Abstract: A method including receiving a source file containing a plurality of documents which, to a computer, initially are indistinguishable from each other. A first classification stage is applied to the source file using a convolutional neural network image classification to identify source documents in the multitude of documents and to produce a partially parsed file having a multitude of identified source documents. The partially parsed file includes sub-images corresponding to the plurality of identified source documents. A second classification stage, including a natural language processing artificial intelligence, is applied to sets of text in bounding boxes of the sub-images, to classify each of the multitude of identified source documents as a corresponding sub-type of document. Each of the sets of text corresponding to one of the sub-images. A parsed file having a multitude of identified sub-types of documents is produced. The parsed file is further computer processed.

Abstract: A method including receiving a source file containing a plurality of documents which, to a computer, initially are indistinguishable from each other. A first classification stage is applied to the source file using a convolutional neural network image classification to identify source documents in the multitude of documents and to produce a partially parsed file having a multitude of identified source documents. The partially parsed file includes sub-images corresponding to the plurality of identified source documents. A second classification stage, including a natural language processing artificial intelligence, is applied to sets of text in bounding boxes of the sub-images, to classify each of the multitude of identified source documents as a corresponding sub-type of document. Each of the sets of text corresponding to one of the sub-images. A parsed file having a multitude of identified sub-types of documents is produced. The parsed file is further computer processed.

Abstract: The disclosed embodiments provide a system that facilitates interaction between a client and a web application. During operation, the system identifies a request that lacks a session identifier from the client to the web application. Next, the system obtains a client identifier associated with the client from the request. If a cached session identifier is found for the client identifier, the system adds the cached session identifier to the request. Finally, the system forwards the request to the web application.

Abstract: The invention relates to a method for tracking time using a mobile computing device. The method steps include providing a first event manager on the mobile computing device for managing event records, wherein each event record is synchronized via an exchange server to a corresponding event record managed by a second event manager on a client machine, generating a time tracking record based on input from a user of the mobile computing device, wherein the time tracking record is added to the event records as a surrogate event record, transmitting the surrogate event record via the exchange server to the second event manager operatively coupled to a client application on the client machine, extracting time entry information from the surrogate event record using the client application for tracking time, and generating estimated time entry information automatically based on the event record.

Abstract: The invention relates to a method for tracking time using a mobile computing device.