Template-based intelligent document processing method and apparatus

    公开(公告)号:US11574118B2

    公开(公告)日:2023-02-07

    申请号:US17219633

    申请日:2021-03-31

    Abstract: A blank template form generation method and system may employ synthetically generated blank template forms, differing from each other in one or more respects, to train a neural network to recognize relevant differences between otherwise similar forms, including types and locations of keywords and potential locations of values corresponding to the keywords. In an embodiment, filled or partly filled forms as well as blank template forms may be used later in training. Forms are input in pairs to identify differences between the two. Depending on the differences, weights of a neural network may be adjusted. After training, when a form is input into the system, whether the form is filled or blank, a blank template may be generated for future use.

    3D-printed article with transitional metastructures

    公开(公告)号:US11495202B2

    公开(公告)日:2022-11-08

    申请号:US16557464

    申请日:2019-08-30

    Inventor: Jun Amano

    Abstract: A single-step method of generating a three dimensional (3D) printed article includes: selecting a first metastructure and a second metastructure; designing and constructing a first transitional metastructure that transitions from the first metastructure to the second metastructure; depositing a first layer comprising the first metastructure; seamlessly connecting the first and first transitional metastructures by depositing a first transitional layer comprising the first transitional metastructure on the first layer; and seamlessly connecting the first transitional and second metastructures by depositing a second layer comprising the second metastructure on the first transitional layer.

    Authentication server and method that provide authentication information upon interruption of power supply

    公开(公告)号:US11470082B2

    公开(公告)日:2022-10-11

    申请号:US16836126

    申请日:2020-03-31

    Inventor: Hiroki Ikari

    Abstract: An authentication server is connected to a client device via a network and includes: an uninterruptible power supply (UPS) that supplies power to the authentication server upon interruption of a main power supply; a storage that stores a database including: a piece of user information of a user of the client device; and a piece of authentication information for the user to log into the client device or a predetermined server on the network via the client device; and a processor that, once the UPS starts to supply the power to the authentication server, transmits to the client device the piece of authentication information corresponding to the piece of user information before the authentication server is shut down.

    Identifying sequence headings in a document

    公开(公告)号:US11468346B2

    公开(公告)日:2022-10-11

    申请号:US16370724

    申请日:2019-03-29

    Inventor: Darrell Bellert

    Abstract: A method for processing an electronic document (ED) to infer a sequence of section headings in the ED. The method includes generating, by a computer processor, based on regular expression matching of a predetermined section heading pattern and a plurality of characters in the ED, a list of candidate headings in the ED; generating, by the computer processor and based on the list of candidate headings, a list of chain fragments for inferring a portion of the sequence of section headings; and generating, by the computer processor and based on predetermined criteria, the sequence of section headings by merging at least two chain fragments in the list of chain fragments.

    Separation of projection and capture in collaboration environment

    公开(公告)号:US11425310B2

    公开(公告)日:2022-08-23

    申请号:US17144627

    申请日:2021-01-08

    Abstract: An optical shutter device includes: a projection shutter disposed in front of a projection device that projects an AR image onto an object surface with a local content; an imaging shutter disposed in front of an image capturing device that captures a local image of the local content; and a controller that electrically drives the projection and imaging shutters and switches the optical shutter device between a projection state and an imaging state. In the projection state, the controller electrically drives: the projection shutter to an open state, and the imaging shutter to a closed state. In the imaging state, the controller electrically drives: the projection shutter to the closed state, and the imaging shutter to the open state.

    Method, apparatus, and system to manage patient treatment

    公开(公告)号:US11335445B2

    公开(公告)日:2022-05-17

    申请号:US16837967

    申请日:2020-04-01

    Inventor: John Parmley

    Abstract: A care plan risk rating (CPR2) system and method enables physicians and other clinicians to manage patient health care plans remotely in response to patient input to generate CPR2 values. In one aspect, patients under care for a particular condition respond to a series of questions related to that condition. The questions may be weighted according to predetermined criteria which a physician or clinician may set. Based on the CPR2 values, the physician or clinician may alter a care plan for a patient or a group of patients. In one aspect, patients with CPR2 values in a predetermined range may be grouped into a cohort, and their care plans managed as a group.

    Online training data generation for optical character recognition

    公开(公告)号:US11295155B2

    公开(公告)日:2022-04-05

    申请号:US16843811

    申请日:2020-04-08

    Inventor: Ting Xu

    Abstract: A method and system to generate training data for a deep learning model in memory instead of loading pre-generated data from disk storage. A corpus may be stored as lines of text. The lines of text can be manipulated in the memory of a central processing unit (CPU) of a computing system, using asynchronous multi-processing, in parallel with a training process being conducted on the system's graphics processing unit (GPU). With such an approach, for a given line of text, it is possible to take advantage of different fonts and different types of image augmentation without having to put the images in disk storage for subsequent retrieval. Consequently, the same line of text can be used to generate different training images for use in different epochs, providing more variability in training data (no training sample is trained on more than once). A single training corpus may yield many different training data sets. In one aspect, the model being trained is a deep learning model, which may be one of several different types of neural networks. The training enables the deep learning model to perform OCR on line images.

    Ultra high frequency and tunable carbon nanotube resonator

    公开(公告)号:US11271538B2

    公开(公告)日:2022-03-08

    申请号:US16147355

    申请日:2018-09-28

    Abstract: A carbon nanotube (CNT) resonator includes: a first CNT having a first end and a second end both fixed to a substrate; and a second CNT having a first end fixed to the substrate. The second CNT creates a Van der Waals (VdW) bond with the first CNT where the second CNT overlaps the first CNT. A length of the VdW bond along a distance between the first and the second CNTs oscillates based on a DC voltage applied between the first end of the first CNT and the first end of the second CNT. An electrical current passing through the first and the second CNTs using the VdW bond oscillates based on the oscillation of the length of the VdW bond.

Patent Agency Ranking