Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

3084 results about "Similarity computation" patented technology

Knotarization intelligent question and answer customer service method and system based on knowledge graph

The invention provides a notarization intelligent question and answer customer service method and system based on a knowledge graph, and relates to the technical field of information, and the method comprises the steps: collecting multi-source heterogeneous data in the notarization field, forming an entity set and a relationship set, combining to form an initial knowledge graph, carrying out a dynamic update mechanism based on time decay, and supplementing to form a dynamic knowledge graph. Carrying out vectorization expression to obtain an atlas vector; receiving a multi-modal problem, determining fusion features, performing deep semantic understanding, obtaining semantic features, determining a user intention, and forming a structured query expression; based on the user intention and the structured query expression, carrying out multi-hop reasoning in the dynamic knowledge graph, carrying out similarity calculation by utilizing graph vectors, determining a reasoning path in combination with the user intention, carrying out knowledge association reasoning along the reasoning path, obtaining a preliminary reasoning result, carrying out interpretability analysis on the preliminary reasoning result, and obtaining a final reasoning result; and generating a reasoning chain and a confidence score, forming a detailed reasoning result, and finally generating a personalized answer.
Owner:SUZHOU LIANZHENG INTELLIGENT TECH CO LTD

Dynamic vector knowledge base construction and retrieval method based on multi-modal large model

The invention belongs to the technical field of knowledge retrieval, and discloses a multi-modal large model-based dynamic vector knowledge base construction and retrieval method, which comprises the following steps of: obtaining a multi-source heterogeneous modal data set, and carrying out preprocessing and modal standardization processing on the multi-source heterogeneous modal data set to obtain a standardized multi-modal data set; performing feature extraction and semantic vector representation generation by using the pre-trained multi-modal large model, and constructing a multi-modal knowledge vector set; semantic association analysis and hierarchical clustering are carried out on the multi-modal knowledge vector set, and a structured vector knowledge base is constructed; performing semantic similarity calculation and relation modeling on the vector knowledge base to form a vector relation network; intention analysis and vector representation are performed based on mixed modal query information input by a user, and efficient similarity retrieval is realized in combination with a vector relation network; dynamic optimization is carried out through user feedback, personalized retrieval result adjustment is achieved, and the problem of limitation of a traditional retrieval system during multi-modal data processing is effectively solved.
Owner:南京迅集科技有限公司

Cross-modal retrieval method for semantic and vector fusion in data space

The invention provides a cross-modal retrieval method for semantic and vector fusion in a data space, which belongs to the field of cross-modal information retrieval, and comprises the following steps: firstly, collecting and preprocessing multi-modal data; generating modal embedding and storing by utilizing the pre-training model; a shared semantic space is constructed, cross-modal vector alignment is optimized through comparative learning, and a modal mapping network is designed to enhance the embedding projection effect; storing the aligned embedding by using a Milvus database, and constructing an HNSW index; user text or image query is processed, text query analyzes limiting conditions to generate enhanced embedding, and image query extracts characters through OCR and fuses the characters with image features to generate embedding; in a database, through condition screening and semantic similarity calculation, a Top-K candidate item is retrieved; performing multi-modal correlation sorting on the candidate results and returning the results; according to the method, the shared semantic space is constructed, the alignment effect of different modal embedding is optimized, efficient storage and index management of multi-modal embedding are carried out, and real-time retrieval of large-scale cross-modal data is achieved.
Owner:HARBIN ENG UNIV

Memory retrieval method for enhancing multi-modal long-context dialogue ability of large language model

