330 results about "Source text" patented technology

Methods and systems for retrieval-augmented generation are described. Responsive to a user input, an input embedding associated with the user input is obtained. A synthetic question embedding is retrieved from an embeddings database, based on a similarity to the input embedding. The synthetic question embedding is used to obtain a relevant source text based on a stored mapping between the synthetic question embedding and the source text. A prompt is provided to a large language model (LLM) to generate and display a textual response to the user input, based on the user input and the source text. The disclosed methods and systems effectively narrow the pool of source documents based on similarity measures between the user input embedding and the synthetic question embedding, to enable the retrieval of more relevant sources for use in response generation.

Enumerated source text passages may be determined based on one or more source text documents. The enumerated source text passages may include source text passage identifiers uniquely identifying the passages. A novel text passage including novel text portions may be determined based on a query and the enumerated source text passages. One or more of the novel text portions may be verified by a large language model to produce text verification information. A novel text generation message including novel text generated by the large language model may be determined based on the text verification information and sent to a client machine.

A neural text-to-speech system may be configured to emphasize words. Applying emphasis where appropriate enables the TTS system to better reproduce prosodic characteristics of human speech. Emphasis may make the resulting synthesized speech more understandable and engaging than synthesized speech lacking emphasis. Emphasis may be manually annotated to, and / or predicted from, a source text (e.g., a book). In some implementations, the system may use a generative model such as a variational autoencoder to generate word acoustic embeddings indicating how emphasis is to be reflected in the synthesized speech. A phoneme encoder of the TTS system may process phonemes to generate phoneme embeddings. A decoder may process the word acoustic embeddings and the phoneme embeddings to generate spectrogram data representing the synthesized speech.

A computing system for generating verbose tax category descriptions includes a computing device with processing circuitry configured to identify defined tax categories. For each defined tax category, the processing circuitry is configured to extract source text data associated with the defined tax category, generate embeddings representing the source text data, and store the source text embeddings in a vector database. The processing circuitry is further configured to receive an instruction requesting a verbose tax category description of an indicated tax category, generate instruction text embeddings, and query the vector database with the instruction text embeddings to identify a subset of matching source text embeddings. The processing circuitry is further configured to retrieve matching source text data, generate a prompt for a generative language model, input the prompt into the model to generate verbose tax category description text, and output the verbose tax category description text.

The invention relates to the technical field of language translation, in particular to a translation precision optimization method and system based on artificial intelligence, and the method comprises the steps: obtaining a source language text, carrying out the phrasing operation on the source language text to obtain a source language sentence sequence of the source text, carrying out the word segmentation operation on each source language sentence in the source language sentence sequence, and carrying out the word segmentation operation on each source language sentence; obtaining a word sequence of the source language sentence; and performing sentiment classification on each source language sentence in the source language sentence sequence based on a pre-trained first sentiment classification model. The sentiment classification is performed on the source language sentences and the target language sentences on the basis of the first sentiment classification model and the second sentiment classification model, and the similarity between the sentences is calculated, so that the sentences after translation are kept consistent in sentiment, the problem of sentiment deviation generated in a machine translation process is favorably avoided, and the translation efficiency is improved. Especially for some texts with strong emotion colors, it is ensured that translated emotion information can be correctly conveyed.

The invention discloses a multi-source text-based dynamic hotspot clue accurate extraction method, which realizes real-time adaptation and efficient training of a sensitive intelligence recognition model through dynamic label configuration and Prompt design in combination with a lightweight fine tuning technology (RsLoRA), and can accurately recognize in a changeable intelligence scene without re-training. Through human feedback reinforcement learning (PPO) and sorting training, clue texts output by the generative large model are optimized, event subjects and contents are accurately extracted, and a generated result is structured and highly summarized. A semantic vector model and a dynamic multi-layer DBSCAN clustering algorithm are combined, the problem that an existing clustering algorithm is insufficient in adaptability to semantic density difference scenes is solved, and high-precision clue aggregation and popularity statistics are achieved. The overall scheme reduces resource consumption and training time through the RsLoRA technology, comprehensively improves intelligence processing efficiency and analysis ability, and has significant technical advantages and wide application prospects in the fields of intelligent public security, government management and the like.

