137 results about "Context window" patented technology

The invention discloses an intelligent education robot question answering system based on voice recognition and a knowledge graph, and particularly relates to the technical field of artificial intelligence. The method comprises the following steps: performing feature extraction on a user voice signal to obtain a text sequence and a multi-modal context feature; recognizing subject domain judgment and question answering intentions based on supervised classification and keyword rule fusion, and outputting a subject domain prior probability and a question answering target vector; determining polysemy words in the text sequence by using a context window, generating a semantic item sequence and semantic item confidence, constructing a subject domain sub-graph based on a subject domain prior probability, and obtaining a candidate reasoning path and a path scoring vector; determining a target teaching concept and an optimal reasoning path by combining Bayesian inference and consistency verification; generating a personalized question answering result aiming at the question asked by the user through fact retrieval and knowledge derivation in combination with the question answering target vector; accurate and efficient intelligent teaching question answering can be realized, and question answering accuracy and intelligent interaction capability of the education robot are effectively improved.

The invention relates to the field of intelligent report generation, in particular to an intelligent insight report generation method and system based on an AI large model, and the method comprises the steps: inputting an insight demand, and generating an insight data package comprising insight contents, associated data and industry labels; extracting a basic keyword set of the insight data packet to form a mixed feature code; after mixed feature coding preprocessing, weight distribution is carried out; and after weight distribution of the AI large model, injecting a high-weight feature vector into a semantic understanding core layer, injecting a low-weight feature vector into a logical reasoning layer, and outputting analysis data to form an intelligent insight report. According to the method, word embedding parameters are optimized according to field semantic characteristics, a parameter verification mechanism is introduced, field text characteristics are adapted by adjusting vector dimensions, context windows and low-frequency vocabulary filtering threshold values, window parameter validity is verified through cosine similarity, word frequency threshold value reasonability is verified through standard deviation, and field text characteristic matching is achieved. And it is ensured that the feature vectors can accurately capture domain-specific semantics.

The invention relates to a knowledge enhancement method and system based on a context structure. The method comprises the following steps: acquiring a query request input by a user; screening candidate evidences related to the query request from a pre-constructed case knowledge base based on multi-view retrieval; performing weighted calculation on a retrieval result of each view to generate an evidence score of each candidate evidence; screening based on the evidence scores to obtain a candidate evidence set and preprocessing the candidate evidence set; calculating the value and length of each candidate evidence in the pre-processed candidate evidence set; constructing an evidence selection problem based on a preset context window value and the value and length of each candidate evidence; solving the evidence selection problem to obtain an evidence subset with maximum value; generating a context structure based on the evidence subset with the maximum value and a preset prompt template; and inputting the context structure into a general language model for knowledge enhancement, and generating a knowledge enhancement result.

The invention relates to the technical field of translation, and discloses a translation calibration method based on big data, which can accurately identify semantic deviation in a multi-meaning scene, for example, accurately judge that'cell 'should be translated into'cell' instead of'house 'in a biological text. The system can detect the language field mismatching problem of spoken expression in the official file, and provides term correction suggestions conforming to industry standards. Aiming at technical terms with multiple meanings in legal clauses, the calibration process can be combined with context window analysis to select an optimal translation scheme, the omission ratio of manual review is remarkably reduced, continuous optimization and cross-language knowledge sharing of a translation calibration model are realized, and the accuracy of translation calibration is improved. The problems that a traditional system is lagged in updating and low-resource language performance is insufficient are solved.

A query is received from a client device. A subset of documents relevant to the query is determined in part by determining an optimal configuration for the query. The subset of documents is inputted in a context window for a response generator and the query is inputted as a prompt for a query response. The query response received from the response generator is outputted to the client device.

