237 results about "Context learning" patented technology

The invention relates to power distribution network fault processing equipment applied to the technical field of power distribution, and aims to improve the fault prediction, diagnosis and processing capabilities of a power system. The equipment comprises a pre-training module, a neural network architecture module, a data acquisition layer, an edge calculation layer, a core processing layer, a context learning module, a reasoning processing module, an output and interaction layer and a continuous learning and improvement layer, and is characterized in that a large-scale pre-trained Transform model is utilized, and professional knowledge of a power system is combined; according to the method, deep understanding and analysis of a complex power grid state are realized, through multi-source data fusion, edge calculation and central cooperative processing, the equipment can monitor the power grid state in real time, accurately predict potential faults and provide intelligent diagnosis and repair suggestions, and model pre-training and optimization are performed by adopting self-supervised learning and federated learning technologies; using reinforcement learning to optimize a fault response strategy; the interpretability of the model is realized, and the decision transparency is improved.

The invention discloses a civil administration service question and answer method based on a large model and knowledge graph retrieval enhancement, and the method comprises the steps: S10, inputting a user question, and carrying out the question analysis and entity recognition; s20, the problem complexity is judged, if the problem is a single-hop problem, knowledge graph single-hop retrieval is carried out, and if the problem is a multi-hop problem, knowledge graph multi-hop retrieval is carried out; s30, performing semantic matching sorting to generate sub-answers; and S40, based on the sub-answers and the user question, performing synthesis to generate a final answer. According to the method, the structured knowledge of the knowledge graph and the natural language processing capability of the large language model are fused; a question decomposition module is used to enhance the interpretability of multi-hop information retrieval and answers; and using contextual learning (ICL) and thinking chain (CoT) prompts to generate an individually processed explicit inference chain to improve authenticity; the defects of traditional civil administration service questions and answers in the aspects of knowledge accuracy, reasoning ability and interpretability are overcome.

One or more systems, devices, computer program products and / or computer-implemented methods of use provided herein relate to enhancing LLMs using in-context learning and online knowledge. The computer-implemented system can comprise a memory that can store computer executable components. The computer-implemented system can further comprise a processor that can execute the computer executable components stored in the memory, wherein the computer executable components can comprise a semantic retrieval component that can extract information from an online source, according to a query, to generate an in-context learning input utilized by an LLM for responding to the query.

A disclosed method facilitates AI-generation of a customized email per a methodology that significantly reduces the risk of the customized email including hallucinated facts or undesirable personal identity information (PII). The method includes identifying an email template and a recipient identifier that identifies a recipient of the customized email based on user inputs to an email application; mining contextual data stored in association with the recipient identifier; generating a large language model (LLM) prompt based on the email template and the contextual data; providing the LLM prompt as input to a trained large language model (LLM); receiving the customized email as an output from the LLM; and returning the customized email to the email application for display within a user interface.

The invention discloses a context learning-based database query generation method and system and a storage medium, and the method comprises the steps: extracting keywords and phrases from a natural language query, retrieving values similar to the keywords in a database, and returning values most related to the keywords and corresponding columns thereof, retrieving description information related to the keywords and the phrases in a database directory; performing mode selection aiming at the most relevant value of each keyword and the corresponding column, namely screening out the column irrelevant to the natural language query, further selecting a table necessary for generating the SQL query, and finally reducing the mode to a minimum column set necessary for generating the SQL query; and correcting logic and grammar errors of the method model through the database mode, the natural language query, the generated candidate SQL query and the execution result thereof. According to the method, the efficient SQL query statement is generated by intelligently understanding the data context and the query requirement.

The invention belongs to the field of natural language processing, and particularly relates to a causal atlas formation model construction method based on adaptive context learning, a causal atlas formation model comprises a searcher and a large language model, and the construction method is divided into two stages of searcher pre-training and adaptive context learning fine tuning. A sample retriever based on self-supervised learning is constructed by utilizing contrast learning loss, and text vector representation is optimized; besides, cue words containing sample examples are designed, a self-adaptive context learning strategy is combined, and the large language model is finely adjusted, so that the large language model captures event causal relationship modes in similar samples, and the accuracy of implicit event causal relationship extraction is improved. According to the method, the affair logic knowledge in the text can be fully mined, and the extraction accuracy of the implicit causal event relationship is improved, so that a high-quality causal affair graph can be automatically and efficiently constructed, and the development of downstream tasks such as causal knowledge question answering and reasoning is promoted.

