Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

3448 results about "Generative model" patented technology

In statistical classification, including machine learning, two main approaches are called the generative approach and the discriminative approach. These compute classifiers by different approaches, differing in the degree of statistical modelling. Terminology is inconsistent, but three major types can be distinguished, following Jebara (2004): Given an observable variable X and a target variable Y, a generative model is a statistical model of the joint probability distribution on X × Y, P(X,Y); A discriminative model is a model of the conditional probability of the target Y, given an observation x, symbolically, P(Y|X=x); and Classifiers computed without using a probability model are also referred to loosely as "discriminative".

Generative summarization dialog-based information retrieval system

Embodiments of the disclosed technologies include generating a search prompt based on an input portion of an online dialog involving a user of a computing device. The search prompt includes a dialog summarization instruction configured to instruct a generative artificial intelligence model to generate and output a dialog summary. The search prompt is sent to a first generative model. In response to the search prompt, a search query is generated and output by the first generative model based on the dialog summary. The search query is sent to a search system. Search result data is determined based on an execution of the search query by the search system. At least some of the search result data is included in an output portion of the online dialog. The output portion is configured to be displayed at the computing device in response to the input portion of the online dialog.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

Artificial intelligence (AI) based data filters

An Artificial Intelligence (AI) based filter apparatus includes an input filter and an output filter protecting a generative AI model and preventing restricted content from being transmitted to user devices. When a user query is received, the input filter determines if the user query can be transmitted to the generative AI model by generating an input risk score for the received user query. If the user query is transmitted and a model query response is received from the generative AI model, the output filter determines an output risk score based on which the model query response may be transmitted to the user. The input filter and the output filter each include a pre-trained language model as a base with additional layers trained to estimate the corresponding risk scores.
Owner:ACCENTURE GLOBAL SOLUTIONS LTD

Model evaluation metrics and effective model selection

A variety of generative models are trained that are trained on a reference data set. The generative models are evaluated by candidate metrics to determine the relative rankings of the models as evaluated by the different candidate metrics. Rankings as generated by the models is compared with human evaluation of the generated results as simulated and the candidate metrics that most align with the human evaluation may then be used to automatically evaluate subsequent generative models. The candidate metrics may include various types of encoding models trained for non-generative purposes, such that the selected candidate metric may represent selecting an encoding model that performs well on the generative data.
Owner:THE TORONTO DOMINION BANK

Vector embedding preprocessing and retrieval for generative models

Certain aspects of the present disclosure provide techniques for preprocessing data prior to generating vector representations. The data is preprocessed to generate one or more natural language texts describing entities and relationships included in the data. Vector representations of the natural language format texts are stored in a vector database. The embeddings may be retrieved to augment a prompt for a generative model. The embeddings may be selected by performing a search of the vector database using an embedding for the prompt to determine relevant or similar embeddings. The augmented prompt can be input into a large language model. Although the model may be unaware of the data from which the embeddings of the embedding database were generated, the augmented prompt may enable the model to use the data to improve breadth and depth of responses. The preprocessing of the data improves response results of the model.
Owner:INTUIT INC

Configuring a generative machine learning model using a syntactic interface

Described herein are a system, method, and device for configuring a generative machine learning model using a syntactic interface. A system may include a user interface, a memory, and a processor configured to, using a syntactic interface displayed using the user interface, receive a syntactic interface input from a user; identify an electronic medical record (EMR) by generating an EMR database query as a function of the syntactic interface input, querying an EMR database using the EMR database query, and receiving, from the EMR database, an EMR database response; generate a prompt as a function of the syntactic interface input; generate a first generative model output as a function of the prompt and the EMR using a trained generative machine learning model; and using a conversational interface displayed using the user interface, display the first generative model output to the user.
Owner:NFERENCE INC

Monitoring generative model quality

A system is disclosed that uses expert systems to monitor and evaluate quality in a large language model. The system can include a prompt library that associates prompts with areas of expertise. The system selects prompts from the library and evaluates first responses generated by a large language model for the set of prompts against second responses generated by a modified version of the large language model to the set of prompts. The evaluation uses expert systems associated with the areas of expertise for the set of prompts. If the system determines that the evaluation indicates a degradation criterion is met, the system may take remedial action. The system provides an effective way to evaluate and prevent the use of modified language models that do not meet the required standards.
Owner:GOOGLE LLC

