250 results about "Polyglot" patented technology

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 a cross-language code semantic alignment method, which constructs a shared semantic space through a unified abstract syntax tree (AST) and a graph matching network (GMN) so as to reduce the difference of different programming languages in syntax structure and node representation. The method comprises the following steps: (1) mapping a multi-language AST node to a unified general label set and performing structure enhancement; (2) performing node feature coding on the unified AST, and realizing cross-language interaction in combination with a cross-graph attention mechanism; (3) node representation is generated through intra-graph loop updating, and an overall semantic vector is obtained through global attention pooling; and (4) through comparative learning training in the shared space, the distance between semantically equivalent positive sample vectors is shortened, and the distance between non-equivalent negative sample vectors is shortened, so that the discrimination capability of cross-language semantic representation is enhanced. According to the method, the semantic consistency of the functional level can be effectively captured, and the accuracy and efficiency of cross-language code understanding, multiplexing and retrieval are remarkably improved.

The invention relates to a method for improving the internal accuracy of a response from an artificial intelligence (AI) trained in multiple languages, in particular a generative AI trained in multiple languages. The invention further relates to a data processing system for carrying out the method.

The invention discloses a multi-language data analysis-oriented extensible system, method, equipment and medium, and relates to the technical field of multi-language analysis, the multi-language data analysis-oriented extensible system comprises a grammar analysis module used for analyzing a query language and generating a language-specific syntax tree structure after analysis; the grammar adaptation module is used for converting a language-specific grammar tree structure into an abstract grammar tree AST in a uniform format; the abstract syntax tree processing module injects a permission control strategy, a field desensitization rule and an alarm exception expression into the AST; the business processing module is used for executing business-related rule check and label injection; the query plan generation module is used for constructing a logic query path and a corresponding distributed execution scheme; and the task scheduling module issues the distributed execution scheme to the corresponding execution node. According to the method, by constructing a unified multi-language grammar analysis framework and a standardized abstract syntax tree AST representation mechanism, compatibility and fusion of multiple query languages such as SQL, SPL and natural language are achieved.

The invention discloses a lightweight cross-platform PLC (Programmable Logic Controller) multi-language code generation method, which relates to the field of industrial process control, and firstly provides a unified intermediate data model, and on the basis, a module for converting each PLC language into the unified intermediate data model is realized; on the basis of a standardized JSON data structure, a modularized unified intermediate language conversion chain is further supported, an analyzer and a generator communicate through a JSON interface, a cross-platform conversion path is supported, and unified intermediate language conversion from PLC to JSON to XML to ST to C is completed; the method comprises the following steps of: integrating an open source compiler and runtime, constructing an open and pluggable automatic execution framework, compiling a generated C code into a platform executable file by using an adaptive GCC tool chain aiming at different target platforms, and deploying a program generated by compiling to a soft PLC runtime system supporting multiple platforms. According to the method, a JSON intermediate data structure which is light in weight, unrelated to languages and uniform in structure and a matched conversion framework of the JSON intermediate data structure are constructed.

The invention discloses a multi-language code generation method based on self-supervised pre-training, which comprises the following steps: acquiring and cleaning multi-language code data to form a training corpus; the method comprises the following steps: representing code data as an abstract syntax tree, extracting a control flow diagram and a data flow diagram of the code data, and obtaining unified semantic representation through combination of a diagram encoder and a sequence encoder; designing a self-supervised pre-training task, and pre-training the semantic representation based on the training corpus; constructing a multi-language pre-training model based on the structure-improved recurrent neural tensor network and the multi-language embedding matrix; when a user inputs a natural language, generating a target language code by using the multi-language pre-training model; and target language code correction is carried out through conventional function testing and grammar checking. According to the method, multi-channel recursive combination and a hierarchical recursive expansion mechanism are combined with self-supervised pre-training, so that accurate generation and performability improvement of cross-language codes are realized.

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 provides a software architecture governance system based on automatic modeling and holographic penetration analysis. The software architecture governance system comprises multiple modules: a project management module used for managing all analysis projects; the source code management module is used for pulling, updating and deleting project source codes; the analysis drive management module is used for uniformly managing and calling analysis drive programs; the multi-language analysis driving cluster is integrated with analysis driving programs corresponding to multiple programming languages and is responsible for analyzing source codes, generating a standardized software chart model and storing the standardized software chart model in a database; the rule engine module is used for supporting a complex code analysis service; the cross-project integrated analysis module generates a system architecture diagram according to the plurality of software models and stores the system architecture diagram into a diagram model library; the multi-dimensional data fusion interface module provides penetrating analysis interfaces of a code layer, a design layer and a framework layer; and the architecture model visualization module is responsible for displaying the system architecture in a multi-dimensional visualization manner. The method can be used for automatic modeling, tracing analysis and interactive visual presentation of a complex system architecture.

