Asset Value Evaluation Using Graph Convolution and Attribute Embeddings
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing asset value evaluation methods suffer from low accuracy due to reliance on fixed indicators and manual assessments, which are subjective and fail to account for user-specific relationships between assets and their attributes.
Innovation Solution
An asset value evaluation method utilizing a graph convolutional network model that performs embedding representations based on asset attributes and historical interactions, incorporating a training process involving first- and second-type triplets to determine asset embedding vectors, enhancing the accuracy of asset value determination.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If fixed indicators and manual assessments are used for asset value evaluation, then the evaluation process is simple and fast, but the accuracy and objectivity of the evaluation results deteriorate
Solution Approach 1:
The patent replaces manual mechanical assessment with an automated graph convolutional network model that processes asset data through embedding representations and neural network computations, substituting human judgment with algorithmic evaluation to improve objectivity and accuracy
Solution Approach 2:
The patent transforms asset evaluation from using fixed static indicators to dynamic embedding vectors that capture complex relationships between assets and their attributes, changing the parameter representation from simple fixed values to high-dimensional learned representations that improve measurement precision
2Device complexity
If traditional evaluation methods are used, then the system complexity is low, but the ability to account for user-specific relationships between assets and attributes deteriorates
Solution Approach 1:
The patent introduces a new dimensional framework by constructing asset knowledge graphs and using graph convolutional networks to model relationships in multiple dimensions (asset-asset, asset-attribute, user-asset), moving beyond traditional single-dimensional evaluation to capture complex user-specific relationships
Solution Approach 2:
The patent introduces embedding vectors as intermediary representations that mediate between raw asset data and evaluation outcomes, allowing the system to capture and process complex relationships through learned vector representations that bridge data and decision-making
Data Source
AI summary
Disclosed are an asset value evaluation method and apparatus, a model training method and apparatus, and a readable storage medium. The asset value evaluation method includes: acquiring input asset value query information for a user; when it is determined that there is historical asset interaction information of the user, determining an asset set obtained by means of making a query using the asset value query information, the asset set includes at least one asset; performing embedding representation on each asset, so as to determine an asset embedding vector of each asset, the asset embedding vector is obtained by means of training based on the relationship between each asset and an attribute, and the attribute is used for representing an inherent parameter of the asset; and inputting the asset embedding vector of each asset into a graph convolutional network model to obtain the value of each asset for the user.