112 results about "Context based" patented technology

The invention relates to the technical field of natural language processing, in particular to a context-based Prompt generative model optimization system, which comprises a context analysis module, a cue word generation module, a context optimization module, a semantic check module and a structure reconstruction module. According to the method, the context path and the semantic hierarchy information of the semantic unit are introduced, the fine degree of semantic matching degree recognition is improved, semantic guide deviation caused by statement template solidification is avoided, the cue words are recombined in combination with the semantic coherence weight and the logic dependency relationship, and the recognition accuracy is improved. The consistency and expression accuracy of the prompt content in the context are enhanced, the prompt word insertion sequence and connection mode are dynamically adjusted through a semantic conflict detection and structure rechecking mechanism, coherence and stability of a semantic structure and controllable generation of the prompt content are kept, semantic conflicts and expression chaos caused by static matching are effectively avoided in the generation process, and the generation efficiency is improved. And dynamic adaptation of prompt configuration and smooth optimization of language output are integrally realized.

The invention provides an intelligent education resource sharing and authority management system based on a block chain, and belongs to the technical field of intelligent education, and the system comprises a block chain network layer, a resource right confirmation module, an intelligent contract module, a distributed storage network, a cross-chain interaction gateway and a dynamic optimization module, comprising a resource authentication chain, an authority management chain and a cross-chain interaction chain, and the chains realize data intercommunication through relay nodes; the resource right confirmation module adopts a three-level Hash nested structure to generate a non-tampering digital fingerprint, and binding and uplink the educational resource metadata and the creator DID; the intelligent contract module comprises a dynamic authority management contract and a resource transaction contract, and supports an access control strategy based on context awareness. According to the intelligent education resource sharing system, the core problems that the right of the education resources is difficult to confirm, the sharing efficiency is low, and the right management is inflexible are solved, and the safe, intelligent and extensible intelligent education resource sharing system is constructed.

The invention relates to a large language model dynamic routing method and device based on context learning model characterization and a readable storage medium. Query is embedded and mapped to a language model input space by using a projection model, semantic alignment is realized, a representative evaluation set covering multi-dimensional capability is automatically screened from a benchmark question bank, and the representative evaluation set is used for evaluating the multi-dimensional capability. Performance characteristics of the model on an evaluation set are efficiently obtained at a time, and high-quality context model capability representation is formed; then real-time query embedding and context model capability representation are combined, a lightweight routing language model is used for supervised learning, so that the fine-grained model distinguishing capability is achieved, an increment embedding updating mechanism is designed, and when a new model is accessed or an old model is upgraded, cold start can be rapidly completed only through a very small number of fixed questions, so that the efficiency is improved. The calculation and maintenance cost is greatly reduced, and the accuracy, real-time performance and flexible expansibility of model routing are effectively improved.

The invention relates to the technical field of intelligent questioning and answering, in particular to an intelligent questioning and answering method based on context semantics and dynamic retrieval, which comprises the following steps of: splicing data to form a complete dialogue text, extracting a dialogue core theme by using a large model in combination with a thinking chain and small sample learning, and extracting the dialogue core theme based on the dialogue text and a current question. Generating a dynamic keyword set in combination with BM25 and BERT MLM, finally splicing the current problem, the keyword set and the core topic into a multi-dimensional semantic representation, and vectorizing the multi-dimensional semantic representation by using a BGE-M3 embedding model to generate an embedded vector; by combining context topic extraction and dynamic keyword generation technologies, the system can capture core intentions and semantic changes in multiple rounds of dialogues in real time, so that knowledge base retrieval does not depend on fixed keyword matching any more, but dynamically adjusts a retrieval strategy according to a dialogue context; therefore, the matching precision of the question and the knowledge base content is remarkably improved.

The invention discloses a vertical federal learning feature selection method based on context awareness, and belongs to the technical field of artificial intelligence and data privacy protection. According to the method, firstly, an unsupervised sparse network is utilized at a client to initialize the importance of local features so as to accelerate convergence and reduce calculation complexity; and then, obtaining the embedded representation of each client in a pre-training stage, and screening the embedded representation by combining context features through a server side, thereby indirectly identifying key features. In the feature selection stage, the client side performs local feature screening according to the significant embedded index issued by the server, and the influence of irrelevant features on calculation and communication is further reduced. According to the invention, an attention mechanism is introduced to dynamically evaluate contributions of different participants, so that fair weight distribution is realized. According to the method, through staged joint optimization, the communication and calculation cost in the federation training process is effectively reduced, and meanwhile, the prediction precision and interpretability of the model are improved.

