825 results about "Response generation" patented technology

A method of generating outputs in LLMs including receiving including textual content, defining a context for the documents including identifying a topic or a category, segmenting the textual content into content chunks associated with the topic or category, assigning a tag to each content chunk, identifying selected chunks, adding metadata to the selected chunks indexing the selected chunks, receiving a query, and performing a response generation process including determining if a cache includes information for the query and either retrieving the information from the cache or performing a search of the index to retrieve the information, generating an augmented query by augmenting the query with retrieved information, generating a response from the augmented query, evaluating the response for compliance with criteria, and one of generating a final response and transmitting the final response to the user or performing a fine-tuning process comprising redefining the of the one or more contexts.

The invention discloses a tunnel multi-source fusion dynamic twin surrounding rock intelligent prediction and control method and system, and the method comprises the steps: collecting multi-source heterogeneous data in real time through intelligent drilling equipment, a distributed optical fiber sensing network and a mobile scanning device which are disposed on a tunnel construction surface; inputting the multi-source heterogeneous data into a space-time diagram convolutional network, constructing a space-time correlation model of geological features and construction disturbance parameters, and outputting a coupling feature matrix; based on the coupling characteristic matrix, simulating the dynamic response of the surrounding rock-support system through a streaming voxelization engine and a multi-physics coupling engine, and generating a risk evolution three-dimensional thermodynamic diagram; and inputting the risk evolution three-dimensional thermodynamic diagram into the deep reinforcement learning model, and dynamically optimizing to generate a construction parameter regulation and control instruction meeting a safety constraint condition. According to the technology, a full-link channel of'data perception-mechanical analysis-decision execution 'is opened in a closed-loop mode, and therefore the double risks of'data distortion misjudgment' and'response lag out-of-control 'of a traditional method are avoided.

Methods and systems for retrieval-augmented generation are described. Responsive to a user input, an input embedding associated with the user input is obtained. A synthetic question embedding is retrieved from an embeddings database, based on a similarity to the input embedding. The synthetic question embedding is used to obtain a relevant source text based on a stored mapping between the synthetic question embedding and the source text. A prompt is provided to a large language model (LLM) to generate and display a textual response to the user input, based on the user input and the source text. The disclosed methods and systems effectively narrow the pool of source documents based on similarity measures between the user input embedding and the synthetic question embedding, to enable the retrieval of more relevant sources for use in response generation.

The invention provides a multi-round dialogue interaction method and system based on context reconstruction and multi-library retrieval, and the method comprises the steps: firstly obtaining a multi-round dialogue data set of a target user, which comprises a plurality of dialogue round sequences composed of user input statements and system response statements; performing context reconstruction processing on the multi-round dialogue data set to generate context reconstruction characteristics of each dialogue round sequence, covering current round semantic focus offset and historical round semantic dependence intensity, and retrieving a matched multi-database retrieval result from a preset heterogeneous database based on a dynamic context window, a candidate response statement set and confidence are included. Performing multi-strategy matching on context reconstruction features and retrieval results, generating a response generation strategy to adjust candidate response semantic priorities and confidence thresholds, and finally feeding back the response generation strategy to a dialogue service system to trigger response optimization operation, and updating heterogeneous database retrieval weights and context window dynamic adjustment parameters.

Embodiments described herein relate to systems and methods for automatically generating content for a generative answer interface of a collaboration platform. The system receives a natural language user input identifying corresponding blocks of text or snippets using a content extraction service. A prompt is generated using the blocks of text and is used to obtain a generative response. The generative response and links to corresponding content are displayed in the generative answer interface and can be inserted into content of the collaboration platform. The systems and methods described use a network architecture that includes a prompt generation service and a set of one or more purpose-configured large language model instances (LLMs) and / or other trained classifiers or natural language processors used to provide generative responses for content collaboration platforms.

The invention relates to a multi-modal intelligent robot system and an interaction method, and belongs to the technical field of robot digital data processing, and the method comprises the following steps: S1, multi-modal input collection; s2, carrying out multi-modal input preprocessing; s3, performing multi-modal information fusion, inputting the information into a pre-trained multi-modal feature fusion model, and performing feature fusion on each modal feature through a quantitative feature data fusion mechanism to obtain a user interaction intention vector and a user emotional state vector; s4, interaction response generation: matching a preset interaction response strategy library based on the user interaction intention vector to obtain basic response content, and performing emotion adaptation adjustment on the basic response content in combination with the user emotion state vector to generate multi-modal response content including text information, voice information and action information; s5, interactive feedback is executed; the method has the beneficial effects that the robot is fused with multi-modal information through the basic response content and the user emotional state vector, and interaction is dynamically optimized.

