FORM 2
THE PATENTS ACT, 1970
THE PATENTS RULES, 2003
COMPLETE SPECIFICATION
APPLICANT
JIO PLATFORMS LIMITED
of Office-101, Saffron, Nr. Centre Point, Panchwati 5 Rasta, Ambawadi, Ahmedabad - 380006, Gujarat, India; Nationality: India
The following specification particularly describes
the invention and the manner in which
it is to be performed

RESERVATION OF RIGHTS
[001] A portion of the disclosure of this patent document contains material
which is subject to intellectual property rights such as, but are not limited to, copyright, design, trademark, integrated circuit (IC) layout design, and/or trade dress protection, belonging to Jio Platforms Limited (JPL) or its affiliates (herein after referred as owner). The owner has no objection to the facsimile reproduction by anyone of the patent document or the patent disclosure, as it appears in the Patent and Trademark Office patent files or records, but otherwise reserves all rights whatsoever. All rights to such intellectual property are fully reserved by the owner.
TECHNICAL FIELD
[002] The present disclosure relates to a field of communications network,
and specifically to a system and a method for Answer Seizure Ratio (ASR)
prediction.
BACKGROUND
[003] The following description of related art is intended to provide
background information pertaining to the field of the disclosure. This section may include certain aspects of the art that may be related to various features of the present disclosure. However, it should be appreciated that this section be used only to enhance the understanding of the reader with respect to the present disclosure, and not as admissions of prior art.
[004] The Answer Seizure Ratio (ASR) is a metric used to measure the
efficiency of call completion in telecommunication networks. ASR represents the ratio of successfully answered calls to the total number of calls attempted. A high ASR indicates a high-quality network where most call attempts are successfully completed, while a low ASR suggests potential issues within the network that may lead to call failures and poor user experience.
[005] In the context of telecommunication networks, maintaining a high
ASR is essential not only for customer satisfaction but also for regulatory compliance. The ASR value is often regulated by telecommunications authorities,

and a drop below certain thresholds can result in significant penalties for service providers. Furthermore, a low ASR can damage the reputation of the network provider as it directly affects the user experience, leading to customer dissatisfaction and potential loss of subscribers.
[006] Traditionally, ASR values are monitored and analyzed after issues
have already occurred. This reactive approach means that network providers often identify and address problems only after they have affected users, leading to degraded service quality and user dissatisfaction. Conventional methods involve manual monitoring and post-incident analysis, which can be time-consuming and inefficient. These methods are inadequate for proactively managing network performance and preventing ASR drops.
[007] A patent document US20190036795A1, discloses methods for
monitoring network performance metrics, including ASR, using historical data analysis. This reference provides for an anomaly detection and remedial service that includes receiving data from a network, performing a Gaussian Probabilistic Latent Semantic Analysis (GPLSA) using the data, detecting anomaly data included in the data based on the GPLSA, and invoking a remedial measure in the network based on the detection. However, it does not explicitly disclose applying time series forecasting machine learning algorithms to predict future ASR values or providing a user the option to choose from multiple models.
[008] Another patent document, US20230216953A1, describes systems
for identifying international calling performance issues by monitoring network traffic data for international calls and using an anomaly detection model to identify performance anomalies. While this reference discloses monitoring and analyzing network performance, it does not explicitly address the application of time series forecasting machine learning algorithms for predicting future ASR values or allowing user selection of predictive models.
[009] Non-patent publication, "Telecommunications observability with
the Elastic Stack: Monitoring voice traffic data" by Elastic NV, discusses the storage and analysis of call data records (CDRs) using Elasticsearch and highlights the ability to derive key performance indicators (KPIs) such as ASR. However, this

reference does not explicitly disclose the use of machine learning algorithms for future ASR values forecasting or providing users the option to select from multiple predictive models.
[0010] There remains a need for a method and system that can forecast
future ASR values using time series forecasting machine learning algorithms, allow user selection of the best predictive model, and provide a user interface for displaying prediction results. These features enable proactive management of network performance, ensuring regulatory compliance and enhancing user satisfaction by preventing ASR drops before they occur.
OBJECTS OF THE PRESENT DISCLOSURE
[0011] It is an object of the present disclosure to provide a system for
predicting a dip in an Answer Seizure Ratio (ASR) value beforehand.
[0012] It is an object of the present disclosure to provide a detailed analysis
of probable causes that result in fall of an ASR value.
[0013] It is an object of the present disclosure to provide an auto-estimated
forecast of the ASR value for the next few days in future.
[0014] It is an object of the present disclosure to maintain the ASR value
for improving user experience.
[0015] It is an object of the present disclosure to avoid degradation in
customer services in advance, thereby improving user experience.
SUMMARY
[0016] In an exemplary embodiment, a method of forecasting Answer
Seizure Ratio (ASR) metric in a telecommunication network is described. The method includes fetching, by a processing engine, past ASR data uploaded by a user through a User Interface (UI) and performing exploratory data analysis, by a forecasting module, on the ASR data to determine optimal parameters for an AI model. The method further includes receiving selection, by the forecasting module from the user, of a predefined number of AI models from available AI models through the UI (206). The forecasting microservice trains the predefined number

