Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

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

A big data and product technology, applied in the field of big data analysis, can solve the problems of lack of competitive panorama, insufficient comparison, and inability to predict the belonging of competing products circle

Active Publication Date: 2022-02-18
广东数鼎科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method and device for quantitatively generating product competition relationship based on big data
  • A method and device for quantitatively generating product competition relationship based on big data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] Please refer to figure 1 , a preferred embodiment of the present invention provides a method for quantitatively generating product competition relationships based on big data, including:

[0047] Step 1, obtaining data of each stage of user consumption; the data of each stage includes data of attention stage, data of intention stage and data of consideration stage;

[0048] Step 2, processing the data of each stage, cleaning and standardizing the data of each stage according to the rules, and vectorizing the data of each stage;

[0049] Step 3. Using the vectorized product features to calculate the distance between two products through cluster analysis method and divide the competition circle based on this.

[0050] In this embodiment, the attention stage data includes search and comment network big data of related products; the intention stage data includes comparison times between related products and big network data that reflects the relationship between related pr...

Embodiment 2

[0052] In this embodiment, in step 2, in the processing of the data of each stage, the processing of the data of the attention stage includes:

[0053] Identify and remove unqualified reviews;

[0054] Segment each comment based on the industry thesaurus and word segmentation software, and extract key information; the key information includes product image, product function, and analogous other related products;

[0055] When the mention rate of other products being compared exceeds the preset mention rate threshold, the image of the product being compared is weighted and transferred to the image of this product;

[0056] The image and function of each product are converted into vectors through the word vector tool, and the image word vector and function word vector of each product are integrated into a vector, and then the distance between the two products is calculated using the vector calculation algorithm.

Embodiment 3

[0058] In this embodiment, in step 2, in the processing of the data of each stage, the processing of the data of the intention stage includes:

[0059] Judging the total number of times the user ID compares the product, when the total number of times the user ID compares the product is higher than the multiple threshold of the average number of comparisons of each user ID, then remove all the comparison behaviors that occur by the user ID;

[0060] The number of times that two products are compared forms a comparison matrix, and the above comparison matrix is ​​normalized by using the total number of times each product is compared;

[0061] The distance between the two products is calculated by vector arithmetic operation on the normalized comparison matrix data.

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

No PUM Login to View More

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...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06Q30/02
CPCG06Q30/0202G06Q30/0201G06F18/23G06F18/24G06F18/214
Inventor 程博
Owner 广东数鼎科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products