CROSS-REFERENCE TO RELATED APPLICATIONS AND PRIORITY
[001] The present application does not claim priority from any patent application.
TECHNICAL FIELD
[002] The present disclosure in general relates to the field of a telecommunication network. More particularly, the present invention relates to a system and method for predicting network service quality and generating suggestions to improve the same.
BACKGROUND
[003] In a telecommunication network, the service quality of the network to which a set of devices are connected has to be of a high level and consistent. Typically, the service quality is determined based on analysis of data, available to Telecom Service Providers (TSP). It is to be noted that the TSP have huge amount of the data. Some technics are available to determine the service quality based on analysis of the data. At times, the service quality of the network degrades due to faults, failures or traffic congestion. In this case, the TSP may have to spend lot of time to identify reasons of degradation of the service quality. Also, the available technics does not predict degradation of the service quality, in future. Hence, the TSP cannot take any action to mitigate degradation of the service quality and to provide best service quality for the set of devices.
SUMMARY
[004] Before the present systems and methods for predicting network service quality and generating suggestions to improve the same, is described, it is to be understood that this application is not limited to the particular systems, and methodologies described, as there can be multiple possible embodiments which are not expressly illustrated in the present disclosure. It is also to be understood that the terminology used in the description is for the purpose of describing the particular versions or embodiments only, and is not intended to limit the scope of the present application. This summary is provided to introduce concepts related to systems and method for predicting the network service quality and generating the suggestions to improve the network service quality. This summary is not intended to identify essential features of the claimed subject matter nor is it intended for use in determining or limiting the scope of the claimed subject matter.
3
[005] In one implementation, a system for predicting network service quality and generating suggestions, for network service providers, to improve the network service quality is illustrated. The system comprises a memory and a processor coupled to the memory, further the processor is configured to execute programmed instructions stored in the memory. In one embodiment, the processor may execute programmed instructions stored in the memory for receiving real-time data from a set of devices present in a network. The processor may further execute programmed instructions stored in the memory for identifying functional characteristics and behavioral characteristics of each device, from the set of devices, based on analysis of the real-time data. The processor may execute programmed instructions stored in the memory for identifying a subset of key performance parameters, from a set of key performance parameters, associated with the set of devices. The subset of key performance parameters may be identified based on analysis of the functional characteristics and the behavioral characteristics. Further, the processor may execute programmed instructions stored in the memory for determining a current service quality matrix associated with the set of devices. The current service quality matrix may be determined based on correlation between the subset of key performance parameters. The processor may execute programmed instructions stored in the memory for deriving a predicted service quality matrix based on analysis of the real-time data and historical data, received from the set of devices, stored in a historical repository. The processor may further execute programmed instructions stored in the memory for identifying one or more issues, associated with a network service quality of the set of devices, based on comparison of the current service quality and the predicted service quality. Further, the processor may execute programmed instructions stored in the memory for analysing the one or more issues based on historical defect data to generate one or more suggestions to improve the network service quality.
[006] In another implementation, a method for predicting network service quality and generating suggestions, for network service providers, to improve the network service quality is illustrated. In one embodiment, the method may comprise receiving real-time data from a set of devices present in a network. The method may further comprise identifying functional characteristics and behavioral characteristics of each device, from the set of devices, based on analysis of the real-time data. The method may comprise identifying a subset of key performance parameters, from a set of key performance parameters, associated with the set of devices. The subset of key performance parameters
4
may be identified based on analysis of the functional characteristics and the behavioral characteristics. Further, the method may comprise determining a current service quality matrix associated with the set of devices. The current service quality matrix may be determined based on correlation between the subset of key performance parameters. The method may comprise deriving a predicted service quality matrix based on analysis of the real-time data and historical data, received from the set of devices, stored in a historical repository. The method may comprise identifying one or more issues, associated with a network service quality of the set of devices, based on comparison of the current service quality and the predicted service quality. Further, the method may comprise analysing the one or more issues based on historical defect data to generate one or more suggestions to improve the network service quality.