Dynamic threat mitigating of generative artificial intelligence models

The disclosure relates to a method and system for dynamically mitigating threats of generative Artificial Intelligence (AI) models. Conventional systems often suffer from inefficiencies due to sequentially applying threat detection checks leading to unnecessary preprocessing and increased computational demands. Additionally, such systems typically focus only on input data, neglecting potential threats in outputs. The disclosed system and method addresses these drawbacks by employing a hierarchical structure of macro and nano classifiers. The system utilizes macro classifiers for broad initial threat categorization followed by specialized nano classifiers for detailed analysis of specific threat subtypes, thereby optimizing processing time and computational resources. The system operates in real time, applying predefined moderation rules to both input and output data to ensure comprehensive threat mitigation. Additionally, continuous telemetry data updates refine nano classifiers and threat identification mechanisms, maintaining high accuracy and adaptability. The disclosed method enhances safety efficiency and reliability of generative AI models.
Owner:INFOSYS LTD

Four-dimensional object and scene model synthesis using generative models

In various examples, systems and methods are disclosed relating to generation of four-dimensional (4D) content models, such as 4D content models to render realistic sequences of frames of 3D data. The systems can initialize a 3D component of the 4D content model, such as a 3D Gaussian splatting representation, based at least on a prompt for the 4D content. The system can configure motion and / or dynamics for the sequence of frames by evaluating frames rendered from the 4D content model using one or more latent diffusion models (LDMs), including a video LDM. The system can perform operations such as autoregressive generation of frames to create long sequences of content, motion amplification to facilitate realistic, dynamic motion generation, and regularization to facilitate generation of complex dynamics.
Owner:NVIDIA CORP

Apparatus and methods for generating obfuscated data within a computing environment

An apparatus for generating obfuscated data within a computing environment, comprising a processor and a memory containing instructions configuring the processor to access a database containing a plurality of private data elements belonging to at least a private record, generate a set of obfuscated data elements, representative of the at least a private record, as a function of the plurality of private data elements using an generative model, determine a first distance measure between at least an obfuscated data element within the set of obfuscated data elements and at least a private data element of the plurality of private data elements within the database, and verify the first distance measure is within a distance range, wherein a minimum threshold of the distance range is determined as a function of a deidentification parameter and a maximum threshold of the distance range is determined as a function of an obfuscation parameter.
Owner:NFERENCE INC

Generating diverse message content suggestions

Embodiments of the disclosed technologies are capable of generating diverse suggested message content. The embodiments describe generating a message plan comprising attribute data and section data. The embodiments further describe inputting the message plan as a prompt to a first generative model. The first generative model is fine-tuned using a training message plan. The training message plan comprises an ordered sequence of training attribute data and training section data. The training attribute data and training section data are extracted from historic messages or generated messages. The embodiments further describe generating, by the first generative model, message content suggestions based on the attribute data and section data.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

System and method for efficient scene continuity in visual and multimedia using generative artificial intelligence

A system and method for generating multimedia artifacts with managed scene continuity in visual and multimedia using an AI-based and scene continuity aware media generation platform. The system receives a user or AI agent specification or simulation result(s), selects or trains generative models based on the specification, preprocesses relevant data, and generates scene narrative or frame-specific, sequence specific or broader continuity aware content using the selected or trained model(s). The generated content may be further enhanced using frame interpolation and view synthesis techniques to create smooth transitions or novel viewpoints or to aid in more efficient transmission or viewing or persistence of resultant content. The system enables efficient and customizable generation of high-quality scene continuity aware content for various applications in visual and multimedia production using neuro-symbolic and simulation enhanced compression, representation and generation processes.
Owner:QOMPLX INC

