Decentration equipment, multi-device system and voice control method thereof

Abstract

Decentration equipment comprises a voice recognition module, an energy value calculation module, an energy value screening and sorting module, a transceiving module and an execution module, wherein the energy value calculation module, the transceiving module and the execution module are in signal connection with the energy value screening and sorting module, the energy value calculation module isfurther in signal connection with the voice recognition module and the transceiving modules, and the transceiving modules of different devices can communicate with one another. A decentralized multi-device system comprises a plurality of devices as described above. According to the invention, a decentralized processing mode is adopted for multi-device identification; centralized processing equipment is removed, recognition is converted into equipment self-processing, complex calculation is decomposed into multiple pieces of equipment to be carried out in parallel, the network bandwidth requirement is lowered while the calculation speed is increased, the response speed of the system is increased, and the user experience is improved.

Description

technical field [0001] The invention belongs to the field of artificial intelligence and relates to voice recognition technology, in particular to a decentralized device, a multi-device system and a voice control method thereof. Background technique [0002] With the rise of the voice recognition function, there may be many smart voice devices in the same scene, such as a lobby, and these devices need to be woken up with a wake-up word when in use. However, if the wake-up words of these devices are the same, then multiple devices may respond to the user's wake-up words, interfering with the user's real needs. E.g figure 1 In a specific scenario shown in , the user issues a voice command, and the wake-up words of devices A1, A2, and A3 are exactly the same, and the command may be recognized and executed. [0003] In order to solve the above problems, the common practice in the prior art is to use a processing center, such as a cloud server, to uniformly judge which device t...

AI Technical Summary

Problems solved by technology

[0003] In order to solve the above problems, the common practice in the prior art is to use a processing center, such as a cloud server, to uniformly judge which device the user is closest to, and which device will respond to the user's wake-up command, but this method requires an additional server to judge , which increases the cost; the existing technology can calculate and sort by directly receiving voice information and then calculating, and select the device to execute the command by calculating the distance of each device. This kind of wake-up distance calculation of multiple devices is handled by one center. If there are many devices , it may be due to the insufficient processing capacity of the center, and the calculation feedback is too slow, resulting in a large delay in the response of the device to the user. At the same time, the original voice information with a large amount of data is directly uploaded, which also requires network bandwidth, which increases the application cost.

Images