MACHINE LEARNING TO ADAPT EXTRACTION TO DIFFERENT DOCUMENTS

    公开(公告)号:US20240303531A1

    公开(公告)日:2024-09-12

    申请号:US18118994

    申请日:2023-03-08

    Applicant: Kaoru Watanabe

    Inventor: Kaoru Watanabe

    CPC classification number: G06N20/00

    Abstract: Techniques for adapting extraction to different documents using machine learning are provided. In one technique, multiple parsing rules are stored, each parsing rule being used to map field values in extracted text to field names associated with the parsing rule. In response to receiving a request to use a parsing rule for a particular document, a particular parsing rule is selected from among the parsing rules. Text data associated with the particular document is extracted. The particular parsing rule is used to map field values (in the extracted text data) to field names associated with the particular parsing rule. First input that selects data associated with a particular field name of the field names is received. Second input that selects a visual portion of the particular document is also received. The particular parsing rule is updated based on the first and second inputs to generate an updated parsing rule.

    AUTOMATIC DATA CAPTURE OF DESIRED DATA FIELDS AND GENERATION OF METADATA BASED ON CAPTURED DATA FIELDS

    公开(公告)号:US20210271716A1

    公开(公告)日:2021-09-02

    申请号:US16805663

    申请日:2020-02-28

    Applicant: Kaoru Watanabe

    Inventor: Kaoru Watanabe

    Abstract: An approach is provided for generating parsing rules that automatically identify attributes and attribute values from documents and generates metadata mapping information that is associated with electronic versions of documents processed. A graphical user interface (GUI) is displayed on a client device that contains a sample document containing field labels and field values, which represent attributes and attribute values. The GUI is configured to receive a first set of inputs identify field labels and field values. In response to receiving the first set of inputs, parsing rules are generated that define the relationships between the field labels and corresponding field values. A second set of inputs are received that include a selection of a subset of the parsing rules to generate metadata mapping that maps a subset of the field values to display labels. The metadata mapping is associated to a document library that manages views of the destination folder such that the parsing rules and the metadata mapping are applied to each document routed to the destination folder.

    GUIDED WEB-APPLICATION GENERATION
    3.
    发明申请

    公开(公告)号:US20190235845A1

    公开(公告)日:2019-08-01

    申请号:US15886501

    申请日:2018-02-01

    Abstract: Techniques are described herein for generating and managing Web applications. Embodiments include receiving organized data and analyzing the organized data to determine one or more data types contained in the organized data. Based on the one or more data types, suggested widgets are determined, including determining whether a particular data type can be split into two or more data types and suggesting widgets for each split data type. The suggested widgets are presented to a user, and in response to user input accepting the suggested widgets, a Web application comprising the suggested widgets is generated.

    Virtual Sticky Generation
    4.
    发明申请

    公开(公告)号:US20180203834A1

    公开(公告)日:2018-07-19

    申请号:US15925473

    申请日:2018-03-19

    Applicant: Kaoru Watanabe

    Inventor: Kaoru Watanabe

    Abstract: Digital programmed logic implemented on a computing device programmed to cause the display of an electronic document on a graphical user interface within the computing device. The electronic document displayed includes a plurality of data items of information. The programmed logic is programmed to automatically generate summary data that summarizes at least two data items from the plurality of data items included in the electronic document. The programmed logic is further programmed to generate a virtual sticky and display the virtual sticky on the electronic document. The virtual sticky displays the automatically generated summary data and the display of the virtual sticky is overlaid onto at least a portion of the display of the electronic document.

    Virtual sticky generation
    5.
    发明授权

    公开(公告)号:US09922016B2

    公开(公告)日:2018-03-20

    申请号:US15148199

    申请日:2016-05-06

    Applicant: Kaoru Watanabe

    Inventor: Kaoru Watanabe

    Abstract: Digital programmed logic implemented on a computing device programmed to cause the display of an electronic document on a graphical user interface within the computing device. The electronic document displayed includes a plurality of data items of information. The programmed logic is programmed to automatically generate summary data that summarizes at least two data items from the plurality of data items included in the electronic document. The programmed logic is further programmed to generate a virtual sticky and display the virtual sticky on the electronic document. The virtual sticky displays the automatically generated summary data and the display of the virtual sticky is overlaid onto at least a portion of the display of the electronic document.