The invention provides an interactive real-time loop feedback programming teaching system based on a large language model, and the system comprises a task driving module which is used for generating a multi-language exercise library based on the large language model and dynamically recommending tasks in combination with the programming capability of a user and an interest label; the code writing and debugging module is used for writing multi-language codes by a user, receiving the multi-language codes submitted by the user, executing multi-language compilation and generating compilation data, and the compilation data comprises execution logs, performance data and error information; the programming capability portrait module is used for analyzing the compiling data by utilizing a large language model to obtain programming behavior data, and processing the programming behavior data to obtain a user programming capability portrait; the intelligent interaction module is used for analyzing the programming ability portrait by adopting a large language model to generate targeted teaching feedback, and calling AI assistant teaching to execute five-step guide teaching based on the targeted teaching feedback; the reflection internalization module is used for generating a reflection log based on the user ability portrait generated by the programming ability portrait module, the reflection log comprises an error mode, a learning habit and a cognitive blind spot, and an internalization strategy is recommended according to the content of the reflection log. The internalization strategy refers to providing personalized learning methods, learning plans, learning guide, learning guidance and recommendation tasks of updating the task driving module for the user according to the current error type.

The invention discloses a message issuing speed control method and system based on an AI large model. The method comprises the steps of collecting multi-source data in real time and constructing a multi-dimensional fusion feature vector; based on the BERT-CNN distillation architecture, detecting abnormity and executing hierarchical fusing; based on the fusion feature vector, using a reinforcement learning model to predict message issuing rates of a plurality of time windows in the future and dynamically adjusting priorities; in the offline stage, a mixed integer programming model is adopted to generate minimum cloud resource cost, and in the online stage, a deep reinforcement learning model is adopted to carry out real-time resource fine tuning; based on the node health degree, calculating a traffic allocation weight through a smooth weighted polling algorithm so as to carry out load balancing; different business scenes are adapted through domain adversarial training and multi-task learning, and different languages are adapted through multi-language BERT coding. The message rate is accurately controlled to improve the system stability and the resource utilization rate; low-cost scheduling fine tuning of cloud resources is realized; various business scenes and languages can be quickly adapted, and the development cost and time are reduced.

According to the intelligent terminal equipment intelligent adaptation method and device, intelligent terminal automatic discovery is carried out based on scene-based adaptive ARP scanning and multi-fingerprint UPnP filtering, access equipment is obtained, automatic and precise discovery of intelligent terminal equipment is achieved, and the intelligent terminal equipment can be automatically and accurately found by standardizing the scanning frequency and the filtering rule. The equipment discovery efficiency and accuracy are improved, the access equipment is subjected to prefabricated API library matching and AI reverse analysis to obtain interface information of the access equipment, automatic analysis of a standard interface and a private interface is realized based on a multi-dimensional analysis technology of an AI large language model, and the equipment discovery efficiency and accuracy are improved by utilizing the AI large language model and combining a built-in multi-language programming template. According to the method, the adaptive code matched with the interface information is automatically compiled, the adaptive code is automatically generated based on the AI technology, the compatibility of multi-protocol and multi-interface type equipment is supported, and finally the core problems of low efficiency, poor compatibility, difficult maintenance and high threshold in the existing intelligent terminal adaptation process are solved.

The invention relates to a federal multi-language machine translation method based on efficient fine tuning, and belongs to the technical field of natural language processing. Aiming at the problems of high communication cost and long training time in a federated learning-based multi-language machine translation method, the invention provides a federated multi-language machine translation method based on efficient fine tuning, which comprises the following steps of: efficiently fine-tuning a multi-language translation model of a client; performing gradient similarity clustering on the fine-tuned multi-language translation model; carrying out average aggregation based on the clustered multi-language translation model; and deploying a federal multi-language machine translation device based on efficient fine tuning. According to the method, the calculation and communication overhead is greatly reduced while the translation performance is kept, and the method is suitable for distributed translation tasks in a multi-language scene.