A system and method for transforming text within documents using, such as by using large language models (LLMs). Users can select source text from a source document, in response to which a painting configuration is identified or generated based on the source text, such as by providing the source text and a source prompt to a large language model to produce source output, and selecting or generating the painting configuration based on the source output. The user can select destination text, in response to which the painting configuration is applied to the destination text, such as by selecting or generating a destination action definition based on the painting configuration and the destination text, and providing the destination action definition to a large language model to produce destination output. The destination text may be replaced with the destination output, or output derived therefrom. In this way, the system can extract a variety of sophisticated properties, such as style or tone, from user-selected text source text, and apply those properties to user-selected destination text, with minimal user input.

The invention provides an archive knowledge editing and research method, system and device and a storage medium, and the method comprises the steps: obtaining editing and research demand information and an archive knowledge graph, and rewriting the editing and research demand information through employing a prompt engineering technology, and obtaining an editing and research description; in the archive knowledge graph, determining and recalling a target tetrad matched with the editing and research description; determining an additional feature according to a demand type associated with the editing and research description, and associating the additional feature with the target tetrad; and taking the target tetrad, the source text associated with the target tetrad, the additional features associated with the target tetrad and the editing and research description as input information of a large language model, and outputting an archive knowledge editing and research result through the large language model. According to the technical scheme, the accuracy level of the input instruction of the large language model is improved, the illusion of the large language model can be overcome, and the credibility and the text quality of the target editing and research content output by the large language model are improved.

The invention discloses a method and system for generating an EBT scene of a pilot based on a text and flight data, and the method comprises the steps: extracting threat error items in the operation of the pilot from a multi-source text through employing a scene perception word frequency-inverse document frequency method, and generating text analysis; a method of combining time feature attention, convolutional self-encoding and a long short-term memory network is utilized to comprehensively analyze flight data of daily routes and simulator training, dynamic features and potential risk factors in pilot operation are extracted, and flight data analysis is generated; in combination with text data analysis, flight data analysis and a scene element library, training scene elements are generated by adopting a hierarchical rule structure condition generative adversarial network method, and a teacher performs screening and combination to generate a personalized training scene. Through multi-source data fusion and data-driven analysis, a pilot personalized training scene is generated, the pertinence and effectiveness of training are improved, the use of training resources is optimized, and the overall flight safety and training quality are improved.

A computer-implemented process is programmed to programmatically receive at a first computer a digital electronic object comprising a source text having been composed at a second computer, send instructions to the second computer for presenting filters via a user interface, which are programmed to adjust the source text when they are selected and executed, receive a selection of a first filter, generate an output set of suggestions based on executing the first filter over the source text, transmit the output set of suggestions to the second computer, receive a specification to apply the suggestions, and in response, automatically apply all the suggestions to the source text and transmit updated presentation instructions to the second computer which when rendered using the second computer cause displaying an updated text with all the suggestions having been applied to the source text.

The invention discloses a railway engineering unfavorable geology knowledge base construction method and system, and the method comprises the steps: collecting and preprocessing multi-source railway engineering text data, and obtaining a multi-source text data set; performing knowledge extraction, knowledge fusion and knowledge processing based on the multi-source file data set; constructing a railway engineering unfavorable geology knowledge base; and carrying out user interaction design based on a railway unfavorable geology knowledge base. According to the method, unfavorable geological knowledge of railway engineering can be automatically extracted from a large amount of text data, a structured knowledge base is constructed, the knowledge base not only improves the knowledge extraction efficiency and accuracy, but also provides scientific and accurate information support for safety management and decision-making of railway engineering in the form of the knowledge graph, and the method is suitable for popularization and application. Therefore, key fault information can be better mastered for railway operation enterprises, and accurate and effective information data and technical support are provided for decision making.