[007] In yet another implementation, a computer program product having embodied computer program for predicting network service quality and generating suggestions, for network service providers, to improve the network service quality is disclosed. In one embodiment, the program may comprise a program code for receiving real-time data from a set of devices present in a network. The program may further comprise a program code for identifying functional characteristics and behavioral characteristics of each device, from the set of devices, based on analysis of the real-time data. The program may comprise a program code for identifying a subset of key performance parameters, from a set of key performance parameters, associated with the set of devices. The subset of key performance parameters may be identified based on analysis of the functional characteristics and the behavioral characteristics. Further, the program may comprise a program code for determining a current service quality matrix associated with the set of devices. The current service quality matrix may be determined based on correlation between the subset of key performance parameters. The program may comprise a program code for deriving a predicted service quality matrix based on analysis of the real-time data and historical data, received from the set of devices, stored in a historical repository. The program may further comprise a program code for identifying one or more issues, associated with a network service quality of the set of devices, based on comparison of the current service quality and the predicted service quality. Further, the program may comprise a program code for analysing the one or more issues based on historical defect data to generate one or more suggestions to improve the network service quality.
5
BRIEF DESCRIPTION OF DRAWINGS
[008] The detailed description is described with reference to the accompanying figures. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The same numbers are used throughout the drawings to refer like features and components.
[009] Figure 1 illustrates a network implementation of system for predicting network service quality and generating suggestions to improve the network service quality, in accordance with an embodiment of the present subject matter.
[0010] Figure 2 illustrates the system for predicting network service quality and generating suggestions to improve the network service quality, in accordance with an embodiment of the present subject matter.
[0011] Figure 3 illustrates a method for predicting network service quality and generating suggestions to improve the network service quality, in accordance with an embodiment of the present subject matter.
[0012] Figure 4 illustrates an analytic and prediction system for predicting network service quality and generating suggestions to improve the network service quality, in accordance with an embodiment of the present subject matter.
[0013] Figure 5 illustrates an exemplary embodiment of the system for predicting network service quality and generating suggestions to improve the network service quality, implemented in a telecom network, in accordance with an embodiment of the present subject matter.
DETAILED DESCRIPTION
[0014] Some embodiments of the present disclosure, illustrating all its features, will now be discussed in detail. The words “receiving”, “identifying”, “determining”, “deriving”, “analysing”, “generating” and other forms thereof, are intended to be equivalent in meaning and be open ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items, or meant to be limited to only the listed item or items. It must also be noted that as used herein and in the appended claims, the singular forms "a", "an" and "the" include plural references unless the context clearly
6
dictates otherwise. Although any systems and methods similar or equivalent to those described herein can be used in the practice or testing of embodiments of the present disclosure, the exemplary, systems and methods for predicting network service quality and generating suggestions to improve the network service quality are now described. The disclosed embodiments of the system and method for generating the predicting network service quality and suggestions to improve the network service quality are merely exemplary of the disclosure, which may be embodied in various forms.
[0015] Various modifications to the embodiment will be readily apparent to those skilled in the art and the generic principles herein may be applied to other embodiments. However, one of ordinary skill in the art will readily recognize that the present disclosure for predicting network service quality and generating suggestions to improve the network service quality is not intended to be limited to the embodiments illustrated, but is to be accorded the widest scope consistent with the principles and features described herein.
[0016] The present subject matter relates to predicting network service quality and generating suggestions to improve the network service quality. In one embodiment, real-time data may be received from a set of devices present in a network. The real-time data comprises configuration data, topology data, interface data, operational data and traffic data, associated with each device from the set of devices. Once the real-time data is received, functional characteristics and behavioral characteristics of each device, from the set of devices, may be identified based on analysis of the real-time data. Further, the functional characteristics and the behavioral characteristics may be analysed using a machine learning algorithm to identify a subset of key performance parameters, from a set of key performance parameters, associated with the set of devices. Based on correlation between the subset of key performance parameters, a current service quality matrix, associated with the set of devices, may be determined. Further, a predicted service quality matrix is derived based on analysis of the real-time data and historical data stored in a historical repository. The historical data may comprise a time series based traffic data, associated with the set of devices, and historical events such as notification, defects, incidents. The current service quality matrix and the predicted service quality matrix may be compared to identify one or more issues, associated with network service quality of the set of devices. One or more of these issues may be further analysed based on historical
7
defect data to generate one or more suggestions. These suggestions may be further used to improve the network service quality.