Systems and methods are provided for enhancing the speech modality in a large language model (LLM) and for retaining in-context learning capabilities without overfitting to trained tasks. Systems obtain a first set of training data comprising tuples of a sample of speech combined with synthetically generated pairings of speech comprehension test questions and answers that correspond to the sample of speech and obtain a second set of training data comprising pairings of automatic speech recognition data. Systems generate and align a first set of encodings of the first set of training data and a second set of encodings of the second set of training data. Systems train the LLM on a greater amount of the first set of training data than the second set of training data and use the trained LLM to perform a natural language processing task.

The invention discloses a sports video commentary generation method and system based on a multi-modal large language model, and the method comprises the steps: obtaining a multi-modal data set which comprises a sports video, and an audio and a commentary text corresponding to the sports video; constructing a multi-modal large language model, encoding the sports video, the audio and the explanation text so as to project corresponding video frames, audio waveforms and metadata to a shared embedding space, and determining a multi-modal embedding vector; a multi-modal clustering memory unit is set, multi-modal embedded vectors are grouped, and feature alignment between modals is optimized through comparative learning and information entropy regularization; based on a retrieval enhanced context learning mechanism, a historical instance is retrieved through sparse regularization distance measurement to serve as reference input of a current input multi-mode embedded vector; and jointly inputting the current multi-modal embedded vector and the reference input into the multi-modal large language model to obtain a sports video commentary. According to the method and the device, the problems of insufficient multi-modal information integration and insufficient context utilization are solved.

The invention provides an SQL statement generation method and system based on long and short term memory of a large language model, and relates to the field of man-machine interaction, the SQL statement generation method comprises the following steps: obtaining a preset large language model, and extracting mode design information of a target database of the large language model through a database administrator; analyzing and complementing the pattern design information, and generating long-term memory to introduce a large language model; extracting query elements through multiple rounds of conversations between a user and the model, and generating short-term memory to introduce a large language model; and obtaining an SQL generation task, and generating an SQL statement according to the large language model after the long-term memory and the short-term memory are introduced, so as to extract information from the target database. According to the method, the long and short term memory ability is introduced into the large language model, the flexible interaction ability of the large language model is fully utilized on the basis of a prompt word project of context learning, the user is gradually prompted and recommended to improve the query request, and the accuracy and availability of the generated SQL can be improved.

The invention provides a large model ecological online evolution learning method based on end-cloud collaboration and an application thereof, and the method is applied to the field of e-commerce, so that efficient training and deployment of an e-commerce model are realized. According to the method, an end-cloud collaborative architecture is adopted, a cloud end deploys a large language model, an end side uses a small and medium-sized language model, and efficient training and reasoning of large model ecology are realized through collaborative work of the cloud end and the end side. In the training process, the cloud model serves as a teacher model, a pseudo tag is generated to supplement a data set, and optimization training of the end side model is guided. Meanwhile, a multi-model cooperation self-training mechanism is introduced, multiple models play different roles and mutually discuss, training labels are autonomously generated, and the end side model is further optimized. And meanwhile, user feedback information is brought into cue words of the cloud model for situational learning, so that the model performance is continuously optimized. The method is applied to an e-commerce scene, the e-commerce model ecology is successfully constructed and deployed, and intelligent development of the field is realized.

The invention relates to the technical field of large language models, in particular to a complex multi-field guided teaching question and answer generation method, device and equipment and a computer storage medium. According to the complex multi-field guided teaching question and answer generation method, aiming at the problem that the model is single in application field, the corresponding multi-round question and answer pair data set is processed by using a multi-field data source, and the model is finely adjusted based on the multi-round question and answer pair data set, so that the problem that the related field is single is solved, and the applicability and practicability of the teaching question and answer model are enhanced; aiming at the problem that the model lacks guiding ability, the input of the teaching question and answer model is further processed through thinking chain-based question extraction and disassembly and prompt engineering and context learning mechanism-based processing, so that the model question guiding ability is improved; in order to solve the problem that teaching effect evaluation indexes are single, the invention provides a new evaluation system, and a plurality of evaluation indexes can more comprehensively and accurately evaluate and optimize model teaching effects.

A contrastive in-context learning protocol for large language models. The protocol includes inputting positive and negative examples to a large language model. Additionally, the large language model may be instructed to analyze the reasons behind the positive examples being positive and the negative examples being negative. The large language model with such contrastive in-context learning can generate specific responses / answers based on user preferences, generally not possible using conventional models.

