Method and system for classification of venue by analyzing data from venue website

• US 8,918,369 B2
• Filed: 06/05/2008
• Issued: 12/23/2014
• Est. Priority Date: 06/05/2008
• Status: Active Grant

• Current Assignee: Craze, Inc.
• Original Assignee: Craze, Inc.
• Inventors: Sanguinetti, Thomas V., Sanguinetti, Dave T., Ploetner, Jeffrey S.
• Primary Examiner(s): CHANNAVAJJALA, SRIRAMA T
• Application Number:
  US12/134,126
• Publication Number:
  US 20090307238A1
• Time in Patent Office: 2,392 Days
• Field of Search: 707/609, 707/687, 707/694, 707695-700, 707705-711, 707723-731, 707747-753, 707/755, 707776-777, 707/688, 707/736, 707/758, 706 45- 50, 715205-209, 715233-235
• US Class Current: 707/688
• CPC Class Codes: G06F 16/00 Information retrieval; Database structures therefor; File system structures therefor
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0627 using item specifications
• CPC Class Codes: G06Q 50/12 Hotels or restaurants

Abstract

A method and system classifies a venue by analyzing venue data from a venue website. The method includes receiving preliminary venue-related data. The method includes scanning the venue website to retrieve venue data, wherein scanning the venue website includes retrieving the venue data from HTML pages, text documents, PDF documents, and images. The method includes retrieving verifiable venue data from the venue data. The verifiable venue data is a subset of the venue data. The method includes analyzing the verifiable venue data by comparing the verifiable venue data to the preliminary venue-related data and determining a probability level for the venue URL from the comparison. If the probability level for the venue URL is equal or greater than a first probability level, the venue website data is further analyzed to extract attributes and attribute counts in a robust and context-sensitive way. The method includes determining the percentage of the attribute representation from the total number of preselected attributes in the venue data and classifying the venue based on the percentage of the attribute representation.

Claims

1. A method for classifying a venue by analyzing venue data from a venue website, comprising:

receiving preliminary venue-related data including a venue URL;

scanning the venue website to retrieve venue data;

retrieving verifiable venue data from the venue data, the verifiable venue data being a subset of the venue data;

analyzing, using a computer, the verifiable venue data by comparing the verifiable venue data to the preliminary venue-related data;

determining a probability level for the venue URL from the comparison;

if the probability level for the venue URL is equal or greater than a first probability level, determining the number of selected attributes in the venue data;

determining the percentage of the attribute representation from the total number of preselected attributes in the venue data; and

classifying the venue based on the percentage of the attribute representation.

2. The method of claim 1, further comprising:

determining attribute distance association by identifying correlation of attributes;

quantifying attribute similarities from the attribute distance association;

comparing the classified venue to other venues based on quantified attribute similarities.

3. The method of claim 1, further comprising:

classifying the atmosphere of the venue based on the attributes.

4. The method of claim 1, wherein the classification of the venue further comprises:

assigning a classifier factor for each selected attribute in the venue data;

classifying the venue from the assigned classifier factors, wherein the classifier factor is an activity factor.

5. A computer-implemented method for determining attributes of a venue, the method comprising steps to:

analyze first data associated with a first venue to identify a first set of venue attributes associated with the first venue;

analyze second data associated with a second venue to identify a second set of venue attributes associated with the second venue;

compare, using a computing device, the first set of venue attributes with the second set of venue attributes; and

determine, based on comparing the first set and the second set, a level of similarity between the first venue and the second venue.

6. The method of claim 5, wherein one or more venue attributes of the first set are identified based on an existence of synonymous words in the first data.

7. The method of claim 5, the method further comprising steps to:

determine a first number of occurrences that a first venue attribute of the first set appears in the data.

8. The method of claim 7, wherein the first number of occurrences includes occurrences of a first word and a second word in the data, wherein the first word and the second word have synonymous meanings.

9. The method of claim 7, the method further comprising steps to:

determine, for each remaining venue attribute of the first set, a respective number of occurrences that the respective venue attribute appears in the data.

10. The method of claim 9, the method further comprising steps to:

sum the first number of occurrences with each of the respective number of occurrences to achieve a total number of occurrences;

determine a first ratio between the first number of occurrences and the total number of occurrences; and

determine a relative attribute prominence for the first venue attribute based on the first ratio and other data associated with other venues.

11. The method of claim 5, the method further comprising steps to:

determine a first inferred attribute of the venue based on the data, wherein the venue attributes include the first inferred attribute.

12. The method of claim 11, the method further comprising steps to:

determine the first inferred attribute based on an existence of a first venue attribute and a second venue attribute in the first set of venue attributes.

13. The method of claim 12, the method further comprising steps to:

determine the first inferred attribute based on a comparison between a first number of occurrences of the first venue attribute in the data and a second number of occurrences of the second venue attribute in the data.

