AI-boosted software automation: learning from human pair programmers

Peng, Xin; Xing, Zhenchang; Sun, Jun

doi:10.1007/s11432-018-9854-3

Cited by 5 publications

(11 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…And when the same code is being suggested to the developer, the same error may get propagated. The application the creativity and uncertainty contained in the design, the diversity and difference of various software projects in the business and technical fields, the data quality of code and other software development resources (Peng et al, 2019).…”

Section: Future Prospectsmentioning

confidence: 99%

Section: Future Prospectsmentioning

confidence: 99%

“…Using Code reuse recommendation based on deep learning, errors or bugs can be identified and halted, thus solving the problem of uncertainty and helping constructing a robust and self-learned model. However, due to the inherent complexity and uncertainty of software development, there are still a series of technical challenges in the full realization of intelligent code reuse recommendations in enterprise software development, including software requirements and the creativity and uncertainty contained in the design, the diversity and difference of various software projects in the business and technical fields, the data quality of code and other software development resources (Peng et al , 2019).…”

Section: Future Prospectsmentioning

confidence: 99%

“…The working mode of the intelligent assistant should be similar to pair programming, which can continuously interact and collaborate with software developers. For this reason, this kind of intelligent assistant should have the following abilities in many aspects (Peng et al , 2019). Interactive clarification and explanation: Interactively clarify the developer's intentions and provide principle explanations and explanations for the recommendations given.Gradually refine the solution proposal: According to the developer's way of thinking, gradually recommend and refine code reuse and problem solutions from coarse to fine, instead of getting into the details at the beginning.Acquire and utilize technical and business background knowledge: Have technical and business background knowledge of programming languages, APIs, domain models, etc., to support efficient interaction with developers and reuse recommendations.Incorporating new coding language in a software company or organization is a humongous decision; management has to take into account different parameters like software costs, staff training cost, new equipment's/systems cost, etc.…”

Section: Future Prospectsmentioning

confidence: 99%

See 3 more Smart Citations

Context-based intelligent recommendation by code reuse for smart decision support and cognitive adaptive systems

Khapre

Singh

Shankar

et al. 2021

IJIUS

View full text Add to dashboard Cite

PurposeThis paper aims to use the concept of machine learning to enable people and machines to interact more certainly to extend and expand human expertise and cognition.Design/methodology/approachIntelligent code reuse recommendations based on code big data analysis, mining and learning can effectively improve the efficiency and quality of software reuse, including common code units in a specific field and common code units that are not related to the field.FindingsFocusing on the topic of context-based intelligent code reuse recommendation, this paper expounds the research work in two aspects mainly in practical applications of smart decision support and cognitive adaptive systems: code reuse recommendation based on template mining and code reuse recommendation based on deep learning.Originality/valueOn this basis, the future development direction of intelligent code reuse recommendation based on context has prospected.

show abstract

Section: Future Prospectsmentioning

confidence: 99%

Section: Future Prospectsmentioning

confidence: 99%

Section: Future Prospectsmentioning

confidence: 99%

Section: Future Prospectsmentioning

confidence: 99%

See 2 more Smart Citations

Context-based intelligent recommendation by code reuse for smart decision support and cognitive adaptive systems

Khapre

Singh

Shankar

et al. 2021

IJIUS

View full text Add to dashboard Cite

show abstract

“…The workflow (coding steps, best practices, emergent errors and fixes) in programming screencasts complement know-what programming knowledge (e.g., API documentation, Stack Overflow discussions) with know-hows [1], [2]. The know-how knowledge is also important for task-oriented knowledge recommendation [3], [4] In spite of its importance, the workflow is implicitly embedded in the screencasts, which greatly limits the access and interaction with programming workflow in programming screencasts. This makes it hard for developers to get a quick overview of the workflow, or to navigate and search the workflow steps [5], [2].…”

Section: Introduction Computer Programming Involves Two Types Of Know...mentioning

confidence: 99%

ActionNet: Vision-Based Workflow Action Recognition From Programming Screencasts

Zhao

Xing

Chen

et al. 2019

2019 IEEE/ACM 41st International Conference on Software Engineering (ICSE)

View full text Add to dashboard Cite

Programming screencasts (e.g., video tutorials on Youtube or live coding stream on Twitch) are important knowledge source for developers to learn programming knowledge, especially the workflow of completing a programming task. Nonetheless, the image nature of programming screencasts limits the accessibility of screencast content and the workflow embedded in it, resulting in a gap to access and interact with the content and workflow in programming screencasts. Existing non-intrusive methods are limited to extract either primitive human-computer interaction (HCI) actions or coarse-grained video fragments. In this work, we leverage Computer Vision (CV) techniques to build a programming screencast analysis tool which can automatically extract code-line editing steps (enter text, delete text, edit text and select text) from screencasts. Given a programming screencast, our approach outputs a sequence of coding steps and code snippets involved in each step, which we refer to as programming workflow. The proposed method is evaluated on 41 hours of tutorial videos and live coding screencasts with diverse programming environments. The results demonstrate our tool can extract code-line editing steps accurately and the extracted workflow steps can be intuitively understood by developers.

show abstract

The Potential of AI-Driven Assistants in Scaled Agile Software Development

Saklamaeva,

Pavlič

2023

Applied Sciences

View full text Add to dashboard Cite

Scaled agile development approaches are now used widely in modern software engineering, allowing businesses to improve teamwork, productivity, and product quality. The incorporation of artificial intelligence (AI) into scaled agile development methods (SADMs) has emerged as a potential strategy in response to the ongoing demand for simplified procedures and the increasing complexity of software projects. This paper explores the intersection of AI-driven assistants within the context of the scaled agile framework (SAFe) for large-scale software development, as it stands out as the most widely adopted framework. Our paper pursues three principal objectives: (1) an evaluation of the challenges and impediments encountered by organizations during the implementation of SADMs, (2) an assessment of the potential advantages stemming from the incorporation of AI in large-scale contexts, and (3) the compilation of aspects of SADMs that AI-driven assistants enhance. Through a comprehensive systematic literature review, we identified and described 18 distinct challenges that organizations confront. In the course of our research, we pinpointed seven benefits and five challenges associated with the implementation of AI in SADMs. These findings were systematically categorized based on their occurrence either within the development phase or the phases encompassing planning and control. Furthermore, we compiled a list of 15 different AI-driven assistants and tools, subjecting them to a more detailed examination, and employing them to address the challenges we uncovered during our research. One of the key takeaways from this paper is the exceptional versatility and effectiveness of AI-driven assistants, demonstrating their capability to tackle a broader spectrum of problems. In conclusion, this paper not only sheds light on the transformative potential of AI, but also provides invaluable insights for organizations aiming to enhance their agility and management capabilities.

show abstract

AI-boosted software automation: learning from human pair programmers

Cited by 5 publications

References 8 publications

Context-based intelligent recommendation by code reuse for smart decision support and cognitive adaptive systems

Context-based intelligent recommendation by code reuse for smart decision support and cognitive adaptive systems

ActionNet: Vision-Based Workflow Action Recognition From Programming Screencasts

The Potential of AI-Driven Assistants in Scaled Agile Software Development

Contact Info

Product

Resources

About