Method for obtaining commodity recommendation sequence and commodity recommendation

Abstract

A method for obtain a commodity recommendation sequence and a commodity recommendation method are disclosed. That method is use for providing a commodity recommendation sequence for a user to be recommended, and score the commodity to be recommended of the user to be recommended according to the history purchase commodity information of the user to be recommended, and obtaining a prediction score.Clustering the history purchased goods of the recommended user, obtaining a plurality of commodity categories, calculating the distance between each commodity to be recommended and a plurality of commodity categories, and obtaining the distance value between each commodity to be recommended and a plurality of commodity categories; Obtaining evaluation parameters of each commodity to be recommended corresponding to the user to be recommended according to the prediction score and the distance value; According to the size of the evaluation parameters of each commodity to be recommended, all thecommodities to be recommended are sorted, and the first K commodities are recommended to the users to be recommended.

Description

technical field

[0001] The invention relates to a data mining recommendation method, in particular to a method for obtaining a product recommendation sequence and a product recommendation method. Background technique

[0002] With the continuous expansion of the scale of e-commerce and the rapid growth of the number and types of commodities, customers need to spend a lot of time to find the commodities they want to buy. This process of browsing a large amount of irrelevant information and products will undoubtedly cause consumers who are submerged in the problem of information overload to continue to lose.

[0003] The current recommendation system mainly uses the user's historical purchase records and the user's social network relationship to recommend the user. These methods can only passively predict and recommend the user's next purchase, and are rarely able to guide or attract users. Choose to buy some items. In the current recommendation method, the similarity betwee...

Examples

Embodiment 1

[0034] The invention discloses a method for obtaining a product recommendation sequence, which is used to select a sequence composed of some products to be recommended from a plurality of products to be recommended as a product recommendation sequence for a user, and the user has a history of purchasing products.

[0035] The present invention proposes to maximize the non-linear combination effect, expecting to be able to recommend the product that maximizes the user's preference and the product that matches the purchased product. Using this method, the shopping history of a specific target user can be automatically learned, and the target user can be learned. The product category and the target user's preference in the user's historical shopping record, that is to say, the recommendation method provided by the present invention not only considers the user's preference, but also considers the purchased thing and the existing product when recommending a new product Whether the m...

Embodiment 2

[0096] A commodity recommendation method, used for recommending commodities for users to be recommended, said method comprising:

[0097] Step A. Determine whether the user to be recommended has a purchase history: if the user to be recommended has a purchase history, perform step B; otherwise, perform step C;

[0098] Step B. Using the method for obtaining the product recommendation sequence described in Embodiment 1, obtain the product recommendation sequence of the user to be recommended, and recommend the product in the product recommendation sequence to the user to be recommended;

[0099] Step C. Obtain the relationship matrix between the user to be recommended and the neighbor user. Each neighbor user has a history of purchasing commodities. The method of obtaining the commodity recommendation sequence in Embodiment 1 is used to obtain the commodity recommendation sequence of each neighbor user. According to the commodity recommendation sequence of each neighbor user, t...

Embodiment 3

[0108] In this embodiment, the user to be recommended has a history of purchasing commodities, and commodities are recommended for the user to be recommended.

[0109] User set to be recommended U={u 1 ,u 2 ,u 3 ,u 4}, commodity collection Item={I 1 ,I 2 ,I 3 ,I 4 ,I 5 ,I 6 ,I 7 ,I 8 ,I 9}, where {I 1 ,I 2 ,I 3 ,I 4 ,I 5} for historical purchases, {I 6 ,I 7 ,I 8 ,I 9} is the product to be recommended.

[0110] The user-product rating matrix Rating is:

[0111] [[3,4,5,1,2,? ,? ,? ,? ],

[0112] [2,4,3,4,5,3,2,1,4]

[0113] [2,3,2,4,2,5,4,3,4]

[0114] [2,3,5,4,3,4,3,5,4]]

[0115] In the user-product rating matrix Rating, "?" represents that the user to be recommended has not purchased the product, and the collaborative filtering method based on content expansion is needed to obtain the predicted score of each product to be recommended by the user to be recommended.

[0116] Meta-data=[[2,3,4,5,6,2,4,7,5],[2,3,5,4,2,7,4,5,8],[3,2, 4,6,5,4,2,8,5],...

technical field

[0001] The invention relates to a data mining recommendation method, in particular to a method for obtaining a product recommendation sequence and a product recommendation method. Background technique

[0002] With the continuous expansion of the scale of e-commerce and the rapid growth of the number and types of commodities, customers need to spend a lot of time to find the commodities they want to buy. This process of browsing a large amount of irrelevant information and products will undoubtedly cause consumers who are submerged in the problem of information overload to continue to lose.

[0003] The current recommendation system mainly uses the user's historical purchase records and the user's social network relationship to recommend the user. These methods can only passively predict and recommend the user's next purchase, and are rarely able to guide or attract users. Choose to buy some items. In the current recommendation method, the similarity betwee...

Examples

Embodiment 1

[0034] The invention discloses a method for obtaining a product recommendation sequence, which is used to select a sequence composed of some products to be recommended from a plurality of products to be recommended as a product recommendation sequence for a user, and the user has a history of purchasing products.

[0035] The present invention proposes to maximize the non-linear combination effect, expecting to be able to recommend the product that maximizes the user's preference and the product that matches the purchased product. Using this method, the shopping history of a specific target user can be automatically learned, and the target user can be learned. The product category and the target user's preference in the user's historical shopping record, that is to say, the recommendation method provided by the present invention not only considers the user's preference, but also considers the purchased thing and the existing product when recommending a new product Whether the m...

Embodiment 2

[0096] A commodity recommendation method, used for recommending commodities for users to be recommended, said method comprising:

[0097] Step A. Determine whether the user to be recommended has a purchase history: if the user to be recommended has a purchase history, perform step B; otherwise, perform step C;

[0098] Step B. Using the method for obtaining the product recommendation sequence described in Embodiment 1, obtain the product recommendation sequence of the user to be recommended, and recommend the product in the product recommendation sequence to the user to be recommended;

[0099] Step C. Obtain the relationship matrix between the user to be recommended and the neighbor user. Each neighbor user has a history of purchasing commodities. The method of obtaining the commodity recommendation sequence in Embodiment 1 is used to obtain the commodity recommendation sequence of each neighbor user. According to the commodity recommendation sequence of each neighbor user, t...

Embodiment 3

[0108] In this embodiment, the user to be recommended has a history of purchasing commodities, and commodities are recommended for the user to be recommended.

[0109] User set to be recommended U={u 1 ,u 2 ,u 3 ,u 4}, commodity collection Item={I 1 ,I 2 ,I 3 ,I 4 ,I 5 ,I 6 ,I 7 ,I 8 ,I 9}, where {I 1 ,I 2 ,I 3 ,I 4 ,I 5} for historical purchases, {I 6 ,I 7 ,I 8 ,I 9} is the product to be recommended.

[0110] The user-product rating matrix Rating is:

[0111] [[3,4,5,1,2,? ,? ,? ,? ],

[0112] [2,4,3,4,5,3,2,1,4]

[0113] [2,3,2,4,2,5,4,3,4]

[0114] [2,3,5,4,3,4,3,5,4]]

[0115] In the user-product rating matrix Rating, "?" represents that the user to be recommended has not purchased the product, and the collaborative filtering method based on content expansion is needed to obtain the predicted score of each product to be recommended by the user to be recommended.

[0116] Meta-data=[[2,3,4,5,6,2,4,7,5],[2,3,5,4,2,7,4,5,8],[3,2, 4,6,5,4,2,8,5],...

Images