System and method for visualization of categories

• US 20050108284A1
• Filed: 09/30/2004
• Published: 05/19/2005
• Est. Priority Date: 06/28/2002
• Status: Abandoned Application

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Rounthwaite, Robert L., Chickering, David Maxwell, Heckerman, David Earl, Tang, Zhaohui, Bocharov, Alexei V., Oveson, Scott Conrad
• Application Number:
  US10/954,669
• Publication Number:
  US 20050108284A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 16/5854 using shape and object relationship
• CPC Class Codes: G06T 11/206 Drawing of charts or graphs
• CPC Class Codes: Y10S 707/917 Text
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

Distribution displays for categories are provided which illuminate the distribution of continuous attributes over all cases in a category, and which provide a histogram of the population of the different states of categorical attributes. An array of such displays by attribute (in one dimension) and category (in another dimension) may be provided. Category diagram displays are also provided for visualizing the different categories, and their distributions, populations, and similarities. These are displayed through different shading of nodes and edges representing categories and the relationship between two categories, and through proximity of nodes.

Claims

1-42. -42. (canceled)

43. A method for displaying category data, where a data set comprises at least two categories, each comprising a category data set, said method comprising:

providing a display where each of said at least two categories is represented by an object, and where each of said at least two categories is connected to each other of said at least two categories by an edge;

accepting a state of a categorical attribute of said data set;

calculating a probability of said state of said categorical attribute in said category data for each of said at least one categories; and

shading each of said objects proportionally to said probability for said category represented by said object.

44. The method of claim 43, where the darkest shading corresponds to a probability of one and the lightest shading corresponds to a probability of zero.

45. A method for displaying category data, where a data set comprises at least two categories, each comprising a category data set, said method comprising:

providing a display where each of said at least two categories is represented by an object, and where each of said at least two categories is connected to each other of said at least two categories by an edge;

accepting a value for a continuous attribute of said data set;

calculating a density at said value of said continuous attribute in said category data for each of said at least one categories; and

shading each of said objects proportionally to said density for said category represented by said object.

46. A method for displaying category data, where a data set comprises at least two categories, each comprising a category data set, said method comprising:

providing a display where each of said at least two categories is represented by an object, and where each of said at least two categories is connected to each other of said at least two categories by an edge;

accepting a range for a value of a continuous attribute of said data set;

calculating a probability that said value of said continuous attribute in said category data for each of said at least one categories falls into said range; and

shading each of said objects proportionally to said probability for said category represented by said object.

47. A method for displaying category data, where a data set comprises at least two categories, each comprising a category data set, said method comprising:

providing a display where each of said at least two categories is represented by an object, and where each of said at least two categories is connected to each other of said at least two categories by an edge;

calculating the number of cases in each of said category data sets; and

shading each of said objects proportionally to number of cases in said category represented by said object.

48. The method of claim 47, where the darkest shading corresponds to the total number of cases in all category data sets.

49. The method of claim 47, where the darkest shading corresponds to the number of cases in largest category data set of all category data sets.

50. A method for displaying category data, where a data set comprises at least two categories, each comprising a category data set, said method comprising:

providing a display where each of said at least two categories is represented by an object, and where each of said at least two categories is connected to each other of said at least two categories by an edge;

calculating similarity for each pair of categories from among said at least two categories; and

shading each edge proportionally to said similarity of the categories represented by the objects connected by said edge.

51. The method of claim 50, where edges connecting objects representing categories with a similarity less than a minimum similarity value are not displayed.

52. The method of claim 50, said method further comprising:

accepting the selection of a selected category from among said at least one category from a user;

coloring each edge connecting an object representing said selected category to another object a first color; and

coloring each edge not connecting an object representing said selected category to another object a second color.

53. A method for displaying category data, where a data set comprises at least two categories, each comprising a category data set, said method comprising:

providing a display where each of said at least two categories is represented by an object, and where each of said at least two categories is connected to each other of said at least two categories by an edge;

accepting the selection of a selected category from among said at least one category from a user;

calculating similarity for said selected category and each other category from among said at least two categories; and

shading each edge proportionally to said similarity of the categories represented by the objects connected by said edge where the darkest shading corresponds to the largest of said calculated similarities and the lightest shading correspond to the smallest of said calculated similarities.

54-96. -96. (canceled)

97. A computer-readable medium comprising computer-executable modules having computer-executable instructions for displaying category data, where a data set comprises at least one category comprising a category data set, said modules comprising:

a module for providing a display where each of said at least two categories is represented by an object, and where each of said at least two categories is connected to each other of said at least two categories by an edge;

a module for accepting a state of a categorical attribute of said data set;

a module for calculating a probability of said state of said categorical attribute in said category data for each of said at least one categories; and

a module for shading each of said objects proportionally to said probability for said category represented by said object.

98. The computer-readable medium of claim 97, where the darkest shading corresponds to a probability of one and the lightest shading corresponds to a probability of zero.

99. A computer-readable medium comprising computer-executable modules having computer-executable instructions for displaying category data, where a data set comprises at least two categories, each comprising a category data set, said modules comprising:

a module for providing a display where each of said at least two categories is represented by an object, and where each of said at least two categories is connected to each other of said at least two categories by an edge;

a module for accepting a value for a continuous attribute of said data set;

a module for calculating a density at said value of said continuous attribute in said category data for each of said at least one categories; and

a module for shading each of said objects proportionally to said density for said category represented by said object.

100. A computer-readable medium comprising computer-executable modules having computer-executable instructions for displaying category data, where a data set comprises at least two categories, each comprising a category data set, said modules comprising:

a module for providing a display where each of said at least two categories is represented by an object, and where each of said at least two categories is connected to each other of said at least two categories by an edge;

a module for accepting a range for a value of a continuous attribute of said data set;

a module for calculating a probability that said value of said continuous attribute in said category data for each of said at least one categories falls into said range; and

a module for shading each of said objects proportionally to said probability for said category represented by said object.

