The image processing apparatus has an obtaining unit configured to obtain a scanned image, a first determination unit configured to determine a document type of a document format similar to a document format of the scanned image based on information on each registered document type, an extraction unit configured to extract a character string corresponding to a predetermined item, a second determination unit configured to use a different method for determining whether the document format indicated by the scanned image is similar to the document format of the document type determined by the first determination unit in a case where a user modifies the extracted character string, and a display control unit configured to display a screen prompting the user to perform overwriting in a case where the second determination unit determines that the document format is similar.

The image processing apparatus has an obtaining unit configured to obtain a scanned image, a first determination unit configured to determine a document type of a document format similar to a document format of the scanned image based on information on each registered document type, an extraction unit configured to extract a character string corresponding to a predetermined item, a second determination unit configured to use a different method for determining whether the document format indicated by the scanned image is similar to the document format of the document type determined by the first determination unit in a case where a user modifies the extracted character string, and a display control unit configured to display a screen prompting the user to perform overwriting in a case where the second determination unit determines that the document format is similar.

Computer implemented methods and systems are disclosed for automatically identifying declined services from service records by extracting information from fields in the service record, analyzing the extracted information to identify issues found and issues addressed in the service record, comparing the issues found and issues addressed to identify issues found in the service record unrelated to the issues addressed, and inferring the issues found unrelated to the issues addressed to be declined services.

Random access to any arbitrary object stored in a database from a displayed virtual object image corresponding to an object wherein some properties of the object are displayed in the virtual object image is provided through manipulation of a drag icon to cause, in sequence, display of a ghost template listing types of properties for which data is stored in a database, select a property type from the ghost template, display all instances of the selected property type and display another virtual object image containing a selected instance of the property type and including other properties of a corresponding object. All properties of the object to which the resulting virtual object image corresponds can be determined from further manipulation of the drag icon to display another ghost template.

A bipartite application implements a table auto-completion (TAC) algorithm on the client side and the server side. A client module runs a local model of the TAC algorithm on a user device and a server module runs a global model of the TAC algorithm on a server machine. The local model is continuously adapted through on-the-fly training, with as few as a negative example, to perform TAC on the client side, one document at a time. Knowledge thus learned by the local model is used to improve the global model on the server side. The global model can be utilized to automatically and intelligently extract table information from a large number of documents with significantly improved accuracy, requiring minimal human intervention even on complex tables.

A bipartite application implements a table auto-completion (TAC) algorithm on the client side and the server side. A client module runs a local model of the TAC algorithm on a user device and a server module runs a global model of the TAC algorithm on a server machine. The local model is continuously adapted through on-the-fly training, with as few as a negative example, to perform TAC on the client side, one document at a time. Knowledge thus learned by the local model is used to improve the global model on the server side. The global model can be utilized to automatically and intelligently extract table information from a large number of documents with significantly improved accuracy, requiring minimal human intervention even on complex tables.

Described herein is a method and system for generating product descriptions of vehicles. A request for a customized vehicle publication is received, which includes at least a vehicle type, a set of standard features, and a set of optional features. One or more story templates associated with the vehicle type input are automatically received, where each of the story templates have populatable fields corresponding to the vehicle type, the set of standard features, and the set of optional features. The story templates have a theme correlated to usage of a vehicle having the vehicle type. A selection of a story template is received, and the vehicle characteristics are automatically populated. The completed vehicle product description is then provided.

Described herein is a method and system for generating product descriptions of vehicles. A request for a customized vehicle publication is received, which includes at least a vehicle type, a set of standard features, and a set of optional features. One or more story templates associated with the vehicle type input are automatically received, where each of the story templates have populatable fields corresponding to the vehicle type, the set of standard features, and the set of optional features. The story templates have a theme correlated to usage of a vehicle having the vehicle type. A selection of a story template is received, and the vehicle characteristics are automatically populated. The completed vehicle product description is then provided.

An advocacy system uses trained machine learning models to create messages that are sent to advocates or policymakers to achieve desired outcomes for an organization. Desired outcomes can include, for example: an advocate sending a message to a policymaker or legislative representative advocating in favor or the organization's position on an issue; a policymaker acting or voting in favor of the organization's position on an issue; or an advocate making a financial contribution to the organization. The machine learning models can be configured to select possible message characteristics or features that the system will include/use in creating/sending messages to/for individual senders and recipients. The machine learning models can be trained based on message characteristics, personal profile characteristics of senders/recipients, and outcomes from previously sent messages. Personal profile characteristics of senders/recipients can indicate correlations between certain message characteristics and certain outcomes of sending messages.

A method includes receiving a designation of one or more first items that are to be included in a new table from a user, specifying, based on metadata related to second items included in each of a plurality of existing tables, an existing table from among the plurality of existing tables, the existing table including at least one of the designated one or more first items in the second items, specifying, based on other metadata related to an input item and an output item accompanied with execution of each of a plurality of programs, a program from among the plurality of programs, the program causing the designated one or more first items to be output as the output item when one of the second items included in the specified existing table is input as the input item, and outputting the specified existing table and the specified program.