78 results about "Cross lingual" patented technology

The application discloses a cross-natural language code retrieval model training method, a cross-natural language code retrieval method, a device, equipment and a medium, and relates to the technical field of artificial intelligence and software engineering. The cross-natural language code retrieval model training method comprises the following steps: obtaining an original corpus database, and constructing training data according to the original corpus database; performing confusion and inversion on main language codes to obtain main language code samples, wherein the main language code samples comprise main language code positive samples and main language code negative samples; and training an initial model through a gradient inversion layer according to the training data and the main language code samples to obtain a target model. According to the application, the natural language-specific "fingerprint" features in the codes can be removed, the embedding space alignment direction can be unified, the sampling distribution deviation in the training process can be reduced, and the consistency and generalization capability of cross-language code retrieval can be improved.

The present application relates to the cross technical field of speech signal processing, respiratory physiological monitoring and artificial intelligence, and specifically discloses a respiratory-speech pause signal analysis system and method. The present application synchronously collects speech and respiratory signals, extracts language-adapted pause parameters and physiological indexes, performs time sequence alignment and correlation analysis, and then fuses a prediction model and a true-false recognition model for intelligent analysis, thereby solving the problems that traditional heart-lung function detection relies on professional equipment and cannot be remotely and non-contactly monitored, and that existing speech analysis lacks a physiological coupling mechanism, leading to the inability to identify synthetic speech and insufficient cross-language adaptation, and realizing the dual ability improvement of non-contact respiratory physiological state evaluation and speech fraud recognition.

This invention belongs to the field of medical wristband technology, specifically disclosing a translation method for bidirectional communication between medical staff and patients based on multimodal interaction, including the following steps: Step S1, the multimodal interaction unit receives multimodal input signals; Step S2, the multimodal interaction unit fuses the multimodal input signals to generate comprehensive input information; Step S3, the comprehensive input information is identified and translated based on a medical-specific translation engine; Step S4, the context-aware module analyzes the dialogue content, identifies the scenario, and dynamically adjusts the translation results; Step S5, the adjusted translation results are synchronously output bidirectionally and broadcast via voice. This invention achieves three core breakthroughs in clinical cross-language communication through a translation mechanism combining multimodal signal fusion and context awareness: enabling real-time, accurate, and private barrier-free communication between doctors and patients, reducing the risk of medical errors due to language barriers, improving consultation efficiency and patient satisfaction, and reducing the risk of misdiagnosis.

This invention belongs to the field of natural language processing and neural machine translation technology, and discloses a low-resource neural machine translation method that integrates a shared semantic space and bidirectional iterative generative optimization (BIGO). The method includes constructing a shared semantic space module and a bidirectional iterative generative optimization module. First, this invention utilizes singular value decomposition and entropy regularization for optimal transport to map the source language and the target low-resource language into a unified semantic space, achieving high consistency between the two languages ​​at the representation level, thereby significantly improving the model's cross-language generalization ability under conditions of insufficient data. Subsequently, this invention continuously improves translation quality through alternating training of forward and backward Transformer models, in a loop of generating pseudo-bilingual corpora, backward reconstruction, and joint forward and backward optimization. This allows the model to correct errors generated in the previous iteration and enhance semantic consistency in each iteration. This invention can stably achieve dual convergence of model parameters and semantic alignment matrix, significantly improving the accuracy, robustness, and long sentence consistency of low-resource language translation, and effectively reducing training instability and overfitting.

The present application relates to a large model Lao translation method and system based on agent cooperation and cross-language semantic alignment, belonging to the field of natural language processing and machine translation. In the independent multilingual translation generation stage, the target Lao translation corresponding to the source sentence, the reference language translation and the linguistically similar language translation are generated respectively; cross-language semantic alignment and correction are carried out, the English translation is taken as the semantic alignment reference, the Thai translation provides morphological and syntactic guidance, and through the iterative information interaction between agents, the Lao translation is continuously evaluated and corrected; in the semantic clarification and strengthening stage, the key semantic fragments of the source sentence are extracted by analyzing the agent, the overall structure is simplified, and the Lao agent is assisted to generate the final high-fidelity translation result. The present application significantly improves the semantic accuracy and structural rationality of the Lao translation result; effectively solves the semantic illusion problem easily produced by the large language model in the Lao machine translation scene due to data scarcity.