The invention relates to the technical field of intelligent retrieval of papers, and discloses a paper review expert intelligent recommendation method and system.According to the method, word paraphrasing is carried out on review expert text information and to-be-reviewed paper text information, semantic connotation supplementation and extension can be carried out on text information with limited information amount, and therefore the content of paper review experts is improved. Richer and more useful information is provided; multi-source information fusion is carried out on the expanded text information, the expanded rich multi-source text information can be summarized, extracted and summarized, and comprehensive text information with sufficient information content and high distinction degree is provided; and performing overall vectorization on the comprehensive text information, performing similarity calculation and sorting on the review expert text vector and the to-be-reviewed paper text vector, and screening out review expert information with relatively high similarity as output. The method can effectively improve the matching precision of the paper'small peer 'review experts, reduces the rejection rate caused by inconsistent research directions, and provides technical support for improving the review quality and shortening the review period.

The invention relates to the technical field of equipment maintenance and overhaul decision, and discloses a knowledge graph driven two-stage classification equipment condition-based overhaul decision method, which comprises the following steps: acquiring multi-source text data; performing first-stage classification on the equipment based on the equipment importance evaluation model, and performing second-stage classification on the parts based on the maintenance strategy; a device entity, a fault mode entity and a maintenance measure entity are taken as knowledge ontologies, state variable nodes are embedded, and a knowledge graph fusing state variables is constructed by using a long-short-term memory network; in combination with a semantic context sensing mechanism and a graph structure stability constraint mechanism, outputting candidate fault nodes; candidate maintenance measures corresponding to the candidate fault nodes are retrieved in the knowledge graph, candidate maintenance measure verification is carried out in combination with soft constraints and hard constraints, and a maintenance measure list is converted into an equipment maintenance decision scheme by utilizing an execution arrangement generator, so that intelligence of the maintenance decision scheme is realized in combination with the knowledge graph; and decision support is provided for maintenance personnel.

The invention discloses a text generation method and device, equipment and a storage medium, and the method comprises the steps: obtaining a source text, and carrying out word segmentation sorting to obtain a text sequence; converting the text sequence into word embedding representation; performing semantic feature extraction based on a global encoder, and fusing output vectors of the last plurality of encoding layers based on an attention mechanism to obtain first semantic encoding information; performing semantic feature extraction based on a local encoder to obtain second semantic encoding information; performing feature fusion and filtering based on a global gating unit to obtain a context semantic vector; and decoding the context semantic vector based on a decoder to generate a target text. The context semantic vector is obtained through semantic feature fusion and filtering, redundant features are removed, and post-processing is not needed; the global encoder carries out multi-coding-layer output vector fusion based on an attention mechanism, and the local encoder fuses features through a gating unit, so that richer key information features can be obtained.

Digital video editing techniques are described that are based on a target digital image. In one or more implementations, inputs are received. The inputs include a target text prompt, a target digital image depicting a target object, and a source digital video having a plurality of frames depicting a source object. Regions-of-interest are identified in the plurality of frames of the source digital video, respectively, based on the target text prompt and the target digital image using a machine-learning model, e.g., a diffusion model. A plurality of frames of a target digital video are generated as having the target object using a generative machine-learning model. The generating is based on the regions-of-interest, the target digital image, the source digital video, and a source text prompt describing the source digital video.

The invention relates to the technical field of building information, and provides a knowledge base construction and retrieval method and system based on a multi-source text in the building field, and the method comprises the following steps: a knowledge base construction stage: constructing a multi-dimensional metadata feature vector for a multivariate text based on a standard classification index table; the method comprises the following steps of: converting and segmenting a document, splicing an end clause with all superior title texts by utilizing a context inheritance algorithm to form a text unit with complete semantics, and performing dynamic filtering based on an analyzed query intention and a metadata vector at a user retrieval stage; then, in the screening set, performing fusion calculation on semantic vector similarity, keyword matching degree and authority offset weight based on effectiveness attribute and implementation time, and performing mixed retrieval and reordering on the text units; and finally selecting a text unit according to a sorting result and inputting the text unit into the large language model to generate answers. According to the method, high-precision and high-compliance intelligent retrieval and question answering of building domain knowledge are realized.

A text processing method, which is executed by means of a computer device. The method comprises: acquiring source text to be processed, wherein the source text comprises a plurality of tokens (S501); on the basis of a relative distance between paired tokens in the source text, determining a relative position code corresponding to the relative distance between the paired tokens, and obtaining position code information comprising the relative position code (S502); acquiring a distance threshold value, determining from the position code information a first relative position code that corresponds to a relative distance exceeding the distance threshold value, and calling a text processing model to map the first relative position code in the position code information to a position code range of the text processing model, so as to obtain mapped position code information (S503); and calling the text processing model to perform semantic understanding on the source text on the basis of the mapped position code information, so as to generate semantically associated text for the source text (S504).

