74 results about "General-purpose language" patented technology

The invention relates to the technical field of language translation, in particular to a low-resource language translation method and system based on deconstruction distillation, and the method comprises the steps: obtaining parallel corpus data of a low-resource language and a general language; the method comprises the following steps: constructing a teacher model by taking parallel corpus data as input, constructing a student model trunk based on a pre-trained BERT big language model and optimizing the student model, calculating cross-task attention alignment loss based on the teacher model and the student model, and outputting and executing logits distillation based on the teacher model and the student model. Deployment of low-resource language translation is completed based on the trained student model, a high-quality knowledge migration source is provided for the student model by constructing the BERT teacher model subjected to full-parameter fine adjustment, and meanwhile, the problem of translation precision caused by insufficient low-resource language data is effectively solved by means of dual supervision of cross-task attention alignment and logits distillation.

The invention discloses an anomaly detection method, system and device for a multi-mode large model of power equipment and a medium. The method comprises the following steps: acquiring a general anomaly detection vision sub-model, a general text encoder and a general language sub-model of a general power scene; the method is based on a general anomaly detection vision sub-model, a general text encoder and a general language sub-model. And a second sample image of the target power scene, a second prompt text associated with the second sample image, a second anomaly detection problem text associated with the second sample image, a second anomaly detection positioning tag associated with the second sample image and a second anomaly detection answer tag associated with the second sample image. Obtaining a power equipment multi-modal large model of the target power scene; and performing anomaly detection on the to-be-detected image of the target power scene by using the power equipment multi-modal large model of the target power scene. According to the embodiment of the invention, the construction efficiency of the multi-modal large model of the power equipment and the anomaly detection accuracy of the to-be-detected image can be improved.

A system may include a non-transitory storage medium storing computer program instructions and a processor configured to execute the computer program instructions to cause operations. The operations may include receiving, by a generic language model, a question from a user and querying, by the generic language model, a domain-specific knowledge model for an answer to the question. The operations may further include providing the answer to the user and / or providing documentation associated with the answer to the user.

Disclosed herein are computer-implemented methods of providing universal language understanding, the computer-implemented method including parsing an input in a language domain into an enriched tree data-structure, wherein the enriched tree data-structure comprises at least one of a unique identification of an entity, a classification, and a resolution; processing the enriched tree data-structure by matching the enriched tree data-structure with one or more dynamic language graphs, wherein the one or more dynamic language graphs store a relation between elements of the language domain, a causation of the entities, and a property of the entities; and upon determining the enriched tree data-structure does not match with the one or more dynamic language graphs, at least a portion of the enriched tree data-structure that does not match is inserted into the one or more dynamic language graphs.

The technology necessary for hands-free video gaming is available, especially for head-gesture-centric controls. However, remapping controls to head gestures ranges from frustratingly tedious to impossible. The inventor proposes a common language of gestures and game actions that categorizes the controls by their use frequency. The suggested categories are primary, secondary, tertiary, and quaternary. The most preferred gestures and more frequently used controls are classified as primary while the least preferred gestures and least frequently used controls classified as quaternary. The inventor also proposes constructing an interface software and API to gather data from game designers, hardware designers, and users to suggest optimized game controls for users requiring accessibility.

The invention discloses a data knowledge extraction method, system and device based on a large language model, and a storage medium. The method comprises the following steps: preprocessing obtained original data; extracting features from the original data, selecting corresponding task features, and removing high-correlation features by calculating a correlation coefficient matrix between the features; selecting a large language model of the task, capturing general languages and knowledge, and performing fine tuning on the large language model on an annotation data set of a specific field or task; based on big language model reasoning and cue word engineering, knowledge source information is extracted by adopting a secondary block iteration mode, and information extracted from different data sources is integrated by utilizing context understanding ability of a big language model after fine tuning training; and defining an evaluation standard, analyzing an error case of the large language model, identifying an improvement direction, and adjusting model parameters and training data according to an evaluation result and error analysis. The method has the advantage of improving the efficiency and accuracy of the knowledge extraction method.