The invention provides a multi-objective optimization method fusing a classifier and an active learning strategy, and belongs to the technical field of artificial intelligence and optimization design, and the method specifically comprises the steps: obtaining a sample data set containing a plurality of target performance function values; performing non-dominated sorting on the sample data set to extract a Pareto frontier point set, and extracting geometric features from the point set as a geometric feature vector sequence; using the geometric features and the corresponding convex marks to train a classifier model of a Transform architecture, wherein the classifier model supports a multi-head attention mechanism and a position coding structure; judging the convex confidence coefficient of the current Pareto front by using a classifier model, and obtaining a candidate scheme; and inputting the candidate scheme into a double-attention mechanism prediction model based on context reasoning, and predicting the multi-target performance of the candidate scheme. According to the method, the experiment frequency can be reduced, the target performance can be accelerated to be achieved, and the intelligence and efficiency of the multi-target optimization process are improved.

The invention relates to the technical field of natural language processing (NLP), in particular to an intelligent self-adaptive document segmentation method oriented to an RAG system. The method comprises the steps that S1, a deep learning model is adopted to dynamically adjust the size and the step length of a window according to document content density, structure information and context semantics; s2, in combination with a window representation result, calculating the context semantic similarity of the segmentation blocks by adopting a language model, and automatically adjusting the size of an overlapping region based on the context semantic similarity; and S3, based on a context segmentation block representation result, associating the segmentation block with the context by introducing a BERT model, automatically adjusting an overlapping part and a window size, and optimizing a segmentation effect. The invention aims to provide the intelligent self-adaptive document segmentation method oriented to the RAG system so as to improve the document segmentation efficiency and quality and optimize the recall rate and the generation quality of the RAG system.

The invention provides an embedded data synthesis method and device fusing retrieval and large model distillation and a medium. The method comprises the following steps of: preprocessing an unstructured document in a vertical field, and dividing the unstructured document into multi-granularity text blocks with a hierarchical association relationship; forming a context based on the combination of the multi-granularity text blocks, injecting disturbance information corresponding to the priori knowledge in the vertical field into the context, calling a generative model to generate a retrieval query according to the context, and determining a target text block corresponding to the retrieval query as an initial positive sample; false negative sample text blocks are filtered according to the incidence relation between the text blocks, and a positive sample set and a negative sample set are formed; and constructing a comparative learning training sample, and training the semantic representation model by using the comparative learning training sample to generate an embedded vector for the retrieval task. According to the method, the retrieval task construction efficiency and authenticity can be improved, the positive sample coverage integrity is improved, and the contrast learning training stability and retrieval precision are enhanced.

Systems and methods for advanced event ranking and correlation for threat detection. A method includes real-time processing of events with stateful threat detection, combining immediate detection capabilities with sophisticated threat analysis. A method further includes multi-stage processing in a detection engine, where generic events from endpoint detection and response (EDR) agents are scored and enriched to provide extended context based on machine learning models for event scoring, enriched events correlation, and applying security rules to detect threats.

Systems and methods are disclosed for optimizing a first machine learning (ML) model using a second ML model. In some examples, a system generates modifications to the first ML model. Each of the modifications is associated with a respective node of the first ML model. The system tracks a processing characteristic corresponding to modified variants of the first ML model (corresponding to the modifications) processing a test dataset to generate respective results. In some examples, the system trains the second ML model based on context (the modifications and the respective changes). The system identifies, using the second ML model and based on the context (e.g., the training), a modification to the first ML model that adjusts the processing characteristic of the first ML model in a predetermined direction. The system modifies the first ML model according to the modification to generate a modified first ML model.

System and method including an artificially intelligent assistant are described. An example method includes, in response to initiation of an artificially intelligent assistant at a head-wearable device, capturing contextual data. The contextual data includes one or more of image data, audio data, and / or sensor data. The method includes determining, based on the contextual data, a contextual cue, and providing a portion of the contextual data and a portion of the contextual cue to the artificially intelligent assistant. The method includes determining, by the artificially intelligent assistant, a user request based on the portion of the contextual data and the contextual cue, and receiving a response to the user request. The response is generated using a machine learning model. The method further includes causing the head-wearable device to present the response.

