3114results about "Character recognition" patented technology

Systems and methods for determining attributes in media content. A computing device may be configured to obtain the media content based on a received media content identifier and segment the media content into scenes. The computing device may analyze viewer engagement metrics to identify a scene associated with a viewer engagement score that exceeds a threshold, select video frames from the identified scene, and identify primary objects in the series of images in the scene. The computing device may add a bounding box around the identified primary objects in one or more selected frames and perform text extraction within the bounding box. The computing device may determine object attributes of the identified primary objects, querying a database to identify topics of interest (ToIs) based on the extracted text and the determined object attributes, and performing a responsive action in response to identifying the one or more ToIs.

An apparatus includes a base having a platform configured for placement of one or more items on a surface of the platform, a frame coupled to the base, and a plurality of camera units coupled to the frame. Each camera unit is configured to capture images of at least a portion of the platform and the plurality of camera units includes a plurality of side-view camera units arranged above the platform along a horizontal plane, wherein each camera unit of the side-view camera units comprises two vertically stacked cameras and is configured to capture perspective images of at least a portion of the platform. An overhead-view camera unit is positioned over the platform, wherein the overhead-view camera unit comprises two cameras and is configured to capture top view images of the platform.

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 extracting, based on the live stream of image data and by an optical character recognition program resident on the client device, one or more data fields from the financial instrument and communicating the extracted one or more data fields to a remote deposit server to complete the electronic deposit.

A processor captures a first image of a platform using a first camera of a plurality of cameras and determines a color metric based on the first image, wherein the color metric indicates a color of the first image. The processor compares the color metric to the color metric. In response to determining that the color metric associated with the first image does not match with the color setpoint, the processor adjusts brightness of at least one of a first set of warm LEDs or a second set of cool LEDs to cause the color of the light incident on the platform to match the color setpoint.

A computer implemented method, system and non-transitory computer-readable device for a remote deposit environment. Upon receiving a user 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 extracting in real-time, based on the formation of byte array objects from the live stream of image data, data fields from a ranked sequence of imagery to be processed by an optical character recognition (OCR) program resident on the client device. The OCR process extracts one or more data fields from of the financial instrument that are communicated to a remote deposit server to complete the electronic deposit.

A method can include receiving a document associated with a checklist item. A method can include identifying a template associated with the document. A method can include identifying an area of the document associated with a value of a key-value pair based at least in part on the template. A method can include extracting, using a first optical character recognition process, the value from the area. A method may cause display of the value. A method can include receiving a corrected value from the user. A method may include extracting, using a second optical character recognition process, full text of the document. A method may include determining a location of the corrected value in the document. A method may include updating the first optical character recognition process, wherein updating the first optical character recognition process causes the first optical character recognition to extract the value from the location.

A system and method for managing greenhouse gas emissions is described. In one aspect, the system and method are configured to receive real-time emission data from distributed data sources, including IoT sensors, optical character recognition systems, and augmented reality measurement devices. ML models are trained using ML engines based on historical data and the received emission data. The trained models process and validate the real-time emission data using ML engines. Timestamp blocks are generated using a proof of history blockchain architecture with a variable delay function. The validated emission data is stored and verified in the generated timestamp blocks. The verified emission data is transformed into standardized carbon credit tokens. Visualizations of greenhouse gas emissions are displayed on a user interface, showing information from a real-time emission report. The system and method enable automated collection, validation, storage, and visualization of greenhouse gas emission data using blockchain and ML technologies.

The invention discloses a voice interaction method and device and a storage medium, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining a target voice instruction of a user, and carrying out the analysis of the target voice instruction according to a preset target large language model, and obtaining a control intention; determining a position sequence of a target interface element corresponding to the control intention according to the control intention and a UI interface corresponding to a controlled device; determining a trigger action sequence according to the control intention; the controlled device is controlled to respond to the target voice instruction based on the position sequence and the trigger action sequence, and the quantity of component elements of the position sequence is equal to that of component elements of the trigger action sequence. Interaction with the user interface can be automatically completed according to the voice instruction input by the user, and the interaction efficiency is improved.

In an embodiment, a method for converting a set of legal documents of varied type related to a legal task into structured data suitable for the legal task is disclosed. The method uses artificial intelligence and is performed by at least one processor including hardware. The method includes receiving digitized versions of a plurality of legal documents from a user. The method further includes extracting electronic data from the digitized legal documents using optical character recognition and analyzing the extracted electronic data from each document using a sequence of microprompts to a trained large language model. The analyzing includes using the LLM to identify a type of the document and data keys within the electronic data, and to generate a name for the document. The method further includes storing and sending to the user the analyzed electronic data processed with the LLM as structured data suitable for the legal task.

