Abstract: Aspect pre-selection techniques using machine learning are described. In one example, an artificial assistant system is configured to implement a chat bot. A user then engages in a first natural-language conversation. As part of this first natural-language conversation, a communication is generated by the chat bot to prompt the user to specify an aspect of a category that is a subject of a first natural-language conversation and user data is received in response. Data that describes this first natural-language conversation is used to train a model using machine learning. Data is then received by the chat bot as part of a second natural-language conversation. This data, from the second natural-language conversation, is processed using the model as part of machine learning to generate the second search query to include the aspect of the category automatically and without user intervention.

Abstract: Aspect pre-selection techniques using machine learning are described. In one example, an artificial assistant system is configured to implement a chat bot. A user then engages in a first natural-language conversation. As part of this first natural-language conversation, a communication is generated by the chat bot to prompt the user to specify an aspect of a category that is a subject of a first natural-language conversation and user data is received in response. Data that describes this first natural-language conversation is used to train a model using machine learning. Data, is then be received by the chat bot as part of a second natural-language conversation. This data, from the second natural-language conversation, is processed using the model as part of machine learning to generate the second search query to include the aspect of the category automatically and without user intervention.

Abstract: Aspect pre-selection techniques using machine learning are described. In one example, an artificial assistant system is configured to implement a chat bot. A user then engages in a first natural-language conversation. As part of this first natural-language conversation, a communication is generated by the chat bot to prompt the user to specify an aspect of a category that is a subject of a first natural-language conversation and user data is received in response. Data that describes this first natural-language conversation is used to train a model using machine learning. Data, is then be received by the chat bot as part of a second natural-language conversation. This data, from the second natural-language conversation, is processed using the model as part of machine learning to generate the second search query to include the aspect of the category automatically and without user intervention.

Abstract: Aspect pre-selection techniques using machine learning are described. In one example, an artificial assistant system is configured to implement a chat bot. A user then engages in a first natural-language conversation. As part of this first natural-language conversation, a communication is generated by the chat bot to prompt the user to specify an aspect of a category that is a subject of a first natural-language conversation and user data is received in response. Data that describes this first natural-language conversation is used to train a model using machine learning. Data, is then be received by the chat bot as part of a second natural-language conversation. This data, from the second natural-language conversation, is processed using the model as part of machine learning to generate the second search query to include the aspect of the category automatically and without user intervention.

Abstract: Embodiments of the present disclosure are related to electronic commerce within instant messaging. A system may include a commerce server and an instant messaging server. The instant messaging server is configured to support an instant messaging service with an instant messaging client. The instant messaging server may include an application for supporting further communication in the instant messaging service between the instant messaging client and the commerce server. The method includes first instant messaging a query to an instant messaging client and receiving a response to the query at an application at an instant messaging server. The method further includes second instant messaging query results to the instant messaging client with the query results determined at a commerce server and based on the response.

Abstract: Aspect pre-selection techniques using machine learning are described. In one example, an artificial assistant system is configured to implement a chat bot. A user then engages in a first natural-language conversation. As part of this first natural-language conversation, a communication is generated by the chat bot to prompt the user to specify an aspect of a category that is a subject of a first natural-language conversation and user data is received in response. Data that describes this first natural-language conversation is used to train a model using machine learning. Data, is then be received by the chat bot as part of a second natural-language conversation. This data, from the second natural-language conversation, is processed using the model as part of machine learning to generate the second search query to include the aspect of the category automatically and without user intervention.

Abstract: Computing systems and methods for enhanced ticket sales are provided. The enhanced ticket sales may include presentation of community-sourced seat information to a potential ticket buyer that describes the human experience of sitting in each particular seat at a venue. The community-sourced seat information for each particular seat can be photos, comments, or other data that have been gathered by a ticket server from online content posted by people that have attended previous events in that seat. The online content can be gathered from email accounts, social network accounts, or other online sources. In this way, the human experience of some or all of the people who have sat in a particular seat at various events, as recorded in photos, comments, articles or other online data, can be collected, filtered, and provided to a potential purchaser of a ticked for that seat.

Abstract: Computing systems and methods for facilitating automatic generation and maintenance of an online scrapbook are provided. The online scrapbook may be a repository of ticketed-event information and associated photos, comments or other mementos associated with the ticketed events. The scrapbook may include a timeline of future and past purchased-ticket events and associated links for inviting others to future events, reselling tickets to future events, sharing events with others through social networking, displaying photos of past events, or commenting on past or future events. Events for the webpage may be identified through a user account on a ticket server or by scraping a user's email account for event-related emails. The photos may be gathered from social networking sites associated with the user and sorted by event based on the time, location, or content of the photo.

Abstract: Computing systems and methods for automatically providing event-related notifications to users are provided. Purchased-ticket events can be identified by scraping user emails. Ticket information such as dates and locations of events can also be gathered. User friends such as contacts in the user's social networks that have purchased tickets for the identified events may be identified. For future events, the user can be notified of friends that are attending the event, event-related vendor offers, ticket resale alerts, and event-time alerts. For past events, the user can be notified of shared comments or photos from friends or others. Consumers in a common geographical area with the user that have purchased tickets for the same events can also be identified. The user can be notified of identified neighbors attending the event or a community chat webpagc for the event can be provided.