The invention belongs to the technical field of computer information security, and particularly relates to a log auditing technology based on multi-agent cooperation and an implementation framework thereof, which comprises the following steps that: a task decomposition agent performs structured modeling and logic slicing on original log data by utilizing a thinking chain reasoning mechanism to obtain a log auditing result; a complex internal threat detection task is decomposed into a plurality of subtasks with clear logic and independent semantics, and each subtask corresponds to a specific log analysis problem; and the tool generation agent automatically generates a reusable exclusive analysis tool by adopting an example-based programming normal form based on the semantic target and the input structure of each subtask. By constructing a three-layer collaborative architecture of a task decomposition agent, a tool generation agent and a task execution agent, the context window limitation of a single language model during processing of an ultra-long log sequence is effectively broken through, and structured and modular analysis of complex internal threat behaviors is realized.

The invention relates to the technical field of artificial intelligence, in particular to an adaptive context processing method and system for a large language model. The method comprises the following steps: collecting multi-source candidate context segments related to current user query; performing utility evaluation on each candidate fragment, outputting a quantized utility score, and performing multi-granularity compression on each fragment based on the utility score and a preset quality constraint to obtain a compressed fragment set; taking the maximization of the total utility score as a target, taking the condition that the total token cost is less than or equal to the global token budget as a constraint, and carrying out optimization selection to obtain an optimal context combination; and inputting the optimal context combination into a large language model to generate an output result for the current query. By applying the method, the context window management of the large language model can be optimized, the adaptive context processing capability of the information utilization efficiency is improved, and the problems of context window limitation, value judgment and the like are solved.

The invention provides an agent memory management method and device based on a decoder memory component, and the method comprises the steps: obtaining user input data; inputting the user input data into a pre-constructed large language model to generate a user response; asynchronous monitoring is carried out on the user response, and multi-source information fed back by the user is extracted; generating a training queue according to the multi-source information; and performing incremental training on the training queue and then performing knowledge solidification to realize intelligent agent memory management. According to the method and the device, the auxiliary small model is introduced, and the long-term memory is stripped from the context window of the large language model, so that flexible management and persistent storage of the long-term memory are realized, new knowledge can be efficiently captured, and loss of time sequence structure information is avoided.

The invention discloses a dialogue memory management method, system and device and a storage medium. In the scheme, newly added dialogue data generated by dialogue interaction is received and cached to a queue to be updated; and asynchronously extracting memory information of the data in the queue in batches according to a preset period to obtain candidate memory information. And updating the long-term memory bank based on the candidate memory information. And when a new dialogue request is responded, obtaining a request context from the context window, and retrieving related memory information from the updated long-term memory library according to the request context. According to the method, memory updating and real-time response are decoupled through a cache and asynchronous batch processing mechanism, the response delay is remarkably reduced while the memory accuracy and consistency are guaranteed, and the resource utilization efficiency and the system stability are improved.

The invention discloses a real-time 8K video sensing super-resolution reconstruction method and system, and the method comprises the steps: S1, carrying out the serialized analysis of an input low-resolution video stream through a space-time window mechanism, constructing a space-time context window containing a target frame and an adjacent frame, and obtaining a low-resolution frame sequence set; s2, performing multi-scale spatio-temporal feature extraction on the low-resolution frame sequence set by adopting a shallow 3D convolutional neural network to obtain a spatio-temporal feature map; s3, processing the spatial-temporal feature map through two parallel modules of motion compensation analysis and texture complexity analysis, and generating a perception attention map reflecting visual perception importance; and S4, performing super-resolution reconstruction on the spatial-temporal feature map by using a depth residual generation network guided by a perceptual attention map, and outputting a high-resolution 8K video frame. According to the 8K super-resolution reconstruction method, high-quality 8K super-resolution reconstruction of a low-resolution video can be realized, the processing efficiency is remarkably improved while the reconstruction quality is ensured, and the application requirement of real-time 8K video processing is met.

