Intuit, Inc.

Gregory Kenneth Coulombe

Roger Charles Meike

Sricharan Kallur Palli Kumar

Cynthia Joann Osmon

Richard J Becker

Pavlo Malynin

Daniel Leontin Moise

Conrad De Peuter

Horace Chan

Kimia Hassanzadeh

Cole MacKenzie

Certain aspects of the present disclosure provide techniques for executing a function in a software application through a conversational user interface based on a knowledge graph associated with the function. An example method generally includes receiving a request to execute a function in a software application through a conversational user interface. A graph definition of the function is retrieved from a knowledge engine. Input is iteratively requested through the conversational user interface for each parameter of the parameters identified in the graph definition of the function based on a traversal of the graph definition of the function. Based on a completeness graph associated with the function, it is determined that the requested inputs corresponding to the parameters identified in the graph definition of the function have been provided through the conversational user interface. The function is executed using the requested inputs as parameters for executing the function.

Conversational user interfaces based on knowledge graphs

Certain aspects of the present disclosure provide techniques for optimizing results generated by functions executed using a rule-based knowledge graph. The method generally includes generating a neural network based on a knowledge graph and inputs for performing a function using the knowledge graph. Inputs for the function are received and used to generate a result of the function. A request to optimize the generated result of the function is received. A loss function is generated for the neural network. Generally, the loss function identifies a desired optimization for the function. Values of parameters in the neural network are adjusted to optimize the generated result based on the generated loss function, and the adjusted values of the parameters in the neural network are output in response to the request to optimize the generated result of the function.

Method and system for optimizing results of a function in a knowledge graph using neural networks

Certain aspects of the present disclosure provide techniques for mapping natural language to stored information. The method generally includes receiving a long-tail query comprising a natural language utterance from a user of an application associated with a set of topics and providing the natural language utterance to a natural language model configured to identify nodes of a knowledge graph. The method further includes, based on output of the natural language model, identifying a node of a knowledge graph associated with the natural language utterance, wherein the output of the natural language model includes a node identifier for the node of the knowledge graph and providing the node identifier to the knowledge engine. The method further includes receiving a response associated with the node of the knowledge graph from the knowledge engine and transmitting the response to the user in response to the long-tail query.

Mapping natural language utterances to nodes in a knowledge graph

Certain aspects of the present disclosure provide techniques for processing natural language utterances in a knowledge graph. An example method generally includes receiving a long-tail query comprising a natural language utterance from a user of an application. Operands and operators are extracted from the natural language utterance using a natural language model. Operands may be mapped to nodes in a knowledge graph, the nodes representing values calculated from data input into the application, and operators may be mapped to operations to be performed on data extracted from the knowledge graph. The functions associated with the operators are executed using data extracted from the nodes in the knowledge graph associated with the operands to generate a query result. The query result is returned as a response to the received long-tail query.

Mapping natural language utterances to operations over a knowledge graph

Aspects of the present disclosure provide techniques for intent matching. Embodiments include receiving input of text by a user via a user interface. Embodiments include determining weights for portions of the text based on a plurality of keywords. Embodiment include generating an embedding of the text. Embodiments include determining an intent of the text by weighting, based on the weights, word mover's distances from the embedding of the text to a known embedding of known text associated with the intent in order to determine a similarity measure between the text and the known text. Embodiments include providing content to the user via the user interface based on the intent.

Enhanced intent matching using keyword-based word mover's distance

Certain aspects of the present disclosure provide techniques for node matching with accuracy by combining statistical methods with a knowledge graph to assist in responding (e.g., providing content) to a user query in a user support system. In order to provide content, a keyword matching algorithm, statistical method (e.g., a trained BERT model), and data retrieval are each implemented to identify node(s) in a knowledge graph with encoded content relevant to the user's query. The implementation of the keyword matching algorithm, statistical method, and data retrieval results in a matching metric score, semantic score, and graph metric data, respectively. Each score associated with a node is combined to generate an overall score that can be used to rank nodes. Once the nodes are ranked, the top ranking nodes are displayed to the user for selection. Based on the selection, content encoded in the node is displayed to the user.

Combining statistical methods with a knowledge graph

The present disclosure relates to simulating the capture of images. In some embodiments, a document and a camera are simulated using a three-dimensional modeling engine. In certain embodiments, a plurality of images are captured of the simulated document from a perspective of the simulated camera, each of the plurality of images being captured under a different set of simulated circumstances within the three-dimensional modeling engine. In some embodiments, a model is trained based at least on the plurality of images which determines at least a first technique for adjusting a set of parameters in a separate image to prepare the separate image for optical character recognition (OCR).

Simulating image capture

The disclosed embodiments provide a system that facilitates geolocation of a user. The system includes a server and an electronic device. First, the server receives a location of the user from an electronic device of the user and determines a window around the location. Next, the server transmits the window and one or more geofences within the window to the electronic device. The electronic device then obtains one or more precision buffers associated with one or more levels of accuracy for detecting the location of the user near the one or more geofences. Finally, the electronic device facilitates use of the one or more geofences by varying a geolocation technique for tracking the location of the user based on the one or more precision buffers.

Adaptive geolocation of users to facilitate use of geofences

The disclosed embodiments provide a system that dynamically updates a geofence of a mobile business. During operation, the system establishes a first location and a first geofence for the mobile business. Next, the system receives a second location of the mobile business different than the first location of the mobile business. The system then generates an updated geofence for the mobile business based on the second location of the mobile business. The system subsequently broadcasts the second location of the mobile business to a set of mobile clients monitoring the mobile business.

Growing community of inventors

Sherwood Park, Canada

Gregory Kenneth Coulombe