This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision Last revision Both sides next revision | ||
teaching:mfe:ia [2022/11/30 13:34] stuetzle [Text Categorisation and quality control through automatic language processing] |
teaching:mfe:ia [2024/07/01 16:14] stuetzle |
||
---|---|---|---|
Line 243: | Line 243: | ||
- | ===== Automated summaries of long or multiple texts through automated language processing ===== | + | ===== Autonomous AI agents to help in online sales ===== |
- | This thesis is developed in collaboration with the Energy Efficiency in Industrial Processes (EEIP) company. EEIP is a global industry information network. As part of their activities, they disseminate articles, reports and case studies to their global network of 150.000 business professionals. EEIP has already implemented an ALP algorithm (Bidirectional and Auto-Regressive Transformer (BART)) to summarize articles with a length of max. 1500 words. This solution is the result of a former thesis which was completed in 2021. | + | This thesis is developed in collaboration with the Energy Efficiency in Industrial Processes (EEIP) company. EEIP is a global industry information network. As part of their activities, they disseminate articles, reports and case studies to their global network of 150.000 business professionals. Currently, EEIP is about to start a mobile quiz as a serious gaming application including a content marketing service. EEIP wants autonomous AI agents to help in online sales for this business-to-business (B2B) online marketing services. |
- | + | ||
- | The main goal of this project is to develop an automatic language processing algorithm and process capable of summarizing long text (e.g. reports, 25-100 pages long) and multiple texts into a single summaries (e.g. 3 articles dealing with implementation of smart pump systems in industry). | + | “Autonomous AI agents, at their core, are intelligent entities capable of decision-making and action execution without direct human intervention. These agents leverage advanced algorithms and machine learning models to analyze data, draw insights, and execute tasks autonomously.” Source:https://www.analyticsvidhya.com/blog/2023/12/autonomous-ai-agents/#:~:text=Autonomous%20AI%20Agents%2C%20at%20their,insights%2C%20and%20execute%20tasks%20autonomously |
- | + | ||
- | Testing and training the algorithm is a key part, during the development (thesis-) phase but also after being in operation to improve the quality based on manual feedback via corrected summaries. A specific challenge is represented by the limited data environment (+/- 1000 case studies as training set), likely requiring using external test data sets during development. | + | The main goal of this thesis is to develop an autonomous AI agent which can help and execute autonomously the process of the online sales of the B2B content marketing service. To this aim, the scope of the thesis is to design an autonomous AI agent which can serve as a sales agent identifying sales prospects, contacting and interacting with them up to guiding them through a sales process to close the deal. |
+ | |||
+ | The particular scope of the master thesis is open for discussion. | ||
- | A possible extension could be the pre-selection of external content (articles, case studies and reports) by analysing its relevance for EEIP based on fit with the thematic categories EEIP is using to represent the energy transition. This could be based on categorization capabilities of the new ALP algorithm or in conjunction with the algorithm used in EEIP’s recommendation engine. | ||
* Contacts : | * Contacts : | ||
Line 401: | Line 402: | ||
* [[http://iridia.ulb.ac.be/~stuetzle|Thomas Stützle (IRIDIA)]] | * [[http://iridia.ulb.ac.be/~stuetzle|Thomas Stützle (IRIDIA)]] | ||
* [[http://code.ulb.ac.be/iridia.people.php?id=1388|Federico Pagnozzi (IRIDIA)]] | * [[http://code.ulb.ac.be/iridia.people.php?id=1388|Federico Pagnozzi (IRIDIA)]] | ||
+ | |||
+ | |||
+ | ===== Automated configuration of multi-objective algorithms ===== | ||
+ | |||
+ | We have recently developed a software framework from which hybrid local search algorithms can be designed automatically. This framework has only been applied to a few problems. The goal of this project would be to extend this framework to multi-objective problems and start by including Pareto local search and two-phase local search algorithms and showing that it actually can obtain state-of-the-art results on one or various multi-objective problems. The student will learn to solve combinatorial optimization problems with heuristic algorithms, automatic configuration of optimization algorithms, and the analysis and comparison of optimization algorithms. | ||
+ | |||
+ | * Contacts : | ||
+ | * [[http://iridia.ulb.ac.be/~stuetzle|Thomas Stützle (IRIDIA)]] | ||
+ | * [Yunshuang Xiao (IRIDIA)]] | ||