Abstract: One embodiment provides a system for generating an inference model that determines an activity type for a user from contextual information. During operation, the system receives a set of contextual information associated with the user, wherein the contextual information includes at least a set of location coordinates. The system then determines an association between the contextual information and an activity type. Next, the system generates an activity inference model based in part on the association, wherein the activity inference model takes an instance of contextual information as an input parameter and outputs a corresponding activity type. The model's parameters are based at least on statistics associated with the user's contextual history but not based on the complete contents of the user's contextual history.

Abstract: One embodiment provides a system for generating an inference model that determines an activity type for a user from contextual information. During operation, the system receives a set of contextual information associated with the user, wherein the contextual information includes at least a set of location coordinates. The system then determines an association between the contextual information and an activity type. Next, the system generates an activity inference model based in part on the association, wherein the activity inference model takes an instance of contextual information as an input parameter and outputs a corresponding activity type. The model's parameters are based at least on statistics associated with the user's contextual history but not based on the complete contents of the user's contextual history.

Abstract: One embodiment of the present invention provides a system for facilitating presentation of activity-based advertising. During operation, the system receives a set of contextual data of a customer and makes a prediction of the customer's future activity. The system then receives a number of advertisements from the advertisers. Based on the prediction, the system chooses a received advertisement to present to the customer. The system further determines the customer's subsequent activity and confirms the prediction of the customer's activity. The system then receives payments from the advertisers whose advertisement is presented based on whether the prediction is confirmed.

Abstract: A recommender system uses an activity decision tree to model the changes in a user's behavior according to a plurality of time-related features. The system determines historical activities for the user, and generates a decision tree for the user's historical activities. Each leaf node of the decision tree is associated with an activity-prediction model that computes a probability for a corresponding activity. The system selects a path of the decision tree from a root node to a leaf node of the decision tree based on a target time. The selected path traverses two or more non-leaf nodes that are each associated with a temporal decision model that compares the target time against a temporal classifier. The system then determines a probability for a user activity based on an activity-prediction model of the selected path.

Abstract: A system facilitates automatically determining the hypothetical context information or the distribution of hypothetical contexts. During operation, the system receives a request from a user for one or more recommendations. The system also receives a current context substantially associated with the request. The system then determines a hypothetical context for the request, wherein the hypothetical context may be determined by considering several sources of information, including but not limited to the current context, past contexts, and relationships between the current context and past contexts. Next, the system determines one or more recommendations for the user based on the hypothetical context. Finally, the system returns the one or more recommendations to the user.

Abstract: One embodiment provides a system for facilitating document printing from a portable device. During operation, the system receives a document at a server. Next, the system generates a document optical code corresponding to the document. Subsequently, the system communicates the document optical code to the portable device, thereby allowing the portable device to display the document optical code to a scanning mechanism associated with a printer, Next, the system receives a request, indicating the optical code, from the printer. Subsequently, the system retrieves the document in response to the request, and sends the document to the printer.

Abstract: Embodiments of the disclosed technology provide a system and method for automatically filling paper form with electronic data. The system receives from a user a scanned image of a paper form that includes a plurality of fields. The system then retrieves a schema map that maps the plurality of fields in the paper form to a plurality of fields in an electronic data record associated with the user. Next, the system retrieves data values of the fields in the electronic data record based on the schema map. The system also synthesizes the retrieved data values and the scanned image to create an image of the paper form in which the fields are filled with the retrieved data values.

Abstract: A wait-queue modeling system facilitates computing a wait time for an activity type. During operation, the system obtains user-behavior events associated with one or more users waiting to perform an activity of a target activity type. The system can determine, based on the user-behavior events, activity-waiting attributes associated with users entering or leaving a waiting queue for an activity of the target activity type. The system then computes a wait time for the activity type based on the determined activity-waiting attributes.

Abstract: A recommender system determines a probability threshold for an activity-prediction model, and uses the probability threshold to predict whether a user is performing a target activity. To determine the probability threshold, the system computes a set of activity probabilities based on contextual information for a set of historical activities, and based on an activity-prediction model for a target activity. The system then compares a set of probability thresholds with the set of activity probabilities to determine a prediction success rate for each probability threshold. The system computes a utility score for each probability threshold based on the prediction success rates and a utility function, and selects a probability threshold whose utility score is optimal amongst the utility scores of the set of thresholds and greater than or equal to a baseline utility score. The system then assigns the probability threshold to the activity-prediction model.

Abstract: One embodiment provides a system for printing a document from a portable device. During operation, the system captures an image of an optical code that identifies a printing device, wherein the optical code is displayed on a panel of the printing device or is printed by the printing device. Next, the system transfers information identifying the printing device to a remote printing service, thereby allowing the remote printing service to print a document at the printing device.

