公开(公告)号：US11902221B2

公开(公告)日：2024-02-13

申请号：US17037554

申请日：2020-09-29

Applicant: Salesforce, Inc.

Inventor： Xinyi Yang ,  Tian Xie ,  Caiming Xiong ,  Wenhao Liu ,  Huan Wang ,  Kazuma Hashimoto ,  Jin Qu ,  Feihong Wu ,  Yingbo Zhou

IPC: G06F40/35 ,  H04L51/02 ,  G06N3/04 ,  G06F18/214

CPC classification number: H04L51/02 ,  G06F18/2148 ,  G06F40/35 ,  G06N3/04

Abstract: A conversation engine performs conversations with users using chatbots customized for performing a set of tasks that can be performed using an online system. The conversation engine loads a chatbot configuration that specifies the behavior of a chatbot including the tasks that can be performed by the chatbot, the types of entities relevant to each task, and so on. The conversation may be voice based and use natural language. The conversation engine may load different chatbot configurations to implement different chatbots. The conversation engine receives a conversation engine configuration that specifies the behavior of the conversation engine across chatbots. The system may be a multi-tenant system that allows customization of the chatbots for each tenant.

公开(公告)号：US20230419027A1

公开(公告)日：2023-12-28

申请号：US18060411

申请日：2022-11-30

Applicant: Salesforce, Inc.

Inventor： Bo Pang ,  Semih Yavuz ,  Caiming Xiong ,  Yingbo Zhou

IPC: G06F40/20 ,  G06N3/08

CPC classification number: G06F40/20 ,  G06N3/084

Abstract: Embodiments described herein provide a prompt-based transfer learning method that employs shared latent space prompt tuning). Specifically, a shared latent space is assumed, among all source and target tasks, where each vector in the space captures a basis skill to do a particular task. Given an instance (from either a source task or a target task), it is first encoded into an instance representation vector and then queries the latent space, which yields a skill vector for this instance. This vector modulates a frozen model, via soft prompts which are a simple prompt transformation (the prompt generator in FIG. 3) of the basis skill vector, to generate an answer for the instance. The latent space and prompt transformation are learned end-to-end in upstream pre-training on source tasks.

公开(公告)号：US12079602B2

公开(公告)日：2024-09-03

申请号：US17889998

申请日：2022-08-17

Applicant: Salesforce, Inc.

Inventor： Hiroaki Hayashi ,  Yingbo Zhou ,  Bo Pang ,  Erik Nijkamp

IPC: G06F8/35 ,  G06F8/10 ,  G06N20/00

CPC classification number: G06F8/35 ,  G06F8/10 ,  G06N20/00

Abstract: Embodiments described herein provide a program synthesis framework that generates code programs through a multi-turn conversation between a user and a system. Specifically, the description to solve a target problem is factorized into multiple steps, each of which includes a description in natural language (prompt) to be input into the generation model as a user utterance. The model in turn synthesizes functionally correct subprograms following the current user utterance and considering descriptions and synthesized subprograms at previous steps. The subprograms generated at the multiple steps are then combined to form an output of program in response to the target problem.

公开(公告)号：US20240118937A1

公开(公告)日：2024-04-11

申请号：US17962301

申请日：2022-10-07

Applicant: Salesforce, Inc.

Inventor： Bo Zong ,  Huan Wang ,  Tian Lan ,  Ran Yao ,  Tony Wong ,  Daeki Cho ,  Caiming Xiong ,  Silvio Savarese ,  Yingbo Zhou

IPC: G06F9/50 ,  G06F9/46

CPC classification number: G06F9/505 ,  G06F9/468 ,  G06F9/5072

Abstract: Embodiments herein relate to prediction, based on previous usage of a cloud-based computing resource by a user of one or more users of the cloud-based computing resource, future usage of the cloud-based computing resource. Based on the predicted future usage, embodiments relate to identifying that throttling of access to the cloud-based computing resource is to occur, and notifying the user of the throttling. Other embodiments may be described and/or claimed.

公开(公告)号：US20230186916A1

公开(公告)日：2023-06-15

申请号：US18108434

申请日：2023-02-10

Applicant: Salesforce, Inc.

Inventor： Xinyi Yang ,  Tian Xie ,  Caiming Xiong ,  Wenhao Liu ,  Huan Wang ,  Kazuma Hashimoto ,  Yingbo Zhou ,  Xugang Ye ,  Jin Qu ,  Feihong Wu

IPC: G10L15/22 ,  G10L15/16 ,  G10L15/30 ,  G10L15/26

CPC classification number: G10L15/22 ,  G10L15/16 ,  G10L15/30 ,  G10L15/26 ,  G10L2015/223

Abstract: A conversation engine performs conversations with users using chatbots customized for performing a set of tasks that can be performed using an online system. The conversation engine loads a chatbot configuration that specifies the behavior of a chatbot including the tasks that can be performed by the chatbot, the types of entities relevant to each task, and so on. The conversation may be voice based and use natural language. The conversation engine may load different chatbot configurations to implement different chatbots. The conversation engine receives a conversation engine configuration that specifies the behavior of the conversation engine across chatbots. The system may be a multi-tenant system that allows customization of the chatbots for each tenant.

