KR-20260067218-A - Analysis method of mobile-phone activity data using interactive cyber-physical social system and computing device for executing the same

Abstract

The present invention relates to a method for analyzing mobile phone activity data using a cyber-physical social system. An analysis method according to one disclosed embodiment is a method for analyzing mobile phone activity data using a cyber-physical social system (CPSS) performed on a computing device having one or more processors and a memory storing one or more programs executed by one or more processors, comprising the steps of collecting Call Detail Record (CDR) data within a pre-set city, performing preprocessing on the collected data, and analyzing one or more of spatial patterns and temporal patterns of network traffic based on the preprocessed Call Detail Record data.

Inventors

• 최규상
• 아민파르한

Assignees

• 영남대학교 산학협력단

Dates

Publication Date

20260512

Application Date

20241105

Claims (20)

1. One or more processors, and A method for analyzing mobile phone activity data using a cyber-physical social system (CPSS) performed on a computing device having a memory for storing one or more programs executed by the above-mentioned one or more processors, wherein A step of collecting Call Detail Record (CDR) data within a pre-set city and performing preprocessing on the collected data; and An analysis method comprising the step of analyzing one or more of the spatial and temporal patterns of network traffic based on the above-mentioned preprocessed call detailed record data.
2. In claim 1, The step of performing the above preprocessing is, An analysis method comprising the step of supplementing missing values using the average value of the previous time stamp and the subsequent time stamp when data missing values occur between consecutive time stamps of the above-mentioned detailed call record data.
3. In claim 1, The step of performing the above preprocessing is, A step of detecting duplicate call detail record data based on one or more of user ID, call time, location information, and data type in the above call detail record data; and An analysis method comprising the step of, when the above-mentioned duplicate call detail record data is detected, retaining the most recent call detail record data based on a time stamp among the above-mentioned duplicate call detail record data and removing the remaining call detail record data.
4. In claim 1, The above analysis method is, It further includes the step of converting a call-related network for the city into a graph based on the above-mentioned preprocessed call detailed record data, and The step of converting to the above graph is, Analysis method for setting user ID or location information in the above call detail record data as nodes of a graph, and setting the degree of interaction between the two set nodes as edges of the graph.
5. In claim 4, The above analysis method is, An analysis method further comprising the step of assigning weights to edges connecting the two nodes based on one or more of the number of calls, the number of text message exchanges, and internet usage between the two nodes.
6. In claim 4, The step of converting to the above graph is, A step of generating a main graph of the call-related network based on detailed call record data for all users of the above city; and An analysis method comprising the step of dividing a subgraph based on one or more of the call time, location information, and network traffic density of the call detail record data in the main graph above.
7. In claim 4, The above-mentioned analysis step is, An analysis method comprising the step of analyzing spatial patterns through the correlation coefficient of network traffic between different nodes at a specific time period within the above city.
8. In claim 7, The above-mentioned analysis step is, An analysis method comprising the step of calculating the amount of communication between two users corresponding to the node or between two locations corresponding to the node during the aforementioned specific time period through the Pearson correlation coefficient.
9. In claim 4, The above-mentioned analysis step is, An analysis method comprising the step of analyzing changes in network traffic over a certain period of time in a specific area or user group in the above city.
10. In claim 9, The step of analyzing the above network traffic changes is, An analysis method comprising the step of calculating the correlation between communication usage in the aforementioned specific region or user group at regular time intervals using an autocorrelation function (ACF) to calculate a pattern of increase or decrease in network traffic.
11. One or more processors; Memory; and Includes one or more programs, The above one or more programs are stored in the memory and configured to be executed by the above one or more processors, and The above one or more programs are, A command for collecting Call Detail Record (CDR) data within a pre-set city and performing preprocessing on the collected data; and A computing device comprising a command for analyzing one or more of the spatial and temporal patterns of network traffic based on the above-mentioned preprocessed call detail record data.
12. In claim 11, The command to perform the above preprocessing is, A command for detecting duplicate call detail record data based on one or more of user ID, call time, location information, and data type in the above call detail record data; and A computing device comprising a command to retain the most recent call detail record data based on a timestamp and remove the remaining call detail record data when the above duplicate call detail record data is detected.
13. In claim 11, The above one or more programs are, It further includes a command to convert a call-related network for the city into a graph based on the above-mentioned preprocessed call detailed record data, and The command to convert to the above graph is, A computing device that sets user ID or location information in the above call detail record data as nodes of a graph, and sets the degree of interaction between the two set nodes as edges of the graph.
14. In claim 13, The above one or more programs are, A computing device further comprising a command for assigning weights to an edge connecting the two nodes based on one or more of the number of calls, the number of text message exchanges, and internet usage between the two nodes.
15. In claim 13, The command to convert to the above graph is, A command to generate a main graph of the call-related network based on detailed call record data for all users of the above city; and A computing device comprising a command for dividing a subgraph based on one or more of the call time, location information, and network traffic density of the call detail record data in the main graph above.
16. In claim 13, The command for the above analysis is, A computing device comprising a command for analyzing spatial patterns through the correlation coefficient of network traffic between different nodes at a specific time period within the above city.
17. In claim 16, The command for the above analysis is, A computing device that calculates the amount of communication between two users corresponding to the node or between two locations corresponding to the node during the aforementioned specific time period through the Pearson correlation coefficient.
18. In claim 13, The command for the above analysis is, A computing device comprising a command for analyzing changes in network traffic over a certain period of time in a specific area or user group in the above city.
19. In claim 18, The command for analyzing the above network traffic changes is, A computing device that calculates the correlation between communication usage in the aforementioned specific region or user group at regular time intervals using an autocorrelation function (ACF) to calculate a pattern of increase or decrease in network traffic.
20. As a computer program stored on a non-transitory computer-readable storage medium, The above computer program includes one or more instructions, and when the instructions are executed by a computing device having one or more processors, the computing device, A step of collecting Call Detail Record (CDR) data within a pre-set city and performing preprocessing on the collected data; and A computer program that performs the step of analyzing one or more of the spatial and temporal patterns of network traffic based on the above-mentioned preprocessed call detail record data.

