632 results about "Polyglot" patented technology

The invention discloses a method for enhancing dynamic knowledge retrieval based on a large language model, belongs to the field of knowledge retrieval, and aims to solve the problems of knowledge solidification, insufficient timeliness and illusion of a traditional LLM (Logistics Language Model). A multi-granularity knowledge base is dynamically constructed, and a rule and semantic partitioning technology is combined, so that a text is converted into a normalized vector, and a hybrid index is established; a two-channel retrieval triggering mechanism is adopted, keyword matching scores and BERT semantic probability analysis are fused, and retrieval requirements are intelligently judged; vectorization retrieval is realized through a BGE-M3 model, and candidate results are reordered in combination with a cross encoder to improve the precision. The system supports multi-language adaptive processing, dynamic switching of word segmentation strategies and cross-language retrieval, and introduces real-time knowledge updating and version control. According to the method, the answer timeliness and accuracy are remarkably improved, the context coherence of multiple rounds of dialogues is optimized, the method can be widely applied to the fields of intelligent customer service, professional questions and answers and the like, the LLM illusion risk is effectively reduced, and the knowledge traceability is enhanced.

The embodiment of the invention provides a cross-chip platform compiling tool chain method which comprises the following steps: scanning a target platform architecture specification file to extract instruction set features, constructing a platform difference matrix based on the instruction set features to record instruction formats and system call differences of different chip platforms, and normalizing a multi-language syntax tree into a unified intermediate representation; constructing a cross-platform compiler to convert the intermediate representation into a target code; designing a unified intermediate language based on a platform difference matrix to support multi-language compilation; creating an instruction mapper to convert the intermediate representation into a target platform instruction; identifying a target architecture type through a platform identification code; designing a test case to verify a compiling result, and deploying the optimized target program to a target platform; according to the method and the device, the expandability and the code quality of the compiling tool chain can be improved by constructing the unified intermediate presentation layer and the optimization framework, and more efficient cross-platform support is realized.

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 provides an AI-assisted large-model intelligent question and answer accuracy improvement method, and belongs to the technical field of intelligent question and answer. Comprising the steps of data collection, data cleaning, data labeling, dynamic knowledge base construction, knowledge base updating trigger mechanism establishment, pre-training language model improvement, post-processing language understanding enhancement, combination of rule-based and machine learning reasoning, reasoning result verification and optimization, dialogue strategy optimization, emotion perception and response, multi-language search and language recognition search. And multi-dimensional evaluation index setting and regular evaluation and feedback improvement are realized. The intelligent question and answer accuracy improving method is high in understanding ability, timely in data updating, outstanding in reasoning ability and high in language recognition and dialogue ability.

Aspects of the present disclosure relate to detecting hallucinations in language model outputs. Embodiments include receiving a user query. Embodiments further include prompting a language processing machine learning model to generate responses to the user query in each language of a set of multiple languages. Embodiments further include receiving the responses from the language processing machine learning model in response to the prompting. Embodiments further include creating embedding representations of the responses. Embodiments further include calculating, based on the embedding representations, a degree of semantic similarity between the responses. Embodiments further include determining that a response of the responses contains a model hallucination based on comparing the degree of semantic similarity between the responses to a threshold.

Systems and methods provide for a machine learning system to tokenize, classify, and generate representations from a provided input to provide a combined output. An input may be received and processed into tokens for classification based on semiotic classes. For a given semiotic class, particular rule-based algorithms may be selected to generate a desired output for a selected output language. An input may include an auditory or textual input, which may be in a different language from the selected output language, where the particular rule-based algorithms may include morphological rules for particular semiotic classes. Different rule-based algorithms may be modularly generated for particular languages and semiotic classes to build a library of models for processing different inputs.

