| ID | 4.2.7 |
| Title | Learning and Recommending Algorithms |
| Expert | Christian Raeck (FOKUS) |
| Priority | mandatory |
| Description | Learning algorithms capture correlations between user, group, and service behaviour and the current situation. The result of the learning process is stored in a user, group, or service model. In the process of recommending, the recommender retrieves related learning results from the model, applies it in the current situation and gives recommendations to user, group or service. For example the modality recommender gives personalised modality solutions as recommendations based on the learning result from the modality learner and the current context information. |
| Rationale | Each service running on the SPICE platform must be able to adapt its behaviour (e.g. provision of multiple modalities or service contents) to the individual needs, wishes, and interests of a user, group, or service that uses this service. Hence the SPICE platform must be able to learn multiple user, group, and service models based on context information. These models serve as an input for various knowledge inference mechanisms (e.g. recommendations). Furthermore, the SPICE platform should be able to use these learning results and give recommendations that can reflect and meet the individual interests of the user, group or service, therefore the users' time and effort are saved from configuring and interacting with the service and the system platform themselves. The recommendations can be content, modality or service recommendations. |
| Type | functional |
| Depends on | 4.3.5 - Prediction 8.1.2 - Limited push-behaviour of Spice 8.1.3 - Non-biased recommendations and queries results 8.1.5 - No user location tracking w/o user's explicit consent 8.1.6 - Users' rating of consumed services |
| Child dependencies | 4.3.5 - Prediction 7.3.2 - Adaptation Decisions 7.3.4 - Changing the Presentation Modality and Interactive Modality |
| Environment | |
| Other_info | |
| Category | technical;user;device |
| Subcategory | |
| Subcategory2 | |
| Scenario_scene | unified.scene7 unified.scene8 unified.scene11 |
| SPICE_value | (seamless) service adaptation;service matching |
| Demo | |
| Keywords | learning;recommending;algorithm;inferrence;habits;user;history;data;knowledge |
| Home |