76 results about "Intelligent document" patented technology

An intelligent document recognition-based document management system includes modules for image capture, image enhancement, image identification, optical character recognition, data extraction and quality assurance. The system captures data from electronic documents as diverse as facsimile images, scanned images and images from document management systems. It processes these images and presents the data in, for example, a standard XML format. The document management system processes both structured document images (ones which have a standard format) and unstructured document images (ones which do not have a standard format). The system can extract images directly from a facsimile machine, a scanner or a document management system for processing.

A data structuring and artificial intelligence (AI), natural language processing (NLP) and Machine Learning knowledge system that enhances source content by identifying content topics and keywords and integrating associated and related internal and external content along with extracted information such as summaries, conclusions, action items, time sensitive topics, etc., is disclosed. The data structuring and AI/NLP/Machine Learning knowledge system includes an intelligent document viewer system and a communication sub-system with an objective communication system, an objective calendar communication system, and voice commands/responses system.

Autonomous embedded data cognition enables data to perform real-time environmental configuration control, self-manage, perform analyses, determine its current situation, and evaluate behavior to respond accordingly. When created, security measures, and access controls are selected. Highly sensitive data can be extracted and substituted with creator label and/or functional representation. Data-to-data reasoning and analysis can be performed. The processing method comprises autonomous monitoring for a state change and analyzing the current user to determine if the instantiation should exist. If affirmed, the cognition engine automatically configures the computational environment in which it resides. If denied, environmental behavior is further analyzed for security problems or an erroneous situation. If detected, the creator is alerted and provided with incident information enabling remote creator control of the data. Cognitive data can decide to self-destruct mitigating risk of undesirable instantiations. Intelligent Agents, a comprehensive data structure, and intelligent document means are leveraged for implementation.

The invention belongs to the field of image recognition processing. The invention relates to a self-adaptive intelligent document recognition and input device and a use method thereof. A data acquisition module acquires a paper text of a client into a picture file through scanning or shooting, the preprocessing module carries out block processing on the text in an image by utilizing a morphological processing algorithm, lattices in each line or table are made into unequal cell blocks, and the character recognition module carries out binary processing on each cell block; Then, the correlation analysis module performs correlation analysis according to a pre-configured keyword and a pre-configured rule; According to the technical scheme, the relation between text blocks is analyzed, a data extraction module is guided to extract needed field content, a deviation rectification module can perform verification and automatic correction on the extracted content according to previous identification and deviation rectification historical data, and finally a result is stored and returned to a calling party. The system is ingenious in design concept, safe and convenient to use, high in intelligent degree, high in recognition accuracy, friendly to application environment and wide in market prospect.

Document transaction processes between systems comprising the following steps: The client requests a form; the host supplies the form rendered into HTML and PDF from XML template; the client fills in the form and submits the completed form to the host; the host receives and processes the form, extracts key information and stores the processed form; the host composes and sends a responding form for confirmation and the processed information to the client; the client receives and processes and stores the responding form; the client makes change or mark/correct any discrepancy/dispute on the responding form and returns it back to the host; the host receives and processes the returned responding form containing change and discrepancy/dispute marked by the client; the host revises the responding form and returns it to the client; the client receives, processes, and stores the responding form.

A document architecture system includes an intelligent document processing engine that can receive raw data streamed from external data source(s), analyze the raw data to identify triggering events, apply rules to the triggering events identified, break down the raw data accordingly, and generating messages in an internal format to represent the pieces of data without any formatting or layout information. The messages can be augmented with custom metadata and stored as fragments that reference, but that do not physically incorporate, the messages. The stored fragments can be used by the document process engine to intelligently render documents and versions thereof. The messages and fragments are in internal formats under control of the document architecture system. The renditions are in final formats that can be delivered, for instance, via an output connector to various output delivery channels.

A self-authenticating intelligent document in sheet medium form has an information storage and transfer means incorporated thereinto for storing the original text portion of document information formed on the surface of the sheet medium and for storing an image of the completed document after supplemental information has been added to the original text portion on the surface of the sheet medium. The information storage and transfer means is either a single RFID tag having a first memory portion for storing the text portion and a second memory portion for storing the image of the completed document; or a first RFID tag having a memory portion for storing the text portion and a second RFID tag for storing the image of the completed document. To verify the authenticity of the document, the image stored in the information storage and transfer means is read out and compared with the visible version. When the two are identical, the document is authentic.

This application relates to document generation and management and, more particularly, cross-tier intelligent document generation and management. Various embodiments provide systems, methods, and software to quickly generate document templates with fields associated with data items, instantiate documents from such document templates, and submit the documents for processing and dispatch to intended recipients.

