Property analysis method and system for entities

An attribute analysis and entity technology, applied in the field of data analysis, can solve problems such as unreasonable thresholds, difficulty in ensuring the accuracy of screening results, time-consuming and labor-intensive manual screening, etc., to simplify user operations and achieve accurate and reliable analysis results.

Active Publication Date: 2018-02-09
KOUBEI SHANGHAI INFORMATION TECH CO LTD
View PDF10 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, in the process of implementing the present invention, the inventor found that there are at least the following problems in the prior art: the number of attributes of entities is too numerous to enumerate, and the attributes of different entities vary widely, so it is difficult to determine the exact

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Property analysis method and system for entities
  • Property analysis method and system for entities
  • Property analysis method and system for entities

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0059] Example one

[0060] figure 1 It shows a flowchart of an attribute analysis method for an entity provided by Embodiment 1 of the present invention. Such as figure 1 As shown, the method includes:

[0061] Step S110: Receive a labeled sample set, and determine the entity type of each labeled sample in the labeled sample set.

[0062] Among them, the labeled sample set contains multiple labeled samples. For example, the set of labeled samples may be input by the user. Normally, the set of annotation samples entered by the user is set according to specific business requirements. For example, the business operation staff may mark each known entity (such as a store) as whether or not they are selected according to the business goal that they ultimately want to achieve, which can be a positive sample, a negative sample, or a graded sample.

[0063] Among them, each labeling sample usually belongs to the same entity type, for example, all belong to the store type; or each labeling ...

Example Embodiment

[0079] Example two

[0080] figure 2 It shows a flowchart of an attribute analysis method for an entity provided in the second embodiment of the present invention. Such as figure 2 As shown, the method includes:

[0081] Step S200: Pre-set an entity index library.

[0082] In actual situations, the solution in the present invention can be universally applied to multiple types of entities. In specific implementation, the present invention actually provides an attribute analysis system, which can realize the analysis operation of various types of entities. Correspondingly, the entity indicator database stores entity indicators corresponding to various types of entities. . For example, multiple store entity indicators corresponding to the entity of the store type may be stored, multiple commodity entity indicators corresponding to the entity of the product type may also be stored, and multiple entities corresponding to the entity of the electronic coupon type may also be stored. E...

Example

[0112] Example 1:

[0113] This example uses products as an example. In this example, there are two different scenarios. Scenario One is: Operation A needs to select products for activities; Scenario Two: Operation B has to deal with consumption upgrades, there is a new product corresponding to high-end users, and a boutique product pool needs to be established .

[0114] Based on their own experience, both Operation A and Operation B marked 200 products that meet the conditions as the label sample input system. The following commodity entity indicators are stored in the existing entity indicator database in the system:

[0115] (1) Product category, brand, brand tone score, attributes, keywords extracted by algorithm, main image quality score, product id (GSPUid) and other product identifications;

[0116] (2) The sales amount and number of products, conversion rate, single purchase number, unit price, purchase amount and quantity associated with the order, frequency and time inter...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a property analysis method and system for entities and relates to the field of data analysis. The method comprises the steps that an annotation sample set is received, and an entity type of all annotation samples in the annotation sample set is determined; an entity index set corresponding to the entity type is determined according to a preset entity index base, and sampleproperty information corresponding to all the annotation samples in the annotation sample set is determined according to the entity index set; and a corresponding property analysis model is trained according to annotation results of all the annotation samples in the annotation sample set and the sample property information corresponding to all the annotation samples, and properties of the entitiesare analyzed through the property analysis model. In this way, user operation is simplified; and moreover, as many as entity properties are stored in the entity index base, and the property analysismodel is subjected to machine learning and training, so that the analysis result is accurate and reliable.

Description

technical field [0001] The invention relates to the field of data analysis, in particular to an attribute analysis method and system for entities. Background technique [0002] Entities refer to objects or things that exist objectively in the real world and can be distinguished from each other. Usually, the difference between entities can be described by a series of attributes. For example, in the e-commerce and O2O (full name "Online To Offline", that is: online offline / online to offline) industries, commodities, stores, electronic coupons, and merchants can all be called entities. Taking the commodity entity as an example, the characteristics of the commodity such as name, price, category, sales volume, and evaluation can be used as attributes describing the commodity entity. By analyzing the attributes of the entity, various business functions can be realized. For example, various purposes such as investment promotion, promotional activities, bottom-up elimination, new ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F17/30G06Q30/02
CPCG06F16/20G06Q30/0201
Inventor 沈晶晶
Owner KOUBEI SHANGHAI INFORMATION TECH CO LTD
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap