A system for enrichment of location-based KPI data collected in mobile networks and filling missing data by using generative artificial intelligence

Abstract

The present invention relates to a system (1) for providing a comprehensive solution for analysing and improving network performance by using location¬ based point data in mobile networks.

Description

[0001] DESCRIPTION

[0002] A SYSTEM FOR ENRICHMENT OF LOCATION-BASED KPI DATA COLLECTED IN MOBILE NETWORKS AND FILLING MISSING DATA BY USING GENERATIVE ARTIFICIAL INTELLIGENCE

[0003] Technical Field

[0004] The present invention relates to a system for providing a comprehensive solution for analysing and improving network performance by using location-based point data in mobile networks.

[0005] Background of the Invention

[0006] Today, there are methods that offer a server system for coverage estimation and network optimisation on wireless networks. The server analyses signal performance metrics by identifying areas of interest, processes data samples, and produces coverage estimates. In addition, performance metrics such as antenna gain and signal-to-noise ratio are calculated. However, it does not include a gridbased structure and incomplete data generation but it directly analyses signal metrics. Artificial intelligence techniques such as neural networks are used for data enrichment and prediction, and the user interface is not detailed for viewing and managing coverage estimates.

[0007] Therefore, considering the studies and deficiencies included in the current technique, it is understood that there is a need for a system which collects, pre- processes and locates user signal data through a data collection and processing server, a KPI (Key Performance Indicator) data analysis server and a data enrichment and prediction server; converts this data into a grid-based structure and then calculates the combined KPI values for each grid; generates missing KPI data for grids in areas where no users are available by utilizing generative artificial intelligence techniques; thereby completes the data set and allows the network operators to more clearly evaluate each point of the network; and makes preparations so as to guarantee service quality by predicting and generating KPI data that vary according to time and location, in case there are no customers in the relevant location or if there is no sufficient data due to the lack of use of the application to be measured, through data generation and enrichment with generative artificial intelligence (Gen Al- Generative Artificial Intelligence).

[0008] The Chinese patent document no. CN104469833A, an application included in the state of the art, discloses a system for optimizing the network. In the said invention, a network node autonomously runs fault analysis on the detected fault, adjusts the relevant operation and maintenance data, achieves fault self-healing and optimises the network. Missing data in key alarm information includes data with no identification of alarm network element, data with no identification of alarm type, and data with no identification of alarm time. A mapping is established between fault alarm information, KPI indicators and network faults; a fault location model is constructed; and the network fault is found through a BP neural network.

[0009] Summary of the Invention

[0010] An object of the present invention is to realize a system which is developed with the aim of providing a comprehensive solution in order to analyse and improve network performance by using location-based point data in mobile networks.

[0011] Another object of the present invention is to realise a system which is developed with the aim of collecting, pre-processing, and positioning user signal data through the KPI data analysis server and the data enrichment and prediction server; converting this data into a grid-based structure and then calculating the combined KPI values for each grid; generating missing KPI data for grids in regions where no users are available, by using generative artificial intelligence techniques; and thereby completing the data set and achieving a more clear evaluation of each point of the network by network operators.

[0012] Another object of the present invention is to realise a system which is developed with the aim of establishing secure communication between data security, confidentiality, and communication server that provides data security, confidentiality, user authorization and data transfer, and all internal units.

[0013] Another object of the present invention is to realise a system which is developed with the aim of observing network analyses and model successes with a user interface where users interact, illustrate and manage data; storing all functions regularly on the data storage server and allowing holistic data management throughout the entire process.

[0014] Another object of the present invention is to realise a system which is developed with the aim of empowering network operators to maximize network performance and improve the user experience by making data-driven decisions.

[0015] Another object of the present invention is to realise a system which is developed with the aim of determining which service / application can be provided regionally and how the customer experiences will result by utilising mobile network communication data faster with intelligent algorithms.

[0016] Another object of the present invention is to realise a system which is developed with the aim of preparing to guarantee service quality by predicting and generating KPI data that varies according to time and location, in case there are no customers in the relevant location or if there is no sufficient data due to the lack of use of the application to be measured, through data generation and enrichment with generative artificial intelligence (GenAI). Another object of the present invention is to realise a system which is developed with the aim of providing a comprehensive data processing and analytics platform to extract meaningful and strategic information from location-based user data, starting with the collecting of user signal data and integrating data pre-processing, positioning, KPI analysis, and data enrichment with generative Al; evaluating every point of the network comprehensively with this integration; and solving the problem of missing data in areas with low user density with artificial intelligence.

