Emoji frequency detection and deep link frequency

• US 9,712,550 B1
• Filed: 09/24/2016
• Issued: 07/18/2017
• Est. Priority Date: 06/12/2016
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Thakurta, Abhradeep Guha, Freudinger, Julien, Prakash, Vipul Ved, Legendre, Arnaud, Duplinsky, Steven, Vyrros, Andrew H., Vaishampayan, Umesh S., Kapoor, Gaurav
• Primary Examiner(s): Schwartz, Darren B
• Application Number:
  US15/275,358
• Time in Patent Office: 297 Days
• CPC Class Codes: G06F 21/6254 by anonymising data, e.g. decorrelating personal data from the owner's identification
• CPC Class Codes: G06F 40/134 Hyperlinking
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: H04L 63/0421 Anonymous communication, i.e. the party's identifiers are hidden from the other party or parties, e.g. using an anonymizer
• CPC Class Codes: H04L 63/1425 Traffic logging, e.g. anomaly detection

Abstract

Systems and methods are disclosed for generating term frequencies of known terms based on crowdsourced differentially private sketches of the known terms. An asset catalog can be updated with new frequency counts for known terms based on the crowdsourced differentially private sketches. Known terms can have a classification. A client device can maintain a privacy budget for each classification of known terms. Classifications can include emojis, deep links, locations, finance terms, and health terms, etc. A privacy budget ensures that a client does not transmit too much information to a term frequency server, thereby compromising the privacy of the client device.

Claims

1. A computer-implemented method practiced on a client device, comprising:

receiving a term from an application on the client device by a differential privacy engine executing on the client device;

applying, by the differential privacy engine, a differential privacy algorithm to the term thereby generating a differentially private sketch of the term, the differentially private sketch having a plurality of rows;

selecting, by the differential privacy engine, a row from the differentially private sketch;

determining, by the differential privacy engine, a privacy budget of the client device for transmission of the row of the differentially private sketch to a term frequency server;

storing, by the differential privacy engine, the row of the differentially private sketch for transmission to the term frequency server in response to determining that there is privacy budget available to transmit the row of the differentially private sketch of the term to the term frequency server.

2. The method of claim 1, discarding the term in response to determining that there is not privacy budget available to transmit the row of the differentially private sketch to the term frequency server.

3. The method of claim 1, further comprising periodically increasing or replenishing the privacy budget.

4. The method of claim 1, further comprising:

associating the term with a classification; and

associating a privacy budget with the classification.

5. The method of claim 1, further comprising:

storing the term in a transmitted terms storage in response to storing the row of the differentially private sketch for transmission to a term frequency server.

6. The method of claim 1, further comprising:

discarding the term in response to determining that the term appears on a blacklist of terms.

7. The method of claim 1, further comprising:

discarding the term in response to determining one of;

the term appears in a transmitted terms storage of terms that have had a row of a differentially private sketch for the term previously transmitted to the term frequency server;

the term appears in a user private dictionary and the term has been previously indicated by the user that the term and a row of the differentially private sketch of the term is not to be transmitted to the term frequency server;

or

the term is a duplicate of a term stored for transmission to the term frequency server.

8. The method of claim 1, wherein the term is a deep link and further comprising modifying the deep link before storage for transmission to the frequency server.

9. The method of claim 1, further comprising receiving an updated asset catalog that includes at least one of an updated emoji frequency or an updated deep link frequency, wherein the updated asset catalog was derived from locally differentially private data received from multiple client devices.

10. A non-transitory computer readable medium programmed with instructions that, when executed by a processing system, perform operations, comprising:

receiving a term from an application on the client device by a differential privacy engine executing on the client device;

applying, by the differential privacy engine, a differential privacy algorithm to the term thereby generating a differentially private sketch of the term, the differentially private sketch having a plurality of rows;

selecting, by the differential privacy engine, a row of the differentially private sketch;

determining, by the differential privacy engine, a privacy budget of the client device for transmission of the row of the differentially private sketch to a term frequency server;

storing, by the differential privacy engine, the row of the differentially private sketch for transmission to the term frequency server in response to determining that there is privacy budget available to transmit the row of the differentially private sketch of the term to the term frequency server.

11. The medium of claim 10, the operations further comprising:

discarding the term in response to determining that there is not privacy budget available to transmit the row of the differentially private sketch to the term frequency server.

12. The medium of claim 10, the operations further comprising periodically increasing or replenishing the privacy budget.

13. The medium of claim 10, the operations further comprising:

associating the term with a classification; and

associating a privacy budget with the classification.

14. The medium of claim 10, the operations further comprising:

storing the term in a transmitted terms storage in response to storing the selected row of the differentially private sketch for transmission to a term frequency server.

15. The medium of claim 10, the operations further comprising:

discarding the term in response to determining that the term appears on a blacklist of terms.

16. The medium of claim 10, the operations further comprising:

discarding the term in response to determining one of;

the term appears in a transmitted terms storage of terms that have had a row of the differentially private sketch for the term previously transmitted to the term frequency server;

the term appears in a user private dictionary and the term has been previously indicated by the user that the term and a row of the differentially private sketch of the term is not to be transmitted to the term frequency server;

or

the term is a duplicate of a term stored for transmission to the term frequency server.

17. The medium of claim 10, wherein the term is a deep link and further comprising modifying the deep link before storage for transmission to the frequency server.

18. The medium of claim 10, further comprising receiving an updated asset catalog that includes at least one of an updated emoji frequency or an updated deep link frequency, wherein the updated asset catalog was derived from locally differentially private data received from multiple client devices.

19. A system comprising:

a processing system coupled to a memory programmed with executable instructions that, when executed by the processing system perform operations, comprising;

receiving a term from an application on the client device by a differential privacy engine executing on the client device;

applying, by the differential privacy engine, a differential privacy algorithm to the term thereby generating a differentially private sketch of the term, the differentially private sketch having a plurality of rows;

selecting, by the differential privacy engine, a row of the differentially private sketch;

determining, by the differential privacy engine, a privacy budget of the client device for transmission of the row of the differentially private sketch to a term frequency server;

storing, by the differential privacy engine, the row of the differentially private sketch for transmission to the term frequency server in response to determining that there is privacy budget available to transmit the row of the differentially private sketch of the term to the term frequency server.

20. The system of claim 19, the operations further comprising:

discarding the term in response to determining that there is not privacy budget available to transmit the row of the differentially private sketch to the term frequency server.

21. The system of claim 19, the operations further comprising periodically increasing or replenishing the privacy budget.

22. The system of claim 19, the operations further comprising:

associating the term with a classification; and

associating a privacy budget with the classification.

23. The system of claim 19, the operations further comprising:

storing the term in a transmitted terms storage in response to storing the row of the differentially private sketch for transmission to a term frequency server.

24. The system of claim 19, the operations further comprising:

discarding the term in response to determining that the term appears on a blacklist of terms.

25. The system of claim 19, the operations further comprising:

discarding the term in response to determining one of;

the term appears in a transmitted terms storage of terms that have had a row of the differentially private sketch for the term previously transmitted to the term frequency server;

the term appears in a user private dictionary and the term has been previously indicated by the user that the term a row of a differentially private sketch of the term is not to be transmitted to the term frequency server;

the term is a duplicate of a term stored for transmission to the term frequency server.

26. The system of claim 19, further comprising receiving an updated asset catalog that includes at least one of an updated emoji frequency or an updated deep link frequency, wherein the updated asset catalog was derived from locally differentially private data received from multiple client devices.