# US 2018/0322526 A1 · Advertisement detection method, advertisement detection apparatus, and storage medium

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

- Number: US 2018/0322526 A1
- Document ID: US20180322526A1
- Status: Published application
- Kind: A1
- Application number: 16/030,749
- Filed: 2018-07-09
- Published: 2018-11-08
- Earliest claimed: 2016-05-03
- Assignees: Tencent Technology (Shenzhen) Company Limited
- Applicants: Tencent Technology (Shenzhen) Company Limited
- Inventors: Hong YI; Jiabin WANG; Yuanhai LUO
- Web page: https://patentgrep.com/patent/US20180322526A1

## CPC

- G06Q 30/0243: {Comparative campaigns}
- G06F 21/56: Computer malware detection or handling, e.g. anti-virus arrangements
- G06Q 30/0273: Determination of fees for advertising
- 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
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A device extracts a plurality of characteristics from a sample set. For each extracted characteristic, the device determines different types of advertisements carried in advertisement samples in the sample set matching the characteristic. The device determines characteristic values of the characteristic that correspond to the different types of advertisements. The device filters based on characteristic values of the characteristic that correspond to the different types of advertisements, the extracted plurality of characteristics to obtain respective advertisement characteristics of the different types of advertisements. The device matches the advertisement characteristics of the different types of advertisements against characteristics extracted from a to-be-detected sample, and determines whether the to-be-detected sample carries an advertisement, and if so, which type of advertisement.

## Claims

### Claim 1

An advertisement detection method, comprising:
extracting a plurality of characteristics from a sample set, including extracting a respective characteristic of each advertisement sample in the sample set;
for each characteristic of the extracted plurality of characteristics:
determining different types of advertisements carried in advertisement samples in the sample set matching the characteristic, and
determining characteristic values of the characteristic that correspond to the different types of advertisements, each of the characteristic values representing a probability that the characteristic is an advertisement characteristic of a corresponding type of advertisements, including:
determining, for each type of advertisements, a quantity of advertisement samples in the sample set that match the characteristic and carry the corresponding type of advertisements, and determining, based on the quantity, a characteristic value of the characteristic corresponding to the corresponding type of advertisement; and
filtering, based on characteristic values of the characteristic that correspond to the different types of advertisements, the extracted plurality of characteristics to obtain respective advertisement characteristics of the different types of advertisements;
matching the advertisement characteristics of the different types of advertisements against characteristics extracted from a to-be-detected sample; and
determining, when a match is found based on the matching, that the to-be-detected sample carries an advertisement, and carries an advertisement of a type corresponding to a matching advertisement characteristic.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the sample set further comprises at least one non-advertisement sample that does not carry an advertisement; and
the determining, based on the quantity, a characteristic value of the characteristic corresponding to the corresponding type of advertisement comprises:
determining, based on a quantity of non-advertisement samples in the sample set that match the characteristic, and the quantity of advertisement samples that match the characteristic and carry the corresponding type of advertisement, the characteristic value of the characteristic corresponding to the corresponding type of advertisement.

### Claim 3 (depends on 0)

The method according to claim 0, wherein the determining, based on the quantity of non-advertisement samples in the sample set that match the characteristic, and the quantity of advertisement samples that match the characteristic and carry the corresponding type of advertisement, the characteristic value of the characteristic corresponding to the corresponding type of advertisement comprises:
calculating a ratio of the quantity of advertisement samples that match the characteristic and carry the corresponding type of advertisement to a sum, to obtain the characteristic value of the characteristic corresponding to the corresponding type of advertisement, the sum being a sum of the quantity of non-advertisement samples matching the characteristic and the quantity of advertisement samples that match the characteristic and carry the corresponding type of advertisement.

### Claim 4 (depends on 1)

The method according to claim 1, wherein the filtering, based on the characteristic values of the characteristic that correspond to the different types of advertisements, the extracted plurality of characteristics to obtain the respective advertisement characteristics of the different types of advertisements carried in the advertisement samples comprises:
determining, for each type of advertisements, that a characteristic of an only matching advertisement sample carrying the corresponding type of advertisement is an advertisement characteristic of the corresponding type of advertisement.

### Claim 5 (depends on 1)

The method according to claim 1, wherein the filtering, based on the characteristic values of the characteristic that correspond to the different types of advertisements, the extracted plurality of characteristics to obtain the respective advertisement characteristics of the different types of advertisements comprises:
for each characteristic, when the characteristic matches an advertisement sample carrying a plurality of types of advertisements, based on the advertisement characteristics of each of the plurality of types of advertisements, choosing an advertisement characteristic of a type of advertisements having a maximum characteristic value as the characteristic value of the characteristic.

