13 results about "User studies" patented technology

The present disclosure is directed to systems and methods of providing systems and methods of autonomously generating summary documents based, at least in part, on a plurality of queries provided by a system user. The systems and methods disclosed herein include processor circuitry to identify a plurality of information sources for a specific topic guided by an ontology with specific concepts and relations. The systems and methods disclosed herein also include processor circuitry to generate user-focused extractive text summarization from each of at least some of the plurality of identified information sources using a plurality of queries supplied by the user / researcher.

The present invention relates to a personalized paper recommendation method based on time-sensitive auxiliary task driving, comprising the following steps: constructing an academic HIN graph, and using a HIN subgraph extraction function to extract HIN subgraphs within long and short time spans. Adding a fully connected layer to the output of the classical BERT language model for fine-tuning to obtain paper keyword semantic features, aggregating the keyword semantic features through a self-attention mechanism to obtain paper content features, and aggregating the paper content features through a self-attention mechanism to obtain the current user's research direction features. Embedding a GNN network in the HIN subgraphs of the two time spans to capture user reading preference features and paper audience preference features. Performing multi-time-span related feature capture through the cfLSTM predictor in the present invention. Calculating the matching degree between the user's research direction and the paper content and calculating the matching degree between the user's reading preference and the paper audience preference, and linearly fusing the two matching degrees to obtain a recommendation probability value.

The invention provides a library subject service intelligent recommendation method and system based on big data mining, and relates to the technical field of library services.The method comprises the steps that firstly, library subject service big data is mined, and subject user research process features covering subject user research stages, resource use tracks and demand evolution features are constructed; and establishing a dynamic adaptation relationship between the research process and the resources in combination with a library subject resource pool. And splitting resource service modules according to research process stages to form staged subject resource service architectures, and generating a staged subject service recommendation list after series connection. And collecting user research process data in real time, dynamically adjusting a recommendation list, supplementing transition resources and services, and forming dynamic subject service recommendation contents. And finally, outputting recommended content and collecting feedback data, and integrating big data to optimize research process characteristics and dynamic adaptation relationships. According to the invention, accurate, dynamic and systematic library subject service recommendation can be provided for the user, and the service quality and the user research efficiency are improved.

The invention discloses a petrochemical engineering HSE training method and system based on virtual reality, and relates to the technical field of petrochemical engineering safety training. The problems that in the prior art, interaction data are fixed, tasks cannot be adjusted in real time for different posts, the training effect is poor, and the efficiency is low are solved. Comprising the steps of S1, constructing a training virtual scene, S2, collecting feature information, S3, pushing a training scheme, S4, training users to interact in the virtual scene, S5, training users to complete training contents, S6, pushing sudden accident training users to quickly make decisions and operations, and S7, evaluating, examining and recording the operation accuracy and duration of training users, and pushing solutions and improvement suggestions S8, a virtual tutor diagnosis and question answering function assists the training user in learning; and S9, a report card and a trend chart are pushed to the training user. The petrochemical engineering HSE training method and system based on virtual reality are used for petrochemical engineering health, safety and environment practice operation skill training, and the training effect and efficiency of training users and the handling capacity of sudden accidents are improved.

A system and method for AI-mediated discovery, notification, and licensed access to copyrighted works during a research session. The system comprises: a content registry in which copyright holders register works and grant trusted read access to authorized AI tools; a trusted content ingestion module that reads the full text of registered works and generates internal representations including semantic embeddings, structural analysis, and portion-level summaries, and generates indexing information for the content registry; an AI research tool that draws on its comprehension of registered works to identify works relevant to a user's research query and present a non-disclosive notification describing relevance and pricing; a trust boundary enforced by technical and contractual controls preventing disclosure of protected content prior to authorized payment; a transaction processing layer that processes payment from the user to the copyright holder; and a content delivery module that delivers the authorized portion within the research session.

The invention discloses a learning course user intelligent supervision method and system based on image recognition, and relates to the technical field of learning state supervision, and the method comprises the steps: collecting user academic record level data, user learning image data and user learning range course data; based on the user learning image data and the micro-expression type image data, micro-expression type analysis processing during user learning is carried out, and user micro-expression type change feature data is generated; according to the learning course user intelligent supervision method and system based on image recognition, the learning efficiency of the user is judged by collecting the micro-expression data of the user and analyzing the micro-expression change characteristics of the user in the learning process, the learning efficiency of each user student in the learning course can be known conveniently, and when the learning efficiency of the user is reduced, the learning efficiency of the user is improved. The method for adjusting the learning state is recommended to the user to ensure that the user learns in a good learning state, and a more suitable course is recommended to the user when the efficiency of learning the course by the user is extremely low.

An approach is provided for generative artificial intelligence (GenAI)-enabled user research using synthetic personas. Data for user research for a product or service is collected. The data is included in categories of individual profile data for users, product feature data, company metadata, and historical data. The collected data is evaluated using a neural network. Scores for types of data in each category are determined based on the evaluated data. An overall fit score is determined by aggregating the scores. Based on the overall fit score, a recommendation of areas of focus is generated. The areas of focus are associated with the product or service and require an evaluation. One or more synthetic personas are generated based on the individual profile data. The evaluation of the areas of focus is performed by using the one or more synthetic personas.