The invention discloses a cross-border logistics document multi-language machine translation method based on natural language processing, and relates to the technical field of machine translation, and the method comprises the steps: collecting original data of a cross-border logistics document, and carrying out text extraction and preprocessing through an OCR technology; performing language recognition and format analysis on the preprocessed document text to determine a source language and a target language; using a pre-trained cross-language alignment translation model to translate the document text into a target language text; the translation result is input into a compliance auditing module, and automatic compliance auditing is conducted through a knowledge graph and a double-check algorithm; and generating an output containing a translation result and a compliance audit report, and supporting manual review and revision. According to the method, the translation accuracy of the documents can be effectively improved, the manual auditing burden is reduced, and the globalization requirements of cross-border e-commerce and logistics enterprises are met.

The invention provides an atlas updating method and device based on a large model, electronic equipment and a medium, information is extracted from large-scale text data by utilizing a natural language processing model, and the method mainly comprises the steps of data collection and preprocessing, entity extraction, relation extraction, atlas updating, model evaluation and iteration and the like. According to the method, an automatic crawler technology, multi-language text processing, transfer learning, visual data auxiliary entity extraction, relation extraction based on a pre-training language model and other technologies are comprehensively applied, and multiple beneficial effects of graph timeliness, multi-language adaptability, model generalization ability improvement, extraction accuracy improvement and the like are achieved. The atlas updating and continuous optimization process is optimized by means of an incremental updating strategy, a dynamic learning system, user feedback data, a conflict resolution strategy and the like. In conclusion, according to the method, the accuracy, the integrity and the user friendliness of the atlas are remarkably improved, meanwhile, the dependence on the annotation data is reduced, and the overall calculation efficiency and the model generalization ability are improved.

The invention discloses a multi-language internationalization translation method and system, a medium and equipment, and is applied to a distributed control system.The method comprises the steps that a background processing program reads a user visible text wrapped by an internationalization identifier in a source file and stores the user visible text as a json file; the automatic translation large model translates the user visible text to obtain the translated user visible text, and the background processing program stores the translated user visible text into the json file again; when the distributed control system runs based on a source code, automatically loading a dynamic library, matching a user visible text required to be translated of an internationalized identifier package with a json file, and displaying the user visible text required to be translated as a translated user visible text based on a result returned after matching, the multi-language version can be obtained without modifying a large number of source codes, the system language switching efficiency is improved, the labor cost is reduced, and the system maintenance efficiency is improved.

The invention provides a method and a system for realizing cross-platform business rule dynamic analysis and centralized management based on GraalVM, business rule scripts of different code languages are generated through a rule configuration center and are stored in a MinIO distributed file system in a file form, and a business system front end obtains the business rule script compatible with a current terminal and executes local verification; the back-end service creates an isolated and safe execution environment by integrating a GraalVM multi-language runtime engine, loads a business rule script which is completely the same as that of the front end from a MinIO distributed file system, and executes homologous rule verification; and when the business rules are changed, the rule configuration center updates the business rule scripts and stores the business rule scripts in the MinIO distributed file system in a file form. According to the invention, the problems of logic repetition, maintenance difficulty, update lag and the like caused by repeated coding of service rules at the front end, the rear end and various clients in the existing service system are solved.

The invention relates to the technical field of risk control scene feature development, in particular to a multi-source data intelligent feature development system based on large language model driving, which comprises a data preprocessing module, a feature generation module and a feature screening optimization module, the data preprocessing module realizes automatic processing and multi-language support of unstructured data; the feature generation module generates complex features and advanced semantic features according to business scene requirements by using a large language model, so that the feature dimension and depth are greatly expanded; and the feature screening optimization module performs multi-stage filtering on the high-dimensional candidate features, and determines an optimal feature subset through feature combination optimization. The system can intelligently and efficiently extract high-quality features from multi-source data, significantly improve the data processing efficiency and the quality of model features, enhance the adaptability to a new business scene, reduce the labor cost of feature engineering, and have good expansibility and application value.

One or more unit-test cases are generated from a monolingual code corpus and the generated unit-test cases are filtered to generate a corpus of unit-test cases which have acceptability scores exceeding one or more predefined thresholds. One or more of the code samples of the monolingual code corpus are translated from a source language to a target language using a pretrained Large Language Model and the generated unit-test cases are translated from the source language to the target language. The LLM-translated code samples are validated using the translated unit-test cases and a parallel-data training corpus comprising the LLM-translated code samples that pass the validation is created. The pretrained large language model (LLM) is fine-tuned using the parallel-data training corpus, a given code segment is translated using the fine-tuned large language model (LLM), the translated given code segment is tested and the tested given code segment is deployed.

