36 results about "Text string" patented technology

This invention provides a drawing processing method and system based on scene text recognition. It identifies all graphic and non-graphic elements within the global scope of a drawing. Based on the shape features of the graphic elements, it divides the drawing into several sets of non-graphic elements. Based on the connected components of all non-graphic elements within each set, it generates several text strings corresponding to those sets and performs fuzzy classification to identify the text results of the non-graphic element sets. Based on the spatial distribution information of the graphic and non-graphic elements on the drawing, it preprocesses the text results and overlays them onto the corresponding areas of the drawing, distinguishing between non-graphic and graphic elements. It also performs connectivity recognition on the non-graphic elements, initially labeling the text strings within them to obtain their corresponding text results. This achieves synchronous association recognition of graphics and text within the drawing, improving the efficiency and accuracy of drawing editing.

An information handling system may include a memory and a processor communicatively coupled to the memory and configured to convert a string of text into a text-based scannable code comprising a string of characters including space characters, special characters, and linefeed characters, such that when the string of characters is displayed to a display device, the string of characters resembles an image-based scannable code.

This invention discloses a method for handling rail transit anomalies and training a rail transit anomaly handling model. The method includes: acquiring a knowledge base of current train anomalies and train schedule adjustments; determining an anomaly text string based on the current train anomaly; performing vector transformation on each phrase in the anomaly text string to obtain at least one first phrase vector; performing vector transformation on each phrase of each entry in the train schedule adjustment knowledge base to obtain at least one second phrase vector; calculating the similarity between each first phrase vector and each second phrase vector; filtering entries in the train schedule adjustment knowledge base based on the similarity between each first phrase vector and each second phrase vector to obtain the optimal schedule adjustment entry; and processing the current train anomaly based on the optimal schedule adjustment entry. This invention can improve the efficiency of rail transit train operation schedule adjustments.

Systems and methods to facilitate determining camera motion for a video segment(s) are provided. The system may receive training data including a first plurality of video segments and a first plurality of classifications characterizing camera motion for a video segment of the first plurality of video segments. The system may receive a text string. The system may determine, from the text string, a first prompt associated with generating a video, based on the training data. The system may determine, from the text string, a second prompt associated with the camera motion for the video, based on the training data.

The application relates to the technical field of natural language processing and information extraction, and discloses a table information extraction method and system for an object attribute detail table and a medium. The method comprises the following steps: obtaining an HTML document of a target table, and preprocessing the HTML document to obtain a text string of the target table; extracting a plurality of features in the text string to construct a feature matrix; the plurality of features comprise text features, position features and label features; inputting the feature matrix into a trained cell classification model to output all cell category discrimination results of the target table; and performing path query in all cells of the target table based on the cell category discrimination results, so that all data information capable of forming groups in the target table is obtained. The application improves the accuracy and universality of table information extraction.

This invention relates to the fields of computer vision, text processing, font generation, and adaptive learning, and specifically to an adaptive text display method and system for assisting memory. The method involves inputting text content to be memorized, which can be a text string and its corresponding vector font file, or a rasterized image containing the text content. Based on the input type, auxiliary display elements are generated or acquired to partially replace or cover the original text's visual form. Based on the user's memory proficiency index and / or the semantic features of the text content, several target layout rules are selected from a predefined layout rule library. According to the target layout rules, the original text data and the auxiliary display elements are logically fused to output the desired adaptive memory-assisting display interface. This invention elevates memory-assisting technology from a simple font transformation to a context-aware intelligent interactive interface, breaking the limitations of traditional font technology application scenarios.

The present invention concerns a method for detecting faults in mechanical components by classifying text strings describing issues with said mechanical components by combining deterministic, rule-based keyword extraction algorithm with deep learning models. It uses a Generative AI model to generate synthetic data, especially for underrepresented classes. The system consists of two main components: a probability map that implements a deterministic, rule-based keyword extraction algorithm by focusing on negations and relevant keywords, and a Transformer-based model that handles long-range dependencies in sequential data. The outputs from both models are combined using score-based aggregation, and an ensemble classifier is trained to integrate these outputs, leading to improved accuracy in handling diverse data. The invention also includes a system with modules for data collection, preprocessing, augmentation, training, and evaluation to ensure optimal classification performance.