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 discloses a multi-language PLC configuration software component library expansion method and system based on LLVM, and relates to the technical field of configuration software, the method comprises the following steps: obtaining language source codes of various types of programming languages supporting the LLVM front end; inputting the language source code of each type of programming language into a corresponding LLVM front-end compiler, and converting the language source code into a standard intermediate representation; establishing a general language characteristic analysis framework; establishing a general abstract metadata injection framework; building a mapping rule framework; integrating the general language framework, the general abstract metadata injection framework, the mapping rule framework and the output result, and generating a unified extended intermediate representation; and generating an interface component library conforming to the IEC standard. According to the method, any programming language with an LLVM front end is supported, a developer can directly utilize a mature algorithm library in each language ecosystem to select the programming language most suitable for a specific application scene, and the development period is remarkably shortened.

The invention relates to the technical field of financial science and technology, and provides a prompt generation method and device, electronic equipment and a computer readable storage medium, and the method comprises the steps: obtaining a no-label data set and task type information; inputting the label-free data set into a pre-trained universal language model for reasoning processing to obtain candidate response information; splicing the label-free data set and the candidate response information to obtain a candidate pseudo example; selecting a target scoring function from a preset selector according to the task type information; screening the candidate pseudo examples according to the target scoring function to obtain target pseudo examples; and performing prediction processing on the target pseudo example according to the universal language model to obtain prediction prompt information. Through the technical scheme, the performance of the universal language model in zero-sample and few-sample scenes can be improved, so that the output is more accurate, the accuracy of the intelligent answer system can be improved, and better use experience is brought to a user.

The invention relates to a scoring method and system for question answering of national general languages and characters. The national general language character question answering scoring method comprises the steps that based on a public English data set Mohler, the English data set Mohler is translated into Chinese, wrong translations in the English data set Mohler are corrected and then trained, and a question answering model used for automatic scoring is obtained. The method mainly comprises a feature extraction part, a semantic similarity evaluation part and a problem score calculation part. According to the feature extraction part, a question text to be scored and an answer text to be scored are obtained and then sent to a BERT encoder, so that a question text vector and an answer text vector containing deep text semantic features are obtained; in the semantic similarity evaluation part, a multi-head attention mechanism is used for calculating the questions and the answer texts subjected to BERT fine tuning so as to determine the similarity between the questions and the answer texts; and the answer score calculation part is used for filtering irrelevant parts in answers and questions by applying a gating convolution unit, and scoring the answers of the user. According to the national general language character question answering and scoring method and system, the question answering and scoring accuracy of farmers and herdsmen in the aspect of learning national general language characters can be improved.

The invention discloses a vehicle-mounted scene hot word recognition method and related equipment, and relates to the technical field of Internet, and the method comprises the steps: obtaining voice data inputted by a user, extracting a hot word text from the voice data, and obtaining fusion features of the voice data and the hot word text; analyzing the hot word text to generate a plurality of mapping paths, and constructing a hot word language model based on the plurality of mapping paths; decoding the fusion feature based on the hot word language model to obtain a hot word decoding result; decoding the fusion feature based on the universal language model to obtain a universal decoding result; and determining a target recognition result based on the hot word decoding result and the general decoding result.

The invention provides a multi-model fusion vertical class domain knowledge question-answering method and system, and belongs to the field of artificial intelligence natural language processing. According to the scheme, a traditional single large model is disassembled into a plurality of specialized models for cooperative work; firstly, an enhanced small parameter model trained for the vertical field is used for performing document analysis, and fixed position information is extracted in combination with rules in an auxiliary manner; then performing intention understanding by using a general language model with relatively low parameters, assisted by a cue word strategy, a rule model or a knowledge graph; then, based on the analyzed document information and the understood user intention, knowledge retrieval and answer generation are carried out through a model with large parameters; and finally, carrying out style optimization by adopting a special small parameter model, and generating an answer conforming to the characteristics of the vertical class field. An answer backflow mechanism is further designed, and continuous optimization of the system is achieved. According to the scheme, the resource consumption is greatly reduced, the accuracy and efficiency of the knowledge questions and answers in the vertical class domain are improved, and the'illusion 'problem existing in the prior art is solved.

