Package optimization system and method based on rapid analysis of gpu and adjacent massive data
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology for rapid analysis and massive data, applied in data processing applications, genetic models, predictions, etc., to achieve rapid analysis, avoid parameter estimation and model errors, and avoid high time complexity
Active Publication Date: 2017-05-17
UNIV OF JINAN
View PDF6 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0005] In order to solve the above technical problems, the present invention provides a package optimization system and method based on GPU and rapid analysis of adjacent massive data, which can realize automatic high-speed processing of massive telecommunication data, and obtain a package plan that highly matches the needs of target user groups. Avoid the high time complexity problems caused by using complex models to model massive data and improve the reliability of optimization results
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 2
[0115] (1) User input related parameters
[0116] Step (201): According to the target user group, the user selects 100 representative target users from the customer information database.
[0117] Step (202): Set the desired package including call duration less than 100 minutes, text message range less than 50, data not included, and package tariff standard between 10 yuan and 20 yuan.
[0118] Step (203): set the time length as the data of the past 2 years.
[0119] Step (204): Set the reference data size to 10,000 user records.
[0120] Step (205): set the population size to 50, and the maximum number of iterations to 10,000 generations.
[0121] (2) Automatic package optimization by computer
[0122] Step (206): extract the original target data of the user records of the target user group in the last 2 years.
[0123] Step (207): Extract feature vectors for each user from the original target data (user's monthly average call time, user's average number of SMS messages pe...
specific Embodiment 3
[0152] (1) User input related parameters
[0153] Step (301): The user selects 100 representative target users from the customer information database according to the target user group.
[0154] Step (302): Set the expected package to include 30 to 50 text messages, 5M to 10M traffic, excluding calls, and the package fee to be between 10 and 20 yuan.
[0155] Step (303): set the time length as the data of the last 3 years.
[0156] Step (304): Set the reference data size as 100,000 user records.
[0157] Step (305): set the population size to 100, and the maximum number of iterations to 3000 generations.
[0158] (2) Automatic package optimization by computer
[0159] Step (306): extract the original target data of the user records of the target user group in the last 3 years.
[0160]Step (307): Extract feature vectors for each user from the original target data (the average number of SMS messages per month, the average monthly Internet traffic of the user, the monthly co...
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 discloses a package optimizing system and method based on a GPU and neighboring mass data rapid analysis. The package optimizing system based on the GPU and neighboring mass data rapid analysis comprises a parameter input module, wherein the parameter input module is used for transmitting parameter information to a data generation module and a package optimization module, the data generation module transmits data to the package optimization module, the parameter input module and the data generation module extract information from a client information database, the package optimization module comprises an evolutionary algorithm module and a GPU acceleration module, communication is carried out between the evolutionary algorithm module and the GPU acceleration module, the GPU acceleration module comprises a plurality of package adaptive value evaluation modules, and each package adaptive value evaluation module comprises a similarity calculation module. According to the package optimizing system and method based on the GPU and neighboring mass data rapid analysis, automatic high-speed processing of mass teledata can be achieved, a package scheme which highly meets the demand of a target user group is obtained, the problem that high time complexity is caused due to modeling by using a complex model is solved, and reliability of optimization results is improved.
Description
technical field [0001] This project mainly involves the fields of telecommunications technology, high-performance computing, and data mining. Specifically, it involves a package optimization system and method based on GPU and rapid analysis of adjacent massive data. Background technique [0002] The telecommunications industry occupies an important position in the national economy and penetrates into every aspect of people's lives. On the one hand, when telecom operators launch new service packages, different user groups have different needs, resulting in diversity and complexity of user needs. On the other hand, due to the high penetration rate of telecom operators and the high frequency of information exchange and collection, the amount of data they possess is extremely large. Telecom operators have massive user data, signaling data, log data, traffic data, location data, etc. Therefore, there is an urgent need for an automated optimization design technology, so that tar...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more