Patents
Literature
Patsnap Copilot is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Patsnap Copilot

48results about How to "Accurate answer" patented technology

Telephone robot speech recognition result correction method based on deep learning

The invention discloses a telephone robot speech recognition result correction method based on deep learning. The correction method comprises the following steps: obtaining a pinyin sentence text dataset Sp and a correct sentence text sample set Sc based on a historical speech data set; establishing a correction model by adopting deep learning; establishing the correction model comprises an encoder part construction based on a multi-head attention model and a feedforward neural network and a decoder part construction based on two stacked multi-head attention models and a feedforward neural network; training the established correction model based on the correct sentence text sample set Sc; and inputting a speech recognition result to be corrected into the trained correction model after being processed by a vectorization procedure to obtain a corrected text. The telephone robot speech recognition result correction method based on deep learning fully utilizes historical recording data resources, trains a speech recognition result correction model, and efficiently recognizes and corrects the speech in an unquiet environment and under the conditions of low speech recognition precisionsuch as a plurality of different speaking modes, pronunciation accuracy, sound receiving capability and the like.
Owner:成都富王科技有限公司

Consultation data recommendation method and device, computer equipment and storage medium

The invention relates to a consultation data recommendation method and device, computer equipment and a storage medium. The method comprises a step of acquiring a current question to be answered and performing word segmentation, extracting feature words according to a word segmentation result, and obtaining a first feature word set corresponding to the current question to be answered, a step of acquiring a second feature word set corresponding to each index node in a pre-established index, a step of calculating a cosine similarity between the first feature word set and the second feature wordset, sorting each index node according to a first similarity calculation result to select a preset number of index nodes as target index nodes, and obtaining a target index node set, a step of obtaining a question and answer pair corresponding to each target index node from an inquiry database, and a step of calculating a second similarity between the current question to be answered and a questioncorresponding to each question and answer pair, sorting each question and answer pair according to a second similarity calculation result to select a target question and answer pair, and recommendingconsultation data according to the selected target question and answer pair.
Owner:PING AN TECH (SHENZHEN) CO LTD

Personalized precise medical question-answering system based on data and knowledge

The invention belongs to the field of medical health and artificial intelligence, and particularly relates to a personalized precise medical question answering system based on data and knowledge. The invention aims at solving the problems that in the prior art, pertinence and real-time performance are not achieved, the data utilization rate is low, and user problems cannot be efficiently and accurately understood, and a problem that real-time deep-level accurate medical question answering cannot be realized for individuals. The system comprises a personal health data module which obtains personal health data of a user; a user question understanding module which sequentially carries out word, syntactic and semantic analysis on user questions after preprocessing the user questions; an efficient knowledge graph module which performs knowledge extraction, knowledge fusion, knowledge storage and knowledge calculation on the knowledge base to construct an efficient knowledge graph; and an intelligent medical service module which performs user health data management and health monitoring through semantic matching and knowledge reasoning, performs online hospital guide on problem information, assists the decision making and generates response information. The method has the advantages of pertinence, real-time performance, high data utilization rate and high accuracy.
Owner:INST OF AUTOMATION CHINESE ACAD OF SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products