The invention discloses a data query method and system based on a natural language text. The method comprises the following steps: dynamically shielding the natural language text to generate a semantic vector sequence; key entities and association relationships thereof in the semantic vector sequence are extracted, and a structured entity relationship set is obtained; matching the structured entity relationship set with knowledge graph nodes to generate a heterogeneous semantic graph; performing heterogeneous fusion on the heterogeneous semantic graph and text syntactic features to generate intermediate query representation; processing the intermediate query representation to generate an executable statement carrying a semantic association identifier; and verifying the semantic consistency of the response content of the executable statement and the original input, and iterating to regenerate the executable statement when the semantic consistency does not pass the verification. And efficient and accurate natural language query conversion and response generation are realized through dynamic shielding enhanced semantic robustness, knowledge graph path extension and weight iterative optimization, heterogeneous feature fusion and a multi-modal verification mechanism.

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.

The invention relates to the technical field of natural language processing, in particular to an intelligent customer service system based on natural language processing, which comprises a dynamic term ambiguity resolution module, a context intention chain construction module, a domain emotion vectorization module, a compliance response decision module and an aging knowledge injection module. Wherein the dynamic term ambiguity resolution module is used for receiving an original statement of a user and generating a standard term set; the context intention chain construction module is used for generating a structured intention chain; the domain emotion vectorization module is used for generating a three-dimensional emotion vector; the compliance response decision module is used for generating a to-be-verified response scheme; and the timeliness knowledge injection module is used for verifying the timeliness of legal provisions in the response scheme to be verified. According to the method, through fusion of dynamic term disambiguation, context intention chain modeling, emotion vector quantization and law and regulation aging verification, accurate semantic understanding and compliance response generation of the intelligent customer service system in multiple rounds of dialogues are realized.

Systems and methods are provided for improving the performance of artificial intelligence agents. A computer-implemented method for improving artificial intelligence agent performance is provided that includes processing a plurality of inputs through an agent management logic and, in response, generating a plurality of outputs. The inputs in the plurality of inputs are sourced from past runtime execution of a plurality of agents. The outputs in the plurality of outputs are configured to improve future runtime execution of the plurality of agents.

The invention relates to the technical field of computer science and artificial intelligence, and discloses a digital twin basin flood disaster early warning plan generation system based on deep learning, and the system comprises a data collection and processing module which obtains and standardizes multi-source data of basin meteorology, hydrology, terrain, remote sensing and the like in real time, and provides real-time data input; the digital twinborn modeling module is used for constructing a digital twinborn model of a watershed hydrological dynamic process according to the real-time data and outputting a simulation result; the deep learning prediction module is used for receiving a simulation result, training a prediction model and outputting space and time distribution prediction of flood disasters; the emergency response generation module is used for generating an emergency plan of the flood disaster according to the prediction result; and the system feedback module is used for evaluating an emergency plan and a prediction effect and providing an adjustment basis for future disaster early warning. According to the invention, accurate flood disaster prediction based on real-time data can be realized, the accuracy and response efficiency of an emergency plan are improved, and disaster loss is reduced.

The invention relates to the technical field of cooperative control, in particular to a multi-machine cooperative control method and system for a bridge cable hoisting device, and the method comprises the following steps: collecting tension change characteristics through a distributed sensor array, extracting indexes through a sliding window algorithm to generate a response time window, and generating a cooperative time window through time sequence overlapping and speed trend adjustment. Calculating a compensation value by combining inertial parameters and acceleration to generate a trigger window, detecting tension and displacement difference, inputting the tension and displacement difference into a dynamic threshold function for screening and fusion, outputting a synchronous trigger condition, and generating a synchronous control instruction by encoding a device number and a tension change rate after timestamp alignment. According to the method, multi-node tension synchronous acquisition and normalization processing, dynamic response generation through a sliding window, boundary matching action triggering adjustment through an overlapping algorithm, response lag correction through inertia compensation, tension and displacement difference real-time detection, dynamic threshold screening and triggering condition fusion and timestamp alignment packaging instruction consistency are carried out; and the cooperation precision and the system robustness are improved.

