5732 results about "Language model" patented technology

An advanced model management platform for optimizing and securing generative artificial intelligence systems such as large language models (LLMs) and diffusion models. The platform incorporates various techniques to address the limitations of current generative AI systems, such as hallucination, lack of validation, security vulnerabilities, and inadequate model management. The system employs reinforcement learning algorithms for model optimization, retrieval augmented generation (RAG) for hallucination mitigation, domain-specific validation against expert knowledge, model distillation and similarity scoring for security, adversarial training for robustness, and attention mechanism search and model blending for advanced management and neuro symbolic AI routine combinations. By integrating these techniques, the platform significantly improves the performance, reliability, and security of generative AI across a wide range of tasks and domains leveraging the best elements of symbolic and connectionist techniques alongside automated planning and modeling simulation.

The invention discloses an intelligent programming auxiliary method and system based on a multi-modal AI language model, and belongs to the technical field of programming auxiliary tools. The method comprises the following steps: a multi-modal input processing stage; a dynamic context modeling stage; a hierarchical semantic analysis stage; in the code generation stage, codes are generated in two stages by adopting a Codex-Plus large model; the reinforcement learning driven code optimization stage is used for carrying out multi-objective optimization and reward function design on the codes generated in the code generation stage; a multi-dimensional feedback stage; an interaction and visualization stage; code semantic deep analysis, dynamic context sensing, multi-target optimization generation and real-time interactive feedback are realized by fusing code texts, natural language description, developer behavior data and a domain knowledge graph, and programming efficiency and code quality can be remarkably improved.

The systems and methods described herein relate to improvements to generative artificial intelligence systems through the use of generative artificial intelligence pipelines to supply external information to pre-trained large language models for use in answering queries. To improve the efficiency and accuracy of large language models in responding to user queries, according to various aspects described herein, such queries may be modified and augmented with additional relevant information from decentralized data sources. The retrieval-augmented generation pipeline may interface with one or more decentralized data sources and retrieve the external information, including unstructured text and / or structured data.

The implementations herein disclose advanced systems and methods for integrating, analyzing, and reasoning over heterogeneous data at scale. In some implementations, the system comprises a synergistic data processing infrastructure featuring: a graph database core for unified data representation; specialized loaders for concurrent ingestion and processing of structured, unstructured, and time series data; a natural language reasoning engine leveraging large language models; and a multi-modal user interface.

An example operation may include one or more of storing a data store of credit card documentation, conversing with a user via a chatbot within a chat window of a software application, wherein the conversing comprises receiving natural language inputs with requests for information about a payment card, identifying a benefit obtained by the user based on the conversation, executing a large language model (LLM) on the identified benefit and the data store of the credit card documentation to generate a letter of confirmation, and generating an electronic message with the letter of confirmation attached, and transmitting the electronic message to a user device.

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.

Herein disclosed is receiving predetermined content, receiving a request to transform the predetermined content into a derivative work, receiving a requested theme for the derivative work, using generative artificial intelligence to create the derivative work generated as a function of the predetermined content and the requested theme, determining if the generated derivative work is approved based on a machine learning model configured to determine a content approval score as a function of content owner preferences, in response to determining the generated derivative work is approved, applying a digital watermark to the approved derivative work, configuring an authorization server to govern use of the approved derivative work based on the digital watermark and providing user access to the authorized derivative work. The requested theme may be determined using a Large Language Model (LLM) and a chatbot interview. The generative artificial intelligence may comprise a diffusion model. The content may comprise music.

Systems and methods for protecting and fortifying machine learning engines, artificial intelligence (AI) engines, large language models, deep learning engines, reinforcement learning engines, and AI-based agentic units. An Offline Protection Unit analyzes characteristics of a Protected Engine, and performs offline fortification of the Protected Engine against attacks; by changing operational properties or operational parameters of the Protected Engine to reduce its vulnerability to attacks. An Online Protection Unit performs analysis of at least one of: (i) inputs that are intended to be inputs of the Protected Engine, (ii) outputs that are generated by the Protected Engine; and based on the analysis, dynamically performs online fortification of the Protected Engine against attacks; by dynamically changing operational properties or operational parameters of the Protected Engine to reduce its vulnerability to attacks.

Computer-implemented systems and methods including language models for explaining and resolving code errors. A computer-implemented method may include: receiving or accessing a log comprising an error message, the error message indicating an error in code; determining the error message from the log; determining a context associated with the error; generating a prompt for a large language model (“LLM”), the prompt comprising at least: the error message, and the context associated with the error; transmitting the prompt to the LLM; and receiving an output from the LLM in response to the prompt, the output comprising at least: an explanation of the error message, and a suggested fix for the error.