The invention discloses a domain knowledge content generation method and system based on retrieval enhancement generation, and belongs to the technical field of natural language processing and knowledge generation. Performing fuzzy semantic retrieval in the structured knowledge base to obtain semantic matching entries and calculate semantic relevancy; constructing a semantic fusion representation vector to form an enhanced representation set; performing context alignment with the query vector, and extracting a causal path fragment with the maximum weight; inputting the causal path and the query vector into a large language model, and executing a condition generation operation; analyzing and judging whether the generated content has term jump or logic chain scission or not based on the term dependency graph, if so, adjusting a context window and regenerating, and finally outputting professional content meeting dependency consistency; according to the method, the accuracy and logic consistency of professional field text generation are effectively improved, and the method is suitable for knowledge generation tasks in complex semantic scenes.

The invention provides an enhancement method for a question answering system during testing based on reinforcement learning, and belongs to the technical field of natural language processing. The method aims at solving the technical problems that an existing large language model (LLM) faces knowledge blind areas, reasoning chain breakage and context length limitation in a question and answer (QA) task, an existing fine adjustment method is high in calculation cost and damaged in generalization ability, and a prompt strategy seriously depends on a limited context window and lacks long-term memory. The method comprises the following steps: firstly, collecting reflection experience through multiple attempts and a failure reflection mechanism, and constructing an experience library; thirdly, performing text embedding, clustering and semantic abstracting on experiences in the experience library, and constructing an external memory library; secondly, a memory selection process is formalized into a Markov decision process (MDP), reinforcement learning (such as a PPO algorithm) is used for training a strategy agent, and the agent is optimized with a current task as a state, with memory item selection as an action and with LLM answer correctness as a reward; finally, in a test time (inference) phase, the agent dynamically selects the most helpful memory entry according to the new task and integrates it into the hint of the LLM to generate a final answer. According to the method, under the condition that LLM internal parameters do not need to be updated, the question and answer accuracy is dynamically improved, the calculation overhead is reduced, and the limitation of a context window is effectively overcome.

The application relates to the technical field of large language model application, in particular to a fault-tolerant processing method and system for super-long text in a large model service and a storage medium. The method comprises the following steps: obtaining a to-be-processed super-long text and a maximum Token threshold of a large model context window, completing Tokenization and judging whether the Token is out of limit; starting a multi-level alternative solution containing fast compression, dynamic compression and chat history compression; starting an error recovery mechanism containing hierarchical exception processing, intelligent degradation and parameter verification; outputting a target text with a compliant Token number; the system comprises a text acquisition module, a multi-level alternative solution execution module, an error recovery module and an output module; the storage medium stores a computer program, and the computer program realizes the above method when executed, can be adapted to multiple models, meets the industrial super-long text processing demand, and solves the problems of the absence of a fault-tolerant mechanism, Token out-of-limit errors caused by insufficient boundary processing and unstable reasoning service in the prior art.

The invention relates to an intelligent collecting and processing method for open source intelligence data crawling, and belongs to the technical field of data processing. According to the method, after open-source information data is crawled by a traditional crawler method, an HTML tag exceeding the length of a context window of a large language model in the open-source information data is subjected to iterative segmentation from coarse to fine, and segmentation blocks with context relation are recombined into single segmentation blocks in each time of segmentation; and after each finally obtained segmentation block does not exceed the length of the context window, stopping segmentation iteration, and performing semantic recognition on a segmentation result by using a large language model to complete the collection of open source intelligence data. According to the method, the acquisition speed of the open source information data is ensured by a traditional crawler method, the recognition accuracy of the large language model on the HTML tag is ensured to the greatest extent on the basis of adaptive segmentation on the HTML tag, and finally, the acquisition speed and accuracy of the LLM-based crawler method on the open source information data can be improved.