The invention discloses a code processing method and device fusing grammar structure and graph structure learning, and the method comprises the steps: collecting high-performance project codes, extracting hot code segments, and analyzing the structural features of the hot code segments; converting the hot code segment into an abstract syntax tree AST file, performing structured analysis, converting the file into Python tree structure data, and expanding node attributes; converting the tree structure data into graph structure data, generating edge, graph and node index files, and constructing the graph structure data and corresponding code structure labels; constructing a graph attention network model for different code structures, and training a plurality of GAT models based on graph structure data and labels; and converting the user input code, inputting the converted code into each GAT model for prediction, and integrating and outputting a feature vector. According to the method, grammar logic is accurately captured through AST conversion and node expansion, multi-language AST is unified into a graph structure, the recognition accuracy of a complex code structure is improved through a GAT multi-model architecture, full-process automation is achieved, and the labor cost is reduced.

The invention provides a multi-language-oriented source code automatic verification method and system, and relates to the technical field of computers.The method comprises the steps that multi-language source codes are obtained; compiling the multi-language source code through an LLVM compiler to generate an intermediate file; the intermediate file is optimized; analyzing the optimized intermediate file through an IR analyzer to generate a symbolic execution model; performing simulation execution operation on the symbolic execution model; and performing security verification on the symbolic execution model after simulation execution operation to obtain a verification report. Unified verification of multi-language source codes can be achieved, the verification environment building and development cost is greatly reduced, and the overall verification efficiency is improved; and the analysis capability of the intermediate file can be enhanced, the logic constraint relationship in the code can be accurately captured, the comprehensiveness and reliability of the verification work can be practically guaranteed, and diversified software security verification requirements can be met.

The invention provides a low-resource multi-language large model training method and system for personalized course learning, and belongs to the technical field of large language models, and the method comprises the steps: S1, collecting training samples of multiple languages; performing de-duplication and de-noising processing on each sample, then unifying data formats, and adding language attributes as language labels; s2, initializing parameters of an adaptive sampling scheduler and a dynamic loss scheduler; and S3, taking the pre-trained large language model as a base model, and adding an adaptive sampling scheduler and a dynamic loss scheduler in the training process. According to the method, the dependence on low-resource language annotation data is reduced, and the training weights of different language samples can be adaptively balanced; and dynamically matching the multi-language task difficulty with the model learning progress.

The invention discloses a method and a system for automatically repairing context learning code vulnerabilities of a large language model, and aims to solve the problems that invalid patches are easily generated, vulnerability causes are misunderstood and verification is lacked in existing LLM zero sample repairing, and a traditional method depends on annotated data or test input. The method comprises the following steps: processing a vulnerability code-patch pair containing a plurality of different CWE types and a target vulnerability code, extracting vulnerability-related codes and constructing an example pool; an adaptive example is selected through comprehensive comparison of semantics, lexical and structural similarity; generating prompt words in combination with related codes and adaptive examples, driving LLMs to generate candidate patches, and outputting effective patches after verification of multiple LLMs; the system comprises a code processing module, an example selection module and a patch generation and verification module. According to the method, LLM and a large amount of annotated data do not need to be finely adjusted, the repair efficiency and accuracy are improved, the labor cost is reduced, multi-language extension is supported, and industrialization potential is achieved.

A computer-implemented system analyzes program and data flows in a software system comprising code written in multiple programming languages using a generative large language model (LLM) directed by programming-language-specific prompts. The LLM identifies functional components within the code, generating labeled graph nodes that include a node type, a node name, and dependency information. A graph construction computer system processes the labeled graph nodes to generate a directed graph, where nodes represent functional components and directed edges represent dependencies. The system stores the graph in a database and provides a web-based interface for visualization, allowing users to explore, query, and analyze program and data flows across the software system. The system enables automated, language-agnostic dependency mapping, facilitating software analysis, debugging, and modernization.

The invention relates to the technical field of big data translation systems, and discloses a language translation system and method based on big data. The method comprises the steps of collecting multi-language historical data, and obtaining a source language text data set, a target language text data set and a translation evaluation data set which are collected within a preset time range; then, executing stability evaluation on the three data sets to obtain a language use stability factor, a translation consistency stability factor and an evaluation reliability stability factor; then, the stability factors serve as key indexes, dense exploration is executed in a translation parameter configuration domain, and priority translation configuration is determined; and finally, translating the input source language text according to the priority translation configuration and a predetermined translation task set to generate a serialized translation data set, analyzing the set by adopting a translation result analyzer, and outputting a final translation result.