The invention discloses a knowledge base enhancement generation method and system based on hybrid retrieval and fact verification. The method comprises the following steps: receiving an original query of a user; performing intention analysis and rewriting on the query, identifying an intention type and generating a sub-query adapted to retrieval; executing mixed retrieval of vector retrieval, keyword retrieval and selectable knowledge graph retrieval based on the sub-query, and recalling related knowledge fragments; performing deduplication clustering, fact conflict recognition processing and correlation reordering on the knowledge fragments; according to the intention type and the reordered knowledge fragment, dynamically selecting a prompt template to construct an enhanced prompt; and sending the enhanced prompt into the large language model, and generating a target response with the reference source. According to the method, knowledge recall comprehensiveness is improved through mixed retrieval, knowledge reliability is ensured through fact verification, generation logicality is enhanced in combination with dynamic prompt construction, and response accuracy and credibility are improved.

The invention provides a multi-agent collaborative question and answer enhancement method and system based on heterogeneous data knowledge, and belongs to the technical field of information management. The planning optimization intelligent agent carries out structured processing on the input complex natural language problem; a multi-modal retrieval mechanism on the heterogeneous knowledge source is constructed based on the problem disassembly and entity recognition result, and a multi-path recall agent passes through a semantic matching model of a double-tower structure; the abstract extraction agent performs semantic fusion and information extraction on the text segments and the knowledge graph sub-graphs output by the multi-path recall module; logic verification and quality evaluation are carried out on the answers generated by the abstract extraction module by the reflection iteration agent; and by setting a threshold mechanism and combining importance weights of the sub-questions, performing scoring and reflection optimization on the generated answers by utilizing a large language model LLM (Language Language Model). The method can effectively cope with cross-domain and multi-level complex question and answer tasks, and has good expandability and intelligent level.

Various embodiments of the present disclosure relate to operator assistance based on extracting natural language characters from one or more sensed objects. For instance, particular embodiments may generate a natural language utterance based on extracting natural language text in a nearby traffic sign. In an illustrative example, particular embodiments may detect, via object detection and within image data, one or more regions of the image data depicting the traffic sign. Particular embodiments can then extract one or more first natural language characters represented in the traffic sign based at least on performing optical character recognition within the one or more regions of the image data in response to detecting the one or more regions of the image data depicting the traffic sign.

The invention discloses an agent architecture based on a multi-modal large model, which comprises an external support module and an internal core module, and is characterized in that the external support module comprises an input module; an output module; a large model capability module; the internal core module comprises a sensing module; a memory module; a portrait configuration module; a planning module; a tool use module; and an action module. According to the intelligent agent architecture based on the multi-modal large model, the efficient, flexible and extensible intelligent agent architecture is innovatively realized, and the problem that most of existing intelligent agents are single-function artificial intelligence systems and are difficult to meet the requirement for multi-capability combination in a complex application scene is effectively solved.

The invention discloses an intention classification method and device based on vector retrieval and context awareness and a medium, and relates to the technical field of artificial intelligence. The method comprises the steps of extracting business metadata and associating the business metadata with typical problem examples to generate a standardized service description document; encoding the standardized service description document into a high-dimensional semantic vector through a pre-training language model, and constructing a neighbor search index to store the high-dimensional semantic vector; splicing the user identity information and the current question text into an enhanced query statement, and encoding the enhanced query statement into a context-aware dynamic query vector through a semantic model; performing similarity retrieval based on the dynamic query vector to obtain candidate intelligent services, performing business domain filtering, context weighted sorting and dynamic priority rearrangement, and outputting target recommendation services; by collecting interactive behavior data of a target recommendation service, quality scoring is performed on service descriptions and problem examples based on a preset evaluation rule, and the service descriptions and the problem examples of which the quality scores are lower than a quality threshold value are updated.

The present disclosure includes computer-implemented methods of guardrails for securely using large language models (LLMs). The method comprises monitoring user data flow using an application programming interface (API) and receiving an administrative policy from an administration communication interface. The method involves dynamically applying a plurality of LLM input inspectors to LLM input data. The application of the plurality of LLM input inspectors is based on the administration policy. The dynamic application of the plurality of LLM input inspectors is in sequence for latency optimization. The plurality of LLM input inspectors serve as LLM input guardrails for a plurality of secure deployed large language models (LLMs). The plurality of LLM input inspectors are configured by the administrative policy and validate the LLM input data to validated LLM input data based on the administration policy. Additionally, the method comprises dynamically applying a plurality of LLM output inspectors to LLM output data.