One embodiment of the present invention sets forth a technique for extracting data from a document. The technique includes determining, via execution of one or more machine learning models, a first set of bounding boxes for a first set of values associated with a first key within the document and a second set of bounding boxes for a second set of values associated with a second key within the document. The technique also includes generating a first set of mappings between a list of items in the document and the first set of bounding boxes and a second set of mappings between the first and second sets of bounding boxes based on locations of the bounding boxes. The technique further includes determining, for a given item, one or more associated bounding boxes in the first and second sets of bounding boxes based on the mappings.

A computer-implemented method is provided for a mobile device to detect, by a camera of the mobile device, a plurality of checks; determine, by a processing unit of the mobile device, that the image of the plurality of checks is of sufficient quality; instruct, by a display of the mobile device, a user to take a photograph of the plurality of checks; crop, by the processing unit, the photograph of the plurality of checks into a plurality of images, wherein each of the plurality of images contains one of the plurality of checks; and transmit, by a transmitter of the mobile device, the plurality of images to a server via a network. The plurality of images may be transmitted individually (i.e., one at time), or alternatively, collectively and in one payload.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for detecting text instances of arbitrary shapes, sizes, and locations. In one aspect, a method comprises processing an image depicting one or more text instances, generating a respective prediction for each character in a sequence of characters that are predicted to be depicted in the text instance, the respective prediction comprising a respective character class to which the predicted character belongs, the respective character class selected from a set that includes printable character classes and a space character class and a bounding box that contains the character within the image, and grouping the sequence of characters into a plurality of words based on locations of characters that are predicted to belong to the space character class.

Using generative AI to supplement automated information extraction is disclosed. Computer vision (CV) and / or optical character recognition (OCR) models and a generative artificial intelligence (AI) model are used together to extract information (e.g., names, dates, invoice numbers, etc.) from a source. Acceptance threshold(s) may be used to accept predictions for extracted data elements from the models, and the prediction from the generative AI model may be preferred or a human may be tasked with reviewing the element. If no model meets its respective acceptance threshold (whether common or specific to that model), these element(s) may be marked for subsequent human review, or a human can be looped in to correct these element(s). The models may then be retrained using these labeled elements.

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.

The present disclosure provides a system for generating customized messages to a prospect. The system comprises: a data input module configured to receive prospect data, wherein the prospect data comprises data related to a prospect and data gathered from a plurality of sources; an input data processing module configured to select a subset of the data to create an input data; a first model trained to generate one or more sentences based on the input data; and a second model trained to determine whether the one or more sentences are unacceptable, wherein upon determining the one or more sentences are unacceptable, directing the input data processing module to select another subset of the data to create a new input data.

Systems and methods for generating images with legible scene text are described. Embodiments are configured to obtain a prompt describing a scene, where the prompt includes scene text indicating text that is intended to be shown in a generated image; encode, using a prompt encoder, the prompt to generate a prompt embedding; encode, using a character-level encoder, the scene text to generate a character-level embedding; and generate, using an image generation network, an image that includes the scene text based on the prompt embedding and the character-level embedding.

A data extraction service is disclosed. The data extraction service may receive an image that includes a data table. The data extraction service may perform optical character recognition on the image. The data extraction service may label text in the image to identify the table. The data extraction service may generate a digital data table corresponding to the data table in the image. The data extraction service may format the digital data table and provide the formatted digital data table to a downstream entity.

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.

A computer-implemented method for extracting data from printed documents comprises receiving a printed document and identifying the printed document as one of a structured form (including fully structured and semi-structured) and an unstructured form. Where the printed document is identified as a structured form, the method identifies first text features corresponding to keys for key-value pairs and identifies second text features that satisfy a proximity threshold (and optionally one or more key constraints) relative to the respective first text feature as the respective values of the respective key-value pairs, and records the values of the key-value pairs. Where the printed document is identified as a semi-structured form, the method may further comprise identifying at least one unstructured portion of the printed document and applying a trained machine learning model to the unstructured portion of the printed document to obtain additional values for additional key-value pairs.

A deep neural network-based system for detection and recognition of construction elements in construction engineering drawings. A first neural network performs object detection and recognition to detect and recognize ducts and fittings. A second neural network performs text detection to detect text. A third neural network performs text recognition. Pixel tracing of the construction engineering drawing is performed using the bounding box for detected text as a reference point. The recognized text is filtered to output system types and system sizes from the recognized text. Each system type and size instance is correlated to a detected duct, pipe or fitting instance to determine object coordinates, system type, item type, size and length. A list of construction elements is generated for all detected duct, pipe and fitting instances. An interactive visualization of the construction engineering drawing based on the list of construction elements and / or a costing may be provided.

