Patents
Literature
9results about How to "Extensive knowledge" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
Intelligent question answering system and method for cross-domain knowledge reasoning
InactiveCN119443288AAchieve integrationimprove accuracyDigital data information retrievalKnowledge representationLinguistic modelProcessing
The invention discloses an intelligent question answering system and method for cross-domain knowledge reasoning, and relates to the technical field of intelligent question answering. In order to solve the problem that an existing intelligent question answering system is limited by technical shortages and cannot give satisfactory reply to a user in cross-domain question processing, the adopted scheme comprises the steps that a domain knowledge base construction module collects multi-domain knowledge data, and the multi-domain knowledge data is stored in a corresponding domain vector knowledge base after being preprocessed and vectorized; the user interaction module provides an interface, receives input, interacts and returns a result; the field identification module identifies the field and extracts key information by using a large language model; the knowledge retrieval module retrieves related information accordingly; the cross-domain knowledge reasoning module is used for reasoning a knowledge logic relationship of each domain and guiding a large language model to integrate fused knowledge; and the intelligent question-answering module generates prompt words, inputs the prompt words into the large language model to obtain a final response, and returns each result to the user interaction module for display. According to the method, knowledge from multiple fields can be processed, and the method is suitable for various different types of problems and scenes.
Owner:SHANDONG INSPUR SCI RES INST CO LTD
Personalized scenic spot content generation method, system and equipment based on multi-modal knowledge graph, and medium
PendingCN121958670Aclear structureClear depth of interestData processing applicationsDigital data information retrievalPersonalizationKnowledge graph
The invention relates to the technical field of smart tourism, in particular to a personalized scenic spot content generation method, system and device based on a multi-modal knowledge graph and a medium, and the method comprises the steps: collecting multi-modal data of a scenic spot, and constructing a structured multi-modal scenic spot knowledge graph based on the multi-modal data; obtaining personalized data provided by the tourist, and constructing a personalized portrait of the tourist based on the personalized data; in response to an operation of acquiring an image in a scenic spot, identifying the scenery in the image, and extracting a corresponding initial knowledge subset from the multi-modal scenic spot knowledge graph according to an identification result; performing personalized screening and expansion on the knowledge nodes in the initial knowledge subset by calculating the matching degree between the knowledge nodes in the initial knowledge subset and the tourist interest in the personalized portrait of the tourist, and dynamically binding multi-modal resources to generate a personalized knowledge graph; and presenting the personalized knowledge graph. According to the invention, the multi-mode scenic spot knowledge experience of which the structure is matched with the interest and the knowledge background can be provided for tourists.
Owner:SHANDONG LANGCHAO SMART CULTURAL TOURISM IND DEV CO LTD
Methods, devices, and media for training semantic recognition models based on contrastive learning
The present application relates to the field of deep learning technology, and proposes a semantic recognition model training method, device and medium based on contrastive learning, the method comprising: performing synonym replacement on each of the first target words in the original sentence text to obtain a first processed sentence text; and performing antonym replacement on each of the second target words in the original sentence text to obtain a second processed sentence text; training the initial semantic recognition model through the original sentence text, the first processed sentence text and the second processed sentence text to obtain a target semantic recognition model. The purpose of the embodiment of the present invention is to provide a contrastive learning method that can identify small changes in semantics, and to modify the problem that positive and negative samples are easy to distinguish before, so that the model can learn richer knowledge and improve the model training effect.
Owner:CHINA PING AN LIFE INSURANCE CO LTD
Multi-dimensional feature fusion clustering method for visual angle missing face recognition
PendingCN119600403Aefficient miningExtensive knowledgeCharacter and pattern recognitionPattern recognitionOriginal data
A multi-dimensional feature fusion clustering method for visual angle missing face recognition belongs to the field of face image data clustering processing in computer vision, and comprises the following steps: firstly, constructing a kernel matrix for incomplete multi-visual angle face image data, and performing multi-kernel completion; secondly, mapping the kernel matrix under each view angle to different dimension spaces through feature decomposition to obtain feature matrixes of different dimensions, and fusing the feature matrixes into a consistent representation matrix of a fixed dimension through a rotation matrix; and performing tensor subspace learning by taking the consistent representation as substitution of original data, calculating an affinity matrix according to a learned tensor subspace matrix, and performing spectral clustering on the affinity matrix to obtain a final clustering result. Compared with other methods, the method is higher in accuracy and more stable in performance.