### Claim 6 (depends on 1)

The method according to claim 1, wherein the filtering, based on the characteristic values of the characteristic that correspond to the different types of advertisements, the extracted plurality of characteristics to obtain the respective advertisement characteristics of the different types of advertisements comprises:
selecting, based on the characteristic values of the characteristic that correspond to the different types of advertisements, a characteristic whose characteristic value exceeds a characteristic value threshold as an advertisement characteristic of a corresponding type of advertisement.

### Claim 7 (depends on 1)

The method according to claim 1, further comprising:
filtering out, before the determining the characteristic values of the characteristic that correspond to the different types of advertisements, a characteristic corresponding to third-party plug-in code from the extracted plurality of characteristics, wherein
the third-party plug-in code comprises: a payment plug-in and an account login software development kit; and
the method further comprises:
updating the sample set by using the to-be-detected sample, and
determining, based on the updated sample set, the advertisement characteristics of the different types of advertisements again.

### Claim 8

A computing device, comprising:
one or more processors;
memory;
a display; and
a plurality of instructions stored in the memory that, when executed by the one or more processors, cause the one or more processors to perform the following operations:
extracting a plurality of characteristics from a sample set, including extracting a respective characteristic of each advertisement sample in the sample set;
for each characteristic of the extracted plurality of characteristics:
determining different types of advertisements carried in advertisement samples in the sample set matching the characteristic, and
determining characteristic values of the characteristic that correspond to the different types of advertisements, each of the characteristic values representing a probability that the characteristic is an advertisement characteristic of a corresponding type of advertisements, including:
determining, for each type of advertisements, a quantity of advertisement samples in the sample set that match the characteristic and carry the corresponding type of advertisements, and
determining, based on the quantity, a characteristic value of the characteristic corresponding to the corresponding type of advertisement; and
filtering, based on characteristic values of the characteristic that correspond to the different types of advertisements, the extracted plurality of characteristics to obtain respective advertisement characteristics of the different types of advertisements;
matching the advertisement characteristics of the different types of advertisements against characteristics extracted from a to-be-detected sample; and
determining, when a match is found based on the matching, that the to-be-detected sample carries an advertisement, and carries an advertisement of a type corresponding to a matching advertisement characteristic.

### Claim 9 (depends on 8)

The computing device according to claim 8, wherein the sample set further comprises at least one non-advertisement sample that does not carry an advertisement; and
the determining, based on the quantity, a characteristic value of the characteristic corresponding to the corresponding type of advertisement comprises:
determining, based on a quantity of non-advertisement samples in the sample set that match the characteristic, and the quantity of advertisement samples that match the characteristic and carry the corresponding type of advertisement, the characteristic value of the characteristic corresponding to the corresponding type of advertisement.

### Claim 10 (depends on 9)

The computing device according to claim 9, wherein the determining, based on the quantity of non-advertisement samples in the sample set that match the characteristic, and the quantity of advertisement samples that match the characteristic and carry the corresponding type of advertisement, the characteristic value of the characteristic corresponding to the corresponding type of advertisement comprises:
calculating a ratio of the quantity of advertisement samples that match the characteristic and carry the corresponding type of advertisement to a sum, to obtain the characteristic value of the characteristic corresponding to the corresponding type of advertisement, the sum being a sum of the quantity of non-advertisement samples matching the characteristic and the quantity of advertisement samples that match the characteristic and carry the corresponding type of advertisement.

### Claim 11 (depends on 8)

The computing device according to claim 8, wherein the filtering, based on the characteristic values of the characteristic that correspond to the different types of advertisements, the extracted plurality of characteristics to obtain the respective advertisement characteristics of the different types of advertisements carried in the advertisement samples comprises:
determining, for each type of advertisements, that a characteristic of an only matching advertisement sample carrying the corresponding type of advertisement is an advertisement characteristic of the corresponding type of advertisement.

### Claim 12 (depends on 8)

The computing device according to claim 8, wherein the filtering, based on the characteristic values of the characteristic that correspond to the different types of advertisements, the extracted plurality of characteristics to obtain the respective advertisement characteristics of the different types of advertisements comprises:
for each characteristic, when the characteristic matches an advertisement sample carrying a plurality of types of advertisements, based on the advertisement characteristics of each of the plurality of types of advertisements, choosing an advertisement characteristic of a type of advertisements having a maximum characteristic value as the characteristic value of the characteristic.

### Claim 13 (depends on 8)

The computing device according to claim 8, wherein the filtering, based on the characteristic values of the characteristic that correspond to the different types of advertisements, the extracted plurality of characteristics to obtain the respective advertisement characteristics of the different types of advertisements comprises:
selecting, based on the characteristic values of the characteristic that correspond to the different types of advertisements, a characteristic whose characteristic value exceeds a characteristic value threshold as an advertisement characteristic of a corresponding type of advertisement.