The invention relates to the technical field of data processing, in particular to a large model reasoning optimization method based on context incremental updating, which comprises the following steps: processing a multi-modal data stream through timestamp alignment and a filtering algorithm, extracting features by adopting a shared encoder and a private encoder, and realizing feature decoupling through a depth information bottleneck principle. A dynamic emotion map is constructed by using Gaussian process regression and a random process algorithm, and self-adaptive updating control is realized by combining meta-learning and Bayesian optimization. Incremental state management is realized by adopting a neural Turing machine, reasoning consistency is guaranteed through a generative adversarial network, model parameters are optimized in combination with a digital twin system and reinforcement learning, and a mental health service response is finally generated through a conditional generation model and hierarchical reinforcement learning. According to the method, the problem of asynchronism of multi-modal emotion feature dynamic evolution and context increment updating is effectively solved, accumulated drift of emotion state tracking is eliminated, and the continuity of reasoning logic is guaranteed.

The invention discloses a target-driven navigation method and device based on context awareness and imitation learning, and the method comprises the steps: recognizing an object instance of interest in an image based on a target detector DETR, and constructing an object graph; based on context perception graph reasoning, in the navigation process, dynamic context information such as images, actions and memories serves as guidance, object features are projected to hyperplanes of corresponding contexts by means of a TransH method at each time step, the object relation is dynamically learned, and an intelligent agent can better understand the complex environment. Based on visual representation of Transform, visual features and graph features are fused, and spatial semantic information of the environment is better captured. Based on generative adversarial imitation learning, a new dynamic reward function is designed, and an intelligent agent is helped to avoid a deadlock state in combination with environment rewards. Based on a standard asynchronous dominant actor-commentator algorithm, an effective navigation strategy is trained by using a new reward function, and the navigation success rate and efficiency of the intelligent agent in an unfamiliar environment are improved.

The invention discloses a test code repairing method which is applied to a code development platform and comprises the steps that a test code corresponding to a source code is obtained, then the test code is executed, execution information of the test code is obtained, and the execution information comprises abnormal stack tracking information output when the test code is executed; then error positioning is conducted on the test code according to the execution information, position information of an error code is obtained, context information is extracted according to the position information of the error code, and the context information comprises at least one of an error test case, error description or error content; and inputting a prompt constructed based on the context information into a language model for reasoning to obtain a first repair code. According to the method, error positioning is carried out by combining execution information, context information is extracted according to position information of error codes, and based on the context information, more accurate and complex repair codes are generated through an advanced language model so as to adapt to various complex error scenes, and the repair efficiency and accuracy are improved.

The invention provides a dialogue method and system based on context awareness, electronic equipment and a storage medium, and the method comprises the steps: carrying out the vectorization of a current dialogue instruction, obtaining a current dialogue instruction vector, calculating the correlation between the current dialogue instruction and N historical dialogue instructions, and obtaining a plurality of first correlation; determining whether to call the context based on the plurality of first correlations; calculating the correlation between the current dialogue instruction and the N historical dialogue instructions to obtain a multi-dimensional correlation score vector, and determining a plurality of second correlations based on the multi-dimensional correlation score vector; for each second correlation, performing multi-dimensional feature extraction on the historical dialogue instruction based on the second correlation to obtain a multi-dimensional feature vector corresponding to the historical dialogue instruction; obtaining a corresponding target input vector based on the target input sub-vector corresponding to each dimension; and determining a target answer based on the target input vector and the current dialogue instruction vector. The accuracy of reply in the dialogue process can be improved.

The application discloses a large language model prompt word injection attack detection method and device based on context learning, and belongs to the technical field of artificial intelligence, and comprises the following steps: based on a Bert pre-training model, inherent features and dependency relationships between different levels and different labels are learned by introducing a label-based attention module, a multi-level, multi-label and fine-grained classification model for prompt word injection attack is designed, and accurate identification of the prompt word injection attack is realized.Meanwhile, according to the context learning, the prediction ability of the classification model is combined with the ability of the large language model, and the defense ability of the large language model to the prompt word injection attack is improved.The application can automatically detect the prompt word injection attack, improve the effectiveness and comprehensiveness of detection, and can be effectively applied to the field of large model security detection.