Methods and systems for prompting a Large Language Model (LLM) with a set of text data outside pre-inference trained categories and a test prompt for an initial parameter which has a known ground truth, calculating an uncertainty of an LLM's output, selecting another LLM model parameter and calculating the total uncertainty of the LLM's output with the other LLM model parameter. The methods and systems further include prompting the LLM with another test prompt, with the initial LLM parameter and the other LLM parameter, and calculating the total uncertainty of the LLM's output for initial LLM model parameter and the other LLM model parameter, decomposing the total uncertainty of the LLM into Aleatoric Uncertainty (AU) and Epistemic Uncertainty (EU) components, and rating the total uncertainty of the LLM, using the decomposed total uncertainty as a metric.

The invention discloses a recommendation system deviation correction method fusing big language model world knowledge, which comprises the following steps: acquiring an open source data set of a recommendation system, and generating a training set; guiding a large language model to generate description information of an article and preference reasoning of a user through a training set in combination with a context learning technology; encoding the description information of the article and the preference reasoning of the user through a pre-trained text encoder to generate a first encoding vector, and encoding the IDs of the user and the article to generate a second encoding vector; inputting the first coding vector and the second coding vector into a multi-mode expert network module to obtain final representations of the user and the article; inputting the final representations of the user and the article into a prediction layer to obtain a prediction value, and optimizing a multi-modal expert network module through a cross entropy loss function; and performing recommendation system correction through the optimized multi-mode expert network module. The inherent deviation in the user behavior data is eliminated, the real preference of the user is captured, and recommendation system deviation correction is completed.

Methods, systems, and apparatuses, including computer programs encoded on computer storage media, for configuring a set of language model neural networks, e.g., a first large language model and a second smaller-sized language model, and performing a machine learning task on new inputs using the set of language model neural networks. Configuring the language model neural networks and performing a machine learning task can include leveraging the ability of a first large language model to follow prompt-engineered instructions and perform chain-of-thought reasoning, while also fine-tuning a second, smaller language model neural network to optimize the machine learning task performance.

The invention discloses a software testing method and system based on a large model, and relates to the technical field of software testing, and the method comprises the following steps: step 1: describing a code review rule, and expanding specifications required to be checked: firstly, listing the check specifications required to be satisfied by a code, and according to a thinking chain and a zero- / feed-shot example, establishing a list of the check specifications required to be satisfied by the code; the check rules in the list are described as reasoning instructions of the model according to the check key points and the check steps through combination of one or more technologies of context learning; 2, code slicing: performing structure analysis and dependency analysis on the tested software project: firstly, slicing the code according to a function by utilizing a code analysis tool; according to the software testing method and system based on the large model, convenient project management, user-defined configuration and high-automation-degree test execution can be implemented on a software evaluation task, and the evaluation efficiency is effectively improved.

An example operation may include one or more of storing a table comprising a plurality of columns corresponding to a plurality of attributes and a plurality of rows corresponding to a plurality of records, receiving a target record of a task of an artificial intelligence (AI) model, converting the plurality of records into a plurality of embeddings in multi-dimensional vector space, converting the target record into a target embedding in the multi-dimensional vector space, identifying a subset of records from among the plurality of records that are nearest to the target record in content based on distances between embeddings of the subset of records and the target embedding within the multi-dimensional vector space, and executing the AI model on the subset of records to generate a predicted output with respect to the task.

The invention discloses an image annotation method, system and device for spacecraft target type and attribute classification and a medium, and belongs to the technical field of image recognition. The method comprises the following steps: constructing a multi-dimensional attribute model based on key elements of a spacecraft image; based on the multi-dimensional attribute model, constructing a reference prompt template, obtaining a preliminary output result through the reference prompt template, and carrying out optimization processing on the reference prompt template and the preliminary output result by adopting few-sample learning to obtain a first output result; performing output supervision on the thinking process of the first output result in combination with the thinking chain, and obtaining a second output result through an optimization prompt template; and according to the first output result, the second output result and the plurality of output results, generating an output result data set, and obtaining an image annotation result. According to the method, through a semi-supervised labeling method combining multi-attribute modeling and context learning, the accuracy and robustness of fine-grained labeling of the spacecraft image in a few-sample scene are improved by utilizing a generative large model.