A computer-implemented method for operating an artificial intelligence voice agent system includes receiving voice input through communication channels; analyzing converted text through natural language processing (NLP) pipelines implementing intent recognition and sentiment analysis detecting emotional cues using a multimodal large language model (LLM); generating response content using machine learning models trained on domain-specific corpora; converting generated responses to synthetic speech through text-to-speech (TTS) engines; integrating with a customer relationship management (CRM) platforms or an enterprise resource planning (ERP) database; and implementing continuous learning by updating language understanding models using conversation logs, voice recognition parameters based on user feedback, and response generation patterns. One implementation is a computer-implemented system and method that operates a suite of intelligent interactive devices and platforms including an artificial intelligence voice agent, enhanced communication platforms, an intimacy companion system, and augmented / virtual reality eyeglasses. Further, one implementation includes AR / VR eyeglasses that project visual content onto interchangeable lenses or directly onto the user's retina via laser-based retinal projection, provide prescription adjustments, incorporate ear-mounted sensors for monitoring physiological parameters like heart rate, oxygen saturation, and blood pressure, and utilize wireless data transmission, onboard environmental sensing, and remote calibration, all designed to offer dynamically adaptive, secure, and context-aware interactions across communication, personal assistance, health monitoring, and immersive augmented or virtual reality environments.

The invention relates to the technical field of information retrieval, in particular to an intelligent RAG knowledge base system fused with a dynamic knowledge graph. Comprising a data processing module for preprocessing original data to obtain a standardized data set; the graph construction and updating module is used for carrying out knowledge extraction on the standardized data set by utilizing a large model, constructing a knowledge graph and carrying out dynamic updating; the dialogue management and understanding module is used for recording complete information construction of a current dialogue, updating a dialogue state and calculating a retrieval weight adjustment amount; the mixed retrieval module is used for performing mixed retrieval in combination with DPR and PPR retrieval methods to obtain a first retrieval result and a second retrieval result, setting an initial retrieval weight according to the question type, and obtaining a comprehensive retrieval result in combination with the retrieval weight adjustment amount; and the response optimization module is used for outputting an optimal response according to the comprehensive retrieval result and user feedback by utilizing reinforcement learning based on strategy gradient. According to the method, the retrieval and response generation effect can be optimized, and the user satisfaction is improved.

The invention discloses an intelligent traffic data analysis and decision generation system based on multi-model dynamic collaboration, and the system comprises a multi-mode collection module which collects voice, text, video and structured data and loads a traffic knowledge graph; the feature processing module is used for extracting semantic, time sequence and spatial features and generating a fusion vector; the semantic modeling module is used for generating an intention vector in combination with the knowledge graph and the interaction record; the dynamic routing module selects an edge or cloud model according to the intention vector to generate a query statement; the Prompt memory module fuses the historical template and the alignment parameters to generate a query draft; the query verification module is used for executing semantic and structure verification and outputting a correction statement; the query execution module generates a response vector; the causal interpretation module generates an interpretation vector; and the response generation module outputs a multi-granularity result according to the user role. According to the method, the cooperative processing capability and semantic analysis precision of complex traffic query are improved.

The invention relates to the technical field of intelligent interaction systems, and discloses an intelligent interaction system and method based on a multi-modal large model. The system comprises a multi-modal input layer, a context sensing module, a cross-modal fusion module, a dynamic response generation module and a system monitoring module. The multi-modal input layer preprocesses multi-modal data; the context sensing module constructs a dynamic context vector; the cross-modal fusion module fuses the data to generate joint features; the dynamic response generation module generates a response strategy through hierarchical decision; and the system monitoring module monitors the key indexes and triggers an optimization mechanism. All the modules work cooperatively, multi-modal data deep fusion, precise context sensing, efficient dynamic response and system self-optimization are achieved, the accuracy, adaptability and stability of intelligent interaction are improved, and the method can be widely applied to multiple fields such as intelligent home and intelligent customer service.

The invention discloses a deep learning artificial intelligence security vulnerability detection platform, and relates to the technical field of intelligent detection, and the platform comprises an information processing module which collects heterogeneous data in real time, carries out the labeling, format unification and modal aggregation processing of the data, and generates a sample set; the feature learning module is used for performing feature unwrapping on the sample set by using a variational auto-encoder, extracting modal data features and potential space representation learning, and outputting a potential space vector; the response generation module is used for generating a vulnerability response strategy through a modal consistency verification and response template matching mechanism based on the vulnerability risk level vector in combination with a response generation engine; and the repair feedback module is used for executing automatic vulnerability repair operation in combination with federal reinforcement learning and Bayesian optimization, performing feedback optimization according to an execution result, and outputting the vulnerability repair operation and a feedback result. According to the method, the response strategy is combined with intelligent matching of the real-time risk level, so that the accuracy and adaptability of vulnerability repair are improved.