    Virtual Sticky Generation
    6.
    发明申请

    公开(公告)号:US20170322918A1

    公开(公告)日:2017-11-09

    申请号:US15148199

    申请日:2016-05-06

    Applicant: Kaoru Watanabe

    Inventor: Kaoru Watanabe

    Abstract: Digital programmed logic implemented on a computing device programmed to cause the display of an electronic document on a graphical user interface within the computing device. The electronic document displayed includes a plurality of data items of information. The programmed logic is programmed to automatically generate summary data that summarizes at least two data items from the plurality of data items included in the electronic document. The programmed logic is further programmed to generate a virtual sticky and display the virtual sticky on the electronic document. The virtual sticky displays the automatically generated summary data and the display of the virtual sticky is overlaid onto at least a portion of the display of the electronic document.

    Document processing job control via a mobile device
    7.
    发明授权
    Document processing job control via a mobile device 有权
    通过移动设备进行文档处理作业控制

    公开(公告)号:US08908205B2

    公开(公告)日:2014-12-09

    申请号:US13034282

    申请日:2011-02-24

    Abstract: Techniques are provided for allowing a user to create a document processing job (e.g., a print job, a scan job, a copy job, fax job) at a mobile device instead of at a document processing device, such as a printer, scanner, or copier. A cloud service interacts with the mobile device to retrieve job settings data from the mobile device. The cloud service generates a job identifier, associates the job identifier with job settings associated with the job settings data, and sends the job identifier to the mobile device, which displays the job identifier to the user. The user later enters the job identifier at the document processing device, which, in turn, uses the job identifier to request the job settings from the cloud service. The cloud service identifies the job settings based on the job identifier and sends the job settings to the document processing device.

    Abstract translation: 提供了技术,用于允许用户在移动设备而不是文档处理设备(例如打印机,扫描仪)上创建文档处理作业(例如,打印作业,扫描作业,复印作业,传真作业) 或复印机。 云服务与移动设备交互以从移动设备检索作业设置数据。 云服务生成作业标识符,将作业标识符与作业设置数据相关联的作业设置相关联,并将作业标识符发送到移动设备,该移动设备将作业标识符显示给用户。 用户稍后在文档处理设备处输入作业标识符,该文件处理设备又使用作业标识符从云服务请求作业设置。 云服务基于作业标识识别作业设置,并将作业设置发送到文档处理设备。

    Image-holding member cases, developing device cases, and image-forming apparatus
    8.
    发明授权
    Image-holding member cases, developing device cases, and image-forming apparatus 有权
    图像保持构件壳体,显影装置壳体和图像形成装置

    公开(公告)号:US08457522B2

    公开(公告)日:2013-06-04

    申请号:US12908523

    申请日:2010-10-20

    Applicant: Kaoru Watanabe

    Inventor: Kaoru Watanabe

    CPC classification number: G03G21/18

    Abstract: An image-forming apparatus includes: an image-holding member casing that encases an image-holding member; an apparatus main body into which the image-holding member casing is inserted to a predetermined position; a developing device casing provided in the apparatus main body, the developing device casing encasing a developing device; a pushing member provided in the apparatus main body to push the developing device casing in a first direction toward the image-holding member; and a contact portion provided on the image-holding member casing so as to contact the developing device casing for a predetermined period during insertion of the image-holding member casing toward the predetermined position, to push the developing device casing in a second direction opposite to the first direction, wherein, after the predetermined period, when the image-holding member casing reaches the predetermined position, the contact portion does not push the developing device casing in the second direction.

