# US 2025/0156500 A1 · Methods and Systems for Data Feature Extraction

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

- Number: US 2025/0156500 A1
- Document ID: US20250156500A1
- Status: Published application
- Kind: A1
- Application number: 19/019,999
- Filed: 2025-01-14
- Published: 2025-05-15
- Earliest claimed: 2022-07-27
- Assignees: Huawei Technologies Co., Ltd.
- Applicants: Huawei Technologies Co., Ltd.
- Inventors: Bidi YING; Xu LI; Chenchen YANG
- Web page: https://patentgrep.com/patent/US20250156500A1

## CPC

- G06F 18/2132: based on discrimination criteria, e.g. discriminant analysis
- G06F 21/6245: {Protecting personal data, e.g. for financial or medical purposes}
- G06F 21/32: using biometric data, e.g. fingerprints, iris scans or voiceprints
- H03M 7/3059: {Digital compression and data reduction techniques where the original information is represented by a subset or similar information, e.g. lossy compression}
- H03M 7/607: {Selection between different types of compressors}
- H04L 63/08: {for authentication of entities (cryptographic mechanisms or cryptographic arrangements for entity authentication H04L9/32)}
- H04L 69/04: Protocols for data compression, e.g. ROHC
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H03M: CODING; DECODING; CODE CONVERSION IN GENERAL (using fluidic means F15C4/00; optical analogue/digital converters G02F7/00; coding, decoding or code conversion, specially adapted for particular applications, see the relevant subclasses, e.g. G01D, G01R, G06F, G06T, G09G, G10L, G11B, G11C, H04B, H04L, H04M, H04N; ciphering or deciphering for cryptography or other purposes involving the need for secrecy G09C)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

There is provided systems and methods for data feature extraction based on feedback from a network. The system may be used generally to enable feature-specific network operations, including one or more of access control, data compression and selective encryption. Further, embodiments provide methods and systems for data compression based on feature similarity and may include privacy protection.

## Claims

### Claim 1

A system for feature extraction, the system comprising a feature extraction router and a feature validation center, wherein each of the feature extraction router and the feature validation center have one or more associated memories storing instructions, wherein execution of the instructions by one or more associated processors results in:
the feature extraction router being configured to:
receive a request for feature extraction from a data consumer;
extract a data feature in response to the request; and
send the data feature to the feature validation center; and
the feature validation center being configured to:
determine whether the data feature belongs to a feature set, wherein the feature set includes existing data features provided by a third party off-line;
upon determination that the data feature does not belong to the feature set, generate a feedback which indicates potential data features, wherein the potential data features are associated with the data feature and the existing data features and send the feedback to the feature extraction router to re-extract a new data feature; and
upon determination that the data feature belongs to the feature set, trigger feature-enabled network operations at least in part based on a set of valid data features, the set of valid data features is associated with the feature set and the data feature.

### Claim 2 (depends on 1)

The system of claim 1, wherein when determining whether the data feature belongs to the feature set, the feature validation center is further configured to:
calculate a feature similarity between the data feature and the existing data features, the feature similarity indicative of a level of similarity; and
upon determination that the feature similarity exceeds a threshold, determine the data feature belongs to the feature set.

### Claim 3 (depends on 1)

The system of claim 1, wherein the feature extraction router is further configured to:
receive the feedback; and
re-extract the new data feature with respect to the feedback.

### Claim 4 (depends on 1)

The system of claim 1, wherein the set of valid data features includes at least one of:
a list of features IDs with respective feature similarity; and
a privacy indication of whether sensitive data protection, whereas the privacy indication is generated by the feature validation center.

### Claim 5 (depends on 1)

The system of claim 1, wherein the system further comprises a function configured to implement feature-enabled network operations, the feature validation center triggering the function by sending the set of valid data features to the function.

### Claim 6 (depends on 5)

The system of claim 5, wherein the function is a compression controller, the compression controller being configured to:
determine a compression solution based on at least one of an input, compression performances of existing compression solutions, and an indication from a data consumer;
wherein the input includes the set of valid data features; and
wherein the indication is indicative of whether, upon decompression, data meets necessary service requirements.

### Claim 7 (depends on 6)

The system of claim 6, wherein the compression controller is further configured to:
compress data based on the compression solution to obtain compressed data and send the compressed data to the data consumer; and
wherein to obtain the data from the compressed data, decompression is performed by the data consumer.