[0017] Another object of the present invention is to realise a system which is developed with the aim of full compliance with privacy standards and legal regulations by enabling secure data transfer and access; allowing operators to easily manage, analyse, and report on their data sets through user-friendly interfaces; providing mobile network operators with a complete network view while boosting operational efficiency; improving customer satisfaction; providing the necessary tools to make data-driven decisions in network planning and optimisation strategies; thereby enabling operators to achieve a competitive advantage; and strengthening their market position.

[0018] Detailed Description of the Invention

[0019] “A System for Enrichment of Location-Based KPI Data Collected in Mobile Networks and Filling Missing Data by Using Generative Artificial Intelligence” realized to fulfil the objectives of the present invention is shown in the figure attached, in which:

[0020] Figure 1: is a schematic view of the inventive system.

[0021] The components illustrated in the figure are individually numbered, where the numbers refer to the following:

[0022] 1. System 2. Electronic Device

[0023] 3. Integration and User Interface Server

[0024] 4. Data Security, Privacy, and Communication Server

[0025] 5. Data Storage Server

[0026] 5.1 Signal Data Storage

[0027] 5.2 KPI Analysis Repository

[0028] 5.3 Enriched Data Storage

[0029] 6. Data Collection and Processing Server

[0030] 6.1 Data Collection Device

[0031] 6.2 Data Pre-processing Module

[0032] 6.3 Signal Data Localisation Module

[0033] 7. KPI Data Analysis Server

[0034] 8. Data Enrichment and Prediction Server

[0035] 8.1 Data Collection Processing Module for Artificial Intelligence

[0036] 8.2 Productive Artificial Intelligence Training Module

[0037] 8.3 Artificial Intelligence Evaluation Module

[0038] 8.4 Management of Trained Generative Artificial Intelligence Module

[0039] A. User Interface

[0040] The inventive system (1) which is developed with the aim of providing a comprehensive solution for analysing and improving network performance by using location-based point data in mobile networks comprises

[0041] - at least one electronic device (2) which is configured to exchange data and run at least one application thereon by using any remote communication protocol; at least one integration and user interface server (3) which is configured to establish a connection with the electronic device (2); to be a central platform where users can interact, illustrate, and manage data, monitor KPI analysis results and audit models; to perform a series of functions through user interfaces (A) such as data operations, data transfer, and model management; to evaluate the model success and report the relevant results; to include the integration of data security and protocols;

[0042] - at least one data security, privacy and communication server (4) which is configured to fulfil the basic security tasks of the mobile network data processing infrastructure; to maintain data security and user confidentiality and to communicate with all internal units in a secure and encrypted manner; to secure all data transfers used in communication and provide encryption and protocols that enable different servers and modules in the network to exchange information securely with each other; to be able to mask or anonymise data when necessary, in particular in accordance with data privacy principles and regulations in the storage and processing of personal data; to perform operations in compliance with legal compliance by protecting the privacy rights of users; to host authorisation and authentication mechanisms for the users and processes that will access them; to regulate permissions to access data and control access rights on a user-by-user basis; to ensure the accessibility of data only by authorised persons; to prevent sensitive data from falling into the wrong hands by verifying users and processes; to transfer data securely from one server to another or from one module to another; to build a line of defence against cyber threats while maintaining the integrity and availability of data;