A method for reducing the risk of unexpected or unintended actions during a Remote Desktop Protocol (RDP) or SSH (Secure Shell) session by automatically detecting anomalies using vaulted credentials. The method includes initiating a RDP / SSH session on a server and taking screenshots of the session. The screenshots are sent to a system that uses a computer vision algorithm to transcribe the screen information into a text-based transcription of the session. The text-based transcription of the session recording is then provided to a pre-trained LLM which is prompted to look for anomalies using in-context learning. The detected anomalies are presented to a system administrator or sent as alerts to the system administrator.

The invention relates to a multi-language large model translation performance optimization method and system based on prompt strategy activation, and belongs to the field of natural language processing. In a low-resource language environment, the translation performance of a multi-language large model still has insufficiency. The understanding ability of a large model on low-resource language input semantics is limited, so that part of potential translation ability of the large model is not fully activated, in order to relieve the influence, prompts are screened from a high-quality corpus based on four prompt strategies, a context learning template is constructed to serve as large model user input, and therefore the user input of the large model is improved. Task guidance serves as system input, and finally performance optimization of a large model in a low-resource language translation task is achieved by dynamically adjusting a prompt strategy and model parameters. According to the method, the potential translation ability of a large model can be effectively activated, and the translation quality of the large model in a low-resource language environment is remarkably improved.

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.

A test question recommendation method based on large language model adaptive multi-level evaluation constructs a multi-level architecture including semantic consistency verification, fine-grained fact alignment and dynamic cognitive evaluation, and comprises the following steps: constructing an initialized data stream and executing dynamic random sampling; calculating discrete semantic entropy by using NLI bidirectional implication clustering so as to quantify and eliminate illusion content with high uncertainty; under the RAG framework, the test questions are deconstructed into atomic statements, and a fact deviation is corrected by calculating a retrieval relevance vector and a logical implication consistency score; analyzing and screening low-quality texts based on multidimensional language features of syntax and logic; vector fusion is carried out on the generated intention and the cognitive portrait of the student, and a dynamic evaluation index system adaptive to a specific teaching scene is constructed in real time by utilizing context learning. The problems of accuracy and adaptability of automatic question setting are effectively solved, and intelligent closed-loop control from test question generation to cognitive alignment is realized.

The method comprises the following steps: constructing an intelligent research and judgment model, carrying out environment modeling on the intelligent research and judgment model, constructing a network attack path according to the intelligent research and judgment model, and identifying a network attack by using a known signature of the network attack or a rule-based detection technology; classifying and marking the data of the network security equipment by using an SVM classification algorithm, training an intelligent study and judgment model, establishing a threat identification strategy of the network attack, and identifying the features of the network attack; performing context learning and state prediction by using the intelligent study and judgment model, and optimizing a threat identification strategy of network attacks; a data field of a normal HTTP request is slightly disturbed, an adversarial sample is generated by using a threat of a known network attack, adversarial training is performed in combination with a forged HTTP request, and a deceptive network attack is identified. According to the method, cross validation and correlation analysis of high-quality and multi-source threat intelligence are realized, and the attack defense capability is improved.

The invention provides a medical intelligent causal decision-making and scheduling system based on an improved large language model, and the system comprises a pre-training language model module which is used for processing unstructured medical text data, and extracting a text feature vector and a medical entity relationship; the knowledge graph enhancement module is used for constructing a medical knowledge graph based on the medical entity relationship, and reasoning to generate a knowledge enhancement feature vector; the multi-modal feature fusion module is used for generating a fusion feature vector based on the text feature vector and pre-stored structured data; the dynamic time sequence modeling module is used for generating a time sequence prediction vector based on the fusion feature vector and the knowledge enhancement feature vector; the self-adaptive scheduling optimization module is used for making a medical scheduling decision based on the time sequence prediction vector and generating a scheduling scheme; and the scheduling calibration module is used for matching similar case features for the scheduling scheme through a context learning mechanism based on the knowledge enhancement feature vector and calibrating the similar case features to generate an optimized scheduling scheme. And medical resources and scheduling can be allocated more accurately.