The embodiment of the invention provides a code exception analysis method and device, a storage medium and a program product. In the embodiment of the invention, in the preset plug-in, the global knowledge graph is constructed through the logic syntax tree of the plurality of original business codes, so that intelligent anomaly analysis is carried out on the modified to-be-detected codes, multi-language and heterogeneous programming styles and complex dependency limitation are broken through, and cross-language and cross-file analysis is supported; change code snippets and associated influence code snippets thereof are accurately identified, and a data basis is tamped and analyzed; the analysis depth is deepened and the accuracy is improved through a multi-dimensional anomaly analysis large model and four-dimensional collaborative analysis in combination with an adaptive review rule and a knowledge graph; and finally, performing correction based on the generated repair scheme. Through the technical fusion of an MCP protocol, a multi-AI model, a syntax tree and a knowledge graph, the high efficiency, accuracy and real-time performance of code examination and repair are realized, and the service development quality and the system operation stability are remarkably improved.

The invention relates to the technical field of data processing, in particular to a multi-language intelligent query method and device, equipment, a medium and a programmer.The method comprises the steps that a query request input by a user in a specific natural language is obtained; determining a corresponding natural language type according to the query request, extracting key information of the query request, and generating a corresponding SQL query instruction according to the key information; and querying a preset database according to the SQL query instruction to generate a query result. Therefore, the problems that in the prior art, only natural language query of a single language is supported, user requirements in a multi-language environment cannot be met, and contextual information in query is difficult to accurately capture and understand, so that data processing accuracy is low and the like are solved.

Disclosed are systems and techniques for training machine learning models. The techniques include generating, using a first automatic speech recognition (ASR) model, a first text output based on a vector representation of a first speech data and generating, using a second ASR model, a second text output, wherein the second ASR model adds noise to a vector representation of the first text output to obtain a noisy vector representation of the first text output and is trained to remove the noise from the noisy vector representation of the first text output. The techniques include calculating a first loss of the second ASR model based at least on a comparison between the second text output and the first text output and modifying learnable parameters of the second ASR model to improve an accuracy of the second ASR model.

The technology provides a model-based approach for multilingual text rewriting that is applicable across many languages and across different styles including formality levels or other textual attributes. The model is configured to manipulate both language and textual attributes jointly. This approach supports zero-shot formality-sensitive translation, with no labeled data in the target language. An encoder-decoder architectural approach with attribute extraction is used to train rewriter models that can thus be used in “universal” textual rewriting across many different languages. A cross-lingual learning signal can be incorporated into the training approach. Certain training processes do not employ any exemplars. This approach enables not just straight translation, but also the ability to create new sentences with different attributes.

The invention provides an execution method and device for a test case in a verification platform, equipment and a storage medium, and the method comprises the steps: obtaining a target test case constructed by an interpreted language, and starting the execution of the target test case on the verification platform; the target test case is a program for providing an excitation component for verification of the to-be-tested design file; in response to execution of the target test case, generating a test trigger instruction through the flow controller, and transmitting the test trigger instruction to a sequence control tool in the verification platform through the socket interface; a sequence control tool is used for analyzing the test trigger instruction, the starting and excitation sending sequence of an excitation assembly in the execution process of the target test case is controlled through an analysis result, an excitation execution result is obtained, and the sequence control tool is compiled through a compilation type language; and the excitation execution result is transmitted to the flow controller through the socket interface to be output. According to the application, multi-language compatibility is realized by adopting the socket interface.

The invention relates to an event knowledge pre-training enhanced cross-language event causal relationship identification method and device. According to the method, a multi-language pre-training language model is combined with multi-language alignment event knowledge in an external event common sense knowledge base, and the multi-language event knowledge is integrated into mPLMs through pre-training task design, so that event causal relationship recognition performance in a low-resource language scene is improved. The method comprises the following steps: firstly, extracting event common knowledge of multi-language alignment from ConceptNet; designing a pre-training method based on a parameter sharing adapter, and integrating event node knowledge and relation knowledge between nodes into mPLMs through an event mask pre-training task and a self-supervision link prediction task; and applying the pre-trained mPLMs to a cross-language event causal relationship extraction task. According to the method, the number of parameters of the model is remarkably reduced, the calculation cost is reduced, and the event causal relationship recognition performance is effectively improved.