The invention discloses a memory retrieval method for enhancing multi-modal long-context dialogue ability of a large language model. The method comprises the following steps: carrying out self-adaptive segmentation based on information density on an original multi-modal dialogue sequence and extracting local features; constructing a three-layer feature pyramid structure to realize multi-scale feature representation; the time sequence expression capability of the features is enhanced through feature compression and time sequence dependency graph modeling; constructing a memory vector sequence based on feature stability evaluation; carrying out structured representation on the query data and carrying out multi-level interaction with the memory vector; efficient retrieval is realized through hierarchical indexing and multi-dimensional similarity calculation; the memory sequence is periodically optimized based on user feedback. According to the method, the multi-modal information understanding and retrieval capability of the model in a long dialogue scene can be effectively improved, and the method has important practical application value.
Owner:NANJING ARTIFICIAL INTELLIGENCE CHIPS RES INST OF AUTOMATION CHINESE ACAD OF SCI +1

Distributed power data asset management privacy protection encryption architecture design method

The invention provides a distributed power data asset management privacy protection encryption architecture design method, which comprises the steps of generating a watermark with robustness and imperceptibility by adopting a content-based digital watermarking algorithm according to statistical characteristics of power data assets, and storing a watermark embedding process and an extraction result through a blockchain; a graph-based data model is adopted, the electric power data assets carrying the watermarks serve as nodes, the data flow relation serves as edges, and an electric power data asset consanguinity graph is constructed; for distributed storage of the blood relationship map, a P2P network topology is constructed by adopting a block chain and a distributed hash table, and blood relationship map data is stored in each node of an alliance chain in a distributed manner; and verifying the digital watermark information embedded in all circulation path nodes through which the power data assets pass in the blood relationship map, calculating the similarity between the extracted watermark and the original watermark, calculating the distortion rate, and judging whether the power data assets are tampered or not.
Owner:董召杰 +1

Unmanned aerial vehicle accessory intelligent identification and access method and system based on sensor

The invention provides an unmanned aerial vehicle accessory intelligent identification and access method and system based on a sensor, and relates to the technical field of unmanned aerial vehicle accessory management, and the method comprises the steps: collecting the three-dimensional contour information of unmanned aerial vehicle accessories, generating standard point cloud data, carrying out the feature extraction, and carrying out the feature alignment and interaction, generating a high-dimensional fusion feature matrix of the target unmanned aerial vehicle accessories; based on the feature pyramid network, constructing multi-scale feature representation, generating hierarchical feature descriptors, performing similarity calculation, generating a similarity score matrix, performing optimal matching, establishing an adaptive verification rule base and performing accessory verification; calculating an optimal action sequence of an access path based on model information, mapping the optimal action sequence into a motion track parameter of a mechanical arm, collecting multi-point stress data, predicting the optimal clamping force, establishing an accessory service life prediction model, performing prediction in combination with historical data, and generating an accessory state evaluation report and a maintenance suggestion.
Owner:ZHONGDIAN GUOKE TECH CO LTD +1

Remote sensing image change detection method based on language guidance

The invention relates to the field of remote sensing image change detection, and discloses a remote sensing image change detection method based on language guidance. The method comprises the following steps of: extracting a two-time-phase remote sensing image semantic feature map by adopting an Officient SAM as a visual basic model, constructing a multi-layer adapter, and extracting a two-time-phase multi-scale feature map; constructing spatial attention, and extracting visual features; the input text description is processed through a text encoder, and word embedding and overall expression embedding are obtained; a multi-head cross attention method is adopted, and a pre-fusion module is constructed and used for fusion operation of multiple layers of feature maps after word embedding and splicing; and constructing a two-channel decoder structure, performing similarity calculation on the obtained image features and semantic embedding, and outputting a final change detection mask. According to the method, a multi-layer vision-language feature cross layer is designed, so that the model fully learns related information of images and corresponding types of texts, and universal detection of multi-category remote sensing image changes can be realized by taking natural language as guidance.
Owner:SICHUAN UNIV

Ship design knowledge retrieval method and system based on multi-modal knowledge graph