[0017] Referring now to Figure 1, a network implementation 100 of a system 102 for predicting network service quality and generating suggestions to improve the network service quality is disclosed. Although the present subject matter is explained considering that the system 102 is implemented on a server, it may be understood that the system 102 may also be implemented in a variety of computing systems, such as a laptop computer, a desktop computer, a notebook, a workstation, a mainframe computer, a server, a network server, and the like. In one implementation, the system 102 may be implemented over a cloud network. Further, it will be understood that the system 102 may be accessed by multiple users through one or more user devices 104-1, 104-2…104-N, collectively referred to as user device 104 hereinafter, or applications residing on the user device 104. Examples of the user device 104 may include, but are not limited to, a portable computer, a personal digital assistant, a handheld device, and a workstation. The user device 104 may be communicatively coupled to the system 102 through a network 106.
[0018] In one implementation, the network 106 may be a wireless network, a wired network or a combination thereof. The network 106 may be implemented as one of the different types of networks, such as intranet, local area network (LAN), wide area network (WAN), the internet, and the like. The network 106 may either be a dedicated network or a shared network. The shared network represents an association of the different types of networks that use a variety of protocols, for example, Hypertext Transfer Protocol (HTTP), Transmission Control Protocol/Internet Protocol (TCP/IP), Wireless Application Protocol (WAP), and the like, to communicate with one another. Further, the network 106 may include a variety of network devices, including routers, bridges, servers, computing devices, storage devices, and the like.
[0019] In one embodiment, the system 102 may receive real-time data from a set of devices present in a network. The real-time data may comprise configuration data, topology data, interface data, operational data, and traffic data. The configuration data may correspond to a device type, a device equipage status, a device capacity, a device power range and the like. The topology data may correspond to interconnection information between devices, redundancy and the like. The interface data may correspond to a device link type, a device link speed and the like. The operational data may correspond to a device
8
failure, device faults and the like. The traffic data may correspond to traffic pattern, throughput, load pattern and the like.
[0020] The system 102 may analyse the configuration data, the topology data and the interface data to identify functional characteristics associated with each device, from the set of devices. Further, the system 102 may analyse the operational data and the traffic data, associated with the set of devices, to identify the behavioral characteristics. The system 102 may further analyse the functional characteristics and the behavioral characteristics to identify a subset of key performance parameters, from a set of key performance parameters. In one example, the set of devices may be categorised based on the subset of key performance parameters. In one embodiment, the functional characteristics and the behavioral characteristics may be analysed using a machine learning algorithm.
[0021] Further, the system 102 may identify correlation between the subset of key performance parameters. Based on the correlation, the system 102 may determine a current service quality matrix associated with the set of devices. In one embodiment, the current service quality matrix may be a real-time service quality matrix.
[0022] The system 102 may further analyse the real-time data and historical data, received from the set of devices, stored in a historical repository using a prediction algorithm. The historical data may comprise a time series based traffic data associated with the set of devices. Based on the analysis of the real-time data and the historical data, the system 102 may identify a subset of predicted key performance parameters, from the set of key performance parameters. The system 102 may analyse correlation between the subset of predicted key performance parameters. Based on the analysis of the correlation, the system 102 may derive a predicted service quality matrix. In one embodiment, the predicted service quality matrix may be future service quality.
[0023] Further, the system 102 may compare the current service quality matrix and the predicted service quality matrix. Based on the comparison, the system 102 may identify one or more issues associated with network service quality of the set of devices. In one example, the one or more issues may be referred as reasons associated with degradation of the predicted service quality matrix as compared to the current service quality matrix. The system 102 may further analyse one or more issues based on historical defect data. Based on the analysis, the system 102 may generate one or more suggestions for the network
9
service providers. One or more suggestions may be used to improve the network service quality. These suggestions may correspond to solution used to mitigate the degradation in the network service quality.
[0024] Referring now to figure 2, the system 102 for predicting network service quality and generating suggestions to improve the network service quality is illustrated in accordance with an embodiment of the present subject matter. In one embodiment, the system 102 may include at least one processor 202, an input/output (I/O) interface 204, and a memory 206. The at least one processor 202 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities, at least one processor 202 may be configured to fetch and execute computer-readable instructions stored in the memory 206.
[0025] The I/O interface 204 may include a variety of software and hardware interfaces, for example, a web interface, a graphical user interface, and the like. The I/O interface 204 may allow the system 102 to interact with the user directly or through the user device 104. Further, the I/O interface 204 may enable the system 102 to communicate with other computing devices, such as web servers and external data servers (not shown). The I/O interface 204 may facilitate multiple communications within a wide variety of networks and protocol types, including wired networks, for example, LAN, cable, etc., and wireless networks, such as WLAN, cellular, or satellite. The I/O interface 204 may include one or more ports for connecting a number of devices to one another or to another server.
