Method for filtering content using neural networks

• US 7,487,132 B2
• Filed: 07/25/2003
• Issued: 02/03/2009
• Est. Priority Date: 01/06/2000
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Auvenshine, John Jason
• Primary Examiner(s): SALAD, ABDULLAHI ELMI
• Application Number:
  US10/628,000
• Publication Number:
  US 20040019650A1
• Time in Patent Office: 2,020 Days
• Field of Search: 709/206, 709/224, 706 14- 25, 707/5
• US Class Current: 706/15
• CPC Class Codes: G06F 16/00 Information retrieval; Database structures therefor; File system structures therefor

Abstract

Provided is a method for filtering communications received from over a network for a person-to-person communication program. A communication is received for the person-to person communication program. The communication is processed to determine predefined language statements. Information on the determined language statements is inputted into a neural network to produce an output value. A determination is made as to whether the output value indicates that the communication is unacceptable. The communication is forwarded to the person-to-person communication program unchanged if the output value indicates that the communication is acceptable. An action is performed with respect to the communication upon determining that the communication is unacceptable that differs from the forwarding of the communication that occurs if the output value indicates that the communication is acceptable.

Claims

1. A method for filtering communications received from over a network for a person-to-person communication program, comprising:

receiving a communication for the person-to person communication program;

processing the communication to determine predefined language statements;

inputting information on the determined language statements into a neural network to produce an output value;

determining whether the output value indicates that the communication is unacceptable;

forwarding the communication to the person-to-person communication program unchanged if the output value indicates that the communication is acceptable; and

performing an action with respect to the communication upon determining that the communication is unacceptable that differs from the forwarding of the communication that occurs if the output value indicates that the communication is acceptable.

2. The method of claim 1, wherein the person-to-person communication program is intended for use in a work environment, and wherein determining predefined language statements comprises determining non-work related terms that are often searched for by employees.

3. The method of claim 2, wherein the neural network includes an input node for each predefined language statement and wherein inputting the information on the determined non-work related statements comprises inputting a value related to number of occurrences of each non-work related statement on the input node corresponding to the non-work related statement.

4. The method of claim 3, wherein the non-work related statements are members of the set of statement types comprising at least one of:

sport scores, stock quotes, news, hate words, and sexually explicit words.

5. The method of claim 1, wherein the person-to-person communication program is intended for use by a user at a predetermined age level, and wherein determining predefined language statements comprises determining inappropriate terms for the predetermined age level.

6. The method of claim 5, wherein the neural network includes an input node for each inappropriate term for the predetermined age level and wherein inputting the information on the determined inappropriate terms for the predetermined age level comprises inputting a value related to a number of occurrences of each inappropriate term for the predetermined age level on the input node corresponding to the inappropriate term for the predetermined age level.

7. The method of claim 5, wherein the inappropriate terms for the predetermined age level are members of the set of statement types comprising:

inappropriate sexual references for the predetermined age level, inappropriate swear words for the predetermined age level, and inappropriate hate words for the predetermined age level.

8. The method of claim 1, wherein the person-to-person communication program comprises an email program or instant messaging program.

9. The method of claim 1, wherein the communication is received in packets that together comprise the entire communication, and wherein each packet is processed to determine predefined language statements.

10. The method of claim 1, wherein processing the communication comprises determining a weighted number of occurrences of predefined language statements, wherein the neural network includes an input node for each predefined language statement and wherein inputting the information on the determined language statements comprises inputting the weighted number of occurrences of each predefined language statement on the input node corresponding to the predefined language statement.

11. The method of claim 10, wherein the predefined language statements include unacceptable language statements and content language statements, further comprising:

determining proximity of predefined content and unacceptable language statements; and

inputting information on the proximity of the predefined language statements at input nodes, wherein the output value is based on the number of occurrences of unacceptable and content language statements and the proximity of content and unacceptable language statements.

12. The method of claim 1, wherein performing the action with respect to the communication upon determining that the communication is unacceptable comprises inhibiting the person-to-person communication program access to the communication.

13. The method of claim 12, wherein inhibiting the person-to-person communication program access to the communication upon determining that the communication is unacceptable comprises blocking access to the entire communication.

14. The method of claim 12, further comprising determining language statements in the communication that are unacceptable, wherein inhibiting the person-to-person communication program access to the communication upon determining that the communication is unacceptable comprises blocking access to the unacceptable language statements and allowing access to language statements not determined to be unacceptable in the communication.

15. The method of claim 1, wherein the predefined language statements are capable of being modified by an administrator.