The embodiment of the invention provides a model construction method and device, a data risk identification method and device, a medium and a product. The model construction method comprises the following steps: acquiring a preset seed training data set, and training a preset offline intention recognition model by using the seed training data set; obtaining a to-be-marked training data set, and predicting a first intention label of to-be-marked training data in the to-be-marked training data set by using the trained offline intention recognition model; constructing prompt content containing to-be-marked training data and a plurality of preset intention tags, and inputting the prompt content to the universal language model, so that the universal language model identifies a second intention tag of the to-be-marked training data in the plurality of preset intention tags; and based on the to-be-marked training data with the same first intention label and second intention label, the preset online intention recognition model is trained, so that the manpower marking cost is reduced, and the recognition accuracy of the online intention recognition model is improved.

The invention belongs to the field of operation inspection intelligent models, and discloses a power equipment operation inspection intelligent agent construction method and a related system.The power equipment operation inspection intelligent agent construction method comprises the steps that a power equipment related professional word list is introduced when a corpus is constructed, and the power equipment related professional word list is combined with an original word list; the understanding accuracy of the model on electric power terminologies, equipment operation scenes and details in an operation and inspection process can be obviously improved; in the multi-stage progressive pre-training and subsequent fine tuning process, the pre-training model continuously learns in the corpus which is richer and more accordant with the power operation inspection requirement, and professional knowledge and general language understanding ability supplement each other. By adopting multi-stage progressive pre-training, the method can progressively transition from basic language ability to knowledge mastering of a power equipment scene, and the logical reasoning ability of the model in a complex scene is gradually enhanced.

The invention relates to an intention recognition method and device for a financial service application, computer equipment, a storage medium and a computer program product, relates to the field of artificial intelligence, and can improve the intention recognition efficiency. The method comprises the steps of obtaining a to-be-recognized text which is input by a user in a financial service application and is to be subjected to intention recognition; comparing the text feature corresponding to the to-be-recognized text with text features corresponding to a plurality of financial industry knowledge texts in a pre-constructed financial industry knowledge base, and determining a target financial industry knowledge text associated with the to-be-recognized text according to the similarity of the text features obtained by comparison; inputting the target financial industry knowledge text and the to-be-recognized text into a pre-trained universal language model, and determining context semantics of the to-be-recognized text by the universal language model according to the target financial industry knowledge text, and determining a user intention corresponding to the to-be-recognized text according to the context semantics.

A system may include a non-transitory storage medium storing computer program instructions and a processor configured to execute the computer program instructions to cause operations. The operations may include receiving, by a generic language model, a question from a user and querying, by the generic language model, a domain-specific knowledge model for an answer to the question. The operations may further include providing the answer to the user and / or providing documentation associated with the answer to the user.

The application discloses a kind of data knowledge extraction method, system, equipment and storage medium based on large language model, method includes: the original data obtained is preprocessed;Feature is extracted from original data, select corresponding task feature, remove the feature of high correlation by calculating the correlation coefficient matrix between features;Select the large language model of task, capture general language and knowledge, fine-tune the large language model on the labeled data set of specific field or task;Based on large language model inference and prompt word engineering, knowledge source information is extracted using a secondary block iteration method, and the context understanding ability of the large language model after fine-tuning is used to integrate the information extracted from different data sources;Define evaluation criteria, analyze the error cases of the large language model, identify the improvement direction, and adjust the model parameters and training data according to the evaluation results and error analysis.The application has the advantages of improving the efficiency and accuracy of the knowledge extraction method.

The specification discloses a patent retrieval method, device and equipment for multiple retrieval scenarios. Patent field language models are obtained by training general language models with fields of patent documents as training data. For multiple retrieval scenarios, positive and negative samples of each patent document are screened through different weight multi-path recall and random sampling, and training data of a patent semantic representation model of each retrieval scenario is constructed to train the patent field language models, and then the patent semantic representation model of each retrieval scenario is obtained to generate semantic vectors of each field of the patent, and the semantic vectors are stored in a patent retrieval vector database of each retrieval scenario. According to the semantic vectors of the retrieval fields, similar patent documents are searched from the patent retrieval vector database of the target retrieval scenario. Through the above scheme, the semantic representation ability of the patent semantic representation model for the patent fields of different retrieval scenarios is improved, and the retrieval precision is improved.