A method for fact retrieval includes receiving an input from a user, said input including a string of text that represents a user intent. The method includes performing natural language processing on the input to generate an embedding that corresponds to a semantic representation of the string of text, and based on the generated embedding, identifying an action that is associated with the user intent. The method includes executing the identified action, such that the executed action returns a result associated with the user intent, and providing the result to the user.

Certain aspects of the disclosure provide a method performing entity recognition to classify user inputs for resolving user intent. In aspects, the method includes receiving user input comprising a text string associated, the user input associated with a web-based application; generating a transformed text string by applying a set of rule-based alterations to the user input; parsing the transformed text string to identify a set of tokens; identifying one or more prioritized tokens from the set of tokens; sequentially executing a set of ordered binary classification tests for each of the one or more prioritized tokens until a true indication associated with a sequential binary classification test of the set of ordered binary classification tests is received; and sending a classification for the user input to a domain service associated with a content service of the web-based application.

Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: performing natural language processing to process a text string of a user, wherein the text string specifies characteristics of a container image to be built; processing, with use of natural language processing, instances of text-based data that describe respective ones of a plurality of container images stored within a container image repository; selecting, in dependence on a result of the performing natural language processing, and the processing, a base image from the plurality of container images; and presenting prompting data to the user that prompts building of a new container image, wherein the prompting data references the base image.

Implementations leverage AI-driven whiteboards to enhance communication and collaboration. A user can provide handwritten input via a whiteboard user interface, and one or more machine learning models can be utilized to recognize and interpret the handwritten input to generate whiteboard content that is responsive to the handwritten input and to be rendered within the whiteboard user interface relative to the handwritten input. The handwritten input can include a handwritten text string and / or a hand-drawn sketch. The whiteboard content can be customized based on a user profile, audible input, and / or control input.

This disclosure provides a document display method, apparatus, device, and program product. It identifies target text in a target document that matches playback time information. The document content of the target document has a consistent association with the corresponding audio / video content, and the target text of the target document is the text displayed on the screen. Based on the global text string corresponding to the target document, it obtains the text index information corresponding to the target text. Based on the text index information, it determines the target area coordinates corresponding to the target text. Based on the target area coordinates, it highlights the target text in the target document. Thus, it can automatically highlight the matching text in the target document based on the playback time information of the audio / video, achieving real-time linkage between the playback progress of the audio / video and the highlighted area of ​​the document content.

Disclosed herein are system, method, apparatus, and computer-readable medium embodiments for a multi-tiered hierarchical language model judging system for efficient and accurate model evaluation. A system receives a first text string specifying a question from a first user interface and a second text string specifying an answer generated by a language model. The system receives, from a first model, a first token probability for the second set of one or more tokens and generates a first confidence score. Based on the first confidence score satisfying a threshold, the system outputs the second text string and the first confidence score to the user interface. If the first confidence score fails to satisfy the threshold, the system outputs the second text string and one of a second confidence score generated based on a second token probability from a second model or a third confidence score generated by a reasoning model.

A computer-implemented method including identifying a plurality of messages for a customer, extracting from messages of the plurality of messages, shipping information for at least one shipment, the extracting including solely obtaining a uniform resource locator, URL, for a web resource from digital content corresponding to a given message of the plurality of messages, determining, based on the URL and on the web resource, shipping information for a particular shipment by inputting the URL into one or more machine learning (ML) models and obtaining, based on an output of the one or more ML models, a text string corresponding to the tracking number from the URL, the shipping information including at least one of an indication that the web resource is for tracking the particular shipment, a tracking number for the particular shipment, and a shipping provider for the particular shipment, and storing, in memory, the shipping information for obtaining tracking updates for the particular shipment. 20 26 20 50 06 26 J un 2 02 6 2 0 2 6 2 0 5 0 0 6 2 6 J u n 2 0 2 6

This application discloses an intelligent voice dialogue method and system based on a large language model, belonging to the field of speech processing technology. The method includes: acquiring an audio stream of the user's surrounding environment; processing the audio stream by frame and determining whether it contains speech to obtain a valid audio stream; converting the valid audio stream into a text string using a deep learning model; performing deep analysis using a large language model to dynamically parse the user's immediate state, potential needs, and emotional inclinations, generating natural language response text, and converting it into an audio stream for playback using speech synthesis technology. This method leverages the powerful natural language understanding capabilities of the large language model to dynamically and deeply understand the user's immediate state, potential needs, and emotional tone, forming a richer, more vivid, and context-dependent user understanding. This results in a more natural, considerate, and accurate response generation and service provision, achieving a more human-centered human-computer voice interaction experience.

