Accenture Global Solutions Limited

Sukryool Kang

Guanglei Xiong

Chung-Sheng Li

Anwitha Paruchuri

Lan Guan

Sujeong Cha

Anupam Anurag Tripathi

Emmanuel Munguia Tapia

Colin Connors

Neeru Narang

Benjamin Nathan Grosof

Jayashree Subrahmonia

Neeraj D Vadhan

Ashish Jain

Thomas Wayne Hancock

Jill Gengelbach-wylie

Surya Raghavendra Vadlamani

Christopher Yen-Chu Chan

Yuan He

Andrew Francis Hickl

Peter Royer Smith, Jr

Wenxian Zhang

Madhura Shivaram

Daniel Garrison

Jingyun Fan

Mohammad Jawad Ghorbani

Kayhan Moharreri

Mingzhu Lu

Kyle Patrick Johnson

Golnaz Ghasemiesfeh

Tsunghan Wu

Bo Zhang

Louise Noreen Barrere

Danielle Moffat

Ivan A Wong

Michael C Petersen

Aaron James Sander

Dennis P Delaney

Neha Wadhwa Dang

Ivan Wong

Mohamed Suhail

Jatinder Singh

Jing Su Brewer

Described herein are systems, methods, devices, and other techniques for comprehensive and automated evaluation of digital images generated from artificial intelligence (AI) models in order to promote accurate representations of real-world content. Prompts are received at the system that are then passed to both a search engine and a generative AI model. Synthesized digital images are obtained from the generative AI model. The top-matching image from the search engine is used as a verification of the ground truth of the synthesized digital images. A realism score is generated for each synthesized digital image that characterizes the accuracy of the synthesized digital image with reference to the verification image. The realism score can be used to assist and expedite the image selection process, as well as serve as input to fine-tune the performance of generative models.

System and method for extracting object information from digital images to evaluate for realism

The present disclosure relates to a system, a method, and a product for using machine learning models to quantify and/or improve trust in conversations. The system includes a non-transitory memory; and a processor in communication with the non-transitory memory. The processor executes the instructions to cause the system to: obtain a set of vocal features and a set of text features for each sample in audio samples; obtain a trust score for each sample; perform a preprocess to obtain a set of input features for each sample; determine a type of machine-learning algorithm for the machine-learning network; tune a set of hyper parameters for the machine-learning network; generate a predicated trust score by the machine-learning network with the sets of input features for each sample; and train the machine-learning network based on the predicated trust score and the trust score for each sample to obtain the training result.

Systems and methods to improve trust in conversations

The present disclosure relates to systems, methods, and products for using machine-learning networks to generate trustworthy audio and face mesh. A system, serving as a digital avatar, generates a trust audio and trust face mesh corresponding to an input text. A method includes generating a set of trust embedding vectors based on a reference audio; generate a text embedding vector based on the input text; generate a conditioned vector based on the set of trust embedding vectors and the text embedding vector; synthesize an audio representation based on the conditioned vector; generate the trust audio based on the synthesized audio representation; obtain a speech feature representation based on the trust audio; obtain an abstract feature vector based on the speech feature representation; and generate positions of vertices based on the abstract feature vector, the positions of vertices being used for generating the trust face mesh.

Systems and methods to automate trust delivery

Methods, systems, and apparatus are provided for generating an image. A personalized text prompt is generated by processing an input embedding using a transformer model followed by a first fully connected neural network. The input embedding comprises a multi-dimensional embedding vector associated with a user profile and a plurality of user items. A scored label set is generated identifying a user's preferences by processing a set of attributes for the plurality of user items using a second fully connected neural network. The image is generated by processing the personalized text prompt and the scored label set using a diffusion model.

Hyper-personalized prompt based content generation

Implementations are directed to receiving a set of tuples, each tuple including an entity and a product from a set of products, for each tuple: generating, by an embedding module, a total latent vector as input to a recommender network, the total latent vector generated based on a structural vector, a textual vector, and a categorical vector, each generated based on a product profile of a respective product and an entity profile of the entity, generating, by a context integration module, a latent context vector based on a context vector representative of a context of the entity, and inputting the total latent vector and the latent context vector to the recommender network, the recommender network being trained by few-shot learning using a multi-task loss function, and generating, by the recommender network, a prediction including a set of recommendations specific to the entity.

