Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: A method that includes obtaining, for a task, a help file including steps, and generating, from the help file, a knowledge graph for the task, the knowledge graph includes nodes connected by directed edges. Generating the knowledge graph includes, for a step of the set of steps obtaining, from the step, a first step attribute value defining an action type of an action specified by the step, generating a natural language instruction based on the action type and a second step attribute value, in the step, corresponding to a parameter of the action, and storing the natural language instruction in a node. The method further includes storing the knowledge graph.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.