170 results about "Context window" patented technology

The invention provides a long document processing method and system based on multi-agent collaborative reasoning. The method specifically comprises the steps that semantic coherence is reserved by adopting a sliding window overlapping partitioning strategy; a structured reasoning chain is generated by analyzing the agents, the agents are integrated to eliminate cross-block contradictions based on vector similarity and triple conflict detection, and a paragraph-level unified conclusion is output; and the summarizing agent constructs a global logic relationship by utilizing thinking chain prompt, reconstructs an answer framework according to user questions and binds a source identifier, and generates a traceable complete abstract or answer. According to the method, the technical problems of global reasoning failure caused by context window length limitation, semantic splitting and conclusion conflict caused by block processing, low single-model serial efficiency and the like in the prior art can be solved.

A method for managing conversation history in an Al system is disclosed. A user message is received and full conversation history payload is retrieved from a memory service. The full conversation history payload includes one or more messages, summaries, or moments. A prompt budget is dynamically allocated, based on an available context window. The prompt budget determines token allocations for the messages, summaries, or moments from the full conversation history payload. A prompt is assembled for a language model by selecting conversation history elements to fit within the allocated prompt budget. The selecting balances between recent verbatim messages, summarized content of older messages, and relevant older moments. The prompt budget is iteratively adjusted and the prompt is iteratively reassembled as new information is added, from one or more language model outputs or tool calls, while maintaining the full conversation history payload in the memory service.

The invention discloses a large-model context control system and method based on hierarchical memory and an association graph, and the method comprises the steps: constructing a tree graph mixed memory structure and a logic hierarchical memory model for a context control unit between a user and an LLM, and carrying out the self-adaptive processing of a super-long context through a self-adaptive processing engine, a single-theme persistent dialogue control mechanism, and the like. According to the method, the problem that an LLM context window is limited (including introduction of a mechanism similar to an Agent) is solved, just like an operating system helps developers / users to solve the problems that hardware standards hidden behind are not uniform, and complex resource control is caused, a reliable LLM memory (context) control service with multiple details hidden is provided for upper developers, and the method has the advantages of being high in practicability and easy to popularize and use. The final objective of the method is to approximately relieve the limitation of an LLM context window through a set of self-consistent system mechanism, so that a developer does not need to pay too much attention to the details of a bottom layer, and more energy can be focused on the implementation of an application function.

The invention relates to the technical field of large language model application, in particular to a fault-tolerant processing method and system for a super-long text in large model service and a storage medium, and the method comprises the following steps: obtaining a super-long text to be processed and a maximum Token threshold of a large model context window, completing Token processing and judging whether the super-long text exceeds the limit or not; starting a multi-level alternative scheme including rapid compression, dynamic compression and chat history compression; starting an error recovery mechanism including hierarchical exception processing, intelligent degradation and parameter verification; outputting the target text of which the Token number is compliant; the system comprises a text acquisition module, a multi-level alternative scheme execution module, an error recovery module and an output module. The storage medium stores a computer program, realizes the method during execution, can adapt to multiple models, and meets industrial-grade super-long text processing requirements; the problems of Token overrun errors and inference service instability caused by lack of fault-tolerant mechanisms and insufficient boundary processing in the prior art are solved.

A computer-implemented method comprising: receiving, as input, a query and a source document intended for a content-grounded question-answering or multi-turn conversation task by a specified large language model (LLM) which has a context window size limit, wherein the source document has a size which exceeds the context window size limit; dividing the source document into a plurality of segments; applying a language model to each of the segments, to assign to each of the segments a relevance score; selecting the k-top segments having the highest the relevance scores; combining the selected k-top segments into a virtual document having a size which complies with the context window size limit; and feeding the virtual document as input to the specified LLM, to generate a response that is grounded in the content of the virtual document.

The invention relates to the technical field of big language model dialogue system optimization, in particular to a big language model dynamic dialogue history compression method and system.The method comprises the steps that the maximum length of a context window matched with a target big language model, the maximum number of newly-generated lexical elements and the size of a safety buffer area are set, and then dialogue history is loaded; initial compression and verification are carried out through a keyword and TF-IDF mixed scoring system, multiple times of dynamic compression are carried out according to gradients if the conditions are not met, and finally, parameters are adjusted to adapt to the residual space when a model is called to generate response. The system comprises a dialogue history loading module, a parameter configuration module, a dynamic compression engine module and a large language model integration module. Through a multi-stage compression verification mechanism and a progressive multi-stage dynamic compression strategy, super-long texts such as engineering technology documents can be processed, service interruption is reduced, the compression efficiency is improved on the premise that key semantics are reserved, and multi-language dynamic compression is supported. The problems of system token overrun and service instability in the prior art are solved.

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 discloses a graph-driven self-attention compressible memory management method, and belongs to the technical field of penetration testing. According to the graph-driven self-attention compressible memory management method, an attention graph is constructed, semantic dependence and attention flow directions among multiple Agent nodes are accurately described by utilizing edge weights, the relevance and the accessibility of information are improved, and in the aspects of screening and loading, the expandability of the memory is improved. According to the method, key memory fragments are screened on the basis of concerned graph edge weights and task related features, only the loaded information is loaded, redundancy is effectively eliminated, the data volume processed by a system is reduced, and the system operation efficiency is improved; the semantic compression module can perform abstract processing on historical information based on various elements, and on the premise of ensuring that key semantic information is not lost, the abstract length is controlled within the window limit, so that the model can normally process information, and the adaptability and stability of the system to different data volumes are improved.