[0043] - at least one data storage server (5) which is configured to permanently store the data acquired and processed from mobile networks; to host a plurality of data storages (Signal data storage (5.1), KPI Analysis repository (5.2), Enriched data storage (5.3)) dedicated and customized for various data sets obtained as a result of data processing and analysis running thereon; to store raw signal data collected and cleaned from mobile user equipment and stations, and data including users’ signal KPI values and location information through the signal data storage (5.1) running thereon; to store the grid-based and spatial KPI data and KPI values calculated and aggregated for each grid, processed through the KPI analysis repository (5.2) running thereon; to store enriched or predicted data by using generative artificial intelligence models through the enriched data storage (5.3) running thereon; to include model-generated KPI values for grids where no users are available or insufficient data is collected; thereby provide a more comprehensive and detailed analysis for the entire network, to manage the continuously updated data flow, to be the outputs of the data collection and processing process, to maintain data integrity and accessibility through the signal data storage (5.1), the KPI analysis repository (5.2) and the enriched data storage (5.3); at least one data collection and processing server (6) which is configured to analyse mobile network performance; to run three key modules (Data Collection Device (6.1), Data Pre-processing Module (6.2), and Signal Data Positioning Module (6.3)) thereon that are critical for analysing and improving mobile network performance; to collect signal data from user equipment with various parameters such as signal strength, signal quality, signal angle of arrival, and time information through the data collection device (6.1) running thereon; to process the signal data received as raw in the first stage, to clean, organise, and pre-process the collected data through the data pre-processing module (6.2) running thereon; to locate the signals by using the data processed and make this data ready for further analysis, to calculate the source positions of the signals from the processed data, and to make the positioning data available for further processing by correlating it with the signal as well as the incoming KPI metrics through the Signal Data Localisation module (6.3) running thereon; at least one KPI data analysis server (7) which is configured to strategically analyse mobile network data; to receive pre-positioned user data via the data security, privacy, and communication server (4) -a secure channel; to transform this data into a grid-based structure; to calculate the aggregated KPI values for each grid by assigning point data to grids and grouping this data; to store them in the KPI analysis repository (5.2) for later analysis and reporting; to communicate securely with the signal data storage (5.1) through the data security, confidentiality, and communication server (4); to receive positioned user data collected from mobile users’ devices via this communication channel, including various pre-processed KPI metrics such as signal strength, quality, angle of arrival, and timing; to process received point data on grids with predefined boundaries; to evaluate each point data in the closest grid according to their geographical location and distance to the grid centres; and to form the grid-based matrix structure; and to group data based on grids with this process; at least one data enrichment and prediction server (8) which is configured to use generative Al techniques to complement missing KPI data; to run four sub-modules (Data Collection Processing Module for Artificial Intelligence (8.1), Generative Artificial Intelligence Training Module

[0044] (8.2), Artificial Intelligence Evaluation Module (8.3), and Managing Trained Generative Artificial Intelligence Module (8.4)) that enable the training, evaluation, and management of artificial intelligence models; to access the KPI analysis repository (5.2) through the data security, privacy and communication server (4) -a secure communication channel, to convert the point-based KPI dataset received for a specific region into a grid-based matrix structure, and to provide the structured data format required for artificial intelligence learning with this matrix structure through the data collection processing module (8.1) for artificial intelligence running thereon; to receive the processed data and prepare the necessary data sets for artificial intelligence training, to mask a random part of the KPI data in the matrix structure within the data set during the training process to enable the model to learn to predict that missing data, to train the model correctly by separating the data sets required for training and testing through the generative artificial intelligence training module

[0045] (8.2) running thereon; to evaluate the trained generative artificial intelligence model with the test data set, to measure the prediction success of the model by filling the masked data points in the test data set, and to report the success of the model by comparing the results obtained through the artificial intelligence evaluation module (8.3) running thereon.

[0046] The electronic device (2) included in the inventive system (1) is configured to exchange data and run at least one application thereon by using any remote communication protocol. The electronic device (2) is a device such as tablet, desktop computer, phone, sensor, and / or portable computer. The electronic device

[0047] (2) is configured to run the user interface (A) thereon. The electronic device (2) is configured to establish a connection with the integration and user interface server

[0048] (3) by using any remote communication protocol included in the state of the art.

[0049] The integration and user interface server (3) included in the inventive system (1) is configured to establish a connection with the electronic device (2). The integration and user interface server (3) is configured to be a central platform where users can interact, illustrate, and manage data; to monitor KPI analysis results and audit models. The integration and user interface server (3) is configured to perform a series of functions through user interfaces (A) such as data operations, data transfer, and model management. The integration and user interface server (3) is configured to evaluate the model success and report the relevant results. The integration and user interface server (3) is configured to include the integration of data security and protocols.

