Abstract: A method and system uses a probabilistic topic model to identify topics that are relevant search query terms received by a customer support system from a user, according to one embodiment. The probabilistic topic model identifies topics that are relevant to the search query terms at least partially based on the context around the receipt of the search query terms, according to one embodiment. By identifying relevant topics at least partially based on the context around the receipt of the search query terms, a likelihood of inaccurately identifying a relevant topic is reduced, according to one embodiment.

Abstract: Embodiments presented herein provide techniques for inferring the current emotional state of a user based on paralinguistic features derived from audio input from that user. If the emotional state meets triggering conditions, the system provides the user with a prompt which allows the user to connect with a support agent. If the user accepts, the system selects a support agent for the user based on the predicted emotional state and on attributes of the support agent found in an agent profile. The system can also determine a priority level for the user based on the score and based on a profile of the user and determine where to place the user in a queue for the support agent.

Abstract: Techniques are disclosed for adjusting user experience of a software application based on paralinguistic information. One embodiment presented herein includes a computer-implemented method for adjusting a user experience of a software application. The method comprises receiving, at a computing device, an audio stream comprising audio of a user. The method further comprises analyzing the audio stream for paralinguistic information to determine an attribute of the user. The method further comprises identifying content of the audio stream. The method further comprises determining one or more actions based on the content of the audio stream. The method further comprises selecting at least one of the one or more actions based on the attribute of the user.

Abstract: A computer-implemented method of generating rich content webpages from a question and answer (Q&A) library includes providing a topic and one or more seed questions related to the topic. The computing device searches the one or more seed questions against all questions in the Q&A library and identifies questions related to the topic. The computing device clusters the text of the questions related to the topic into a plurality of clusters and then removes substantial duplicates from the plurality of clusters. The computing device generates a rich content webpage by aggregating a question from each cluster onto a single webpage containing the topic.

Abstract: Techniques are disclosed for assisting a support agent based on paralinguistic information determined from a user interacting with a software application. One embodiment presented herein includes a computer-implemented method. The method includes receiving, at a computing device, an audio stream including audio of a user interacting with an application. The method also includes evaluating the audio stream to identify a collection of paralinguistic information present in the audio stream. The paralinguistic information includes a set of descriptors characterizing acoustic aspects of the audio that are distinct from verbal content of the audio. The method further includes determining, from the paralinguistic information, attribute measures associated with the user interacting with the application.

Abstract: A customer self-help system employs artificial intelligence to generate personalized self-help content that is responsive to a user query submitted to the customer self-help system, according to one embodiment. The customer self-help system includes a pre-processor that characterizes and categorizes the self-help content into self-help content components, by using one or more content processing algorithms (e.g., a natural language processing algorithm), according to one embodiment. The customer self-help system includes an intent extractor engine that determines characteristics of the user query based on the user query and user profile data, according to one embodiment. The customer self-help system aggregates portions of the self-help content components into a personalized self-help content by matching characteristics of the user query with characteristics of the self-help content, according to one embodiment.

Abstract: A method and system provides personalized search results to users of a data management system. The method and system receives a search query from a user and generate initial search results including a plurality of assistance documents relevant to the query data. The method and system utilizes natural language analysis and machine learning processes to analyze the query data, user attributes data, and the assistance documents in order to generate personalized previews of the assistance documents for the user. The method and system output personalized search results to the user including the personalized previews of the assistance documents.

Abstract: Disclosed methods and systems crowdsource quality assurance testing and error detection for user experience pages of a tax return preparation system, according to one embodiment. Testing and debugging combinations and sequences user experience pages can be time consuming and costly, and crowdsourcing error detection can reduce the length of time typically consumed in detecting all errors in a user experience flow, according to one embodiment. The methods and system include monitoring users' navigation behavior (e.g., system access data) within one or more user experience pages, using predictive models to detect when users are experiencing a potential issue, and providing issue resolution content to both help the users and characterize the potential issue, according to one embodiment. If the potential issue is an error, the methods and systems include requesting more information about the error, to facilitate resolving the error for current and subsequent users, according to one embodiment.

Abstract: The present disclosure includes techniques for selecting a response to an audio stream query. In one embodiment, an application server receives an audio stream query including content spoken by a user interacting with a voice-user interface. The application server determines a set of paralinguistic features from the audio stream query, and estimates at least a first attribute of the user based on the set of paralinguistic features. The application server identifies subject matter corresponding to the spoken content in the audio stream query, and determines two or more query responses corresponding to the identified subject matter. The application server then selects one of the query responses to present to the user based, at least in part, on the attribute of the user estimated from the set of paralinguistic features.

Abstract: A method and system determines a level of popularity of submission content, prior to publicizing the submission content with a question and answer customer support system, to improve user satisfaction with content of the question and answer customer support system, according to one embodiment. The method and system include receiving submission content from a user, and identifying a plurality of attributes of the submission content, according to one embodiment. The method and system include applying at least some of the attributes of the submission content to an analytics model to generate a score that is indicative of a likely level of popularity of the submission content, according to one embodiment. Prior to publicizing the submission content with the question and answer customer support system, the method and system include providing suggestions to the user for altering attributes of the submission content, to affect the score, according to one embodiment.

