Natural language processor extension transmission data protection

• US 10,540,513 B2
• Filed: 09/13/2016
• Issued: 01/21/2020
• Est. Priority Date: 09/13/2016
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Van Hoof, Hubert, Brennan, David J., Sankaranarayanan, Vidyaraman, Bhargava, Ruchita, Sonnino, Roberto
• Primary Examiner(s): Gurmu, Muluemebet
• Application Number:
  US15/264,575
• Publication Number:
  US 20180075251A1
• Time in Patent Office: 1,225 Days
• Field of Search: 707722
• CPC Class Codes: G06F 21/6227 where protection concerns the structure of data, e.g. records, types, queries

Abstract

A natural language query can be received at a main natural language processor inside a data protection compliance boundary in a computer system. The natural language query can be processed via the main natural language processor. The data from the query can be transmitted to a data protection computer component. It can be determined via the data protection component whether the data from the query includes protected data whose transmission to a computerized extension would violate a computer-readable data protection rule. The extension is outside the compliance boundary in the computer system and is configured to participate in responding to natural language queries received by the main natural language processor. In response to determining that the data from the query includes the protected data, transmission of the protected data from the main natural language processor to the extension as part of responding to the query can be inhibited.

Claims

1. A computer system comprising:

at least one processor; and

memory comprising instructions stored thereon that when executed by the at least one processor cause the at least one processor to perform acts comprising;

receiving a natural language query at a natural language processor inside a data protection compliance boundary in the computer system;

processing the natural language query via the natural language processor;

transmitting data from the natural language query to a data protection computer component;

determining, via the data protection computer component, that the data from the natural language query comprises protected data whose transmission to a computerized extension would violate a data protection rule, wherein the computerized extension is outside the data protection compliance boundary in the computer system, wherein the computerized extension is configured to participate in responding to natural language queries received by the natural language processor, and wherein the determining that the data protection rule would be violated comprises determining that the data from the natural language query comprises the protected data whose transmission from the natural language processor to the computerized extension would violate the data protection rule; and

in response to the determining that the data protection rule would be violated, inhibiting a transmission of the protected data from the natural language processor to the computerized extension as part of responding to the natural language query, wherein the inhibiting comprises;

masking the protected data to produce transmission data that hides the protected data; and

sending the transmission data to the computerized extension as part of responding to the natural language query.

2. The computer system of claim 1, wherein the acts further comprise processing an intent set for the for the natural language query, with the intent set comprising one or more determined intents of the natural language query, wherein the intent set comprises the protected data.

3. The computer system of claim 2, wherein the protected data comprises one or more of a determined intent of the natural language query and an entity of the intent.

4. The computer system of claim 1, wherein the data protection computer component operates independently of the natural language processor.

5. The computer system of claim 1, wherein the acts further comprise transmitting other data from the natural language query to the computerized extension, with the other data from the natural language query being data other than the protected data.

6. The computer system of claim 5, wherein the other data comprises an intent of the natural language query, and wherein the acts further comprise passing to the computerized extension an instruction to respond to the intent of the natural language query.

7. The computer system of claim 5, wherein the acts further comprise passing to the computerized extension a request to return an intent for the natural language query using the other data, with the determining that the data from the natural language query comprises the protected data being performed prior to the passing of the request to the computerized extension.

8. The computer system of claim 1, further comprising blocking a response to the natural language query in response to the determining, via the data protection computer component, that the data from the natural language query comprises the protected data whose transmission to the computerized extension would violate the data protection rule.

9. The computer system of claim 1, wherein the determining, via the data protection computer component, that the data from the natural language query comprises the protected data whose transmission to the computerized extension would violate the data protection rule comprises comparing the data from the natural language query to a data structure comprising key words indicating protected data.

20. The computer system of claim 1, wherein the transmission data that hides the protected data is specific to a user profile from which the natural language query is received.

10. A computer-implemented method, comprising the following acts:

receiving a natural language query from a client device at a natural language processor inside a data protection compliance boundary in a computer system;

processing the natural language query via the natural language processor;

transmitting data from the natural language query, with the transmitting of the data from the natural language query being from the natural language processor to a data protection computer component;

determining, via the data protection computer component, that the data from the natural language query comprises protected data whose transmission to a computerized extension would violate a data protection rule, wherein the computerized extension is outside the data protection compliance boundary in the computer system, wherein the computerized extension is configured to participate in responding to natural language queries received by the natural language processor, and wherein the determining that the data protection rule would be violated comprises comparing the data from the natural language query to a data structure comprising key words indicating protected data; and

in response to the determining that the data protection rule would be violated, inhibiting a transmission of the protected data from the natural language processor to the computerized extension, wherein the inhibiting comprises;

masking the protected data to produce transmission data that hides the protected data; and

sending the transmission data to the computerized extension as part of responding to the natural language query.

11. The method of claim 10, wherein the natural language processor is a first natural language processor and wherein the inhibited transmission is a transmission to a second natural language processor, which is a natural language processor of the computerized extension that is programmed to produce intents for natural language queries.

12. The method of claim 10, wherein the inhibited transmission is a transmission to a conversation query processor that is programmed to use determined intents queries in generating answers to those queries.

13. The method of claim 12, wherein the protected data comprises one or more of a determined intent of the natural language query and a determined entity of a determined query intent.

14. The method of claim 10, wherein the inhibiting comprises asking for user input as to whether to make the inhibited transmission, and making the inhibited transmission only if the user input indicates that the inhibited transmission is to be made.

15. The method of claim 10, wherein the determining, via the data protection computer component, that the data from the natural language query comprises the protected data whose transmission to the computerized extension would violate the data protection rule comprises invoking a natural language understanding computer component.

16. The method of claim 10, wherein the data protection computer component operates independently of the natural language processor.

17. The method of claim 10, further comprising transmitting other data from the natural language query to the computerized extension, with the other data from the natural language query being data other than the protected data.

19. The method of claim 10, wherein the transmission data that hides the protected data is specific to a user profile from which the natural language query is received.

21. The method of claim 10, wherein the determining that the data from the natural language query comprises the protected data whose transmission to the computerized extension would violate the data protection rule comprises determining that the data from the natural language query comprises the protected data whose transmission from the natural language processor to the computerized extension would violate the data protection rule.

18. One or more computer-readable storage media having computer-executable instructions embodied thereon that, when executed by at least one processor, cause at least one processor to perform acts comprising:

receiving a natural language query from a client device at a first natural language processor inside a data protection compliance boundary in a computer system;

processing the natural language query via the first natural language processor;

transmitting data from the natural language query, with the transmitting of the data from the natural language query being from the first natural language processor to a data protection computer component;

determining, via the data protection computer component, that the data from the natural language query comprises protected data whose transmission to a computerized extension would violate a data protection rule, wherein the computerized extension is outside the data protection compliance boundary in the computer system, wherein the computerized extension is configured to participate in responding to natural language queries received by the first natural language processor, and wherein the determining that the data protection rule would be violated comprises determining that the data from the natural language query comprises the protected data whose transmission from the natural language processor to the computerized extension would violate the data protection rule; and

in response to the determining that the data protection rule would be violated, inhibiting a transmission of the protected data from the first natural language processor to the computerized extension that would have occurred the determining that the data protection rule would be violated, wherein the inhibited transmission is a transmission to a second natural language processor, which is a natural language processor of the computerized extension that is programmed to produce intents for natural language queries, and wherein the inhibiting comprises;

masking the protected data to produce transmission data that hides the protected data; and

sending the transmission data to the computerized extension as part of responding to the natural language query.