14. The method of claim 11, the method further comprising steps to:

determine the first inferred attribute based on there not being a particular venue attribute among the first set of venue attributes.

15. The method of claim 11, the method further comprising steps to:

determine the first inferred attribute based on an existence, in the data, of a first word from among a group of synonymous words.

16. The method of claim 15, wherein the first word is a fancy or elegant word compared to other synonymous words in the group, and wherein the first inferred attribute indicates that the venue is high-end or upscale compared to other venues.

17. The method of claim 15, the method further comprising steps to:

determine a different inferred attribute for a different venue based on an existence, in different data associated with the different venue, of a second word from among the group of synonymous words.

18. The method of claim 5, the method further comprising steps to:

identify a first venue attribute from the first set of venue attributes;

determine an attribute distance association related to a co-occurrence of the first venue attribute and a different venue attribute in other data associated with other venues.

19. The method of claim 18, the method further comprising steps to:

identify one or more venues from the other venues that are associated with the different venue attribute; and

determine levels of similarity between the first venue and the one or more venues based on the attribute distance association relating to the first venue attribute and the different venue attribute.

20. The method of claim 5, the method further comprising steps to:

analyze other data associated with other venues to determine possible attributes from which the venue attributes are identified.

21. A system for determining attributes of a venue, the system comprising one or more processors that are operable to:

analyze first data associated with a first venue to identify a first set of venue attributes associated with the first venue;

analyze second data associated with a second venue to identify a second set of venue attributes associated with the second venue;

compare, using a computing device, the first set of venue attributes with the second set of venue attributes; and

determine, based on comparing the first set and the second set, a level of similarity between the first venue and the second venue.

22. The system of claim 21, wherein the one or more processors are further operable to:

determine a first number of occurrences that a first venue attribute of the first set appears in the data, wherein the first number of occurrences includes occurrences of a first word and a second word in the data, wherein the first word and the second word have synonymous meanings;

determine, for each remaining venue attribute of the first set, a respective number of occurrences that the respective venue attribute appears in the data;

sum the first number of occurrences with each of the respective number of occurrences to achieve a total number of occurrences;

determine a first ratio between the first number of occurrences and the total number of occurrences;

determine a relative attribute prominence for the first venue attribute based on the first ratio and other data associated with other venues;

determine a first inferred attribute of the venue based on the data, wherein the venue attributes include the first inferred attribute;

determine the first inferred attribute based on an existence of a first venue attribute and a second venue attribute in the first set of venue attributes;

determine the first inferred attribute based on a comparison between a first number of occurrences of the first venue attribute in the data and a second number of occurrences of the second venue attribute in the data;

identify a first venue attribute from the first set of venue attributes;

determine an attribute distance association related to a co-occurrence of the first venue attribute and a different venue attribute in other data associated with other venues;

identify one or more venues from the other venues that are associated with the different venue attribute; and

determine levels of similarity between the first venue and the one or more venues based on the attribute distance association relating to the first venue attribute and the different venue attribute.

23. A computer program product comprising a non-transitory computer usable medium having a computer readable program code embodied therein, said computer readable program code adapted to be executed to implement a method for determining attributes of a venue, the method comprising steps to:

analyze first data associated with a first venue to identify a first set of venue attributes associated with the first venue;

analyze second data associated with a second venue to identify a second set of venue attributes associated with the second venue;

compare, using a computing device, the first set of venue attributes with the second set of venue attributes; and

determine, based on comparing the first set and the second set, a level of similarity between the first venue and the second venue.

24. The computer program product of claim 23, the method further comprising steps to:

determine a first number of occurrences that a first venue attribute of the first set appears in the data, wherein the first number of occurrences includes occurrences of a first word and a second word in the data, wherein the first word and the second word have synonymous meanings;

determine, for each remaining venue attribute of the first set, a respective number of occurrences that the respective venue attribute appears in the data;

sum the first number of occurrences with each of the respective number of occurrences to achieve a total number of occurrences;

determine a first ratio between the first number of occurrences and the total number of occurrences;

determine a relative attribute prominence for the first venue attribute based on the first ratio and other data associated with other venues;

determine a first inferred attribute of the venue based on the data, wherein the venue attributes include the first inferred attribute;

determine the first inferred attribute based on an existence of a first venue attribute and a second venue attribute in the first set of venue attributes;

determine the first inferred attribute based on a comparison between a first number of occurrences of the first venue attribute in the data and a second number of occurrences of the second venue attribute in the data;

identify a first venue attribute from the first set of venue attributes;

determine an attribute distance association related to a co-occurrence of the first venue attribute and a different venue attribute in other data associated with other venues;

identify one or more venues from the other venues that are associated with the different venue attribute; and

determine levels of similarity between the first venue and the one or more venues based on the attribute distance association relating to the first venue attribute and the different venue attribute.