231 results about "Multiple language" patented technology

The present invention facilitates communication between sign language users and machines by translating sign language and text using AI models, deep learning computer vision, and word embeddings. Users interact via sign language, captured and processed through deep learning and NLP modules. The system converts sign language videos into text, constructs coherent sentences, and generates contextually appropriate responses using a Retrieve and Generate (RAG) model. Responses are translated back into sign language videos, spelling out words not found in the dictionary. If requested, a human agent can respond. Key features include high-accuracy recognition, context-aware response generation, dynamic vocabulary updates, and optional human interaction. The method ensures efficient processing with LLM, embedding techniques, and deep learning, optimizing translation accuracy and user experience. The system adapts to multiple languages and dialects by training on specific sign languages, making it applicable globally.

The invention discloses an uncertainty guided few-sample harmful speech detection method (U-GIFT). According to the method, a pre-training language model is finely adjusted based on a small number of labeled samples, and a semi-supervised self-training and uncertainty guiding strategy is combined. Monte Carlo Dropout is started in the reasoning stage, multiple times of random forward propagation are carried out to obtain sample posterior distribution, prediction entropy and information gain are calculated, pseudo-label samples are sorted and screened, and only high-confidence samples are selected to be added into a training set. And in order to reduce the influence of a pseudo labeling error, designing a stability weighting mechanism, giving a sample weight according to a prediction variance, and constructing a joint loss function, so that the model preferentially learns a stable sample to improve the detection performance. According to the method, the semantic and attention mechanism of the pre-training model is utilized, the detection effect is remarkably improved under the conditions of few samples, imbalance, multiple languages and cross domains, models such as BERT, RoBERTa, XLM-R, LLaMA2 and DeepSeek-R1 are compatible, and the method is suitable for content auditing and risk prevention and control.

The invention relates to a memory retrieval method, a memory generation method and related devices. The method comprises the following steps: acquiring an input search word, and translating the input search word into a search word of a target language; performing memory retrieval by using the input retrieval word and the retrieval word of the target language according to the memory index to obtain a retrieval result; wherein the memory index is established according to at least one of an original and a copy of the memory information; the copy is obtained by translating the original into a target language. The method can match and support multiple languages.

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 present disclosure generally relates to evaluating and enhancing LLM responses. In some implementations, a system includes multiple language models with different specialized roles that work together to improve response reliability and transparency. A responder model can generate initial responses to user queries, providing diverse perspectives on the same input. An evaluator model can assess and combines responses from the responder models into an accurate and reliable output. A reporter model can generate summaries and alerts about response quality and confidence levels, providing transparency to users about the decision-making process. An artificial intelligence (AI) engine can manage the flow of information between the different models, orchestrating their interactions and ensuring proper sequencing of operations. A retrieval system can provide additional context from external knowledge sources, allowing the system to generate accurate and well-informed responses.

A system is provided.SOLUTION: A system comprising: means for a user to upload an article; means for a server to parse the uploaded article; means for the server to automatically translate the parsed article into multiple languages; means for the server to extract and embed SEO keywords for the translated article; means for the server to generate and link relevant images and video to the article; and means for the server to distribute the processed article to platforms in each country.SELECTED DRAWING: Figure 1

To provide a recommendation system or the like for suitably proposing an LLM capable of appropriately answering a user's request.SOLUTION: In a recommendation system, a task execution unit receives a request including text data from a user and causes a first language model, which is one language model designated by the user from a plurality of language models, to generate a first answer to the request. The evaluation information acquisition unit acquires evaluation information on each of the plurality of language models from a predetermined database. The recommendation information generation unit causes a second language model having an execution environment different from that of the first language model to select a recommended language model for generating an answer to the request from the plurality of language models on the basis of the request, the first answer, and the evaluation information. Further, the recommendation information generation unit causes the second language model to generate recommendation information including a message for presenting the recommended language model to the user.SELECTED DRAWING: Figure 2

The invention discloses a knowledge graph query method and device based on multi-language model result fusion. The method comprises the following steps: multi-query result generation: obtaining a query problem; generating query statements under the plurality of model parameters by utilizing the plurality of large language models, and performing query in the knowledge graph by respectively using each query statement; multiple query results are synthesized, wherein reply integration is conducted on the execution conditions of the multiple query statements generated by the same large language model and subjected to parameter adjustment, and model-level query reply is obtained; and for a plurality of model-level query answers, eliminating the model-level query answers with relatively low semantic similarity, and merging the model-level query answers which are not eliminated to obtain a result fusion query answer. By the adoption of the technical scheme, the multiple query statements under the multiple model parameters of the multiple language models are beneficial to comprehensively obtaining information from the knowledge graph, then the query replies are integrated and merged, and noise in the query replies can be effectively reduced and avoided.