of AI models selected by the user based on the past ASR data in a distributed fashion for faster results. The method further includes predicting, by the forecasting module, future ASR values using a best performing AI model from the selected predefined number of AI models by the forecasting microservice, and displaying, by the user interface (UI), the prediction results to the user on the user interface (UI). The best performing AI model is selected based on a portion of the past ASR data. In an embodiment, there are different ways for selecting the best AI model. For example, best AI model can be selected based on the performance, user input, complexity of the model, the level of control and flexibility desired, and size of the data.
[0017] In some embodiments, the method further includes making, by the
processing engine, appropriate actions based on the prediction results.
[0018] In some embodiments, the forecasting module applies time series
forecasting machine learning algorithms selected from a group consisting of ARIMA, LSTM, and Prophet..
[0019] In some embodiments, the method further includes periodically
retraining, by a retraining module, the predefined number of AI models as new ASR data becomes available.
[0020] In some embodiments, the method further includes receiving, by the
forecasting module, past ASR data in a CSV format on the User Interface (UI).
[0021] In another exemplary embodiment, a system for forecasting Answer
Seizure Ratio (ASR) metric in a telecommunication network is described. The system comprises a processing engine configured to fetch past ASR data uploaded by a user through a User Interface (UI); a forecasting module configured to perform exploratory data analysis on the ASR data to determine optimal parameters for an AI model, receive selection from the user of a predefined number of models from available models, and to train the predefined number of models based on the past ASR data or the optimal parameters in a distributed fashion for faster results, and predict future ASR values using a best performing AI model from the predefined number of AI models; and the user interface (UI) configured to display the prediction results to the user.

[0022] In some embodiments, the processing engine is further configured to
make appropriate actions based on the prediction results.
[0023] In some embodiments, the forecasting module is configured to apply
time series forecasting machine learning algorithms selected from a group consisting of ARIMA, LSTM, and Prophet.
[0024] In some embodiments, the system further includes a retraining
module configured to periodically retrain the model as new data becomes available.
[0025] In some embodiments, the forecasting module is configured to
receive past ASR data in a CSV format on the User Interface (UI).
[0026] A computer program product comprising a non-transitory computer-
readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to execute a method for forecasting Answer Seizure Ratio (ASR) metric in a telecommunication network, the method comprising fetching, by a processing engine (208), past ASR data uploaded by a user through a User Interface (UI) (206); performing exploratory data analysis, by a forecasting module (214) including a forecasting microservice, on the ASR data to determine optimal parameters for a specific model; receiving selection, by the forecasting module (214) from the user, of a predefined number of models from available models, wherein the forecasting microservice trains the predefined number of models selected by the user based on the ASR data in a distributed fashion for faster results; predicting, by the forecasting module (214), future ASR values using a best performing model; and displaying, by the user interface (206), the prediction results to the user on the user interface (206).
BRIEF DESCRIPTION OF THE DRAWINGS
[0027] In the figures, similar components and/or features may have the
same reference label. Further, various components of the same type may be distinguished by following the reference label with a second label that distinguishes among the similar components. If only the first reference label is used in the specification, the description is applicable to any one of the similar components having the same first reference label irrespective of the second reference label.

[0028] The diagrams are for illustration only, which thus is not a limitation
of the present disclosure, and wherein:
[0029] FIG. 1 illustrates an exemplary network architecture in which or with
which embodiments of the present disclosure may be implemented.
[0030] FIG. 2 illustrates an exemplary block diagram of an Answer Seizure
Ratio (ASR) prediction system, in accordance with an embodiment of the present
disclosure.
[0031] FIG. 3 illustrate an exemplary architecture of the ASR prediction
system, in accordance with an embodiment of the present disclosure.
[0032] FIG. 4 illustrates an exemplary flow chart of an ASR prediction
method, in accordance with an embodiment of the present disclosure.
[0033] FIG. 5 illustrates an exemplary computer system in which or with
which embodiments of the present disclosure may be implemented.
[0034] FIG. 6 illustrates an exemplary workflow diagram of diagram for
forecasting Answer Seizure Ratio (ASR) metric in a telecommunication network,
in accordance with an embodiment of the present disclosure.
LIST OF REFERENCES:
100: Network architecture
102-1, 102-2…102-N: Users
104-1, 104-2…104-N: User equipments (smart devices, handheld wireless
communication devices, wearable computer devices, etc.)
106: Network (5G network, 6G network, WAN, LAN, etc.)
108: System
112: Centralized server (stand-alone server, server blade, server rack, etc.)
200: System architecture
202: Processor(s)
204: Memory
206: Interface(s)
208: Processing engine
210: Database

