Method and device for offering matched product based on correlation degree between products

Abstract

The invention relates to the field of electronic commerce and discloses a method and a device for offering a matched product based on correlation degree between products. The method and the device for offering the matched product based on the correlation degree between the products are used for improving accuracy of the recommended matched product when a user selects one product. Namely, when the matched product of the targeted product selected by the user is determined, an affair assembly is determined based on the setting time length so that on one hand, effectiveness of formation of affairs is guaranteed and on the other hand, relevance, between the products, contained in the affairs is guaranteed. In the process of calculating the absolute support degree of monomial set and multinomial set of the products, correlative detection is introduced to compensate statistics property shortage of the absolute support degree so that when the best matched relationship between products is determined based on the correlation degree of the products, the accuracy of the matched product determined in effectively improved, and therefore when the matched product of the targeted product is shown to the user, the accurate matched product is offered in time to the user by an electronic commerce website based on requirements of the user, and electronic commerce service quality is effectively guaranteed.

Description

technical field [0001] The invention relates to the field of electronic commerce, in particular to a method and device for providing matching products based on the degree of correlation between products. Background technique [0002] With the increasing popularity of e-commerce applications, related e-commerce websites have also achieved unprecedented development. Under the prior art, when a user selects (for example, browses, purchases, or collects) a product on a webpage of an e-commerce website, the e-commerce website will recommend a matching product (also known as a product) that has the best correlation with the selected product in the website to the user. It is called the best matching product), so that it is convenient for users to discover and purchase products related to their purchase intention at one time, thereby reducing the user's operation time, improving the transaction processing efficiency of e-commerce websites, and improving the service quality of e-comm...

AI Technical Summary

Problems solved by technology

Usually, this type of e-commerce website operates by placing an order as a "one purchase", and the products required by the user often need to be purchased multiple times at different merchants. Therefore, placing an order as a "One-time purchase" to establish a transaction set will cut off the correlation between products purchased from different merchants, thus affecting the accuracy of the final recommendation result

[0017] On the other hand, due to the universality of purchasing a large number of popular products, there are a large number of product combinations (two product combinations, three product combinations, etc.) containing these products, and their existence probability is much higher than that of other products. types of product combinations, so that the probability of these product combinations being recommended increases accordingly

The recommendation of popular products is ineffective in two aspects: one is that popular products already have a high recognition rate among customers due to word-of-mouth or rankings, and users can easily make recommendations for them without going through recommendations. The decision to buy or not; the second is that the absolute support represents only the number of times a product is purchased, which reflects the statistical sufficiency and does not reflect the correlation between products. Therefore, there will be such a situation: products containing popular products Although the absolute support of the combination is high, the popular products contained in the product combination are not related or have a low degree of correlation with other products. Furthermore, the highest support does not represent the highest correlation. Therefore, based on the highest support To determine the best matching relationship combination, its accuracy is open to question

[0018] Secondly, when selecting two product combinations or three product combinations as the final best matching relationship combination, the existing scheme is: as long as the three product combination sets are not empty, determine the PA according to the three product combination sets, generally Generally speaking, the advantage of choosing a three-item product portfolio set is that it appropriately expands the number of constituent products and effectively expands user interests. The degree of correlation between the products in the set, or when the correlation between products in some combinations in the three-item product mix set is low, the accuracy of simply selecting the three-item product mix set as the final result is also open to question

Images