The present disclosure provides a multilingual keyboard comprising a first set of keys with Organic Light-Emitting Diode (OLED) displays and matte-finished key caps, produced through a blending process for clear visibility and aesthetic appeal. The multilingual keyboard includes at least two sets of keys: the first set with OLED displays for dynamic character updates based on the selected language, and a second set with fixed functions for a familiar typing experience. The multilingual keyboard incorporates a language switching system that enables seamless transitions between multiple languages with real-time updates on the OLED displays of the first set of keys. Designed to replace multiple keyboards and complex software mappings, the multilingual keyboard offers a versatile typing solution.

The system according to this embodiment aims to understand the context of a conversation and suggest appropriate responses in multiple languages. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a suggestion unit, and a translation unit. The collection unit collects the other party's spoken and nonverbal information. The analysis unit analyzes the information collected by the collection unit and understands the context of the conversation. The suggestion unit suggests an appropriate response based on the context understood by the analysis unit. The translation unit translates the response suggested by the suggestion unit into multiple languages.

This application discloses a training method and related apparatus, equipment, and medium for a speech feature extraction model. The training method includes: acquiring sample speech data; converting the sample recognition text of the first sample speech into a first phonetic symbol sequence based on the pronunciation rules of the language to which the first sample speech belongs, and aligning the first feature sequence of the first sample speech with the first phonetic symbol sequence to determine the first sample phonetic symbol of the first speech frame in the first sample speech; training a phonetic symbol prediction model based on the first sample phonetic symbol of the first speech frame; predicting the second feature sequence of the second sample speech based on the phonetic symbol prediction model to obtain the second phonetic symbol sequence of the second sample speech; and training a speech feature extraction model based on the first speech frame and its first sample phonetic symbol, and the second speech frame and its second sample phonetic symbol. This approach can improve the model's general representation capability for multiple languages ​​while reducing model training costs.

The embodiment of the invention discloses a multi-language entry management method, electronic equipment and a storage medium. The method comprises the steps that a structured form file is constructed to serve as a unified data source of multi-language entries, wherein the structured form file comprises a key column used for storing a unique key name and a plurality of language columns used for storing translation texts of all languages; reading the structured table file, constructing a mapping relationship between a key name and a translated text for each language type, and generating a corresponding language entry file; and reading the plurality of language entry files, extracting and combining mapping relationships between key names and translated texts in the files, and generating the structured form file. By means of the mode, centralized management and bidirectional reversible conversion of the multi-language entries can be achieved, development and maintenance cost is reduced, multi-language consistency and quality are improved, and proofreading and auditing of the entries are facilitated.

The invention provides a multi-format translated file processing method and system, electronic equipment and a storage medium, and the method comprises the steps: carrying out the structural analysis of a translated file when determining that the format of the received translated file meets a format requirement, and obtaining a translation key value; based on the translation key value, processing a data structure and a format of translation content in the translation file to obtain a target translation file; performing multi-language translation on the target translation file, and performing structured storage based on a translation result of each language; and when the intelligent translation function is triggered, performing multi-language translation on the target translation file to obtain a translation result. Parallel translation processing of multiple languages is innovatively realized, so that the translation efficiency and the translation precision are improved. The translation efficiency is improved by adopting a key algorithm of source language intelligent detection and batch translation mapping. According to the technology, the labor cost is remarkably reduced, and the human translation requirement is reduced. In addition, the maintenance cost is reduced through a unified management mechanism.

We provide the system. [Solution] A means of automatically generating entertainment content related to tourist destinations using generative artificial intelligence, A means for delivering relevant augmented reality content to a user's device based on the user's location information, A means of translating the generated content into multiple languages ​​and adapting it to international users, A means for users to virtually experience specific celebrities or historical events through augmented reality experiences at tourist destinations, A system that includes this.

