1688results about "Character recognition" patented technology

Systems and methods for reducing the search space by processing media content to refine search parameters. A computing device may obtain the media content in response to receiving a request for inclusion of the media content in a media content knowledge repository, extract an audio component, a video component, and a text component of the media content, and determine attributes within the extracted components. The computing device may determine segment attributes based on a result of correlating the determined audio, video, and text attributes, integrate the segment attributes into the media content knowledge repository, and / or perform any of a variety of responsive actions.

Various embodiments include methods for generating image datasets for training an artificial intelligence machine learning (AI / ML) optical character recognition (OCR) model. Image processing may be performed on a plurality of roadway images to identify street signs within the images and generate a dataset of sign images categorized into sign variants of the same shape, color, pictogram, and characters. An OCR model may process sign images to obtain OCR results for images of each sign variant. An aggregation process may be performed on the OCR results for all sign images within each sign variant to identify a ground truth OCR result for each sign variant. The ground truth OCR result may be used to automatically label all sign images of each sign variant to produce an OCR model training dataset. The produced training dataset may then be used to retrain the initial AI / ML OCR model and / or train other AI / ML OCR models.

The invention provides a power grid wiring diagram automatic analysis system and method based on deep learning. The method comprises the steps of S1, data preprocessing and model training; s2, carrying out equipment identification and association; step S3, topology reasoning and verification are carried out; s4, standardized output: converting the verified power grid network model into a regulation and control cloud platform standard graphic file, and optimizing graphic arrangement through an adaptive layout algorithm; step S5, performing closed-loop optimization; and S6, performing manual intervention and iteration. According to the method, the wiring diagram analysis efficiency and accuracy can be remarkably improved, manual intervention is reduced, standardized graph generation of a power grid regulation and control cloud platform is supported, and a reliable data basis is provided for power system analysis and decision making.

A computer implemented method, system and non-transitory computer-readable device for a remote deposit environment activating, on a client device, a financial application, wherein the financial application is configured to instantiate a customer interface (UI) on the client device. Upon receiving a customer request, based on interactions with the UI, the method implements an electronic deposit of a financial instrument by activating a camera on the client device to generate a live stream of image data of a field of view of at least one camera, wherein the live stream includes imagery of at least a portion of the financial instrument. The method continues by blending common pixels from the imagery to form a blended image, and extracting by an optical character recognition program one or more data fields from the blended image of the financial instrument.

Disclosed is a new document processing solution that combines the powers of machine learning and deep learning and leverages the knowledge of a knowledge base. Textual information in an input image of a document can be converted to semantic information utilizing the knowledge base. A semantic image can then be generated utilizing the semantic information and geometries of the textual information. The semantic information can be coded by semantic type determined utilizing the knowledge base and positioned in the semantic image utilizing the geometries of the textual information. A region-based convolutional neural network (R-CNN) can be trained to extract regions from the semantic image utilizing the coded semantic information and the geometries. The regions can be mapped to the textual information for classification / data extraction. With semantic images, the number of samples and time needed to train the R-CNN for document processing can be significantly reduced.

Systems and methods for reducing the search space by processing media content to refine search parameters. A computing device may obtain the media content in response to receiving a request for inclusion of the media content in a media content knowledge repository, extract an audio component, a video component, and a text component of the media content, and determine attributes within the extracted components. The computing device may determine segment attributes based on a result of correlating the determined audio, video, and text attributes, integrate the segment attributes into the media content knowledge repository, and / or perform any of a variety of responsive actions.

Disclosed herein are system, apparatus, device, method and / or computer program product embodiments for identifying, in a remote deposit system, a level of correspondence of a financial instrument with past deposit activity. The level of correspondence may be used to determine a funds availability schedule and / or identify counterfeit financial instruments. In some embodiments, the level of correspondence may be determined by comparing a date associated with the financial instrument to a date parameter, an amount of the financial instrument to an amount parameter, and / or one or more financial instrument characteristics with one or more payer-specific financial instrument characteristics.

