System for processing data received from various data sources

• US 9,990,424 B2
• Filed: 05/11/2016
• Issued: 06/05/2018
• Est. Priority Date: 05/09/2013
• Status: Active Grant

• Current Assignee: Ricoh Company Limited
• Original Assignee: Ricoh Company Limited
• Inventors: Motoyama, Tetsuro
• Primary Examiner(s): Le, Debbie
• Application Number:
  US15/152,424
• Publication Number:
  US 20160253414A1
• Time in Patent Office: 755 Days
• Field of Search: None
• CPC Class Codes: G06F 16/353 into predefined classes
• CPC Class Codes: G06F 16/355 Class or cluster creation or modification
• CPC Class Codes: G06F 16/358 Browsing; Visualisation therefor
• CPC Class Codes: G06F 3/0604 Improving or facilitating administration, e.g. storage management
• CPC Class Codes: G06F 3/0638 Organizing or formatting or addressing of data
• CPC Class Codes: G06F 3/0673 Single storage device
• CPC Class Codes: G06F 9/4843 by program, e.g. task dispatcher, supervisor, operating system
• CPC Class Codes: G06V 30/224 of printed characters having additional code marks or containing code marks

Abstract

Techniques are provided for processing and categorizing data received from data sources. The processing and categorizing of the received data comprises: determining whether the digital data can be associated with one or more categories by determining whether a first match between one or more image characteristics of the one or more categories and one or more image characteristics of the digital data is found; in response to determining that the first match is found: associating the one or more categories with the digital data; determining, based at least in part on the one or more categories, one or more applications that are to be used to process the digital data; in response to determining the one or more applications that are to be used to process the digital data, initiating the one or more applications to process the digital data.

Claims

1. An apparatus comprising:

one or more processors;

memory storing one or more sequences of instructions which, when executed by the one or more processors, cause;

receiving digital data;

converting the digital data into text data and identifying a plurality of words in the text data;

determining, based on the plurality of words, one or more characteristics of the text data; and

in response to determining that a first match between the one or more characteristics of the text data and one or more characteristics of one or more categories is found;

determining, based at least in part on the one or more characteristics of one or more categories, one or more first applications that are to be used to process the text data; and

initiating the one or more first applications to process the text data.

2. The apparatus of claim 1, wherein the memory further stores additional instructions which, when executed by the one or more processors, cause:

determining, based on the plurality of words, one or more word characteristics of the text data; and

in response to determining that a second match between the one or more word characteristics of the text data and one or more word characteristics of one or more categories is found;

determining, based at least in part on the one or more word characteristics of one or more categories, one or more second applications that are to be used to process the text data; and

initiating the one or more second applications to process the text data.

3. The apparatus of claim 2, wherein the memory further stores additional instructions which, when executed by the one or more processors, cause:

determining, based on a semantic analysis of the text data, one or more semantic characteristics of the text data; and

in response to determining that a third match between the one or more semantic characteristics of the text data and one or more semantic characteristics of one or more categories is found;

determining, based at least in part on the one or more semantic characteristics of one or more categories, one or more third applications that are to be used to process the text data; and

initiating the one or more third applications to process the text data.

4. The apparatus of claim 3, wherein the memory further stores additional instructions which, when executed by the one or more processors, cause:

performing one or more modifications of any one of;

the one or more characteristics of one or more categories, the one or more word characteristics of one or more categories, the one or more semantic characteristics of one or more categories, or one or more references to any one of;

the one or more first applications, the one or more second applications, or the one or more third applications;

wherein the instructions that cause performing one or more modifications further comprise instructions which, when executed by the one or more processors, cause;

extracting additional characteristic data from an input and decision log;

identifying a decision process resulting in deriving an incorrect decision; and

modifying the decision process resulting in deriving the incorrect decision.

