4 results about "Lexical set" patented technology

The application provides a text review subject sentiment analysis method, device and equipment, which comprises the following steps: preprocessing obtained review data about a museum to obtain a vocabulary set; performing importance sorting on the vocabulary in the vocabulary set based on a TF-IDF algorithm; screening first and second emotional seed words based on the sorting result; selecting target words with a required similarity to the emotional seed words from the vocabulary set based on a SO-PPMI algorithm; forming an emotional dictionary based on the target words and a general emotional dictionary; determining the weight of each word based on the similarity between each word and each emotional seed word recorded in the emotional dictionary; constructing a WLDA model based on the weight and an LDA model, and determining the subject words corresponding to each subject based on the model; and determining the emotional tendency of each subject based on the subject, the subject words and the emotional dictionary. The method can quickly and accurately perform sentiment analysis on museum reviews.

The application discloses a demand similarity determination method and device, electronic equipment and a computer storage medium. The industry characteristic data of a first demand and the industry characteristic data of a second demand are compared to determine a vocabulary set. The target matching result of the first demand and the second demand is determined according to the vocabulary set, wherein the target matching result is used to indicate the similarity of the first demand and the second demand. Therefore, the similarity between the new demand and the plurality of preset demands in the database can be identified, and the repeated development, function conflict and the like are avoided, and the development efficiency is improved.

The application discloses a semantic generation and cognitive evolution control system based on a familiar word pool constraint. The system comprises a familiar word pool construction unit, which is used for acquiring and maintaining a set of mastered words of a user, constructing a dynamically updatable familiar word pool, and performing hierarchical management and state recording on the familiar word pool; a restricted expression space construction unit, which is used for constructing a structured restricted expression space based on the familiar word pool, so as to limit the range of words and the range of expression structures that can be used in a semantic generation process; a semantic structure analysis unit, which is used for performing semantic analysis on input text, and generating a target semantic structure representation; and a semantic generation unit, which is used for scheduling a semantic generation process in the restricted expression space, and imposing constraint control on a generation path to realize controlled expression of the target semantic structure.

A method and system for accelerating inference in a long-context generative model are disclosed. In the pre-filling inference stage of the generative model, an attention increment metric is calculated for the input lexical at a preset stop-calculation start layer, and an active lexical set is determined according to a preset retention ratio. The active lexical set is reused in the subsequent calculation of the network block, that is, only the lexical subsequences corresponding to the active lexical set are used to perform network block calculation, further calculation of inactive lexical is stopped, and its hidden representation is kept as the last update result, thereby reducing the overall computational load of the pre-filling stage.