The invention relates to the technical field of prompt optimization engineering, in particular to an embedded clustering multi-path recall large model question and answer method, system and device and a medium, and the method comprises the following steps: preprocessing a multi-source text to generate an associated paragraph, and converting the associated paragraph into a semantic vector; executing clustering and adjusting a clustering center based on a matching strategy to form a vector library; receiving queries, converting the queries into semantic vectors and retrieving related units in parallel; the recall result is comprehensively evaluated on the basis of a credibility perception attention mechanism in combination with semantic matching and timeliness score, the semantic matching score is calculated by a local bge-ryanker-v2-m3 model, the timeliness score is quantized through a date difference attenuation function, and finally high-quality content is weighted and screened to be input into a large language model to generate question and answer output. And the result accuracy, timeliness and service adaptability are improved.

Systems and techniques for linguistic learning using automatically cascaded text are described herein. A data model is generated to identify linguistic relationships among respective words and word groups in a source text. The data model is augmented with linguistic properties associated with individual words in the source text. An arrangement of cascaded text is determined based on the linguistic relationships identified in the data model. The arrangement of cascaded text includes horizontal displacement and vertical displacement for the respective words and word groups. Display enhancements to the arrangement of cascaded text are determined wherein the display enhancements are based on user-selected options to show visual aids that identify the linguistic relationships among the respective words and word groups or linguistic properties associated with individual words. The arrangement of cascaded text and the display enhancements are output in a user interface.

The invention discloses a multi-language text self-adaptive configuration method and electronic equipment, and relates to the technical field of computers, and the method comprises the following steps: obtaining a source text set in response to a translation instruction received when a page runs, and translating the source text set according to a target language identifier and a constraint strategy to obtain a translated text set; according to a constraint strategy, carrying out adaptability detection on each translation in the translation set to obtain an adaptive set and a non-adaptive set; performing semantic rewriting on each non-adaptive translation in the non-adaptive set to obtain a target candidate set; and aggregating the adaptation set and the target candidate set in the same rendering frame, and rendering and displaying the adaptation set and the target candidate set in batches, so that the problems of lack of multi-language dynamic adaptation capability and insufficient semantic equivalent compression are solved, the accumulated layout offset is remarkably reduced on the premise of ensuring semantic integrity and readability, and the layout efficiency is improved. And the page stability and the user experience are improved.

The invention discloses a structured data storage method based on natural language transformation, which comprises the following steps of: a system initialization configuration stage: deploying a protocol adapter in a local memory of a PC (Personal Computer) client, and loading natural language processing pipeline configuration parameters; a heterogeneous data acquisition stage: capturing a multi-source text data stream through the protocol adapter, uniformly converting the multi-source text data stream into a standardized data packet, and sending the standardized data packet to a message queue theme; a text cleaning stage: a named entity recognition stage: inputting the pure text data into an NER module deployed with a language model loader; in the conditional feature extraction stage, feature vectors are generated for texts meeting preset conditions on the basis of entity type tags in the entity recognition result; and a consistent storage stage: inserting the entity identification results into a relational database in batches, and updating the entity mapping relationship in the cache. According to the method, the intelligent level of cache management is remarkably improved, and the access fluency of the key data of the user is guaranteed.

Methods, systems, and computer programs are presented for abstractive summarization of text by viewing sequence transduction as a language modeling problem. One method comprises an operation for training a machine-learning program to create a machine-learning model that estimates a word to be added to a running summary for the text being summarized. The method further comprises operations for detecting the text to be summarized, initializing the running summary, and performing a plurality of iterations. Each iteration comprises providing, to the machine-learning model, the source text and the running summary, and adding, using the machine-learning model, a new word to the running summary. Further, the method comprises an operation for storing, on a memory, the running summary as the summary of the text.