A system is provided.SOLUTION: A system comprising: means for a user to input a research theme and purpose; means for a server to collect relevant AI from information sources using a generative data model; means for the server to analyze the information and extract information relevant to the user's research theme; means for the server to generate reports and presentation materials based on the extracted information; and means for the server to deliver the generated materials to the user and provide necessary feedback and corrections.SELECTED DRAWING: Figure 1

The present disclosure is directed to systems and methods of providing systems and methods of autonomously generating summary documents based, at least in part, on a plurality of queries provided by a system user. The systems and methods disclosed herein include processor circuitry to identify a plurality of information sources for a specific topic guided by an ontology with specific concepts and relations. The systems and methods disclosed herein also include processor circuitry to generate user-focused extractive text summarization from each of at least some of the plurality of identified information sources using a plurality of queries supplied by the user / researcher.

The invention discloses a knowledge graph-based research tourism personalized itinerary generation method. The method comprises the steps of S1, constructing a research knowledge graph; s2, setting an education target weight matrix, a time window modulation vector and a path coupling vector in the research knowledge graph; s3, an improved PairRE model is adopted to execute bidirectional vector transformation and element-level combination, and multi-relation vector representation is generated; s4, receiving research and study requirements of the user and generating a user preference vector and a constraint parameter; s5, on the basis of the multi-relation vector and the user preference, performing graph search in the graph structure in combination with traffic and time window constraints, and generating a research activity sequence set; s6, calling an improved PairRE scoring process for each activity sequence, and combining the three types of parameters to generate an itinerary scoring value; and S7, sorting the research activity sequence according to the stroke score values, and outputting a personalized research stroke. According to the invention, unified optimization of education objectives, time limitation and route feasibility is realized.

The invention belongs to the technical field of information recommendation, and discloses an academic paper recommendation method, system and device based on a large model and a medium, comprising: obtaining semantic features of user information, constructing initial research interest, performing rule matching verification and semantic check verification on the initial research interest, and obtaining an academic paper recommendation result; generating final research interests in combination with user feedback after verification is passed; extracting user features related to user interest core semantics in the final research interest; extracting core semantic information related to user research interests in the paper information as paper features; and inputting the user features and the thesis features into an intelligent recommendation model for correlation analysis and scoring to obtain a recommendation score corresponding to the current to-be-recommended thesis. According to the method, multidisciplinary research interests of the user can be accurately captured and integrated, a high-quality recommendation result is generated, and the accuracy, diversity and effectiveness of Chinese academic paper recommendation are remarkably improved.

The present invention discloses a method for speech-driven facial animation simulation based on facial muscle linkage, belonging to the field of artificial intelligence, including the steps of: S1, constructing a PPMF encoder; S2, constructing a decoder based on FDCP to decode the features F provided by the PPMF to obtain facial animations; S3, training the speech-driven 3D face animation framework DCPTalk; S4, model optimization; S5, model quantitative evaluation. The present invention proposes the DCPTalk framework and, based on the linkage characteristics of facial muscle groups, proposes Mouth2Face. The mouth movement has a strong correlation with the speech signal and is easily synthesized with vocal tract dynamics. In order to further enhance the details of facial movements, a Refine Decoder is used to simulate the skin deformation on the surface to refine the facial animations. The inherent body characteristics and the body characteristics related to the facial muscle group movements are embedded into Mouth2Face to construct a personalized facial muscle control system, and at the same time, the external drive signal is modulated by the speaking style. Qualitative and quantitative experiments and user studies show that DCPTalk is superior to the existing state-of-the-art methods. P The mouth movement has a strong correlation with the speech signal and is easily synthesized with vocal tract dynamics. In order to further enhance the details of facial movements, a Refine Decoder is used to simulate the skin deformation on the surface to refine the facial animations. The inherent body characteristics and the body characteristics related to the facial muscle group movements are embedded into Mouth2Face to construct a personalized facial muscle control system, and at the same time, the external drive signal is modulated by the speaking style. Qualitative and quantitative experiments and user studies show that DCPTalk is superior to the existing state-of-the-art methods.

Systems and methods for interpretable sequence and time-series data modeling. A novel interpretable and manipulable deep sequence modeling technique is disclosed. This technique combines prototype learning and RNNs to achieve both interpretability and high accuracy. Experiments and case studies on various real-world sequence prediction / classification tasks demonstrate that the model is not only as accurate as other state-of-the-art machine learning techniques, but also significantly more interpretable. Furthermore, large-scale user studies on Amazon Mechanical Turk demonstrate that for familiar domains, such as sentiment analysis of text, the model is able to select high-quality prototypes that well match human knowledge for prediction and interpretation. Moreover, the model achieves better interpretability without performance loss by updating the prototypes by incorporating feedback from user studies, demonstrating the benefits of involving human-machine loops for interpretable machine learning.