# US 10,504,154 B1 · Systems and methods for private local sponsored content

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 10,504,154 B1
- Document ID: US10504154B1
- Status: Granted
- Kind: B1
- Application number: 15/270,165
- Filed: 2016-09-20
- Granted: 2019-12-10
- Earliest claimed: 2016-09-20
- Assignees: Google Inc.
- Applicants: Google Inc.
- Inventors: Keith Bonawitz; Daniel Ramage; David Petrou
- Web page: https://patentgrep.com/patent/US10504154B1

## CPC

- G06Q 30/0269: {based on user profile or attribute}
- G06N 5/025: Extracting rules from data
- G06N 20/00: Machine learning
- G06Q 30/0251: Targeted advertisements
- G06Q 30/0261: {based on user location}
- H04L 9/008: {involving homomorphic encryption}
- H04L 63/0428: {wherein the data content is protected, e.g. by encrypting or encapsulating the payload}
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- H04L 2209/805: Lightweight hardware, e.g. radio-frequency identification [RFID] or sensor
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

Systems and methods are shown for providing private local sponsored content selection and improving intelligence models through distribution among mobile devices. This allows greater data gathering capabilities through the use of the sensors of the mobile devices as well as data stored on data storage components of the mobile devices to create predicted models while offering better opportunities to preserve privacy. Locally stored profiles comprising machine intelligence models may also be used to determine the relevance of the data gathered and in improving an aggregated model for identifying the relevance of data and the selection of sponsored content items. Distributed optimization is used in conjunction with privacy techniques to create the improved machine intelligence models. Publishers may also benefit from the improved privacy by protecting the statistics of type or volume of sponsored content items shown with publisher content.

## Claims

### Claim 1

A system comprising:
one or more processors of a device;
a display electrically connected to the one or more processors;
a network interface electrically connected to the one or more processors; and
a computer storage device electrically connected to the one or more processors and storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
receiving, via the network interface, a machine intelligence model comprising rules and a first parameter and a second parameter;
storing, by the computer storage device, the machine intelligence model comprising rules and the first parameter and the second parameter to create a stored machine intelligence model;
receiving, via the network interface, an updated value for the first parameter of the machine intelligence model;
updating the stored machine intelligence model based on the updated value for the first parameter;
receiving, via the network interface, one or more parameters for a differentially private mechanism;
retrieving a first local data from the computer storage device;
adjusting a value of the second parameter of the stored machine intelligence model based on the first local data to create an adjusted value of the second parameter;
transmitting data associated with the adjusted value of the second parameter by applying the one or more parameters for the differentially private mechanism to the adjusted value of the second parameter via the network interface;
applying the stored machine intelligence model to second local data retrieved from the computer storage device to determine whether the second local data is relevant in selecting sponsored content items;
transmitting a request via the network interface, based on a relevance of the second local data, for a homomorphically encrypted sponsored content item, the request comprising a vector of encrypted entries;
receiving, via the network interface, the homomorphically encrypted sponsored content item;
decrypting the received homomorphically encrypted sponsored content item; and
presenting the decrypted received homomorphically encrypted sponsored content item on the display.

### Claim 2 (depends on 1)

The system of claim 1, further comprising:
a sensor operably connected to the device; and
further instructions that cause the one or more processors to perform operations comprising:
receiving a sensor data from the sensor, the second local data comprising the received sensor data.

### Claim 3 (depends on 1)

The system of claim 1, further comprising instructions that cause the one or more processors to perform operations comprising:
retrieving data from the computer storage device comprising demographic data from a user profile; and
transmitting, via the network interface, an identification of the retrieved demographic data and data indicating an impression or conversion of the decrypted received homomorphically encrypted sponsored content item on the display by applying the one or more parameters for the differentially private mechanism to the demographic data and data indicating an impression or conversion.

### Claim 4 (depends on 1)

The system of claim 1, wherein determining the second local data is relevant in selecting sponsored content items comprises comparing features extracted from the second local data to features from a plurality of possible sponsored content items.

### Claim 5

A system comprising:
one or more processors of a device;
a display electrically connected to the one or more processors;
a network interface electrically connected to the one or more processors; and
a computer storage device electrically connected to the one or more processors and storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
receiving, via the network interface, a machine intelligence model comprising rules and a first parameter and a second parameter;
storing, by the computer storage device, the machine intelligence model comprising rules and the first parameter and the second parameter to create a stored machine intelligence model;
receiving, via the network interface, an updated value for the first parameter of the machine intelligence model;
updating the stored machine intelligence model based on the updated value for the first parameter;
retrieving a first local data from the computer storage device;
adjusting a value of the second parameter of the stored machine intelligence model based on the first local data to create an adjusted value of the second parameter;
encrypting the adjusted value of the second parameter of the stored machine intelligence model with a public key to create an encrypted, adjusted value of the second parameter;
transmitting, via the network interface, a data comprising the encrypted, adjusted value of the second parameter;
receiving, via the network interface, a data associated with the transmitted encrypted, adjusted value of the second parameter;
decrypting, using a private key corresponding to the public key, the data associated with the transmitted encrypted, adjusted value of the second parameter to create decrypted data associated with the transmitted encrypted, adjusted value of the second parameter;
transmitting, via the network interface, the decrypted data associated with the transmitted encrypted, adjusted value of the second parameter;
applying the stored machine intelligence model to second local data retrieved from the computer storage device to determine whether the second local data is relevant in selecting sponsored content items;
transmitting a request via the network interface, based on a relevance of the second local data, for a homomorphically encrypted sponsored content item, the request comprising a vector of encrypted entries;
receiving, via the network interface, the homomorphically encrypted sponsored content item;
decrypting the received homomorphically encrypted sponsored content item; and
presenting the decrypted received homomorphically encrypted sponsored content item on the display.