The invention discloses an international remote translation system based on AI and an implementation method thereof, and belongs to the technical field of artificial intelligence. Comprising a voice input module, an emotion perception module, a predictive simultaneous interpretation module, a language adaptation module based on few-sample learning, a dynamic translation quality evaluation and feedback module and a multi-language cooperative processing module, and can automatically recognize an input language and dynamically adjust a translation model in a multi-language environment. The emotion information in the voice and the text is captured in real time, the translation path is optimized in combination with the context weight, the emotion transmission accuracy and the translation context consistency are remarkably improved, the term requirements of different fields can be rapidly met, the translation quality is continuously optimized through dynamic feedback, the translation accuracy and smoothness are ensured, and the translation efficiency is improved. And the method has wide applicability in multi-language, cross-cultural communication and professional field application, and has relatively high innovativeness and practical value.

The invention discloses a dynamic interactive prompt sequence control method for chemical production, and relates to the field of flow industrial processes. Based on a state transition rule of a Phase functional block, linear execution and conditional jump of sequential control steps in a polymerization reaction temperature step control scene are realized through SFC programming, interactive processing and SFC logic steps are bound, and an interactive dialog box is triggered in a unified manner through an operation guide window. And the main program and the subprogram realize abnormal state linkage through an FAILIDX mark, and automatically detect a fault clearing state when the abnormity is recovered. The interactive processing dynamically generates an option list, supports multi-language switching, verifies input values in real time, and provides historical suggested values. The method aims at solving the problems that in a traditional sequence control system, the coupling degree of interaction logic and a core control program is high, operation interfaces are not uniform, and the misoperation risk is high, transplanting of cross-control systems and cross-process packages is supported, and the secondary development cost is remarkably reduced.

The invention provides an intelligent agent language ability automatic testing method based on multi-language model self-evolution. The intelligent agent language ability automatic testing method based on multi-language model self-evolution comprises the steps that associated information is acquired; performing similarity retrieval in a pre-constructed sample library to obtain a retrieval sample meeting a set requirement; constructing cue words; the prompt words are input into a voter, the voter comprises a plurality of voting language models, and each voting language model outputs a corresponding voting result; and based on the plurality of voting results, evaluating an output result of the intelligent agent to obtain a judgment result. The purpose of improving efficiency and accuracy is achieved. And when the confidence coefficient is high enough, the result is automatically incorporated into the sample library, and high-quality samples are continuously increased in a dynamic expansion manner, so that the generalization ability of the voting language model is improved, and the self-evolution of the model is realized.

The invention relates to the technical field of natural language processing, and discloses a super-large-scale multi-language neural machine translation method based on a MoE system architecture, which comprises the following steps: S1, an encoder and a decoder adopt a Transform-based architecture, and a MoE layer is embedded in the Transform-based architecture; s2, the MoE layer comprises a plurality of expert models for specific language pair or language characteristic optimization; s3, designing a dynamic gating mechanism, and selecting the most suitable expert model for prediction according to input data features; s4, introducing a load balancing mechanism to ensure that all expert models are subjected to balanced training and use; s5, performing model training by adopting a combined strategy of data parallelism and MoE parallelism; and S6, compressing and optimizing the model by applying knowledge distillation and quantification technologies. The invention discloses a super-large-scale multi-language neural machine translation method based on a MoE system architecture. The super-large-scale multi-language neural machine translation method is an innovative and challenging technology. By reasonably designing and optimizing a model structure, a gating mechanism and a training strategy, the performance and efficiency of multi-language machine translation can be remarkably improved.