A small sample based general image counting method, comprising: performing feature extraction on a first image to obtain first features; performing attention calculation based on the first features, a general language representation and a general visual representation to obtain first example features of a first example target, wherein the general language representation is used to describe categories of different objects, the general visual representation is used to describe visual information of different objects, the first example target is an object related to an example frame in the first image, and the first example features include a first language representation and a first visual representation, the first language representation is used to describe a category of the first example target, and the first visual representation is used to describe visual information of the first example target; performing matching on the first example features and the first features to obtain a correlation feature map; and obtaining a first counting result related to the first example target based on the correlation feature map. The method can greatly improve the generalization of the counting algorithm.

The invention provides a large language model staged pre-training method and system. The method comprises the following steps: training a Transform model by using a basic data set, optimizing a negative logarithm likelihood target, and adopting an AdamW optimizer and a cosine attenuation learning rate; continuing training by using the universal knowledge data set based on the first-stage parameters; and weighting the professional data in the training field by adopting an oversampling strategy. By structuring a training target and a data type, the model can efficiently learn language basis, general knowledge and professional skills in stages. Experiments show that according to the method, the training efficiency of the model in the basic stage is improved by 40%, the overall training time is shortened by 30%, and meanwhile the accuracy rate of tasks in the professional field is 15%-20% higher than that of traditional end-to-end training. Finally, model parameters are evaluated through professional ability, and both universal language understanding and domain specialty are achieved.

The invention discloses an NL2SQL-based power intrinsic safety question-answering system construction method, system and device and a medium, and belongs to the technical field of power safety. The method comprises the following steps: collecting fine tuning data and constructing a fine tuning data set; performing low-rank adaptive fine tuning on a pre-trained large language model through the fine tuning data set to obtain a fine tuning large language model, and triggering an annealing strategy for optimization; building prompts through the fine-tuning large language model in combination with user questions and database structure information; and generating a structured query language statement based on the prompt, querying a database to obtain a query result, and adjusting the prompt according to the query result to process an error. According to the method, low-rank fine tuning in the field of electric power intrinsic safety is carried out on a general pre-training large model by introducing the LoRA technology, so that the model has general language understanding ability and industry exclusive knowledge at the same time, and the problem that a traditional model is high in universality but low in specialty is solved.

System and techniques for processing spoken language to use as input to a control system are described herein. After an utterance is obtained from a user in a general language, a generative neural network model is invoked on the utterance to transform the utterance into a phrase that conforms to a domain-specific language. The domain specific language phrase is provided a control system that accepts phrases of the domain-specific language as input and controls a device based on the input.

The invention relates to the technical field of computers, and discloses a multi-language conversion method and device of a code, computer equipment and a storage medium, the method comprises the following steps: obtaining an initial language code through a preset code entry processing tool, and performing entry processing on the initial language code to generate a to-be-uploaded code; generating an initial universal language code according to the code database and the to-be-uploaded code; and determining the initial universal language code passing the verification as a target universal language code. In this way, the initial language code is obtained through the preset code entry processing tool, and the quality and readability of the code are improved. According to the preset code database and the to-be-uploaded code, the initial universal language code is generated, redundancy and errors of the code are reduced, and maintainability and readability of the code are improved. And the initial universal language code passing the verification is determined as the target universal language code, so that the stability of the code is improved, and the development efficiency is further improved.

This application discloses a method and related equipment for identifying hot words in a vehicle-mounted scene, relating to the field of Internet technology. The method includes: acquiring user-input voice data; extracting hot word text from the voice data; and acquiring fusion features between the voice data and the hot word text; parsing the hot word text to generate multiple mapping paths; constructing a hot word language model based on the multiple mapping paths; decoding the fusion features based on the hot word language model to obtain a hot word decoding result; decoding the fusion features based on the general language model to obtain a general decoding result; and determining a target recognition result based on the hot word decoding result and the general decoding result.

Some implementations described herein provide techniques and apparatuses for software parameter management through a universal interface. The techniques and apparatuses include a user device including a universal parameter management application. The user device may receive multiple sets of changeable parameters that may be provided to the user device using different formats, different machine languages, and / or different language scripts. The universal parameter management application may translate the multiple sets of changeable parameters into a common format, common machine language, and / or common language script. The user device may then provide each of the multiple sets through a common, changeable graphical representation of the changeable parameters on a graphical user interface of the device. The user may change each of the multiple sets of changeable parameters through an input that changes the common, changeable graphical representation.

