Abstract: Systems and methods for training machine learning models based on domain constraints are disclosed. An example method includes receiving a plurality of images, each image associated with a cluster of a plurality of clusters, the plurality of clusters representing an output of a second machine learning model, assigning a label to each cluster of the plurality of clusters based at least in part on a plurality of constraints, identifying, based at least in part on the plurality of constraints, a first label mismatch for a first image, the first label mismatch indicating that the first image belongs to a first cluster but should be assigned to a second cluster different from the first cluster, reassigning the first image to the second cluster, and training the first machine learning model, based on the labeled clusters of the plurality of clusters, to predict labels associated with subsequently received image data.

Abstract: A method implements hybrid artificial intelligence generated actionable recommendations. The method includes processing an event to identify an action of an event action set. The event includes an event value. The method further includes processing the event action set to generate an objective value, corresponding to the action, and a probability, corresponding to the action, and to form a model action set from the event action set. The method further includes filtering the model action set using action rule data and rule user data to generate a filtered action set. The method further includes processing, using the objective value and the probability, the filtered action set with an optimization controller to generate suggested action sets from which a selected action set is selected. The selected action set corresponds to a combined action value that satisfies the event value.

Abstract: A method and system to learn new forms to be incorporated into an electronic document preparation system, or to learn the behavior of existing systems, receive form data related to a new form having a plurality of data fields that expect data values based on specific functions. The method and system gather training set data including previously filled forms having completed data fields corresponding to the data fields of the new form. The method and system include multiple analysis modules that each generate candidate functions for providing data values for the data fields of the new form. The method and system evaluate the candidate functions from each analysis technique and select the candidate functions that are most accurate based on comparisons with the training set data.

Abstract: A computer-implemented system and method for predicting rule-based compliance scenarios to implement rule-based topic determinations. A server computing device generates a compliance scenario prediction model by training a machine learning model for a topic with historical user data and cohort labels created by analyzing the scenarios in a completeness graph to predict a set of scenario cohorts that constitute a set of most probable compliance scenarios. The server computing device executes the scenario prediction model to process a user profile including data features associated with the topic to predict a scenario cohort and a compliance scenario corresponding to the predicted cohort for the user. The server computing device automatically infers one or more personalized responses to at least one question of the respective decision node based on the predicted compliance scenario.

Abstract: A method and system to learn new forms to be incorporated into an electronic document preparation system, or to learn the behavior of existing systems, receive form data related to a new form having a plurality of data fields that expect data values based on specific functions. The method and system gather training set data including previously filled forms having completed data fields corresponding to the data fields of the new form. The method and system include multiple analysis modules that each generate candidate functions for providing data values for the data fields of the new form. The method and system evaluate the candidate functions from each analysis technique and select the candidate functions that are most accurate based on comparisons with the training set data.

Abstract: A method and system to learn new forms to be incorporated into an electronic document preparation system, or to learn the behavior of existing systems, receive form data related to a new form having a plurality of data fields that expect data values based on specific functions. The method and system gather training set data including previously filled forms having completed data fields corresponding to the data fields of the new form. The method and system include multiple analysis modules that each generate candidate functions for providing data values for the data fields of the new form. The method and system evaluate the candidate functions from each analysis technique and select the candidate functions that are most accurate based on comparisons with the training set data.

Abstract: The disclosed embodiments provide a system that processes data. During operation, the system obtains a communication associated with a document and extracts data associated with the document from the communication. Next, the system uses the extracted data from the communication and document data from the document to build a context associated with the document. The system then uses the context to facilitate use of the document by a user associated with the communication.

Abstract: A method and system generates sufficient sample data sets for efficiently and accurately testing a new calculation for preparing a portion of an electronic document for users of an electronic document preparation system. The method and system prepares the new calculation and gathers historical user data related to previously prepared electronic documents for a large number of historical users. The method and system generates a representative value for each historical user data, based on the sections of a previous version of electronic document preparation software which were executed for each historical user in preparing electronic documents for the historical users. The method and system groups the historical users based on the hash values which indicates the historical user's behavior in the software. The groups are then sampled by selecting a small number of historical users from each group.

Abstract: The disclosed embodiments provide a system that processes data. One example embodiment is a computer-implemented method for processing data. The computer-implemented method includes obtaining text from a document associated with a user, wherein the document was generated based on a template and, with the obtained text intact, applying a set of rules to each term in the obtained text to determine a broad category of a plurality of terms associated with the term. The computer-implemented method further includes applying an additional set of rules to refine the broad category associated with the term to a refined category of fewer terms based on a location in the document of at least one term in the broad category of the plurality of terms, extracting a term from the obtained text using template-independent code developed to process documents generated based on a plurality of templates and enabling use of the term with an application.