The disclosed concepts relate to automatically identifying conditions in a video game to trigger a help session. When a help session is triggered, another video game player or machine learning model can temporarily take over for the current video game player until an ending condition is reached. Help session triggering can be designated by evaluation of prior gameplay data of other video game players to identify in-game conditions that may tend to cause user disengagement, such as in-game conditions that are associated with difficult in-game goals or negative in-game consequences.

A machine learning based computing method for extracting data from electronic documents, is disclosed. The machine learning based computing method includes steps of: receiving the electronic documents from data sources; converting formats of the electronic documents into first images associated with the electronic documents; classifying the first images associated with the electronic documents as second images including tabular data, and third images including non-tabular data, based on a CNN based machine learning model; determining tabular regions in tabular data associated with the second images by identifying bounding box coordinates indicating tabular regions in tabular data, based on a YOLO architecture based machine learning model; extracting first data from the tabular regions; extracting second data from non-tabular regions; and providing an output of the first data and the second data to second users on a user interface associated with electronic devices.

The invention discloses an invoice automatic auditing and intelligent settlement system for automobile road rescue, and relates to the technical field of intelligent settlement systems, a correction module integrates a machine learning model to analyze historical bills, automatically corrects unreasonable settlement amount and generates a correction suggestion report, a prompt module builds an intelligent priority matrix, and the intelligent priority matrix is sent to a server. The reminding frequency is dynamically adjusted according to parameters such as the historical settlement scale and the service life of a supplier, the settlement module recognizes an abnormal invoicing terminal by combining an invoicing equipment fingerprint recognition technology, a payment process is automatically triggered after verification is passed, a supplier credit portrait system is established, and a dynamic settlement scheme is supported. The settlement system establishes an intelligent priority matrix to realize important supplier high-frequency reminding and low-risk project low-frequency intervention, so that the whole process timeliness is guaranteed, the defects of a traditional rule engine in coping with complex scenes are effectively overcome, and the response capability and the autonomous decision-making capability of the system to abnormal behaviors are improved.

This disclosure provides systems, methods, and devices for vehicle driving assistance systems that support image processing. In a first aspect, the methods addresses traffic sign recognition as a language model-based image reasoning task by utilizing a multi-modal transformer architecture that combines the strength of vision and language machine learning (ML) models. The transformer architecture recognizes traffic signs based on visual features and associated taxonomy of the traffic signs. In a second aspect, the methods leverage context surrounding an autonomous vehicle through a graph-based modeling framework that fuses outputs from multiple perception modules to construct a semantic scene graph representation of an intersection, which consolidates processing diverse data types for traffic light relevancy detection. Other aspects and features are also claimed and described.

A trained machine learning model and a training dataset used to train the trained machine learning model can be received. Based on the training dataset, unsupervised adversarial examples can be generated. Robustness of the trained machine learning model can be determined using the generated unsupervised adversarial examples. The training dataset can be augmented with the generated unsupervised adversarial examples. The trained machine learning model can be retrained using the augmented training dataset.

A page identification technique is configurable to select regions of a screen for optical character recognition. The size of the regions may be selected to reduce the CPU resources needed to identify a page. Pre-processing and post-processing may be performed to improve the accuracy of the optical character recognition. A word mapping algorithm may include logical condition to determine a page name.

A computer implemented method, system and non-transitory computer-readable device for a remote deposit environment activating, on a client device, a financial application, wherein the financial application is configured to instantiate a customer interface (UI) on the client device. Upon receiving a customer request, based on interactions with the UI, the method implements an electronic deposit of a financial instrument by generating a live stream of image data of a field of view of at least one camera, wherein the live stream of image data includes imagery of at least a portion of the financial instrument, determining, based on the live stream of image data and a machine learning model (ML), an impermissibility score of the financial instrument and, based on exceeding a selectable threshold of the impermissibility score, modifying a status of the remote deposit to pause or terminate the remote deposit.