公开(公告)号：US20250005276A1

公开(公告)日：2025-01-02

申请号：US18498886

申请日：2023-10-31

Applicant: Salesforce, Inc.

Inventor： Meghana Bhat ,  Semih Yavuz ,  Rui Meng ,  Yingbo Zhou

IPC: G06F40/20

Abstract: Embodiments described herein provide a system for selecting a neural network based natural language processing (NLP) model for building a custom artificial intelligence (AI) stack for a user. The system includes a communication interface that established connections to one or more external servers hosting one or more neural network based NLP models, a memory; and a processor executing operations including: selecting a source document based on a custom NLP application; generating, by a first language model, a summary of the source document; generating, by a second language model, one or more questions based on at least one of the summary or the source document; transmitting, via the communication interface, the one or more questions to the one or more neural network based NLP models; receiving, via the communication interface, one or more answers generated by the one or more neural network based NLP models.

公开(公告)号：US20240428044A1

公开(公告)日：2024-12-26

申请号：US18497395

申请日：2023-10-30

Applicant: Salesforce, Inc.

Inventor： Ye Liu ,  Semih Yavuz ,  Meghana Moorthy Bhat ,  Rui Meng ,  Shafiq Joty ,  Caiming Xiong ,  Yingbo Zhou

IPC: G06N3/006 ,  G06N3/0455

Abstract: Embodiments described herein provide a framework that integrates a retriever model and the LLM to feed retrieved passages to an LLM to generate an answer conditioned on the retrieved passages in response to a query. For example, in one embodiment, a single-round approach is implemented, which involves directly transmitting the retrieved passages to the LLM. For another example, a multi-round methodology is implemented, which involves initially presenting the retrieved passages to the Language Model, collecting its responses, and then adjusting our interaction with the Language Model based on this acquired feedback.

公开(公告)号：US12105744B2

公开(公告)日：2024-10-01

申请号：US18059691

申请日：2022-11-29

Applicant: Salesforce, Inc.

Inventor： Ye Liu ,  Semih Yavuz ,  Yingbo Zhou ,  Rui Meng

IPC: G06F16/00 ,  G06F16/33 ,  G06F16/332 ,  G06F40/205 ,  G06F40/295 ,  G06F40/30 ,  G06F40/40

CPC classification number: G06F16/3329 ,  G06F16/3344 ,  G06F40/205 ,  G06F40/295 ,  G06F40/30 ,  G06F40/40

Abstract: Embodiments described herein provide a semantic parsing framework which may be referred to as Uni-Parser. The Uni-Parser framework may be applied to question answering on both knowledge bases and databases. The three main stages of the Uni-Parser framework are enumeration, ranking, and generation. At the enumeration stage, primitives are enumerated based on matching the question to the data structure. After enumerating primitives, the Uni-Parser framework may rank the primitives used a trained ranker model. The top ranked primitives may then be used as inputs to a generator which is a learned sequence to sequence model which produces a logical form.

公开(公告)号：US11941346B2

公开(公告)日：2024-03-26

申请号：US17589650

申请日：2022-01-31

Applicant: Salesforce, Inc.

Inventor： Bo Pang ,  Erik Nijkamp ,  Yingbo Zhou ,  Caiming Xiong

IPC: G06F40/166 ,  G06F40/284

CPC classification number: G06F40/166 ,  G06F40/284

Abstract: Embodiments described herein provide methods and systems for effectively and efficiently summarizing long documents. A transformer is provided with bottom-up and top-down inference combined to effectively capture long-range dependency. In the bottom-up inference, each token only attends to nearby tokens within a window of a specified size. In the top-down inference, full self-attention is given using units with coarser granularity. The bottom-up-inferred token representations are then updated with the top-down representations, which is achieved with cross-attention between the top and token levels. Multiple levels of top-down representations with increasingly coarser granularity can be used if documents are extremely long.

公开(公告)号：US20230280985A1

公开(公告)日：2023-09-07

申请号：US17889998

申请日：2022-08-17

Applicant: Salesforce, Inc.

Inventor： Hiroaki Hayashi ,  Yingbo Zhou ,  Bo Pang ,  Erik Nijkamp

IPC: G06F8/35 ,  G06F8/10 ,  G06N20/00

CPC classification number: G06F8/35 ,  G06F8/10 ,  G06N20/00

Abstract: Embodiments described herein provide a program synthesis framework that generates code programs through a multi-turn conversation between a user and a system. Specifically, the description to solve a target problem is factorized into multiple steps, each of which includes a description in natural language (prompt) to be input into the generation model as a user utterance. The model in turn synthesizes functionally correct subprograms following the current user utterance and considering descriptions and synthesized subprograms at previous steps. The subprograms generated at the multiple steps are then combined to form an output of program in response to the target problem.