This application discloses a method and system for multilingual enhancement based on a large language model using model ensemble. The system includes: a pre-trained multilingual translation model, a semantic representation mapping module, and a large language model. The multilingual translation model is used for multilingual semantic modeling and language generation, including a multilingual encoder module and a multilingual decoder module. The semantic representation mapping module is used to transform the latent space representations of different models into an interactive unified semantic space based on a cross-model representation mapping mechanism. The output of the multilingual encoder is mapped to the unified semantic representation space of the large language model, and the mapped semantics are input into the large language model to perform language-independent instruction understanding. The intermediate semantic representation output by the large language model is mapped and transformed to a cross-attention representation space, generating the final output text under the target language distribution. The system of this application outperforms existing technologies in terms of efficiency, stability, and generation quality in multilingual capability extension.

Described herein are methods, systems, and media for supporting multi-language user sessions and fulfillments comprising: maintaining a repository of fulfillment objects each comprising a language and a region; establishing a user session with a user; determining a user region for the user in association with establishing the user session; identifying one or more fulfillment objects in the repository available for the user region; processing the user session, the user session comprising one or more user requests; applying a language detection model to each request to determine a user request spoken language; applying an understanding module to each request to recommend one or more of the fulfillment objects matching the region for the user; and rendering a response to each request to the user, utilizing the one or more of the fulfillment objects matching the region for the user, in the user request spoken language.

The application discloses a kind of multilingual code generation methods based on self-supervised pre-training, comprising the following steps: obtaining and cleaning multilingual code data, forming training corpus;Code data is represented as abstract syntax tree, the control flow graph and data flow graph of code data are extracted, and unified semantic representation is obtained by combining graph encoder and sequence encoder;Self-supervised pre-training task is designed, and the semantic representation is pre-trained based on the training corpus;Multilingual pre-training model is constructed based on the recursive neural tensor network and multilingual embedding matrix improved in structure;When natural language is input by user, the multilingual pre-training model is used to generate target language code;Target language code is corrected by routine function test and syntax check.The application realizes accurate generation and executable improvement of cross-language code by combining self-supervised pre-training with multichannel recursive combination and hierarchical recursive development mechanism.

The invention discloses a character marking and identifying method and device, equipment and a storage medium, and the method comprises the steps: obtaining the text content of a current text input by a user, mapping the mantissa feature of each Unicode point value in the text content to a private area, generating a corresponding private area code point, and carrying out the recognition of the Unicode point value in the private area; the private area comprises a basic multi-language plane private area, a private area A and a private area B; inserting the private area code points into the text content as zero-width characters to obtain updated target text content; the original mantissa features of the code points of the private area are compared with the actual mantissa features of the target text content, and the current text is judged to be manually input or other source content including AI generation according to the comparison result, so that the reliability and accuracy of text identification can be remarkably improved; the method does not need to depend on a large language model for complex analysis, greatly reduces the technical threshold and detection cost, and has good cross-platform compatibility and practical application value.

The invention relates to the technical field of MCU instruction driving, and discloses an AI-based MCU instruction driving generation method and system.The AI-based MCU instruction driving generation method comprises the steps that a concept ontology network is obtained according to a unified semantic representation framework, and a mapping relation between multi-language expression and a core concept is established; according to the concept ontology network, a holographic semantic system architecture is obtained; determining a conceptual language joint learning mechanism according to the holographic semantic system architecture; zero sample cross-language migration capability is realized according to a conceptual language joint learning mechanism; and obtaining an ontology-based knowledge organization system in combination with the zero sample cross-language migration capability to form structured MCU-driven domain knowledge representation. Through the unified semantic representation theory and the concept ontology network, the understanding accuracy of the same technical requirement expressed in different languages is improved.

System and methods for generating a cross-domain multilingual model are disclosed. In some embodiments, a disclosed method includes: storing, in a database, a plurality of first utterances associated with a first language, training a first model using the plurality of first utterances, the first model being associated with the first language, generating, using the first model, a plurality of first representations associated with the plurality of first utterances, training a second model, using the plurality of first representations, the second model being associated with a plurality of second languages, receiving, using the second model, a second utterance in the second language, and generating, using the second model, a response in one or more languages of the plurality of second languages.