The invention provides a ship design knowledge retrieval method and system based on a multi-modal knowledge graph. The method comprises the steps of collecting and constructing a ship design set from the ship design field; forming a hierarchical multi-modal knowledge graph for describing a ship design field concept, physical characteristics and design specifications; enhancing association among different modal data through vector similarity calculation; the hierarchical multi-modal knowledge graph is integrated into a ChatGLM model; positioning knowledge nodes related to user demands in the hierarchical multi-modal knowledge graph; matching and positioning the ship design knowledge related to the query content of the user, and feeding back the ship design knowledge obtained by the intelligent semantic retrieval to the user in a hierarchical form. According to the method, ship design knowledge retrieval based on the multi-modal knowledge graph enhanced ChatGLM is realized, and the information acquisition efficiency of engineering designers and the practical application value of the system are improved.
Owner:SANYA SCI & EDUCATION INNOVATION PARK WUHAN UNIV OF TECH

Retrieval optimization method based on hierarchical expert routing model and CoT reasoning

The embodiment of the invention provides a retrieval optimization method based on a hierarchical expert routing model and CoT reasoning, which belongs to the technical field of data processing and specifically comprises the following steps: creating a hierarchical knowledge base; extracting and clustering each fragment abstract in each layer in the hierarchical knowledge base, and creating a hierarchical semantic library; constructing a hierarchical index database by using each central abstract in the hierarchical semantic database, and forming a hierarchical expert routing model in combination with an intelligent routing mechanism; determining a target hierarchical index matched with the question in a hierarchical index database by utilizing a hierarchical expert routing model; performing similarity calculation on the vectorized problem and a target hierarchical index; returning the fragment of the original document in the hierarchical semantic library with the highest similarity; and driving hierarchy switching by using CoT reasoning, finally merging fragments and returning the fragments to the large model, and generating answers corresponding to the questions. By means of the scheme, the response speed and accuracy of user query are improved, self-adaptive adjustment of the retrieval path is achieved, and the retrieval efficiency and adaptability of complex query are improved.
Owner:XIANGJIANG LAB

Comparative learning unsupervised cross-modal hash retrieval algorithm based on graph attention mechanism

The invention discloses a contrast learning unsupervised cross-modal hash retrieval algorithm based on a graph attention mechanism, and relates to the technical field of cross-modal retrieval. According to the graph attention mechanism-based contrast learning unsupervised cross-modal Hash retrieval algorithm, feature extraction is performed on image and text data through a pre-trained CLIP model to obtain image modal features and text modal features, and additional positive samples are generated through data enhancement; the similarity is calculated through Euclidean distance and cosine similarity on the basis of a graph attention network, and high weight is given to positive samples and low weight is given to negative samples by comparing adjacent matrixes. The method has the advantages that the features of the image mode and the text mode can be effectively fused and mapped to the common Hash space, a graph attention mechanism can adaptively adjust the connection weight between the features of the different modes, samples with high semantic correlation are highlighted, and therefore the semantic consistency between the image and the text is ensured.
Owner:JIANGSU DONGYIYUAN ELECTRONIC TECH CO LTD

Multi-source heterogeneous data fusion and processing method based on localized LLM model

The invention discloses a multi-source heterogeneous data fusion and processing method based on a localized LLM model, and relates to the technical field of factory energy management.The method comprises the steps that multi-source heterogeneous data is collected from a factory energy management system, and the collected original data is preprocessed and standardized; performing feature selection, feature extraction and feature combination on the processed data; carrying out embedding dimensionality reduction by adopting principal component analysis and a localized LLM model; performing intelligent semantic analysis and fusion on the dimension reduction feature data by utilizing a localized LLM model, performing weighted fusion on embedded vectors by adopting a multi-head attention mechanism, and extracting semantic association among the data; and performing intelligent anomaly detection on the fused high-quality data by using localized LLM model embedding analysis and cosine similarity calculation. According to the method, the processing efficiency and quality of the multi-source heterogeneous data are comprehensively improved, high-quality data support is provided for comprehensive energy management of factories, and efficient and intelligent energy scheduling and management optimization are achieved.
Owner:UNIV OF ELECTRONIC SCI & TECH OF CHINA CHENGDU COLLEGE