Arrangements for intelligent content generation for process automation are provided. A domain model, being structured into tasks according to a defined schema, may be exported for processing by a large language model. A prompt and a context window associated with a task of the domain model may be received. A task template associated with the task may be modified. The modified task template may be enriched with data from a backend system. Content validation may be performed on content of the modified task template enriched with the data from the backend system. Schema validation may be performed for validating the modified task template enriched with the data from the backend system against the defined schema. Correction of invalid tasks may be performed in an iterative loop until the modified task template enriched with the data from the backend system is validated. Then, changes to the domain model may be applied.

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 belongs to the field of text questioning and answering, and relates to a large language model long text questioning and answering method and system based on a hybrid context compression technology. The method comprises the following steps: analyzing and preprocessing a document, and converting an unstructured original text into a normalized text paragraph set; classifying questions of the long text question and answer scene based on a large language model; according to the question type and the preprocessed text, adaptively selecting the most suitable context compression method to compress the long text to obtain a compressed context; and generating an answer to the question based on a large language model by using the compressed context. According to the method, the advantages of two context compression technologies are integrated, the problem of context window limitation of processing a long text by a large language model is effectively solved, high-quality question and answer performance is kept while computing resource consumption and processing delay of the compression technologies are reduced, and the limitation of a single compression method on different types of problems is relieved.

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.

In some embodiments provided herein is a generative foundation model trained over millions of health system-scale electronic health records along with web-scale medical text corpora to acquire knowledge of both medical practices and theories, and use of the generative model for rare disease diagnosis (including rare ophthalmic, diseases and rare systemic diseases), emergency condition identification (including ophthalmic emergencies and systemic emergencies), complex disease solving ("diagnostic puzzles"), or generating multimodal medical imaging reports (including ophthalmic images and radiology images such as X-rays and CT scans). In some embodiments, the generative model involves the use of language data, for pre-training, language data for supervised finetuning using a instruction tuning approach (e.g., QA pairs), and a human-machine hybrid evaluation strategy. In some embodiments, both the pre-training and supervised finetuning phases involve the use of a particular method of scaling to extend the context window. In some embodiments, the human-machine hybrid evaluation strategy involves language data for automated evaluations, as well as evaluations by generalists and by different specialists (e.g., ophthalmologists and radiologists) of varying levels of experience. In some embodiments, the generative foundation model, MetaGP, is used for unmet clinical needs through integration of medical and multimodal imaging data.

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 provides a time sequence prediction task-oriented basic model construction method, which comprises the following steps of: constructing a Patch division layer which is used for cutting an input time sequence by adopting a context window adaptive mechanism combining time domain and frequency domain statistical characteristics to generate overlapped time periods; an embedded layer is constructed and used for converting the processed time sequence into embedded representation and generating an embedded Token through linear projection processing; constructing a forward and reverse frequency domain enhanced bidirectional state space module which is used for outputting forward and reverse modeling results by taking the input sequence and the time reversal sequence thereof as input, and fusing the forward and reverse modeling results to obtain a final fusion result; constructing a feed-forward layer which is used for taking the final fusion result as input to encode a time dependency relationship; and constructing an output and projection layer for mapping the coded time sequence to a predicted future value through linear projection. The method can adapt to various time series data under zero sample setting, and has good modeling robustness and cross-variable modeling capability.

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 discloses a text-oriented violent word abbreviation detection method, device and equipment and a storage medium, and relates to the technical field of natural language process.The method comprises the steps that preprocessing, candidate abbreviation dynamic positioning and context modeling are conducted on an input text, and a semantic relation graph is constructed; fusing the text semantic feature and the graph structure feature of the graph to generate a joint feature vector; performing multi-dimensional alignment on the vector and a preset violent knowledge graph, and calculating cosine similarity between the vector and each graph node; if the maximum cosine similarity exceeds a preset similarity threshold value and the hazard level of the corresponding node is higher than a preset hazard level, marking the candidate abbreviation corresponding to the maximum value as a violent word abbreviation; and if the predefined security counter-example word exists in the dynamic context window, clearing the mark. According to the method, the novel abbreviation variant of the violent word in the text can be accurately identified, the violent intention in an ambiguous context is distinguished, and the zero sample scene adaptability and the attack and defense resisting capability are improved.

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.

Systems and methods for automated emotional text analysis and markup utilizing a sliding window mechanism. A method includes receiving input text data and employing a text preprocessing unit to parse the data into text segments. A contextual window control unit within a text markup unit applies a sliding window mechanism to each text segment, creating context windows for sentiment analysis. An emotional analysis model within the sentiment classification unit classifies the sentiment of the text segments within context windows. The emotional text markup unit associates classification results with the respective text segments, generating marked-up text that is used to produce media content with emotional expressions.

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.