The invention discloses an automatic multi-language construction method, system and device and a storage medium, which are used for improving the generation efficiency of a language package and reducing the maintenance cost of multi-language development. The method comprises the following steps: acquiring a project source file, and constructing a tree structure file based on the project source file; traversing the tree structure file, and identifying and extracting text content in the tree structure file; distributing a corresponding position label for each text content, and generating a first language package based on the text content and the position label; extracting a to-be-translated target text in the first language package, and obtaining translation results of a plurality of preset languages in a translation result library according to the target text; generating a second language package of a plurality of preset languages according to the translation result and the position tag; when a request of switching to a target language is received, determining a target language package corresponding to the target language in the second language package; and performing text replacement on the current text content by using the target language package and the target position tag corresponding to the current text content.

The invention discloses a cross-language information sorting method and device based on semantic space clustering prompt, equipment and a storage medium, a prompt template of an unlimited language is initialized by averagely pooling a source language prompt template and a target language prompt template embedding vector, and a progressive multi-language transcoding method is introduced. Language bias in the model learning process is reduced; in the answer engineering stage, an answer space construction method based on clustering is provided, and a unified multi-language answer space is constructed through semantic space clustering guided by semantic consistency, so that multi-language prompt learning answers are clustered, and then information sorting categories are obtained. The method solves the problem of poor cross-language information sorting performance caused by inconsistent answer spaces in prompt learning of different languages in the prior art. And the cross-language scene-oriented information sorting task performance is improved.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing text-to-speech modeling. In some implementations, a computer device receives input text in a first language to convert to a desired speech in a second language. The computer device receives one or more criteria for modifying the desired speech and converts the input text to a desired text in the second language. The computer device generates audio representations of the desired text in the second language and predicts, for each of the audio representations of the desired text and using the one or more received criteria, a pitch value and a duration value. The computer device generates the desired output speech using the predicted pitch value and the predicted duration value for each of the audio representations and provides the desired speech for output.

The invention discloses a multi-language dynamic switching system and method of embedded equipment, and relates to the technical field of human-machine interfaces and embedded systems.The method comprises the steps that source codes in an HMI program are traversed through a character extraction module to extract all character strings; eliminating repeated items, numbering the character strings, and outputting a database file and a replacement array; substituting the serial number into the source code file again by using the substitution array to replace the character string at the corresponding position; outputting the translated database file as a C language source code, compiling the C language source code into a dictionary generation module project, generating an executable file, and outputting the dictionary file to an HMI running directory after the device is started; after the HMI program is started, the dictionary is read into different dictionary arrays according to blocks, and character strings at corresponding positions in the dictionary arrays are extracted after a page sends a request. The method has the advantages of being lower in maintenance difficulty, more efficient in resource utilization, shorter in indexing time, better in system robustness and the like.

The invention relates to a multi-language intelligent question and answer method and device, equipment and a medium in the technical field of e-commerce, and the method comprises the steps: obtaining a question text provided by a user, and determining a question language of the question text; when the question language is consistent with a knowledge language corresponding to the question and answer knowledge base, determining a pre-stored question matched with the question text in the question and answer knowledge base, and taking an answer text corresponding to the pre-stored question as a target answer text; when the question language is inconsistent with the knowledge language, translating the question text into a target question text corresponding to the knowledge language, determining a pre-stored question matched with the target question text in a question and answer knowledge base, and translating an answer text corresponding to the pre-stored question into a target answer text corresponding to the knowledge language; and sending the target answer text to the user. Only one question and answer knowledge base of a specific language needs to be maintained, and the management and maintenance workload of the question and answer knowledge base is remarkably reduced.

The invention discloses a multi-modal-based multi-language custom instruction identification method and system, and the method comprises the steps: S1, constructing a multi-modal large model, and training the model, the multi-modal large model constructing a support input processing unit, a query input processing unit and a measurement discriminator; s2, on the basis of the step S1, registering a user-defined voice instruction; wherein a support feature vector of a user registration instruction is acquired and stored through the support input processing unit trained in the step S1; s3, user voice is obtained, and reasoning and instruction recognition are conducted through the model generated in the step S2; wherein the trained query input processing unit is used for processing the user voice to output a query vector, and the matching degree of the query vector and a pre-stored support feature vector is calculated, so that a user voice instruction is recognized. According to the method, efficient and extensible multi-language self-defined instruction recognition is realized based on a multi-modal fusion and metric learning framework.