[0026] The memory 206 may include any computer-readable medium known in the art including, for example, volatile memory, such as static random access memory (SRAM) and dynamic random access memory (DRAM), and/or non-volatile memory, such as read only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and magnetic tapes. The memory 206 may include modules 208 and data 210.
[0027] The modules 208 may include routines, programs, objects, components, data structures, and the like, which perform particular tasks, functions or implement particular abstract data types. In one implementation, the module 208 may include data receiving module 212, an identification module 214, a determination module 216, a prediction
10
module 218, a generation module 220, and other modules 222. The other modules 222 may include programs or coded instructions that supplement applications and functions of the system 102.
[0028] The data 210, amongst other things, serve as a repository for storing data processed, received, and generated by one or more of the modules 208. The data 210 may also include a repository 224, and other data 226. In one embodiment, the other data 226 may include data generated as a result of the execution of one or more modules in the other modules 222.
[0029] In one implementation, a user may access the system 102 via the I/O interface 204. The user may be registered using the I/O interface 204 in order to use the system 102. In one aspect, the user may access the I/O interface 204 of the system 102 for obtaining information, providing input information or configuring the system 102.
[0030] In one embodiment, the data receiving module 212 may receive real-time data from a set of devices present in a network. In one example, the set of devices may be connected to a base station in the network. The network may be a telecommunication network. The real-time data may comprise configuration data, topology data, interface data, operational data and traffic data, associated with each device from the set of devices.
[0031] In one embodiment, the configuration data may correspond to a device type, a device equipage status, a device capacity, a device power range and the like. The topology data may correspond to interconnection information between devices, redundancy and the like. The interface data may correspond to a device link type, a device link speed and the like. The operational data may correspond to a device failure, device faults and the like. The traffic data may correspond to traffic pattern, throughput, load pattern and the like.
[0032] Once the real-time data is received, the identification module 214 may identify functional characteristics and behavioral characteristics associated with each device from the set of devices, based on analysis of the real-time data. In one embodiment, the identification module 214 may analyse the configuration data, the topology data, and the interface data to identify the functional characteristics of each device. One or more functional modelling algorithm may be applied on the configuration data, the topology data and the interface data to identify the functional characteristics. In one embodiment, the
11
functional characteristics may be device capacity, device link type, device link speed, interconnection between devices and the like.
[0033] Further, the identification module 214 may analyse the operational data and the traffic data to identify the behavioral characteristics of each device. In one example, the behavioral characteristics may be referred to behavioral pattern of each device. The behavioral pattern may comprise traffic pattern, throughput, load pattern, congestion and the like. The behavioral pattern, of each device, may be followed on time of day and day of week.
[0034] Further, the identification module 214 may analyse the functional characteristics and the behavioral characteristics to identify a subset of key performance parameters, from a set of key performance parameters. The functional characteristics and the behavioral characteristics may be analysed using a machine learning algorithm. The subset of key performance parameters may be associated with the set of devices. The subset of key performance parameters may comprise a call setup success rate, a call establishment success, a call completion and the like. In one example, the set of devices may be categorised based on the subset of key performance parameters.
[0035] Once the subset of key performance parameters is identified, the determination module 216 may determine a current service quality matrix associated with the set of devices. The current service quality matrix may be a real-time service quality. The current service quality matrix may be determined based on correlation between the subset of key performance parameters. One or more correlation algorithms may be applied on the subset of key performance parameters to identify the correlation between the subset of key performance parameters. In one embodiment, the current service quality matrix may be determined based on applying transformation algorithm on the subset of key performance parameters. In one embodiment, applying the transformation algorithm may involve providing weightage to each key performance parameter based on an impact of the key performance parameter. Further, the weightage of each key performance parameter may be aggregated to derive the current service quality matrix. In one aspect, a regression algorithm may be used to derive the current service quality matrix.
[0036] In one embodiment, the service quality may be tied to the subset of key performance parameters. In one example, a voice service quality may be tied to a voice
12
service key performance parameter such as a call setup success rate, a call establishment success, a call completion and the like. In order words, the subset of key performance parameters may be used to determine the current service quality matrix using correlation algorithm and transformation algorithm.