### Claim 6 (depends on 5)

The system of claim 5, further comprising:
a sensor operably connected to the device; and
further instructions that cause the one or more processors to perform operations comprising:
receiving a sensor data from the sensor, the second local data comprising the received sensor data.

### Claim 7 (depends on 5)

The system of claim 5, further comprising instructions that cause the one or more processors to perform operations comprising:
retrieving data from the computer storage device comprising demographic data from a user profile to create retrieved data;
encrypting the retrieved data and data indicating an impression or conversion of the decrypted received homomorphically encrypted sponsored content item presented on the display using a second public key to create encrypted, retrieved data; and
transmitting, via the network interface, the encrypted, retrieved data.

### Claim 8 (depends on 5)

The system of claim 5, further comprising instructions that cause the one or more processors to perform operations comprising:
retrieving a data from the computer storage device comprising demographic data from a user profile;
encrypting the data from the computer storage device comprising demographic data from the user profile and data indicating an impression or conversion of the decrypted received homomorphically encrypted sponsored content item presented on the display using the public key to create encrypted, retrieved data;
transmitting, via the network interface, the encrypted, retrieved data.

### Claim 9 (depends on 5)

The system of claim 5, further comprising instructions that cause the one or more processors to perform operations comprising:
receiving, via the network interface, a data associated with a plurality of sponsored content items; and
generating the request for the homomorphically encrypted sponsored content item comprising a vector of encrypted entries corresponding to the data associated with the plurality of sponsored content items with an entry corresponding to the homomorphically encrypted sponsored content item an encryption of one and remaining encrypted entries of the vector of encrypted entries an encryption of zero.

### Claim 10 (depends on 9)

The system of claim 9, further comprising instructions that cause the one or more processors to perform operations comprising:
retrieving data from the computer storage device comprising demographic data from a user profile;
encrypting the data from the computer storage device comprising demographic data from the user profile and data indicating an impression or conversion of the decrypted received homomorphically encrypted sponsored content item presented on the display using a second public key to create encrypted, retrieved data;
transmitting, via the network interface, the encrypted, retrieved data.

### Claim 11 (depends on 9)

The system of claim 9, wherein determining the second local data is relevant in selecting sponsored content items comprises comparing features extracted from the second local data to features from a plurality of possible sponsored content items.

### Claim 12

A method comprising:
receiving, by a computing device, a machine intelligence model comprising rules and a first parameter and a second parameter;
storing, on the computing device, the machine intelligence model to create a stored machine intelligence model;
receiving, by the computing device, an updated value for the first parameter of the machine intelligence model;
updating the machine intelligence model stored on the computing device based on the updated value for the first parameter;
receiving, by the computing device, one or more parameters for a differentially private mechanism;
retrieving, by the computing device, a first local data;
adjusting a value of the second parameter of the stored machine intelligence model based on the first local data to create an adjusted value of the second parameter;
transmitting, by the computing device, a data associated with the adjusted value of the second parameter by applying the one or more parameters for the differentially private mechanism to the adjusted value of the second parameter;
applying the stored machine intelligence model to second local data retrieved from the computer storage device to determine whether the second local data is relevant in selecting sponsored content items;
transmitting a request, by the computing device, based on a relevance of the second local data, for a homomorphically encrypted sponsored content item, the request comprising a vector of encrypted entries;
receiving, by the computing device, the homomorphically encrypted sponsored content item;
decrypting the received homomorphically encrypted sponsored content item; and
presenting, by the computing device, the decrypted received homomorphically sponsored content item on a display.

### Claim 13 (depends on 12)

The method of claim 12, further comprising receiving a sensor data from a sensor of the computing device, the second local data comprising the received sensor data.

### Claim 14 (depends on 12)

The method of claim 12, further comprising retrieving a data from a data storage device of the computing device, the second local data comprising the data from the data storage device of the computing device.

### Claim 15 (depends on 14)

The method of claim 14, further comprising:
retrieving a data from a data storage of the computing device comprising demographic data from a user profile; and
transmitting, by the computing device, an identification of the retrieved demographic data from the user profile and data indicating an impression or conversion of the decrypted received homomorphically encrypted sponsored content item on the display by applying the one or more parameters for the differentially private mechanism to the demographic data and data indicating an impression or conversion.

### Claim 16 (depends on 12)

The method of claim 12, further comprising:
retrieving data from a data storage of the computing device comprising demographic data from a user profile; and
transmitting, by the computing device, an identification of the retrieved demographic data from the user profile and data indicating an impression or conversion of the decrypted received homomorphically encrypted sponsored content item on the display by applying the one or more parameters for the differentially private mechanism to the demographic data and data indicating an impression or conversion.

### Claim 17 (depends on 12)

The method of claim 12, wherein determining the second local data is relevant in selecting sponsored content items comprises comparing features extracted from the second local data to features from a plurality of possible sponsored content items.