Classification and storage of documents

• US 9,870,420 B2
• Filed: 01/19/2015
• Issued: 01/16/2018
• Est. Priority Date: 01/19/2015
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Meyer, Cayden, Onofrio, Joel Christopher
• Primary Examiner(s): Vy, Hung T
• Application Number:
  US14/599,793
• Publication Number:
  US 20160210347A1
• Time in Patent Office: 1,093 Days
• Field of Search: 707378, 707756, 707769, 707706, 726 23
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/353 into predefined classes
• CPC Class Codes: G06F 16/93 Document management systems

Abstract

A method includes defining a plurality of known document types, obtaining a collection of previously classified documents that are each associated with one of the known document types, and extracting features from each document from the collection of previously classified documents to define feature information. The method also includes obtaining a subject document that is associated with a user, extracting one or more features from the subject document, comparing the one or more features from the subject document to the feature information, associating the subject document with one of the known document types based on the comparison, and transmitting the document to a cloud storage system for storage in a dedicated storage location that is associated with the user and contains only documents of the respective known document type that is associated with the subject document.

Claims

1. A method comprising:

defining a plurality of known document types that are each associated with feature information that is determined for a respective known document type by extracting features from manually classified documents that were each identified as corresponding to the respective known document type by a manual classification input;

monitoring an email account associated with a user to detect that an email message has been received at the email account associated with the user, wherein a subject document is included as an attachment to the email message; and

processing the subject document without action by the user, in response to detecting that the email message has been received, including the steps of;

extracting one or more features from the subject document,

comparing the one or more features from the subject document to the feature information,

determining a document type of the subject document from the plurality of known document types based on the comparison of the one or more features from the subject document to the feature information,

selecting a dedicated storage location at a cloud storage system from a plurality of dedicated storage locations associated with the user based on the respective known document type that is associated with the subject document, wherein each of the plurality of dedicated storage locations corresponds to a respective folder of a hierarchical storage structure of the cloud storage system, and wherein the selected dedicated storage location is associated with the user and contains only documents of the respective known document type, and

transmitting the subject document to a cloud storage system for storage in the selected dedicated storage location.

2. The method of claim 1, wherein the subject document is a photograph.

3. The method of claim 1, wherein the one or more features are alphanumeric text-based features that include at least one of text size, text font, text positioning, or substantive text content.

4. An apparatus comprising:

a memory; and

a processor configured to execute instructions stored in the memory to;

define a plurality of known document types that are each associated with feature information that is determined for a respective known document type by extracting features from manually classified documents that were each identified as corresponding to the respective known document type by a manual classification input,

monitor an email account associated with a user to detect that an email message has been received at the email account associated with the user, wherein a subject document is included as an attachment to the email message, and

process the subject document without action by the user, in response to detecting that the email message has been received, by executing further instruction stored in the memory to;

extract one or more features from the subject document,

compare the one or more features from the subject document to the feature information,

determine a document type of the subject document from the plurality of known document types based on the comparison of the one or more features from the subject document to the feature information,

select a dedicated storage location at a cloud storage system from a plurality of dedicated storage locations associated with the user based on the respective known document type that is associated with the subject document, wherein each of the plurality of dedicated storage locations corresponds to a respective folder of a hierarchical storage structure of the cloud storage system, and wherein the selected dedicated storage location is associated with the user and contains only documents of the respective known document type, and

transmit the subject document to a cloud storage system for storage in the selected dedicated storage location.

5. The apparatus of claim 4, wherein the subject document is a photograph.

6. The apparatus of claim 4, wherein the one or more features are alphanumeric text-based features that include at least one of text size, text font, text positioning, or substantive text content.

7. A method comprising:

obtaining a document that is associated with a user;

extracting one or more features from the document, wherein the one or more features are alphanumeric text-based features that include at least one of text size, text font, text positioning, or substantive text content;

comparing the one or more features from the document to receipt feature information describing features extracted from a collection of sales receipts;

determining that a document of type of the document is a sales receipt from a plurality of known document types based on the comparison of one or more features from the document to the receipt feature information;

selecting a dedicated storage location at a cloud storage system from a plurality of dedicated storage locations associated with the user based on the determination that the document is a sales receipt, wherein each of the plurality of dedicated storage locations corresponds to a respective folder of a hierarchical storage structure of the cloud storage system, and wherein the selected dedicated storage location is associated with the user and contains only sales receipt documents; and

transmitting the document to a cloud storage system for storage in the selected dedicated storage location.

8. The method of claim 7, wherein the document is an attachment to an email message.

9. The method of claim 7, wherein obtaining the document includes monitoring, without action by the user, an email account associated with a user to detect that an email message has been received at the email account associated with the user, and storing a copy of an email attachment from the email message as the document.

10. The method of claim 7, wherein the document is a photograph.

11. The method of claim 10, wherein obtaining the document includes monitoring, without action by the user, a collection of photographs that are associated with the user and storing a copy of a newly added photograph from the collection of photographs as the document.

12. An apparatus comprising:

a memory; and

a processor configured to execute instructions stored in the memory to;

obtain a document that is associated with a user,

extract one or more features from the document, wherein the one or more features are alphanumeric text-based features that include at least one of text size, text font, text positioning, or substantive text content,

compare the one or more features from the document to receipt feature information describing features extracted from a collection of sales receipts,

determine that a document type of the document is a sales receipt from a plurality of known document types based on the comparison of one or more features from the document to the receipt feature information,

select a dedicated storage location at a cloud storage system from a plurality of dedicated storage locations associated with the user based on the determination that the document is a sales receipt, wherein each of the plurality of dedicated storage locations corresponds to a respective folder of a hierarchical storage structure of the cloud storage system, and wherein the selected dedicated storage location is associated with the user and contains only sales receipt documents, and

transmit the document to a cloud storage system for storage in the selected dedicated storage location that is associated with the user.

13. The apparatus of claim 12, wherein the document is an attachment to an email message.

14. The apparatus of claim 12, wherein obtaining the document includes monitoring, without action by the user, an email account associated with a user to detect that an email message has been received at the email account associated with the user, an email message and storing a copy of an email attachment from the email message as the document.

15. The apparatus of claim 12, wherein the document is a photograph.

16. The apparatus of claim 15, wherein the processor executes further instructions to obtain the document by monitoring, without action by the user, a collection of photographs that are associated with the user and storing a copy of a newly added photograph from the collection of photographs as the document.