[0037] Further, the prediction module 218 may analyse the real-time data and historical data, stored in a historical database. The historical data may be received from the set of devices. The historical data may comprise a time-series based traffic data. The real-time data and the historical data may be analysed using one or more prediction algorithms. Based on the analysis of the real-time data and the historical data, the prediction module 218 may identify a subset of predicted key performance parameters, from the set of key performance parameters. The prediction module 218 may further identify correlation between the subset of predicted key performance parameters using the correlation algorithm. Based on the correlation between the subset of predicted key performance parameters, the prediction module 218 may derive a predicted service quality matrix of the set of devices. In one example, the predicted service quality matrix may be future service quality.
[0038] Once the predicted service quality matrix is derived, the generation module 220 may compare the current service quality matrix and the predicted service quality matrix. Based on the comparison, the generation module 220 may fine tune the predicted service quality matrix. Upon tuning the predicted service quality matrix, the generation module 220 may again compare the current service quality matrix with the tuned predicted service quality matrix. In one example, the generation module 220 may identify degradation in the predicted service quality matrix based on the comparison. The generation module 220 may identify one or more issues associated with network service quality based on the comparison. In one example, the one or more issues may correspond to reasons for degradation in the predicted service quality matrix.
[0039] Once the one or more issues are identified, the generation module 220 may analyse the one or more issues based on historical defect data. The historical defect data may be stored in a knowledge database. The historical defect data may comprise support data, defect data and incidental data. The defect data and the incidental data may correspond to defects or incidents occurred in past that caused degradation in the network service quality. The support data may correspond to solution or actions takes in past to overcome the defects or incidents occurred in the past. In one embodiment, the generation module
13
220 may identify one or more solutions, from the knowledge database, to resolve the one or more issues.
[0040] Based on the analysis, the generation module 220 may generate one or more suggestions to improve the network service quality. The one or more suggestions may be provided to the network service providers. The one or more suggestions may be used to mitigate degradation in the network service quality. In one aspect, the one or more suggestions may be provided in real-time. The network service provider may take proper action based on the one or more suggestions to mitigate degradation in the network service quality.
[0041] In one embodiment, the one or more suggestions may be generated based on comparison of the network service quality, associated with one base station, and network service quality, associated with another base station. These suggestions may be provided to select the base station based on the comparison of the network service quality.
[0042] Exemplary embodiments discussed above may provide certain advantages. Though not required to practice aspects of the disclosure, these advantages may include those provided by the following features.
[0043] Some embodiments of the system and the method is configured to real-time suggestions to improve telecommunication network service quality.
[0044] Some embodiments of the system and the method is configured to perform multi-level analysis of data.
[0045] Some embodiments of the system and method is beneficial for telecom and digital service providers to provide accurate network service quality.
[0046] Referring now to figure 3, a method 300 for predicting network service quality and generating suggestion to improve the network service quality, is disclosed in accordance with an embodiment of the present subject matter. The method 300 may be described in the general context of computer executable instructions. Generally, computer executable instructions can include routines, programs, objects, components, data structures, procedures, modules, functions, and the like, that perform particular functions or implement particular abstract data types. The method 300 may also be practiced in a
14
distributed computing environment where functions are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, computer executable instructions may be located in both local and remote computer storage media, including memory storage devices.
[0047] The order in which the method 300 is described is not intended to be construed as a limitation, and any number of the described method blocks can be combined in any order to implement the method 300 or alternate methods. Additionally, individual blocks may be deleted from the method 300 without departing from the spirit and scope of the subject matter described herein. Furthermore, the method 300 can be implemented in any suitable hardware, software, firmware, or combination thereof. However, for ease of explanation, in the embodiments described below, the method 300 may be considered to be implemented in the above described system 102.
[0048] At block 302, real-time data may be received from a set of devices present in a network. In one implementation, the data receiving module 212 may receive the real-time data from the set of devices. The real-time data may comprise configuration data, topology data, interface data, operational data and traffic data, associated with each device from the set of devices.
[0049] At block 304, functional characteristics and behavioral characteristics associated with each device, from the set of devices, may be identified. In one implementation, the identification module 214 may identify the functional characteristics and the behavioral characteristics based on analysis of the real-time data.
