Model updating method and device

A model update and updated technology, applied in the field of artificial intelligence, can solve the problems of low reliability and low update flexibility of machine learning models, and achieve the effects of improving user experience, improving flexibility, and improving prediction accuracy
CN114444705APending Publication Date: 2022-05-06HUAWEI TECH CO LTD
0 Cites 2 Cited by

Patent Information

Authority / Receiving Office
CN Ā· China
Patent Type
Applications(China)
Current Assignee / Owner
HUAWEI TECH CO LTD
Publication Date
2022-05-06

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a model updating method and device, and belongs to the field of AI. The method comprises the following steps: obtaining exception explanatory information, the exception explanatory information being explanatory information for explaining content exception, and the explanatory information being information for explaining an output result of a machine learning model; adjusting a training sample set of the machine learning model based on the abnormal interpretive information; and obtaining an updated machine learning model, wherein the machine learning model is obtained by training based on the adjusted training sample set. The reliability of the updated machine learning model can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present application relates to the field of artificial intelligence (AI), in particular to a method and device for updating a model. Background technique

[0002] Machine learning refers to allowing machines to train machine learning models based on training samples, so that machine learning models have predictive capabilities (such as category predictive capabilities) for data other than training samples. As an important branch of the AI ā€‹ā€‹field, machine learning has been widely used in many fields.

[0003] As the environment or rules change, the original machine learning model needs to be updated over time. At present, the update of the machine learning model is triggered by human experience or periodically updated, and the update flexibility is low, resulting in low reliability of the updated machine learning model. Contents of the invention

[0004] Embodiments of the present application provide a model updating method and device. The tec...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More