Augmented reality allows users to superimpose digital information (typically, of operational type) upon real world entities. The synergy of analytical frameworks and augmented reality opens the door to a new wave of situated OLAP, in which users within a physical environment are provided with immersive analyses of local contextual data. In this paper we propose an approach that, based on the sensed augmented context (provided by wearable and smart devices), proposes a set of relevant analytical queries to the user. This is done by relying on a mapping between the entities that can be recognized by the devices and the elements of the enterprise data, and also taking into account the queries preferred by users during previous interactions that occurred in similar contexts. A set of experimental tests evaluates the proposed approach in terms of efficiency and effectiveness. http://ceur-ws.org/Vol-2324/Paper02-MGolfarelli.pdf

1. Augmented
Business Intelligence
Matteo Francia, Matteo Golfarelli, Stefano Rizzi
DISI – University of Bologna
{m.francia, matteo.golfarelli, stefano.rizzi} @unibo.it

2. Application scope
!
Matteo Francia – University of Bologna 2

3. Application scope
What’s
going on?
Inspector
!
Matteo Francia – University of Bologna 3

4. Application scope
Analytical report
Sensing
Recommending
Matteo Francia – University of Bologna 4
We have data!
• Internet of Things
• Digital twin [1]
[1] Tao, F., Cheng, J., Qi, Q., Zhang, M., Zhang, H., & Sui, F. (2018). Digital twin-driven product design, manufacturing
and service with big data. The International Journal of Advanced Manufacturing Technology, 94(9-12), 3563-3576.

5. Augmented Business Intelligence
A-BI: a 3D-marriage
• Augmented Reality
• Business Intelligence
• Recommendation
Matteo Francia – University of Bologna 5

6. A-BI: Overview
LogAugmented Reality
(real-time)
Query Log
(user exp.)
OLAP reports
Augmented Business Intelligence
Matteo Francia – University of Bologna 6
Data
Sources
Outputs
DM & Mappings
(a-priori)

7. A-BI: Augmented Reality
• Sensing augmented
environments [2]
• Real-time information
• Interaction
• Engagement [3]
• Constrained visualization
• i.e., cardinality constraint
Context
<Device, ConveyorBelt> dist = 0.5m
<Device, TempSensor> dist = 1m
<Role, Inspector>
<Location, RoomA.1> dist = 0m
<Date, 16/10/2018>
Context generation
Matteo Francia – University of Bologna 7
[2] Croatti, A., & Ricci, A. (2017, April). Towards the web of augmented things. In 2017 IEEE International Conference on Software Architecture Workshops (ICSAW)
[3] Su, Y. C., & Grauman, K. (2016, October). Detecting engagement in egocentric video. In European Conference on Computer Vision

8. A-BI: Business Intelligence
Date
Maint.Type
Month
Year
Context
<Device, ConveyorBelt> dist = 0.5m
<Device, TempSensor> dist = 1m
<Role, Inspector>
<Location, RoomA.1> dist = 0m
<Date, 16/10/2018>
Context generation
Device
DeviceType
MaintenanceActivity
Duration
• Data dictionary
• What do we recognize?
• Context: subset of data
dictionary entries
• Mappings to md-elements
• A-priori interest
• OLAP
• Report generation
Matteo Francia – University of Bologna 8
Data Mart

9. A-BI: Recommendation
Context
<Device, ConveyorBelt>
<Role, Inspector>
…
Matteo Francia – University of Bologna 9
1. Get the context
• Context T over data dictionary
• Follow (a-priori) mappings…
• ... Project T to image I of md-elements
2. Add the log L
• Get queries with positive feedback from similar contexts
• Enrich I to I* with «unperceived» elements from T
3. Get the queries
Directly translate I* into a well formed query
• High cardinality I * = hardly interpretable «monster query»
• Single query, no diversification
Log

10. A-BI
A two-step approach:
• Context interpretation
• Diversification
Matteo Francia – University of Bologna 10
Log
Context interpretation
maximal queryContext
<Device, ConveyorBelt>
<Role, Inspector>
…
diversified queries
Diversification

