A method for predicting activation volume of electronic products and a server cluster
A server cluster and electronic product technology, applied in the field of data processing, can solve problems such as low accuracy rate, unstable effect, and inability to fit the law of the activation amount of electronic products over time, so as to reduce training error and test error, The effect of stability and accuracy improvement
Active Publication Date: 2020-12-18
LENOVO (BEIJING) LTD
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] In the prior art, the prediction of the activation amount of electronic products is all predicted by a single regression model or time series analysis method. However, the former cannot fit the time law of the data, that is, it is impossible to fit the activation amount of electronic products with time. The law of time change, the latter cannot learn the influence of related factors changing over time, that is, it cannot learn the influence of related factors that affect the activation of electronic products (such as promotional activities, endorsement activities, etc.) over time, so its effect Both are unstable and the accuracy is very low
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
[0034] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments, but not as a limitation of the present invention.
[0035] Various aspects and features of the invention are described herein with reference to the accompanying drawings.
[0036] It should be understood that various modifications may be made to the embodiments of the inventions herein. Accordingly, the above description should not be viewed as limiting, but only as exemplifications of embodiments. Those skilled in the art will envision other modifications within the scope and spirit of the invention.
[0037] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and, together with the general description of the invention given above and the detailed description of the embodiments given below, serve to explain the invention. principle.
[0038] These ...
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 present invention provides an electronic product activation volume prediction method and a server cluster. The method comprises a step of obtaining first activation volume data and at least one first factor data which influences the first activation volume data, a step of carrying out time serialization on the first activation volume data and the at least one factor data, a step of carrying out time rule dismantling on the data which is subjected to time serialization and obtaining second activation volume data which comprises change trend data which changes with time in the condition that electronic product activation volume is not affected by the at least one first factor data, a step of judging whether the change trend data has a time rule or not, and a step of carrying out characterization processing on the change trend data to generate second factor data if the change trend data has the time rule, inputting the at least one first factor data and a second factor data into a preset model to learn, and predicting the electronic product activation volume of a predetermined time. According to the scheme of the invention, the electronic product activation volume of the predetermined time can be accurately predicted.
Description
technical field [0001] The invention relates to data processing, in particular to a method for predicting the activation amount of electronic products and a server cluster. Background technique [0002] Personal computers (PCs), mobile phones, tablet computers and other electronic products are expensive hardware products. The backlog of their inventory, whether it is the inventory of the whole machine or the inventory of parts, will seriously affect the flow of funds, and even drag down the capital chain of the enterprise. The most effective way to reduce inventory is: first, to accurately grasp the market demand, so that the difference between production volume and sales volume (that is, inventory) is minimized; second, to grasp the market demand in advance, by giving the forecast value before the procurement lead time , to guide scientific and reasonable procurement. So how to measure market demand to reduce inventory? Due to the intelligence of electronic products, the ...
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 Patents(China)
IPC IPC(8): G06Q30/02G06F17/18
CPCG06F17/18G06Q30/0202
Inventor 李冬阳
Owner LENOVO (BEIJING) LTD