Classification model monitoring method, device, terminal and computer storage medium
A classification model and classified technology, applied in computing, hardware monitoring, instruments, etc., can solve the problem that the actual quality of the model cannot be supervised, and achieve the effect of intuitive quality
Active Publication Date: 2021-02-19
MASHANG CONSUMER FINANCE CO LTD
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] Under normal circumstances, once the model is put into practical application, the performance of the model will not be monitored, and the actual quality of the model will not be supervised
Method used
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
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0031] The following will clearly and completely describe the technical solutions in the embodiments of the application with reference to the drawings in the embodiments of the application. Apparently, the described embodiments are only some of the embodiments of the application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.
[0032] A model is a concept in machine learning and refers to an algorithm that processes multivariate feature input values. In supervised machine learning, the model can be understood as a multivariate function mapping relationship. This model is based on a large number of known input and output sample sets, trained to obtain the regulatory coefficients of the functional relationship, and finally applied to actual use scenarios for result prediction.
[0033] The classification mod...
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 PUM
Login to View More Abstract
The present application discloses a monitoring method of a classification model, a monitoring device, a monitoring terminal and a computer storage medium. The monitoring method includes: inputting data to be classified into the classification model, and obtaining the classified prediction result containing the classified data after the classification processing of the model Classified data; sampling the classified data, obtaining the sampled classified data and the classification prediction result of the sampled classified data; obtaining the correct classification result of the sampled classified data; passing the sampled classified data The classification prediction result and the correct classification result are calculated to obtain the basic index data of the sampled classified data; and the monitoring report of the classification model is generated based on the basic index data. Through the above method, the quality performance of the classification model after it is put into use can be supervised.
Description
technical field [0001] The present application relates to the technical field of model application, in particular to a monitoring method, device, terminal and computer storage medium of a classification model. Background technique [0002] In real life, in order to solve some practical problems, models are usually established according to needs, such as classification models. When these models are initially established, they will be trained with a lot of test data to obtain various index parameters. After passing the test into market applications. [0003] In general, once a model is put into practical application, the performance of the model will not be monitored, and the actual quality of the model will not be supervised. Contents of the invention [0004] The technical problem mainly solved by this application is to provide a classification model monitoring method, device, terminal and computer storage medium, which can monitor the performance of the classification mo...
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 Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F11/30G06F11/34
CPCG06F11/302G06F11/3476
Inventor 张波刘爽王能
Owner MASHANG CONSUMER FINANCE CO LTD