The invention provides an intelligent judgment method and system for lung cancer tissue pathological typing. The method comprises the following steps: acquiring pathological section image data; preprocessing the pathological section image data to extract feature information in the pathological section image; analyzing the feature information by using a trained deep learning model, wherein the deep learning model is trained based on a large number of labeled lung cancer pathological images; according to an output result of the deep learning model, combining lung cancer pathological typing standards in an expert knowledge base, and intelligently judging a pathological typing category to which the pathological section image belongs; and outputting the pathological typing category and the corresponding confidence degree information to the user. According to the method, the target query statement is generated through the large model, the query intention of a user can be more accurately understood, the corresponding query statement is generated according to the database description information, and therefore the accuracy and correlation of the query result are improved, and the query efficiency is improved by recalling the related sample pairs from the sample set. And the sample pairs are used for performing context learning, so that the system can better understand and process various types of query requests, and can give reasonable response even if the system faces new queries which are not seen before.

The invention discloses a medical insurance field document intelligent question-answering system and method based on an AI large model, and belongs to the technical field of artificial intelligence. The technical problems that an existing medical insurance question-answering system depends on manual configuration and is poor in flexibility and low in intelligent level are solved. According to the technical scheme, the system comprises a document processing module for analyzing and segmenting original documents such as medical insurance policy documents, vectorizing the original documents and storing the original documents into a vector database; and the knowledge question and answer module is used for analyzing user questions by using an AI large model, driving AIAgent to retrieve related knowledge in a vector database, performing reasoning in combination with injected professional knowledge such as business dictionaries and analysis logic, and generating accurate and traceable answers. Through context learning, logical reasoning and automatic generation ability of a large model, tedious intention model training and manual QA configuration are not needed, the intelligent level, adaptability and user experience of a medical insurance question-answering system are remarkably improved, and the operation and maintenance cost is reduced.

The embodiment of the invention relates to the technical field of large model data analysis, and discloses a large model evolution multi-agent investment decision matrix system. The investment Transform module is used for acquiring financial data and performing feature extraction and feature fusion on the financial data in combination with a context learning enhancement function and a financial domain knowledge enhancement function; the interpretability analysis module is used for acquiring the feature representation in the investment Transform module and carrying out feature relation mapping and interpretability analysis; the multi-agent decision-making module is used for carrying out collaborative decision-making through multiple agents; the optimization module is used for providing interpretation optimization for the interpretability analysis module and providing strategy optimization for the multi-agent decision-making module; and the knowledge base module is used for providing an investment template for the investment Transformer module, providing causal relationship knowledge for the interpretability analysis module and providing rule constraints for the multi-agent decision-making module. The technical problem of investment decision analysis can be at least solved.

Aspects provide in-context learning with calibration for a foundation model. A validation prompt including one or more demonstration samples and an evaluation example is received and an output probability generated using the foundation model and the validation prompt. A calibration loss is computed based on the output probability and a set of calibration parameters. The set of calibration parameters is updated based on the calibration loss using an optimization algorithm. An inferencing operation is performed using the updated calibration parameters.

The invention discloses a knowledge graph inference method based on prior knowledge enhancement, and mainly solves the problem of inaccurate reward caused by insufficient knowledge graph prior knowledge in the existing knowledge graph inference method based on reinforcement learning, thereby optimizing a model more effectively. The method comprises the following steps: reasoning path searching based on reinforcement learning; calculating an answer correctness reward; logic rationality reward calculation; a reward enhancement strategy based on path importance; performing logic rationality reward enhancement based on large language model context learning; and optimizing the model. According to the method, on the basis of an existing knowledge graph reasoning method based on reinforcement learning, huge internal knowledge of a large language model is fused into reward calculation in an efficient and information loss resistant mode, and the problem that rewards are inaccurate due to insufficient prior knowledge of a knowledge graph is solved. The performance of the knowledge graph reasoning method based on priori knowledge enhancement is remarkably improved compared with that of an existing method.

The invention discloses a small sample unified granularity relation extraction method based on a large language model, which comprises the following steps of: firstly, giving a specific task description as a part of an input context of the large language model; thirdly, giving an analogous example to the large language model as context demonstration; in order to better prompt the position information of the entity of the large language model in the context, performing entity enhancement on the context input into the large language model; and finally, a mode for serializing the relation triad is defined, and thinking chain reasoning information is fused in the mode, so that a large language model can be helped to perform relation extraction by utilizing thinking chain prompts. According to the method, context learning, thinking chain and entity enhancement technologies are introduced for unified granularity relation extraction tasks including a sentence level, a document level and a cross-document level, the powerful reasoning ability of a large language model is fully played, and the effectiveness of the model in the unified granularity relation extraction task, especially in a small sample scene, is improved.