公开(公告)号：US20250094734A1

公开(公告)日：2025-03-20

申请号：US18885501

申请日：2024-09-13

Applicant: Oracle International Corporation

Inventor： Vanshika Sridharan ,  Xinwei Zhang ,  Steven Martijn Davelaar ,  Neerja Bhatt ,  Xin Xu

IPC: G06F40/40 ,  G06F9/451 ,  G06N3/0475

Abstract: Techniques for using a LLM to detect OOS and OOD utterances. In one aspect, a method includes routing an utterance to a skill bot. The skill bot is configured to execute an action for completing a task associated with the utterance, and a workflow associated with the action includes a GenAI component state configured to facilitate completion of at least part of the task. The method further includes inputting a prompt into a GenAI model for processing. The prompt includes the utterance and scope-related elements that teach the GenAI model to output an invalid input variable when the utterance is OOS or OOD. When the GenAI model determines the utterance is OOS or OOD as part of the processing, the response is generated to include the invalid input variable, and the GenAI component state is caused to transition to a different state or workflow based on the response.

公开(公告)号：US20250094733A1

公开(公告)日：2025-03-20

申请号：US18798049

申请日：2024-08-08

Applicant: Oracle International Corporation

Inventor： Xin Xu ,  Vishal Vishnoi ,  Srinivasa Phani Kumar Gadde ,  Ying Xu ,  Diego Andres Cornejo Barra ,  Raman Grover ,  Stephen Andrew McRitchie

IPC: G06F40/40

Abstract: Techniques are disclosed herein for configuring agents for use by digital assistants that use generative artificial intelligence. An agent may be in the form of a container that is configured to have one or more actions that can be executed by a digital assistant. The agent may be configured by initially defining specification parameters for the agent based on natural language input from a user. Configuration information for the one or more assets can be imported into the agent. One or more actions may then be defined for the agent based on importing of the configuration information, the natural language input from the user, or both. A specification document can be generated for the agent and can comprise various description metadata, such as agent, asset, or action metadata, or combinations thereof. The specification document may be stored in a data store that is communicatively coupled to the digital assistant.

公开(公告)号：US20250094717A1

公开(公告)日：2025-03-20

申请号：US18885356

申请日：2024-09-13

Applicant: Oracle International Corporation

Inventor： Aashna Devang Kanuga ,  Yingqiong Shi ,  Charles Woodrow Dickstein ,  Xin Xu ,  King-Hwa Lee

IPC: G06F40/289 ,  G06F16/33 ,  G06F40/205 ,  G06F40/40

Abstract: Techniques are disclosed for returning references associated with an answer to a query. The techniques include accessing a text portion and identifying a plurality of sentences in the text portion. Each of the sentences is embedded to generate a respective plurality of text sentence embeddings. The text portion or a derivative thereof and a query are provided to a language model and a response to the query based on the text portion is received from the language model. A plurality of sentences are identified in the response. The plurality of sentences in the response is embedded to generate a plurality of response embeddings. The response embeddings are compared to the sentence embeddings to generate a similarity score for each sentence embedding-response embedding pair. Based on the similarity scores, an indication of a subset of the plurality of sentences is output with the response to the query.

公开(公告)号：US20250094455A1

公开(公告)日：2025-03-20

申请号：US18885347

申请日：2024-09-13

Applicant: Oracle International Corporation

Inventor： Umanga Bista ,  Ying Xu ,  Aashna Devang Kanuga ,  Xin Xu ,  Vishal Vishnoi ,  Charles Woodrow Dickstein

IPC: G06F16/332 ,  G06F16/33

Abstract: Techniques are disclosed herein for contextual query rewriting. The techniques include inputting a first user utterance and a conversation history to a first language model. The first language model identifies an ambiguity in the first user utterance and one or more terms in the conversation history to resolve the ambiguity, modifies the first user utterance to include the one or more terms identified to resolve the ambiguity to generate a modified utterance, and outputs the modified utterance. The computing system provides the modified utterance as input to a second language model. The second language model performs a natural language processing task based on the input modified utterance and outputs a result. The computing system outputs a response to the first user utterance based on the result.

公开(公告)号：US12249314B2

公开(公告)日：2025-03-11

申请号：US18136745

申请日：2023-04-19

Applicant: Oracle International Corporation

Inventor： Vishal Vishnoi ,  Xin Xu ,  Srinivasa Phani Kumar Gadde ,  Fen Wang ,  Muruganantham Chinnananchi ,  Manish Parekh ,  Stephen Andrew McRitchie ,  Jae Min John ,  Crystal C. Pan ,  Gautam Singaraju ,  Saba Amsalu Teserra

IPC: G06F17/00 ,  G06N5/04 ,  G06N20/00 ,  G10L13/08

Abstract: Techniques are described for invoking and switching between chatbots of a chatbot system. In some embodiments, the chatbot system is capable of routing an utterance received while a user is already interacting with a first chatbot in the chatbot system. For instance, the chatbot system may identify a second chatbot based on determining that (i) such an utterance is an invalid input to the first chatbot or (ii) that the first chatbot is attempting to route the utterance to a destination associated with the first chatbot. Identifying the second chatbot can involve computing, using a predictive model, separate confidence scores for the first chatbot and the second chatbot, and then determining that a confidence score for the second chatbot satisfies one or more confidence score thresholds. The utterance is then routed to the second chatbot based on the identifying of the second chatbot.