5. The apparatus of claim 4,

wherein the instructions that cause the processors to determine whether a first match between the one or more characteristics of the text data and one or more characteristics of one or more categories is found further comprise instructions which, when executed, cause:

determining a first confidence level value indicating how well the one or more characteristics of the text data match the one or more characteristics of one or more categories;

wherein the instructions that cause the processors to determine whether a second match between the one or more word characteristics of the text data and one or more word characteristics of one or more categories is found further comprise instructions which, when executed, cause;

determining a second confidence level value indicating how well the one or more word characteristics of the text data match the one or more word characteristics of one or more categories; and

wherein the instructions that cause the processors to determine whether a third match between the one or more semantic characteristics of the text data and one or more semantic characteristics of one or more categories is found further comprise instructions which, when executed, cause;

determining a third confidence level value indicating how well the one or more semantic characteristics of the text data match the one or more semantic characteristics of one or more categories.

6. The apparatus of claim 1, wherein the memory further stores additional instructions which, when executed by the one or more processors, cause:

maintaining a category data object for each of one or more categories;

wherein the category data object is generated during a training phase and using one or more sets of training data;

wherein the category data object comprises one or more of;

a main category identifier, one or more levels of one or more subcategories, one or more image characteristics, one or more word characteristics, one or more semantics characteristics, or one or more references to one or more applications; and

wherein a new category may be added to the one or more categories by defining a new category data object, comprising one or more of;

a new main category identifier, one or more levels of one or more new subcategories, one or more new image characteristics, one or more new word characteristics, one or more new semantics characteristics, or one or more new references to the one or more applications.

7. The apparatus of claim 1, wherein the memory further stores additional instructions which, when executed by the one or more processors, cause:

creating and storing an information object for the digital data;

wherein the information object comprises one or more of;

a digital reference to the digital data, a word characteristic reference to the word characteristics, a semantic analysis data reference to the semantic characteristics, an application reference to one or more applications, a category information reference to the one or more categories, or a confidence level reference indicating confidence levels determined for each of the one or more categories.

8. The apparatus of claim 1, wherein the memory further stores additional instructions which, when executed by the one or more processors, cause:

adding a new category using a category editor;

wherein the category editor displays a graphical user interface (GUI) for adding the new category.

9. A non-transitory computer-readable storage medium storing one or more sequences of instructions which, when executed by one or more processors, cause:

receiving digital data;

converting the digital data into text data and identifying a plurality of words in the text data;

determining, based on the plurality of words, one or more characteristics of the text data; and

in response to determining that a first match between the one or more characteristics of the text data and one or more characteristics of one or more categories is found;

determining, based at least in part on the one or more characteristics of one or more categories, one or more first applications that are to be used to process the text data; and

initiating the one or more first applications to process the text data.

10. The non-transitory computer-readable storage medium of claim 9, further storing additional instructions which, when executed by the one or more processors, cause:

determining, based on the plurality of words, one or more word characteristics of the text data; and

in response to determining that a second match between the one or more word characteristics of the text data and one or more word characteristics of one or more categories is found;

determining, based at least in part on the one or more word characteristics of one or more categories, one or more second applications that are to be used to process the text data; and

initiating the one or more second applications to process the text data.

11. The non-transitory computer-readable storage medium of claim 10, further storing additional instructions which, when executed by the one or more processors, cause:

determining, based on a semantic analysis of the text data, one or more semantic characteristics of the text data; and

in response to determining that a third match between the one or more semantic characteristics of the text data and one or more semantic characteristics of one or more categories is found;

determining, based at least in part on the one or more semantic characteristics of one or more categories, one or more third applications that are to be used to process the text data; and

initiating the one or more third applications to process the text data.

12. The non-transitory computer-readable storage medium of claim 11, further storing additional instructions which, when executed by the one or more processors, cause:

performing one or more modifications of any one of;

the one or more characteristics of one or more categories, the one or more word characteristics of one or more categories, the one or more semantic characteristics of one or more categories, or one or more references to any one of;

the one or more first applications, the one or more second applications, or the one or more third applications;

wherein the instructions that cause performing one or more modifications further comprise instructions which, when executed by the one or more processors, cause;

extracting additional characteristic data from an input and decision log;

identifying a decision process resulting in deriving an incorrect decision; and

modifying the decision process resulting in deriving the incorrect decision.

