Sap Se

Prerna Makanawala

Venkitesh Subramanian

Kedar Shiroor

Abhijit Mitra

Karan Sood

Rei Kasai

Terence Chesire

Niyanth Kudumula

Ryan Currier

Preeta Kulavil

Praveen Kalla

Jean-Francois Desjeans Gauthier

Jing Ye

Yann Le Biannic

Prajesh K

Devasena Rajamohan

Claus Wallacher

Karthik S J

Krithika Manohar

Arjun Karat

Xiaoqing He

Amy He

Subhobrata Dey

Amith Manoharan Chithambaram

Brian Yip

Ke Sun

Sebastine Augustine

Gabriele Bodda

Kiran Karadi

Nayaki Nayyar

Riya Thosar

Georg Glantschnig

Sushant Potdar

Venkat Iyer

Lin Pang

Janani Bhuvaneswari Sundar

Jaideep Godara

Jothish Karunakaran

A method of improving usability and transparency of machine-learning aspects of applications providing various types of services is disclosed. Based on a request submitted through an administrative user interface, a data readiness check is performed on underlying data associated with the application. Based on a successful completion of the data readiness check, a configuration file is retrieved from an application server. The configuration file specifies a plurality of keys for generating a machine-learned model for the application. The machine-learned model is trained based on the plurality of keys specified in the configuration file. The machine-learned model is selected from a plurality of machine-learned models based on dry runs of the each of the plurality of models. The machine-learned model is activated with respect to the application. Scores are identified from the underlying data items based on the selected machine-learned model.

Applying scoring systems using an auto-machine learning classification approach

An issue tracking system capable of predicting the likelihood that an outcome of interest will occur during the lifecycle of an active support ticket. The likelihood can be represented as a severity index score. The issue tracking system can apply a predictive algorithm on attributes of the active support ticket to generate the severity index score. The predictive algorithm to use can depend on the outcome of interest while the correlation factors used to configure the predictive algorithm can depend on support tickets that have already been completed.

Predicting the severity of an active support ticket

A sales application is described that includes multiple automated sales tools that can be combined to help improve sales within a sales team. A deal finder sales tool is described to help identify sales opportunities. A deal playbook sales tool is also described to help structure the sales opportunity into a sales play by recommending products to sale in conjunction and also constructing a sales team. An influencer sales tool is also described to help identify business relationships that can be utilized to influence members of the sales team.

Automated software tools for improving sales

Techniques are described for providing additional content that is relevant to an upcoming service appointment in an audible format. The additional content can be retrieved from remote sources and aggregated to form an audio package to be played back to the technician as the technician travels to a destination address that corresponds with the upcoming service appointment. The additional content retrieved can depend on the estimated travel time to the destination address. By presenting the additional content audibly at the same time as route directions are being presented graphically, the driver can multi-task which results in time savings since the additional content has been consumed during the drive to the upcoming appointment rather than when the technician arrives at the destination address.

Audible consumption of content while traveling to a destination

Systems and method for identifying individuals who may be potentially influential on a particular identified contact for a particular sales opportunity are disclosed. The individuals identified as potential influencers are then ranked according to a predicted level of influence and displayed in a graphic representation. In one embodiment, the ranked potential influencers are displayed as icons in a spiral formation relative to an icon representing the identified contact. The closer an icon representing a particular potential influencer is to the icon representing the identified contact, the greater the level influence is that that influencer might have on the identified contact.

Predicting levels of influence

According to various embodiments, a social media message posted on a social media system is accessed. One or more similar messages determined to be similar to the social media message may be selected from a database of previously posted messages, based on, for example, an author, product, problem, keyword, etc., identified in the social media message. The similar messages may be displayed in a similar message recommendation list of a user interface. One or more relevant knowledgebase articles determined to be relevant to the social media message may be selected from a knowledgebase repository, based on, for example, a product, problem, keyword, etc., identified in the social media message. The relevant knowledgebase articles may be displayed in a knowledgebase article list of a user interface.

Systems and methods for customer relationship management

Growing community of inventors

Mountain View, CA, United States of America

Prerna Makanawala