公开(公告)号：US20240086767A1

公开(公告)日：2024-03-14

申请号：US18295018

申请日：2023-04-03

Applicant: Oracle International Corporation

Inventor： Ying Xu ,  Vladislav Blinov ,  Ahmed Ataallah Ataallah Abobakr ,  Mark Edward Johnson ,  Thanh Long Duong ,  Srinivasa Phani Kumar Gadde ,  Vishal Vishnoi ,  Xin Xu ,  Elias Luqman Jalaluddin ,  Umanga Bista

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: Techniques are disclosed herein for continuous hyperparameter tuning with automatic domain weight adjustment based on periodic performance checkpoints. In one aspect, a method is provided that includes initializing a machine learning algorithm with a set of hyperparameter values and obtaining a hyperparameter objective function that is defined at least in part on a plurality of domains of a search space that is associated with the machine learning algorithm. For each trial of a hyperparameter tuning process: running the machine learning algorithm in different domains using the set of hyperparameter values, periodically checking a performance of the machine learning algorithm in the different domains based on the hyperparameter objective function; and continuing hyperparameter tuning with a new set of hyperparameter values after automatically adjusting the domain weights according to a regression status of the different domains. Once the machine learning algorithm has reached convergence, at least one machine learning model is output.

公开(公告)号：US20230419127A1

公开(公告)日：2023-12-28

申请号：US18163235

申请日：2023-02-01

Applicant: Oracle International Corporation

Inventor： Ahmed Ataallah Ataallah Abobakr ,  Shivashankar Subramanian ,  Ying Xu ,  Vladislav Blinov ,  Umanga Bista ,  Tuyen Quang Pham ,  Thanh Long Duong ,  Mark Edward Johnson ,  Elias Luqman Jalaluddin ,  Vanshika Sridharan ,  Xin Xu ,  Srinivasa Phani Kumar Gadde ,  Vishal Vishnoi

IPC: G06N5/022

CPC classification number: G06N5/022

Abstract: Novel techniques are described for negative entity-aware augmentation using a two-stage augmentation to improve the stability of the model to entity value changes for intent prediction. In some embodiments, a method comprises accessing a first set of training data for an intent prediction model, the first set of training data comprising utterances and intent labels; applying one or more negative entity-aware data augmentation techniques to the first set of training data, depending on the tuning requirements for hyper-parameters, to result in a second set of training data, where the one or more negative entity-aware data augmentation techniques comprise Keyword Augmentation Technique (“KAT”) plus entity without context technique and KAT plus entity in random context as OOD technique; combining the first set of training data and the second set of training data to generate expanded training data; and training the intent prediction model using the expanded training data.

公开(公告)号：US20230419040A1

公开(公告)日：2023-12-28

申请号：US18163230

申请日：2023-02-01

Applicant: Oracle International Corporation

Inventor： Ahmed Ataallah Ataallah Abobakr ,  Shivashankar Subramanian ,  Ying Xu ,  Vladislav Blinov ,  Umanga Bista ,  Tuyen Quang Pham ,  Thanh Long Duong ,  Mark Edward Johnson ,  Elias Luqman Jalaluddin ,  Vanshika Sridharan ,  Xin Xu ,  Srinivasa Phani Kumar Gadde ,  Vishal Vishnoi

IPC: G06F40/295 ,  G06F40/247 ,  G06N5/04

CPC classification number: G06F40/295 ,  G06F40/247 ,  G06N5/04

Abstract: Novel techniques are described for data augmentation using a two-stage entity-aware augmentation to improve model robustness to entity value changes for intent prediction. In some embodiments, a method comprises accessing a first set of training data for an intent prediction model; applying one or more data augmentation techniques to the first set of training data to result in a second set of training data; applying an additional augmentation technique to augment the second set of training data to create a post-processed augmented training data where the additional augmentation technique comprises replacing at least one or more entity values of the named entities within the second set of training data with random values of same entity type; and combining the first set of training data and the post-processed augmented training data to

公开(公告)号：US20230376700A1

公开(公告)日：2023-11-23

申请号：US18314509

申请日：2023-05-09

Applicant: Oracle International Corporation

Inventor： Umanga Bista ,  Vladislav Blinov ,  Mark Edward Johnson ,  Ahmed Ataallah Ataallah Abobakr ,  Thanh Long Duong ,  Srinivasa Phani Kumar Gadde ,  Vishal Vishnoi ,  Elias Luqman Jalaluddin ,  Xin Xu ,  Shivashankar Subramanian

IPC: G06F40/58 ,  G06F40/35 ,  H04L51/02

CPC classification number: G06F40/58 ,  G06F40/35 ,  H04L51/02 ,  G06F40/205

Abstract: Techniques are provided for generating training data to facilitate fine-tuning embedding models. Training data including anchor utterances is obtained. Positive utterances and negative utterances are generated from the anchor utterances. Tuples including the anchor utterances, the positive utterances, and the negative utterances are formed. Embeddings for the tuples are generated and a pre-trained embedding model is fine-tuned based on the embeddings. The fine-tuned model can be deployed to a system.

公开(公告)号：US20250094725A1

公开(公告)日：2025-03-20

申请号：US18624472

申请日：2024-04-02

Applicant: Oracle International Corporation

Inventor： Vishal Vishnoi ,  Xin Xu ,  Diego Andres Cornejo Barra ,  Ying Xu ,  Yakupitiyage Don Thanuja Samodhve Dharmasiri ,  Aashna Devang Kanuga ,  Srinivasa Phani Kumar Gadde ,  Thanh Long Duong ,  Mark Edward Johnson

IPC: G06F40/35 ,  G06F16/332

Abstract: Techniques are disclosed herein for implementing digital assistants using generative artificial intelligence. An input prompt comprising a natural language utterance and candidate agents and associated actions can be constructed. An execution plan can be generated using a first generative artificial model based on the input prompt. The execution plan can be executed to perform actions included in the execution plan using agents indicated by the execution plan. A response to the natural language utterance can be generated by a second generative artificial intelligence model using one or more outputs from executing the execution plan.