13. The non-transitory computer-readable storage medium of claim 12,

wherein the instructions that cause the processors to determine whether a first match between the one or more characteristics of the text data and one or more characteristics of one or more categories is found further comprise instructions which, when executed, cause:

determining a first confidence level value indicating how well the one or more characteristics of the text data match the one or more characteristics of one or more categories;

wherein the instructions that cause the processors to determine whether a second match between the one or more word characteristics of the text data and one or more word characteristics of one or more categories is found further comprise instructions which, when executed, cause;

determining a second confidence level value indicating how well the one or more word characteristics of the text data match the one or more word characteristics of one or more categories; and

wherein the instructions that cause the processors to determine whether a third match between the one or more semantic characteristics of the text data and one or more semantic characteristics of one or more categories is found further comprise instructions which, when executed, cause;

determining a third confidence level value indicating how well the one or more semantic characteristics of the text data match the one or more semantic characteristics of one or more categories.

14. The non-transitory computer-readable storage medium of claim 9, further storing additional instructions which, when executed by the one or more processors, cause:

maintaining a category data object for each of one or more categories;

wherein the category data object is generated during a training phase and using one or more sets of training data;

wherein the category data object comprises one or more of;

a main category identifier, one or more levels of one or more subcategories, one or more image characteristics, one or more word characteristics, one or more semantics characteristics, or one or more references to one or more applications; and

wherein a new category may be added to the one or more categories by defining a new category data object, comprising one or more of;

a new main category identifier, one or more levels of one or more new subcategories, one or more new image characteristics, one or more new word characteristics, one or more new semantics characteristics, or one or more new references to the one or more applications.

15. The non-transitory computer-readable storage medium of claim 9, further storing additional instructions which, when executed by the one or more processors, cause:

creating and storing an information object for the digital data;

wherein the information object comprises one or more of;

a digital reference to the digital data, a word characteristic reference to the word characteristics, a semantic analysis data reference to the semantic characteristics, an application reference to one or more applications, a category information reference to the one or more categories, or a confidence level reference indicating confidence levels determined for each of the one or more categories.

16. The non-transitory computer-readable storage medium of claim 9, further storing additional instructions which, when executed by the one or more processors, cause:

adding a new category using a category editor;

wherein the category editor displays a graphical user interface (GUI) for adding the new category.

17. A method comprising:

receiving digital data;

converting the digital data into text data and identifying a plurality of words in the text data;

determining, based on the plurality of words, one or more characteristics of the text data; and

in response to determining that a first match between the one or more characteristics of the text data and one or more characteristics of one or more categories is found;

determining, based at least in part on the one or more characteristics of one or more categories, one or more first applications that are to be used to process the text data; and

initiating the one or more first applications to process the text data.

18. The method of claim 17, further comprising:

determining, based on the plurality of words, one or more word characteristics of the text data; and

in response to determining that a second match between the one or more word characteristics of the text data and one or more word characteristics of one or more categories is found;

determining, based at least in part on the one or more word characteristics of one or more categories, one or more second applications that are to be used to process the text data; and

initiating the one or more second applications to process the text data.

19. The method of claim 18, further comprising:

determining, based on a semantic analysis of the text data, one or more semantic characteristics of the text data; and

in response to determining that a third match between the one or more semantic characteristics of the text data and one or more semantic characteristics of one or more categories is found;

determining, based at least in part on the one or more semantic characteristics of one or more categories, one or more third applications that are to be used to process the text data; and

initiating the one or more third applications to process the text data.

20. The method of claim 19, further comprising:

performing one or more modifications of any one of;

the one or more characteristics of one or more categories, the one or more word characteristics of one or more categories, or the one or more semantic characteristics of one or more categories, or one or more references to any one of;

the one or more first applications, the one or more second applications, or the one or more third applications;

wherein performing one or more modifications comprises;

extracting additional characteristic data from an input and decision log;

identifying a decision process resulting in deriving an incorrect decision; and

modifying the decision process resulting in deriving the incorrect decision.