Abstract: Some embodiments of the present invention provide a system that infers activity-related context information from a message. Upon receiving the message, the system looks for activity-related keywords in the message, wherein the activity-related keywords are from a content database. If one or more activity-related keywords are found in the message, the system infers message-related context information from the one or more activity-related keywords. Next, the system uses the message-related context information to facilitate recommending an activity to a user.

Abstract: One embodiment provides a system for facilitating document printing from a portable device. During operation, the system receives at an email server an email which includes an attached document. Next, the system generates at the email server a document optical code associated with the document, wherein the document optical code can be scanned and recognized by a scanning mechanism associated with a printer. Subsequently, the system attaches the optical code as an additional attachment to the email, thereby allowing a portable device to print the attached document by displaying the optical code to the scanning mechanism associated with the printer.

Abstract: One embodiment provides a system for printing a document from a portable device. During operation, the system obtains the document to be printed. Next, the system obtains a document optical code that identifies the document. Subsequently, the system displays the document optical code on the portable device in such a way that the document optical code can be scanned and recognized by a scanner associated with the printer. Next, the system allows the printer to retrieve and print the document based at least on the document optical code.

Abstract: A performance-efficient activity-modeling system generates a group-activity model for a population group using information from an optimal subset of users of the population group. During operation, the system computes utility scores for a set of users based on a utility-scoring function, such that a respective utility score indicates a usefulness or penalty of collecting a corresponding user's contextual information. The system then selects, from the set of users, a subset of users with highest utility scores, and receives user information from each of the selected users. The system generates the group-activity model based on the user information received from the selected users.

Abstract: A performance-efficient activity-modeling system generates a group-activity model for a population group using information from an optimal subset of users of the population group. During operation, the system computes utility scores for a set of users based on a utility-scoring function, such that a respective utility score indicates a usefulness or penalty of collecting a corresponding user's contextual information. The system then selects, from the set of users, a subset of users with highest utility scores, and receives user information from each of the selected users. The system generates the group-activity model based on the user information received from the selected users.

Abstract: A client device can receive information about a population to which a user belongs. During operation, the client device determines information about a user, determines a group identifier for the user, and communicates the determined information about the local user and the group identifier to a group-modeling server. The client device then receives a group-activity model that corresponds to the group identifier, and generates a user-activity model for the local user based on the group-activity model and the determined information about the local user. The client device uses the user-activity model to compute an activity probability for a corresponding target activity. The group-modeling server receives user information from a plurality of client devices of a group, and generates a group-activity model for the group based on the user information. The server then sends the group-activity model to users of the identified group.

Abstract: A recommender system uses an activity decision tree to model the changes in a user's behavior according to a plurality of time-related features. The system determines historical activities for the user, and generates a decision tree for the user's historical activities. Each leaf node of the decision tree is associated with an activity-prediction model that computes a probability for a corresponding activity. The system selects a path of the decision tree from a root node to a leaf node of the decision tree based on a target time. The selected path traverses two or more non-leaf nodes that are each associated with a temporal decision model that compares the target time against a temporal classifier. The system then determines a probability for a user activity based on an activity-prediction model of the selected path.

Abstract: A recommender system determines a probability threshold for an activity-prediction model, and uses the probability threshold to predict whether a user is performing a target activity. To determine the probability threshold, the system computes a set of activity probabilities based on contextual information for a set of historical activities, and based on an activity-prediction model for a target activity. The system then compares a set of probability thresholds with the set of activity probabilities to determine a prediction success rate for each probability threshold. The system computes a utility score for each probability threshold based on the prediction success rates and a utility function, and selects a probability threshold whose utility score is optimal amongst the utility scores of the set of thresholds and greater than or equal to a baseline utility score. The system then assigns the probability threshold to the activity-prediction model.

Abstract: One embodiment of the present invention provides a system that selectively transfers code to a data producer in a networked system. In this system, the data producer generates data and then sends the data to a device. The device receives the data from the data producer, and then uses code on the device to perform a processing operation on the data. Next, the system analyzes characteristics of the data to determine whether performing the processing operation on the data producer can reduce resource usage. If so, the system transfers the code from the device to the data producer, and subsequently executes the code on the data producer. By executing the code on the data producer, the system can optimize resource usage in the networked system.

Abstract: An orientation-determining system determines a person's compass orientation from data generated by one or more sensors embedded within a portable device transported by the person. In some scenarios, the system uses the person's initial orientation to calculate an initial orientation delta describing a difference between the person's initial orientation and an initial orientation of the device. In other scenarios, the system calculates the person's current orientation based on an initial orientation of the device and a known or assumed orientation delta. The system can apply the orientation delta to the device's current orientation to determine the person's current orientation. The system can update the orientation delta based on any changes to the orientation of the person or the device.