Professional degree scoring method and system and article recommendation method and system, equipment and storage medium

A technology of professionalism and items, applied in the computer field, can solve problems such as lack of object scoring results, low professionalism of experts, and too little expert data

Pending Publication Date: 2019-12-03
BEIJING JINGDONG SHANGKE INFORMATION TECH CO LTD +1
3 Cites 1 Cited by

AI-Extracted Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to overcome the lack of objectivity of the object scoring results due to the low professionalism of e...
View more

Method used

By extracting the professional degree data corresponding to the target article category of all users from the behavior data of all users, and then extracting the professional degree data of a target user, according to the above-mentioned professional degree data, the target user is further obtained to the target article category. Professionalism score. Through the above method, the professional degree of each user can be scored, and users with higher professional degree scores can be further classified as professional users under the target item category. In this way, a relatively large amount of expert data can be guaranteed. In the follow-up In the process of item evaluation, ensure that the evaluation results are more intelligent and more objective....
View more

Abstract

The invention discloses a professional degree scoring method and system, an article recommendation method and system, equipment and a storage medium. The user professional degree scoring method comprises: acquiring behavior data of all users; randomly selecting a target article category and a target user; extracting professional degree data of the target user under the target article category fromthe behavior data; extracting professional degree data of all the users under the target article category from the behavior data; and according to the profession degree data of the target user and the profession degree data of all users, obtaining a profession degree score of the target user for the target article category. According to the method, the profession degree data of the target articlecategory corresponding to all the users are extracted from the behavior data of all the users, then the profession degree data of one target user are extracted, and the profession degree score of thetarget user for the target article category is further obtained according to the profession degree data.

Application Domain

Buying/selling/leasing transactionsMarket data gathering

Technology Topic

Data miningScore method +1

Image

  • Professional degree scoring method and system and article recommendation method and system, equipment and storage medium
  • Professional degree scoring method and system and article recommendation method and system, equipment and storage medium
  • Professional degree scoring method and system and article recommendation method and system, equipment and storage medium

Examples

  • Experimental program(14)

Example Embodiment

[0096] Example 1
[0097] A method of scoring user professionalism, such as figure 1 As shown, the method for scoring user professionalism includes:
[0098] Step 110: Obtain behavior data of all users;
[0099] Step 120: arbitrarily select a target item category and a target user;
[0100] Step 130: Extract the professionalism data of the target user under the target item category from the behavior data;
[0101] Step 140: Extract professional data of all users in the target item category from the behavior data;
[0102] Step 150: Obtain the professional degree score of the target user for the target item category according to the professional degree data of the target user and the professional degree data of all users.
[0103] It should be noted that the above-mentioned professionalism data may be user purchase data or user comment data or may be evaluations made by other users on the user after the user comments on the item. For example, like data.
[0104] By extracting the professionalism data of all users corresponding to the target item category from the behavior data of all users, and then extracting a target user's professionalism data, the target user's professionalism score for the target item category is further obtained based on the above-mentioned professionalism data . Through the above method, the professionalism of each user can be scored. Furthermore, users with higher professionalism scores can be classified as professional users under the target item. In this way, a relatively large amount of expert data can be guaranteed. In the process of item evaluation, ensure that the evaluation results are more intelligent and objective.

Example Embodiment

[0105] Example 2
[0106] The user professionalism scoring method of this embodiment is a further improvement on the basis of embodiment 1. The professionalism data includes consumption data of the user's purchase of goods, such as figure 2 As shown, step 150 specifically includes:
[0107] Step 1511, extract some items with the highest unit price among all items in the target item category;
[0108] Step 1512: Obtain the first consumption amount of all items purchased by the target user and the second consumption amount of some items purchased by the target user according to the consumption data of the target user;
[0109] Step 1513: Obtain the total sales of some items according to the consumption data of all users;
[0110] Step 1514: Calculate according to the first consumption amount, the second consumption amount and the total sales amount to obtain a first professional degree score used to characterize the purchase professional degree of the target user; the professional degree score includes the first professional degree score; specifically, The first professionalism score may be obtained by multiplying the ratio of the second consumption amount to the first consumption amount and the ratio of the second consumption amount to the total sales amount;
[0111] In this embodiment, users who follow a product with a higher price are generally more professional and worthy of attention. Therefore, some items with a higher unit price are extracted for subsequent data processing;
[0112] In addition, in this embodiment, it is also possible to filter out items in which no consumption record has occurred. Step 1511 specifically includes:
[0113] Filter out items that have no purchase records under the target item category, and extract some items with the highest unit price from the filtered items.
[0114] In this embodiment, the first professional degree score of the target user’s purchase professionalism of the target item category is calculated according to the consumption data of the target user’s purchase of items. If only the consumption data of the target user is considered to evaluate the professional degree of the target user, The first professional score is used as the professional score of the target user for the target item category.

Example Embodiment

[0115] Example 3
[0116] The method for scoring user professionalism in this embodiment is a further improvement on the basis of Embodiment 2. The professionalism data includes comment data of user-reviewed items, such as image 3 As shown, another implementation manner of step 150 is provided, which specifically includes:
[0117] Step 1521. A tag library is preset, and the tag library stores multiple tags corresponding to the target item category; it should be noted that the tags here may be professional nouns or professional sentences corresponding to the target item category.
[0118] Step 1522: Calculate the first ratio of the number of tags belonging to the tag library in the comment data of the target user to the total number of tags in the tag library;
[0119] Step 1523: Obtain a second professional degree score for representing the professional degree of the target user's comment according to the first ratio; the professional degree score includes the second professional degree score.
[0120] In this embodiment, the second professional degree score of the target user’s comment professionalism for the target item category is calculated according to the comment data of the target user’s comment item. If only the comment data of the target user is considered to evaluate the professional degree of the target user, The second professional degree score serves as the professional degree score of the target user for the target item category.

PUM

no PUM

Description & Claims & Application Information

We can also present the details of the Description, Claims and Application information to help users get a comprehensive understanding of the technical details of the patent, such as background art, summary of invention, brief description of drawings, description of embodiments, and other original content. On the other hand, users can also determine the specific scope of protection of the technology through the list of claims; as well as understand the changes in the life cycle of the technology with the presentation of the patent timeline. Login to view more.
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
Try Eureka
PatSnap group products