O9 Solutions, Inc.

Koustuv Chatterjee

Chakradhar Gottemukkala

Raghav Ranganathan

Umesh Arasu

Amit Agarwal

Baskaran Manohar

Narasimha Kamath

Prashant Jhaba

S Pandiarajan

Mayuri Deb

Gautham K Kudva

Srinath Goud Vanga

Siddarth Wardhan

Rajeev Karri

Rohit Jangid

Devaraya Prabhu

Systems and techniques for alert-based learning for multi-dimensional data processing are described herein. Alert data may be received from a big data platform. An alert definition may be generated that includes a set of key performance indicators (KPIs) for an alert based on a determination that an alert definition does not exist for the alert. A calculation configuration may be created for the alert. Historical data from the big data platform may be evaluated with the calculation configuration to calculate the KPIs. An alert condition may be established for the alert based on the KPIs. The alert condition may be stored in the big data platform.

Alert-based learning for multi-dimensional data processing

Systems and techniques for hierarchical tournament-based machine learning predictions are described herein. A machine learning selection model may be trained with training data. A configuration may be received that includes the metric and a target prediction. A set of evaluation component combinations may be selected using the machine learning selection model. Each evaluation component combination of the set of evaluation component combinations may include an algorithm, a hierarchical learning model corresponding to a level of a hierarchy, and a prediction model for the target prediction. The set of evaluation component combinations may be transmitted to a cluster of computing nodes. Output results may be received for the set of evaluation component combinations. The output results may be evaluated using the metric to determine a winning evaluation component combination. The winning evaluation component combination may be stored in storage for use in calculating future predictions for the target prediction.

Hierarchical tournament-based machine learning predictions

Systems and techniques for aggregated physical and logical network mesh view are described herein. A selection may be obtained of a portion of a graph network data structure. Nodes may be identified in the portion of the graph network data structure. Geolocation data may be determined for each node of the nodes. Geographical boundaries may be calculated for the portion of the graph network data structure. A geographical map and a network map may be generated. A physical network view may be generated for display in the user interface as an aggregated view of the geographical map and the network map. The geographical map may represent a physical layer and the network map may represent a logical layer. The aggregated view may be output for display with a set of controls that correspond to the physical layer and a set of controls that correspond to the logical layer.

Aggregated physical and logical network mesh view

An unstructured data input is accessed that includes an electronic communication. Content of the unstructured data is parsed to determine one or more terms in the unstructured data input. It is determined that one or more particular elements defined in a structured business data model correspond to the terms. Tags are assigned to the unstructured data based on the terms corresponding to the one or more particular elements, where the tags define an association between the unstructured data and the structured data model.

Unstructured data processing in plan modeling

Systems and techniques for a computational unified graph hierarchy model are disclosed herein. A set of source data may be received that may include entity data and relationship data. An entity may be identified in the entity data. A hierarchy may be determined for the entity. An entity graph network may be generated. A non-hierarchical link between the entity and a related entity may be determined. The entity graph network may be updated to include the non-hierarchical link. A set of measures may be generated for a relational link of the entity. A dependency may be configured between the set of measures for the relational link and a second set of measures of a second relational link. A change may be identified to a value of a measure and a dependent entity node measure value may be updated based on a computational effect of the change to the value.

Computational unified graph hierarchy model

A plan model system provides interactive graphical user interfaces allowing users to view and navigate to multiple alternative views of measures modeled in one or more planning models. A modeled event is provided by a user relating to a measure of a particular plan model modeling outcomes of a particular business domain of a business organization. An effect of the event on values of one or more measures of the plan model is determined. A graphical representation is presented in the graphical user interface illustrating the effect.

Plan modeling visualization

Systems and techniques for read-write network visualization are described herein. A selected sub-region of a visual representation of a graph network may be displayed based on inputs received from a user. Boundaries for the selected sub-region of the visual representation of the graph network may be calculated. State data may be captured for a portion of the graph network associated with the selected sub-region using the calculated boundaries for the selected sub-region of the visual representation upon activation of an edit mode user interface control. A change to an element of the graph network may be identified. The graph network may be modified based on the change. A formula may be identified that is associated with the element of the graph network. The formula may be automatically recompiled and values for the element of the graph network, and nodes and edges that share a path with the element, may be automatically recalculated using the recompiled formula.

Read-write network visualization

An interactive user interface is generated to illustrate a graphical view of a network of plan models. The network of plan models includes a plurality of plan models, each plan model including one or more measures and one or more dimensions. At least one user-entered text character is entered in a query field and the plan models are searched for names of measures and/or dimensions in the plan models that correspond to the user entry. The names are presented as search term suggestions in the search query field and at least one suggestion is selected and adopted as at least a portion of a search query. The network of plan models is searched to generate search results corresponding to the search query. The graphical view of the network of plan models can be revised based on the search results.

Plan model searching

A communication by a particular user within a digital collaboration is determined as related to a particular business entity. A relationship between one or more additional business entities and the particular business entity is identified from one or more business models. The communication is associated with the additional business entities based on the relationship.

Growing community of inventors

San Ramon, CA, United States of America

Koustuv Chatterjee