[0050] The data security, privacy and communication server (4) included in the inventive system (1) is configured to fulfil the basic security tasks of the mobile network data processing infrastructure. The data security, privacy and communication server (4) is configured to maintain data security and user confidentiality and to communicate with all internal units in a secure and encrypted manner. The data security, privacy and communication server (4) is configured to secure all data transfers used in communication and provide encryption and protocols that enable different servers and modules in the network to exchange information securely with each other. The data security, privacy and communication server (4) is configured to be able to mask or anonymise data, when necessary, in particular in accordance with data privacy principles and regulations in the storage and processing of personal data; to perform operations in compliance with legal compliance by protecting the privacy rights of users. The data security, privacy and communication server (4) is configured to host authorisation and authentication mechanisms for the users and processes that will access them; to regulate permissions to access data and control access rights on a user-by-user basis. The data security, privacy and communication server (4) is configured to ensure the accessibility of data only by authorised persons; and to prevent sensitive data from falling into the wrong hands by verifying users and processes. The data security, privacy and communication server (4) is configured to transfer data securely from one server to another or from one module to another; to build a line of defence against cyber threats while maintaining the integrity and availability of data.

[0051] The data storage server (5) included in the inventive system (1) is configured to permanently store the data acquired and processed from mobile networks. The data storage server (5) is configured to host a plurality of data storages (Signal data storage (5.1), KPI Analysis repository (5.2), Enriched data storage (5.3)) dedicated and customized for various data sets obtained as a result of data processing and analysis running thereon. The signal data storage (5.1) running on the data storage server (5) is configured to store raw signal data collected and cleaned from mobile user equipment and stations, and data including users’ signal KPI values and location information. The KPI analysis repository (5.2) running on the data storage server (5) is configured to store grid-based and spatial KPI data processed by the KPI data analysis server (7), and the calculated and aggregated KPI values for each grid. The enriched data store (5.3) running on the data storage server (5) is configured to store the data enriched or predicted by using generative Al models, and to include model-generated KPI values for grids where no users are available or insufficient data is collected; and thereby provide a more comprehensive and detailed analysis for the entire network. The data storage server (5) is configured to manage the continuously updated data flow, to be the output of the data collection and processing process, to maintain data integrity and accessibility through the signal data storage (5.1), the KPI analysis repository (5.2) and the enriched data storage (5.3).

[0052] The data collection and processing server (6) included in the inventive system (1) is configured to analyse the mobile network performance. The data collection and processing server (6) is configured to run three key modules (Data Collection Device (6.1), Data Pre-processing Module (6.2), and Signal Data Positioning Module (6.3)) thereon that are critical for analysing and improving mobile network performance. The data collection device (6.1) running on the data collection and processing server (6) is configured to collect signal data from user equipment with various parameters such as signal strength, signal quality, signal angle of arrival, and time information. The data pre-processing module (6.2) running on the data collection and processing server (6) is configured to process the signal data received as raw in the first stage, to clean, organize, and pre- process the collected data. The signal data positioning module (6.3) running on the data collection and processing server (6) is configured to locate the signals by using the processed data and make this data ready for further analysis, to calculate the source positions of the signals from the processed data, to make the obtained positioning data available for further processing by correlating it with the signal as well as the incoming KPI metrics.

[0053] The KPI data analysis server (7) included in the inventive system (1) is configured to strategically analyse mobile network data. The KPI data analysis server (7) is configured to receive pre -positioned user data via the data security, privacy, and communication server (4) -a secure channel; to transform this data into a gridbased structure; to calculate the aggregated KPI values for each grid by assigning point data to grids and grouping this data; to store them in the KPI analysis repository (5.2) for later analysis and reporting. The KPI data analysis server (7) is configured to communicate securely with the signal data storage (5.1) through the data security, confidentiality, and communication server (4); to receive positioned user data collected from mobile users’ devices via this communication channel, including various pre-processed KPI metrics such as signal strength, quality, angle of arrival, and timing. The KPI data analysis server (7) is configured to process received point data on grids with predefined boundaries; to evaluate each point data in the closest grid according to their geographical location and distance to the grid centres; and to form the grid-based matrix structure; and to group data based on grids with this process. The KPI data analysis server (7) is configured to combine the KPI values of the data points placed in each grid using specific algorithms; to make statistical calculations such as mean, median, minimum, and maximum of the KPI data measured from all data points in a grid; and to achieve a unified, representative set of KPI values for each grid as a result of these operations. The KPI data analysis server (7) is configured to save the processed and aggregated KPI values in the KPI analysis repository (5.2). The KPI data analysis server (7) is configured to provide an overall measurement of KPI values for specific regions of the network, not for each individual user.