The application discloses a code library UML diagram automatic generation method and system based on cooperation of abstract syntax tree and large language model, comprising an AST analysis and structure extraction layer, which is used for being responsible for abstract syntax tree analysis on source files in the code library and extracting skeleton structure information of the code library, and a large language model semantic analysis layer, which is used for receiving structured code skeleton data output by the AST analysis layer and submitting the structured data to the large language model for semantic analysis through a carefully designed prompt word (Prompt), wherein the application extracts structured skeleton information of the code library through AST analysis instead of directly processing original source code, compresses the information volume to 10% to 20% of the original code amount, greatly improves the effective information density of the input large language model, enables a larger scale code library to be covered in a limited context window, and solves the problem that the existing large language model scheme cannot process a large scale code library due to Token waste.

Embodiments of the present application provide a structured data context isolation addressing and multi-layer cache analysis method, device and electronic equipment for large language model Agent tool invocation, which relates to the field of artificial intelligence data processing. The method comprises: calling a data acquisition tool to obtain a structured data set of an analysis object and a data set index Key thereof; based on the data set index Key, concurrently starting multiple independent analysis tracks, and after completion of analysis, storing analysis result data to a persistent index layer and an object storage layer, and generating an analysis result identification Key; and based on the analysis result identification Key of each track, the server autonomously reads each dimension analysis result data from the persistent index layer and the object storage layer, and after merging and processing, generates a structured comprehensive analysis report. The technical solution solves problems such as context window pollution, cross-tool data transmission redundancy, lack of efficient cache mechanism for LLM analysis results, and lack of fault tolerance and breakpoint resume capability for analysis pipeline.

Systems and techniques for machine learning model operation and / or optimization are described. In some examples, a system identifies a difference between an input size of an input and a context window size associated with a trained machine learning model. The trained machine learning model is associated with a computational graph having a static shape. The computational graph includes a plurality of operations. The system processes the input using the trained machine learning model to generate an output. To process the input using the trained machine learning model, the system executes a first subset of the plurality of operations (e.g., valid operations and / or semi-valid operations) and skips a second subset of the plurality of operations (e.g., invalid operations). The first subset of the plurality of operations is associated with the input. The second subset of the plurality of operations is associated with the difference.

The invention relates to an electronic medical record quality evaluation and verification method, which comprises the following steps of: S1, cleaning, analyzing and standardizing a complete electronic medical record to obtain a standardized patient panoramic context and a text block set capable of being retrieved by a vector; s2, constructing a mixed quality control knowledge base according to the external medical knowledge base and the quality control rule set; and S3, inputting the patient panoramic context, the mixed quality control knowledge base and a to-be-executed quality control point into a dynamic context manager, checking the document sequence set by adopting a quality evaluation function, and outputting a structured defect report. According to the method, an electronic medical record quality evaluation and verification framework integrating dynamic context management, multi-source knowledge fusion and large-scale language model reasoning ability is constructed, and the core contribution of the method is that the context window limitation of LLM is effectively avoided by designing an exquisite context manager mathcal {M}, and the reliability of the system is improved. And therefore, deep and explainable logic review can be executed on high-dimensional and time-sequence EMR (Empirical Mode Register) data.

The application designs a sensitive data prediction method based on user editing track in a collaborative editing scene, relates to the field of data security, and comprises the following steps: obtaining user historical text data, screening target text containing sensitive data, performing theme division, word segmentation, extracting keywords and position information to establish a text editing track; for each keyword of the text keyword set, a context window mechanism is adopted to select a sensitive word set and divide the sensitive word security level; according to the keyword editing clue, the theme label and the sensitive word set with the level division, a graph attention network is used to construct a user track model based on keywords; inputting the editing process text, identifying the keywords and labels, combining the received person role identity level, and inputting the track graph model to obtain a predicted sensitive word set. The application creates a model based on the user editing track, can accelerate the identification efficiency of sensitive data, reduce the risk of leakage, and improve the sensitive word identification accuracy under different text themes.

