A method and device for quantitatively generating product competition relationship based on big data

Abstract

The invention discloses a method for quantitatively generating product competition relationship based on big data, including: S1, obtaining data of each stage of user consumption; S2, processing the data of each stage, cleaning and standardizing the data of each stage according to the rules, and then Data at each stage is vectorized; S3, through the cluster analysis method, use the vectorized product features to calculate the distance between two products and divide the competing product circle; S4, use the classification algorithm to train the classification model, and superimpose the model results The target image or physical attributes of new products on the market can predict the future competition circle of new products; the invention also discloses a quantitative generation device for product competition relationship based on big data; the invention processes product data in three different stages , to vectorize the product, and then divide the competing product circle and predict its future competing product circle, so as to quickly understand the competition situation of the product in the market, and realize the accurate prediction of the main competing products of this product and the competing product circle to which it belongs. .

Description

technical field [0001] The present invention relates to the field of big data analysis, in particular to a method and device for quantifying product competition relationship based on big data. Background technique [0002] With the intensification of market competition, commercial vehicle manufacturers have entered the passenger car market. Independent passenger car manufacturers have continuously launched high-end models to compete with joint ventures. Joint venture non-luxury manufacturers design low-cost models to expand consumer audiences. Luxury manufacturers lower the entry threshold , Continuously launching small luxury cars to squeeze joint venture non-luxury high-end models. In such a fierce competition of innovation, quickly understand the overall market competition situation, accurately divide the competition circle, identify which competition circle you belong to, and who your main competitors are. In the prior art, some merchants have launched solutions to assi...

AI Technical Summary

Problems solved by technology

[0003] The disadvantages of the positive and negative comparison scheme are: 1) Lack of a competitive panorama: all the information provided is the relationship between two models, and it is difficult to see at a glance which models form a competition circle, which model is on the edge of the competition circle, etc.; 2) Positive and negative comparisons are two dimensions, and it is still a problem to combine them into one dimension to measure which competing product is closer

If the sales volume of a real competing product is moderate, it is likely to be ignored because it is not the first in the comparison ranking; 4) Unlisted or newly launched products cannot be predicted because of insufficient comparison volume.

[0004] The disadvantages of the scheme of comparison times are: 1) the lack of a competitive panorama, for the same reasons as above; 2) the definition of distance is not clear, and often does not match with empirical knowledge or other data source verification; 3) the total amount of competing products compared is not the same as competing products and this product 4) Unlisted or just-launched products cannot predict the ownership of competing products due to insufficient comparison volume

Images