Intuit, Inc.

Oracle America, Inc.

Cynthia Joann Osmon

Roger Charles Meike

Sricharan Kallur Palli Kumar

Gregory Kenneth Coulombe

Alexander S Ran

Pavlo Malynin

Sricharan Kallur Kumar

William Taylor Laaser

Komal Bhatia

Christopher Z Lesner

Jason Michael Webb

Shreeshankar Chatterjee

Conrad De Peuter

Daniel Leontin Moise

Wolfgang Paulus

Jacob Nathaniel Huffman

Vijay Thomas

James B Clarke

Manav Kohli

Nicholas Roberts

Tracy Fung

Mithun Madadevan

Diane L Weiss

Mithun Mahadevan

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

A method includes obtaining a help file including steps for a task and generating a knowledge graph including instructions corresponding to the steps. The method further includes extracting, from a user input of a user, an intent to complete the task. Responsive to extracting the intent to complete the task, obtaining the knowledge graph is obtained. Using the knowledge graph, an instruction of the knowledge graph is presented to perform an action in a workflow to complete the task.

Graphical user interface for conversational task completion

Certain aspects of the present disclosure provide techniques for generating a replacement sentence with the same or similar meaning but a different sentiment than an input sentence. The method generally includes receiving a request for a replacement sentence and iteratively determining a next word of the replacement sentence word-by-word based on an input sentence. Iteratively determining the next word generally includes evaluating a set of words of the input sentence using a language model configured to output candidate sentences and evaluating the candidate sentences using a sentiment model configured to output sentiment scores for the candidates sentences. Iteratively determining the next word further includes calculating convex combinations for the candidate sentences and selecting an ending word of one of the candidate sentences as the next word of the replacement sentence. The method further includes transmitting the replacement sentence in response to the request for the replacement sentence.

Generating replacement sentences for a particular sentiment

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

A method involves scanning a symbol presented on a point of sale (POS) system including a POS processor; decoding the symbol to obtain purchase data and bidirectional connection data, where the bidirectional connection data describes a bidirectional connection; generating payment data using the purchase data; establishing the bidirectional connection with the POS system; sending the payment data to the POS system over the bidirectional connection; and receiving payment confirmation from the POS system over the bidirectional connection in response to the sending the payment data.

System and method to enable payment using mark generation and mobile device

A non-transitory computer readable medium including instructions that, when executed by a processor, perform a method involving: receiving, by a point of sale (POS) system, purchase data for a customer; generating bidirectional connection data for the customer, where the bidirectional connection data describes a bidirectional connection; encoding a symbol with the purchase data and the bidirectional connection data; presenting the symbol to the customer; enabling the bidirectional connection in response to a connection request from the customer; receiving payment data from the customer over the bidirectional connection; comparing the payment data to the purchase data; and sending a payment confirmation to the customer over the bidirectional connection in response to a determination that the payment data satisfies the purchase data.

A personalized financial podcast generation system, the system includes a user data module configured to acquire user data associated with a user and analyze the user data to identify a keyword associated with a financial topic of interest to the user. The system also includes a keyword analyzer configured to calculate a weight of the keyword. The system further includes a content analyzer configured to identify financial media content based on the keyword and the weight. Moreover, the system includes a summarizer configured to identify a relevant sentence in the financial media content. In addition, the system includes a speech processor configured to synthesize speech based on the relevant sentence.

Methods, systems and computer program products for generating personalized financial podcasts

A technique for authenticating a user is described. During this authentication technique, an electronic device (such as a cellular telephone) captures multiple images of the user while the user moves the electronic device in a pre-defined manner (for example, along a path in 3-dimensional space), and determines positions of the electronic device when the multiple images were captured. Then, the electronic device compares the images at the positions with corresponding pre-existing images of the user captured at different points of view. If the comparisons achieve a match condition, the electronic device authenticates the user. In this way, the authentication technique may be used to prevent successful replay attacks.

Mitigating replay attacks using multiple-image authentication

An embedded device includes a web interface configured to receive a request for an electronic product information (EPID) report, and send the request to a request handling service. The embedded device further includes the request handling service, configured to deploy one or more event handling components based on the request. The embedded device further includes the one or more event handling components configured to generate an EPID event cycle based on an EPID read cycle, according to an event cycle boundary condition, generate the EPID report based on the EPID event cycle, and transmit the EPID report to a client. The embedded device further includes a reader adapter configured to obtain the EPID read cycle, and transmit the EPID read cycle to the one or more event handling components.

Growing community of inventors

Sunnyvale, CA, United States of America

Cynthia Joann Osmon