212: AI/ML engine 214: Forecasting module 216: Other modules 500: Computer System 510: External Storage Device 520: Bus
530: Main Memory 540: Read-Only Memory 550: Mass Storage Device 560: Communication Port(s) 570: Processor 600: Method
DETAILED DESCRIPTION
[0035] The following is a detailed description of embodiments of the
disclosure depicted in the accompanying drawings. The embodiments are in such detail as to clearly communicate the disclosure. However, the amount of detail offered is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the present disclosure as defined by the appended claims.
[0036] In the following description, for the purposes of explanation, various
specific details are set forth in order to provide a thorough understanding of embodiments of the present disclosure. It will be apparent, however, that embodiments of the present disclosure may be practiced without these specific details. Several features described hereafter can each be used independently of one another or with any combination of other features. An individual feature may not address all of the problems discussed above or might address only some of the

problems discussed above. Some of the problems discussed above might not be fully addressed by any of the features described herein.
[0037] The ensuing description provides exemplary embodiments only, and
is not intended to limit the scope, applicability, or configuration of the disclosure. 5 Rather, the ensuing description of the exemplary embodiments will provide those skilled in the art with an enabling description for implementing an exemplary embodiment. It should be understood that various changes may be made in the function and arrangement of elements without departing from the spirit and scope of the disclosure as set forth.
10 [0038] Specific details are given in the following description to provide a
thorough understanding of the embodiments. However, it will be understood by one of ordinary skill in the art that the embodiments may be practiced without these specific details. For example, circuits, systems, networks, processes, and other components may be shown as components in block diagram form in order not to
15 obscure the embodiments in unnecessary detail. In other instances, well-known
circuits, processes, algorithms, structures, and techniques may be shown without
unnecessary detail in order to avoid obscuring the embodiments.
[0039] Also, it is noted that individual embodiments may be described as a
process which is depicted as a flowchart, a flow diagram, a data flow diagram, a
20 structure diagram, or a block diagram. Although a flowchart may describe the operations as a sequential process, many of the operations can be performed in parallel or concurrently. In addition, the order of the operations may be re-arranged. A process is terminated when its operations are completed but could have additional steps not included in a figure. A process may correspond to a method, a function, a
25 procedure, a subroutine, a subprogram, etc. When a process corresponds to a function, its termination can correspond to a return of the function to the calling function or the main function.
[0040] The word “exemplary” and/or “demonstrative” is used herein to
mean serving as an example, instance, or illustration. For the avoidance of doubt,
30 the subject matter disclosed herein is not limited by such examples. In addition, any aspect or design described herein as “exemplary” and/or “demonstrative” is not
9

necessarily to be construed as preferred or advantageous over other aspects or designs, nor is it meant to preclude equivalent exemplary structures and techniques known to those of ordinary skill in the art. Furthermore, to the extent that the terms “includes,” “has,” “contains,” and other similar words are used in either the detailed 5 description or the claims, such terms are intended to be inclusive in a manner similar to the term “comprising” as an open transition word without precluding any additional or other elements.
[0041] Reference throughout this specification to “one embodiment” or “an
embodiment” or “an instance” or “one instance” means that a particular feature,
10 structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Thus, the appearances of the phrases “in one embodiment” or “in an embodiment” in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined
15 in any suitable manner in one or more embodiments.
[0042] The terminology used herein is for the purpose of describing
particular embodiments only and is not intended to be limiting of the disclosure. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further
20 understood that the terms “comprises” and/or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. As used herein, the term “and/or” includes any and all combinations
25 of one or more of the associated listed items.
[0043] The present disclosure may provide a system to train an Artificial
intelligence/Machine Learning model based on historical call record’s data. The system may predict a dip in an Answer Seizure Ratio (ASR) value in advance. The system may provide a detailed analysis of probable causes that result in fall of ASR
30 value. The system may provide an auto-estimated forecast of the ASR value for the next few days in future. Based on the forecasting, the network operators may take
10