A method and a system for classifying one or more hyperlinks in a document are provided. The method includes identifying the one or more hyperlinks in the document based on an analysis of text strings of the document. The method further includes analyzing surrounding text strings around each of the one or more hyperlinks and classifying, based on the analysis of the surrounding text strings around each of the one or more hyperlinks, the one or more hyperlinks into at least one category among a plurality of predetermined categories.

The application relates to the technical field of semantic analysis, in particular to a bid evaluation clause extraction system based on semantic analysis, which comprises a bid text analysis module, wherein according to a bid text segment in an extracted bid, concept node information entropy weight is generated, the concept node information entropy weight is calculated with an extracted node associated semantic vector, and a binary semantic feature fingerprint is generated. In the application, the maximum weight matching node set is subjected to position alignment splicing, numerical parameter and text string reconstruction, and an index label is established in combination with entity name content and time node value, finally forming a bid evaluation rule extraction dictionary, so that the output result is changed from pure semantic interpretation into a structured rule unit which is searchable, archivable, callable and reviewable, and the bid evaluation rule extraction scene presents stronger clause restoration capability, rule aggregation capability, heterogeneous expression compatibility and subsequent reuse capability.

In non-limiting examples of the present disclosure, systems, methods and devices for classifying text strings, augmenting text strings, and identifying classified text strings for intelligent autofill are provided. A fact store may be populated with facts from a plurality of data sources associated with a user account. The fact store may comprise unstructured data, semi-structured data, and structured data. An intent type associated with a text string displayed by a local computing device may be determined. The text string may comprise form data or freeform data. A context associated with the local computing device may also be determined. Based on the intent type and the context, a text string corresponding to a fact in the fact store may be identified for surfacing on the local computing device.

This disclosure provides a mechanism for the enrichment of sparse datasets using language models. By training language models on the specific distribution of known values in a dataset, missing values can be predicted, and the predicted values added, thereby resulting in a more complete dataset. This method also facilitates the enhancement and augmentation of datasets by predicting values for new properties that were not previously available. The approach proves particularly effective at scale, transforming large sparse datasets into more complete and enhanced datasets. Masking language modeling may be employed to train language models capable of generating representations of technical data. Training data includes corpuses of technical data that may be represented as text strings. These pretrained models are fine-tuned to predict various properties. The resulting models can predict missing values in large technical datasets, providing valuable data for guiding scientific research.

This application relates to a text processing method, apparatus, computer device, and storage medium. The method includes: acquiring text to be parsed; converting the text to be parsed into a text string; the text string including prompt information and answer information from the text to be parsed; filling the prompt information and answer information from the text string into a prompt template according to a pre-determined prompt template; inputting the filled prompt template into a pre-trained reinforcement learning agent; outputting the answer information from the prompt template; and converting the answer information into a prediction result of the reinforcement learning agent. This method can process the text to be parsed into a standardized format using prompt templates, ensuring that the reinforcement learning agent can handle new scenarios with unlabeled or poorly labeled text, allowing the reinforcement learning agent to adapt to new text processing scenarios and guaranteeing the recognition accuracy of new texts to be parsed.

This application provides a deep learning-based regular expression matching method, apparatus, electronic device, and storage medium. The method includes acquiring a text string to be processed and segmenting it into multiple text substrings; sequentially inputting the multiple text substrings into a pre-trained prediction model to obtain the initial state prediction results output by the prediction model, the initial state prediction results including the predicted initial DFA state value of each text substring; for each text substring, performing string scanning based on the predicted initial DFA state value of the text substring to obtain the corresponding regular expression scanning result; and determining whether the concatenation condition is satisfied based on the connection relationship between the scanning results corresponding to all text substrings to obtain the regular expression scanning result of the text string to be processed.