### Claim 8

A method for feature extraction, the method comprising:
receiving, by a feature extraction router, a request for feature extraction from a data consumer;
extracting, by the feature extraction router, a data feature in response to the request;
determining, by the feature validation center, whether the data feature belongs to a feature set, wherein the feature set includes existing data features provided by a third party off-line;
upon determination that the data feature does not belong to the feature set, generating, by the feature validation center, feedback which indicates potential data features, wherein the potential data features are identified from or associated with the data feature and the existing data features and sending, by the feature validation center, the feedback to the feature extraction router to re-extract a new data feature; and
upon determination that the data feature belongs to the feature set, triggering, by the feature validation center, feature-enabled network operations at least in part based on a set of valid data features, the set of valid data features associated with the feature set and the data feature.

### Claim 9 (depends on 8)

The method of claim 8, wherein when determining whether the data feature belongs to the feature set, the method further comprises:
calculating, by the feature validation center, a feature similarity between the data feature and the existing data features, the feature similarity indicative of a level of similarity; and
upon determination that the feature similarity exceeds a threshold, determining, by the feature validation center, the data feature belongs to the feature set.

### Claim 10 (depends on 8)

The method of claim 8, wherein the method further includes:
receiving, by the feature extraction router, the feedback; and
re-extracting, by the feature extraction router, the new data feature with respect to the feedback.

### Claim 11 (depends on 8)

The method of claim 8, wherein the set of valid data features includes at least one of:
a list of features IDs with respective feature similarity; and
a privacy indication of whether sensitive data protection, whereas the privacy indication is generated by the feature validation center.

### Claim 12 (depends on 8)

The method of claim 8, wherein the method further comprises triggering, by the feature validation center, a function configured to implement feature-enabled network operations by sending the set of valid data features to the function.

### Claim 13 (depends on 12)

The method of claim 12, wherein the function is configured as a compression controller, the method further comprising:
determining, by the compression controller, a compression solution based on at least one of an input, compression performances of existing compression solutions, and an indication from a data consumer;
wherein the input includes the set of valid data features; and
wherein the indication is indicative of whether, upon decompression, data meets necessary service requirements.

### Claim 14 (depends on 13)

The method of claim 13, further comprising:
compressing, by the compression controller, data based on the compression solution to obtain compressed data and send the compressed data to the data consumer; and
wherein to obtain the data from the compressed data, decompression is performed by the data consumer.

### Claim 15

A method for data feature validation, comprising:
receiving, by a feature validation center, a data feature from a feature extraction router;
determining, by the feature validation center, whether the data feature belongs to a feature set, wherein the feature set includes existing data features provided by a third party off-line;
upon determination that the data feature does not belong to the feature set, generating, by the feature validation center, feedback which indicates potential data features, wherein the potential data features are identified from or associated with the data feature and the existing data features and sending, by the feature validation center, the feedback to the feature extraction router to re-extract a new data feature; and
upon determination that the data feature belongs to the feature set, triggering, by the feature validation center, feature-enabled network operations at least in part based on a set of valid data features, the set of valid data features is associated with the feature set.

### Claim 16 (depends on 15)

The method of claim 15, when determining, by the feature validation center, whether the data feature belongs to the feature set, the feature validation center is further configured to:
calculate, by the feature validation center, a feature similarity between the data feature and the existing data features, the feature similarity indicative of a level of similarity; and
upon determination that the feature similarity exceeds a threshold, determine, by the feature validation center, the data feature belongs to the feature set.

### Claim 17 (depends on 15)

The method of claim 15, wherein the set of valid data features includes at least one of:
a list of features IDs with respective feature similarity; and
a privacy indication of whether sensitive data protection, whereas the privacy indication is generated by the feature validation center.

### Claim 18

A device for data feature validation, the device comprising:
a transceiver module, configured to receive a data feature from a feature extraction router;
a processing module, configured to determine whether the data feature belongs to a feature set, wherein the feature set includes existing data features provided by a third party off-line, wherein
upon determination that the data feature does not belong to the feature set, generate, by the processing module, feedback which indicates potential data features, wherein the potential data features are identified from or associated with the data feature and the existing data features and send, by the transceiver module, the feedback to the feature extraction router to re-extract a new data feature; and
upon determination that the data feature belongs to the feature set, trigger, by the processing module, feature-enabled network operations at least in part based on a set of valid data features, the set of valid data features is associated with the feature set and the data feature.

### Claim 19 (depends on 18)

The device of claim 18, wherein the processing module, configured to calculate a feature similarity between the data feature and the existing data features, the feature similarity indicative of a level of similarity;
upon determination that the feature similarity exceeds a threshold, the processing module, configured to determine the data feature belongs to the feature set.

### Claim 20 (depends on 18)

The device of claim 18, wherein the set of valid data features includes at least one of:
a list of features IDs with respective feature similarity;
a privacy indication of whether sensitive data protection, whereas the privacy indication is generated by the feature validation center.