Owner:HARBIN UNIV OF SCI & TECH
Computer-implemented method for updating view of spatial scene
PendingCN121999107Aeasy to masterextensive knowledgeImage enhancementImage analysisComputer graphics (images)Radiology
The invention relates to a computer-implemented method for updating a view of a spatial scene, comprising the following steps: S1) receiving image points of the view of the spatial scene, S2) acquiring a plurality of acquisition points of the scene by means of a camera, S3) assigning the acquisition points to respective corresponding image points of the view as a function of position information, S4) determining a corresponding deviation, and S5) updating the view of the spatial scene by means of the deviation. S5) excluding from the update those acquisition points with deviations below a tolerance threshold, S6) summarizing a plurality of image points of the view into a sub-view, S7) determining a spatial environment for sub-view image points of a subset with deviations above the tolerance threshold, S8) determining whether at least one acquisition point is located within a volume spanned by the determined spatial environment and an image sensor of the camera, and if the at least one acquisition point is located within the volume spanned by the determined spatial environment and the image sensor of the camera, if the at least one acquisition point is located within the volume spanned by the determined spatial environment and the image sensor of the camera. S9) excluding the sub-view image points from the update if the deviation of at least one acquisition point located within the volume is above a motion threshold, S10) updating only the image points of the view not excluded from the update based only on the acquisition points not excluded from the update, S11) providing an updated view.
Owner:SIEMENS HEALTHINEERS AG
Knowledge distillation model training methods, apparatus, computer equipment, and storage media
This application relates to a method, apparatus, computer device, storage medium, and computer program product for training a knowledge distillation model. The method includes: adding a first weight matrix and a second weight matrix to the linear layer of the student model to be trained, based on the original weight matrix of the linear layer; obtaining a first predicted label for sample data using a teacher model, and obtaining a second predicted label for the sample data using the student model to be trained; the sample data carrying sample labels; determining the model loss value of the student model to be trained using the first predicted label, the second predicted label, and the sample labels; freezing the original weight matrix, and adjusting the first and second weight matrices using the model loss value to train the model, thereby obtaining the trained student model. This method can improve the training efficiency of the student model and reduce processing resource consumption.
Owner:TENCENT TECHNOLOGY (SHENZHEN) CO LTD
ADAS intelligent driving real vehicle road test calibration method
PendingCN119512084Aimprove decision makingImprove response speedVehicle testingVehicle position/course/altitude controlAutopilotReliability engineering
Owner:SCI & TECH CO LTD HEFEI INTELLIGENT VEHICLE TECH CO LTD
Traditional Chinese medicine evidence-based knowledge extraction method and system
InactiveCN119324070Aensure reliabilityimprove readabilityMedical data miningNeural learning methodsPattern recognitionImaging processing
The invention provides a traditional Chinese medicine evidence-based knowledge extraction method and system. The method comprises the following steps: collecting diversified literature data related to traditional Chinese medicine from multiple channels; performing imaging processing on the diversified literature data to obtain a literature image, and performing chromatic aberration balance on the literature image to obtain a balanced image; performing image enhancement processing on the balanced image to obtain an enhanced image; performing OCR recognition according to the enhanced image to obtain a recognition text, and performing data cleaning on the recognition text to obtain to-be-detected data; and inputting to-be-tested data into the constructed multi-strategy knowledge extraction model to obtain an extraction result. The traditional Chinese medicine related literature data is collected through multiple channels, the universality and diversity of data sources are ensured, and therefore rich knowledge and research results in the traditional Chinese medicine field are reflected. In the processing process, the readability of the literature image is improved through the application of image processing and chromatic aberration balancing technologies, and high-quality input is provided for subsequent OCR recognition.
Owner:INST OF INFORMATION ON TRADITIONAL CHINESE MEDICINE CACMS
Method and system for using 2D pre-trained model as backbone network for 3D downstream tasks
The embodiments of the present application relate to the field of artificial intelligence technology, and in particular to a method and system for using a 2D pre-trained model as a 3D downstream task backbone network, the method comprising: first, mapping a point cloud into high-dimensional features; then, setting a number of task symbols, splicing the task symbols with the high-dimensional features to obtain spliced data; inputting the spliced data into the backbone network of the 2D pre-trained model, updating the high-dimensional features to obtain updated point cloud features; based on the updated point cloud features, decoding the updated point cloud features to obtain prediction information. The present application can solve the problem in existing 3D pre-training methods that it is difficult to obtain a pre-trained model with rich knowledge due to the small amount of data in the 3D field.
Owner:SHANGHAI ARTIFICIAL INTELLIGENCE INNOVATION CENT