Method for converting incomplete ordered key value type condition data into category sets

Abstract

The invention discloses a method for converting incomplete ordered key value type condition data into category sets. The method comprises the steps of obtaining the incomplete ordered key value type condition data; processing incomplete condition data; obtaining complete ordered key value type condition data; obtaining complete condition data; setting M category sets, and selecting M category setcenters; calculating distance values of the complete condition data and the category sets; judging whether M is equal to 2 or not, and if yes, finishing conversion from the incomplete data to the category sets; otherwise, calculating a ratio of a data quantity in the M category sets to a total data quantity; and judging whether the category set with the ratio exceeding 1 / 2 exists or not, and if yes, dividing the category set into two category sets, otherwise, finishing the conversion from the incomplete data to the category sets. The method has the beneficial effects that the incomplete ordered key value type condition data can be complemented under the condition that the data is incomplete, and all the complemented data is converted into the category sets; and the accuracy of the complemented data and the completeness of the category sets obtained by conversion can be improved.

Description

technical field [0001] The invention relates to the technical field of working condition data processing, in particular to a method for converting category sets of incomplete ordered key-value working condition data. Background technique [0002] In the existing data collection process, some samples in the data set are missing due to errors in data measurement, limitations in data acquisition, and deviations in understanding the data. For example, the description of cultural relics in archeology may be vague, or some record items cannot be obtained; when collecting data in industry, the collection of data may fail due to environmental problems, large errors in data measurement or results with Random noise data, these may cause some attributes missing in the field data. If the data is incomplete, it will often affect the next step of work, so the processing of incomplete data is very important, but it is also relatively complicated. [0003] For the collected working condit...

AI Technical Summary

Problems solved by technology

[0002] In the existing data collection process, some samples in the data set are missing due to errors in data measurement, limitations in data acquisition, and deviations in understanding the data.

For example, the description of cultural relics in archeology may be vague, or some record items cannot be obtained; when collecting data in industry, the collection of data may fail due to environmental problems, large errors in data measurement or results with Data with random noise, which may cause some attributes to be missing in field data

If the data is incomplete, it will often affect the next step of work, so the processing of incomplete data is very important, but also more complicated

[0003] For the collected working condition data, due to technical reasons, it is difficult to obtain complete data

Images