The invention provides a link monitoring method and device for a distributed system, electronic equipment and a medium, and the method comprises the steps: capturing the operation state of an application program corresponding to a monitoring agent program based on the monitoring agent program installed at each computing node of the distributed system according to a preset link tracking protocol, corresponding operation information is obtained; wherein the application programs installed in the computing nodes are developed based on multiple programming languages; converting the operation information of the running state of each application program into tracking data in a uniform format; sending the tracking data to a monitoring platform; wherein the monitoring platform is used for analyzing tracking data of different application programs to identify an application layer event, and the application layer event is used for being associated with network layer transmission data to realize link monitoring. According to the method, full-link monitoring can be realized in a multi-language and multi-protocol scene, and the method is suitable for a complex application scene.

The invention discloses an English text automatic proofreading system and method based on intelligent AI, and relates to the technical field of natural language processing, and the method comprises the steps: inputting an original English text, generating a syntactic graph through dependency syntax analysis, calculating a node syntactic centrality weight, and generating a triple description set after screening key nodes; on the basis of the triple description set, constructing a structured prompt template, executing English-in-English bidirectional conversion verification through a multi-language model, generating an initial image, and outputting an aligned final image through iterative optimization circulation; and searching a syntax compliance candidate word library for the conflict text node set, selecting a candidate word with the highest comprehensive score, and outputting a corrected text, a video stream and an error analysis report. According to the method, the text assertion and the visual assertion are synchronously verified through the differentiable grammar rule matrix, and the problem that context sensitive errors are difficult to detect through a traditional method is solved.

The invention discloses a method of connecting multilingual translation module / s with large language model / s for optimized output generation and output translation of user inputs in the user preferred language. This method is carried out by a worker module which is connected to large language model / s and third-party translation module / s to provide seamless translation and text generation capabilities for a user input. Existing machine translation systems and text generation models have limitations in handling multiple languages and integrating translation with complex text generation. The proposed invention addresses these limitations by connecting and integrating user input translation, text generation, and subsequent translation of the output to the user's original language. The invention offers a more coherent and contextually relevant interaction for users who prefer to communicate in their native language with generative text AI by bridging the gap between translation and text generation.

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

The invention relates to 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 the technical field of smart home, and discloses an equipment control method and device, computer equipment, a storage medium and a program product. The method comprises the following steps: acquiring an original control instruction set; performing multi-language expression conversion on each original control instruction to generate various variant control instructions matched with the original control instructions, and executing the same target operation on the variant control instructions and the original control instructions; for any variant control instruction, role conversion is carried out on the variant control instruction, and a voice control instruction set corresponding to each role is generated; and training the target control model by using the voice control instruction set, so that the target control model responds to the voice control instruction set and controls the target equipment to execute the target operation. By implementing the technical scheme of the invention, the adaptability of the smart home device to different user language habits and role identities is improved, and the naturalness and flexibility of voice interaction are enhanced.

The invention provides a complex scene-oriented end-to-end semantic extraction system, belongs to the technical field of artificial intelligence and natural language processing, and realizes cross-modal information association through a multi-source heterogeneous data fusion module to construct a dynamic semantic network model. A hierarchical attention mechanism is adopted to carry out context-aware coding on unstructured input, and unsupervised pre-training and a weak supervised fine tuning strategy are combined to optimize a feature representation space. And designing an adaptive inference engine, automatically switching semantic analysis paths based on scene complexity, and generating a structured output result. According to the method, the dependency on specific knowledge in the field is reduced, the semantic understanding generalization ability in a complex scene is remarkably improved, high-precision analysis performance can still be kept in a low-resource environment, meanwhile, calculation resource consumption is reduced, and the method is suitable for practical application scenes with multi-language mixing, serious noise interference and high real-time performance requirements.