4 results about "Semantic property" patented technology

The application provides a privacy record linkage method and system for semantic heterogeneous data, involving multiple linkage participants and a linkage unit. Firstly, the attribute is divided into strong and weak categories by calculating the average difference of semantic similarity of data attribute characters. For weak semantic attributes, an improved CLK-CRBF counter Bloom filter is used to generate integer encoding. For strong semantic attributes, a fine-tuning embedding model is used to generate a dense vector. Then, the integer encoding is fused as a structured disturbance with the dense vector to form a semantic-aware encoding vector and sent to the linkage unit. The linkage unit uses locally sensitive hashing in an adaptive hybrid encoding space to block, generate candidate record pairs in the group, and calculate the similarity. Finally, the matching result is determined according to the negotiated threshold. The method significantly improves the linkage effect of semantic heterogeneous data while ensuring privacy, and the greater the data difference ratio, the more obvious the advantage.

The application discloses a large model text generation method based on semantic adaptation and dynamic hierarchical comparison, and belongs to the technical field of artificial intelligence and natural language processing, which can at least partially solve the problems of lack of semantic perception ability, fixed hierarchical selection strategy and waste of computing resources in the prior art contrast decoding technology, and introduces a semantic routing module in the decoding process.The method obtains the hidden state of different levels of the model and the final layer output distribution when the model reasons and generates each word element; the semantic routing module is used for semantic attribute determination and uncertainty calculation on the current generation state; according to the determination result, a strategy is dynamically selected from a preset decoding strategy set to calculate the final output value; and the final output value is normalized and combined with a sampling algorithm to generate a word element.The application realizes dynamic balance of factuality and fluency, suppresses hallucinations and reduces reasoning delay.

The application discloses a kind of based on knowledge graph and big language model's examination point accurate diagnosis method and system, belong to intelligent education technical field, this method includes: the subject knowledge graph comprising knowledge point and inheritance, composition, precursor relationship is constructed;Symbolic analysis and textbook progress constraint are carried out to input question, and preprocessing information is obtained;Parallelly execute full-text search, semantic attribute matching, fuzzy matching and, recall candidate knowledge point;Knowledge structured extension is carried out by parent class backtracking, subclass expansion;The application is coupled by the structured constraint of knowledge graph and the semantic understanding depth of big language model, effectively solve the term of general big model in education scene is not standard, implicit examination point is difficult to dig and illusion problem, accurate, interpretable examination point diagnosis is realized, and reliable technical support is provided for intelligent tutoring and individualized learning.