corrective actions to maintain the ASR value. Thus, the system avoids degradation in customer services in advance.
[0044] The various embodiments of the present disclosure will be explained
in detail with reference to FIGs. 1 to 6.
5 [0045] FIG. 1 illustrates an exemplary network architecture in which or with
which a system (108) for Answer Seizure Ratio (ASR) prediction in a wireless
network is implemented, in accordance with embodiments of the present disclosure.
[0046] Referring to FIG. 1, the network architecture (100) includes one or
more computing devices or user equipments (104-1, 104-2…104-N) associated
10 with one or more users (102-1, 102-2…102-N) in an environment. A person of ordinary skill in the art will understand that one or more users (102-1, 102-2…102-N) may be individually referred to as the user (102) and collectively referred to as the users (102). Similarly, a person of ordinary skill in the art will understand that one or more user equipments (104-1, 104-2…104-N) may be individually referred
15 to as the user equipment (104) and collectively referred to as the user equipment (104). A person of ordinary skill in the art will appreciate that the terms “computing device(s)” and “user equipment” may be used interchangeably throughout the disclosure. Although three user equipments (104) are depicted in FIG. 1, however any number of the user equipments (104) may be included without departing from
20 the scope of the ongoing description.
[0047] In an embodiment, the user equipment (104) includes smart devices
operating in a smart environment, for example, an Internet of Things (IoT) system. In such an embodiment, the user equipment (104) may include, but is not limited to, smart phones, smart watches, smart sensors (e.g., mechanical, thermal,
25 electrical, magnetic, etc.), networked appliances, networked peripheral devices, networked lighting system, communication devices, networked vehicle accessories, networked vehicular devices, smart accessories, tablets, smart television (TV), computers, smart security system, smart home system, other devices for monitoring or interacting with or for the users (102) and/or entities, or any combination thereof.
30 A person of ordinary skill in the art will appreciate that the user equipment (104) may include, but is not limited to, intelligent, multi-sensing, network-connected
11

devices, that can integrate seamlessly with each other and/or with a central server
or a cloud-computing system or any other device that is network-connected.
[0048] In an embodiment, the user equipment (104) includes, but is not
limited to, a handheld wireless communication device (e.g., a mobile phone, a smart 5 phone, a phablet device, and so on), a wearable computer device(e.g., a head-mounted display computer device, a head-mounted camera device, a wristwatch computer device, and so on), a Global Positioning System (GPS) device, a laptop computer, a tablet computer, or another type of portable computer, a media playing device, a portable gaming system, and/or any other type of computer device with
10 wireless communication capabilities, and the like. In an embodiment, the user equipment (104) includes, but is not limited to, any electrical, electronic, electro¬mechanical, or an equipment, or a combination of one or more of the above devices such as virtual reality (VR) devices, augmented reality (AR) devices, laptop, a general-purpose computer, desktop, personal digital assistant, tablet computer,
15 mainframe computer, or any other computing device, wherein the user equipment (104) may include one or more in-built or externally coupled accessories including, but not limited to, a visual aid device such as a camera, an audio aid, a microphone, a keyboard, and input devices for receiving input from the user (102), or the entity (110) such as touch pad, touch enabled screen, electronic pen, and the like. A person
20 of ordinary skill in the art will appreciate that the user equipment (104) may not be
restricted to the mentioned devices and various other devices may be used.
[0049] Referring to FIG. 1, the user equipment (104) communicates with a
system (108), for example, a system for forecasting Answer Seizure Ratio (ASR) metric, through a network (106). In an embodiment, the network (106) includes at
25 least one of a Fifth Generation (5G) network, 6G network, or the like. The network (106) enables the user equipment (104) to communicate with other devices in the network architecture (100) and/or with the system (108). The network (106) includes a wireless card or some other transceiver connection to facilitate this communication. In another embodiment, the network (106) is implemented as, or
30 include any of a variety of different communication technologies such as a wide area network (WAN), a local area network (LAN), a wireless network, a mobile
12

network, a Virtual Private Network (VPN), the Internet, the Public Switched Telephone Network (PSTN), or the like.
[0050] In another exemplary embodiment, the centralized server (112)
includes or comprise, by way of example but not limitation, one or more of: a stand-5 alone server, a server blade, a server rack, a bank of servers, a server farm, hardware supporting a part of a cloud service or system, a home server, hardware running a virtualized server, one or more processors executing code to function as a server, one or more machines performing server-side functionality as described herein, at least a portion of any of the above, some combination thereof.
10 [0051] In an embodiment, the network (106) is further configured with the
centralized server (112) including a database, where all output is stored as part of
the operational records. It can be retrieved whenever there is a need to reference
this output in the future.
[0052] In an embodiment, the computing device (102) associated with one
15 or more users (110) may transmit the at least one captured data packet over a point-to-point or point-to-multipoint communication channel or network (106) to the system (102).
[0053] In an embodiment, the computing device (102) may involve
collection, analysis, and sharing of data received from the system (108) via the
20 communication network (106).
[0054] Although FIG. 1 shows exemplary components of the network
architecture (100), in other embodiments, the network architecture (100) may include fewer components, different components, differently arranged components, or additional functional components than depicted in FIG. 1. Additionally, or
25 alternatively, one or more components of the network architecture (100) may perform functions described as being performed by one or more other components of the network architecture (100).
[0055] FIG. 2 illustrates an exemplary system architecture (200) of the
system (108), in accordance with embodiments of the present disclosure.
30 [0056] The disclosed system architecture (200) ensures effective
forecasting of Answer Seizure Ratio (ASR) metrics in a telecommunication
13