Unsupervised learning with synthetic data and attention masks

Embodiments of the disclosure relate to unsupervised learning with synthetic data and attention masks. According to example embodiments of the disclosure, a plurality of sample images are generated by providing a plurality of text prompts into a trained generative model, respectively. For a sample image of the plurality of sample images, at least one attention map is obtained from a generative model, the at least one attention map being determined by the generative model for generating the sample image, an attention map indicating visual elements of an object within the sample image. Training of a target model is performed according to unsupervised learning at least based on the plurality of sample images and attention maps for the plurality of sample images, the target model being configured to perform an image processing task.
Owner:LEMON INC(GB)

Use a generative model to create synthetic users for testing and analysis

PendingUS20250165678A1Design optimisation/simulationUser ResearchData science
Conducting user research with human users is time consuming and expensive. Provided with quality training data that represents human users having different personae, models can be trained to offer responses that can emulate different human users. The models may offer synthetic users that can extract information from and respond to inputs to the models. The inputs can include prompts and responses can include answers to the prompts. In some cases, data about human users can be used to build different synthetic user memories, which may be used to generate different prompt chains corresponding to different users. The prompt chain can be used to prompt a model to respond based on the contextual information in the synthetic user memory.
Owner:ROKU INC

Data query statement generation method, apparatus and device, and storage medium

Disclosed are a data query statement generation method, apparatus and device, and a storage medium. The method comprises: acquiring a process presentation requirement and a natural statement to be converted; on the basis of the process presentation requirement, constructing a prompt instruction; and on the basis of the prompt instruction, inputting said natural statement into a pre-trained data query statement generation model, and on the basis of a model output result, determining and outputting an intermediate generation result and a target data query statement which correspond to the process presentation requirement, wherein the pre-trained data query statement generation model is a generative large language model that is trained on the basis of a pre-constructed chain-of-thought, and the pre-constructed chain-of-thought is a chain-of-thought that is constructed after logic segmentation is performed on a logic plan corresponding to a data query statement.
Owner:TRANSWARP TECHNOLOGY (SHANGHAI) CO LTD

Factually consistent generative narrations

Systems, devices, and methods are provided for determining factually consistent generative narrations. A narrative may be generated by performing steps to determine one or more metadata messages for a first portion of a video stream, determine transcribed commentary for a second portion of the video stream, wherein the second portion includes the first portion, and determine a prompt based at least in part on the one or more metadata messages and the transcribed commentary. The prompt may be provided to a generative model that produces an output text. Techniques for performing a factual consistency evaluation may be used to determine a consistency score for the output text that indicates whether the output text is factually consistent with the one or more metadata messages and the transcribed commentary. A narrated highlight video may be generated using the consistent narrative.
Owner:AMAZON TECH INC

Emphasizing portions of synthesized speech

A neural text-to-speech system may be configured to emphasize words. Applying emphasis where appropriate enables the TTS system to better reproduce prosodic characteristics of human speech. Emphasis may make the resulting synthesized speech more understandable and engaging than synthesized speech lacking emphasis. Emphasis may be manually annotated to, and / or predicted from, a source text (e.g., a book). In some implementations, the system may use a generative model such as a variational autoencoder to generate word acoustic embeddings indicating how emphasis is to be reflected in the synthesized speech. A phoneme encoder of the TTS system may process phonemes to generate phoneme embeddings. A decoder may process the word acoustic embeddings and the phoneme embeddings to generate spectrogram data representing the synthesized speech.
Owner:AMAZON TECH INC

Enhanced searching using fine-tuned machine learning models

An advanced search system leverages a pre-trained large language model to enhance user query responses. The system, equipped with hardware processors, a search query via an interface and accesses a pre-trained large language model designed to respond to the search query. The system fine-tunes the model to generate a task-specific generative model. The system employs the task-specific generative model to generate a search result to the search query and analyzes the search result based on a performance metric associated with the task-specific generative model. The system refines the task-specific generative model based on the analyzing of the search result.
Owner:SNOWFLAKE INC

Determining anomalous tool invocations by applications using large generative models