    Abstract translation: 图像形成装置包括:图像保持部件壳体,其包围图像保持部件; 图像保持部件壳体插入到预定位置的装置主体; 设置在所述装置主体中的显影装置壳体,所述显影装置壳体包围显影装置; 推动构件,其设置在所述装置主体中,用于将所述显影装置壳体沿第一方向推向所述图像保持构件; 以及接触部分,设置在图像保持部件壳体上,以便在将图像保持部件壳体朝向预定位置插入期间接触到显影装置壳体一段预定的时间,以沿与第二方向相反的第二方向推动显影装置壳体 第一方向,其中,在所述预定时段之后,当所述图像保持构件壳体到达所述预定位置时,所述接触部分不将所述显影装置壳体沿第二方向推动。

    WORKFLOW MANAGEMENT AT A DOCUMENT PROCESSING DEVICE
    9.
    发明申请
    WORKFLOW MANAGEMENT AT A DOCUMENT PROCESSING DEVICE 审中-公开
    文件处理设备的工作流管理

    公开(公告)号:US20120079409A1

    公开(公告)日:2012-03-29

    申请号:US12892155

    申请日:2010-09-28

    CPC classification number: G06F8/34 G06F8/36

    Abstract: Approaches are provided for workflow creation and management at a scanning device. In one approach, a user initiates a plurality of operations to be performed on, or relative to, scanned document data. A workflow that represents the sequence of operations is created. The workflow may be created with or without user input. The workflow is later provided as an option to a user. Upon selection of the option, the sequence of operations is performed without requiring the user to select each operation separately. In a related approach, a user is also allowed to create a workflow by selecting graphical representations of operations and causing the graphical representations to be arranged in a particular order to create a workflow that may be later selected.

    Abstract translation: 为扫描设备上的工作流创建和管理提供了方法。 在一种方法中,用户发起要对扫描的文档数据执行或相对于扫描的文档数据执行的多个操作。 创建表示操作序列的工作流。 可以使用或不使用用户输入创建工作流程。 工作流随后作为用户的选项提供。 在选择选项时,执行操作顺序,而不需要用户分别选择每个操作。 在相关方法中,还允许用户通过选择操作的图形表示来创建工作流,并使图形表示以特定顺序排列以创建可以稍后选择的工作流。

    SENDING SCANNED DOCUMENT DATA THROUGH A NETWORK TO A MOBILE DEVICE
    10.
    发明申请
    SENDING SCANNED DOCUMENT DATA THROUGH A NETWORK TO A MOBILE DEVICE 审中-公开
    将扫描的文件数据通过网络发送到移动设备

    公开(公告)号:US20120050818A1

    公开(公告)日:2012-03-01

    申请号:US12873116

    申请日:2010-08-31

    Applicant: Kaoru Watanabe

    Inventor: Kaoru Watanabe

    Abstract: An approach for processing scanned document data includes a document processing network service receiving, from a scanning device, scanned document data that represents text contained in one or more printed documents. The document processing network service, sends, based on mobile device data received from the scanning device, the scanned document data (or text data generated from the scanned document data) to one or more mobile devices identified in the mobile device data. An approach for processing scanned document data also includes a document processing network service, in response to receiving scanned document data and recipient data from a scanning device, extracting contact information from the scanned document data and causing the contact information to be stored in association from the recipient data to allow a mobile device of an intended recipient to receive the contact information and initiate a call to a phone number identified in the contact information.

    Abstract translation: 用于处理扫描文档数据的方法包括文件处理网络服务,其从扫描设备接收表示包含在一个或多个打印文档中的文本的扫描文档数据。 文档处理网络服务基于从扫描设备接收的移动设备数据,将扫描的文档数据(或从扫描的文档数据生成的文本数据)发送到在移动设备数据中标识的一个或多个移动设备。 用于处理扫描文档数据的方法还包括文档处理网络服务,响应于从扫描设备接收扫描的文档数据和接收者数据,从扫描的文档数据中提取联系人信息,并使联系人信息从 收件人数据,以允许预期接收者的移动设备接收联系人信息并发起对联系人信息中识别的电话号码的呼叫。

Patent Agency Ranking