[0054] The data enrichment and prediction server (8) included in the inventive system (1) is configured to utilize generative artificial intelligence techniques to complement missing KPI data. The data enrichment and prediction server (8) is configured to run four sub-modules (Data Collection Processing Module for Artificial Intelligence (8.1), Generative Artificial Intelligence Training Module (8.2), Artificial Intelligence Evaluation Module (8.3), and Managing Trained Generative Artificial Intelligence Module (8.4)) that enable the training, evaluation, and management of artificial intelligence models. The data collection processing module for artificial intelligence (8.1) running on the data enrichment and prediction server (8) is configured to access the KPI analysis repository (5.2) through the data security, privacy and communication server (4) -a secure communication channel; to convert the point-based KPI dataset received for a specific region into a grid-based matrix structure; and to provide the structured data format required for artificial intelligence learning with this matrix structure. The generative artificial intelligence training module (8.2) running on the data enrichment and prediction server (8) is configured to receive the processed data and prepare the necessary data sets for artificial intelligence training; to mask a random part of the KPI data in the matrix structure within the data set during the training process to enable the model to learn to predict that missing data; to train the model correctly by separating the data sets required for training and testing. The artificial intelligence evaluation module (8.3) running on the data enrichment and prediction server (8) is configured to evaluate the trained generative artificial intelligence model with the test data set; to measure the prediction success of the model by filling the masked data points in the test data set; and to report the success of the model by comparing the results obtained. The management module of the trained generative artificial intelligence (8.4) running on the data enrichment and prediction server (8) is configured to select the models that succeeded in the evaluation phase; to fill the gaps in the real data sets by using these models; and to transfer the enriched data to the enriched data storage (5.3) over the secure communication channel.

[0055] Industrial Application of the Invention

[0056] The inventive system (1) collects, pre-processes and locates user signal data through servers; converts this data into a grid -based structure and then calculates the combined KPI values for each grid; generates missing KPI data for grids in areas where no users are available by utilizing generative artificial intelligence techniques; thereby completes the data set and allows the network operators to more clearly evaluate each point of the network; and makes preparations so as to guarantee service quality by predicting and generating KPI data that varies according to time and location, in case there are no customers in the relevant location or if there is no sufficient data due to the lack of use of the application to be measured, through data generation and enrichment with generative artificial intelligence (Gen Al- Generative Artificial Intelligence). Within these basic concepts; it is possible to develop various embodiments of the inventive “A System (1) for Enrichment of Location-Based KPI Data Collected in Mobile Networks and Filling Missing Data by Using Generative Artificial Intelligence”; the invention cannot be limited to examples disclosed herein and it is essentially according to claims.

