阅读说明：本技术 一种集成芯片以及处理传感器数据的方法 (Integrated chip and method for processing sensor data ) 是由 朱正超 刘宇 张琦 于 2019-07-31 设计创作，主要内容包括：一种集成芯片(200),属于人工智能领域,其特征在于,包括：第一处理器(221),用于从第一外部传感器(211)获取第一传感器数据,并且从第一传感器数据中提取第一目标数据,第一处理器(221)为实时响应处理器；加速器(230),用于根据第一神经网络模型对第一目标数据进行识别以得到第一识别结果,第一识别结果用于确定与第一识别结果对应的目标操作。还提供了一种处理传感器数据的方法,目的在于在实时响应外部传感器的情况下能够识别复杂场景,处理复杂任务。(An integrated chip (200) belonging to the field of artificial intelligence, characterized in that it comprises: a first processor (221) for acquiring first sensor data from the first external sensor (211) and extracting first target data from the first sensor data, the first processor (221) being a real-time response processor; and the accelerator (230) is used for identifying the first target data according to the first neural network model to obtain a first identification result, and the first identification result is used for determining a target operation corresponding to the first identification result. A method for processing sensor data is also provided, and aims to identify complex scenes and process complex tasks under the condition of responding to an external sensor in real time.)

An integrated chip, comprising:

a first processor for acquiring first sensor data from a first external sensor and extracting first target data from the first sensor data, the first processor being a real-time response processor;

and the accelerator is used for identifying the first target data according to a first neural network model to obtain a first identification result, and the first identification result is used for determining a target operation corresponding to the first identification result.

The integrated chip of claim 1, wherein the integrated chip further comprises:

and the second processor is used for determining the target operation according to the first recognition result.

The integrated chip of claim 2,

the first processor is further used for informing the second processor to switch from a sleep state to a working state after the first characteristic data is extracted;

the second processor is specifically configured to determine the target operation according to the first recognition result when the second processor is in the operating state.

The integrated chip of claim 2 or 3,

the first processor is further configured to determine a third recognition result according to the first sensor data;

the second processor is specifically configured to determine the target operation according to the first recognition result and the third recognition result.

The integrated chip of any of claims 1 to 3,

the first processor is further configured to obtain second sensor data from a second external sensor and extract second target data from the second sensor data;

the accelerator is further configured to identify the second target data according to a second neural network model to obtain a second identification result, where the second identification result and the first identification result are used to jointly determine the target operation.

The integrated chip of claim 5,

the accelerator is further used for identifying the first target data and the second target data in a time-sharing mode.

The integrated chip of claim 6, wherein the integrated chip further comprises:

the controller is used for determining a first priority corresponding to the first target data and a second priority corresponding to the second target data;

the accelerator is specifically configured to identify the first target data and the second target data in a time-sharing manner according to the first priority and the second priority.

The integrated chip of claim 6, wherein the integrated chip further comprises:

the controller is used for determining a first priority corresponding to the first target data and a second priority corresponding to the second target data, and controlling the first processor to send the first target data and the second target data to the accelerator in a time sharing mode according to the first priority and the second priority, so that the accelerator can identify the first target data and the second target data in a time sharing mode.

The integrated chip of any of claims 1 to 8, further comprising:

and the third processor is used for responding to the target operation and switching from the dormant state to the working state.

The integrated chip of any of claims 1 to 9, wherein parameters in the first neural network model are updated over a network.

The integrated chip of any of claims 1 to 10, wherein the first external sensor comprises one of a camera, a microphone, a motion sensor, a distance sensor, an ambient light sensor, a magnetic field sensor, a fingerprint sensor, or a temperature sensor.

An electronic device comprising an integrated chip as claimed in any one of claims 1 to 11.

A method of processing sensor data, comprising:

acquiring first sensor data from a first external sensor in real time, and extracting first target data from the first sensor data;

and identifying the first target data according to a first neural network model to obtain a first identification result, wherein the first identification result is used for determining target operation corresponding to the first identification result.

The method of claim 13, further comprising:

and determining the target operation according to the first recognition result.

The method according to claim 13 or 14, characterized in that the method further comprises:

acquiring second sensor data from a second external sensor in real time, and extracting second target data from the second sensor data;

and identifying the second target data according to a second neural network model to obtain a second identification result, wherein the second identification result and the first identification result are used for jointly determining the target operation.

The method of any of claims 13 to 15, further comprising:

and executing the target operation.

The method of any one of claims 13 to 16, wherein parameters in the first neural network model are updated by a network.

The method of any of claims 13-17, wherein the first external sensor comprises one of a camera, a microphone, a motion sensor, a distance sensor, an ambient light sensor, a magnetic field sensor, a fingerprint sensor, or a temperature sensor.