The application relates to an international public opinion event information dissemination and control system based on artificial intelligence, and relates to the field of social communication science. The system can monitor, identify, analyze, track and effectively control the information dissemination in international public opinion events in real time. The system uses natural language processing (NLP), machine learning (ML), deep learning (DL) and other artificial intelligence technologies to deeply mine and understand massive cross-language and cross-platform data, thereby realizing accurate identification of public opinion events, intelligent analysis of dissemination paths, early warning and intervention of negative information, and guidance and amplification of positive information. The system aims to improve the control efficiency and accuracy of international public opinion events, maintain social stability, and provide decision support and action basis for relevant departments.

The application discloses a programming language project testing method and device, electronic equipment and a computer readable storage medium. The method comprises the following steps: determining a test scenario of a target programming language project; when the test scenario is a cross-language scenario, recording interface traffic in a production environment to obtain first recorded traffic; playing back the first recorded traffic through a pre-translation interface and a post-translation interface in a test environment to obtain first playback traffic and second playback traffic; determining a test result of the target programming language project in the cross-language scenario according to the first playback traffic and the second playback traffic; when the test scenario is a same-language scenario, recording interface traffic of a pre-modified interface to obtain second recorded traffic; playing back the second recorded traffic through a post-modified interface to obtain third playback traffic; and determining a test result of the target programming language project in the same-language scenario according to the second recorded traffic and the third playback traffic. The technical solution provided by the application can realize more accurate programming language project testing.

The application discloses a bilingual question and answer method based on knowledge retrieval and generation collaborative training, and belongs to the technical field of intelligent question and answer, and comprises the following steps: obtaining a corpus g0 and a question and answer library; mapping sentences in the g0 to the same semantic space to form a set A; performing regular hierarchical clustering on the set A to generate a semantic prototype vector of each clustering cluster; generating a knowledge graph g1 and a causal diagram g2 to form a retrieval source set G; marking a sample set and a main retrieval source for a question q of the question and answer library; constructing a knowledge retrieval enhancement model and training the knowledge retrieval enhancement model into a bilingual question and answer model, which is used in intelligent question and answer. The application introduces hierarchical semantic aggregation, cross-source adaptive gating and causal biasing retrieval mechanism, solves existing problems such as scattered knowledge, language alignment and self-learning update, provides a new technical path for low-resource cross-language question and answer, and greatly improves the quality and application value of a cross-language knowledge enhancement question and answer system.

This invention discloses a cross-language network message encapsulation method based on function signatures, belonging to the field of cross-language network message encapsulation technology, including the following steps: S1, function signature parsing; S2, parameter preparation; S3, intelligent serialization; S4, message header assembly; S5, checksum calculation; S6, message assembly and transmission; S7, cross-language parsing. This cross-language network message encapsulation method based on function signatures uses the high 3 bits of the first byte to identify the data type and the low 5 bits to store control information or decimal values, achieving optimal encoding for values ​​in different ranges. It also maintains an independent string cache table for each communication session, with strings as keys and unique integers as indexes. When transmitting a string for the first time, the index and string are transmitted simultaneously; when transmitting the same string subsequently, only the index is transmitted, allowing the receiving end to quickly look up and restore the string, significantly reducing the amount of duplicate strings transmitted.

Embodiments of the present specification provide a task model training method and device, wherein the method comprises: obtaining first training data, the first training data comprising at least two training sample pairs, each training sample pair comprising a first training text and a first training sample corresponding to the first training text, the first training sample comprising a positive sample and a negative sample, and the training sample pair comprising a multilingual training sample pair; training an initial task model based on the at least two training sample pairs to obtain a pre-trained task model; constructing a to-be-trained task model according to the pre-trained task model and a preset downstream task; and training the to-be-trained task model according to second training data corresponding to the preset downstream task to obtain a target task model, the second training data comprising at least one second training sample and a sample label corresponding to each second training sample. By training the initial task model, a strong cross-language understanding capability can be learned, and the model training efficiency and the accuracy of the task execution result can be improved.

This invention relates to a multilingual generative retrieval method based on cross-language semantic compression, belonging to the field of information retrieval technology. The invention includes the following steps: constructing a multilingual document retrieval dataset; extracting keywords from multilingual documents from multiple perspectives using a keyword extraction model, and calculating the extracted keywords using semantic similarity to construct a similarity matrix; performing semantic clustering based on the similarity matrix, representing clusters using atomic IDs, and then assigning document identifiers to each multilingual document by the cluster containing the keywords; in the inference stage, after inputting a query, employing a dynamic multi-complement constraint decoding method, gradually narrowing the decoding range of the document identifier in the current step based on the decoding results of previous steps, thereby obtaining the final document identifier. The retrieval capability of this invention is significantly improved compared to other models.

