Time sequence people flow data and scalar label number fusion method and system

A technology of time series data and fusion method, applied in the information field, can solve the problems of irreparable, insufficient integration, and inability to achieve data dimension completion, and achieve the effect of strong data support, strong versatility, and broad application prospects.

Pending Publication Date: 2022-08-05
SHANGHAI FENZE TIMES SOFTWARE TECH CO LTD
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this invention cannot fully integrate the advantages of existing data, cannot make up for the shortcomings of a single type of data, completes the integration of time series features and scalar features, labeled data and non-labeled data, and cannot realize the completion of data dimensions

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
  • Time sequence people flow data and scalar label number fusion method and system
  • Time sequence people flow data and scalar label number fusion method and system
  • Time sequence people flow data and scalar label number fusion method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] According to a fusion method of time series human flow data and scalar label number provided by the present invention, such as Figure 1-Figure 3 shown, including:

[0059] Step S1: Clean time series data and label data, and obtain time series access data and offline label summary data;

[0060] Step S2: complete the management of time series data and label data;

[0061] Step S3: perform time series data feature engineering;

[0062] Step S4: fitting the feature engineering result data to a normal distribution, and removing values ​​other than the preset standard value;

[0063] Step S5: supplementing the vacant window of values ​​other than the preset standard value, and constructing a time series data distribution curve;

[0064] Step S6: Fit the label data scalar to the distribution curve of the time series data to obtain the population distribution at any time.

[0065] Specifically, in the step S1:

[0066] Clean time-series data and label data, and obtain time...

Embodiment 2

[0097] Embodiment 2 is a preferred example of Embodiment 1, in order to describe the present invention in more detail.

[0098] The invention relates to the technical field of normal distribution, time series data and binomial difference, in particular, to a display system and a correction system of a fusion method of time series human flow data and scalar label number, in particular to a time series human flow data and A fusion method for the number of scalar labels.

[0099] According to a fusion method of time series human flow data and scalar label number provided by the present invention, the method includes the following steps:

[0100] Step S1: Clean time series data and label data, and obtain time series personnel access data within one year and offline label summary data with natural days as a window;

[0101] Step S2: Build an ETL pipeline to complete the management of time series data and label data;

[0102] Step S3: perform time series data feature engineering, ...

Embodiment 3

[0124] Embodiment 3 is a preferred example of Embodiment 1, in order to describe the present invention in more detail.

[0125] The present invention provides a fusion method of time series human flow data and scalar label number, and the implementation and deployment method of the method include the following steps:

[0126]Step S1: Clean time-series data and label data, and obtain time-series personnel access data within one year and offline labels with natural days as a window; this step needs to complete the dimension selection of time-series data and preliminary screening of label data, and select the most recent time-series data. Years of data samples, while obtaining the label data of the corresponding time window, and performing statistical summary and analysis, including gender bucketing, source city orientation, purchase intention extraction, etc.;

[0127] Step S2: Build an ETL pipeline to complete the management of time series data and label data. For cleaning time...

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 provides a method and system for fusing time sequence visitor flow data and scalar label number, and the method comprises the steps: cleaning time sequence data and label data, and obtaining time sequence access data and offline label summary data; finishing the treatment of the time sequence data and the label data; performing time series data feature engineering; fitting normal distribution of the feature engineering result data, and removing numerical values except a preset standard value; vacant windows of numerical values except the preset standard value are supplemented, and a time sequence data distribution curve is constructed; and carrying out scalar fitting on the label data to obtain a distribution curve of the time series data to obtain crowd distribution at any moment. According to the method, the unique advantages of different types of data are fully utilized for mutual complementation, and fusion of time sequence features, scalar features, label data and non-label data is completed. According to the method, the capability of predicting the label crowd in real time can be obtained, and data support is provided for multiple scenes such as large-screen display, business expansion and building portraits.

Description

technical field [0001] The invention relates to the field of information technology, and in particular, to a method and system for fusing time-series human flow data and scalar label numbers. Background technique [0002] In recent years, with the continuous advancement of online and offline advertising business, more and more advertisers have become more and more urgent to explore the audience. However, in real scenarios, the types of data are often incomplete, the data dimension is seriously missing, and a single type of data cannot meet the current needs at all. At present, there is no fusion method of time-series traffic data and scalar labels. Combined with offline advertising and online application feedback data, it is possible to see the distribution of the crowd or the statistics of a single crowd label. Therefore, a method that can integrate crowd time series data and label statistics to generate time series crowd label data becomes particularly important. [0003...

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): G06F16/2458G06F16/9537G06F16/215G06K9/62G06Q30/02
CPCG06F16/2462G06F16/2474G06F16/215G06F16/9537G06Q30/0202G06F18/251G06F18/214
Inventor 曲洋代光英孙亮宁玉杰王小伟
Owner SHANGHAI FENZE TIMES SOFTWARE TECH CO LTD
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