Sap Se

Vladimir Shapiro

Roman Rommel

Jochen Steinbach

Matthias Kaiser

Kai Richter

Thomas Ryborz

Max-Samuel Lang

Luisa Andre

Joachim Sander

Daniel Wurst

Douglas Whelton Muise

Christian Reissmueller

Alexander Schreiber

Implementations include receiving, by a semantic translation service of a ML platform, an output data set from a ML model, the output data set including a predicted value and a set of metrics, determining, by the semantic translation service, a numerical value based on at least two or more metrics in the set of metrics, selecting, by the semantic translation service, a semantic result by mapping the numerical value to a projection including two or more semantic values, and transmitting, by the ML platform, a prediction result at least partially including the semantic result for selective display to a user using one or more user interfaces (UIs).

Interpretable semantic indication of machine learning output

The disclosure generally describes methods, software, and systems for providing solution descriptions. A problem description of a problem is received, from a client, at a cloud-based reasoning service. A solution description for a solution to the problem is received. Case metadata for a case defining the problem and solution are generated by the cloud-based reasoning service. The case metadata, including the problem description and solution description, are stored by the cloud-based reasoning service in a cases repository associating solutions with problems. A new problem is received at the cloud-based reasoning service. An automated analysis of the new problem is performed, and a comparison is made of the new problem with existing solutions in the cases repository to identify solutions matching the new problem. A new solution description is provided that is based on a match between the new problem description and the problem description and using the problem solution.

Case-based reasoning as a cloud service

Provided is a system and method which provides visually-compacted search results with attribute information embedded therein. In one example, the method may include receiving, via a user interface, a search request based on a set of attributes, identifying search results that match the search request based on attributes of the search results with respect to the set of attributes, and displaying, via the user interface, a plurality of circular objects corresponding to the plurality of search results, respectively, each circular object comprising a round-shaped outer bar arranged around an outer boundary of the circular object which includes attribute information of a search result corresponding to the circular object embedded therein.

Compact display of matching results

Disclosed herein are system, method, and computer program product embodiments for obtaining feedback in an explicit, non-disruptive manner. An embodiment operates by determining a trigger corresponding to a feedback event, where the trigger is associated with a particular application that is registered with a feedback application associated with the feedback event; detecting an application event corresponding to the trigger occurs during an execution of the particular application; receiving a screenshot of a user interface of the particular application at a time of the detecting; providing a notification indicating that feedback corresponding to the application event is requested; receiving a request to launch the feedback event; and receiving feedback corresponding to the feedback event via the feedback application.

Non-disruptive explicit feedback system

Disclosed herein are system, method, and computer program product embodiments for implementing facet components and facet collection components for dynamic switching between display contexts. An embodiment operates by presenting, via a first rendering component, a first graphical representation of a numeric component in a first display context within a graphical user interface, determining a second display context associated with the numeric component, and loading a second rendering component associated with the second display context into the numeric component. Further, the embodiment presents, via the second rendering component, a second graphical representation of the numeric component in the second display context within the graphical user interface.

Visual facet components

An interface provides decision support in complex problem environments. An interface engine selectively communicates with a database to display (e.g., in tree form) proposed decisions and various corresponding outcomes resulting from cause-effect relationships of selected decisions. Structured data objects store state information (e.g., current/projected/target) of multi-faceted, inter-connected entities. Object metadata can include entity attributes and/or entity relationship details. The interface allows traversing the tree to explore the cause-effect relationships and/or validate various solution paths. The tree (including the proposed decisions, outcomes, and solution paths) may be initially generated up front, based upon particular problem scenario characteristics. Limited subsequent interaction between the interface engine and the underlying backend data store may enhance speed/performance/user experience. Roundtrip interaction with the underlying database may take place where a user seeks to adjust a decision with specific metrics and simulate the result, and/or create an execution plan/activity based upon a solution path previously designed.

Growing community of inventors

Sinsheim, Germany

Vladimir Shapiro