The invention discloses a long text processing method based on reinforcement learning memory agency, which relates to the technical field of natural language processing and artificial intelligence, and comprises the following steps: firstly, storing an original document, splitting the original document according to a fixed length, allocating paragraph indexes, then initializing a basic large language model, a memory module and a trainer, and allocating context windows; then iteratively processing the text block to generate an update memory with a traceability mark, then calculating an advantage value and a loss value through a GPRO algorithm to update model parameters, meanwhile, calculating a single or multiple answer task reward by using an exclusive formula, and finally outputting an answer with a traceability table to respond to a traceability query request of a user. According to the scheme, the bottleneck of long text processing length is broken through, the calculation complexity is reduced, the memory strategy is optimized, the precision is improved, result traceability is adapted to a high-precision scene, interaction logic is standardized, the process consistency is guaranteed, meanwhile, the existing large language model architecture is adapted, the landing cost is reduced, and stable operation of the system is guaranteed.

The invention discloses an efficient edge reasoning system and method based on a lightweight multi-modal large model, and relates to the technical field of large model edge reasoning, and the method comprises the steps: S1, carrying out the time discretization and alignment segmentation of an original video frame, an audio signal and a text stream, and obtaining a lightweight feature vector, performing splicing and linear projection to obtain unified semantic feature vectors, and performing arrangement to obtain a unified semantic feature sequence; s2, performing memory reading based on the unified semantic feature vector and the memory state to obtain a memory reading feature, and performing calculation to obtain a surprise degree and a routing decision mark; s3, constructing a unified semantic feature sequence based on the routing decision mark and the short-term context window, and executing forward reasoning to obtain core semantic representation and a task output log value vector; and S4, constructing a write-in value vector based on the routing decision mark and the core semantic representation, performing surprise calculation on the write-in intensity, and obtaining the memory state of the next time step through low-rank outer product addition and two-norm truncation processing.

The application discloses a kind of UVM verification platform automatic generation system and method based on generative artificial intelligence, the system includes generative AI dynamic anchoring module, LLM-VCS self-feedback verification module and conflict detection correction module;The generative AI dynamic anchoring module is used to solve the context window limit problem on large language model, by the key component in UVM platform is marked as anchor file and generates subsequent file based on dependency relationship priority;LLM-VCS self-feedback verification module cooperates with large language model and EDA tool chain, forms closed loop system from specification input to UVM platform generation, simulation and debugging;The conflict detection correction module is used to detect and correct the interface inconsistency and logic error between generated files.The application can adapt to the verification needs of different RTL designs, effectively solve the interface consistency problem of high coupling between UVM modules, flexibly generate UVM platform of different structures, significantly improve the verification efficiency and quality.

The application provides a task processing method and computer program product based on a large language model. Metadata and execution logic of each tool are decoupled in advance and mapped into file description information and file content of a file respectively, and stored in a registry. Based on this, after determining a target file in the registry based on an actual user task, the corresponding tool is dynamically loaded based on the file content of the target file and injected into the context window of the large language model. In this way, the problems of token resource exhaustion, reasoning delay and model attention dilution caused by static full loading are avoided, and dynamic loading can be performed as needed, which ensures the accuracy of task reasoning while significantly reducing the reasoning cost and delay.

Disclosed is a system and method for automatic detection and engagement with fraudulent actors. In one embodiment, a method includes identifying a natural language text of a correspondence suspected of describing a fraudulent solicitation using a fraud detection machine learning model using a processor and a memory. The method includes determining that the correspondence from a sender is a solicitation designed to fraudulently convince a recipient to transfer funds to the sender that conveyed the correspondence based on the analysis of the natural language text using the fraud detection machine learning model. The method includes providing the natural language text in a context window to a fine-tuned version of a language model that is optimized based on scam phraseology. The method includes analyzing the natural language text using the fine-tuned version of the language model.

A method, computer program product, and computing system for dividing a speech signal into a plurality of chunks. A first context window is defined with a first period of past context for processing the plurality of chunks with a neural network of a speech processing system. The neural network is trained using the first context window. A second context window is defined with a first period of past context for processing the plurality of chunks with the neural network. The neural network is trained using the second context window.