A method of extracting meta-data from a document includes capturing style attributes from the document, identifying cell-wise location coordinates for text characters using page segmentation and border table extraction, and finding relationship between nearby cells using surrounding embedding by determining shortest distant text cell in top, left, right, and bottom direction. The method further includes applying Graph Convolution Network with Informative Attention (GCN-IA) for providing more attention to informative nodes for generating better representation of surrounding embedding and capturing a deep contextual meaning from text cells. A domain specific language model is utilized and improved by a domain aware tokenizer. The method includes capturing a complex visual layout of the document using the domain specific visual model, determining meta-data information, representing linguistic and visual contexts of the document, and correcting the extracted output by applying advanced-post processing on the extracted output from advanced language-visual model.

Systems and methods for tracking inventory items in an area of real space are disclosed. The method includes receiving a signal generated in dependence on sensors. The signal indicates a change to a portion of an image of an area of real space. The method includes, in response to receiving the signal, implementing a trained location detection model to determine, based on inputs, whether an inventory item identified in the portion of the image has changed a position in the area of real space. The method includes implementing a trained item classification model to determine a classification of the inventory item. The method includes updating an inventory database with inventory item data determined in dependence on the classification of the inventory item to provide an updated map of the area of real space as a result of the received signal indicating the change to the portion of the image.

The invention provides an IM software multi-modal feature fusion instant confidential information detection method and system, and the method comprises the steps: generating a local vectorization capability through deploying a TinyBERT model at a client; configuring a distribution mechanism of the file interception module, separating text, image and voice contents, and generating a multi-mode parallel processing channel; designing a meta-information packaging format of the communication management module, integrating file meta-information features, and generating a three-dimensional feature packaging data stream; and establishing a server sensitive document database and a dynamic rule issuing channel, and generating a closed-loop strategy updating mechanism so as to realize a client-server collaborative hierarchical processing architecture. Analysis can be triggered immediately in the file uploading stage, millisecond-level preliminary risk assessment is achieved, and the method has the advantages of being real-time and low in resource consumption. And when the risk unknown data is encountered, the data is uploaded to the server for further verification, so that the recognition precision of the complex confidential scene is improved.

Disclosed herein are system, apparatus, device, method and / or computer program product embodiments for determining, in a remote deposit system, whether a deposit attempt is illegitimate (e.g. fraudulent). Whether the deposit attempt is illegitimate may be assessed based on one or more of the following processes: comparing location data to a location parameter determined from past deposits, comparing an image capture location with a deposit location, and analyzing image-of-image characteristics obtained through image processing to identify whether an image associated with the deposit attempt is an image of an image. In some embodiments, a remote deposit status related to acceptance of the deposit attempt may be provided in real-time

Large language models (LLMs) and visual-language models (VLMs) are able to provide robust results based on specified formatting and organization. Although LLMs and VLMs are designed to receive natural language input, users often lack the skill, knowledge, or patience to utilize LLMs and VLMs to their full potential. By leveraging screen understanding, AI prompts (or “pills”) may automatically be generated for artificial-intelligence (AI) assistance and query resolution in a VLM / LLM environment. Using an image encoder, a current screenshot is processed into an image embedding and compared to text embeddings representing screenshot activities. By identifying the text embedding having the closest similarity to the image embedding, a screen activity being performed by the user may be determined. Suggested AI prompts (or “pills”) may then be generated in real-time to assist the user in performing the screen activity.

Automatic analyses of customer-agent interactions provide valuable, actionable feedback for managers, agents, and customers. To provide such analyses, methods for recording and analysis of customer-agent interactions using a customer relationship management (CRM) system are disclosed. A recorder application records the customer-agent interaction, and sensitive information may be identified. Sensitive portions of the recording may then be redacted and removed from the recording. The redacted recording is then analyzed to generate useful summary and analytics information.

An analyzer module forms a hypothesis on what are a possible set of cyber threats that could include the identified abnormal behavior and / or suspicious activity with AI models trained with machine learning on possible cyber threats. The Analyzer analyzes a collection of system data, including metric data, to support or refute each of the possible cyber threat hypotheses that could include the identified abnormal behavior and / or suspicious activity data with the AI models. A formatting and ranking module outputs supported possible cyber threat hypotheses into a formalized report that is presented in 1) printable report, 2) presented digitally on a user interface, or 3) both.