Abnormal transaction intelligent monitoring and analysis system and method based on AI drive

The invention discloses an AI-driven abnormal transaction intelligent monitoring and analysis system and method, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining structured features and unstructured features, carrying out the feature fusion, and constructing an account feature vector; constructing a cross-domain heterogeneous graph, learning an embedded vector of an account node in the cross-domain heterogeneous graph based on a time sequence heterogeneous graph neural network, and generating an account portrait vector; training an abnormal transaction detection model, and predicting the abnormal probability of the current real-time transaction record of the account by taking the account portrait vector and the transaction record as input data; dividing all accounts into account groups based on the account portrait vectors, calculating a group abnormal transaction threshold value, and calculating an adaptive abnormal transaction threshold value based on the group abnormal transaction threshold value and the similarity between the account portrait vectors and the center vectors of the account groups to which the account portrait vectors belong; and if the abnormal probability is greater than a self-adaptive abnormal transaction threshold, marking the transaction of the account as an abnormal transaction, triggering risk control measures, and regularly updating the self-adaptive abnormal transaction threshold.
Owner:SHANGHAI YUFENG ELECTRONIC INFORMATION TECH DEV CO LTD

Cloud-native application programming interface (API) recommendation method fusing data augmentation and contrastive learning

Disclosed is a cloud-native application programming interface (API) recommendation method fusing data augmentation and contrastive learning. Service information is included on the basis of a service information double-graph structure, and a mutual attention mechanism is designed to compute an importance degree of each layer of information. A data optimization method for sequence information based on functional similarity and a computation method for similarity between services based on two parts of information are provided; on this basis, data of a service invocation sequence is augmented with the idea of contrastive learning to form an augmented sequence pair; a computational contrastive loss function is combined with a pair-wise recommendation loss function to optimize an overall model, thereby improving the effect of a service recommendation model; and according to a feature embedding representation result of a service, pair-wise recommendation scores are computed to complete service recommendation.
Owner:CHINA JILIANG UNIV

Experimental data processing method and device, AI analysis module and computer equipment

The invention relates to an experimental data processing method and device, an AI analysis module and computer equipment, and belongs to the field of data processing.The method comprises the steps that multi-dimensional original data are partitioned according to types, and formats are unified; generating a similarity matrix based on time and space neighborhood information, and marking abnormal fluctuation points; effective signals are separated through a time-frequency feature matching noise library; extracting multi-layer features of basic statistics, time sequence correlation and trend change; and dynamically screening core features to update the tracking type experimental model. The matched AI analysis module integrates hardware circuits of data partitioning, similarity calculation, anomaly marking, noise matching, feature extraction and model updating, and whole-process acceleration is achieved. According to the method, through multi-dimensional data compatibility processing, accurate anomaly detection, multilayer feature fusion and model adaptive optimization, the experimental data processing efficiency and conclusion reliability are remarkably improved, and the method is suitable for real-time analysis of multiple scenes such as scientific research and industry.
Owner:深圳市伊元科技有限公司

Fraud risk analysis system incorporating a large language model

A system is adapted to automatically report the trustworthiness of an entity. The system includes a processor and a computer readable medium carrying instructions. The instructions include receiving unstructured data pertaining to an entity from public sources, and receiving structured data pertaining to the entity from at least two databases. The instructions also include merging the structured data and the unstructured data into a single document; splitting the single document into chunks; creating embeddings corresponding to the chunks; and storing the embeddings in a vector store. The instructions also include receiving a natural language user query regarding trustworthiness of the entity; converting the query to a query embedding; based on the query embedding and a similarity calculation, fetching a relevant embedding from the vector store; with a large language model (LLM), generating a query response regarding the trustworthiness of the entity; and communicating the query response to the user.
Owner:ACTIMIZE LIMITED