Claims

CLAIMS1. A system (1) which is developed with the aim of providing a comprehensive solution for analysing and improving network performance by using location-based point data in mobile networks; comprising at least one electronic device (2) which is configured to exchange data and run at least one application thereon by using any remote communication protocol; at least one integration and user interface server (3) which is configured to establish a connection with the electronic device (2); to be a central platform where users can interact, illustrate, and manage data, monitor KPI analysis results and audit models; to perform a series of functions through user interfaces (A) such as data operations, data transfer, and model management; to evaluate the model success and report the relevant results; to include the integration of data security and protocols;- at least one data security, privacy and communication server (4) which is configured to fulfil the basic security tasks of the mobile network data processing infrastructure; to maintain data security and user confidentiality and to communicate with all internal units in a secure and encrypted manner; to secure all data transfers used in communication and provide encryption and protocols that enable different servers and modules in the network to exchange information securely with each other; to be able to mask or anonymise data when necessary, in particular in accordance with data privacy principles and regulations in the storage and processing of personal data; to perform operations in compliance with legal compliance by protecting the privacy rights of users; to host authorisation and authentication mechanisms for the users and processes that will access them; to regulate permissions to access data and control access rights on a user-by-user basis; to ensure theaccessibility of data only by authorised persons; to prevent sensitive data from falling into the wrong hands by verifying users and processes; to transfer data securely from one server to another or from one module to another; to build a line of defence against cyber threats while maintaining the integrity and availability of data;- at least one data storage server (5) which is configured to permanently store the data acquired and processed from mobile networks; to host a plurality of data storages (Signal data storage (5.1), KPI Analysis repository (5.2), Enriched data storage (5.3)) dedicated and customized for various data sets obtained as a result of data processing and analysis running thereon; to store raw signal data collected and cleaned from mobile user equipment and stations, and data including users’ signal KPI values and location information through the signal data storage (5.1) running thereon; to store the grid-based and spatial KPI data and KPI values calculated and aggregated for each grid, processed through the KPI analysis repository (5.2) running thereon; to store enriched or predicted data by using generative artificial intelligence models through the enriched data storage (5.3) running thereon; to include model-generated KPI values for grids where no users are available or insufficient data is collected; thereby provide a more comprehensive and detailed analysis for the entire network, to manage the continuously updated data flow, to be the outputs of the data collection and processing process, to maintain data integrity and accessibility through the signal data storage (5.1), the KPI analysis repository (5.2) and the enriched data storage (5.3);- at least one data collection and processing server (6) which is configured to analyse mobile network performance; to run three key modules (Data Collection Device (6.1), Data Pre-processing Module (6.2), and Signal Data Positioning Module (6.3)) thereonthat are critical for analysing and improving mobile network performance; to collect signal data from user equipment with various parameters such as signal strength, signal quality, signal angle of arrival, and time information through the data collection device (6.1) running thereon; to process the signal data received as raw in the first stage, to clean, organise, and pre-process the collected data through the data pre-processing module (6.2) running thereon; to locate the signals by using the data processed and make this data ready for further analysis, to calculate the source positions of the signals from the processed data, and to make the positioning data available for further processing by correlating it with the signal as well as the incoming KPI metrics through the Signal Data Localisation module (6.3) running thereon; and characterized by- at least one KPI data analysis server (7) which is configured to strategically analyse mobile network data; to receive prepositioned user data via the data security, privacy, and communication server (4) -a secure channel; to transform this data into a grid-based structure; to calculate the aggregated KPI values for each grid by assigning point data to grids and grouping this data; to store them in the KPI analysis repository (5.2) for later analysis and reporting; to communicate securely with the signal data storage (5.1) through the data security, confidentiality, and communication server (4); to receive positioned user data collected from mobile users’ devices via this communication channel, including various pre-processed KPI metrics such as signal strength, quality, angle of arrival, and timing; to process received point data on grids with predefined boundaries; to evaluate each point data in the closest grid according to their geographical location and distance to the grid centres; and to form the grid -basedmatrix structure; and to group data based on grids with this process; at least one data enrichment and prediction server (8) which is configured to use generative Al techniques to complement missing KPI data; to run four sub-modules (Data Collection Processing Module for Artificial Intelligence (8.1), Generative Artificial Intelligence Training Module (8.2), Artificial Intelligence Evaluation Module (8.3), and Managing Trained Generative Artificial Intelligence Module (8.4)) that enable the training, evaluation, and management of artificial intelligence models; to access the KPI analysis repository (5.2) through the data security, privacy and communication server (4) -a secure communication channel, to convert the point-based KPI dataset received for a specific region into a grid-based matrix structure, and to provide the structured data format required for artificial intelligence learning with this matrix structure through the data collection processing module (8.1) for artificial intelligence running thereon; to receive the processed data and prepare the necessary data sets for artificial intelligence training, to mask a random part of the KPI data in the matrix structure within the data set during the training process to enable the model to learn to predict that missing data, to train the model correctly by separating the data sets required for training and testing through the generative artificial intelligence training module (8.2) running thereon; to evaluate the trained generative artificial intelligence model with the test data set, to measure the prediction success of the model by filling the masked data points in the test data set, and to report the success of the model by comparing the results obtained through the artificial intelligence evaluation module (8.3) running thereon.

2. A system (1) according to Claim 1; characterized by the electronic device (2) which is configured to exchange data and run at least one application thereon by using any remote communication protocol; and which is a device such as tablet, desktop computer, phone, sensor, and / or portable computer.

3. A system (1) according to Claim 1 or 2; characterized by the electronic device (2) which is configured to run the user interface (A) thereon.

4. A system (1) according to Claim 3; characterized by the electronic device (2) which is configured to establish a connection with the integration and user interface server (3) by using any remote communication protocol.

5. A system (1) according to any one of the preceding claims; characterized by the integration and user interface server (3) which is configured to establish a connection with the electronic device (2).

6. A system (1) according to any one of the preceding claims; characterized by the integration and user interface server (3) which is configured to be a central platform where users can interact, illustrate, and manage data; to monitor KPI analysis results and audit models.