Description

Analysis method of mobile-phone activity data using interactive cyber-physical social system and computing device for executing the same The present invention relates to a technology for analyzing mobile phone activity data using an interactive cyber-physical social system. With the recent increase in demand for mobile and wireless communication, a massive amount of additional spectrum resources is required to accommodate the growing number of mobile and wireless users. Mobile networks are considered a gold mine by the developer community because they contain significant information. Call Detail Records (CDRs) from these mobile networks are used to identify network efficacy and mobile user behavior. Generally, most telecommunications companies record user activity data, including SMS, calls, and internet usage, for monitoring purposes. This is commonly referred to as Call Detail Records Data. In addition to calls, it includes various types of data such as text messages and internet usage. The above CDR includes the phone number of the caller, the phone number of the caller, the call start time, the call duration, the phone number for payment of call charges, the identification of the equipment creating the record, the record unique identification number, the type (voice, SMS, etc.), the error status, the call end time, etc. The aforementioned Call Detail Record (CDR) stands out as highly important to data researchers due to its usability and high potential. When a mobile phone is used to call another person, a CDR is generated in response; if there are too many, telecommunications operators store the data in their system databases. Due to the importance of CDRs in customer analysis, it is necessary to investigate this critical aspect when planning smart cities. Typical telecommunications companies have millions of subscribers and generate vast amounts of data. Consequently, the methods for handling, storing, analyzing, and processing this massive telecommunications data remain key concerns. Furthermore, the telecommunications data must be error-free, free of duplicates, and contain minimal missing values. Therefore, to address these issues, a Cyber-Physics Social System is used to analyze and model large-scale internet usage data, and the said CPS system uses this CDR data to extract useful information and identify the sound predictability of spatiotemporal patterns within network traffic. Recently, it has become clear that cyber-physical systems (CPS) are being used for the analysis and modeling of communication data. The aforementioned CPS is an intelligent system and is largely composed of sensors, controllers, and actuators. The above CPS is used to provide valuable services in smart cities, such as by linking with smart devices to connect the cyber world and the physical world. Telecommunications companies typically manage millions of subscribers, making the generation of massive amounts of data a daily occurrence; in this regard, data storage, analysis, and processing are major areas of interest. To address these issues, the development of methods for analyzing mobile activity data using multi-stage interactive cyber-physical systems (CPS) for the analysis and modeling of large-scale internet data is essential. Figure 1 is an example diagram of a cyber-physical system. Figure 2 is a drawing showing the basic structure and elements of a CPS. Figure 3 is an interactive multi-level CPS system schematic. FIG. 4 is a flowchart of a method for analyzing mobile phone activity data using a cyber-physical social system according to an embodiment of the present invention. Figure 5 is a photograph showing a record of internet activity in the city. Figure 6 is a graph of mobile phone and internet activity in various areas of downtown Milan. Figure 7 is a graph showing the change in the number of internet connections in the Dumo area of Milan. Figure 8 is a graph showing CDR data of a time series curve. Figure 9 is a photograph of a map showing the maximum usage of internet activity records. FIG. 10 is a block diagram illustrating a computing environment including a computing device suitable for use in an exemplary embodiment of the present invention. Hereinafter, specific embodiments of the present invention will be described with reference to the drawings. The following detailed description is provided to facilitate a comprehensive understanding of the methods, apparatus, and/or systems described herein. However, this is merely illustrative and the present invention is not limited thereto. In describing the embodiments of the present invention, detailed descriptions of known technologies related to the present invention are omitted if it is determined that such detailed descriptions may unnecessarily obscure the essence of the present invention. Furthermore, the terms described below are defined in consideration of their functions within the present invention, and these may vary depending on the intentions or pr