### Claim 14 (depends on 8)

The computing device according to claim 8, wherein the operations further include:
filtering out, before the determining the characteristic values of the characteristic that correspond to the different types of advertisements, a characteristic corresponding to third-party plug-in code from the extracted plurality of characteristics, wherein the third-party plug-in code comprises: a payment plug-in and an account login software development kit;
updating the sample set by using the to-be-detected sample, and
determining, based on the updated sample set, the advertisement characteristics of the different types of advertisements again.

### Claim 15

A non-transitory computer-readable storage medium storing a plurality of instructions configured for execution by a computing device having one or more processors and a display, wherein the plurality of instructions cause the computing device to perform the following operations:
extracting a plurality of characteristics from a sample set, including extracting a respective characteristic of each advertisement sample in the sample set;
for each characteristic of the extracted plurality of characteristics:
determining different types of advertisements carried in advertisement samples in the sample set matching the characteristic, and
determining characteristic values of the characteristic that correspond to the different types of advertisements, each of the characteristic values representing a probability that the characteristic is an advertisement characteristic of a corresponding type of advertisements, including:
determining, for each type of advertisements, a quantity of advertisement samples in the sample set that match the characteristic and carry the corresponding type of advertisements, and
determining, based on the quantity, a characteristic value of the characteristic corresponding to the corresponding type of advertisement; and
filtering, based on characteristic values of the characteristic that correspond to the different types of advertisements, the extracted plurality of characteristics to obtain respective advertisement characteristics of the different types of advertisements;
matching the advertisement characteristics of the different types of advertisements against characteristics extracted from a to-be-detected sample; and
determining, when a match is found based on the matching, that the to-be-detected sample carries an advertisement, and carries an advertisement of a type corresponding to a matching advertisement characteristic.

### Claim 16 (depends on 15)

The non-transitory computer-readable storage medium according to claim 15, wherein the sample set further comprises at least one non-advertisement sample that does not carry an advertisement; and
the determining, based on the quantity, a characteristic value of the characteristic corresponding to the corresponding type of advertisement comprises:
determining, based on a quantity of non-advertisement samples in the sample set that match the characteristic, and the quantity of advertisement samples that match the characteristic and carry the corresponding type of advertisement, the characteristic value of the characteristic corresponding to the corresponding type of advertisement.

### Claim 17 (depends on 16)

The non-transitory computer-readable storage medium according to claim 16, wherein the determining, based on the quantity of non-advertisement samples in the sample set that match the characteristic, and the quantity of advertisement samples that match the characteristic and carry the corresponding type of advertisement, the characteristic value of the characteristic corresponding to the corresponding type of advertisement comprises:
calculating a ratio of the quantity of advertisement samples that match the characteristic and carry the corresponding type of advertisement to a sum, to obtain the characteristic value of the characteristic corresponding to the corresponding type of advertisement, the sum being a sum of the quantity of non-advertisement samples matching the characteristic and the quantity of advertisement samples that match the characteristic and carry the corresponding type of advertisement.

### Claim 18 (depends on 15)

The non-transitory computer-readable storage medium according to claim 15, wherein the filtering, based on the characteristic values of the characteristic that correspond to the different types of advertisements, the extracted plurality of characteristics to obtain the respective advertisement characteristics of the different types of advertisements carried in the advertisement samples comprises:
determining, for each type of advertisements, that a characteristic of an only matching advertisement sample carrying the corresponding type of advertisement is an advertisement characteristic of the corresponding type of advertisement.

### Claim 19 (depends on 15)

The non-transitory computer-readable storage medium according to claim 15, wherein the filtering, based on the characteristic values of the characteristic that correspond to the different types of advertisements, the extracted plurality of characteristics to obtain the respective advertisement characteristics of the different types of advertisements comprises:
for each characteristic, when the characteristic matches an advertisement sample carrying a plurality of types of advertisements, based on the advertisement characteristics of each of the plurality of types of advertisements, choosing an advertisement characteristic of a type of advertisements having a maximum characteristic value as the characteristic value of the characteristic.

### Claim 20 (depends on 15)

The non-transitory computer-readable storage medium according to claim 15, wherein the filtering, based on the characteristic values of the characteristic that correspond to the different types of advertisements, the extracted plurality of characteristics to obtain the respective advertisement characteristics of the different types of advertisements comprises:
selecting, based on the characteristic values of the characteristic that correspond to the different types of advertisements, a characteristic whose characteristic value exceeds a characteristic value threshold as an advertisement characteristic of a corresponding type of advertisement.