The invention provides a video machine translation method and device fusing multi-modal fine-grained information. The multi-modal fine-grained information fused video machine translation method comprises the following steps: performing information extraction on a picture in a video to obtain fine-grained visual information in the picture, and performing information extraction on an audio in the video to obtain fine-grained audio information in the audio; fusing the fine-grained visual information and the fine-grained audio information into a source text to obtain a fused text; the source text is subtitles to be translated in the video; and inputting the fused text into a machine translation model to obtain a target translation text. According to the video machine translation method and device fusing the multi-modal fine-grained information, the fine-grained visual information and the fine-grained audio information of the video are fused into the source text, machine translation is performed based on the fused text, and the translation accuracy is improved.

A computer-implemented process is programmed to programmatically receive at a first computer a digital electronic object comprising a source text having been composed at a second computer, send instructions to the second computer for presenting filters via a user interface, which are programmed to adjust the source text when they are selected and executed, receive a selection of a first filter, generate an output set of suggestions based on executing the first filter over the source text, transmit the output set of suggestions to the second computer, receive a specification to apply the suggestions, and in response, automatically apply all the suggestions to the source text and transmit updated presentation instructions to the second computer which when rendered using the second computer cause displaying an updated text with all the suggestions having been applied to the source text.

A method implements pre-trained large language model driven bug localization. The method includes receiving a report and applying a fine-tuned language model to report text from the report, to source text from a source file of a set of source files, and to commit text from a commit of a set of commits to respectively generate a report vector, a source vector, and a commit vector from the fine-tuned language model. The method further includes applying a similarity model to the report vector and the source vector to generate a report source score and includes applying the similarity model to the report vector and the commit vector to generate a report commit score. The method further includes applying a ranking model to the report source score and the report commit score to identify the source file corresponding to the report and includes presenting the source file responsive to the report.

In accordance with the described techniques, a system receives a plurality of facets describing language-agnostic aspects of language translation, a translation document describing language-specific rules for translating from a source language to a target language, and a source text in the source language. Using one or more machine learning models, a plurality of guidelines are extracted from the translation document and assigned to respective facets of the plurality of facets. The system translates the source text to a translated text in the target language using one or more machine learning models conditioned on the plurality of guidelines assigned to the respective facets.

The invention discloses a data element retrieval and archiving system and method for text natural language understanding, and relates to the technical field of data element retrieval and archiving. A multi-source text is obtained, the multi-source text is preprocessed, and an initial text library is established; the complexity of the text is analyzed based on the text data element information and the text structure information, the complexity level of the text is determined, and then the texts with different complexity levels are archived; receiving a keyword input by a user, performing text retrieval according to a keyword expansion strategy and data element tracking, and further generating a text recommendation folder; and analyzing the user access data of each text in the text recommendation folder, and performing text screening according to the texts concerned by the user to generate a secondary text recommendation folder. Information is efficiently extracted from multi-source text data, and accurate and valuable text content is provided for users through intelligent retrieval and personalized recommendation.

The invention discloses a 7 * 24-hour emergency response intelligent advertisement automatic adjustment system, which intelligently judges response rhythm and strategy strength by monitoring multi-source text data, identifying emergencies and influence degrees thereof in real time and combining a dynamic adjustable trigger threshold mechanism and event popularity prediction based on a time sequence model. For similar historical events, the system supports a rapid migration response strategy, and the decision-making efficiency is remarkably improved. And the strategy reasoning module fuses the rule and the machine learning model to generate an optimal advertisement putting scheme with multi-dimensional scoring, and the advertisement scheduling module automatically executes strategy adjustment. And the feedback learning module performs iterative updating on the strategy model by utilizing advertisement effect real-time data based on a reinforcement learning algorithm, and realizes closed-loop self-learning of'prediction-execution-evaluation-re-optimization '.

A system for intelligent editing of legal documents. The system includes a computing device. The computing device is configured to access a plurality of legal source texts from a plurality of legal sources, generate a score for each of the plurality of legal source texts, train a natural language processing model as a function of the scored legal source texts and a first machine-learning process, receive user-input legal text from a user device being operated by a human user to create a user legal document, analyze the user-input legal text using the natural language processing model, suggest, as a function of the analyzing, a modification to a target text of the user-input legal text, and generate a score for a modified user legal document. A method for intelligent editing of legal documents is also provided.