A method and system perform operations comprising: setting a first instruction tuning dataset comprising tasks in a first language; setting a second instruction tuning dataset comprising tasks in a second language; generating a first instruction, written in a same language as the first language, for the first instruction tuning dataset, and storing the first instruction for the first instruction tuning dataset; generating a second instruction, written in a same language as the second language, for the second instruction tuning dataset, and storing the first instruction for the first instruction tuning dataset; generating a cross-language instruction based on the first instruction tuning dataset, the first instruction for the first instruction tuning dataset, the second instruction tuning dataset, and the second instruction for the second instruction tuning dataset; and performing instruction tuning for an artificial intelligence model using the cross-language instruction.

This invention discloses a unified data interaction and standardized interface method for industrial software, relating to the fields of industrial software system integration, cross-language and cross-platform data interaction, and automated invocation of intelligent systems. The core of this invention is a design of "single-business-specific table type + unified interaction rules." It customizes a dedicated Table Value Parameter (TVP) table type for each business segment, adds a core field for operation type as the basis for business action judgment, encapsulates all add, subtract, delete, modify, and query operation logic for a single business into a unique dedicated stored procedure, and exposes a unified standardized interface, thus constructing a universal data interaction paradigm of "dedicated table type, unified rules, and single interface entry point." This invention completely eliminates the technical barriers to interoperability across systems and development languages. It seamlessly adapts to all development languages / systems, including Java, C#, .NET MAUI, Web development, and ARKTS. Different business logics pass parameters using dedicated table types and call according to unified rules, reducing cross-system connectivity and development difficulty to a minimum. Simultaneously, it achieves vulnerability closure through full front-end verification, perfectly adapting to AI automated call requirements. This significantly reduces the costs of multi-system integration, development, and maintenance of industrial software. It can be widely applied in various manufacturing industries such as metallurgy, machinery, chemicals, automobiles, and electronics, as well as in all fields with system data interaction needs, including smart IoT, enterprise digital management, and e-government. It is a set of industrial software data interaction standards that is practical, universal, and intelligent. This invention has been fully implemented in actual industrial ERP and MES systems, and can run stably in real production environments for a long time, demonstrating mature engineering value and industrial promotion capabilities.

The application relates to the technical field of artificial intelligence, and discloses a cross-border logistics customer service conflict intelligent mediation method and device, wherein the method comprises the following steps: acquiring multi-modal complaint data of a user, performing cross-language semantic analysis and alignment on the multi-modal complaint data, and generating unified semantic representation; based on the unified semantic representation, automatically associating and fusing logistics event data in multiple heterogeneous data sources, and constructing a visual evidence chain corresponding to the complaint; matching and reasoning the visual evidence chain with a pre-constructed responsibility association graph, and generating a responsibility judgment result; according to the responsibility judgment result, combining the cargo attributes and customer parameters, and performing joint optimization calculation through a compensation strategy model to generate and output a customized mediation execution scheme. The application can improve the analysis adaptability of multi-modal complaint data and the integration efficiency of multi-source heterogeneous logistics data in cross-border logistics customer service conflict mediation, and improve the accuracy of responsibility judgment and the pertinence of compensation schemes.

The application discloses a kind of based on AI cloud cross-language conversation and external network video and audio translation method and system, comprising the following steps: in the exclusive foreign language access communication identification of intelligent communication terminal preset;When the external input source request of exclusive foreign language access communication identification is monitored to intelligent communication terminal, the transmission path of original audio signal is redirected to AI intelligent body cloud service module;AI intelligent body cloud service module receives original audio signal, determines source language type, and then executes text translation and mother language synthesis, generates target voice stream;Original audio signal is executed in cloud to delete instruction, and target voice stream is encapsulated into downstream data packet;Intelligent communication terminal receives downstream data packet, and outputs pure mother language voice through audio synthesizer.The AI intelligent body service architecture deployed in cloud and the system kernel of intelligent communication terminal are deeply coupled in the application, interception, redirection, translation and original sound are removed to audio stream.

The application relates to the technical field of computer data processing, and discloses a search formula generation method and system based on instruction recombination and local feedback optimization, the search formula generation method comprising the following steps: step S1, dynamic assembly and semantic expansion of instruction segments; step S2, controlled term filtering based on a longest match mechanism; step S3, construction of a Boolean logic tree; and step S4, closed-loop logic repair based on component ID mapping. The application significantly reduces interaction overhead and computing resource consumption, solves the semantic drift problem of composite terms in a cross-language scenario, and realizes the compatibility of the probability of a generative model and the determinacy of a database syntax.

