Seed user screening method, and method and apparatus for evaluating user influence of product

Abstract

The invention discloses a seed user screening method, and a method and an apparatus for evaluating user influence of a product. The seed user screening method based on the user influence comprises the steps of obtaining a user of the product, and searching for a product usage record of the user in using the product, wherein the product usage record comprises usage time of using product each time; obtaining relational network data corresponding to the user; obtaining product usage records of a plurality of relational users in using the product; calculating the influence of the relational users on the user according to the product usage records of the plurality of relational users in using the product; and screening seed users according to the influence. According to the seed user screening method and the evaluation method and apparatus provided by embodiments of the invention, the product usage records of the user and the relational users are obtained through the relational network data of the user, and the spreading force values of the relational users for the user are calculated, so that the usage state of the product by the user can be really reflected; and the promotion and publicity of a new product are realized by utilizing the influence of the user.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a seed user screening method, a product user influence evaluation method and a device. Background technique [0002] A social network is a social structure composed of many nodes. Nodes usually refer to individuals or organizations. Social networks represent various social relationships. link people or organizations together. Social relations include friend relations, classmate relations, business partnerships, race and belief relations, etc. In a social network, everyone will receive and be influenced by the information spread by others. [0003] Currently, the weighted PageRank algorithm can be used to calculate the dissemination power generated by users in their relationship network for a certain product, that is, to calculate the PageRank value of each user in the product’s relationship network with the user’s relationship strength index as the weight , the PageR...

AI Technical Summary

Problems solved by technology

Therefore, the PageRank value cannot truly reflect the actual situation

[0006] 2. The PageRank value only represents the power of communication and has no influence effect, so it cannot be applied to discover potential users of the product

[0007] 3. The PageRank value changes with the strength of the user relationship and does not change with the development of the product, so it cannot be used to assist in judging the stability of product development

Images