The invention belongs to the technical field of artificial intelligence, and particularly relates to a fine tuning model construction and multi-round incremental training framework oriented to power grid innovation management, which is characterized in that power grid multi-source heterogeneous data is introduced to carry out pre-training on the basis of a general pre-training model, and the core is to design a text-time sequence joint masking loss function to obtain a fine tuning model; while the understanding capability of the universal language / time sequence structure of the model is reserved, the model deeply masters the professional characteristics of the power grid, and a basic model with both the universal adaptability and the professional property of the power grid field is constructed. According to the invention, through modularization, low-rank increment, dynamic sparse and rolling increment training and strict online risk management and control, an efficient, controllable and sustainable evolution model training framework oriented to a multi-service scene of the smart power grid is constructed, a landing engineering solution is provided for stable, efficient and sustainable operation of the smart power grid, and the development of the smart power grid is facilitated. The method plays an important role in promoting digitization and intellectualization of a power grid.

This invention discloses a heterogeneous hybrid expert large model architecture and alignment method for high-concurrency online medical dialogue. First, the method proposes a dual-pool heterogeneous routing strategy of "4 general experts + 2 departmental experts." Through physically isolated parallel routing channels, it forces the model to simultaneously activate general language capabilities and specialized medical reasoning when processing input, fundamentally ensuring the focus and professionalism of responses. Second, it adopts a structural evolution strategy based on parameter expansion and selective freezing. By completely freezing the pre-trained basic parameters and training only newly added departmental experts, it completely eliminates catastrophic forgetting. Finally, in the model alignment stage, it employs the Group Relative Policy Optimization (GRPO) algorithm for valueless models to reduce memory overhead and designs a dual-track hybrid reward function combining low-level semantic similarity rewards and high-level structured large model referee scoring, effectively solving the "reward hacking" problem and guiding the model to generate refined responses that combine clinical accuracy and humanized interaction. This invention significantly improves the performance of medical dialogue systems. Its sparse activation and parameter freezing characteristics further ensure low latency and high throughput in online high-concurrency scenarios, providing a complete solution for the deployment of reliable medical dialogue systems.

The technology necessary for hands-free video gaming is available, especially for head-gesture-centric controls. However, remapping controls to head gestures ranges from frustratingly tedious to impossible. The inventor proposes a common language of gestures and game actions that categorizes the controls by their use frequency. The suggested categories are primary, secondary, tertiary, and quaternary. The most preferred gestures and more frequently used controls are classified as primary while the least preferred gestures and least frequently used controls classified as quaternary. The inventor also proposes constructing an interface software and API to gather data from game designers, hardware designers, and users to suggest optimized game controls for users requiring accessibility.

The application provides a pre-training language model fine-tuning method, device and computer readable storage medium, and belongs to the technical field of natural language processing. The pre-training language model fine-tuning method comprises the following steps: obtaining a pre-trained pre-training language model, determining the gradient threshold of each encoding layer in the pre-training language model; training the pre-training language model, and calculating the gradient norm of any encoding layer before updating the model parameters of the encoding layer each time in the training process; and determining whether the model parameters of the encoding layer need to be updated this time according to whether the gradient norm of the encoding layer is less than the gradient threshold of the encoding layer. The application can achieve a better compromise in retaining the general language knowledge of the pre-training language model and training a model suitable for a downstream task, so that the model can retain more general language knowledge and improve the performance of the model.

The invention relates to a knowledge distillation optimization-based semantic bidirectional encoder method special for the field of open source software supply chain security. The method comprises the following steps: acquiring security data of an open source software supply chain; inputting the security data into a pre-trained student model to obtain a security analysis result of the open source software supply chain; the security analysis result comprises a vulnerability detection result; the pre-trained student model is a language model obtained by training according to the sample security data, the first sample label and the second sample label; the first sample label is a sample semantic understanding result output by a plurality of teacher models according to the sample security data, and the second sample label is a sample vulnerability detection result; the plurality of teacher models include a first teacher model for semantic understanding of a general language, a second teacher model for semantic understanding of a secure text, and a third teacher model for semantic understanding of a code. By adopting the method, the security analysis accuracy of the open source software supply chain can be improved.