Methods and systems for interpretable user behavior profiling in off-street parking

• US 10,089,640 B2
• Filed: 02/26/2015
• Issued: 10/02/2018
• Est. Priority Date: 02/26/2015
• Status: Active Grant

• Current Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Original Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Inventors: de Souza, Cesar Roberto, Chidlovskii, Boris, Roulland, Frederic, Ulloa Paredes, Luis Rafael
• Primary Examiner(s): Obaid, Fateh M
• Application Number:
  US14/632,207
• Publication Number:
  US 20160253681A1
• Time in Patent Office: 1,314 Days
• Field of Search: None
• CPC Class Codes: G06F 16/2465 Query processing support for facilitating data mining operations in structured databases
• CPC Class Codes: G06F 16/26 Visual data mining; Browsing structured data
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data

Abstract

Methods and systems for interpretable user behavior profiling in off-street parking applications. To render user profiles easy to interpret by decision makers, the semi-automatic discovery and tagging of user profiles can be implemented. Transaction data from one or more (and geographically close) off-street parking installations can be implemented. An analysis of spatio-temporal behavioral patterns can be implemented based on representation of any parking episode by a set of heterogeneous features, the use of clustering methods for automatic pattern discovery, an assessment of obtained clusters, semi-automatic identification/tagging of space-temporal patterns, and a user-friendly interpretation of obtained patterns.

Claims

1. A parking lot usage profiling method for improving a parking management system, said method comprising:

collecting transaction data from at least one off-street parking area utilizing at least one data extractor among a plurality of data extractors;

analyzing said transaction data with respect to spatio-temporal behavioral patterns using machine learning that includes feature extraction with respect to said transaction data collected from said at least one off-street parking area utilizing said at least one data extractor among said plurality of data extractors;

compiling user profiles from said transaction data in at least one database that communicates with said at least one data extractor, in response to analyzing said transaction data with respect to spatio-temporal behavioral patterns with respect to said at least one off-street parking area; and

providing a visualization engine for visualizing said user profiles and other data, wherein said visualization engine includes a GUI (Graphical User Interface) for visualizing parking and traffic data and implementing a framework for creating, testing, and exploring data processing techniques in geo-spatial data with ease, said GUI comprising a profiling tool displayed in a secondary screen of said GUI that allows said user to select and create a clustering module, and wherein said profiling tool further automatically creates profiles from suggested options that are capable of being manually overridden for exploratory purposes in a third screen of said GUI, wherein said spatio-temporal behavior patterns include said geo-spatial data and wherein said parking and traffic data include said transaction data, which results in improvements in the functioning of said parking management system and user profiling in off-street parking applications.

2. The method of claim 1 further comprising analyzing said transaction data with respect to said spatio-temporal behavioral patterns based on a representation of any parking episode via a set of heterogeneous features by transforming said transaction data into angular variables and incorporating sine and cosine components thereof in feature vectors.

3. The method of claim 1 further comprising analyzing said transaction data with respect to said spatio-temporal behavioral patterns based on clusters of said transaction data for automatic pattern discovery wherein said clusters are provided by said clustering module.

4. The method of claim 1 further comprising analyzing said transaction data with respect to said spatio-temporal behavioral patterns based on an assessment of obtained clusters of said transaction data, wherein said obtained clusters are obtained from said clustering module.

5. The method of claim 4 further comprising:

analyzing said transaction data with respect to said spatio-temporal behavioral patterns based on semi-automatic identification and tagging of said spatio-temporal behavioral patterns, said tagging including at least one tag associated with at least one template among a plurality of templates.

6. The method of claim 1 further comprising analyzing said transaction data with respect to said spatio-temporal behavioral patterns based on an interpretation of said spatio-temporal behavioral patterns wherein said spatio-temporal behavioral patterns include temporal variables comprising circular variables, wherein each circular variable among said circular variables are decomposed into two components, wherein said two components are used for clustering by said clustering module.

7. The method of claim 2 wherein said GUI allows for selecting via said profiling tool of said GUI, varying user characteristics judged relevant for use in compiling at least one user profile among said user profiles and wherein said feature vectors are preprocessed based on balancing weights between every said feature vector among said feature vectors to that said feature vectors are handled by said machine learning, said machine learning comprising unsupervised learning.