Few-shot learning for multi-task recommendation systems

The present disclosure relates to a system, a method, and a product for using deep learning models to quantify and/or improve trust in conversations. The system includes a non-transitory memory storing instructions executable to construct a deep-learning network to quantify trust scores; and a processor in communication with the non-transitory memory. The processor executes the instructions to cause the system to: obtain a trust score for each voice sample in a plurality of audio samples, generate a predicated trust score by the deep-learning network based on each voice sample in the plurality of audio samples, wherein the deep-learning network comprises a plurality of branches and an aggregation network configured to aggregate results from the plurality of branches, and train the deep-learning network based on the predicated trust score and the trust score for each voice sample to obtain a training result.

Systems and methods to improve trust in conversations with deep learning models

Implementations of the present disclosure include receiving a goal, providing a problem-specific knowledge graph that is responsive to at least a portion of the goal, determining a set of events from the problem-specific knowledge graph, processing data representative of events in the set of events through a first machine learning (ML) model to provide a set of event scores, each event score in the set of event scores being associated with a respective event in the set of events, determining a sub-set of events based on the set of event scores, for each event in the sub-set of events, determining at least one action by processing a sequence of actions through a second ML model, and outputting the sub-set of events and a set of actions for execution of at least one action in the set of actions.

Early pattern detection in data for improved enterprise operations

Examples of artificial intelligence-based reasoning explanation are described. In an example implementation, a knowledge model having a plurality of ontologies and a plurality of inferencing rules is generated. Once the knowledge model is generated, based on a real-world problem, a knowledge model from amongst various knowledge models is selected to be used for resolving a real-world problem. The data procured from the real-world problem is clustered and classified into an ontology of the determined knowledge model. Inferencing rules to be used for deconstructing the real-world problem are identified, and a machine reasoning is generated to provide a hypothesis for the problem and an explanation to accompany the hypothesis.

Explainable artificial intelligence

In an example, an ontology analyzer may generate an ontology, based on a claim adjudication request. The claim adjudication request may be processed, based on the ontology to provide an ontology based inference. A rule based analyzer may identify a predefined rule corresponding to the claim adjudication request and process the request, based on the predefined rule. A conflict resolver may resolve a conflict which may occur between the ontology based inference and the rule based inference. When a conflict is detected, a predefined criteria may be selected for resolving the conflict, the predefined criteria comprising rules to select one of the ontology based inference and the rule based inference to maximize a probability of accurately processing the claim adjudication request in case of a conflict.

Ontology and rule based adjudication

Examples of medical concierge are provided. In an example, an claim may be received. The claim may include data relating to service provided, by a provider, to multiple patients. The claim may be parsed to determine the provider, the multiple patients and the service provided. Additional information may then be fetched. The additional information may include one of a number of claims filed in the past, status of each claim, number of appeals filed, status of the appeals, and complaints registered by the provider. Thereafter, the claim and the additional information may be analyzed and a category may be determined for the provider. The category may be determined based on a behaviour model that may be computed based on the claim and the additional information. The category may be indicative of an issue in behaviour of the provider.

Medical concierge

Examples of a character recognition system are provided. In an example, the system may receive an object detection requirement pertaining to a video clip. The system may identify a visual media feature map from visual media data to process the object detection requirement. The system may implement an artificial intelligence component to segment the visual media feature map into a plurality of regions, and identify a plurality of image proposals therein. The system may implement a first cognitive learning operation to allocate a human face identity for a human face and an object name for an object present in the video clip. The system may determine a face identity model for the human face present in the plurality of image proposals and generate a tagged face identity model. The system may implement a second cognitive learning operation to assemble the plurality of frames with an appurtenant tagged face identity model.

Character recognition

A system for determining a response to a query includes a receiver to receive a query along with a plurality of potential responses to the query. A detector detects a topic and a type of the query based on information extracted from text and structure. Further, a selector selects at least one of a plurality of techniques for processing the query and the plurality of potential responses, based on the topic and the type of the query. An obtainer obtains an answer by execution of each of the selected techniques for processing the query and the plurality of potential responses along with an associated confidence score. A determinator determines one of obtained answers as a correct response to the query, based on a comparison between confidence scores associated with the answers.

Determination of a response to a query

A classifier receives policy data corresponding to a new policy. Further, the classifier processes the policy data to classify the policy data into an obligation class and an informational class. An information extractor then extracts metadata from the policy data that is classified into the obligation class. Subsequently, a data translator determines if there is an incremental change in the policy data based on a comparison of the policy data with policy data corresponding to existing policies. On determining the incremental change in the policy data, the data translator translates the policy data that is classified into the obligation class into a rule based on the metadata. A rules engine then receives the rule from the data translator for claims adjudication.

Data translation

Growing community of inventors

Sunnyvale, CA, United States of America

Sukryool Kang