A data query system and methods are provided that are configured to intelligently generate structured data queries from natural language questions using large language models (LLMs). The system includes a processor and a computer readable medium operably coupled thereto, the computer readable medium comprising a plurality of instructions stored in association therewith that are accessible to, and executable by, the processor, to perform operations which include receiving a natural language question for structured data, converting the natural language question to embeddings, matching the embeddings to pre-generated questions from a user questions repository (UQR), determining an accuracy of the matching meets or exceeds a threshold similarity, determining, using an LLM and metadata corresponding to the pre-generated questions from the UQR, a structured data query for querying for the structured data, and querying the structured database system using the structured data query.

A system for creating functionality modules for deployment in a workflow for use in visual programming including a configuration server with a processing element operable to implement the functionality modules and workflow, at least one large language model, a customizable functionality module in a workflow including at least one interface defining one or more customizable properties, and wherein the workflow executes a first operational environment different from a second operational environment executed by the large language models.

An intelligent search agent that can accept search request input in various ways to initiate a search of databases, websites, documents, PDF files, photos, and other digital data. Search requests can be initiated manually, through automated scheduling, and other ways and can be initiated in multiple ways including voice input, text input, form filling, large language model (LLM) processes, AI agents, selecting from dashboard menus, computer instructions and other methods. Applications of machine learning (ML) and natural language processing (NLP) and others are used to enhance the search agent's capabilities while minimizing user effort requirements. The Search Agent works in conjunction with a knowledge base function to dynamically form and manage one or more knowledge bases using search results and to automatically integrate search results into workflow processes.

Systems and methods for generating a message that is to be sent electronically to a user include the use of an artificial intelligence or large language model (AI / LLM) service to provide recommendations about how a message could be changed to improve customer engagement with the message. The systems and methods can present an individual generating the message with options for making changes to a draft of the message, and the individual can then select the changes that are to be made to create a final version of the message. In some instances, the systems and methods include analyzing the change recommendations provided by a AI / LLM service to ensure they will actually improve customer engagement and not clash with or impair the original purpose of the message.

Searches based on an incoming ticket identify quality ticket enrichment data using a vector database. Language model prompts target particular kinds of quality ticket data. The incoming quality ticket, or a search result ticket, or both, are enriched using enrichment data, such as a user intent identification, a workaround suggestion, a resolution description, a target audience description, a relevance description, an impact description, a description of missing resolution facilitation information, an association between the incoming quality ticket and the search result ticket, a user sentiment identification, a tag suggestion, or a feedback utility estimate. The enrichment reduces engineering and support burdens, and facilitates faster more effective resolution of the problem or the request that is stated or implied in the incoming quality ticket. Duplicate tickets are merged or removed. Tickets are prioritized. Missing problem resolution information is identified and requested sooner.

The invention discloses a dangerous environment identification method based on a visual language model and a dynamic scene, particularly relates to the technical field of intelligent risk early warning, and is used for solving the problems of misjudgment and early warning lag caused by lack of event causal chain modeling in the dynamic scene in existing risk identification. According to the method, visual data flow and language description data are fused, a target motion track and a scene change sequence are extracted, a causal logic constraint set is constructed, space-time relevance is verified, a dangerous event causal chain is generated after high-confidence candidate events are screened, and finally a dynamic recognition result is generated based on causal chain overall risk quantification. Through dynamic rule adaptation and causal chain evolution rule matching, the random coexistence event and the real causal relationship are effectively distinguished, the problem of misjudgment caused by static rule stiffness in a traditional method is solved, and the reliability and the disposal timeliness of danger early warning in a complex dynamic scene are improved in combination with a global risk assessment mechanism.

Embodiments of the disclosed technologies are capable of a training pipeline to fine-tune a machine learning model given a limited set of domain-specific data. The embodiments describe using a first machine learning model to generate a pseudo label associated with a domain-specific training document. The pseudo label comprises a machine-generated text of a content type extracted from the domain-specific training document. The embodiments further describe fine-tuning a second machine learning model using the pseudo label, the domain-specific training document, a first low-rank weight matrix, and a second low-rank weight matrix. The fine-tuned second machine learning model generates text of the content type from a domain-specific document.

A system, method, and computer-program product includes identifying a plurality of code synthesis items for a target programming language, generating a code synthesis prompt based on a first sampling of the plurality of code synthesis items, synthesizing, via a large language model, a plurality of raw code segments using the code synthesis prompt, executing the plurality of raw code segments with a code interpreter associated with the target programming language, determining one or more valid code segments of the plurality of raw code segments that the code interpreter successfully executed, aggregating, via a second sampling, the one or more valid code segments into one or more validated code synthesis training samples, and training a code generation model using the one or more validated code synthesis training samples. User interfaces may be provided to allow target coding tasks to be specified via text or speech.