Provided in the present application are an invocation method, an invocation apparatus and a computer device. The method comprises: on the basis of a first source code file, determining collection information of one or more NAPI objects, wherein the first source code file comprises a first code statement, and the first code statement is used for indicating the invocation of information of one or more NAPI objects in a second source code file; on the basis of the first source code file and the collection information of the one or more NAPI objects, generating a machine code file; and running the machine code file, so as to obtain the information of the one or more NAPI objects in the second source code file. In the invocation method, the invocation apparatus and the computer device provided in the present application, collection information of a NAPI object is used for guiding the compilation of a first source code file, and a machine code obtained by means of compilation can run efficiently, thereby improving the efficiency of cross-language invocation and also improving the user experience.

This invention addresses the challenge of trajectory planning for unmanned mining trucks in complex dynamic environments by disclosing a dynamic obstacle avoidance trajectory planning method based on interactive prediction and iterative training. First, a CTRA model is used to predict the trajectory of dynamic obstacles in multiple steps to provide forward-looking information. Then, a deep reinforcement learning decision framework based on SAC is constructed, explicitly encoding the predicted trajectory into the state space and designing a multi-objective adaptive reward function. Simultaneously, a cross-language high-fidelity simulation platform using Python and Simulink is established, integrating a seven-DOF vehicle dynamics model to bridge the Sim-to-Real gap. Finally, an adversarial iterative training mechanism is implemented between the vehicle and dynamic obstacles through policy reuse, enabling the agent to learn higher-order interaction capabilities during self-games, thereby improving traffic efficiency in mixed-traffic scenarios in mines while ensuring safety.

Provide a system. 【Solution means】 Means for acquiring voice information, digitizing the voice information, and transferring it externally; Means for converting the voice information received from the outside into character information; Means for translating the character information between languages; Means for displaying the translation result to the user; Means for acquiring the captured visual information and recognizing the characters in the visual information; Means for providing the results translated in multiple languages in real time by voice or text; Means for referring to the physical guidance devices at tourist attractions, etc., and presenting the route and guidance to the user in multiple languages; A system including the above.

The application relates to the technical field of cross-language vector retrieval, in particular to a vector retrieval method based on a language model. The application adopts a mixed English query text; identifies Chinese segments and English segments, and eliminates stop words; calls a Chinese large-text vector conversion model to generate a Chinese segment vector after optimization; calls an English large-text vector conversion model to generate an English segment vector after optimization; determines a primary index and a secondary index based on the proportion of Chinese segments; calls the primary index for retrieval to obtain a first candidate vector set; calls the secondary index for verification to obtain a second candidate vector set; calculates a plurality of index correction coefficients corresponding to the candidate vectors to calculate a correction similarity; sorts the plurality of candidate vectors based on the correction similarity to generate a first output result; and determines whether a screening mechanism is triggered based on the number of candidate vectors to generate a second output result. The application significantly improves the semantic precision of vector matching.

This application relates to the field of automated migration technology for computer software, specifically a declarative method for automated cross-platform UI translation. The method includes: parsing a source UI file, extracting component types, attributes, modifiers, and child node information, and constructing a structured UI tree; mapping the component types, attributes, and modifiers in the UI tree to the basic structure of the target platform ArkUI based on a predefined cross-language component mapping table, generating an ArkUI code skeleton; constructing prompts, inputting the ArkUI code skeleton and prompts into a large language model, and using the large language model to generate preliminary ArkUI code; correcting syntax errors and incompatibilities in the generated preliminary ArkUI code using deterministic transformation rules, and outputting target code that can be directly compiled and run. This invention significantly improves the engineering implementation efficiency of cross-platform UI translation while maintaining high-fidelity visual effects.

The application relates to the technical field of translation, and discloses a keyboard extension in-knowledge base driven in-situ translation and reply recommendation system, which comprises a data acquisition and preprocessing module, a knowledge retrieval and evidence management module, a content generation and localization module, an emotion adaptation and candidate scoring module, and an in-situ interaction and feedback optimization module. Through the keyboard extension in-knowledge base driven in-situ translation and reply recommendation system and method, various scenes of cross-language communication and instant reply can be covered, not only the accuracy of text translation is concerned, but also elements such as context adaptation, style matching and professional term alignment are included, and user input habits and scene requirements are further combined, so that the translation and recommendation results are more accurate and fit the actual communication scene, and more intelligent support is provided for cross-language communication and efficient reply.

