公开(公告)号：US20240135114A1

公开(公告)日：2024-04-25

申请号：US18161311

申请日：2023-01-30

Applicant: Salesforce, Inc.

Inventor： Nathan William Krapf ,  Michael Justin Smathers ,  Nathan Drew Nichols ,  Matthew Lloyd Trahan

IPC: G06F40/56 ,  G06F40/30 ,  H04L67/50 ,  H04L67/55

CPC classification number: G06F40/56 ,  G06F40/30 ,  H04L67/535 ,  H04L67/55

Abstract: Systems and methods are disclosed for integrating NLG-based natural language narrative story generation with story sharing. A processor can (1) generate a plurality of natural language narrative stories based on a plurality of semantic source models for the natural language narrative stories, (2) analyze the semantic source models to determine a plurality of users to whom the natural language narrative stories that are generated from the analyzed semantic source models are to be shared, and (3) share the generated natural language narrative stories with their determined users. In this fashion, stories can be posted to user-customized newsfeeds in a manner that can more reliably capture stories that are of interest to the users.

公开(公告)号：US11989659B2

公开(公告)日：2024-05-21

申请号：US18061571

申请日：2022-12-05

Applicant: Salesforce, Inc.

Inventor： Nathan Nichols ,  Michael Justin Smathers ,  Lawrence Birnbaum ,  Kristian Hammond ,  Lawrence E. Adams

IPC: G06F40/56 ,  G06N5/02

CPC classification number: G06N5/02 ,  G06F40/56

Abstract: Artificial intelligence methods and systems for triggering the generation of narratives are disclosed. Specific embodiments relate to real-time evaluation and automated generation of narrative stories based on received data. For example, data can be tested against data representative of a plurality of story angles to determine whether a narrative story incorporating one or more such story angles is to be automatically generated.

公开(公告)号：US11989519B2

公开(公告)日：2024-05-21

申请号：US16916248

申请日：2020-06-30

Applicant: Salesforce, Inc.

Inventor： Daniel Joseph Platt ,  Nathan D. Nichols ,  Michael Justin Smathers ,  Jared Lorince

IPC: G06F40/20 ,  G06F16/33 ,  G06F18/214 ,  G06F40/205 ,  G06F40/211 ,  G06F40/253 ,  G06F40/295 ,  G06F40/30 ,  G06F40/56 ,  G06N20/00 ,  G06F40/268 ,  G06F40/279 ,  G10L15/06 ,  G10L15/18 ,  G10L15/22

CPC classification number: G06F40/30 ,  G06F16/3344 ,  G06F18/214 ,  G06F40/205 ,  G06F40/211 ,  G06F40/253 ,  G06F40/295 ,  G06N20/00 ,  G06F40/268 ,  G06F40/279 ,  G06F40/56 ,  G10L15/063 ,  G10L15/1822 ,  G10L15/22

Abstract: Disclosed herein is computer technology that applies natural language processing (NLP) techniques to training data to generate information used to train a natural language generation (NLG) system to produce output that stylistically resembles the training data. In this fashion, the NLG system can be readily trained with training data supplied by a user so that the NLG system is adapted to produce output that stylistically resembles such training data. In an example, an NLP system detects a plurality of linguistic features in the training data. These detected linguistic features are then aggregated into a specification data structure that is arranged for training the NLG system to produce natural language output that stylistically resembles the training data. Parameters in the specification data structure can be linked to objects in an ontology used by the NLG system to facilitate the training of the NLG system based on the detected linguistic features.