Microsoft Technology Licensing, LLC

James Edelen

Jorge Pereira

Tore L Sundelin

John Michael Winn

Michael Anthony Affronti

Andrew Russell Brauninger

Robert Emmett Mccann

James Charles Kleewein

John Guiver

Alexander Wetmore

Fernando Garcia

Rajesh Ramanathan

Bradford R Clark

Britta Burlin

Jian Li

John Fitzgerald Bronskill

Kashif Dastgir

Saravanakumar Rajmohan

Artyom Sadovsky

John Winn

Technologies are generally described for providing an email assistant for sorting through emails received at an email application. The email assistant may prioritize emails and group high and low priority emails separately to enable a user to quickly view and manage an email inbox. The email assistant may also provide suggestions on how to sort and manage emails in the inbox of the email application. The email assistant may observe a user's pattern of interactions with types of emails, and prioritize emails and suggest actions based on the user's interactions. The email assistant may be configured to automatically sort emails and provide management suggestions based on a detected scenario such as a user's return after a period of time away, a large influx of emails, and presence detection.

Email assistant for efficiently managing emails

Generating and utilizing personalized predictive models are provided. When an electronic input is received, a generic predictive model is used to predict a user response to the input. After a prescribed period of time, an analysis is performed to determine the user's actual response to the input, as well as, the user's actual responses to other inputs of the same type. Training is performed on the generic predictive model to generate a new and personalized predictive model based on the user's actual responses to the analyzed inputs. The personalized predictive model is then utilized for predicting user response to future inputs of the same type. At a prescribed frequency, the generated personalized predictive model is updated by analyzing actual user responses to predictions provided by the personalized predictive model.

Personalized predictive models

Techniques for the aggregate and hierarchical display of grouped items spanning multiple storage locations are described. Some techniques may aggregate items in response to user input identifying a scope for item retrieval. The user input may identify a scope such as selection of a local storage location or a search query for retrieving items. The aggregated items may span multiple storage locations and include items within the identified scope and related items outside the identified scope. A group of aggregated items are presented in a hierarchical display within a user interface. The hierarchical display may visually differentiate items inside and outside of the identified scope, and may identify parent-child relationship between related items. An aggregate header for the group of aggregated items may be displayed indicating total items in the group and a status for items in the group within the identified scope. Other embodiments are described and claimed.

Aggregate and hierarchical display of grouped items spanning multiple storage locations

Technologies are generally provided far a hierarchical, feature teed statistical model that cm be used for personalized classification or predictions within a community of users. Personalization refers to learning about the habits and characteristics of individual users and adapting user experiences based on that learning. The model may be used in a communication application to predict user actions on incoming email messages and to help users triage email by making personalized suggestions based on the model predictions. A community of users associated together with the communication application may be incorporated together into a single model to enable for continuous fine-grain interaction between intelligence learned from the community of users as a whole and that learned from individual users. The single model may allow a seamless progression between predictions for a completely new user based on community observations and highly personalized predictions for a long-term user based on individual observations.

Hierarchical statistical model for behavior prediction and classification

User insights derived from communication data may be provided. Communications associated with a user may be collected and analyzed to derive insights about the user. The insight may then be provided to the user, such as for modifying an application functionality, creating a message processing rule, providing new information to the user, and updating an application display or user interface.

Data mining electronic communications

Automatic conversation techniques are described. An apparatus may comprise a computing device having an incoming message module operative to receive an incoming message, a conversation identification module communicatively coupled to the incoming message module, the conversation identification module operative to determine the incoming message is part of a conversation thread, and associate the incoming message with the conversation thread by setting a conversation identifier property of the incoming message to a conversation identifier for the conversation thread, and a conversation manager module communicatively coupled to the conversation identification module, the conversation manager module operative to determine a conversation rule is associated with the conversation thread, and apply the conversation rule to the incoming message. Other embodiments are described and claimed.

Automatic conversation techniques

A system is provided for automatically predicting actions a user is likely to take in response to receiving data. The system may be configured to monitor and observe a user's interactions with incoming data and to identify patterns of actions the user may take in response to the incoming data. The system may enable a trainer component and a classifier component to determine the probability a user may take a particular action and to make predictions of likely user actions based on the observations of the user and the identified pattern of the user's actions. The system may also be configured to continuously observe the user's actions to fine-tune and adjust the identified patterns of user actions and to update the probabilities of likely user actions in order increase the accuracy of the predicted user action in response to incoming data.

Prediction of user response actions to received data

A message is delivered to an external indexing service when a link is located within a given communication. The message includes a request to index content contained within the link to ensure that the link is indexed. When a keyword search query is performed within the communication system, both a local index and an external index associated with the external indexing service are queried. Results from the query are merged and surfaced.

Searching linked content using an external search system

Triaging electronic communications in a computing system environment can mitigate issues related to large volumes of incoming electronic communications. This can include an analysis of user-specific electronic communication data and associated behaviors to predict which communications a user is likely to deem important or unimportant. Client-side application features are exposed based on the evaluation of communication importance to enable the user to process arbitrarily large volumes of incoming communications.

Electronic communications triage using recipient's historical behavioral and feedback

A determination of whether to archive email messages in a user mailbox is made each time an email message is received at a server computer. A storage quota, a first threshold and a second threshold are obtained for the user mailbox. The first threshold is a first percentage of the storage quota. The second threshold is a second percentage of the storage quota. When it is determined that the size of the received email message plus the current size of the user mailbox exceeds the first threshold for the user mailbox, one or more email messages in the user mailbox are archived. The archiving of the one or more email messages reduces the current size of the user mailbox such that the current size of the user mailbox becomes less than the number of bytes corresponding to the second threshold for the user mailbox.

Growing community of inventors

Renton, WA, United States of America

James Edelen