7. A system (1) according to any one of the preceding claims; characterized by the integration and user interface server (3) which is configured to perform a series of functions through user interfaces (A) such as data operations, data transfer, and model management.

8. A system (1) according to any one of the preceding claims; characterized by the integration and user interface server (3) which is configured to evaluate the model success and report the relevant results.

9. A system (1) according to any one of the preceding claims; characterized by the integration and user interface server (3) which is configured to include the integration of data security and protocols.

10. A system (1) according to any one of the preceding claims; characterized by the data security, privacy and communication server (4) which is configured to fulfil the basic security tasks of the mobile network data processing infrastructure.

11. A system (1) according to any one of the preceding claims; characterized by the data security, privacy and communication server (4) which is configured to maintain data security and user confidentiality and to communicate with all internal units in a secure and encrypted manner.

12. A system (1) according to any one of the preceding claims; characterized by the data security, privacy and communication server (4) which is configured to secure all data transfers used in communication and provide encryption and protocols that enable different servers and modules in the network to exchange information securely with each other.

13. A system (1) according to any one of the preceding claims; characterized by the data security, privacy and communication server (4) which is configured to be able to mask or anonymise data, when necessary, in particular in accordance with data privacy principles and regulations in the storage and processing of personal data; to perform operations in compliance with legal compliance by protecting the privacy rights of users.

14. A system (1) according to any one of the preceding claims; characterized by the data security, privacy and communication server (4) which is configured to host authorisation and authentication mechanisms for theusers and processes that will access them; to regulate permissions to access data and control access rights on a user-by-user basis.

15. A system (1) according to any one of the preceding claims; characterized by the data security, privacy and communication server (4) which is configured to ensure the accessibility of data only by authorised persons; and to prevent sensitive data from falling into the wrong hands by verifying users and processes.

16. A system (1) according to any one of the preceding claims; characterized by the data security, privacy and communication server (4) which is configured to transfer data securely from one server to another or from one module to another; to build a line of defence against cyber threats while maintaining the integrity and availability of data.

17. A system (1) according to any one of the preceding claims; characterized by the data storage server (5) which is configured to permanently store the data acquired and processed from mobile networks.

18. A system (1) according to any one of the preceding claims; characterized by the data storage server (5) which is configured to host a plurality of data storages (Signal data storage (5.1), KPI Analysis repository (5.2), Enriched data storage (5.3)) dedicated and customized for various data sets obtained as a result of data processing and analysis running thereon.

19. A system (1) according to any one of the preceding claims; characterized by the data storage server (5) which is configured to store raw signal data collected and cleaned from mobile user equipment and stations, and data including users’ signal KPI values and location information, by means of the signal data storage (5.1) running on itself.

20. A system (1) according to any one of the preceding claims; characterized by the data storage server (5) which is configured to store grid-based and spatial KPI data processed by the KPI data analysis server (7), and the calculated and aggregated KPI values for each grid, by means of the KPI analysis repository (5.2) running on itself.

21. A system (1) according to any one of the preceding claims; characterized by the data storage server (5) which is configured to store data enriched or predicted using generative Al models, and to include model-generated KPI values for grids where no users are available or insufficient data is collected; and thereby provide a more comprehensive and detailed analysis for the entire network, by means of the enriched data store (5.3) running on itself.

22. A system (1) according to any one of the preceding claims; characterized by the data storage server (5) which is configured to manage the continuously updated data flow, to be the output of the data collection and processing process, to maintain data integrity and accessibility through the signal data storage (5.1), the KPI analysis repository (5.2) and the enriched data storage (5.3).

23. A system (1) according to any one of the preceding claims; characterized by the data collection and processing server (6) which is configured to analyse the mobile network performance.

24. A system (1) according to any one of the preceding claims; characterized by the data collection and processing server (6) which is configured to run three key modules (Data Collection Device (6.1), Data Pre-processing Module (6.2), and Signal Data Positioning Module (6.3)) thereon that are critical for analysing and improving mobile network performance.

25. A system (1) according to any one of the preceding claims; characterized by the data collection and processing server (6) which is configured to collect signal data from user equipment with various parameters such as signal strength, signal quality, signal angle of arrival, and time information, by means of the data collection device (6.1) running on itself.

26. A system (1) according to any one of the preceding claims; characterized by the data collection and processing server (6) which is configured to process the signal data received as raw in the first stage, to clean, organize, and pre-process the collected data, by means of the data pre-processing module (6.2) running on itself.