Intelligent talent tag portrait analysis system based on big data

The invention discloses a talent tag portrait intelligent analysis system based on big data, relates to the technical field of intelligent analysis, realizes unified access and processing of multi-source heterogeneous talent data through a vector module, and effectively solves the problems of tag expression inconsistency and semantic drift in combination with BERT embedding and tag semantic evolution mechanisms. Therefore, the accuracy of label normalization and portrait structure consistency is improved. According to the system, the label structure relation and the capability score are linked and fused through a graph construction module, a structurable original portrait vector is generated, a semantic collaboration network between labels is constructed, and deep semantic support is provided for portrait calculation. The matching module improves the man-post matching precision through vector alignment and similarity calculation of post portraits and candidate portraits, triggers a label offset analysis and reconstruction scoring mechanism when the matching value is insufficient, realizes dynamic optimization of the portraits, and enhances the self-learning and label compensation capabilities of the system.
Owner:LUOKE (XIAMEN) NETWORK TECHNOLOGY CO LTD

Intelligent legal document retrieval system based on vector technology

The invention discloses an intelligent legal instrument retrieval system based on a vector technology, which relates to the technical field of information retrieval and comprises an instrument vector generation module, an index construction module, a query vector generation module, a similarity calculation module and a result optimization module, comprising but not limited to word segmentation and stop word removal operations, and converting the legal document into vector representation by using a pre-trained word vector model; through the intelligent legal instrument retrieval system based on the vector technology, semantic meanings of the legal instruments can be effectively understood, and even in the face of fuzzy or inaccurate query input of a user, related legal instruments can be quickly and accurately positioned by means of similarity calculation in a vector space; the efficiency, correlation and accuracy of legal document retrieval are greatly improved, and the urgent demands of the legal industry and related demanders for efficient legal information retrieval are met.
Owner:NANJING SUYUAN INFORMATION TECHNOLOGY CO LTD

AI toy voiceprint recognition interaction method, device and equipment

The invention relates to the technical field of AI toys, and provides an AI toy voiceprint recognition interaction method, device and equipment, and the method comprises the steps: obtaining a to-be-recognized target voice signal, extracting an original audio data set to generate a sound field estimation parameter and a background noise feature, carrying out the voiceprint feature extraction of the target voice signal, obtaining a voiceprint feature vector, and obtaining the voiceprint feature vector; and performing feature clustering on the voiceprint feature vector and a preset child voiceprint vector set to obtain user identity information, a behavior tag and an emotion tag so as to generate a corresponding multi-modal response instruction, and inputting the multi-modal response instruction into a control module of the AI toy. Robustness of a target voice signal in a complex environment is improved by combining sound field estimation parameters and background noise features, and through voiceprint feature vector extraction and clustering and similarity calculation, the target voice signal is improved under the condition that environmental noise interference is remarkable or semantic emotion interaction is complex. The problems of low identification accuracy and low user discrimination degree exist in the prior art.
Owner:SHENZHEN PEMI TECHNOLOGY CO LTD

Multi-platform e-commerce order management method and system based on cloud data analysis

The embodiment of the invention provides a multi-platform e-commerce order management method and system based on cloud data analysis, and the method comprises the steps: carrying out the analysis and standardization processing of order data through employing a dynamic format conversion channel, constructing a dynamic priority evaluation matrix in combination with real-time logistics load and historical aging data, and carrying out the analysis and standardization of the order data. A geographic position weight model is constructed based on equipment fingerprint identification and address similarity calculation, an order topology aggregation scheme is generated through a spatial incidence matrix, a distributed decision tree is constructed according to inventory fluctuation prediction and supplier response rate, a picking path is optimized, and finally logistics node data is integrated to construct a visual tracking interface. According to the technical scheme, abnormal order real-time early warning and compensation path planning are achieved through a self-repairing mechanism, logistics state holographic projection is generated, the flexibility and efficiency of the multi-platform e-commerce order management system are improved, and the problems of high complexity, poor expansibility, performance bottleneck and the like existing in a traditional system are effectively solved.
Owner:BEIJING CENT TECH CO LTD

