Oracle International Corporation

Kyasaram Vishwa Prasad

Anilkumar Gande

Naveen Jafer Nizar

Guru Selvaraj

Srikanth Subrahmanya Nandula

Ayushi Behl

Srinivasan Sankaranarayanan

Subir Kawal Hira

Roya Lashgari Afshar

Margaret Sue Lloyd

Subhadarshi Mishra

Chidambaram Gopal Karthik Murugan

Techniques are described for providing personalized content in applications without revealing personal details to content providers. A base machine learning model is loaded to a cloud environment that is private to a tenant organization. The base machine learning model is used to generate a custom machine learning model specific to the tenant organization based on user interactions within the tenant organization and content categories specific to the tenant organization. The custom machine learning model is used to select content categories for which to provide instances of content items to users based on user interactions with applications. Engagement with the instances of content items is tracked in a user-specific manner privately by the tenant organization, in a tenant-specific manner privately by a cloud services provider, and in a content-specific manner by the content provider. Feedback is provided to the custom machine learning model based on engagement with instances of content items.

Personalized internal services via a privacy-constrained content promotion platform

A computing network includes nodes of different work groups. Nodes of a work group are dedicated to transactions of the work group. If a node of a first work group is predicted to have an idleness window, a second work group may borrow the node to execute a transaction of the second work group. At least a subset of steps of the transaction may be categorized into a step group. Trees of a transaction may be categorized into one or more tree groups. A node is selected for executing a transaction, if the predicted idleness duration of the node is sufficient relative to the predicted runtime of the transaction, the step group, and/or tree group. A credit system is maintained. A first work group transfers a credit to a second work group when borrowing a node of the second work group for executing a transaction of the first work group.

Selecting a node of a work group for executing a target transaction of another work group to execute skippable steps prior to a predicted interruption

A system provides automatic, end-to-end tagging of email messages. While a message is being composed at a sending email client, the server may receive email information that is used as an input to a predictive model. The model identifies tags that are available to a specific user group or email list that apply to the email message. These predicted tags are sent back to the email client, where they may be embedded in the email message with other user-defined tags. As the message is passed through the email server, the system may use any changes made to the predicted tags to retrain the model. When the message is received at a second email client, the receiver may further edit the tags, and any changes may again be used to retrain the model.

End-to-end email tag prediction

Selecting a node group of a work group for executing a target transaction of another work group to optimize parallel execution of steps of the target transaction

An artificial neural network (ANN) determines a conversation snippet sentiment score based on content of the conversation snippet and contextual attributes associated with the conversation snippet. Contextual attributes may include, for example, a role within an organizational hierarchy of a user participating in the conversation snippet. Information representing the content is input into a hidden layer sequence of the ANN; information representing the contextual attributes is input into another hidden layer sequence of the ANN. Additionally or alternatively, a weighing engine determines a topical sentiment score by aggregating weighted conversation snippet sentiment scores. Weights to be applied to the conversation snippet sentiment scores may be determined based on, for example, a proportion of conversation snippets associated with the same topic that are conducted on a particular conversation channel as compared with other conversation channels, and respective roles of users participating in the conversation snippets conducted on the particular conversation channel.

Using neural network and score weighing to incorporate contextual data in sentiment analysis

Methodologies and systems are described herein whereby application functionality may be optimized and extended based on a contextual analysis of the features that are accessed within the application. In one or more embodiments, the contextual analysis includes (a) detecting that an end user of an application is using a particular feature of the application and (b) determining that a set of one or more third-party applications are configured for operations accessing data sets of the same type accessed by the particular feature. Responsive at least to the detecting and determining operations, the set of one or more third-party applications are presented to the user when the user is accessing the particular feature of the first application.

Context-based analytical engine for extending application functionality

Systems and methods, are provided for self-healing solutions to problems that occur during a software build. In one embodiment, build log data structures of build data, generated during execution of a software build of a software application, are automatically monitored. The build data is automatically analyzed to detect patterns that can result in build violations. Detected patterns are automatically matched to remediation solutions stored in a knowledge database. The remediation solutions are automatically applied to the software application.

Growing community of inventors

Hyderabad Telangana, India

Kyasaram Vishwa Prasad