Forecasting Characteristic Information Change Using Pre-Estimation Model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for forecasting future trends in information changes, such as search volume and link click counts, are inadequate as they fail to account for various influencing factors, making accurate predictions difficult, especially when user-adjusted parameters like advertising area and time are involved.
Innovation Solution
A method and apparatus that acquire historical and incremental data to establish a pre-estimation model, using this data to forecast future changes in characteristic information by determining ratios and trends, thereby enhancing prediction accuracy and user understanding.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If forecasting is based only on historical data of characteristic information, then the method is simple, but the prediction accuracy deteriorates because it cannot account for other influencing factors such as delivery area, time, search volume, and user adjustments
Solution Approach 1:
The patent segments the forecasting model into multiple independent components: a pre-estimation model that processes historical characteristic data and incremental data separately, and a post-processing stage that incorporates other influencing factors. This segmentation allows each component to focus on specific factors, improving overall prediction accuracy while maintaining manageable model complexity through modular architecture.
Solution Approach 2:
The patent introduces new dimensions to the forecasting model by incorporating incremental data representing changes in characteristic information, and by adding other influencing factors as separate input dimensions. This dimensional expansion enables the model to capture temporal dynamics and external factors that traditional single-dimensional historical data analysis cannot accommodate, thereby improving prediction accuracy.
2Measurement precision
If the model incorporates multiple influencing factors and user adjustments, then the prediction accuracy improves, but the computational complexity and data processing requirements increase
Solution Approach 1:
The patent performs preliminary processing by pre-calculating and storing historical characteristic data and incremental data in a structured format before the actual forecasting operation. This preliminary action reduces the computational burden during prediction by avoiding redundant data processing, thereby improving computational efficiency while maintaining the incorporation of multiple influencing factors.
Solution Approach 2:
The patent introduces incremental data as an intermediary that bridges historical characteristic data and current forecasting requirements. This intermediary component efficiently encapsulates changes and trends, allowing the model to incorporate multiple influencing factors without requiring direct processing of all raw data, thus improving computational efficiency.
3Measurement precision
If historical data alone is used for forecasting, then data processing is straightforward, but the ability to reflect mutual influences between different characteristic information is lost
Solution Approach 1:
The patent merges historical characteristic data with incremental data and other influencing factors into a unified forecasting framework. This merging process integrates multiple data sources and factor types while maintaining a structured processing architecture, enabling the model to reflect mutual influences between different characteristic information without excessive data processing complexity.
Solution Approach 2:
The patent designs a universal forecasting model that can process multiple types of characteristic information and influencing factors through a common framework. This multi-functional approach allows the model to handle diverse data types and reflect mutual influences across different characteristics while maintaining consistent processing logic, thereby improving prediction accuracy without proportionally increasing data processing complexity.
Data Source
AI summary
Method and apparatus for forecasting a characteristic information change. Historical characteristic data in at least one computation period and current incremental data of multiple pieces of first characteristic information corresponding to a pre-estimation model is acquired. The current incremental data is used for indicating a ratio of characteristic data on a day immediately before a forecasting day of each of the multiple pieces to the historical characteristic data in the at least one computation period of each of the multiple pieces of first characteristic information. A first change information on the forecasting day of second characteristic information is determined by a forecasting process using the pre-estimation model based on the historical characteristic data and the current incremental data. Based on the first change information, change pre-estimation information on the forecasting day of the second characteristic information is determined to prompt a user to execute a corresponding operation.