network by leveraging advanced machine learning algorithms and user interfaces.
[0057] FIG. 2, with reference to FIG. 1, illustrates an exemplary
representation of the system (108) for enabling ASR prediction in a telecommunication network, in accordance with an embodiment of the present 5 disclosure.
[0058] In an aspect, the system (108) may comprise one or more
processor(s) (202). The one or more processor(s) (202) may be implemented as one or more microprocessors, microcomputers, microcontrollers, edge or fog microcontrollers, digital signal processors, central processing units, logic
10 circuitries, and/or any devices that process data based on operational instructions. Among other capabilities, the one or more processor(s) (202) may be configured to fetch and execute computer-readable instructions stored in a memory (204) of the system (108). The memory (204) may be configured to store one or more computer-readable instructions or routines in a non-transitory computer readable storage
15 medium, which may be fetched and executed to create or share data packets over a network service. The memory (204) may comprise any non-transitory storage device including, for example, volatile memory such as Random Access Memory (RAM), or non-volatile memory such as Erasable Programmable Read-Only Memory (EPROM), flash memory, and the like.
20 [0059] Referring to FIG. 2, the system (108) may include an interface(s)
(206). The interface(s) (206) may comprise a variety of interfaces, for example, interfaces for data input and output devices, referred to as I/O devices, storage devices, and the like. The interface(s) (206) may facilitate communication to/from the system (108). The interface(s) (206) may also provide a communication
25 pathway for one or more components of the system (108). Examples of such components include, but are not limited to, a processing engine (208) and a database (210).
[0060] In an embodiment, a processing engine (208) may be implemented
as a combination of hardware and programming (for example, programmable
30 instructions) to implement one or more functionalities of the processing engine (208). In examples described herein, such combinations of hardware and
14

programming may be implemented in several different ways. For example, the programming for the processing engine (208) may be processor-executable instructions stored on a non-transitory machine-readable storage medium and the hardware for the processing engine (208) may comprise a processing resource (for 5 example, one or more processors) to execute such instructions. In the present examples, the machine-readable storage medium may store instructions that, when executed by the processing resource, implement the processing engine (208). In such examples, the system (108) may comprise the machine-readable storage medium storing the instructions and the processing resource to execute the
10 instructions, or the machine-readable storage medium may be separate but
accessible to the system (108) and the processing resource. In other examples, the
processing engine (208) may be implemented by electronic circuitry.
[0061] In an embodiment, a database (210) may comprise data that may be
either stored or generated as a result of functionalities implemented by any of the
15 components of the processor (202) or the processing engine (208). In an
embodiment, the database (210) may be separate from the system (108).
[0062] In an exemplary embodiment, the processing engine (208) may
include one or more modules selected from any of an AI/ML engine (212), a forecasting module (214), and other modules (216) having functions that may
20 include but are not limited to data analysis, model training, prediction, and
peripheral functions such as network monitoring and user interface management.
[0063] The processing engine (208) may include one or more engines
selected from any of the Artificial Intelligence (AI) engine (212), and other engine(s) (216).
25 [0064] The AI/ML engine (212) may be responsible for implementing
machine learning algorithms to process historical ASR data and generate predictive models. The AI/ML engine (212) is based on various machine learning techniques such as supervised learning, unsupervised learning, and reinforcement learning to improve the accuracy of ASR predictions. Supervised learning utilizes labelled
30 historical ASR data to train models that can predict future ASR values based on input features. Techniques such as regression analysis, decision trees, and neural
15

networks are commonly used. Unsupervised learning identifies patterns and relationships within the historical ASR data without labelled responses. Clustering and association algorithms, such as k-means clustering and hierarchical clustering, are employed to detect anomalies and trends. Reinforcement learning continuously 5 improves the predictive models by learning from the outcomes of past predictions and adjusting the algorithms accordingly. This approach enhances the model accuracy over time by incorporating feedback from the network performance. Feature engineering extracts relevant features from the raw ASR data to improve model performance. Such extraction involves transforming and selecting key
10 variables that have the most significant impact on ASR predictions. Model evaluation and tuning continuously evaluates the performance of different models using metrics such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R-squared (R²). Hyperparameter tuning techniques like grid search and random search are applied to optimize model parameters.
15 [0065] The forecasting module (214) utilizes the predictive models
generated by the AI/ML engine (212) to forecast future ASR metrics. The forecasting module (214) performs several key functions. Real-time data processing ingests real-time ASR data from various network sources and pre-processes it for use in the predictive models. This includes data cleaning, normalization, and
20 integration with historical data. Trend analysis analyzes historical ASR trends to identify seasonal patterns, cyclic behavior, and long-term trends that may influence future ASR values. Predictive modeling applies the predictive models to generate short-term and long-term forecasts of ASR metrics. This involves running simulations and scenario analyses to predict how ASR will change under different
25 conditions. Anomaly detection monitors the predicted ASR values for deviations from expected behavior. When anomalies are detected, alerts are generated to notify network operators of potential issues that require attention. Visualization provides graphical representations of ASR forecasts, including time series plots, heatmaps, and dashboards. These visualizations help network operators understand the
30 predictions and make informed decisions. Scenario planning enables network operators to explore different "what-if" scenarios by adjusting input parameters and
16