Systems and methods for performing document entity extraction are described herein. The method can include receiving an inference document and a target schema. The method can also include generating one or more document inputs from the inference document and one or more schema inputs from the target schema. The method can further include, for each combination of the document input and schema input, obtaining one or more extraction inputs by generating a respective extraction input based on the combination, providing the respective extraction input to the machine-learned model, and receiving a respective output of the machine-learned model based on the respective extraction. The method can also include validating the extracted entity data based on reference spatial locations and inference spatial locations and outputting the validated extracted entity data.

An electronic system includes a monitored device and a management device. The monitored device operates according to an operating system and generates a display image. The management device is connected to the monitored device through a communication network. The management device periodically receives, from the monitored device, screen image data corresponding to the display image, determines whether an error that causes the operating system of the monitored device to become inoperable occurs in the operating system of the monitored device based on a network connection state with the monitored device, determines a type of the error based on error determination factors and an analysis result of the screen image data, and transfers, to the monitored device, a request indicating follow-up actions to take to resolve the error, the follow-up actions corresponding to the type of the error.

Systems and methods for deep learning model development for data extraction using a feedback loop. A system generates an interactive graphical user interface (GUI) on one or more user devices for displaying a document with data extracted from the document by a data extraction model together with a user interaction tool allowing the user to correct the extracted data. The system receives, via the interactive GUI, correction information for the extracted data and monitoring performance characteristics of the extraction model in real-time based on the user correction information. The system automatically updates and trains the extraction model using the correction information responsive to detecting that the performance characteristics meet a predetermined performance reduction condition.

The invention proposes a method that receives an unstructured document at the input, extracts its information, reorganizes and makes this information available in files that can be consumed by other systems. The method for extracting and structuring information comprises a (1) document page separator model, (2) block detection and segmentation model, (3) table extractor, (4) image extractor, (5) image classification model, (6) text extractor, (7) computer vision model for improving the image quality of the texts, (8) optical character recognition model, (09) model for spelling correction, (10) models for semantic enrichment of the text, (11) output file organizer and (12) metadata aggregator for information enrichment. There is also part of the invention a synthetic document generator that serves to create a training base made up of millions of synthetic documents, which emulate real documents commonly used by the O&G industry in different layout variations. These synthetic documents are used to train and update the artificial intelligence models used in the main process of extracting information. Accordingly, it comprises the following steps: (1) generation of synthetic documents, in different layout configurations; (2) training / tuning of computer vision and classification models; (3) quality control of the models under synthetic and real sets; (4) assessment of extraction results in the O&G domain; (5) identification of new formats or alterations to existing formats; (6) adjustment of parameters and configuration of new synthetic formats.

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.

Mechanisms are provided for automated document image annotation and data extraction. A received document image is processed to identify a document type of the received document image, and retrieve a corresponding document template having key point location data and annotation location data for documents of the document type. First key points of the received document image are matched with second key points of the corresponding document template and a mapping is generated to map locations of the document template to locations of the received document image. A perspective transformation is applied, based on the mapping, to first annotation locations specified in the document template data structure to generate second annotation locations corresponding to locations in the received document image. Data extraction is performed on data associated with the second annotation locations based on the annotations corresponding to the second annotation locations.

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 herein are methods, systems, and apparatus for automated license plate recognition and methods for training a machine learning model to undertake automated license plate recognition. For example, a method can comprise dividing an image or video frame comprising a license plate into a plurality of image patches, determining a positional vector for each of the image patches, adding the positional vector to each of the image patches and inputting the image patches and their associated positional vectors to a text-adapted vision transformer. The text-adapted vision transformer can be configured to output a prediction concerning the license plate number of the license plate.

The invention relates to a container number and container threshold weight identification method and device based on deep learning. The method comprises the following steps: acquiring a side image of a container body; inputting the side image of the box body into a target detection model, and detecting the coordinates of the area where each target is located and the corresponding target type; cutting out a target image from the box side image, inputting transverse box number images into a box number character block detection model, correspondingly outputting a prediction set by each transverse box number image, detecting character blocks in the prediction sets by adopting non-maximum suppression to obtain a detection set of the character blocks, cutting out character block images, and splicing the character block images to obtain a detection set of the character blocks; obtaining a transverse box number spliced image; and inputting the transverse box number spliced image and other target images into a trained character recognition model, and recognizing the box number, the ISO number and the box threshold weight limiting character. The method has the advantages that the container number and the container threshold weight can be automatically and accurately recognized, the recognition accuracy is high, the method is suitable for various complex container images, and the good recognition effect can be achieved.