[0050] At block 306, a subset of key performance parameters may be identified. In one implementation, the identification module 214 may identify the subset of key performance parameters, from a set of key performance parameters, based on analysis of the functional characteristics and the behavioral characteristics. The functional characteristics and the behavioral characteristics may be analysed using a machine learning algorithm.
[0051] At block 308, a current service quality matrix may be determined. In one implementation, the determination module 216 may determine the current service quality matrix associated with the set of devices. The current service quality matrix may be a real-time service quality. The current service quality matrix may be determined based on correlation between the subset of key performance parameters.
15
[0052] At block 310, a predicted service quality matrix may be derived. In one implementation, the prediction module 218 may derive the predicted service quality matrix based on analysis of the real-time data and historical data, stored in a historical database. The historical data may comprise a time-series based traffic data. The real-time data and the historical data may be analysed using one or more prediction algorithms.
[0053] At block 312, one or more issues, associated with network service quality, may be identified. In one implementation, the generation module 220 may identify the one or more issues based on comparison of the current service quality matrix and the predicted service quality matrix.
[0054] At block 314, one or more suggestions may be generated. In one implementation, the generation module 220 may generate the one or more suggestions by analysing of the one or more issues based on historical defect data. The one or more suggestions may be provided to the network service providers. The one or more suggestions may be used to mitigate degradation in the network service quality.
[0055] Referring now to figure 4, an analytic and prediction system for predicting network service quality and generating suggestions to improve the network service quality, is disclosed in accordance with an embodiment of the present subject matter. In one embodiment, the system 400 may be implemented in a telecom network. The system 400 comprises real-time and batch input telecom data module 401, a functional module 402, a behavioral module 403, a time series module 404, a first stage prediction module 405, a second stage prediction module 406, a service quality determination module 406, a cognitive suggestion module 410, a database 411, a communication interface 413, and other modules. In one aspect, the communication interface 413 may be an interface between determining real time service quality and prediction of the service quality.
[0056] In one embodiment, the real-time and batch input telecom data module 401 may be configured to receive real time and batch mode data from a set of network devices or base stations. The real time and batch mode data may comprise configuration data, topology data, interface data, operational data, and traffic data associated with the set of network devices. In one implementation, a configuration data module 401-A, from the real-time and batch input telecom data module 401, may receive the configuration data from the set of network devices. Further, a topology data module 401-B, from the real-time and batch input
16
telecom data module 401, may receive the topology data from the set of network devices. Furthermore, an interface data module 401-C, from the real-time and batch input telecom data module 401, may receive the interface data from the set of network devices. Furthermore, an operational data module 401-D, from the real-time and batch input telecom data module 401, may receive the operational data from the set of network devices. Furthermore, a traffic data module 401-E, from the real-time and batch input telecom data module 401, may receive the traffic data from the set of network devices.
[0057] Once the real-time and batch mode data is received, the functional module 402 may be configured to analyse the configuration data, the topology data, and the interface data. Based on the analysis, the functional module 402 may identify functional characteristics associated with each device, from the set of network devices. In one embodiment, the functional model 402 may use functional modelling algorithm to analyse the configuration data, the interface data and the topology data.
[0058] Further, the behavioral module 403 may analyse the operational data and the traffic data. Based on the analysis, the behavioral module 403 may identify behavioral characteristics associated with each device, from the set of network devices.
[0059] Upon identifying the functional characteristics and the behavioral characteristics, the service quality determination module 406 may determine a current service quality matrix associated with the set of network devices. In one embodiment, the current service quality matrix may be determined based on functional characteristics and the behavioral characteristics.
[0060] In one embodiment, the system 400 may predict behavior of the base station for next specific period such as how different topologies (2G,3G,4G and 5G) will handle the end devices data, failures that can be occurred in next couple of hours or days based on the batch and real-time data of the base station. In this case, the time series module 404 may receive time series based traffic data from the set of network devices. The time series based traffic data may be used by the time series module 404 to provide a time series prediction of the traffic data.
[0061] Further, the first stage prediction module 405 may analyse the time series based traffic data and the real time and batch mode data. Further, the data analysed by the first stage prediction module 405 may be forwarded to the second stage prediction module 407.
17
The second stage prediction module 407 may analyse the data received from the first stage prediction module 405 and data received from a real-time series based storage module 409. The second stage prediction module 407 may derive a predicted service quality matrix based on analysis of the data.
