CN-122024727-A - Interpersonal communication expression auxiliary system and method

Abstract

The invention belongs to the technical field of intelligent wearing and artificial intelligent interaction, and particularly relates to a human-to-human communication expression auxiliary system and method. The system comprises a voice acquisition unit, a processing unit and an output unit, wherein the voice acquisition unit is used for acquiring the voice of the communication object, identifying and processing the voice, generating an expression auxiliary prompt based on the identification and processing result, outputting the prompt to the user, and not transmitting the original voice to the cloud in the whole process. The invention effectively ensures the privacy safety of the user while realizing communication assistance, is suitable for scenes such as social anxiety, unsmooth in-situ expression and the like, and can obviously improve the interpersonal communication efficiency and quality of the user.

Inventors

• HUANG WENFENG

Assignees

• 黄文峰

Dates

Publication Date

20260512

Application Date

20260318

Claims (5)

1. 1. A human-to-human communication expression assistance system, comprising: the voice acquisition unit is used for acquiring voice of a communication object; The processing unit is used for recognizing and processing the voice and generating an expression auxiliary prompt for human-to-human communication based on the recognition and processing result; the output unit is used for outputting the prompt to a user; The system does not transmit the original speech to the cloud.
2. 2. The system of claim 1, wherein the voice acquisition unit is implemented by a wearable device or a smart terminal.
3. 3. The system of claim 1, wherein the output unit employs at least one of speech, bone conduction, vibration, or text.
4. 4. The system of claim 1, wherein the prompt is at least one of a communication suggestion, a response suggestion, a communication logic, a keyword, or an expression outline.
5. 5. A method for assisting human-to-human communication, comprising: collecting the voice of a communication object; Recognizing and processing the voice and generating an expression auxiliary prompt for human-to-human communication based on the recognition and processing result; Outputting the prompt to a user; the original voice is not uploaded to the cloud end in the whole process.

Description

Interpersonal communication expression auxiliary system and method Technical Field The invention belongs to the technical field of intelligent wearing and artificial intelligent interaction, and particularly relates to a human-to-human communication expression auxiliary system and method. Background In the existing voice interaction technology, although related units of voice acquisition, data processing and result output generally exist, the related units are mostly applied to scenes such as voice translation, voice transcription, man-machine conversation and equipment control, interaction between people and machines is mainly realized, and an expression auxiliary function is not provided for communication between people. Meanwhile, the traditional related scheme generally needs to upload voice data to the cloud for processing, and has the problems of privacy disclosure risk, network dependence, higher delay and the like. Disclosure of Invention Aiming at the problems that the prior art cannot provide expression assistance in human-to-human communication, has insufficient privacy security, high response delay and the like, the invention provides a high-privacy human-to-human communication expression assistance system and a high-privacy human-to-human communication expression assistance method. Technical proposal A human-to-human communication expression auxiliary system and method comprises a voice acquisition unit, a processing unit and an output unit; the voice acquisition unit acquires voice of a communication object; the processing unit is used for recognizing and processing the voice and generating an expression auxiliary prompt for human-to-human communication based on the recognition and processing result; The output unit is used for outputting the prompt to a user; The system does not transmit the original voice to the cloud in the whole process so as to ensure privacy safety. The description and the drawings illustrate a structural block diagram of a human-to-human communication expression auxiliary system provided by the embodiment of the invention in fig. 1, which is used for illustrating a flow architecture of voice acquisition, processing and output. Fig. 2 is a block flow diagram of a method for assisting human-to-human communication, which is used for explaining a complete flow from collecting a communication object voice to outputting an assisting prompt.