In various examples, synthetic question-answer (QA) pairs may be generated using question and answer generation models comprising corresponding language models (e.g., autoregressive LLMs). A repository of textual data representing a particular knowledge base may be used to source synthetic QA pairs by partitioning textual data from the repository into units of text (e.g., paragraphs) that represent context. For each unit of text, the question generation model may be prompted to generate a synthetic question from that unit of text, and the answer generation model may be prompted to generate a synthetic answer to the synthetic question. Textual entailment and / or human evaluations may be used to filter out low quality, incorrect, and / or non-productive QA pairs that may be a result of hallucinations. As such, the synthetic QA pairs may be used as, and / or may be used to generate, training data for one or more machine learning models.

Systems, methods, and computer-readable media for presenting one or more bets to a user based on a natural language query received from the user. In some embodiments, a natural language query from a user may be received. The natural language query may be translated into computer-readable data by a language processing engine. The language processing engine may use a large language model to translate the natural language query into computer-readable data. The computer-readable data may be in the form of an embedding. A bet engine may match the computer-readable data to a bet when the bet and the computer-readable data exceed a predetermined threshold with regard to similarity. The bet engine may generate a new bet corresponding to the computer-readable data. The system may then present the bet to the user.

The systems and methods disclosed herein orchestrate task execution among autonomous (or semi-autonomous) AI agentic models (“agents”) using a gateway router that dynamically coordinates the agents based on prompt characteristics, user context, and / or real-time operational factors. Received inputs (e.g., prompts) are segmented into subcomponents (e.g., sub-queries), which are routed / mapped to candidate agents based on the output parameters of the subcomponent (e.g., performance thresholds, cost thresholds) and operational parameters (e.g., cost, performance metric values, user access restrictions, timing restrictions) of each agent. The gateway router maintains dynamic routing data structures for each agent that are continuously updated based on environmental stimuli (e.g., geo-political stimuli, sensor stimuli, agent stimuli). For example, the gateway router causes agents to dynamically switch between rule engines identified by the routing tables in response to detecting environmental stimuli. Responses from the candidate agents are aggregated into an output that is responsive to the input.

A system and method for extracting data from large language model (LLM) outputs, including: training a model using labeled data items to assign rankings to LLMs; selecting, by the trained model, one or more of the LLMs based on the rankings; sending an LLM prompt to selected models; and outputting, by the model, a refined response to the prompt based on responses to the prompt by the LLMs. Some LLM prompts according to some embodiments may include different sets input parameters of different types—such as, e.g., a set of block parameters and a set of editorial parameters. In some embodiments, a model or LLM may be updated or retrained using a reinforcement learning approach and based output items or refined responses generated by that model or LLM—which may for example be scored or ranked and used in combination with reward or cost functions to update model parameters.

The invention is suitable for the technical field of artificial intelligence, and provides a multi-modal large language model dialogue generation method based on natural language understanding, comprising the following steps: receiving multi-modal information input by a user through a multi-modal large language model, the multi-modal information comprising a plurality of modal data; preprocessing modal data in the multi-modal information, and extracting to obtain multi-modal features; performing unified fusion feature representation on the extracted multi-modal features based on a dynamic weighted fusion strategy of a multi-head attention mechanism; determining the dialogue state of the long context based on a long context processing algorithm, and ensuring that the generated reply content is associated with the dialogue history; and according to the unified fusion feature representation and the dialogue state, a natural language is generated through an RAG retrieval enhancement generation technology for replying. According to the method, input of multiple modes can be processed and understood, the ability of understanding the intention of the user is improved, the continuity of the context is maintained, and the generated reply is more natural.

A database system integrates in-database machine learning (ML) models with in-database large language models (LLMs) or other generative artificial intelligence (AI) models that enable new applications. The database system receives one or more inferences from an ML model and provides an inference input to a retrieval agent of an object store. One or more vector stores represent a plurality of reference documents using semantic encodings. The retrieval agent performs a similarity search of the one or more vector stores to retrieve a set of passages from the plurality of reference documents based on similarity of encodings of the inference input and encodings of passages in the plurality of reference documents. The database system generates a linguistic prompt for an LLM having a context including the inferences and passages and applies the LLM to the linguistic prompt to generate a natural language explanation of the one or more inferences.

A SQL generation method based on a large language model, comprising: generating data definition language (DDL) prompt slot information and data example slot information on the basis of a configuration operation of a user on a SQL database; receiving a natural language query request input by the user, and transcribing the natural language query request to obtain question transcribing slot information; on the basis of the question transcribing slot information, the DDL prompt slot information and the data example slot information, acquiring complete prompt information matched with a large language model; and inputting the complete prompt information into the large language model to generate an executable SQL statement matched with the natural language query request.