Caractériser la qualité d’une odeur est une tâche complexe qui consiste à identifier un ensemble de descripteurs qui synthétise au mieux la sensation olfactive au cours de séances d’analyse sensorielle. Généralement, cette caractérisation est une liste de descripteurs extraite d’un vocabulaire imposé par les industriels d’un domaine pour leurs analyses sensorielles. Ces analyses représentent un coût significatif pour les industriels chaque année. En effet, ces approches dites orientées reposent sur l’apprentissage de vocabulaires, limitent singulièrement les descripteurs pour un public non initié et nécessitent de couteuses phases d’apprentissage. Si cette caractérisation devait être confiée à des évaluateurs naïfs, le nombre de participants pourrait être significativement augmenté tout en réduisant le cout des analyses sensorielles. Malheureusement, chaque description libre n’est alors plus associée à un ensemble de descripteurs non ambigus, mais à un simple sac de mots en langage naturel (LN). Deux problématiques sont alors rattachées à la caractérisation d’odeurs. La première consiste à transformer des descriptions en LN en descripteurs structurés ; la seconde se donne pour objet de résumer un ensemble de descriptions formelles proposées par un panel d’évaluateurs en une synthèse unique et cohérente à des fins industrielles. Ainsi, la première partie de notre travail se focalise sur la définition et l’évaluation de modèles qui peuvent être utilisés pour résumer un ensemble de mots en un ensemble de descripteurs désambiguïsés. Parmi les différentes stratégies envisagées dans cette contribution, nous proposons de comparer des approches hybrides exploitant à la fois des bases de connaissances et des plongements lexicaux définis à partir de grands corpus de textes. Nos résultats illustrent le bénéfice substantiel à utiliser conjointement représentation symbolique et plongement lexical. Nous définissons ensuite de manière formelle le processus de synthèse d’un ensemble de concepts et nous proposons un modèle qui s’apparente à une forme d’intelligence humaine pour évaluer les résumés alternatifs au regard d’un objectif de synthèse donné. L’approche non orientée que nous proposons dans ce manuscrit apparait ainsi comme l’automatisation cognitive des tâches confiées aux opérateurs des séances d’analyse sensorielle. Elle ouvre des perspectives intéressantes pour développer des analyses sensorielles à grande échelle sur de grands panels d’évaluateurs lorsque l’on essaie notamment de caractériser les nuisances olfactives autour d’un site industriel. / Characterizing the quality of smells is a complex process that consists in identifying a set of descriptors best summarizing the olfactory sensation. Generally, this characterization results in a limited set of descriptors provided by sensorial analysis experts. These sensorial analysis sessions are however very costly for industrials. Indeed, such oriented approaches based on vocabulary learning limit, in a restrictive manner, the possible descriptors available for any uninitiated public, and therefore require a costly vocabulary-learning phase. If we could entrust this characterization to neophytes, the number of participants of a sensorial analysis session would be significantly enlarged while reducing costs. However, in that setting, each individual description is not related to a set of non-ambiguous descriptors anymore, but to a bag of terms expressed in natural language (NL). Two issues are then related to smell characterization implementing this approach. The first one is how to translate such NL descriptions into structured descriptors; the second one being how to summarize a set of individual characterizations into a consistent and synthetic unique characterization meaningful for professional purposes. Hence, this work focuses first on the definition and evaluation of models that can be used to summarize a set of terms into unambiguous entity identifiers selected from a given ontology. Among the several strategies explored in this contribution, we propose to compare hybrid approaches taking advantages of knowledge bases (symbolic representations) and word embeddings defined from large text corpora analysis. The results we obtain highlight the relative benefits of mixing symbolic representations with classic word embeddings for this task. We then formally define the problem of summarizing sets of concepts and we propose a model mimicking Human-like Intelligence for scoring alternative summaries with regard to a specific objective function. Interestingly, this non-oriented approach for identifying the quality of odors appears to be an actual cognitive automation of the task today performed by expert operators in sensorial analysis. It therefore opens interesting perspectives for developing scalable sensorial analyses based on large sets of evaluators when assessing, for instance, olfactory pollution around industrial sites.

Conceptual design is an early stage in the design process, in which functional requirements of a design problem are transformed into solution concepts for satisfying the requirements. It is regarded as a crucial step in design, because decisions made in this stage will strongly affect all the subsequent stages of the design process. Research evidence suggests that inspiration is useful for exploration and discovery of new solution spaces, and exploration of a wide variety of concepts increases the chances of developing more novel, and hence more creative solutions. There are various approaches to providing inspiration, e.g., creativity techniques such as trigger word technique, biomimetics such as Idea-Inspire, and computational synthesis approaches such as compositional synthesis. Computational synthesis tools are used for automated generation of concepts, which can be offered to the designer as triggers for inspiring ideation. The advantage of using solutions from computational synthesis as triggers are the following: the solutions can be produced in a relatively unbiased manner, allowing a variety of directions to be explored, and the solutions are exhaustive within the constraints of the databases or rules used, allowing a multitude of possibilities to be offered. However, computational synthesis has been traditionally used for automating solution generation, rather than creating triggers for designers’ ideation. Notwithstanding their potential for inspiring ideation, current computational synthesis approaches rarely focused on this task. One exception is FuncSION, a compositional synthesis tool, which can automatically synthesize solution concepts for mechanical devices, where a set of input and output characteristics i.e. functional requirements are provided by the user and the computer generates solutions by combining building blocks from a library to satisfy the requirements; these solutions are then used as stimuli for ideation by designers. The focus of this thesis is on evaluating and improving the effectiveness of computational synthesis in triggering ideation during conceptual design, in terms of improving the fluency and variety of the concept space produced. FuncSION has been used as the example synthesis approach on which the work has been focused. In order to evaluate the effectiveness of FuncSION in terms of fluency and variety, a method for assessing variety of a concept space is proposed, and a tool for supporting the assessment process has been developed. However, compositional synthesis research has always assumed that the building blocks are given, and has confined its focus on the process of combining the building blocks. It has not been investigated as to how such building blocks can be automatically identified. If new building blocks can be automatically identified, the resulting change in the library of building blocks would have a substantial effect on the outcomes of compositional synthesis, i.e. the triggers that can be offered to the designers for ideation, with a resulting effect on the concepts generated by the designers. Therefore, in this thesis, an automated method for building blocks synthesis has been proposed, and has been implemented as a computational tool.