公开(公告)号：US20250117412A1

公开(公告)日：2025-04-10

申请号：US18731086

申请日：2024-05-31

Applicant: Box, Inc.

Inventor： Sesh JALAGAM ,  Denis GRENADER ,  Benjamin John KUS

IPC: G06F16/332 ,  G06F16/335 ,  G06F16/383

Abstract: Methods, systems, and computer program products for collaboration systems. A method for identifying selected portions of a set of content objects for use in generating a large language model (LLM) prompt comprises: identifying a content management system (CMS) wherein collaboration activities occur over time and over content objects maintained in the CMS, and wherein the CMS maintains a historical record of occurrences of the collaborator activities over the content objects. Upon receiving a natural language query from a CMS collaborator, reducing a larger corpus of content objects to a smaller corpus of context passages that are used in an LLM prompt. The smaller corpus of passages is formed using a two-phase reduction scheme whereby firstly, selected constituents from the larger corpus of content objects are identified based on CMS metadata; and then, rather than considering the larger corpus, instead considering only the selected constituents when generating the LLM prompt.

公开(公告)号：US20240073465A1

公开(公告)日：2024-02-29

申请号：US17823938

申请日：2022-08-31

Applicant: Box, Inc.

Inventor： James Francis LAVINE ,  Benjamin John KUS

IPC: H04N21/25 ,  H04N21/258

CPC classification number: H04N21/252 ,  H04N21/25891

Abstract: A recommendation system integrated with a content management system (CMS). The CMS stores instances of shared content objects and coordinates user interactions by and between a plurality of CMS users. Shared content objects are divided into a plurality of portions, after which any user interactions over the various portions of the content object are observed and analyzed. User interest inferences are drawn from analysis of the observed user interactions taken user over respective particular portions of the content object. Based on the inferred user interests, fine-grained recommendations are formed and propagated. Some fine-grained recommendations refer to further content objects (e.g., content objects of different types). Some fine-grained recommendations are propagated to other CMS users (e.g., to a plurality of CMS users that are related in some way). The fine-grained recommendations refer to one or more specific portions of a content object as well as to the content object itself.