This disclosure relates to utilizing a threat detection system to detect anomalous actions provided by a compromised large generative language model (LLM). For instance, the threat detection system utilizes a detection-based large generative model to process select communication between an application system and the LLM and determine when the LLM may have been potentially compromised. In various implementations, utilizing the detection-based large generative model, the threat detection system determines when an LLM is improperly instructing an application system to invoke tools to perform unapproved actions. Furthermore, when an LLM becomes compromised, the threat detection system intelligently safeguards the detection-based large generative model against similar threats that seek to evade detection or compromise the detection-based large generative model.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

Orchestrator with semantic-based request routing for use in response generation using a trained generative language model

A system is provided for managing specialized tasks and information retrieval processes. Agents are configured to perform tasks and / or retrieve information in a specialized domain. The system receives, via an interaction interface, a message from a user for the trained generative model to generate an output, generates a context of the message, generates a request including the context and the message, executes an orchestrator configured to: receive the request, determine, using semantic decision making, one or more agents to handle the request, input the request into one or more agents to perform a task and / or retrieve information in specialized domains, generate a prompt based on the retrieved information and / or the performed task and the message from the user, provide the prompt to the trained generative model, receive, in response to the prompt, a response from the trained generative model, and output the response to the user.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

Retrieval-augmented generation (RAG) system optimization

A method includes obtaining training data for a retrieval-augmented generation (RAG) architecture having retriever and generative models. The retriever model is configured to identify information chunks relevant to input queries, and the generative model is configured to generate outputs based on the information chunks and the input queries. The method also includes generating a prompt for the generative model and generating multiple sets of queries for the retriever model. Each query in the multiple sets of queries is configured to cause the retriever model to select a set of information chunks associated with the prompt. The method further includes generating multiple responses to the prompt using the generative model and the sets of information chunks and determining rewards associated with the RAG architecture based on the responses. In addition, the method includes training the generative model based on the training data and the rewards to produce an updated RAG architecture.
Owner:GOLDMAN SACHS & CO LLC

Automated root cause determination using a pre-trained generative model

Systems and methods are provided for determining a root cause of an incident that occurred in a 5G / 6G multi-access edge computing and core network system. In particular, the disclosed technology is directed to using a pre-trained generative model to determine the root cause for an incident as recorded in event data of a system log. The present disclosure generates a prompt for the generative model to determine the root cause for an incident as recorded in the system log. The prompt comprises a combination including event data from a system log, function hierarchy graph data, and function information as grounding information in a prefix of the prompt. The prompt further includes a question that requests determining a root cause of an incident as recorded in the event data. An answer as generated by the pre-trained generative model indicates of the root cause and a function call associated with the incident.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

System And Method For Extracting Object Information From Digital Images To Evaluate For Realism

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.
Owner:ACCENTURE GLOBAL SOLUTIONS LTD

Semantic-tree-based ai content management platform

A data processing system implements receiving a call requesting a generative model to generate a semantic tree for a source content; constructing a first prompt including the source content and instructions to the model to analyze a semantic structure of the source content and to generate a semantic outline and content chunks of the source content, the semantic outline including one or more topics each connected with one or more of the content chunks, to compute one summary for each of the content chunks, to apply indices to reference each topic node of the semantic tree to one of the topics, and to apply indices to reference each leaf node of the semantic tree to one of the content chunks and the respective summary; providing the first prompt to the model and receiving the semantic tree of the source content; and storing the semantic tree in a database.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

Supervised time sequence water level data generation method and system and storage medium

The invention relates to the technical field of machine learning, in particular to a supervised time sequence water level data generation method and system and a storage medium. The method comprises the following steps: acquiring multi-source hydrological monitoring data; performing abnormal value identification and data preprocessing according to the hydrological monitoring data to generate standardized hydrological basic data; constructing a data generation model of the conditional generative adversarial network based on the standardized hydrological basic data; hydrological variable driven condition feature regulation and control are carried out on the data generation model, parameter optimization of the generation network is carried out, and hydrological adaptability enhanced condition input feature data are generated; and injecting the condition input characteristic data into the data generation model to generate initial water level time sequence data. According to the method, the rare extreme hydrological events are oversampled by using a hierarchical importance sampling and self-service method (Bootstrap), so that the performance of the generative model in rare event prediction is remarkably enhanced.
Owner:YANGTZE RIVER WATER CONSERVANCY COMMISSION HYDROLOGY MIDDLE YANGTZE RIVER HYDROLOGY & WATER RESOURCES SURVEY BUREAU (YANGTZE RIVER WATER CONSERVANCY COMMISSION HYDROLOGY MIDDLE YANGTZE RIVER WATER ENVIRONMENT MONITORING CENT) +2