[0062] In one aspect, the second stage prediction module 407 may consist two main functional capabilities such as, storing and processing first level predictive data, received from the first stage prediction module 405, based on time, and an algorithm and feedback module 409 that applies different type of predictive algorithm on the first level data to match with real time data received from the real-time and batch input telecom data module 401. Further, the second stage prediction module 407 will may fine tune the initial prediction data with real time data and provide best matching predictive model to the cognitive suggestion module 410.
[0063] Further, the cognitive suggestion module 410 may provide one or more suggestions to alleviate and mitigate the service quality degradation if any by using data stored in the database 411. The database 411 may store support data 411-A, defect data 411-B, and incidental data 411-C. One or more suggestions may be fed back to the network or network service provider. Based on the one or more suggestions, the base stations or any end connected devices may be able to change their behavior on real time bases, and use best possible network resources for the proper communication and end user experience purpose. Further, input/output data handling module 412 may be the communication data interface to receive and send back the predicted service quality suggestions to the base station services and end user devices.
[0064] In one embodiment, the system 400 may suggest the end user or end user device software for suitable network topology selection of a base station or the selection of another available base station based on different service quality parameters and predictable cognitive suggestion of the same by using real time, multi feedback prediction algorithm model.
[0065] Referring now to figure 5, an exemplary embodiment of the system, predicting network service quality and generating suggestions to improve the network service quality, implemented in a telecom network, is disclosed in accordance with an embodiment of the present subject matter. In one embodiment, the system 500 may be implemented and
18
connected to base stations 514 and 516. The base station 514 may be connected to the system 500 via a network intersection point 509a. The base station 516 may be connected to the system 500 via a network intersection point 509b.
[0066] Each base station 514, 516 may comprise different type of networks such as a 2G network 502, a 3G network 506, a 4 G network 507 and a 5G network 508. In one embodiment, a mobile device 502 may be connected in 3G network 506 of the base station 514. Further, an IOT device may be connected in 5G network 508 of the base station 514. In another embodiment, a mobile device 510 may be connected in the 2G network 506 of the base station 516. Further, a device, travelling in a vehicle 511, may be connected in 3G network 506 and then connected in the 5G network 507 of the base station 516.
[0067] In one embodiment, the system 500 may receive real-time data and batch mode data from the base stations 514 and 516. The base stations 514 and 516 may have different level of topology, configuration and type. The system 500 may provide better telecom network service quality assurance based on the real time data and batch mode data. In one aspect, the system 500 may be configured to provide suggestions to the service provider based on comparison of a current service quality matrix and a predicted service quality matrix. Further, the service providers may use the suggestions to improve better handling of the base station resources as well end user services and satisfaction level.
[0068] Although implementations for systems and methods for predicting network service quality and generating suggestions to improve the network service quality have been described, it is to be understood that the appended claims are not necessarily limited to the specific features or methods described. Rather, the specific features and methods are disclosed as examples of implementations for providing generating suggestions to improve network service quality.

WE CLAIM:
1. A system (102) to predict network service quality and generate suggestions, for network service providers, to improve the network service quality, the system comprising:
a memory (206);
a processor (202) coupled to the memory (206), wherein the processor (202) is configured to execute programmed instructions stored in the memory (206) to:
receive real-time data from a set of devices present in a network;
identify functional characteristics and behavioural characteristics of each device from the set of devices based on analysis of the real-time data;
identify a subset of key performance parameters, from a set of key performance parameters, associated with the set of devices, based on analysis of the functional characteristics and the behavioral characteristics;
determine a current service quality matrix, associated with the set of devices, based on correlation between the subset of key performance parameters;
derive a predicted service quality matrix based on analysis of the real-time data and historical data, received from the set of devices, stored in a historical repository;
identify one or more issues, associated with a network service quality of the set of devices, based on comparison of the current service quality matrix and the predicted service quality matrix; and
analyse the one or more issues based on historical defect data to generate one or more suggestions to improve the network service quality.
2. The system (102) as claimed in claim 1, wherein the real-time data comprises configuration data, topology data, interface data, operational data and traffic data, associated with each device from the set of devices.
3. The system (102) as claimed in claim 2, wherein the functional characteristic of each device, from the set of devices, is identified based on analysis of the configuration data, the topology data and the interface data.
20
4. The system (102) as claimed in claim 2, wherein the behavioral characteristics of each device, from the set of devices, is identified based on analysis of the operational data and the traffic data.