A system is provided.SOLUTION: A guide system for assisting a traveler to acquire spot information, comprising: means for automatically summarizing spot information to be presented to the traveler using a generative model; means for translating the summarized spot information into a local language; means for collecting word-of-mouth information corresponding to a plurality of languages and automatically translating and summarizing the word-of-mouth information; means for displaying specific spot information on a map in response to a user request; and QR code reading means for allowing the user to acquire detailed information of a spot.SELECTED DRAWING: Figure 1

A system and method for an artificially intelligent (AI) platform comprising a Knowledge Net (KN) Platform for automatically creating accessible, transparent knowledge stores which reflect a complete spectrum of semantic relationships between concepts. The system comprises a knowledge discovery engine that creates a machine representation of the semantic knowledge graph of a concept, namely a Concept Semantic Knowledge Graph (CSKG), for explainable, human-analogous understanding of natural language data for the full range of automated natural language understanding tasks—wherein the knowledge discovery engine, in discovering the related concepts, uses a variety of linguistic learning methods.

In one implementation, a device obtains a prompt from a user via a user interface that requests a network troubleshooting agent complete a task with respect to a computer network using one or more language models. The device determines instructions for the network troubleshooting agent based on a user group of which the user is a member. The device provides the prompt and the instructions to the network troubleshooting agent, to produce an answer. The device provides the answer to the user interface for review by the user.

We provide the system. [Solution] A means of accepting voice input, A means for converting the voice input into text data, A means for translating the text data into multiple languages, A means of generating phrases suitable for negotiation, Means for outputting the translated text data and the generated phrase, A system that includes this.

The invention provides a reverse synthesis driven multi-language ancient book high-fidelity label generation method and system, and belongs to the technical field of document image processing, and the method comprises the steps: S1, constructing an OCR corpus covering multiple languages; s2, performing typesetting modeling and visual rendering by using a multilingual structure modeling algorithm based on specific writing rules of all languages; s3, constructing a degradation model for a degradation sample, and realizing accurate adjustment of degradation type, intensity and distribution through multi-parameter mapping and combined control; s4, performing automatic quality evaluation on the degraded sample, and performing dynamic self-correction and closed-loop optimization according to an evaluation result to obtain a final degraded sample; and S5, performing semantic-level labeling on the final degraded sample by using a lightweight target detection and OCR recognition network to generate a final standardized labeling result. The method disclosed by the invention provides a solid technical basis for constructing a high-quality and multi-language historical literature database.

A system is provided.SOLUTION: A system comprising: means for receiving information on a travel destination, a period, an activity, and a meal desired by a user; means for generating an optimal visiting place and schedule based on the received information; means for cooperating with a map information providing service to automatically calculate a moving time; means for collectively reserving accommodation facilities, transportation facilities, and activities; means for acquiring weather information and a situation of a tourist spot in real time and proposing a change plan of a travel schedule; and means for coping with a plurality of languages.SELECTED DRAWING: Figure 1

The application provides a low-resource multilingual large model training method and system for personalized course learning, and belongs to the technical field of large language models, and comprises the following steps: S1: collecting training samples in multiple languages; each sample is subjected to deduplication and noise removal processing, then the data format is unified, and a language attribute is added as a language label; S2: initializing parameters of an adaptive sampling scheduler and a dynamic loss scheduler; S3: using a pre-trained large language model as a base model, and adding the adaptive sampling scheduler and the dynamic loss scheduler in the training process. The method can reduce the dependence on low-resource language labeled data, can adaptively balance the training weights of different language samples, and dynamically matches the difficulty of multilingual tasks and the learning progress of the model.

The system according to the embodiment aims to provide entertainment content in multiple languages ​​to tourists. [Solution] A system according to an embodiment includes a location information acquisition unit, an information display unit, a content generation unit, and a multilingual display unit. The location information acquisition unit acquires location information of tourists. The information display unit displays information about tourist spots based on the location information acquired by the location information acquisition unit. The content generation unit generates entertainment content using a generation AI based on the information displayed by the information display unit. The multilingual display unit displays the entertainment content generated by the content generation unit in multiple languages.

This disclosure describes a URL understanding system that determines the value and characteristics of newly discovered URLs. For example, upon discovering a new URL, the URL understanding system quickly determines whether to add the new URL to a URL index (e.g., a URL search index). In various implementations, the URL understanding system can quickly determine the qualities and characteristics of new URLs using multiple language-based generative AI models. For instance, the URL language model builds a URL language model to learn the syntax and structure of URL strings (e.g., a “URL language”). Then, building upon the URL language, the URL understanding system creates a URL prediction model that determines URL characteristics. Based on one or more characteristics, the URL understanding system can perform various actions, such as quickly adding new URLs to a URL index.