A method, system, and apparatus for intelligent document saving. An intelligent document saving method can include cropping a document to frame a changed portion of the document and saving only content framed by the cropping. Notably, the cropping step can include maintaining watermarks in the document to demarcate unchanged portions from both the start and the end of the document and, consequently, a starting and ending position in the document of the changed portion. The position of the watermarks can be repeatedly updated whenever changes are performed to the document.

The invention discloses an interface model of RIA layered framework based on MVC architecture, which mainly uses MVC architecture to realize merging a middleware platform of intelligent document data exchange into the interface design of the RIA layered framework and relates to the field of data communication. The invention comprises a client terminal based on the MVC architecture, a RIA adaptation layer, a HTP server, a MVC-architecture-based server and a database, which realizes the transmission of messages by adding the middleware platform of intelligent document data between the MVC-architecture-based server and the database. The data exchange platform break through the bottleneck of application integration and heterogeneous data integration by merging a middleware platform of WPS intelligent document data exchange into the RIA framework through the interface, thus realizing the data exchange of heterogeneous system. The interface, connectivity, transformation, meta-data and processes inside the data exchange platform all use the component technology and component library management, which consolidates the knowledge of the services, associations, data, processes, etc., in the real world.

A system and method for the creation of a customized investor document for transmission to the investor. In the case of mutual fund purchases, the customized document includes only those of Part A, Part B, Part A notes, and amendments of the then current simplified prospectus required or desired to be provided. The system and method of the present invention also provide for ancillary documents to be provided together with required or desired documents in a single, customized investor document. The present invention is automated and can be used on demand to produce consolidated, personalized investor documents for a myriad of types of transactions.

A document architecture system includes an intelligent document processing engine that can receive raw data streamed from external data source(s), analyze the raw data to identify triggering events, apply rules to the triggering events identified, break down the raw data accordingly, and generating messages in an internal format to represent the pieces of data without any formatting or layout information. The messages can be augmented with custom metadata and stored as fragments that reference, but that do not physically incorporate, the messages. The stored fragments can be used by the document process engine to intelligently render documents and versions thereof. Some embodiments store only unique fragments, resulting in a significant reduction in storage requirements and an extremely efficient way of processing huge amounts of data (e.g., millions of documents) for document production. The messages and fragments are in internal formats under control of the document architecture system.

The invention discloses an intelligent-document-platform-based multi-channel information acquisition and exchange method. The intelligent document platform comprises a server and a database, wherein various application services are deployed on the server; an application program is installed on a variety of terminal equipment which serve as information acquisition channels; the application services communicate with the application program which is distributed on the terminal equipment by calling a unified interface; and the interface is an interface of an application program interface (API) function, which is irrelevant to the terminal equipment. By the multi-channel information acquisition and exchange method, a public data processing center is established for different acquisition channels according to different terminal equipment and acquisition environments; therefore, the information processing and converting capacity is improved. The information is acquired through the method, the information acquisition and exchange time can be greatly shortened, the information flow is accelerated, and the information acquiring and processing period is reduced.

A method of producing a document for a customer at a point-of-need includes selecting an intelligent template for the document from the point-of-need, merging data of the customer with the intelligent template for the document to create an intelligent document, and producing the document for the customer at the point-of-need based on the intelligent document.

A method, apparatus, and system, for scanning a first portion of a data to generate a second portion of data is provided. A control parameter relating to a level of detail associated with filtering a first portion of data is received. The filtering of the first portion of data is performed based upon the control parameter. The filtering of the first portion of data includes a rule-based filtering, a context-based filtering, a statistical-based filtering, or a semantic-based filtering. Performing the filtering provides for a reduction of a portion of the first portion of data. A second portion of data that is smaller than the first portion of data is provided based upon the filtering of the first portion of data.

The invention discloses a custom clearance robot based on an intelligent identification technology. The custom clearance robot comprises an original document receiving module, an intelligent documentgeneration module, an intelligent document verification module and an intelligent interaction docking module, wherein the original document receiving module is responsible for receiving pictures of original custom declaration documents; the intelligent document generation module is responsible for converting content in the pictures of the original custom declaration documents into a text format, and generating the identified text content into electronic file custom declaration documents; the intelligent document verification module is responsible for data verification; the intelligent interaction docking module is responsible for uploading the electronic file custom declaration documents verified by means of the intelligent document verification module to a customs supervision system, andreceiving feedback from the customs supervision system. The custom clearance robot adopts the technologies of intelligent identification of documents, custom declaration intelligent document making, EDI communication and the like, so as to improve the efficiency and accuracy of customs declaration document making, and reduce the subsequent loss caused by errors of document making.