27. A system (1) according to any one of the preceding claims; characterized by the data collection and processing server (6) which is configured to locate the signals using the processed data and make this data ready for further analysis, to calculate the source positions of the signals from the processed data, to make the obtained positioning data available for further processing by correlating it with the signal as well as the incoming KPI metrics, by means of the signal data positioning module (6.3) running on itself.

28. A system (1) according to any one of the preceding claims; characterized by the KPI data analysis server (7) which is configured to strategically analyse mobile network data.

29. A system (1) according to any one of the preceding claims; characterized by the KPI data analysis server (7) which is configured to receive prepositioned user data via the data security, privacy, and communication server (4) -a secure channel; to transform this data into a grid-based structure; to calculate the aggregated KPI values for each grid by assigningpoint data to grids and grouping this data; to store them in the KPI analysis repository (5.2) for later analysis and reporting.

30. A system (1) according to any one of the preceding claims; characterized by the KPI data analysis server (7) which is configured to communicate securely with the signal data storage (5.1) through the data security, confidentiality, and communication server (4); to receive positioned user data collected from mobile users’ devices via this communication channel, including various pre-processed KPI metrics such as signal strength, quality, angle of arrival, and timing.

31. A system (1) according to any one of the preceding claims; characterized by the KPI data analysis server (7) which is configured to process received point data on grids with predefined boundaries; to evaluate each point data in the closest grid according to their geographical location and distance to the grid centres; and to form the grid-based matrix structure; and to group data based on grids with this process.

32. A system (1) according to any one of the preceding claims; characterized by the KPI data analysis server (7) which is configured to combine the KPI values of the data points placed in each grid using specific algorithms; to make statistical calculations such as mean, median, minimum, and maximum of the KPI data measured from all data points in a grid; and to achieve a unified, representative set of KPI values for each grid as a result of these operations.

33. A system (1) according to any one of the preceding claims; characterized by the KPI data analysis server (7) which is configured to save the processed and aggregated KPI values in the KPI analysis repository (5.2).

34. A system (1) according to any one of the preceding claims; characterized by the KPI data analysis server (7) which is configured to provide an overall measurement of KPI values for specific regions of the network, not for each individual user.

35. A system (1) according to any one of the preceding claims; characterized by the data enrichment and prediction server (8) which is configured to utilize generative artificial intelligence techniques to complement missing KPI data.

36. A system (1) according to any one of the preceding claims; characterized by the data enrichment and prediction server (8) which is configured to run four sub-modules (Data Collection Processing Module for Artificial Intelligence (8.1), Generative Artificial Intelligence Training Module (8.2), Artificial Intelligence Evaluation Module (8.3), and Managing Trained Generative Artificial Intelligence Module (8.4)) that enable the training, evaluation, and management of artificial intelligence models.

37. A system (1) according to any one of the preceding claims; characterized by the data enrichment and prediction server (8) which is configured to access the KPI analysis repository (5.2) through the data security, privacy and communication server (4) -a secure communication channel; to convert the point-based KPI dataset received for a specific region into a grid-based matrix structure; and to provide the structured data format required for artificial intelligence learning with this matrix structure, by means of the data collection processing module for artificial intelligence (8.1) running on itself.

38. A system (1) according to any one of the preceding claims; characterized by the data enrichment and prediction server (8) which is configured to receive the processed data and prepare the necessary data sets for artificialintelligence training; to mask a random part of the KPI data in the matrix structure within the data set during the training process to enable the model to learn to predict that missing data; to train the model correctly by separating the data sets required for training and testing, by means of generative artificial intelligence training module (8.2) running on itself.

39. A system (1) according to any one of the preceding claims; characterized by the data enrichment and prediction server (8) which is configured to to evaluate the trained generative artificial intelligence model with the test data set; to measure the prediction success of the model by filling the masked data points in the test data set; and to report the success of the model by comparing the results obtained, by means of the artificial intelligence evaluation module (8.3) running on itself.

40. A system (1) according to any one of the preceding claims; characterized by the data enrichment and prediction server (8) which is configured to select the models that succeeded in the evaluation phase; to fill the gaps in the real data sets using these models; and to transfer the enriched data to the enriched data storage (5.3) over the secure communication channel, by means of the management module of the trained generative artificial intelligence (8.4) running on itself.

Images