We provide the system. [Solution] Means of collecting consumer-related information, A means for analyzing the aforementioned consumer-related information and generating content based on consumer preferences, A means of translating the generated content into multiple languages, A means for optimizing the delivery route of the content translated into the aforementioned multiple languages, A means of promoting the trading of local specialty products using the generated content and suggesting purchases to consumers, A means of suggesting recipes or uses for local specialty products based on consumers' purchase history, A system that includes this.

The application provides a multi-agent collaborative cross-language system translation method and system based on IoAs, and relates to the technical field of intelligent translation. The method comprises the following steps: obtaining to-be-translated text information and conference theme information, and obtaining first fused semantic information; obtaining first target semantic information through a first translation agent; obtaining second target semantic information through a second translation agent; obtaining second fused semantic information through the first target semantic information and the conference theme information, and determining second target language translation text; and obtaining third fused semantic information through the second target semantic information and the conference theme information, and determining first target language translation text. According to the application, the translation accuracy of key text can be improved by referring to the conference theme information, and the semantic consistency of multi-language translation can be improved by cross-attention mechanism to mutually correct the semantic information of multiple languages, so that the overall translation accuracy is improved and the communication cost is reduced.

The application relates to a log processing method and device for a lua program interface and computer equipment. Resource pre-configuration operation is performed based on a lua program interface to obtain a function call library; a log file to be parsed is received; a log parsing function is selected from the function call library, the log parsing function is called to parse the log file, and a log parsing result is obtained. The log processing method for the lua program interface selects a log parsing function from a function call library of a lua program based on a lua program interface to parse a log file and obtain a parsing result, so that the parsing result obtained based on the lua can be conveniently acquired by an application main program written in multiple languages such as C / C++, and the effect of quickly connecting the log parsing function to an outer application main program is achieved.

A prediction device capable of predicting performance of a language model in a case where the language model is trained using a plurality of languages is implemented. The prediction device includes an acquisition unit for acquiring a model size of the language model for a target language to be trained using the plurality of languages, a training data amount used for learning processing, and a target language ratio indicating a ratio of a data amount of the target language in the training data amount, and a prediction unit for predicting a loss of the language model using a product of a function depending on the model size and the training data amount and a constant power of the target language ratio.

This invention relates to the field of instrument display technology, and in particular to a method and instrument device suitable for multilingual display of instruments with limited resources. The method includes: an external device assigning globally unique macro definition IDs to translation entries and extracting actually used non-repeating characters to generate a trimmed dot matrix font library; constructing a binary resource package with a direct addressing structure, which includes a file header, an index addressing area, and a data entity area; and a microcontroller directly locating and quickly rendering the target entry using the ID as an offset through non-retrieval addressing. This invention provides a method and instrument device suitable for multilingual display of instruments with limited resources, solving the bottleneck of multilingual display in embedded devices with extremely low resources. It significantly reduces storage consumption and CPU load without requiring runtime parsing and string comparison, and enables independent updating and maintenance of language resources.

We provide the system. [Solution] A means to automatically detect the popularity of social networking platforms in each region, A means of translating product information into multiple languages, A means of automatically posting translated product information to detected social networking platforms, A means for automatically detecting product-related social media content and generating responses, A means of measuring the performance of marketing activities and generating reports, A system that includes this.

The invention discloses an emotion analysis method and device, a storage medium and electronic equipment, and relates to the technical field of data processing, and the method comprises the steps: obtaining multi-dimensional text feature information of target financial text data; identifying a data type corresponding to the target financial text data according to the multi-dimensional text feature information; under the condition that the data type is a complex data type, performing emotion analysis on the target financial text data through a plurality of language recognition agents and a plurality of financial information agents; and performing fusion analysis on the emotion information obtained by analysis of the plurality of language recognition agents and the plurality of financial information agents, and generating target emotion information corresponding to the target financial text data. According to the method, the target emotion information corresponding to the target financial text data is generated by performing fusion analysis on the emotion information obtained by analyzing the plurality of language recognition agents and the plurality of financial information agents, so that targeted processing of different types of data can be realized, and the accuracy of emotion analysis is improved.