Prediction data output method and device, storage medium and electronic equipment

A technology for predicting data and output methods, applied in the field of artificial intelligence, can solve problems such as the inability to accurately predict the return of resource deployment effects, the failure to achieve high-accuracy predictions, and the complexity of resource deployment channels, so as to improve adaptability and versatility, The effect of solving inaccurate reported data and solving data barriers

Pending Publication Date: 2021-08-27
BEIJING XUEZHITU NETWORK TECH
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the data barriers between cross-platforms, and the complexity and diversification of resource delivery channels, high-accuracy forecasts have not yet been achieved
Relevant technologies cannot accurately predict the return on the effect of cross-platform resource delivery, because large platforms can predict the delivery effect within the platform based on statistical or machine learning models
However, there are data barriers and information synergy between different platforms. The process of investing resources on each platform to affect the final return (such as sales / revenue) is complex and abstract, involving human psychology, with a lot of logic and measurement noise. Currently, there is no special response to this scenario. The techniques and models for forecasting under / problems need to build more complex deep learning models
[0004] For the above-mentioned problems existing in related technologies, no effective solution has been found yet

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
  • Prediction data output method and device, storage medium and electronic equipment
  • Prediction data output method and device, storage medium and electronic equipment
  • Prediction data output method and device, storage medium and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] The method embodiment provided in Embodiment 1 of the present application may be executed in a server, a computer, a mobile phone, or a similar computing device. Take running on the server as an example, figure 1 It is a block diagram of the hardware structure of a server in the embodiment of the present invention. like figure 1 As shown, the server can include one or more ( figure 1 Only one is shown in ) processor 102 (processor 102 may include but not limited to processing devices such as microprocessor MCU or programmable logic device FPGA) and memory 104 for storing data. Optionally, the above-mentioned server can also be A transmission device 106 for communication functions and an input and output device 108 are included. Those of ordinary skill in the art can understand that, figure 1 The shown structure is only for illustration, and it does not limit the structure of the above server. For example, the server may also include figure 1 more or fewer componen...

Embodiment 2

[0092] In this embodiment, a predictive data output device is also provided, which is used to implement the above embodiments and preferred implementation modes, and what has already been described will not be repeated. As used below, the term "module" may be a combination of software and / or hardware that realizes a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementations in hardware, or a combination of software and hardware are also possible and contemplated.

[0093] Image 6 is a structural block diagram of a predictive data output device according to an embodiment of the present invention, such as Image 6 As shown, the device includes: an acquisition module 60, a construction module 62, a receiving module 64, and an output module 66, wherein,

[0094] An acquisition module 60, configured to acquire delivery combination data of the target virtual resource in multiple delivery channels, wh...

Embodiment 3

[0107] An embodiment of the present invention also provides a storage medium, in which a computer program is stored, wherein the computer program is set to execute the steps in any one of the above method embodiments when running.

[0108] Optionally, in this embodiment, the above-mentioned storage medium may be configured to store a computer program for performing the following steps:

[0109] S1. Obtain delivery combination data of the target virtual resource in multiple delivery channels, wherein the delivery combination data includes historical delivery data and return data of the historical delivery data;

[0110] S2, constructing supervision data based on the delivery combination data;

[0111] S3. Receive a user parameter, where the user parameter is used to indicate an output step of the prediction data;

[0112] S4. Input the supervisory data sequence into a sequence seq2seq model, and use the seq2seq model to output prediction data of the target virtual resource at ...

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 prediction data output method and device, a storage medium and electronic equipment, and belongs to the field of artificial intelligence. The method innovatively introduces a coding and decoding structure. The method comprises the following steps: obtaining delivery combination data of a target virtual resource in a plurality of delivery channels, the delivery combination data comprising historical delivery data and return data of the historical delivery data; constructing supervision data based on the putting combination time sequence data; and performing dimension deformation on the supervision data, inputting a sequence into a sequence seq2seq model for training, and predicting and outputting prediction data of the target virtual resource in the future time by adopting the seq2seq model. The technical problem that multi-channel return data cannot be accurately predicted in the prior art is solved, the cross-platform data barrier is solved, and the adaptability and the universality of the prediction model are improved.

Description

technical field [0001] The present invention relates to the field of artificial intelligence, in particular, to a method and device for outputting prediction data, a storage medium, and electronic equipment. Background technique [0002] In related technologies, with the development of science and technology, the amount of Internet information continues to grow, and the number and complexity of resource distribution channels increase. The process of cross-platform resource distribution affecting the final return is in a black box state, and resource providers cannot grasp the expected effect of distribution in advance. In this way, other plans such as future production can be adjusted in time. [0003] In related technologies, it is still impossible to accurately predict the effect of cross-platform delivery. For scenarios with relatively simple environments, it is possible to realize private domain range prediction by building a machine learning model. Due to the data barr...

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): G06Q10/04G06Q40/06G06N3/04G06N3/08
CPCG06Q10/04G06Q40/06G06N3/08G06N3/044G06N3/045
Inventor 张水佩潘亮旭
Owner BEIJING XUEZHITU NETWORK TECH
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