Disclosed are apparatuses, systems, and techniques for automatically generating commentary to videos that capture sporting activities, computer games, artistic events, political rallies, security-sensitive scenes, and / or any other actions. The techniques include processing a video segment that includes a plurality of video frames, to obtain a description of one or more objects pictured in the video segment and generating, using the obtained description, a prompt for a language model (LM). The techniques further include causing the LM to process the prompt to generate a commentary about an action performed by the one or more objects over a time interval associated with the plurality of video frames.

Technologies for language agnostic OCR extraction include identifying a word region of an image using optical character recognition, applying a language agnostic machine learning model to the word region, where the language agnostic machine learning model is trained on training data including a set of image-text pairs and a set of multilingual text translation pairs, receiving, from the language agnostic machine learning model, a word region embedding that is associated with the word region, searching a multilingual index for a text embedding that matches the word region embedding, receiving, from the multilingual index, text associated with the text embedding; and outputting at least one of the text or the text embedding to at least one downstream process, application, system, component, or network.

The present invention discloses a system and method for processing trade finance documents and performing automated compliance screening. The system comprises a computing device, and a database for storing trade finance documents. The system processes documents using OCR to extract text and positional data, generating structured document representations via a layout-aware AI model. An AI classifier module categorizes documents based on content, layout, and domain-specific roles, while a semantic verification module aligns document data with master Letter of Credit templates. A rule management module validates compliance against international trade standards, and a financial crime risk control module performs real-time checks against external sanctions, vessel, and dual-use goods databases. The system further determines and reports discrepancies, anomalies, and compliance issues. The system supports heterogeneous layouts, multi-language documents, and integration with banking APIs.

A computer implemented method, system, and non-transitory computer-readable device for a remote deposit environment. In some embodiments, a predictive machine learning (ML) model may be trained to determine a likelihood an image will be successfully processed via OCR. The predictive ML model may determine the likelihood prior to the image being uploaded to a remote server and / or processed via OCR, allowing the image to be rejected and replaced in real time. In some embodiments, the predictive ML model may be implemented on a mobile device. Optionally, the predictive ML model may be supported by a deep learning model operating to refine the predictive ML model.

An information processing apparatus includes a processor configured to acquire plural scanned images obtained by scanning a bundle of paper media including a plural standard document bundles each of which is a set of a standard document and a related document related to the standard document, extract a title from the plural scanned images, extract, from the plural scanned images, an identifier that is assigned to be common within one standard document bundle and to be different between different standard document bundles, and divide the plural scanned images into bundles such that a scanned image from which the title is extracted is set as a bundle head, scanned images having the same identifier are included in the same bundle, and scanned images having different identifiers are included in different bundles.

The invention discloses a work order generation method, a work order processing method and a work order management system. The work order generation method comprises the following steps: performing text extraction on multi-modal problem data reported by a user to obtain corresponding target text data; analyzing the multi-modal problem data by using the problem classification model to obtain a corresponding problem type, inputting the target text data into a work order template matched with the problem type to obtain a work order to be processed, and determining a generation timestamp of the work order to be processed; analyzing the multi-modal problem data by using an emotional tendency recognition model to obtain a corresponding emotional tendency; and packaging the emotional tendency, the question type, the work order to be processed and the corresponding generation timestamp corresponding to the multi-modal question data into a work order information packet, sending the work order information packet to a server, and receiving a question result fed back by the server. The technical problem that the work order generation accuracy is poor due to the fact that the multi-modal feedback data of the user cannot be fully understood in the related technology is solved.

The invention discloses a court area identification method and device and a storage medium, and relates to the technical field of data processing. According to the method, the depth map and the RGB map of the court acquired by the image acquisition device are acquired, the point cloud data are generated based on the depth map, the point cloud fluctuation amplitude corresponding to the court is determined according to the point cloud data, then the color distribution characteristics and the texture distribution characteristics of the court are determined based on the RGB map, and finally, the color distribution characteristics and the texture distribution characteristics of the court are determined. The area type of the court is determined based on the color distribution characteristics and the texture distribution characteristics of the court and the point cloud fluctuation amplitude corresponding to the court, so that court area identification is more comprehensive and accurate, and the risk that a golf cart enters a forbidden area by mistake is reduced.