The invention discloses an intelligent document engine technology for generating dynamic complicated tables on the basis of Word 2007/Open XML. According to the technology, a template of a Word document is customized by an editor compatible with the XML format and stored into a template library, the customized template and a dynamic data injector jointly inject external business data into a template engine compatible with Freemarker after the template is processed by a dynamic complicated table preprocessor, and finally, a Word document containing the dynamic complicated tables is generated by a late data processor. The intelligent document engine technology has the benefits as follows: the template is customized by the editor compatible with the XML format, the template injects the external business data into the template engine compatible with Freemarker after the template is processed by the dynamic complicated table preprocessor, and finally, the Word document is generated by the late data processor. The method can effectively and rapidly process dynamically changing complicated tables.

The invention relates to a novel geographic computing mode. The computing mode comprises an intelligent document system, a geographic model computing control system and a background interpretation system. The intelligent document system adopts a natural language to describe a calculation task, an evaluation model and a calculation process through a WORD document; the geographic model calculation control system acquires a task name and drives the background interpretation service system; and the background interpretation service system is used for interpreting and executing the WORD document inthe intelligent document system and outputting an execution result. In a traditional geographic computing mode, a technical document only guides a technician to operate, and a computing result completely depends on the level of the technician, but under the novel geographic computing mode, the technical document is intelligentized through the DAS technology, the content of the intelligentized technical document is directly driven by the system, the processing flow of each evaluation index is executed, the evaluation process is automatically recorded, and the flexibility is very high.

The invention discloses an intelligent document editing system comprising: a text editing module configured to provide a text editing interface and a text editing functional module for a user, a text selecting module configured to provide a box or a control for selecting text for a user, a search field generating module configured to generate a search formula for all similar fields and a search formula for the same text field according to the text selected by the user, a searching module configured to searching for fields in the text editing interface of the text editing module or an interface selected by the user according to the search formulas generated by the search field generating module, a replacing module configured to replace all fields obtained by the searching modules with fields with shading and replace the fields with shading with the original fields according to an operation of the user after the user performs a selection operation, and a control inserting module configured to insert a confirming control and a canceling control to the borders of the replaced fields when the replacing module replaces all the obtained modules. The intelligent document editing system can assist a user to check a document, and is convenient and practical.

The invention discloses a portable intelligent document image collecting system based on computer vision. The system comprises a document image collecting terminal and an image data comprehensive processing terminal. The document image collecting terminal comprises a portable foldable imager, an image pre-processing module, an imaging parameter adjustment response module and a data transmission management module. The data transmission management module is used for transmitting data to a host, wherein the data are collected through the imager and are pre-processed. The image data comprehensive processing terminal comprises an analysis processing layer which comprises a vision development base, a quick edge detection module, a Hough transform detection module, an image geometrical information analyzing module, an intelligent scene setting module, an automatic excerpt rectification module, an intelligent continuously-shooting module and an image storage module. The invention further provides a portable intelligent document image collecting method based on the computer vision. The system and method is high in imaging speed, small in occupied space and high in imaging quality.

The invention specifically discloses an intelligent unmanned intelligent file data transporting and selling vehicle and a sharing system, At least a vehicle chassis and a vehicle body are include in that truck, A plurality of warehouses for storing documents and materials are arranged on the vehicle body, the warehouse is provided with multi-layer document shelves, Used to place files neatly, A warehouse or warehouses in which one or more of a plurality of warehouses is provided as a safe deposit box function, Set multiple safety locks, ensure the safety of valuables, state identification of that article is also set, monitoring device, the warehouse sets up the corresponding moisture-proof according to the category, Structural design of anti-theft, the warehouse is detachably mounted separately from the vehicle body, to facilitate the replacement of the type of article being transported, The warehouse is provided with a fixed device or the structural warehouse is provided with a waterproof shell, and the data exchange between the mobile device and the intelligent terminal and between the cloud servers can realize the use of the mobile device and the intelligent terminal as a mobilearticle sales vehicle in addition to the transportation and circulation of the articles, thus creating a new business mode in which the sales and the logistics are combined and intercommunicated witheach other.

The invention discloses an EMD (empirical mode decomposition)-based intelligent document image block detection method. The method includes: subjecting a document image to grey level transformation; calculating an average, a variance and a horizontal projective histogram of a document gray level image; subjecting the histogram to EMD decomposition, and taking a summation result of a last eigenmode modular function component and a residual error as a trend line of the histogram; calculating x-coordinates of intersections between the trend line and the histogram, and calculating spacing distances of the x-coordinates; carrying out image subblock segmentation according to the spacing distances, and calculating an average and a variance of each image subblock; judging whether the image subblocks are background or not according to the average and the variance of the document gray level image; subjecting the histogram to EMD decomposition, and taking a summation result of a last and the averages and the variances of the image subblocks, and processing correspondingly according to judgment results. The method is not only applicable to file images degraded by complicated imaging environments but small in calculated amount and applicable to portable devices. In addition, the method is widely applicable to the field of file image detection.