A system for analyzing a technical document of a storage device and extracting a multi-sentence feature is disclosed. The system includes: a plurality of classifiers, each classifier configured to receive a plurality of sentences from a technical document and generate tags for the plurality of sentences, each of the plurality of tags indicating whether each sentence has a target feature described in the technical document; and a combined neural network configured to sequentially receive the plurality of multi-tags from the plurality of classifiers as a training data set, and as a result of training, generate a plurality of tags for the plurality of sentences based on the training data set. Each of the plurality of classifiers is configured to receive text fragments at different data points corresponding to a plurality of sentences having different context window sizes, and to generate multiple tags corresponding to the text fragments.

Provided herein are systems, methods, and non-transient computer-readable storage media for providing contextualized responses using a virtual coworker within an email account. The disclosed techniques access an email thread, set a conversation context window to encompass the entire email thread, identify contextually relevant keywords within the subject line and email body, and search the email account for related email messages. A context library is created, comprising the email message and related email messages found in the email account. A response is generated based on user input derived from the context library, using a combination of prompts derived from natural language analysis and pre-programmed prompts. Additional features include analyzing the context library to define user input, engineering the initial prompt for the response, incorporating a knowledge base, reading attachments, and implementing digital security measures.

The application provides a multi-modal knowledge recall and context compression optimization method based on Skills scheduling, and relates to the technical field of artificial intelligence. A multi-modal task is parsed into a skill chain with logical dependence through a Skills scheduling layer, a multi-modal knowledge graph bound to the task is constructed, and the multi-modal knowledge graph is divided into atomic semantic scopes one-to-one mapped with skill chain nodes; a structured recall knowledge set is obtained through phased refined knowledge recall and reordering, a pre-trained neural symbolization Token budget scheduling model is used to complete global Token budget allocation; a dynamic compression strategy is determined in combination with recall execution features, semantic saliency calibration and cross-domain state cooperation, context compression is completed and output is obtained. The accuracy, reasoning consistency and context window utilization of the generated are significantly improved by strictly adapting to the Token budget constraint and retaining the core semantics and reasoning logic.

The invention discloses a kernel code review method and device fusing reinforcement learning and prompt word tuning, and relates to the technical field of code review, and the method comprises the steps: extracting patch meta-information, building a code review task, extracting a code difference item and a necessary context thereof to form a to-be-reviewed target code segment, and carrying out the review of the to-be-reviewed target code segment; and forming a primary review prompt template, calling the code review large language model to perform primary code review, summarizing primary review results, forming a filled expert-level review prompt template in combination with the patch meta-information and the kernel knowledge base, and performing expert-level code review to generate a comprehensive review result. A code review process is constructed by applying a Boosting thought in machine learning, the code review efficiency is improved, it is ensured that single input content is located in a context window of a large language model, the integrity of code semantic understanding of the model is guaranteed, a preorder model is corrected by using a postorder model, and the code review efficiency is improved. And the discovery capability of complex logic defects and cross-file problems is effectively improved.

The application discloses a kind of text context dynamic reconstruction methods, comprising: to original document is step length overlap segmentation processing, generate semantic fragment and record physical offset index information;Build document context manager storage original document complete content;Perform vector retrieval and obtain the physical offset index of matching fragment;Real-time analysis and determine the physical position boundary of fragment in original document;From original document, real-time extraction predecessor and successor text block;Splice form complete logical context window.The application establishes the accurate position anchor point of semantic fragment and original document by physical offset index, realizes zero-cost backtracking original;Adopt retrieval time dynamic reconstruction, support according to the context expansion range of adaptive adjustment of retrieval confidence;Provide three-level context mode to meet different retrieval scene demand;Intelligent deduplication eliminates redundant content.Compared with traditional RAG system, retrieval accuracy is improved by about 18%, context completeness is improved by about 31%, and Token consumption is reduced by about 30%.