An exemplary machine-learning-based method for generating a response to a natural-language query from an entity associated with an organization comprises: obtaining a sub-query from the natural-language query; determining if a cache associated with the organization stores a matching historical sub-query: if the cache stores the matching historical sub-query, retrieving a historical sub-response associated with the historical sub-query from the cache as a sub-query response; if the cache does not store any matching historical sub-query: inputting the sub-query into a cache-based enhancement machine-learning model to enhance the sub-query, wherein the cache-based enhancement machine-learning model is trained based on historical query data stored in the cache associated with the organization; and inputting the enhanced sub-query into a language model to generate the sub-query response; and generating the response to the natural-language query based on the sub-query response.

The invention relates to the technical field of financial large models, and provides an RAG method and system for compliance analysis of a multi-modal financial document, and the method comprises the steps: carrying out the preprocessing of an input multi-modal financial document, generating a corresponding text block through the multi-modal data in the multi-modal financial document, and constructing a corresponding vector database; responding to the target query request; according to the target query statement, entering a multi-path retrieval process to generate a binding packet for responding to the sub-query statements; based on the binding packages generated by the multi-path retrieval module, the semantic alignment degree of each binding package and a sub-query statement is calculated, a corresponding time reward score is calculated in combination with a time reward mechanism to obtain a matching score, ranking optimization is conducted on the matching score through a direct preference optimization mechanism, and a preference text block set is obtained to respond and generate a corresponding answer; by integrating the preprocessing module, the retrieval module and the reordering module of the financial document, the defects of the traditional method in the aspects of processing heterogeneous financial data and improving the retrieval recall rate and correlation are effectively overcome.

The invention provides an intelligent interactive question and answer method and system based on multi-modal large model intention recognition, and relates to the technical field of intelligent question and answer, and the method comprises the steps of feature extraction, cross-modal semantic mapping, intention matching, key information extraction and response generation, achieves the unified processing of multi-modal information, can accurately recognize the intention of a user, and improves the user experience. And the association network is dynamically constructed to extract key information, so that the accuracy and semantic coherence of intelligent questions and answers are improved, and the man-machine interaction experience is enhanced.

A method for using a local large language model (LLM) within a user's secure computing environment is disclosed. The LLM operates behind a firewall to prevent transmission of sensitive data, and utilizes an encrypted vector database and artificial intelligence techniques for content retrieval, response generation, and task anticipation. This system can be used on mobile, wearable, vehicle, or IoT devices and offers various services such as health monitoring, financial advice, automated communications handling, and personalized daily activity optimization. It also has the ability to detect fraud, fine-tune responses using augmented user data, assist in negotiations, identify personal interests, and provide health recommendations based on dietary and physical activity data.

The invention relates to the technical field of intelligent customer service, and provides an AI intelligent customer service system based on a large model, and the system is characterized in that an unstructured text processed by a multi-source knowledge fusion subsystem is reconstructed into structured knowledge entries with a multi-dimensional label system, intention classification and context association, and the structured knowledge entries are dynamically integrated into an enterprise knowledge graph; the response generation subsystem is used for receiving the content queried by the user, analyzing the intention through a deep semantic understanding model in combination with an enterprise knowledge graph, and dynamically maintaining the context in combination with a multi-round dialogue state tracking technology; meanwhile, emotion dimension analysis is carried out on the content, and a personalized response is generated by fusing user service feedback; and the autonomous optimization subsystem dynamically adjusts the weight distribution of structured knowledge entries in the enterprise knowledge graph and the priority of process nodes in combination with an attribution analysis result, and triggers a knowledge updating and API process reconstruction mechanism. The method has self-learning and continuous optimization capabilities, and continuously improves the service quality and the user experience.

A system includes one or more processors to receive a natural language query; execute the first language model using the natural language query to generate a text-based response to the natural language query; segment the text-based response into a plurality of segments each corresponding to a different fact-based response to the natural language query; convert each of the segments into a set of queries; generate a query response to each query by using the query to search a data repository; generate a factuality score of the query responses for the text-based response to the natural language query; generate an aggregate factuality score for the natural language query based on the factuality score for each query generated for each of the plurality of segments; and executing decontextualized atomic decomposition responsive to determining the factuality score does not satisfy a threshold.

The invention belongs to the technical field of intelligent power grids, and particularly relates to a circuit breaker control method, system and device of the intelligent Internet of Things, and the method comprises the steps: obtaining the operation data of a sensor; data extraction is carried out on the operation parameters of the sensor, the operation parameters are transmitted to a cloud server through the wide area Internet of Things for analysis, and whether the circuit breaker has an abnormal condition or not is judged according to a preset rule and a historical data training model; if an abnormal condition exists, based on a risk assessment matrix and real-time data monitoring, generating a safety control strategy and establishing a strategy library, performing different-level response according to an abnormal type, and generating a control instruction; and after an instruction is received, dynamically adjusting parameters according to the state of the circuit breaker, interactively verifying the instruction through the block chain node, operating the circuit breaker according to a safety control strategy after the instruction passes, and meanwhile, feeding back and adjusting the strategy. Therefore, the problems that in the prior art, the data processing dimension is single, strategy response lags behind, and the abnormal type recognition capacity is insufficient are solved.