5. The system (102) as claimed in claim 1, wherein the functional characteristics and the behavioral characteristics are analysed using a machine learning algorithm to identify the subset of key performance parameters.
6. The system (102) as claimed in claim 1, wherein the historical data, received from the set of devices, stored in the historical repository, corresponds to a time series based traffic data associated with the set of devices.
7. The system (102) as claimed in claim 1, wherein the derivation of the predicted service quality matrix comprises:
identifying a subset of predicted key performance parameters, from the set of key performance parameters, based on analysing of the real-time data and the historical data using a prediction algorithm; and
deriving the predicted service quality matrix based on correlation between the subset of predicted key performance parameters.
8. The system (102) as claimed in claim 1, further comprises tuning the predicted service quality matrix based on comparison of the current service quality and the predicted service quality matrix.
9. The system (102) as claimed in claim 1, wherein the historical defect data corresponds to support data, defect data, and incident data, and wherein the support data comprises one or more solutions associated with the defect data and the incident data.
10. A method for predicting network service quality and generating suggestions, for network service providers, to improve the network service quality, the method comprises steps of:
receiving, by a processor (202), real-time data from a set of devices present in a network;
21
identifying, by the processor (202), functional characteristics and behavioural characteristics of each device from the set of devices based on analysis of the real-time data;
identifying, by the processor (202), a subset of key performance parameters, from a set of key performance parameters, associated with the set of devices, based on analysis of the functional characteristics and the behavioral characteristics;
determining, by the processor (202), a current service quality matrix, associated with the set of devices, based on correlation between the subset of key performance parameters;
deriving, by the processor (202), a predicted service quality matrix based on analysis of the real-time data and historical data, received from the set of devices, stored in a historical repository;
identifying, by the processor (202), one or more issues, associated with a network service quality of the set of devices, based on comparison of the current service quality matrix and the predicted service quality matrix; and
analysing, by the processor (202), the one or more issues based on historical defect data to generate one or more suggestions to improve the network service quality.
11. The method as claimed in claim 10, wherein the real-time data comprises configuration data, topology data, interface data, operational data and traffic data, associated with each device from the set of devices.
12. The method as claimed in claim 11, wherein the functional characteristic of each device, from the set of devices, is identified based on analysis of the configuration data, the topology data and the interface data.
13. The method as claimed in claim 11, wherein the behavioral characteristics of each device, from the set of devices, is identified based on analysis of the operational data and the traffic data.
14. The method as claimed in claim 10, wherein the functional characteristics and the behavioral characteristics are analysed using a machine learning algorithm to identify the subset of key performance parameters.
22
15. The method as claimed in claim 10, wherein the historical data, received from the set of devices, stored in the historical repository, corresponds to a time series based traffic data associated with the set of devices.
16. The method as claimed in claim 10, wherein the derivation of the predicted service quality matrix comprises:
identifying a subset of predicted key performance parameters, from the set of key performance parameters, based on analysing of the real-time data and the historical data using a prediction algorithm; and
deriving the predicted service quality matrix based on correlation between the subset of predicted key performance parameters.
17. The method as claimed in claim 10, further comprises tuning the predicted service quality matrix based on comparison of the current service quality and the predicted service quality matrix.
18. The method as claimed in claim 10, wherein the historical defect data corresponds to support data, defect data, and incident data, and wherein the support data comprises one or more solutions associated with the defect data and the incident data.
19. A computer program product having embodied thereon a computer program for predicting network service quality and generating suggestions, for network service providers, to improve the network service quality, the computer program product comprises:
a program code for receiving real-time data from a set of devices present in a network;
a program code for identifying functional characteristics and behavioural characteristics of each device from the set of devices based on analysis of the real-time data;
a program code for identifying a subset of key performance parameters, from a set of key performance parameters, associated with the set of devices, based on analysis of the functional characteristics and the behavioral characteristics;
23
a program code for determining a current service quality matrix, associated with the set of devices, based on correlation between the subset of key performance parameters;
a program code for deriving a predicted service quality matrix based on analysis of the real-time data and historical data, received from the set of devices, stored in a historical repository;
a program code for identifying one or more issues, associated with a network service quality of the set of devices, based on comparison of the current service quality matrix and the predicted service quality matrix; and
a program code for analysing the one or more issues based on historical defect data to generate one or more suggestions to improve the network service quality.