Sustainable Test Path Generation for Chatbots using Customized Response

Abstract

In the current researching and Industrial fields have focused on much-attracted technology is chatbots. Informal agents could provide an appropriate and economic environment in online between the users and service provider. Due to a large number of datasets based on the digital tools, the user’s queries based satisfying responses providing are critical in the service oriented chatbots. The successful human-chatbots interaction must be apparent and reacted by the user. This paper presents a technique to generate the test path for effective chatbot software testing. Identification of relations among the chatbots, transformations, and boundaries of the existing methodology are described. This experimental results associated with four peak chatbot response methodologies along with technology specifications. An in-depth experimental of proposed chatbot test path generation methodology, provides the experimental results and comparison.

Rapid medical guideline systems for COVID-19 using database-centric modeling and validation of cyber-physical systems

“…The approach determines the goal of the patient interaction with medical professionals to find more important and effective potential data to find faults with less execution time with more code coverage. To support this goal, the proposed algorithm should find a stack simulation with a higher gain value and visit the stack at least once during the allocation ( Padmanabhan and Prasanna, 2016 , Padmanabhan and Prasanna, 2017a , Padmanabhan, 2018 , Padmanabhan, 2019 , Padmanabhan, 2020 , Wang et al, 2018 ).…”

Performance Analysis of Test Path Generation Techniques Based on Complex Activity Diagrams

“…Currently, the advantages of the test path generation are applied to several real-world problems, for example, (1) to generate test data using the neighborhood search strategy [15] and using the genetic algorithm [16], (2) to generate test paths for effective chatbot software testing using customized response [17], (3) to optimize test cases by generating test path and selecting test data using Cuckoo search and Bee colony algorithm [18], and (4) to generate optimized test data for saving both testing cost and time [19].…”