101. A computer-readable medium comprising computer-executable modules having computer-executable instructions for displaying category data, where a data set comprises at least two categories, each comprising a category data set, said modules comprising:

a module for providing a display where each of said at least two categories is represented by an object, and where each of said at least two categories is connected to each other of said at least two categories by an edge;

a module for calculating the number of cases in each of said category data sets; and

a module for shading each of said objects proportionally to number of cases in said category represented by said object.

102. The computer-readable medium of claim 101, where the darkest shading corresponds to the total number of cases in all category data sets.

103. The computer-readable medium of claim 102, where the darkest shading corresponds to the number of cases in largest category data set of all category data sets.

104. A computer-readable medium comprising computer-executable modules having computer-executable instructions for displaying category data, where a data set comprises at least two categories, each comprising a category data set, said modules comprising:

a module for providing a display where each of said at least two categories is represented by an object, and where each of said at least two categories is connected to each other of said at least two categories by an edge;

a module for calculating similarity for each pair of categories from among said at least two categories; and

a module for shading each edge proportionally to said similarity of the categories represented by the objects connected by said edge.

105. The computer-readable medium of claim 104, where edges connecting objects representing categories with a similarity less than a minimum similarity value are not displayed.

106. The computer-readable medium of claim 104, said modules further comprising:

a module for accepting the selection of a selected category from among said at least one category from a user;

a module for coloring each edge connecting an object representing said selected category to another object a first color; and

a module for coloring each edge not connecting an object representing said selected category to another object a second color.

107. A computer-readable medium comprising computer-executable modules having computer-executable instructions for displaying category data, where a data set comprises at least two categories, each comprising a category data set, said modules comprising:

a module for providing a display where each of said at least two categories is represented by an object, and where each of said at least two categories is connected to each other of said at least two categories by an edge;

a module for accepting the selection of a selected category from among said at least one category from a user;

a module for calculating similarity for said selected category and each other category from among said at least two categories; and

a module for shading each edge proportionally to said similarity of the categories represented by the objects connected by said edge where the darkest shading corresponds to the largest of said calculated similarities and the lightest shading correspond to the smallest of said calculated similarities.

108-150. -150. (canceled)

151. A computer device for displaying category data, where a data set comprises at least one category comprising a category data set, said device comprising:

means for providing a display where each of said at least two categories is represented by an object, and where each of said at least two categories is connected to each other of said at least two categories by an edge;

means for accepting a state of a categorical attribute of said data set;

means for calculating a probability of said state of said categorical attribute in said category data for each of said at least one categories; and

means for shading each of said objects proportionally to said probability for said category represented by said object.

152. The computer device of claim 151, where the darkest shading corresponds to a probability of one and the lightest shading corresponds to a probability of zero.

153. A computer device for displaying category data, where a data set comprises at least two categories, each comprising a category data set, said device comprising:

means for providing a display where each of said at least two categories is represented by an object, and where each of said at least two categories is connected to each other of said at least two categories by an edge;

means for accepting a value for a continuous attribute of said data set;

means for calculating a density at said value of said continuous attribute in said category data for each of said at least one categories; and

means for shading each of said objects proportionally to said density for said category represented by said object.

154. A computer device for displaying category data, where a data set comprises at least two categories, each comprising a category data set, said device comprising:

means for providing a display where each of said at least two categories is represented by an object, and where each of said at least two categories is connected to each other of said at least two categories by an edge;

means for accepting a range for a value of a continuous attribute of said data set;

means for calculating a probability that said value of said continuous attribute in said category data for each of said at least one categories falls into said range; and

means for shading each of said objects proportionally to said probability for said category represented by said object.

155. A computer device for displaying category data, where a data set comprises at least two categories, each comprising a category data set, said device comprising:

means for providing a display where each of said at least two categories is represented by an object, and where each of said at least two categories is connected to each other of said at least two categories by an edge;

means for calculating the number of cases in each of said category data sets; and

means for shading each of said objects proportionally to number of cases in said category represented by said object.

156. The computer device of claim 155, where the darkest shading corresponds to the total number of cases in all category data sets.

157. The computer device of claim 155, where the darkest shading corresponds to the number of cases in largest category data set of all category data sets.

158. A computer device for displaying category data, where a data set comprises at least two categories, each comprising a category data set, said device comprising:

means for providing a display where each of said at least two categories is represented by an object, and where each of said at least two categories is connected to each other of said at least two categories by an edge;

means for calculating similarity for each pair of categories from among said at least two categories; and

means for shading each edge proportionally to said similarity of the categories represented by the objects connected by said edge.

159. The computer device of claim 158, where edges connecting objects representing categories with a similarity less than a minimum similarity value are not displayed.

160. The computer device of claim 158, said device further comprising:

means for accepting the selection of a selected category from among said at least one category from a user;

means for coloring each edge connecting an object representing said selected category to another object a first color; and

means for coloring each edge not connecting an object representing said selected category to another object a second color.

161. A computer device for displaying category data, where a data set comprises at least two categories, each comprising a category data set, said device comprising:

means for providing a display where each of said at least two categories is represented by an object, and where each of said at least two categories is connected to each other of said at least two categories by an edge;

means for accepting the selection of a selected category from among said at least one category from a user;

means for calculating similarity for said selected category and each other category from among said at least two categories; and

means for shading each edge proportionally to said similarity of the categories represented by the objects connected by said edge where the darkest shading corresponds to the largest of said calculated similarities and the lightest shading correspond to the smallest of said calculated similarities.

162. (canceled)