Abstract: Illustrative embodiments improve upon prior machine learning techniques by introducing an additional classification layer that mimics human visual pattern recognition. Building upon classification passes that extract contextual information, illustrative embodiments look for hints of high-level semantic categorization that manifest as visual artifacts in the document, such as font family, font weight, text color, text justification, white space, or CSS class name. An improved lightweight markup language enables display of machine-categorized tokens on a screen for human correction, thereby providing ground truths for further machine classification.

Abstract: A system and method for automatically submitting an online order from a customer to a restaurant. Input data and customer data is used by an order engine to select a deployment platform, such as social media networks, search engines, mobile applications, and related websites, for a user interface. The order engine provides a unique identifier for each restaurant. The unique identifier can be used by third parties, such as online content providers, to return the menu for the restaurant included in the third party content. The user interface automatically populates the restaurant's menu options and business data, allowing the customer to build an order. The order engine submits the order to the restaurant via a non-verbal communication platform.

Abstract: A system and method for document classification are presented. An input document is received (e.g., by at least one server communicatively coupled to a network). A plurality of features are identified in the input document. The plurality of features include sequences of text extracted from the input document. A feature vector of the input document is generated based upon the sequences of text, and the feature vector of the input document is compared to each of a plurality of signature vectors to determine a primary type of the input document. The primary type of the input document is stored into a storage system in communication with the at least one server.

Abstract: A method for performing a market analysis for a first online business is disclosed. Market information for a plurality of online businesses may be collected. A user may request a market analysis for the first online business. Market information for the first online business may also be collected. The marketing information for the plurality of online businesses and the first online business may be canonicalized to make comparisons easier. One or more online businesses in the plurality of online businesses may be selected as being similar to the first online business. The marketing information for the first online business may be compared to the marketing information of the similar one or more online businesses. The results of the comparison may be displayed to the user. The user may request modifications to the first online business. The first online business may be modified and the modified online business may be published.

Abstract: A system and method for automatically assigning marketing allocations, including advertisements and coupons, for a business to marketing channels. An investment engine and recommendation engine uses input data to assign marketing allocations to marketing channels. Consumer activity is generated that produces corresponding output data. The investment engine calculates a return-on-investment (ROI) metric, and the recommendation engine generates a report related to the input and output data. The input data, marketing allocations or channels are adjusted to optimize the ROI metric and recommend marketing campaign strategies. The system also automatically determines which keywords the business should assign their marketing allocations to when a consumer utilizes similar keywords on a search engine. Targeted keywords are determined by applying budget weights to keywords related to the business and monitoring output data, such as a click through rate of the marketing allocations.

Abstract: A system and method for automatically submitting an online order from a customer to a restaurant. Input data and customer data is used by an order engine to select a deployment platform, such as social media networks, search engines, mobile applications, and related websites, for a user interface. The user interface automatically populates the restaurant's menu options and business data, allowing the customer to build an order. The order engine submits the order to the restaurant via a non-verbal communication platform. An automated confirmation call is generated to the restaurant confirming receipt of the order. From the confirmation call the restaurant may choose to repeat the message, accept the order, connect to the customer, connect to the service provider, decline the order, or opt-out. The order engine allows the restaurant to monitor online orders and to enroll in the above services for subsequent online orders.

Abstract: A system and method for automatically submitting an online order from a customer to a restaurant. Input data and customer data is used by an order engine to select a deployment platform, such as social media networks, search engines, mobile applications, and related websites, for a user interface. The user interface automatically populates the restaurant's menu options and business data, allowing the customer to build an order. The order engine submits the order to the restaurant via a non-verbal communication platform. An automated confirmation call is generated to the restaurant confirming receipt of the order. From the confirmation call the restaurant may choose to repeat the message, accept the order, connect to the customer, connect to the service provider, decline the order, or opt-out. The order engine allows the restaurant to monitor online orders and to enroll in the above services for subsequent online orders.

Abstract: A system and method for automatically assigning marketing allocations, including advertisements and coupons, for a business to marketing channels. An investment engine and recommendation engine uses input data to assign marketing allocations to marketing channels. Consumer activity is generated that produces corresponding output data. The investment engine calculates a return-on-investment (ROI) metric, and the recommendation engine generates a report related to the input and output data. The input data, marketing allocations or channels are adjusted to optimize the ROI metric and recommend marketing campaign strategies. The system also automatically determines which keywords the business should assign their marketing allocations to when a consumer utilizes similar keywords on a search engine. Targeted keywords are determined by applying budget weights to keywords related to the business and monitoring output data, such as a click through rate of the marketing allocations.

Abstract: A system and method for automatically determining an amount of review a crowd-sourcing task needs after an initial review has been completed by a processing worker. An evaluation metric is automatically assigned to the work performed by the processing worker to determine the appropriate amount of human review required for a particular task. The evaluation metric may be calculated by accessing and evaluating a plurality of transaction categories related, but not limited to, worker characteristics, document characteristics and processing characteristics. Additionally, the evaluation metric may be used to determine compensation of the processing worker and whether a promotion or demotion is necessary. The system is also capable of balancing individual workloads based upon the evaluation metric.

Abstract: Illustrative embodiments improve upon prior machine learning techniques by introducing an additional classification layer that mimics human visual pattern recognition. Building upon classification passes that extract contextual information, illustrative embodiments look for hints of high-level semantic categorization that manifest as visual artifacts in the document, such as font family, font weight, text color, text justification, white space, or CSS class name. An improved lightweight markup language enables display of machine-categorized tokens on a screen for human correction, thereby providing ground truths for further machine classification.

Abstract: Radio signals containing Loran C pulses from stations from a desired chain are amplified, filtered and ensembled averaged in an acquisition memory which is accessible by a controlling microprocessor. By staggering the ensemble averaging of the first four pulses in a station pulse group in time with respect to the last four pulses of the same pulse group, cross correlating the composite pulses formed by averaging the first four and last four pulses of the station pulse group with the help of the microprocessor provides time skew information which is used to adjust the receiver's master clock to align it with the clock of the transmitter. By varying the amount of time stagger, an ever finer resolution adjustment range is achieved. When the staggered averaging cycle times would exceed the time between successive ensemble averaging cycles without stagger, then successive ensemble averaging cycle time is employed for master clock adjustment.