Systems and Methods for Short Text Identification

    公开(公告)号:US20210232766A1

    公开(公告)日:2021-07-29

    申请号:US16773697

    申请日:2020-01-27

    Abstract: A system for short text identification can determine a plurality of topics and a representative noun that identifies each of the topics in a data repository. The system can determine a co-occurrence matrix for the training words stored in the corpus and determine a word vector embedding for each of the training words in the corpus to relate each of the training words in the corpus to other ones of the training words in the corpus in an n-dimensional vector space. The system can determine word tokens for words in short text in documents in the data repository that is separate and distinct from the corpus and determine sentence vectors for short text based on the word vectors in each short text and determine a plurality of topics in the documents based on clustering of sentence vectors, wherein the plurality of topics indicates topics that are predominant in the documents in the data repository.

    DYNAMIC MINIMUM PRESENTATION FOR OPTIMIZED FRESH ITEM PRODUCTION

    公开(公告)号:US20250139648A1

    公开(公告)日:2025-05-01

    申请号:US18498624

    申请日:2023-10-31

    Abstract: Examples provide for generating dynamic minimum presentation (MP) values for optimizing fresh item production while reducing system resource usage. An MP engine calculates a monetary level impact of overproduction and underproduction of a fresh item using production-related data, including a shelf life of the fresh item and cost of production. The calculated monetary level impact includes predicted monetary loss from lost sales due to an item going out-of-stock and/or monetary loss from unsold instances of the fresh item where too many instances of the fresh item are prepared. The dynamic MP value is generated based on dynamic data, the item attribute data, and the predicted monetary loss. The dynamic MP value is used to create a production plan recommendation customized at a store-item level for a selected date, thereby enabling optimization of safety stock while minimizing system resource usage consumed in generating MP predictions for fresh items.

    Systems and methods for short text identification

    公开(公告)号:US11347944B2

    公开(公告)日:2022-05-31

    申请号:US16773697

    申请日:2020-01-27

    Abstract: A system for short text identification can determine a plurality of topics and a representative noun that identifies each of the topics in a data repository. The system can determine a co-occurrence matrix for the training words stored in the corpus and determine a word vector embedding for each of the training words in the corpus to relate each of the training words in the corpus to other ones of the training words in the corpus in an n-dimensional vector space. The system can determine word tokens for words in short text in documents in the data repository that is separate and distinct from the corpus and determine sentence vectors for short text based on the word vectors in each short text and determine a plurality of topics in the documents based on clustering of sentence vectors, wherein the plurality of topics indicates topics that are predominant in the documents in the data repository.

Patent Agency Ranking