Data sharing system and data sharing method therefor
AssigneeShanghai Cambricon Information Technology Co., Ltd.
InventorsTianshi Chen, Shuai Hu, Yifan Hao
Life of this patent
Estimating the term…
Abstract
The application provides an information processing device, system and method. The information processing device mainly includes a storage module and a data processing module, where the storage module is configured to receive and store input data, instruction and output data, and the input data includes one or more key features; the data processing module is configured to identify the key features included in the input data and score the input data in the storage module according to a judgment result. The information processing device, system and method provided by the application automatically scores text, pictures, audio, video, and the like instead of manually scoring, which is more accurate and faster.
Claims18
An information processing device, comprising:
- a storage module configured to receive and store input data and one or more instructions;
- and
- a data processing module configured to:
- identify one or more key features included in the input data to generate a judgment result, and
- score the input data in the storage module according to the judgment result,
- wherein the storage module stores data and one or more instructions,
- wherein the data includes the input data, input neurons, weights, output neurons,
- wherein the input data is transmitted to each input node in an artificial neural network for subsequent computation,
- wherein values of the output neurons include the judgment result and a score and
- wherein the judgment result and the score are determined as output data and
- wherein the data processing module includes a computation module configured to perform corresponding computation on the data stored in the storage module according to the one or more instructions stored in the storage module and output a computational result to the storage module,
- wherein in each layer of the neural network, the computation module includes:
- one or more multipliers configured to multiply the input data with the weights;
- one or more adders configured to:
- add one or more multiplication results to generate an addition result, and
- determine whether to add a bias value to the addition result;
- and
- an activation function unit configured to perform an activation function to the addition result to generate the output neurons.
A method for information processing, comprising:
- receiving, by a storage module, input data and one or more instructions;
- and
- identifying, by a data processing module, one or more key features included in the input data to generate a judgment result,
- storing, by the storage module, data and one or more instructions, wherein the data includes the input data, input neurons, weights, output neurons;
- transmitting the input data to each input node in an artificial neural network for subsequent computation, wherein values of the output neurons include the judgment result and a score, wherein the judgment result and the score are determined as output data;
- performing, by a computation module of the data processing module, corresponding computation on the data stored in the storage module according to the one or more instructions stored in the storage module and output a computational result to the storage module;
- multiplying, by one or more multiplier of the computation module, the input data with the weights;
- adding, by one or more adders of the computation module, one or more multiplication results to generate an addition result;
- determining, by the one or more adders, whether to add a bias value to the addition result;
- and
- performing, by an activation function unit of the computation module, an activation function to the addition result to generate the output neurons.
Dependencies are inferred from the claim text.