Archive system and method based on artificial intelligence

The invention discloses an archive system and method based on artificial intelligence, and relates to the technical field of artificial intelligence, and the archive system comprises an intelligent retrieval module, an information sharing optimization module, a deep learning engine and an adaptive classification module. The semantic meaning of a retrieval request input by a user can be deeply understood, the deep neural network further strengthens the analysis capability of a complex semantic relationship, the retrieval request and an archive text are converted into high-dimensional vectors in combination with a word vector model, and the retrieval request and the archive text are analyzed through accurate cosine similarity calculation and introduction of a correlation calculation formula of a time decay factor. According to the method, the archives which most meet the requirements are quickly and accurately screened out from massive archives, and even in a huge-scale archive room, a deep learning engine can continuously optimize feature extraction and mode recognition capabilities through training of a large amount of archive data, so that a large amount of time is saved, and the possibility of error occurrence is reduced.
Owner:SHANDONG QIANHE ARCHIVES MANAGEMENT CO LTD

Intelligent analysis method and system for monitoring equipment in power distribution area

The invention discloses a power distribution area equipment monitoring intelligent analysis method, and relates to the technical field of power system equipment monitoring, and the method comprises the steps: collecting and preprocessing the real-time operation data of power distribution area equipment; performing feature extraction on the real-time operation data by using a deep learning model to obtain an operation state feature vector; performing similarity calculation on the running state feature vector and a normal running state feature vector in a historical database to obtain a preliminary abnormal degree quantitative index; performing equipment state evaluation and classification according to the preliminary abnormal degree quantitative index to obtain an equipment state evaluation result; and taking corresponding measures according to an equipment state evaluation result, automatically generating a fault diagnosis report and pushing the fault diagnosis report to a maintenance terminal. The multi-parameter monitoring and deep learning feature extraction technology adopted by the invention improves the accuracy and comprehensiveness of anomaly detection, and can identify some potential fault features which are difficult to find by a traditional method.
Owner:HEYUAN POWER SUPPLY BUREAU GUANGDONG POWER GRID CO LTD

Multi-modal semi-supervised medical image segmentation method based on SAM adaptive fine tuning

The invention discloses a multi-modal semi-supervised medical image segmentation method based on SAM adaptive fine tuning, and the method comprises the steps: obtaining an original multi-modal image, adjusting the original multi-modal image to a preset size, and carrying out the image preprocessing, thereby obtaining a multi-modal image pair; simultaneously inputting the multi-modal image pair into a student branch model and a teacher branch model which are completely identical in structure, wherein each of the student branch model and the teacher branch model comprises a fusion module, an SAM encoder and a layered decoder; the multi-modal image pair passes through a fusion module formed by a convolutional network to obtain fusion features, the fusion features are input to the SAM encoder, and output features of different Transform layers are obtained; and inputting the plurality of output features into a hierarchical decoder, performing similarity calculation by the hierarchical decoder according to the plurality of output features to obtain prototype classification, and obtaining a prediction mask through a linear layer. According to the method, the multi-level features can be well utilized to realize fine-grained segmentation, and a good segmentation effect is realized.
Owner:SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI

Data analysis method based on chain operation benefit supervision system

The invention relates to the technical field of data analysis, and discloses a data analysis method based on a chain operation benefit supervision system, and the method comprises the steps: carrying out the collection and preprocessing of the multi-dimensional data of each store of a chain operation enterprise, and obtaining the multi-dimensional time series data; performing multi-dimensional similarity calculation and fuzzy clustering to obtain a store clustering result and a fuzzy membership degree; constructing a decision tree model and performing store operation state evaluation to obtain a store operation state evaluation result; time sequence feature extraction is carried out, a semantic segmentation network is constructed, and a store business prediction model is obtained; performing deep prediction on the multi-store business data to obtain a store business prediction result; and based on the store operation state evaluation result, the store business prediction result and the fuzzy membership degree, comprehensive anomaly prediction and resource optimization configuration are carried out to obtain an anomaly prediction report and an optimization scheme, so that the accuracy of operation state evaluation is improved.
Owner:深圳市逸马科技有限公司

