Method and device for predicting sales volume data, equipment and storage medium
A technology for data prediction and sales data, applied in the computer field, it can solve the problems of ignoring data, high feature extraction requirements, and difficulty in learning the relationship between different features, so as to achieve the effect of improving accuracy.
Pending Publication Date: 2021-12-03
北京京东智能城市大数据研究院
View PDF4 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] Among them, the traditional time series prediction model can only capture the linear pattern of the data, while ignoring the nonlinear model of the data; the data-driven machine learning model has high requirements for feature extraction, and it is difficult to learn the relationship between different features; The deep learning model of data, modeling and data mining the time series relationship inside the time series data, ignoring the spatiotemporal characteristics of the data
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0033] Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
[0034] Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities ma...
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
Login to View More Abstract
The invention provides a method and device for predicting sales volume data, equipment and a storage medium, and relates to the technical field of computers. The method comprises the following steps: acquiring regional information data of different regions and sales data and intentional sales data of each region in different time periods; based on a pre-configured target sales volume, respectively processing the sales data and intentional sales data of each time period of each region to obtain a time characteristic value data set of each time period of each region; performing feature value aggregation on the region information data of each region to obtain a spatial feature value data set of each region; training the first model based on the time characteristic value data set of each time period of each region and the space characteristic value data set of each region to obtain a spatio-temporal representation data set; wherein the spatio-temporal representation data set is used for training the sales volume data prediction model. The method can combine time features and spatial features, and can improve the accuracy of a sales volume data prediction model.
Description
technical field [0001] The present disclosure relates to the field of computer technology, and in particular to a method, device, device and storage medium for sales data prediction. Background technique [0002] Sales volume forecasting is critical for the online and online retail industry to optimize supply chains, reduce operating costs and increase revenue. Sales forecasts during shopping festivals are crucial for shopping malls and user-centric online retail platforms. Sudden sales surges driven by promotions pose a huge challenge to retailers, leading to problems such as out-of-stocks and even system crashes, bringing consumers a poor shopping experience. For shopping malls and online retail platforms, it is crucial to accurately forecast products in different categories to better prepare their inventories and design appropriate product promotion strategies. [0003] Sales data prediction models in related technologies include: traditional time series prediction mode...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06Q30/02
CPCG06Q30/0205
Inventor 秦慧玲詹仙园郑宇
Owner 北京京东智能城市大数据研究院