Abstract: The disclosed embodiments provide a system that processes data. During operation, the system obtains text from a document associated with a user. Next, the system applies a set of rules to each word in the text to determine a context associated with the word. The system then extracts data associated with the context from the text. Finally, the system enables use of the data with one or more applications without requiring manual input of the data into the one or more applications.

Abstract: A system generates structured compliance form data based on a compliance form having a plurality of data fields. The system includes multiple parsing modules each configured to generate respective parsed form data by analyzing compliance form data related to the compliance form with respective parsing processes. The system includes a combiner module configured to combine the various parsed formed data into combined parsed form data.

Abstract: A method and system to learn new forms to be incorporated into an electronic document preparation system, or to learn the behavior of existing systems, receive form data related to a new form having a plurality of data fields that expect data values based on specific functions. The method and system gather training set data including previously filled forms having completed data fields corresponding to the data fields of the new form. The method and system include multiple analysis modules that each generate candidate functions for providing data values for the data fields of the new form. The method and system evaluate the candidate functions from each analysis technique and select the candidate functions that are most accurate based on comparisons with the training set data.

Abstract: A computer-implemented method for securely receiving user data includes a computer associating a marker with a sensitive data field in a form. The method also includes the computer using the marker to facilitate secure entry of user data corresponding to the sensitive data field. The method further includes the computer entering the user data in the sensitive data field in the form. The marker is configured to refer to the sensitive data field without revealing additional information regarding the sensitive data field.

Abstract: Document processing utilizing extraneous highlight added to the document. Sections or fields of a document including data utilized for document processing are marked or highlighted for processing. For example, a paper or printed document may be manually highlighted by a highlighter pen, or the highlight may be computer generated. An image of the highlighted bill is acquired. Highlighted sections within the image are identified, and bill data within the highlighted fields is extracted and utilized for bill processing.

Abstract: User weighted data indicating acceptance of a given data extraction template and weighted data indicating the number of data fields that the data extraction template can extract accurately is used to calculate data extraction template ranking, or a weighted ranking score, to be associated with the data extraction template. Then the data extraction template having the highest data extraction template ranking score is used in a first attempt to extract data from a source documents of the source document type associated with the data extraction templates. As more data extraction templates associated with a given source document type are received, the data extraction templates having the lowest data extraction template ranking scores are detected/eliminated.

Abstract: User acceptance of a given data extraction template and the number of data fields that the data extraction template can extract accurately is used to calculate data extraction template ranking, or a ranking score, to be associated with the data extraction template. Then the data extraction template having the highest data extraction template ranking score is used in a first attempt to extract data from a source documents of the source document type associated with the data extraction templates. As more data extraction templates associated with a given source document type are received, data extraction template ranking scores are updated/modified, and, in one example, the data extraction templates having the lowest data extraction template ranking scores are detected/eliminated.

Abstract: An optical image of a source document is captured. Two or more source document image test regions are then defined/determined. An optical image scan is performed on each source document image test region to determine if there are identifiable alpha-numeric characters or symbols present. If one or more of the source document image test regions are determined not to contain identifiable alpha-numeric characters, the captured optical image of the source document is determined to be of insufficient quality to identify and extract individual characters and symbols and it is recommended that optical images of source documents determined to be of insufficient quality to identify and extract individual characters and symbols be re-captured using an image capture device.

Abstract: The disclosed embodiments provide a system that processes data. During operation, the system obtains a communication associated with a document and extracts data associated with the document from the communication. Next, the system uses the extracted data from the communication and document data from the document to build a context associated with the document. The system then uses the context to facilitate use of the document by a user associated with the communication.

Abstract: Document processing utilizing extraneous highlight added to the document. Sections or fields of a document including data utilized for document processing are marked or highlighted for processing. For example, a paper or printed document may be manually highlighted by a highlighter pen, or the highlight may be computer generated. An image of the highlighted bill is acquired. Highlighted sections within the image are identified, and bill data within the highlighted fields is extracted and utilized for bill processing.

Abstract: User acceptance of a given data extraction template and the number of data fields that the data extraction template can extract accurately is used to calculate data extraction template ranking, or a ranking score, to be associated with the data extraction template. Then the data extraction template having the highest data extraction template ranking score is used in a first attempt to extract data from a source documents of the source document type associated with the data extraction templates. As more data extraction templates associated with a given source document type are received, data extraction template ranking scores are updated/modified, and, in one example, the data extraction templates having the lowest data extraction template ranking scores are detected/eliminated.