observing the impact on ASR forecasts. This helps in strategic planning and
resource allocation.
[0066] Other modules (216) include additional functionalities that ensure
the efficient operation of the system (108) and provide comprehensive insights into 5 ASR metrics.
[0067] Although FIG. 2 shows an exemplary block diagram (200) of the
ASR prediction system (108), in other embodiments, the ASR prediction system
(108) may include fewer components, different components, differently arranged
components, or additional functional components than depicted in FIG. 2. 10 Additionally, or alternatively, one or more components of the ASR prediction
system (108) may perform functions described as being performed by one or more
other components of the ASR prediction system (108).
[0068] FIG. 3 illustrate the exemplary architecture (300) of the ASR
prediction system (108), in accordance with an embodiment of the present 15 disclosure.
[0069] The ASR prediction system (108) may include an ASR data source
(302), a forecasting engine (304), a graphical user interface (310), and modules for
taking corrective measures (312) by the network team.
[0070] The ASR data source (302) provides historical ASR data, which is
20 utilized for forecasting future ASR metrics. The ASR data may be stored in various
formats, including Comma-Separated Values (CSV) files or within a database. The
ASR data source (302) supplies the necessary historical data for analysis and
prediction.
[0071] The forecasting module (304) is configured for processing the ASR
25 data and generating predictions. The forecasting module (304) includes, but may
not be limited to, a data visualization module (306), a model selection module (308),
and a model training module (314). Each performing specific functions to ensure
accurate forecasting:
[0072] The data visualization module (306) processes and visualizes the
30 ASR data fetched from the ASR data source (302). The data visualization module
(306) is implemented for understanding the data distribution, trends, and patterns,
17

presenting the data in an easily interpretable format through techniques, such as graphs, charts, and heatmaps. The initial data analysis is utilized in preparing the data for further processing and model training.
[0073] The model selection module (308) allows users to select one or more
5 models from the available AI models. This selection is facilitated through the graphical user interface (310). The model selection module (308) provides a list of pre-trained models, such as ARIMA, LSTM, and Prophet, and enables the user to select the most suitable ones based on the data characteristics and forecasting requirements.
10 [0074] Based the selected AI models, the model training module (314)
trains the chosen AI models on the historical ASR data in a distributed manner. Distributed training ensures faster processing and efficient handling of large datasets. This module adjusts the model parameters to fit the historical data accurately, optimizing the models for future predictions.
15 [0075] The predictions module (316) uses the trained models to generate
future ASR values. It applies the models to the processed historical data and
calculates the predicted ASR metrics for upcoming periods. These predictions are
essential for proactive network management and decision-making.
[0076] The graphical user interface (310) is the interactive platform through
20 which users interact with the ASR prediction system (108). Users can upload historical ASR data in CSV format or provide database details via the interface. The UI (310) also facilitates model selection, displays prediction results, and allows users to review and analyze the forecasts. The user-friendly design of the UI (310) ensures that network operators can easily navigate the system, upload data, view
25 predictions, and make informed decisions.
[0077] Based on the predictions displayed on the graphical user interface
(310), the network team takes appropriate corrective measures (312). This involves addressing any anticipated drops in the ASR by implementing necessary adjustments and optimizations in the network infrastructure. The corrective
30 measures (312) are utilized for maintaining high-quality service and preventing potential network issues before they affect users.
18

[0078] FIG. 4 illustrates an exemplary flow chart (400) of an ASR
prediction method, in accordance with an embodiment of the present disclosure.
[0079] Referring to FIG. 4, the ASR prediction method may include
uploading historical data (402) of ASR in CSV format on a UI (404) or by providing 5 details of a database where the data is stored. The method may include fetching the data and performing exploratory data analysis on the given ASR data which helps the user to choose one or more optimal parameters required for training a specific AI model. The optimal parameter may be related to ASR and the specific AI model to be trained. The optimal parameters related to the ASR may include network
10 congestion values, signal strength, call duration threshold, number of calls per user etc. The optimal parameters related to the specific AI model may include parameters such as AI/ML algorithm to be used for that AI model. The method may include training one or more AI models (406) on the given ASR data to predict (408) a drop in ASR values. Best model’s prediction may be taken into
15 consideration by the user to take the appropriate actions. The prediction results may be displayed on the UI. The user may take appropriate action (410) on the instance where the ASR drops. In one embodiment, the appropriate actions may include corrective actions to maintain the ASR value above 99%. The system works to avoid any degradation in customer services in advance. Further, low answer-seizure
20 ratios may be caused by far-end switch congestion, not answering by called parties and busy destination circuits. The corrective action may include handling the switch congestion and increasing the capacity of the destination circuits. Further, the actions may include updating threshold for terminating an ongoing long duration call so that new calls may be connected. The AI model may be retrained periodically
25 as and when new data is available along with the old data, thus providing better predictions.
[0080] FIG. 5 illustrates an exemplary computer system (500) in which or
with which embodiments of the present disclosure may be implemented. As shown in FIG. 5, the computer system (500) may include an external storage device (510),
30 a bus (520), a main memory (530), a read only memory (540), a mass storage device (550), a communication port (560), and a processor (570). A person skilled in the
19