Large model text generation method and system based on adaptive cue words

The invention provides a large model text generation method and system based on self-adaptive cue words, and belongs to the technical field of large model text generation. The technical problem to be solved is that the current large language model text generation has the defects of selection deviation and uncertainty. According to the technical scheme, hierarchical clustering processing is carried out on problems contained in a large-scale multi-task language understanding MMLU data set, a text embedding and similarity calculation matrix is adopted, and a plurality of problem clusters containing similar features are constructed and obtained; randomly extracting representative problem examples from each problem cluster, and constructing excellent cue words with remarkable guide effects for each problem based on domain knowledge and potential semantic association; a Qwen model is adopted to generate candidate cue words with diversity and pertinence for various question clusters divided in advance, a cue word bank is constructed, and each question and cue word pair in the cue word bank is manually scored; the method is applied to text generation.
Owner:CHANGZHI DAYAN TWIN DIGITAL INTELLIGENCE RESEARCH INSTITUTE CO LTD +1

Multi-modal metadata alignment fusion method and device, equipment and storage medium

The invention discloses a multi-modal metadata alignment fusion method and device, equipment and a storage medium, and the method comprises the steps: carrying out the metadata extraction of structured data, unstructured text data and image data, and generating multi-modal metadata with semantic annotations; establishing a shared semantic embedding space, and mapping the multi-modal metadata to the shared semantic embedding space for coding to obtain a unified spatial vector; determining an alignment candidate pair from the unified spatial vector through similarity calculation, and identifying a semantic relationship of the alignment candidate pair; and performing conflict detection on the aligned candidate pairs and the corresponding semantic relationships, and resolving conflicts based on weight weighting fusion to obtain a unified metadata system. According to the method, improvement and optimization are carried out from multiple aspects of multi-modal data processing, semantic understanding, alignment accuracy, conflict resolution and the like, the defects in the prior art are overcome, and a more accurate and comprehensive multi-modal metadata alignment fusion result can be provided.
Owner:CHINESE PEOPLES LIBERATION ARMY INFORMATION SUPPORT CORPS ENGINEERING UNIVERSITY

Real-time intelligent teaching method and system for driving training full-scene behaviors

The invention provides a driving training full-scene behavior-oriented real-time intelligent teaching method and system, and relates to the technical field of intelligent driving, and the method comprises the steps: obtaining full-scene driving behavior data generated by an intelligent agent in a multi-source heterogeneous driving training platform, carrying out the classification marking and fusion mapping of the full-scene driving behavior data, and carrying out the fusion mapping of the full-scene driving behavior data; mapping to generate an agent driving behavior knowledge graph through a knowledge graph construction algorithm; performing comparative analysis on the agent driving behavior cognitive model and a pre-constructed driving behavior sample, and judging driving behavior defects of the agent in different driving dimensions and different driving scenes through similarity calculation and deviation analysis; aiming at the driving behavior defects of the intelligent agent, automatically planning a plurality of stage reinforcement learning tasks, and matching to generate a corresponding driving behavior reinforcement learning scene; the intelligent agent is arranged in a driving behavior reinforcement learning scene, the intelligent agent is guided to master an optimal coping strategy for driving behavior defects, and the method is used for real-time intelligent teaching.
Owner:YIXIAN INTELLIGENCE

High-sampling-rate audio analysis optimization method and system, storage medium and equipment