Intelligent customer risk assessment system and method based on large language model

The invention provides an intelligent customer risk assessment system and method based on a large language model, and relates to the technical field of risk assessment, and the method comprises the steps: obtaining multi-modal data of a customer, carrying out the preprocessing, and extracting structured and unstructured features; constructing a hierarchical risk knowledge system, and realizing adaptive evolution of the knowledge system through a graph neural network and a generative model; constructing an initial negative sample library, and constructing a negative sample database in combination with a non-risk mode labeled by an expert and derivative layer analysis; optimizing the large language model by adopting a strong supervision, weak supervision and reinforcement learning cooperative training mechanism under each classification according to the customer type; mining risk features in a text by using the optimized large language model, processing multi-modal data through a multi-level attention network, and generating a positioning report including contradiction type coding, service influence dimension evaluation and risk level quantification; the accuracy, efficiency and flexibility of customer risk assessment are improved, and the risk management strategy is optimized.
Owner:九一润泽信息技术(北京)有限公司

Face-translator: end-to-end system for speech-translated lip-synchronized and voice preserving video generation

A neural end-to-end system is provided for the face and voice preserving translation of videos. The system is a pipeline of multiple models that produces a video of the original speaker speaking in the target language with modified lip movement to match the target speech, while preserving emphases and prosody of the original speech, and voice characteristics of the original speaker. The pipeline starts with automatic speech recognition including emphasis detection, followed by the translation model. The translated text is then synthesized by a Text-to-Speech model that recreates the original emphases in the target sentence. The resulting synthetic speech is then converted back to the original speakers' voice using a voice conversion model. Finally, to synchronize the lips of the speaker with the translated audio, a generative model generates frames of adapted lip movements which are combined with the audio to produce the final output. The disclosure further describes several use-cases and configurations that apply these techniques to video conferencing, dubbing, low-bandwidth transmission, speech enhancement and assistive technology for the hearing impaired.
Owner:WAIBEL ALEXANDER

Generating query outcomes using domain-based causal graphs and large generative models

This disclosure describes utilizing a causal query system to determine causal outcomes for domain-specific causal queries using a framework that includes causal graphs for targeted domains, a large generative model (LGM), and other models or systems. In various implementations, the causal query system provides a framework that includes generating domain-specific causal graphs, encoding or mapping the causal graphs with local data values, and using the encoded causal graphs to determine causal outcomes to causal queries. In some implementations, the causal query system uses the LGM and data resources (e.g., external sources) to populate missing values of an embedded causal graph before using the causal graph to determine causal outcomes.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

Security for generative models using attention analysis

Devices and techniques are generally described for security threat mitigation for generative machine learning models. In some examples, first prompt data including first data associated with a first natural language input and a first span may be determined. An LLM may determine first plan data using the first prompt data. The first plan data may include a call to the first API. A first classifier model may determine a first trust score for the first span. A first attention score may be determined for the first span and the first action plan. Second plan data may be generated based on at least one of the first trust score and the first attention score or the second trust score and the second attention score.
Owner:AMAZON TECH INC

Producing calibrated confidence estimates for open-ended answers by generative artificial intelligence models

A confidence estimation tool uses a calibrated confidence mapping model to estimate confidence for a model-generated candidate root cause. The tool uses a generative artificial intelligence (“AI”) model to determine, based on a description of a current event, a candidate root cause of the current event. The tool determines a description-based confidence score using the description of the current event and descriptions of a set of relevant historical events in a target domain. The tool also determines a cause-based confidence score using the candidate root cause of the current event and root causes of the set of relevant historical events. Finally, the tool determines a final confidence score using the description-based and cause-based confidence scores. Even if the generative AI model is configured for general-domain applications, by referencing relevant historical events, the tool can accurately estimate confidence for a model-generated candidate root cause within the target domain.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC