# US 2022/0044049 A1 · Method, apparatus, device and storage medium for determining displayed recognized text

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

- Number: US 2022/0044049 A1
- Document ID: US20220044049A1
- Status: Published application
- Kind: A1
- Application number: 17/507,628
- Filed: 2021-10-21
- Published: 2022-02-10
- Earliest claimed: 2020-11-13
- Assignees: Apollo Intelligent Connectivity (Beijing) Technology Co., Ltd.
- Applicants: Apollo Intelligent Connectivity (Beijing) Technology Co., Ltd.
- Inventors: Zexiang WANG
- Web page: https://patentgrep.com/patent/US20220044049A1

## CPC

- G06V 30/153: {using recognition of characters or words}
- G10L 15/32: Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems
- G06F 18/22: Matching criteria, e.g. proximity measures
- G06F 40/279: Recognition of textual entities
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G10L 21/0208: Noise filtering
- G06V 30/10: Character recognition
- G10L 15/30: Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
- G10L 2015/221: {Announcement of recognition results}
- G10L 2021/02082: {the noise being echo, reverberation of the speech}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A method, an apparatus, a device and a storage medium for determining a displayed recognized text are provided. The method may include: determining a to-be-recognized data stream based on a collected data stream of user recording; performing local recognition on the to-be-recognized data stream to obtain an offline recognized text; performing online recognition on the to-be-recognized data stream to obtain an online recognized text; and determining a recognized text better representing a user intention between the online recognized text and the offline recognized text as a displayed recognized text based on a comparison result between the online recognized text and the offline recognized text.

## Claims

### Claim 1

A method for determining a displayed recognized text, the method comprising:
determining a to-be-recognized data stream based on a collected data stream of user recording;
performing a local recognition on the to-be-recognized data stream to obtain an offline recognized text;
performing an online recognition on the to-be-recognized data stream to obtain an online recognized text; and
determining a recognized text better representing a user intention from the online recognized text and the offline recognized text as the displayed recognized text based on a comparison result between the online recognized text and the offline recognized text.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the performing the local recognition on the to-be-recognized data stream to obtain the offline recognized text, further comprises:
displaying the offline recognized text on a display device; and
the determining a recognized text better representing a user intention from the online recognized text and the offline recognized text as a displayed recognized text based on a comparison result between the online recognized text and the offline recognized text, comprises:
maintaining, in response to the offline recognized text comprising the online recognized text, the offline recognized text displayed on the display device.

### Claim 3 (depends on 2)

The method according to claim 2, wherein a length of the online recognized text is smaller than or equal to a length of the offline recognized text.

### Claim 4 (depends on 2)

The method according to claim 2, wherein the determining the recognized text better representing the user intention from the online recognized text and the offline recognized text as the displayed recognized text based on the comparison result between the online recognized text and the offline recognized text, comprises:
replacing, in response to the offline recognized text not comprising the online recognized text, the offline recognized text displayed on the display device with the online recognized text.

### Claim 5 (depends on 1)

The method according to claim 1, wherein the determining the recognized text better representing the user intention from the online recognized text and the offline recognized text as the displayed recognized text based on the comparison result between the online recognized text and the offline recognized text, comprises:
determining, in response to a similarity between the offline recognized text and the online recognized text being smaller than a preset threshold value, the online recognized text as the displayed recognized text.

### Claim 6 (depends on 5)

The method according to claim 5, wherein the determining the recognized text better representing the user intention from the online recognized text and the offline recognized text as the displayed recognized text based on the comparison result between the online recognized text and the offline recognized text, comprising:
determining, in response to the similarity between the offline recognized text and the online recognized text being greater than or equal to the preset threshold value, the offline recognized text as the displayed recognized text.

### Claim 7 (depends on 2)

The method according to claim 2, wherein the method further comprises:
maintaining, in response to the online recognized text being not returned, the offline recognized text displayed on the display device.

### Claim 8 (depends on 1)

The method according to claim 1, wherein the determining the to-be-recognized data stream based on the collected data stream of recording, comprises:
performing preprocessing on the collected recording data stream to obtain the to-be-recognized data stream.

### Claim 9 (depends on 8)

The method according to claim 8, wherein the preprocessing comprises any one of:
noise reduction, echo cancellation or reverberation cancellation.

### Claim 10 (depends on 1)

The method according to claim 1, wherein a length of the offline recognized text is smaller than or equal to a preset threshold value.

### Claim 11

An electronic device, comprising:
at least one processor; and
a memory storing instructions executable by the at least one processor, wherein the instructions, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
determining a to-be-recognized data stream based on a collected data stream of user recording;
performing a local recognition on the to-be-recognized data stream to obtain an offline recognized text;
performing an online recognition on the to-be-recognized data stream to obtain an online recognized text; and
determining a recognized text better representing a user intention from the online recognized text and the offline recognized text as a displayed recognized text based on a comparison result between the online recognized text and the offline recognized text.

### Claim 12 (depends on 11)

The electronic device according to claim 11, wherein the performing the local recognition on the to-be-recognized data stream to obtain the offline recognized text, further comprises:
displaying the offline recognized text on a display device; and
the determining a recognized text better representing a user intention from the online recognized text and the offline recognized text as a displayed recognized text based on a comparison result between the online recognized text and the offline recognized text, comprises:
maintaining, in response to the offline recognized text comprising the online recognized text, the offline recognized text displayed on the display device.

### Claim 13 (depends on 12)

The electronic device according to claim 12, wherein a length of the online recognized text is smaller than or equal to a length of the offline recognized text.

### Claim 14 (depends on 12)

The electronic device according to claim 12, wherein the determining the recognized text better representing the user intention from the online recognized text and the offline recognized text as the displayed recognized text based on the comparison result between the online recognized text and the offline recognized text, comprise:
replacing, in response to the offline recognized text not comprising the online recognized text, the offline recognized text displayed on the display device with the online recognized text.

### Claim 15 (depends on 11)

The electronic device according to claim 11, wherein the determining the recognized text better representing the user intention from the online recognized text and the offline recognized text as the displayed recognized text based on the comparison result between the online recognized text and the offline recognized text, comprises:
determining, in response to a similarity between the offline recognized text and the online recognized text being smaller than a preset threshold value, the online recognized text as the displayed recognized text.

### Claim 16 (depends on 15)

The electronic device according to claim 15, wherein the determining the recognized text better representing the user intention from the online recognized text and the offline recognized text as the displayed recognized text based on the comparison result between the online recognized text and the offline recognized text, comprises:
determining, in response to the similarity between the offline recognized text and the online recognized text being greater than or equal to the preset threshold value, the offline recognized text as the displayed recognized text.

### Claim 17 (depends on 12)

The electronic device according to claim 12, wherein the method further comprises:
maintaining, in response to the online recognized text being not returned, the offline recognized text displayed on the display device.

### Claim 18 (depends on 11)

The electronic device according to claim 11, wherein the determining the to-be-recognized data stream based on the collected data stream of recording, comprises:
performing preprocessing on the collected recording data stream to obtain the to-be-recognized data stream.

### Claim 19 (depends on 18)

The electronic device according to claim 18, wherein the preprocessing comprises any one of:
noise reduction, echo cancellation or reverberation cancellation.

### Claim 20

A non-transitory computer readable storage medium storing computer instructions, wherein the computer instructions, when executed by a computer, cause the computer to perform operations comprising:
determining a to-be-recognized data stream based on a collected data stream of user recording;
performing a local recognition on the to-be-recognized data stream to obtain an offline recognized text;
performing an online recognition on the to-be-recognized data stream to obtain an online recognized text; and
determining a recognized text better representing a user intention from the online recognized text and the offline recognized text as a displayed recognized text based on a comparison result between the online recognized text and the offline recognized text.
