US 2025/0094429 A1Published application

Intelligent grouping of messages into conversation documents for ranking and retrieval

AssigneeGlean Technologies, Inc.

InventorsKrishnan Raghavan, Piyush Prahladka, Hemant Kumar Chodipilli, Prashant Kumar, Yash Chandnani, Debarghya Das

Life of this patent

Estimating the term…

Loading patent…

Abstract

Methods and apparatuses for identifying groups of electronic messages, generating conversation documents using the groups of electronic messages, and indexing the conversation documents to improve search ranking and retrieval for content contained within the electronic messages are described. In some cases, understanding the contents of a group of electronic messages may require context from outside the group of electronic messages, such as context provided by electronic messages outside of the group of electronic messages or context provided by electronic documents linked to by messages of the group of electronic messages. The identification of a group of electronic messages includes detecting a conversation boundary that separates a first set of messages from a second set of messages, which may be determined using machine learning approaches or various heuristics.

Claims20

Dependent claims

A system, comprising:

a hardware storage device configured to store a search index;
and
one or more processors in communication with the storage device configured to:
acquire a first message, the first message is assigned to a first group of messages;
acquire a second message;
determine a first time that the first message was posted to a chat channel and a second time that the second message was posted to the chat channel;
determine a maximum number of messages per grouping based on a number of users who have posted messages to the chat channel within a threshold period of time;
detect that the second message should be assigned to a second group of messages different from the first group of messages based on the first time that the first message was posted to the chat channel, the second time that the second message was posted to the chat channel, and the maximum number of messages per grouping;
identify an electronic document referenced by the second group of messages;
generate a summary of the electronic document using a generative model;
generate a second conversation document corresponding with the second group of messages that includes the summary of the electronic document;
store the second conversation document within the search index;
acquire a search query;
identify a set of relevant documents from the search index using the search query, the set of relevant documents includes the second conversation document;
rank the set of relevant documents;
and
display at least a subset of the set of relevant documents based on the ranking of the set of relevant documents.

14 more elements

A method for operating a search system, comprising:

receiving a first message that is assigned to a first group of messages;
receiving a second message;
determining a first time that the first message was posted to a chat channel;
determining a second time that the second message was posted to the chat channel;
determining a maximum number of messages per grouping based on a number of users who have posted messages to the chat channel;
detecting that the second message should be assigned to a second group of messages different from the first group of messages based on the first time that the first message was posted to the chat channel, the second time that the second message was posted to the chat channel, and the maximum number of messages per grouping;
identifying an electronic document referenced by the second group of messages;
generating a summary of the electronic document using a generative model;
generating a second conversation document corresponding with the second group of messages that includes the summary of the electronic document;
storing the second conversation document within a search index;
acquiring a search query;
identifying a set of relevant documents from the search index using the search query, the set of relevant documents includes the second conversation document;
and
displaying at least a subset of the set of relevant documents.

11 more elements

Dependencies are inferred from the claim text.