This invention discloses a cross-language compiler optimization method based on graph neural networks. The method uses a UAST module to map the abstract syntax trees (ASTs) of different programming languages ​​to a shared semantic space. The FUAST module then fuses control flow and data flow information to form a flow-enhanced AST representation. The Sub2Vec module extracts key optimization subgraphs such as control flow, function inlining, and loops, and models their local structure and global relationships. The IRGAT module uses a sparse attention mechanism after structural pruning to aggregate features from the subgraphs, generating graph-enhanced sequence vectors. Finally, the SALT module, based on a lightweight Transformer architecture, embeds IRGAT as a structure-aware component, which processes and outputs optimization decisions through a feedforward network. This invention achieves unified semantic understanding, dynamic information fusion, and key region focusing for multi-language programs, and possesses compiler platform versatility.

This invention discloses a multi-agent content generation method and system driven by cross-cultural dynamic profiling, belonging to the fields of artificial intelligence and cross-cultural information processing technology. The method includes: S1, collecting multilingual text data through social media interfaces and performing structural verification, language identification, text normalization, deduplication, and quality filtering to construct a cross-cultural corpus knowledge base; S2, dividing the corpus into groups based on clustering algorithms, extracting group features, and constructing structured user profiles; S3, scheduling multiple agents to collaboratively perform content generation, trend analysis, and cross-cultural interaction tasks according to user profile tags and rule-based routing; S4, constructing a virtual audience cluster and pre-evaluating the generation strategy using a simulation mechanism that decouples the generation model and the evaluation model; S5, optimizing and iterating the generation strategy based on the evaluation results to form a closed-loop update mechanism. This invention effectively improves the stability and computational accuracy of the cross-language data processing link.

The present application relates to a cross-language code intelligent auditing and automatic repair system. The system forms a quality and safety governance closed loop through code acquisition and preprocessing, multi-language unified intermediate representation (fusion AST / CFG / DFG / call graph / symbol table), general rule library detection, AI semantic enhancement, repair patch generation and multi-level verification, and feedback learning. The core is to constrain the repair generation of large language models with an interpretable evidence chain, and through automatic verification and failure rollback mechanism containing syntax, test, performance and security, the correctness and minimum change of the patch are ensured. The present application also relates to a corresponding method, device, processor and computer readable storage medium thereof. The cross-language code intelligent auditing and automatic repair system, method, device, processor and storage medium thereof adopt the present application, realize consistent risk detection across languages, significantly reduce the false positive rate and the risk of introducing new defects by repair, and maintain long-term effectiveness through a continuous learning mechanism.

The application is a large model multilingual security alignment system and method based on joint rejection direction. The application relates to the technical field of large model security alignment. The application constructs multilingual security parallel samples, uses the value flow mask on the frozen large language model to construct positive security state and negative security state, further extracts the joint rejection direction shared across languages from the internal representation difference of the two, and uses the layer-by-layer projection track in the direction as the internal description of the security behavior. Through lightweight parameter learning, the track of the low-resource language approximates the high-resource anchor language, thereby improving the security rejection ability of the low-resource language under the condition of few samples, and keeping the original general ability of the model as much as possible.

Methods and systems for training a neural network include training language-specific teacher models using different respective source language datasets. A student model is trained, using the different respective source language datasets and soft labels generated by the language-specific teacher models, including shuffling the source language datasets and shuffling weights of language-dependent layers in language-specific parts of the student model. Weights of language-independent layers of the student model are copied to a language-independent layers of a target model to initialize language-independent layers of the target model. The target model is trained with a target language dataset.

The present disclosure provides a statistical analysis-oriented cross-language code generation method and device, equipment and medium, by acquiring sample data set, initial statistical requirement information and initial semantic hub model; the sample data set and the initial statistical requirement information are input to the initial semantic hub model, and a plurality of sets of initial statistical analysis execution codes corresponding to a preset programming language are mapped; each set of initial statistical analysis execution code is run respectively to obtain a result vector corresponding to each set of initial statistical analysis execution code; each result vector is subjected to consistency check to obtain a consistency check result; if the consistency check result is abnormal, a first model repair instruction is generated to update the initial semantic hub model to obtain a target semantic hub model; statistical requirement information with a target programming language is input to the target semantic hub model, and reliable statistical analysis execution code can be flexibly generated according to user requirements.