8. The method of claim 3 further comprising:

saving generated clusterings with respect to said clusters in said at least one database, wherein said generated clusterings are generated by said clustering module; and

visualizing said generated clusterings and said clusters via said GUI which includes a graphically displayed data visualization tool that displays said generated clusterings and said clusters.

9. The method of claim 8 further comprising:

automatically determining a number of said clusters from said transaction data without a user intervention; and

displaying a statistical analysis of recursively segmented views of said clusters after said clusters are created.

10. The method of claim 1 further comprising automatically describing at least one of said clusters and said user profile by extracting data from utilizing a user-interpretable data mining/machine learning technique.

11. A parking lot usage profiling system that improves a parking management system, said system comprising:

at least one processor; and

a computer-usable medium embodying computer program code, said computer-usable medium capable of communicating with said at least one processor, said computer program code comprising instructions executable by said at least one processor and configured for;

collecting transaction data from at least one off-street parking area utilizing at least one data extractor among a plurality of data extractors;

analyzing said transaction data with respect to spatio-temporal behavioral patterns using machine learning that includes feature extraction with respect to said transaction data collected from said at least one off-street parking area utilizing said at least one data extractor among said plurality of data extractors;

compiling user profiles from said transaction data in at least one database that communicates with said at least one data extractor, in response to analyzing said transaction data with respect to spatio-temporal behavioral patterns with respect to said at least one off-street parking area; and

providing a visualization engine for visualizing said user profiles and other data, wherein said visualization engine includes a GUI (Graphical User Interface) for visualizing parking and traffic data and implementing a framework for creating, testing, and exploring data processing techniques in geo-spatial data with ease, said GUI comprising a profiling tool displayed in a secondary screen of said GUI that allows said user to select and create a clustering module, and wherein said profiling tool further automatically creates profiles from suggested options that are manually overridden for exploratory purposes in a third screen of said GUI, wherein said spatio-temporal behavior patterns include said geo-spatial data and wherein said parking and traffic data include said transaction data, which results in improvements in the functioning of said parking management system and user profiling in off-street parking applications.

12. The system of claim 11 wherein said instructions for analyzing said transaction data with respect to said spatio-temporal behavioral patterns are based on a representation of any parking episode via a set of heterogeneous features by transforming said transaction data into angular variables and incorporating sine and cosine components thereof in feature vectors.

13. The system of claim 11 wherein said instructions for analyzing said transaction data with respect to said spatio-temporal behavioral patterns are based on clusters of said transaction data for automatic pattern discovery.

14. The system of claim 11 wherein said instructions for analyzing said transaction data with respect to said spatio-temporal behavioral patterns are based on an assessment of obtained clusters of said transaction data, wherein said obtained clusters are obtained by said clustering module.

15. The system of claim 14 wherein said instructions for analyzing said transaction data with respect to said spatio-temporal behavioral patterns are based on semi-automatic identification and tagging of said spatio-temporal behavioral patterns, said tagging including at least one tag associated with at least one template among a plurality of templates.

16. The system of claim 12 wherein said instructions for analyzing said transaction data with respect to said spatio-temporal behavioral patterns are based on an interpretation of said spatio-temporal behavioral patterns wherein said spatio-temporal behavioral patterns include temporal variables comprising circular variables, wherein each circular variable among said circular variables are decomposed into two components, wherein said two components are used for clustering by said clustering module.

17. The system of claim 11 wherein said instructions are further configured for selecting via said GUI, varying user characteristics judged relevant for use in compiling at least one user profile among said user profiles and wherein said feature vectors are preprocessed based on balancing weights between every said feature vector among said feature vectors to that said feature vectors are handled by said machine learning, said machine learning comprising unsupervised learning.

18. The system of claim 13 wherein said instructions are further configured for:

saving generated clusterings with respect to said clusters in said at least one database, said generated clusterings generated via said clustering module; and

visualizing said generated clusterings and said clusters via said GUI which includes a graphically displayed data visualization tool that displays said generated clusterings and said clusters provided by said clustering module.

19. The system of claim 18 wherein said instructions are further configured for:

automatically determining a number of said clusters from said transaction data without a user intervention; and

displaying a statistical analysis of recursively segmented views of said clusters after said clusters are created via said clustering module.