A method for using a local large language model (LLM) within a user's secure computing environment is disclosed. The LLM operates behind a firewall to prevent transmission of sensitive data, and utilizes an encrypted vector database and artificial intelligence techniques for content retrieval, response generation, and task anticipation. This system can be used on mobile, wearable, vehicle, or IoT devices and offers various services such as health monitoring, financial advice, automated communications handling, and personalized daily activity optimization. It also has the ability to detect fraud, fine-tune responses using augmented user data, assist in negotiations, identify personal interests, and provide health recommendations based on dietary and physical activity data.

The invention provides a security event association analysis and question answering method and system and a medium, and the method comprises the following steps: context-aware query completion: receiving an original query input by a user, obtaining a historical record of a current dialogue, and forming a context enhanced query according to the original query and the historical record of the current dialogue; dynamic task identification: outputting a prediction task model according to the context enhancement query in combination with a dynamic task identification strategy; multi-dimensional retrieval: performing multi-dimensional retrieval on the prediction task model to obtain a final knowledge context packet; and knowledge-driven response generation: generating a knowledge-driven response based on the knowledge context packet, and outputting a final security analysis report after the generated content passes verification. According to the method, efficient, accurate and explainable intelligent association analysis of the multi-source heterogeneous security data is realized by constructing a multi-dimensional knowledge base, designing a dynamic task recognition mechanism and realizing context-aware query completion.

Systems and methods described herein relate to the use of generative artificial intelligence to facilitate rendering of user interface elements in a user interface associated with a digital assistant. A backend response is automatically generated in response to user input provided via the user interface associated with the digital assistant. Prompt data is generated. The prompt data includes an instruction to generate an intermediate representation of an output data structure supported by the digital assistant. The prompt data is provided to a generative machine learning model to obtain the intermediate representation. The intermediate representation is processed to obtain the output data structure. One or more user interface elements are rendered based on the output data structure. The one or more user interface elements present the response data via the user interface associated with the digital assistant.

Systems and methods for training and using large language models to respond to queries and cascading to new models when their performance falls below a threshold during the response generation cycle are described. The methods involve receiving and analyzing a query using heuristics to determine the query's categories and a level of granularity at which its response is to be evaluated. Selecting a language model based on the query analysis and during the generation of the response, evaluating the model's performance for its ability to predict the next segment in a response. The methods score the evaluation and use the score to determine whether the language model's performance exceeds a confidence threshold. If it does not, then during the response is being generated, e.g., at a point before the response generation is completed, cascading from the model to a different model that can perform at a higher confidence level.

Methods and systems for managing data processing systems are disclosed. A data processing system may include and depend on the operation of hardware and / or software components. Inference models may be implemented to predict future system infrastructure outcomes (e.g., component failures) using information recorded in logs that reflect the operation of the components. However, the models may be complex “black boxes” and may generate critical outcome predictions for downstream consumers without explanations of how the predictions are determined, resulting in downstream consumers having low confidence in the predictions. Therefore, hidden knowledge (e.g., structured knowledge attributes) of the models may be extracted and / or used to understand the underlying processes that the models use to predict the system infrastructure outcomes. The hidden knowledge may be stored in a repository and may be provided for downstream use in order to increase the likelihood of preventing and / or mitigating future data processing system failures.

The invention relates to the crossing field of industrial control system (ICS) safety and artificial intelligence, and particularly discloses a PLC high-interaction honeypot system based on multi-agent task splitting and RAG enhancement, which adopts a localized multi-agent collaborative architecture based on edge computing and is composed of a high-simulation equipment layer and an intelligent decision-making layer. The high-simulation equipment layer comprises a PLC dynamic mirror image, an HMI interface and a sensor data generator, and an active trapping environment is constructed through protocol fingerprint confusion and virtual and real data fusion technologies. The decision-making layer deploys a multi-agent task scheduling engine, integrates four kinds of agents including protocol analysis, behavior analysis, threat assessment and response generation, and realizes attack context perception and strategy dynamic generation based on a local RAG knowledge base. The load balancing agent dynamically allocates tasks according to equipment resources, and cooperates with offline knowledge update (USB flash disk encryption synchronization threat features) to form a closed-loop defense system, thereby ensuring physical isolation of an industrial network and realizing high-fidelity active defense.