The subject matter described herein includes methods, systems, and computer program products for AI tagging of airline fault codes. According to one method, a transformer-based natural language processing (NLP) artificial intelligence (AI) model trained on a dataset is provided. The training dataset includes a plurality of text strings tagged with at least one associated air transport association (ATA) code. The trained AI model then receives an untagged text string as input and automatically tags the text string with an ATA code.

A method includes receiving input dialog including a text string corresponding to at least one question and extracting at least one keyword from the text string. The method also includes generating at least one action prediction and providing one or more sub-questions associated with the at least one question. The method also includes receiving one or more answers to the one or more sub-questions, generating at least one sub-goal based on the one or more answers, and traversing an environment based on the at least one sub-goal. The method also includes receiving one or more images associated with the environment, predicting, using the one or more images, an answer to the at least one question, and providing, at an output mechanism, the answer to the at least one question.

A system for processing employment documents includes one or more processors, coupled with memory. The one or more processors are configured to receive an input document, determine that the input document is associated with a first field and a second field, extract a first extracted text string corresponding to the first field and a second extracted text string corresponding to the second field, generate a first generated text string associated with the first field based on the first extracted text string, and generate a second generated text string associated with the second field based on the second extracted text string.

In the disclosed systems and methods for categorizing medical data, a computer system obtains, in electronic form, a plurality of medical records. Each medical record includes corresponding medical data from a respective medical evaluation and corresponding metadata comprising a plurality of attributes about the respective medical evaluation. Each respective attribute comprises a corresponding string of text. The computer system determines, for each respective pair of medical records consisting of a first medical record and a second medical record, a corresponding pairwise similarity between, for each respective attribute in a set of attributes, the corresponding string of text for the first medical record and the corresponding string of text for the second medical record. The computer system identifies a first subset of the plurality of medical records. Each respective medical record in the first subset is connected to each other through pairwise similarities that each satisfies a similarity threshold.

Methods, apparatuses, and computer program products are described for aggregating user sessions for conversational exchanges using a virtual assistant. A user device can receive conversational inputs, convert the conversational inputs into textual strings, associate, based upon semantic analysis of different portions of the textual strings, a first network and a second network, and initiate, respectively, a first and second user session with a first response module of the first network and a second response module of the second network. The portions of textual strings can be transmitted to the first and second response modules via, respectively, the first and second user sessions. Once response fragments are received from the first and second response modules, the response fragments can be combined in a semantically suitable order to form a generated response.

Apparatuses, systems, and techniques to summarize a plurality of text strings. In at least one embodiment, one or more machine learning structures are used to generate a summary of a plurality of text strings based, at least in part, on an association between one or more words in a text string and one or more words with similar meaning.

One implementation utilizes a smaller LLM to generate content responsive to a user query, causing a portion of the generated content to be rendered as an immediate response to the user query. Another implementation utilizes a larger LLM to generate a refined portion of the content that begins with and includes the portion following that portion of the generated content. This refined portion can then be rendered after the portion of the generated content. In some implementations, instead of using a smaller LLM, the portion of the generated content rendered as an immediate response can be generated based on a default text string or template, where a template can be determined / selected from multiple predefined templates based on natural language understanding of the user query.

This invention discloses a method for recognizing text on medicine bottle labels and extracting drug names with semantic error correction capabilities. The method includes: acquiring and preprocessing medicine bottle images to locate the label area; obtaining the original text sequence through optical character recognition (OCR); inputting the complete text string, retaining all information and without filtering, into a trained large language model; the large language model, based on its internally pre-trained pharmaceutical knowledge graph, simultaneously performing semantic error correction and extracting core drug information during the same reasoning process, correcting character-level errors generated by OCR and outputting key information such as generic names and specifications; and finally verifying the output results through a standard library. This invention embeds the pharmaceutical knowledge semantic parsing capability of the large language model into the post-processing stage of OCR, achieving end-to-end processing from recognition to error correction to extraction, significantly improving the recognition accuracy and error tolerance of pharmaceutical terminology in drug verification scenarios.

In some implementations, the techniques described herein relate to a method including: (i) identifying, by a processor, a generative machine learning model trained on image data, (ii) generating, by the generative machine learning model executed by the processor, an image based on at least one parameter, (iii) editing, by an image-editing algorithm executed by the processor, the image to comprise a specified string of text in a selected area of the image, and (iv) causing display, by the processor, of the edited image.