A training method of a conversation model according to various example embodiments of the present disclosure may include identifying a first context, identifying a first response set corresponding to the first context based on a first model, identifying a response subset selected from the first response set based on a gold response corresponding to the first context and training a second model based on the first context information and the response subset.

The invention relates to a home violation risk identification method, system and device based on artificial intelligence and a medium. The method comprises the following steps: preprocessing audio data to obtain a voice segment; performing automatic voice recognition on the voice segments to obtain a dialogue text sequence, and performing acoustic feature extraction to obtain a time sequence acoustic feature sequence; performing key feature extraction based on context semantics and risk knowledge on the dialogue text sequence to generate a semantic feature vector; performing deep emotion mode learning on the time sequence acoustic feature sequence to generate an acoustic feature vector; performing multi-modal fusion on the semantic feature vector and the acoustic feature vector to obtain a fusion feature vector; and carrying out collaborative risk judgment on the fused feature vector to generate a result containing high, medium and low risk levels and corresponding judgment confidence coefficients. By adopting the method, the limitation of single modal analysis can be overcome, and the home violence risk can be identified more comprehensively and accurately.

This application proposes a model-based question-answering method and apparatus for generating context based on grammatical structure. The method includes: selecting multiple initial code fragments related to the question information from a target code library; obtaining a source code file containing any one of the initial code fragments; locating a first code block node corresponding to the initial code fragment from the abstract syntax tree of the source code file; locating all ancestor nodes of the first code block node from the abstract syntax tree and extracting the code structure information of each ancestor node; generating a target code fragment based on the code structure information of the first code block node and all ancestor nodes; concatenating multiple target code fragments to obtain a target context; and inputting the target context into a question-answering model so that the model outputs answer information based on the target context. The embodiments of this application can effectively improve the question-answering performance of the model.

A system for capturing patient data. The system captures context data of the patient. The context data includes at least one of visual data captured by a camera and audio data captured by a microphone. The system generates a context based on the context data, retrieves one or more guidelines based on the context, sends the one or more guidelines to a machine learning model, and receives instructions from the machine learning model. The system captures the patient data using at least one of the camera and the microphone based on the instructions from the machine learning model. The system stores the patient data in an electronic medical record of the patient.

Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and / or the like for performing context-based document classification prediction using a hierarchical attention-based keyword classifier machine learning framework. Certain embodiments of the present invention utilize systems, methods, and computer program products that perform context-based document classification prediction using at least one of techniques using contextual keyword classifications, techniques using attention-based keyword classifier machine learning framework, techniques using a greedy matching indicator, and / or the like.

The subject technology relates to context-based response formulation for retrieval-augmented generation systems. An example method facilitating context-based response formulation for retrieval-augmented generation systems includes supplementing a query provided to a machine learning model with supplemental entity data, resulting in an augmented query, where the supplemental entity data is determined based on context information associated with the query and expected entity types associated with a determined intent of the query. The method can further include determining an estimated degree of error associated with a document retrieved by the machine learning model in response to the augmented query, and facilitating, in response to the estimated degree of error being lower than a threshold degree of error, generating a response to the query based on the document.

The invention discloses a scientific calculation and language generation collaborative reasoning method and system based on a physical separation hybrid expert architecture and a storage medium, and relates to the technical field of large model and scientific calculation fusion. According to the method, a novel architecture named PiMoE is provided, and intelligent collaboration of a language task and a numerical calculation task on Token granularity is achieved by integrating a frozen high-precision scientific calculation expert module, a text-to-calculation alignment module and a dynamic token router module. Wherein scientific calculation experts pre-train and freeze parameters on specific field data, and calculation precision and interpretability are ensured; the text-to-calculation module learns to map natural language input into numerical representation which can be processed by experts; the token router then dynamically decides, based on context semantics, that each Token should be generated by an expert or LLM. The training process adopts a three-stage decoupling strategy: in the first stage, independently training and freezing an expert model; in the second stage, a text-numerical value alignment module is optimized; and in the third stage, a router is trained to realize dynamic scheduling of experts and LLMs. During reasoning, the system is seamlessly switched between language generation and scientific calculation according to the semantic context, so that high precision of complex calculation is guaranteed, and semantic reasoning and generation capabilities of LLM are kept. According to the method, the problems that a large model is insufficient in precision, uncontrollable and unextensible in a scientific calculation scene are effectively solved, and deep fusion and dynamic collaboration of language understanding and numerical reasoning are realized.

