Commodity pushing method based on regional user habit big data

Abstract

The invention discloses a commodity pushing method based on regional user habit big data. User information comprises positioning information and transaction data, the store information comprises storeposition information and commodity data, and a predicted purchase date is calculated according to purchase frequencies of other users and a previous purchase number, so that a push message is sent toa client before the commodity is used up, the user can be reminded to replenish the commodity in time, and a purchase suggestion is given. Purchase modes are divided into online purchase modes and offline purchase modes. purchase habits of most users in the area are combined; giving a priority purchase mode and an alternative purchase mode. The commodity recommendation method and device can adaptto different commodities and different regional conditions, select the optimal purchase mode, facilitate the customers to purchase the commodities, preferentially give recommended shops with different purchase modes of the same commodities, give recommendation of similar commodities when there is no appropriate same commodity recommendation, and provide alternative schemes for the users to selectand reduce the work of the customers for selecting the commodities.

Description

technical field [0001] The invention relates to the technical field of commodity push, in particular to a commodity push method based on regional user habit big data. Background technique [0002] Push is the most common means of operation, good or bad. It is one of the most efficient channels to contact and influence users. On the good side, it can immediately improve various operating indicators, but on the bad side, it is easy to cause disgust and even uninstall from users. Many operators are cautious about pushing, and the user experience is like a sharp knife hanging over their heads, for fear of interruption. In fact, if the push is good, it will have a multiplier effect on various KPIs. [0003] Most of the existing push methods are based on the user's consumption records, get the consumer's consumption trend and consumption habits, and carry out targeted commodity push. In first-tier cities, with well-developed logistics, rich variety of products, and convenient a...

AI Technical Summary

Problems solved by technology

[0003] Most of the existing push methods are based on the user's consumption records, get the consumer's consumption trend and consumption habits, and carry out targeted commodity push. In first-tier cities, with well-developed logistics, rich variety of products, and convenient after-sales service, they often choose online consumption, while in third- and fourth-tier cities, poor logistics and inconvenient after-sales service, locals often choose to purchase offline. The existing push method push is often not in line with the local conditions, and the push effect is poor. Therefore, a product push method based on big data of regional user habits is needed