# US 2022/0036142 A1 · Recognition method and device for a target perception data

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

- Number: US 2022/0036142 A1
- Document ID: US20220036142A1
- Status: Published application
- Kind: A1
- Application number: 17/403,315
- Filed: 2021-08-16
- Published: 2022-02-03
- Earliest claimed: 2014-09-16
- Assignees: Huawei Technologies Co., Ltd.
- Applicants: Huawei Technologies Co., Ltd.
- Inventors: Liangwei Wang; Jia Chen
- Web page: https://patentgrep.com/patent/US20220036142A1

## CPC

- G06V 20/00: Scenes; Scene-specific elements (control of digital cameras H04N23/60)
- G06F 18/211: Selection of the most significant subset of features
- G06V 10/771: Feature selection, e.g. selecting representative features from a multi-dimensional feature space
- G06V 20/41: {Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items (segmenting video sequences G06V20/49)}
- G10L 15/063: {Training}
- G06V 2201/07: Target detection
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

A data processing method and device includes obtaining target perception data, where the target perception data is any type of the following data, such as image data, video data, or voice data, determining a target scenario to which the target perception data belongs, determining a target perception model corresponding to the target scenario, and computing a recognition result of the target perception data according to the target perception model. A scenario to which perception data belongs is determined, and a recognition result of the perception data is obtained through computation using a perception model corresponding to the scenario.

## Claims

### Claim 1

A data processing method, comprising:
obtaining target perception data, wherein the target perception data comprises at least one of image data, video data, or voice data;
determining a target scenario associated with the target perception data;
determining a target perception model corresponding to the target scenario; and
computing a recognition result of the target perception data according to the target perception model.

### Claim 2 (depends on 1)

The data processing method of claim 1, further comprising:
performing a scenario analysis on the target perception data; and
further determining the target scenario based on the scenario analysis.

### Claim 3 (depends on 2)

The data processing method of claim 2, wherein the target perception data is associated with a location at which a terminal is currently located, and wherein the data processing method further comprises performing the scenario analysis on the target perception data according to positioning information of the location at which the terminal is currently located.

### Claim 4 (depends on 1)

The data processing method of claim 1, further comprising:
sending, to a server, a first request for a scenario associated with the target perception data; and
receiving the target scenario from the server in response to sending the first request.

### Claim 5 (depends on 1)

The data processing method of claim 1, further comprising further determining, from a pre-stored perception model library, the target perception model corresponding to the target scenario, wherein each perception model in the pre-stored perception model library corresponds to a scenario.

### Claim 6 (depends on 5)

The data processing method of claim 5, wherein before obtaining the target perception data, the method further comprises updating the pre-stored perception model library according to a historical scenario sequence of a user, wherein the pre-stored perception model library, after updating, comprises the target perception model.

### Claim 7 (depends on 1)

The data processing method of claim 1, further comprising:
sending, to a server, a second request for a perception model corresponding to the target scenario when a pre-stored perception model library does not include the perception model, wherein each perception model in the pre-stored perception model library corresponds to a scenario; and
receiving, from the server, the target perception model in response to sending the second request.

### Claim 8

A data processing method, comprising:
receiving, from a terminal, a request message for a perception model corresponding to a scenario associated with target perception data, wherein the target perception data comprises at least one of image data, video data, or voice data;
determining, based on the request message, a target scenario associated with the target perception data;
determining, from a pre-stored perception model library, a target perception model corresponding to the target scenario, wherein each model in the pre-stored perception model library corresponds to a scenario; and
sending the target perception model to the terminal to prompt the terminal to compute a recognition result of the target perception data according to the target perception model.

### Claim 9 (depends on 8)

The data processing method of claim 8, wherein before receiving the request message, the method further comprises:
obtaining a perception data sample comprising at least a part of perception data having scenario annotation information and object annotation information;
training, based on the perception data sample, perception models respectively corresponding to different scenarios; and
storing, in the pre-stored perception model library, the perception models, wherein the pre-stored perception model library comprises the target perception model.

### Claim 10 (depends on 8)

The data processing method of claim 8, further comprises:
performing scenario analysis on the target perception data; and
further determining the target scenario based on the scenario analysis.

### Claim 11 (depends on 10)

The data processing method of claim 10, further comprising:
generating the target perception data at a location at which a terminal is currently located; and
performing the scenario analysis on the target perception data according to positioning information of the location at which the terminal is currently located.

### Claim 12 (depends on 8)

The data processing method of claim 8, further comprising further determining the target scenario according to an identifier indicating the target scenario comprised in the request message.

### Claim 13

A data processing device, comprising:
a memory storing instructions; and
a processor coupled to the memory and configured to execute the instructions, which cause the processor to be configured to:
obtain target perception data, wherein the target perception data comprises at least one of image data, video data, or voice data;
determine a target scenario associated with the target perception data;
determine a target perception model corresponding to the target scenario; and
compute a recognition result of the target perception data according to the target perception model.

### Claim 14 (depends on 13)

The data processing device of claim 13, wherein the instructions further cause the processor to be configured to:
perform scenario analysis on the target perception data; and
further determine the target scenario based on the scenario analysis.

### Claim 15 (depends on 14)

The data processing device of claim 14, wherein the target perception data is associated with a location at which a terminal is currently located, and wherein the instructions further cause the processor to be configured to perform the scenario analysis on the target perception data according to positioning information of the location at which the terminal is currently located.

### Claim 16 (depends on 13)

The data processing device of claim 13, wherein the instructions further cause the processor to be configured to:
send, to a server, a first request for a scenario associated with the target perception data; and
receive the target scenario from the server in response to sending the first request.

### Claim 17 (depends on 13)

The data processing device of claim 13, wherein the instructions further cause the processor to be configured to determine, from a pre-stored perception model library, the target perception model corresponding to the target scenario, wherein each perception model in the pre-stored perception model library corresponds to a scenario.

### Claim 18 (depends on 17)

The data processing device of claim 17, wherein before the target perception data is obtained, the instructions further cause the processor to be configured to update the pre-stored perception model library according to a historical scenario sequence of a user, wherein, after the pre-stored perception model library is updated, the pre-stored perception model library comprises the target perception model.

### Claim 19 (depends on 13)

The data processing device of claim 13, wherein the instructions further cause the processor to be configured to:
send, to a server, a second request for a perception model corresponding to the target scenario when a pre-stored perception model library does not include the perception model; and
receive, from the server, the target perception model in response to sending the second request.

### Claim 20 (depends on 19)

The data processing device of claim 19, wherein each perception model in the pre-stored perception model library corresponds to a scenario.