The application discloses a zero-shot abnormal image detection method based on a learnable prompt. A learnable prompt generation module based on context optimization is designed, which contains a learnable prompt and an image abnormal state prompt that can be optimized. A multi-level visual coding feature of a to-be-detected image is obtained by using an image coding network of a visual language large model, and a text feature of a learnable prompt embedding is obtained by using a text coding network. A multi-level cosine similarity between the visual coding feature and the text feature is calculated to construct an image abnormal area calculation module, so that an abnormal area of the to-be-detected image is obtained. The learnable prompt avoids the complexity and instability of manually designed prompts, improves the accuracy of image abnormal detection, guarantees the effectiveness and efficiency of zero-shot learning, and greatly reduces the cost of pre-training of a visual language large model to a downstream task.

A method, non-transitory computer-readable storage medium and system is disclosed for using context-based dictionaries to search through multimedia data using input that specifies tags, words, phrases, descriptions, environments, emotions, sentiments, multimedia objects or content, or other relevant attributes. The system retrieves original content, analyzes and processes it, and presents to the user synchronized multimedia content and text content that is automatically tagged for searching. The system creates dictionaries containing word definitions and information that have been customized according to context; in addition, the system creates textual and non-linguistic attributes that enable and enhance searching functions; moreover, it enables modification of the dictionary entries as well as its searching functions through a feedback loop that may include input from human users and artificial intelligence programs; furthermore, the system may be used to create or modify a linguistic or a multimedia instantiation of a story.

The invention discloses an industrial control instruction stream anomaly detection method and device based on deep learning, and relates to the technical field of energy industry internet security. The method comprises the following steps: restoring to generate an interactive session with a complete context based on a directionally collected industrial control instruction and an equipment state data stream; performing semantic structured processing on the instruction in the interaction session to generate structured semantic information which can be understood by a machine; taking the interaction session and the corresponding structured semantic information as a training sample, and constructing and training an instruction stream semantic model and an instruction stream execution effect prediction model; processing the real-time industrial control instruction stream, and inputting the processed real-time industrial control instruction stream into the instruction stream semantic model and the instruction stream execution effect prediction model to obtain a prediction result; and judging an anomaly detection result of the real-time industrial control instruction flow according to the output prediction result and an anomaly judgment rule.

The invention relates to a method for operating an assistance system (51) in vehicles (50) of a vehicle fleet, wherein in each vehicle (50) of the vehicle fleet: at least one configuration parameter (30) of the assistance system (51) is estimated based on context descriptors (10) using a trained local machine learning model (20L), wherein submodels (22) of the machine learning model (20L, 20G) are assigned to a data domain defined based on the context descriptors (10), wherein the local machine learning model (20L) is trained based on training data (15) collected in the vehicle (50), wherein only parameters (21L) of the assigned submodels (22) and / or associated connections are modified, and wherein the parameters (21L) of these submodels (22) and / or the associated connections are transmitted to a backend server (60) after training.and wherein in the backend server (60): a global machine learning model (20G) is trained based on the parameters (21L) transmitted by the vehicles (50), wherein parameters (21G) of the trained global machine learning model (20G) are transmitted to the vehicles (50) of the vehicle fleet, and wherein the respective local machine learning models (20L) are updated based on the transmitted parameters (21G). Furthermore, the invention relates to a system (1).

Context rules, machine learning, and user interface in context-based search techniques are described. In an implementation, inputs are received via a user interface describing a plurality of contexts associated with user consumption of digital content. A plurality of context rules are generated based on the inputs and a plurality of rule search results are generated based on context data. The context data details the plurality of contexts associated with user consumption of the digital content. One or more machine learning models are trained based on the context data. A determination is made that a transition point has been reached, and in response, a transition is performed between use of the plurality of context rules and use of the one or more machine-learning models in generating a plurality of subsequent search results.