Machine learning model construction method and computer readable storage medium

Abstract

The invention discloses a machine learning model construction method and a computer readable storage medium. The method comprises the following steps: acquiring auxiliary data according to a preset keyword; obtaining business data, and determining data items corresponding to the input items and data items corresponding to the output items; performing label marking on the business data of which thevalues of the data items corresponding to the output items are not empty; obtaining a first sample according to the service data; obtaining service data with label marks in the first sample as a second sample; synthesizing feature items through a feature synthesis technology, and merging the feature items into a second sample as input items; performing positive and negative sample equalization processing on the second sample through a synthetic minority class oversampling technology, and taking newly synthesized sample data as a third sample; combining the second sample and the third sample to obtain a fourth sample; and training the fourth sample through a preset machine learning algorithm to obtain a machine learning model. According to the invention, the accuracy of the machine learning model can be improved.

Description

technical field [0001] The present invention relates to the technical field of machine learning, in particular to a method for constructing a machine learning model and a computer-readable storage medium. Background technique [0002] From October 2017, the former General Administration of Quality Supervision, Inspection and Quarantine issued the "Entry-Exit Inspection and Quarantine Process Management Regulations" and "Inspection and Quarantine Sampling Ratio and Process Time Limit Table" showing the most commonly used sampling methods in the supervision process of inspection and quarantine ports. According to different product categories, the article stipulates the proportion of on-site inspection and quarantine and laboratory inspection and quarantine ratio (sampling ratio) under different conditions. After analysis, except for some products that refer to product risk level classification, enterprise risk level classification and registration and filing management require...

AI Technical Summary

Problems solved by technology

[0006] 2. Due to seasonal temperature and humidity changes, the same port imports goods in different seasons, especially fresh goods, and the applicable spot checks and testing methods are inconsistent

[0007] 3. Due to the change of the voyage period, there may be problems such as corruption and deterioration of fresh and bulk items during the shipping process, which will affect the nature of the goods

[0010] 6. Due to the integrity and qualifications of the declaring enterprises, production enterprises, and consignees, etc., there may be concealment and omissions, etc. For enterprises with low integrity levels and high risks, there are differences in deployment and control with other enterprises

[0011] 7. When there is a large difference between the commodity price and the average price of goods in the market, it should be different from other products in the sampling process

[0025] (1) There are too few lottery factors involved in the lottery rules, which cannot fully reflect the risk level of various commodities in a complex business environment, and cannot implement personalized settings for specific risks

[0026] (2) It is impossible to dynamically increase or decrease the lotting rate corresponding to the lotting factor according to the attributes, characteristics, environmental factors and the dynamic changes of the corresponding inspection results of various commodities, which cannot achieve real-time, accurate and dynamic The sampling decision of

[0027] (3) It is not possible to comprehensively analyze the attributes, characteristics, environmental factors and corresponding inspection results of various commodities through the accumulated big data of imported and exported commodities, extract risk factors that affect the failure of various commodities, and calculate The weight ratio of risk factors and the commodity lottery rate determined by comprehensive decision-making

Images