11. A-BI: Context Interpretation
Context interpretation
maximal queryContext
<Device, ConveyorBelt>
<Role, Inspector>
…
Log
Matteo Francia – University of Bologna 11
• md-element relevance
• Context weight
• Mapping weight
• Relevance over log
• Query relevance
• Maximal query
• Most relevant query enforcing cardinality
constraint
• = Knapsack Problem
• Draw most relevant DM-elements
• s.t. query cardinality is below threshold

12. Log
Context interpretation
maximal queryContext
<Device, ConveyorBelt>
<Role, Inspector>
…
A-BI: Diversification
diversified queries
Diversification
Matteo Francia – University of Bologna 12
• Diversification
• Different flavors of same information
• = Top-N queries maximizing diversity and relevance
• Generate queries from the maximal one
• Operators: rollup/drill/slice
• Query similarity sim (with div = 1 – sim) [4]
• q = amount of diversification
qmax
q
[4] Aligon, J., Golfarelli, M., Marcel, P., Rizzi, S., & Turricchia, E. (2014). Similarity
measures for OLAP sessions. Knowledge and information systems, 39(2), 463-489

13. Evaluation
• Effectiveness
• (Near) Real-time
Matteo Francia – University of Bologna 13

14. A-BI: Test setup
• Cube
• 5 linear hierarchies, 5 levels each
• Maximum cardinality 109
• Dictionary with one entry for md-element
• One-to-one mappings (entry → md-element)
• Random context and mapping weights
• Simulate user moving through a factory
• In 10 different rooms (i.e., 10 context seeds)
• 5 to 15 recognized entities
• Simulate multiple visits to rooms
• Generate seed variations
Matteo Francia – University of Bologna 14
Examples of context seeds

15. A-BI: Effectiveness
Matteo Francia – University of Bologna 15
b = target similarity between qu and qmax
Best query (with log, 1 visit)
After 2 visits: 0.95, 4 visits: 0.98
Best query (no log)
Maximal query
sim(bestquery,qu)
|T| = 10, N = 4

16. A-BI: Efficiency
Matteo Francia – University of Bologna 16q = diversity threshold
• Time required to
recommend a query set
• Query execution is then
demanded to DW system

17. Is A-BI out of reach?
Object recognition (YOLO [5])
Egocentric computer vision [6]
Matteo Francia – University of Bologna 17[5] Redmon, J., & Farhadi, A. (2017). YOLO9000: better, faster, stronger. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7263-7271).
[6] Fathi, A., Farhadi, A., & Rehg, J. M. (2011, November). Understanding egocentric activities. In 2011 International Conference on Computer Vision (pp. 407-414). IEEE.

18. Work in progress: relevance of groups
Matteo Francia – University of Bologna 18
• Up to now
• Relevance of single md-elements
• Recommendation address all the elements together
• Proposal: Relevance is about groups of md-elements
• Element a is relevant with b but not with c
• Definition of group relevance rel
• Review formulation to provide recommendation related to groups
• Given rel({Maint.Type}) = 1 and rel({Duration}) = 1
• rel({Maint.Type, Duration}) = 2.5
• rel({Device, Month}) > rel({Device, Date})

19. Work in progress: query generation
Matteo Francia – University of Bologna 19
• Up to now
• Recommendation as a two-step approach
• Proposal: Optimal formulation for query generation
• Single-step formulation inspired by mutual information
• Minimize amount of information about one query obtained through other query(s)
• Definition and maximization of global relevance relG
• Overlapping queries (i.e., similar queries) → high mutual information
query q’ query q’’
sim(q’, q’’)
relG( ) < relG( )query q’ query q’’’

20. Conclusion
Augmented Business Intelligence
• Recommendation of multi-dimensional analytic reports
• Based on augmented (real) environments
• Under near-real-time and visualization constraints
• Vision
• Analytics in Health-care
• Conversational BI
Matteo Francia – University of Bologna 20

21. Thanks
Matteo Francia – University of Bologna 21