art will appreciate that the computer system (500) may include more than one
processor (570) and communication ports (560). Processor (570) may include
various modules associated with embodiments of the present disclosure.
[0081] In an embodiment, the communication port (560) may be any of an
5 RS-232 port for use with a modem-based dialup connection, a 10/100 Ethernet port, a Gigabit or 10 Gigabit port using copper or fiber, a serial port, a parallel port, or other existing or future ports. The communication port (560) may be chosen depending on a network, such a Local Area Network (LAN), Wide Area Network (WAN), or any network to which the computer system (500) connects.
10 [0082] In an embodiment, the memory (530) may be Random Access
Memory (RAM), or any other dynamic storage device commonly known in the art. Read-only memory (540) may be any static storage device(s) e.g., but not limited to, a Programmable Read Only Memory (PROM) chips for storing static information e.g., start-up or Basic Input/Output System (BIOS) instructions for the
15 processor (570).
[0083] In an embodiment, the mass storage (550) may be any current or
future mass storage solution, which may be used to store information and/or instructions. Exemplary mass storage solutions include, but are not limited to, Parallel Advanced Technology Attachment (PATA) or Serial Advanced
20 Technology Attachment (SATA) hard disk drives or solid-state drives (internal or
external, e.g., having Universal Serial Bus (USB) and/or Firewire interfaces), one
or more optical discs, Redundant Array of Independent Disks (RAID) storage, e.g.,
an array of disks (e.g., SATA arrays).
[0084] In an embodiment, the bus (520) communicatively couples the
25 processor(s) (570) with the other memory, storage and communication blocks. The bus (520) may be, e.g., a Peripheral Component Interconnect (PCI)/PCI Extended (PCI-X) bus, Small Computer System Interface (SCSI), Universal Serial Bus (USB) or the like, for connecting expansion cards, drives and other subsystems as well as other buses, such a front side bus (FSB), which connects the processor (570) to the
30 computer system (500).
[0085] Optionally, operator and administrative interfaces, e.g., a display,
20

keyboard, joystick, and a cursor control device, may also be coupled to the bus
(520) to support direct operator interaction with the computer system (500). Other
operator and administrative interfaces may be provided through network
connections connected through the communication port (560). Components
described above are meant only to exemplify various possibilities. In no way should
the aforementioned exemplary computer system (500) limit the scope of the present
disclosure.
[0086] FIG. 6 illustrates an exemplary workflow diagram of a method (600)
for forecasting Answer Seizure Ratio (ASR) metric in a telecommunication
network, in accordance with embodiments of the present disclosure.
[0087] At step (602), the method includes fetching, by a processing engine,
past ASR data uploaded by a user through a User Interface (UI). This step ensures
that the necessary historical data is available for analysis and forecasting.
[0088] At step (604), the method includes performing exploratory data
analysis, by a forecasting module, on the ASR data to determine optimal parameters
for a specific AI model. This step helps in understanding the data and preparing it
for AI model training by identifying relevant patterns and trends.
[0089] At step (606), the method includes receiving selection, by the
forecasting module from the user, of a predefined number of AI models from
available models, wherein the forecasting microservice trains the predefined
number of AI models selected by the user based on the ASR data or the optimal
parameters in a distributed fashion for faster results. This allows the user to choose
the best AI model suited for their specific forecasting needs.
[0090] At step (608), the method includes predicting, by the forecasting
module, future ASR values using the best performing model. This step involves
applying the trained models to generate accurate forecasts of ASR metrics.
[0091] At step (610), the method includes displaying, by the user interface
(UI), the prediction results to the user on the user interface (UI). This step ensures
that the user can view and analyze the forecasting results to make informed
decisions.
[0092] A user equipment (UE) (104) communicatively coupled with a