Abstract: The present disclosure relates to processing support requests, or support queries, in a software application including automated and human interaction-based support systems. An example method generally includes receiving a support request from a client device. A query processor parses the support request to identify one or more characteristics of the support request and identifies a support system to process the support request based at least in part on the identified one or more characteristics of the support request. The query processor instantiates a support session with the identified support system to process the support request.

Abstract: A computer-implemented method of managing questions and answers on a computer-hosted service. The method includes a computing device receiving text based tax question and answer pairings and inputting the tax question and answer pairings into a content model executed by the device and outputting a content score for each tax question and answer pairing based on the model. The content score comprises a number within a range. One end of the range corresponds to product content and another end of the range corresponds to general tax content. The device outputs an answer quality score for the tax question and answer pairings based at least in part on the content score and votes assigned to each respective question and answer pair, wherein votes comprises up votes and down votes. The device may generate a FAQ list stored in a database based at least in part on the answer quality score.

Abstract: Reduction in latency between question submissions and response submissions in a question and answer based customer support system is reduced by facilitating the use of mobile devices by customer support personnel to submit question responses. The answerability of a question from a mobile device is predicted by pre-submission parsing and analysis of the attributes of the question before the answer is generated. Questions being entered into the question and answer based customer support system that are conveniently answerable from a mobile device are routed to a mobile question and answer queue that enables mobile device users to review and respond to the mobile device answerable questions. The user interface for the mobile device is configured/customized based on the attributes/content/analysis of the question to enable customer support personnel to more quickly respond to question submissions.

Abstract: Embodiments presented herein provide techniques for inferring the current emotional state of a user based on paralinguistic features derived from audio input from that user. If the emotional state meets triggering conditions, the system provides the user with a prompt which allows the user to connect with a support agent. If the user accepts, the system selects a support agent for the user based on the predicted emotional state and on attributes of the support agent found in an agent profile. The system can also determine a priority level for the user based on the score and based on a profile of the user and determine where to place the user in a queue for the support agent.

Abstract: Techniques are disclosed for adjusting a ranking of information content of a software application based on feedback from a user. One embodiment presented herein includes a method comprising receiving, at a computing device, an audio stream comprising audio of the user, the audio being indicative of feedback related to information content. The method further comprises analyzing the audio stream for paralinguistic information to determine an attribute of the user. The method further comprises adjusting a ranking of the information content based on at least one of the feedback and additional feedback and the determined attribute of the user.

Abstract: A question and answer based customer support system is provided through which users submit question data representing questions to be answered using support resources. Low quality and/or high quality question formats are defined and questions having a low quality question format are labeled improperly formatted questions, while questions having a high quality question format are labeled properly formatted questions. Received question data is analyzed to determine if the question data represents an improperly or properly formatted question before allocating support resources to generating an answer. If, a determination is made that the question data represents an improperly formatted question, corrective actions are taken before allocating support resources to generating an answer. If a determination is made that the question data represents a properly formatted question, the question represented by the question data is allocated support resources to generate an answer on a priority basis.

Abstract: Techniques are disclosed for determining application experience of a user based on paralinguistic information determined for the user. One embodiment presented herein includes a computer-implemented method, which includes receiving, at a computing device, one or more audio streams. Each audio stream includes audio from a user interacting with at least one page of an application. The computer-implemented method also includes generating paralinguistic information from at least one of the audio streams. The paralinguistic information characterizes acoustic aspects of the audio stream that are distinct from verbal content of the audio stream.

Abstract: A method for tax preparation, including: obtaining a tax preparation ontology and a set of electronic tax documents; mining, by a computer processor, the set of electronic tax documents to identify relevant tax data based on the tax preparation ontology; constructing, by the computer processor, a semantic graph including the relevant tax data in a set of triples; receiving a semantic query language query; querying the semantic graph based on the semantic language query to obtain a result set; and returning the result set to a tax preparation application, where the tax preparation application displays at least a portion of the result set to a user in response to a help request.

Abstract: The described embodiments relate to techniques for facilitating text inputs with long-tail keywords from a user in a social question and answer (Q&A) application. During operation, the system receives an input from the user. The system then applies a predictive model to determine a predicted business outcome for the received input from the user. Next, the system renders a user interface (UI) for subsequent user interaction with the social Q&A application, based on the predicted business outcome. Finally, the system displays the rendered UI to the user.

Abstract: Techniques are disclosed for adjusting a ranking of information content of a software application based on feedback from a user. One embodiment presented herein includes a method comprising receiving, at a computing device, an audio stream comprising audio of the user, the audio being indicative of feedback related to information content. The method further comprises analyzing the audio stream for paralinguistic information to determine an attribute of the user. The method further comprises adjusting a ranking of the information content based on at least one of the feedback and additional feedback and the determined attribute of the user.