Accenture Global Solutions Limited

Venugopal Ramakrishnan

Muralidhar Yalla

Anand Vijendra

Muralikrishna Neelakandam Jayagopal

Mahender Rajpurohit

Reuben Rajan George

A device may receive historical software data associated with a software development platform, and may train a neural network model, with the historical software data, to generate a trained neural network model. The device may receive, from the software development platform, historical test configuration data, and may train an execution model, with the historical test configuration data, to generate a trained execution model. The device may receive software data identifying software to be tested, and may process the software data, with the trained neural network model, to predict a set of test cases to execute for testing the software. The device may process the set of test cases, with the trained execution model, to identify configurations, scripts, and test targets for executing the set of test cases, and may perform one or more actions based on the set of test cases, the configurations, the scripts, and the test targets.

Utilizing neural network and artificial intelligence models to select and execute test cases in a software development platform

A system may obtain a test utterance sample configured to test a virtual agent. The system may tokenize the test utterance sample into a sample tokens. The system may determine, based on a natural language processing framework, a synonymous set (synset) for at least one of the sample tokens. The synset may include a lemma tokens. The system may obtain a contextual corpus relevant to a natural language context of the virtual agent. The system may select a lemma token that is included in the corpus tokens. The system may generate a new test utterance comprising the selected lemma token. The system may insert the new test utterance in a test repository. The system may communicate the new test utterance to the virtual agent to test the virtual agent based on the new test utterance. If the virtual agent fails a test in respect to the new test utterance, the corpus of the virtual agent can be retrained.

Automated data cartridge for conversational AI bots

A system and method for controlling quality of performance of a digital application is disclosed. Performance data representing test results of a requested performance test on the application is obtained. A performance metric is optimized by analyzing the performance data and classifying analysis results of the analyzing into multiple categories, including an immediate remediation category. An automated modification is initiated based on a first analysis result classified into the immediate remediation category. An automated verification performance test determines a measure of improvement in performance of the application based on the modification by comparing a first verification result of a first performance test without the automated modification with a second verification result of a second performance test of the digital application with the automated front end modification. The digital application with the automated modification may be deployed based on a result of the automated verification performance test.

Growing community of inventors

Aldershot, United Kingdom

Venugopal Ramakrishnan