The invention relates to the technical field of audio signal processing, and discloses a high-sampling-rate audio analysis optimization method and system, a storage medium and equipment, and the method comprises the steps: upgrading an FFTW (Fast Fourier Transform) library, and building an optimized memory management mechanism; carrying out adaptive framing processing on the input audio data, and optimizing the data access efficiency by adopting a multi-stage cache system; the calculation precision of the FFT fast Fourier transform is dynamically adjusted, and the calculation of the FFT fast Fourier transform is optimized by pre-calculating and caching an FFTW plan; performing clock synchronization optimization and jitter elimination on the COAX digital audio signal; establishing a multi-dimensional result cache matrix and an intelligent multiplexing decision tree, and reducing repeated operation through intelligent cache prediction and similarity calculation; system performance indexes are monitored in real time, adaptive parameter adjustment is realized based on an optimization objective function, audio quality and system stability are monitored in combination with subjective and objective evaluation mechanisms, repeated operation is remarkably reduced, and calculation resource allocation is optimized on the premise of ensuring sound quality.
Owner:XIAMEN LEYUNRUI TECHNOLOGY CO LTD

Live broadcast bullet screen real-time feedback method and system based on interactive semantic matching

The invention relates to the technical field of user interaction, in particular to a live broadcast bullet screen real-time feedback method and system based on interaction semantic matching, and the method comprises the steps: receiving and caching user bullet screens in real time, carrying out the density analysis and priority evaluation of bullet screen flows through the combination of filtering and resource optimization rules, dynamically adjusting the response frequency, and screening key bullet screens; a distillation processing mechanism intention unit is introduced, a user intention label in a key bullet screen is extracted, a vector is generated, historical behavior data of a sending user is obtained at the same time, the intention label, the vector and current real-time scene data of a live broadcast room are fused, and a bullet screen vector is constructed; performing similarity calculation in combination with the live broadcast content and user historical behaviors to obtain first feedback content; based on a reinforcement learning sentiment analysis strategy, combining user preference memory to generate second feedback content; and embedding the second feedback content into the current live broadcast interface through the client. According to the invention, real-time forward feedback and intelligent guidance of the live broadcast bullet screen are realized through interactive semantic matching.
Owner:HANGZHOU XINGMAI YUNSHANG TECHNOLOGY CO LTD

Class case recommendation method based on deep understanding

The invention discloses a class case recommendation method based on deep understanding, and the method comprises the following steps: semantic extraction: carrying out the preprocessing of a case text, and carrying out the semantic feature extraction of the preprocessed case text through an encoder; the semantic feature extraction comprises initial crime name prediction and legal entity identification; performing structure extraction, converting nonlinear legal provisions, judicial interpretation and judgment rules into a legal provision map database, performing essential component analysis, and performing entity-essential component matching on a legal entity recognition result and essential components; and performing class case retrieval, performing dynamic fusion on the preliminary crime name prediction result and the entity-essential element matching result to obtain a case feature fusion vector, performing similarity calculation according to the case feature fusion vector, and performing class case recommendation. The technical problems that an existing method is low in recognition accuracy in long legal texts and insufficient in precise semantic boundary recognition of legal terms are solved.
Owner:XIANGTAN UNIV

Electric power metering equipment anomaly detection method and device based on knowledge graph

The invention relates to the technical field of electric power measurement, and discloses an electric power measurement equipment anomaly detection method and device based on a knowledge graph. Preprocessing the power state data; according to abnormal state nodes defined in the electric power metering equipment anomaly detection knowledge graph and attributes of the abnormal state nodes, the closest abnormal state is judged through similarity calculation; and according to the node attribute corresponding to the determined closest abnormal state, obtaining an associated abnormal fault reason and operation and maintenance operation guidance, so as to carry out abnormal operation and maintenance disposal on the electric power metering equipment which is determined to be abnormal. The detection accuracy and reliability are improved, misjudgment and missed judgment are reduced, and operation and maintenance personnel are helped to quickly position problems and take effective measures by automatically associating fault reasons and operation and maintenance guidance, so that the equipment operation and maintenance efficiency is improved.
Owner:MARKETING SERVICE CENT OF STATE GRID HEILONGJIANG ELECTRIC POWER CO LTD