the steps: constructing a graph which represents the similarity relation between known fault samples for all known fault samples in a support set and a label corresponding to each known fault sample; constructing a graph convolutional learning model based on a graph convolutional learning network by adopting the graph; three similar relations are adopted as a measurement structure of a known fault sample, and a corresponding loss function is determined according to the measurement structure; training the graph convolutional learning network by using the support set to obtain an intermediate graph convolutional learning network model; training the intermediate graph convolutional learning network model by using a support set and an inquiry set to obtain a trained graph convolutional learning network model; and for any to-be-identified coupling fault signal, the trained graph convolution learning network model is adopted to output a predicted value of each type of labels, and the predicted value of each type of labels is used for representing whether the fault exists or not. And when only a small number of training samples exist, each label of the coupling fault can be identified.

The invention discloses a common preference enhanced collaborative recommendation method and device, and the method comprises the steps: obtaining user implicit interaction data in a target domain and a source domain, and constructing corresponding user features and commodity feature representations; carrying out fusion coding on the target domain user features, the source domain user features and the target domain commodity features, and generating cross-domain migration features facing target domain recommendation tasks; performing fusion iteration de-noising processing on the cross-domain migration features, gradually inhibiting source domain noise interference and strengthening migratable collaborative preference information through multiple rounds of feature fusion and weight screening operation, and generating de-noised cross-domain user feature representation; after denoising is completed, user structure constraint is introduced, and consistency constraint is carried out on the similarity relation between the target domain users before and after feature enhancement, so that the overall distribution stability of the target domain user interest structure is kept; and finally, performing interactive modeling on the final user representation and the target domain commodity features to obtain a matching relationship between the user and the commodity. The device comprises a processor and a memory. Through a collaborative modeling mode of fusing iterative denoising and structural constraint, the problems of noise interference in cross-domain recommendation and user similarity structure change before and after feature migration can be relieved, and the stability and accuracy of a recommendation result are improved.

This invention discloses a refined model test method, system, and equipment for the soil displacement effect of open-pit pipe piles, relating to the field of open-pit pipe pile driving technology. The method includes: establishing multi-physical quantity similarity criteria and determining similarity constants; based on the similarity constants, preparing grouting mixture and constructing a micro-reinforcing cage; using the micro-reinforcing cage and grouting mixture to construct an open-pit pipe pile model; establishing a model box, preparing soil samples with target density and homogeneity using a layered filling method within the box, and setting up a pile driving test platform; constructing a comparative test scheme, and simultaneously monitoring and recording pile driving data using the pile driving test platform; processing and comparing the pile driving data to obtain data criteria, providing a basis for optimizing open-pit pipe pile driving parameters and construction control. This invention solves the problems of incomplete model similarity relationships, single test monitoring dimensions, difficulty in quantifying and comparing results, and the inability to provide an operational basis for optimizing engineering construction parameters.

This invention discloses a method for determining the non-perfect similarity ratio based on the classification similarity law. The method includes the following steps: S1, extracting a set of parameters describing the physical phenomenon based on experience, previous experimental results, literature, and data; S2, dividing the parameter set into key parameters, basic parameters, and derived parameters; S3, obtaining the similarity ratio of the basic parameters using measurement, material property testing, and other means; S4, deriving the similarity ratio of the derived parameters based on the similarity ratio of the basic parameters; S5, introducing constraint equations based on the physical relationship between the key parameters and the basic and derived parameters to construct a similarity ratio constraint equation; S6, substituting the similarity ratios of the basic and derived parameters into the similarity ratio constraint equation to solve for the similarity ratio of the key parameters. This method, by introducing constraint equations to construct similarity relationships, can effectively reduce scaling errors under non-perfect similarity conditions and is applicable to various scaling test scenarios such as open-loop and closed-loop tests.

The invention relates to the technical field of information retrieval, in particular to an image retrieval model training method, an image retrieval method, equipment and a medium. According to the method, multiple encoders focus on different aspects of images, diversified feature representations can be generated, dominant features of each image are recognized in combination with reconstruction loss (a bottleneck mechanism), the similarity relation between the images is enhanced, and effective capture of inter-class differences and intra-class changes is achieved; according to the method, interaction between individual features is promoted by means of meta-relationships, semantic aggregation of the features is achieved, and the generated binary codes can retain complex semantic relationships through relationship consistency loss optimization.

The application discloses a super-relation extraction method based on bidirectional time LSTM and multi-relation contrast learning, and belongs to the technical field of information extraction. The BiTime-LSTM is introduced, time-dependent relations are effectively captured through a bidirectional gate learning mechanism, main gates divide memory cells into regions with different time sensitivities, and slave gates perform fine-grained updates in different time regions, so that the performance of the model in a time prediction task is significantly improved. Meanwhile, a multi-relation contrast learning method is introduced, the predicted triad relation and the qualifier relation are compared with real labels, the similarities and differences between various relations are identified, discriminative feature representations can be learned, and the confusion problem between similar relations is effectively alleviated.

Provided is a technique for more appropriately proposing similar character candidates. A character candidate proposal device includes: a similar character storage unit that stores a similarity relation of appearances of characters; a real character storage unit that stores real existing character strings; a trust processing unit that receives one or more characters and accepts a request to propose character candidates similar in appearance to the characters; a comparison processing unit that specifies candidates of characters similar in appearance to the received characters by comparing with the similar character storage unit, compares combinations of the candidates of characters similar in appearance with the real existing character strings stored in the real character storage unit; and a candidate character transmission processing unit that outputs, as candidate characters, combinations of the candidates of characters similar in appearance that are hit by the comparison by the comparison processing unit.

The present invention relates to a Chinese-Thai cross-language sensitive information recognition method that integrates a bilingual sensitive dictionary and a heterogeneous graph to solve the problem that bilingual sensitive words are difficult to align in Chinese-Thai sensitive information recognition. The present invention first constructs a Chinese-Thai bilingual sensitive dictionary based on Wikipedia and social media sensitive data. Then, the document and the keywords and sensitive words contained therein are used as nodes, and the bilingual alignment, similarity relationship and different parts of speech are used as edges to construct a Chinese-Thai cross-language heterogeneous graph, enhance the sensitive features of the document and the alignment of the bilingual sensitive features, and use a multilingual pre-trained model to characterize the document nodes and word nodes. Finally, the input document is encoded by a multi-layer graph convolutional neural network, and the sensitive information classifier is used to classify and predict the document. Experimental results show that the proposed model performs better than the general cross-language text classification method in the Chinese-Thai cross-language sensitive information recognition task.

The present invention discloses a design method for a similarity-scaled model of transformer accident oil drainage. To address the current problems of high cost and poor repeatability of in-situ or full-scale experiments, the present invention combines similarity analysis to calculate the design parameters of the scaled model under different transformer sizes and different similarity ratios. The similarity scale of the oil drainage process between the scaled model and the prototype transformer is further calculated. Finally, the scaled model is manufactured based on the design parameters and an oil drainage experiment is conducted. Experimental results show that the use of a scaled model to simulate the transformer oil drainage process is effective. The experimental similarity design method proposed in the present invention can meet the requirements of scaled experiments and maintain a good similarity relationship. Furthermore, the experimental values ​​obtained are highly consistent with the theoretical values, and the scaled model can be verified experimentally.