network (106), the coupling comprises steps of: receiving, by the network (106), a
connection request from the UE (104) and sending, by the network (106), an
acknowledgment of the connection request to the UE (104). The steps further
include transmitting a plurality of signals in response to the connection request,
wherein the network (106) is configured for performing a method for forecasting
Answer Seizure Ratio (ASR) metric in a telecommunication network.
[0093] A computer program product comprising a non-transitory computer-
readable medium comprising instructions that, when executed by one or more
processors, cause the one or more processors to execute a method for forecasting
Answer Seizure Ratio (ASR) metric in a telecommunication network. A processing
engine (208) fetches past ASR data uploaded by a user through a User Interface
(UI) (206). A forecasting module (214) performs exploratory data analysis on the
ASR data to determine optimal parameters for an artificial intelligence (AI) model.
The UI (206) receives a selection from the user of a predefined number of AI
models from available AI models. A forecasting microservice included in the
forecasting module (214) trains the predefined number of AI models selected by
the user based on the optimal parameters in a distributed fashion. The forecasting
module (214) predicts future ASR values using a best performing AI model.
[0094] While the foregoing describes various embodiments of the present
disclosure, other and further embodiments of the present disclosure may be devised without departing from the basic scope thereof. The scope of the present disclosure is determined by the claims that follow. The present disclosure is not limited to the described embodiments, versions or examples, which are included to enable a person having ordinary skill in the art to make and use the present disclosure when combined with information and knowledge available to the person having ordinary skill in the art.
[0095] The present disclosure provides technical advancement related to
Answer Seizure Ratio (ASR) prediction. This advancement addresses the limitations of existing solutions by applying various time series forecasting machine learning algorithms to the ASR data and choose the best predicting algorithm based on a portion of the data. A best performing model is selected to

predict future values, based on which the user (network's team in this case) will take further appropriate steps. This prevents bad customer experience and last minute hassle to scale the system at the affected location in order to cater to increased load.
ADVANTAGES OF THE PRESENT DISCLOSURE
[0096] The present disclosure provides a system for predicting a dip in an
Answer Seizure Ratio (ASR) value beforehand using an Artificial Intelligence (AI) model.
[0097] The present disclosure provides a detailed analysis of probable
causes that result in fall of ASR value.
[0098] The present disclosure provides an auto-estimated forecast of the
ASR value for the next few days in future.
[0099] The present disclosure maintains the ASR value based on the auto-
estimated forecast.
[00100] The present disclosure avoids degradation in customer services in
advance, thereby improving user experience.

We Claim:
1. A method (600) for forecasting Answer Seizure Ratio (ASR) metric in a
telecommunication network, the method comprising:
fetching, by a processing engine (208), past ASR data uploaded by a user through a User Interface (UI) (206);
performing exploratory data analysis, by a forecasting module (214), on the ASR data to determine optimal parameters for an artificial intelligence (AI) model;
receiving selection from the user of na predefined number of AI models from available AI models through the UI (206), wherein a forecasting microservice trains the predefined number of AI models selected by the user based on the optimal parameters in a distributed fashion; and
predicting, by the forecasting module (214), future ASR values using a best performing AI model.
2. The method (600) as claimed in claim 1, further comprising performing, by the processing engine (208), appropriate actions based on the results of the prediction.
3. The method (600) as claimed in claim 1, wherein the forecasting module (214) applies time series forecasting machine learning algorithms selected from a group consisting of ARIMA, LSTM, and Prophet on the predefined number of AI models.
4. The method (600) as claimed in claim 1, further comprising periodically retraining, by a retraining module, the predefined number of AI models as new ASR data becomes available.
5. The method (600) as claimed in claim 1, further comprising receiving, by the forecasting module (214), the past ASR data in a CSV format on the user interface (206).

6. The method (600) as claimed in claim 1, further comprising displaying, by the user interface (206), results of the prediction to the user.
7. A system (108) for forecasting Answer Seizure Ratio (ASR) metric in a telecommunication network, said system (108) comprising:
a processing engine (208) configured to fetch past ASR data uploaded by a user through a User Interface (206);
a forecasting module (214) configured to:
perform exploratory data analysis on the ASR data to
determine optimal parameters for an AI model,
receive selection from the user of a predefined number of
AI models from available AI models, and to train the predefined
number of AI models based on the optimal parameters in a
distributed fashion for faster results, and
predict future ASR values using a best performing AI model from the predefined number of AI models.
8. The system (108) as claimed in claim 7, wherein the processing engine (208) is further configured to perform appropriate actions based on the results of prediction.
9. The system (108) as claimed in claim 7, wherein the forecasting module (214) is configured to apply time series forecasting machine learning algorithms selected from a group consisting of ARIMA, LSTM, and Prophet.
10. The system (108) as claimed in claim 7, further comprising a retraining module configured to periodically retrain the AI model as new ASR data becomes available.

11. The system (108) as claimed in claim 7, wherein the forecasting module (214) is configured to receive the past ASR data in a CSV format on the user interface (206).
12. The system (108) as claimed in claim 7, wherein the user interface (206), displays results of the prediction to the user.
13. A user equipment (UE) (104) communicatively coupled with a network (106), the coupling comprises steps of:
receiving, by the network (106), a connection request from the UE (104);
sending, by the network (106), an acknowledgment of the connection request to the UE (104); and
transmitting a plurality of signals in response to the connection request, wherein the network (106) is configured for performing a method for forecasting Answer Seizure Ratio (ASR) metric in a telecommunication network as claimed in claim 1.