Ajay N Bhoj

US Patent:

20190286995, Sep 19, 2019

Filed:

Nov 7, 2018

Appl. No.:

16/183120

Inventors:

- Palo Alto CA, US
Ajay BHOJ - San Mateo CA, US

International Classification:

G06N 5/02
G06N 5/04
H04L 29/08
H04L 12/26
H04L 12/24
G06F 11/34
G06N 20/00

Abstract:

Systems described herein provide structures and functionality for transforming passive analytics systems into systems that can actively modify software behavior based on analytic data to improve software performance relative to configurable goal metrics. An example method generally includes receiving, via a computing network, time-series data collected by a remotely executed software application for a plurality of sessions; storing the time-series data in a persistent data repository; receiving a goal definition specifying how to calculate a goal score based on at least one metric that is calculable based on the time-series data; for each session, determining a value for the at least one metric; based on the time-series data and the values for the sessions, training a machine-learning model to determine, based on events that precede a decision-point event in a session, one or more actions for the remotely executed software application to perform in response to the decision-point event; generating a decision-making policy from the trained machine-learning model; and deploying the policy to a location in the computing network where decision-making requests originating from the software application are received.

US Patent:

20190287003, Sep 19, 2019

Filed:

Nov 7, 2018

Appl. No.:

16/183288

Inventors:

- Palo Alto CA, US
Ajay BHOJ - San Mateo CA, US
Yuval SCHARF - Mountain View CA, US

International Classification:

G06N 5/04
G06N 5/02
H04L 29/08
G06N 20/00
G06F 11/34

Abstract:

Systems described herein provide structures and functionality for transforming passive analytics systems into systems that can actively modify software behavior based on analytic data to improve software performance relative to configurable goal metrics. An example method generally includes receiving a speculative decision-making request including a consumer identifier from a software application; generating actions associated with mutually exclusive sets of events to be detected during execution of the software application; transmitting content, the sets of events, and actions associated with each event; detecting one of the sets of events; performing the action associated with the detected one of the sets of events; receiving information identifying the detected one of the sets of events and the action associated with the detected one of the sets of events; and saving time-series data associated with the detected one of the sets of events, the decision-point event, and a timestamp associated with the detected event.

US Patent:

20190288927, Sep 19, 2019

Filed:

Nov 7, 2018

Appl. No.:

16/183220

Inventors:

- Palo Alto CA, US
Vidya RANGASAYEE - Monte Sereno CA, US
Ajay BHOJ - San Mateo CA, US

International Classification:

H04L 12/26
H04L 12/24

Abstract:

Systems described herein provide structures and functionality actively modifying software behavior based on analytic data. An example method generally includes receiving session information characterizing interactions between the consumer and a software application; receiving a goal definition specifying how to calculate a goal score based on at least one metric calculable from the session information; grouping the sessions into bins, wherein each bin corresponds to a time interval and includes sessions that have starting times within the time interval; for each session: calculating a current value of a first metric, and determining a current goal score for the session based on the current value for the first metric and the goal definition; calculating a current average goal score for each bin; and rendering a graphical plot of the current average goal scores for the bins against time as partitioned by the bins for display.