Methods and apparatus for performing an internet protocol (IP) multimedia subsystem (IMS) refresh registration process

Abstract

Disclosed herein is a method for performing an internet protocol (IP) multimedia subsystem (IMS) refresh registration process by a user equipment (UE). The method comprises predicting a time instant when the UE enters a limited service area; determining whether to switch to a new proxy-call session control function (P-CSCF) based on a call status of the UE with a current P-CSCF; initiating the IMS refresh registration process prior to the predicted time instant. The IMS refresh registration process includes triggering a refresh register process request based on determining not to switch to the new P-CSCF, and triggering a new IMS register process request to switch to the new P-CSCF based on determining to switch to the new P-CSCF.

Description

METHODS AND APPARATUS FOR PERFORMING AN INTERNET PROTOCOL (IP) MULTIMEDIA SUBSYSTEM (IMS) REFRESH REGISTRATION PROCESS

[0001] The present disclosure relates to an internet protocol (IP) multimedia subsystem (IMS), and more particularly relates to a method and a system for performing an IMS refresh registration process by a user equipment (UE).

[0002] Internet protocol (IP) multimedia subsystem (IMS) is a standardized architecture to deliver IP multimedia services. There are some long pending problems in IP Multimedia service which cause a bad user experience. A first problem is a voice over fifth generation (Vo5G) or voice over new radio (VoNR) voice over long-term-evolution (VoLTE) that gives a better calling experience. However, there are locations like elevators, tunnels, basements, etc. where new radio signal strength is limited, and therefore, leads to IMS refresh registration failures causing the bad user experience.

[0003] Periodic application-level re-registration is initiated by a user equipment (UE) either to refresh an existing registration or in response to a change in the registration status of the UE. A re-registration procedure can also be initiated when the capabilities of the UE have changed, or an IP connectivity access network (IP-CAN) has changed. The UE should perform IMS re-registration when the IP-CAN used by the UE changes between 3rdgeneration partnership project (3GPP) access and WLAN access.

[0004] The UE initiates a re-registration. For periodic registration, the UE initiates a re-registration before the expiry of the agreed registration timer. To re-register, the UE sends a new REGISTER request. The UE sends the REGISTER information flow to the proxy (Public User Identity, Private User Identity, home network domain name, UE IP address, capability information, Instance Identifier, and GRUU Support Indication).

[0005] Figure 1 illustrates a flowchart depicting the steps of the IMS refresh registration process 100 by a UE, according to a conventional technique.

[0006] The UE sends an initial IMS registration (SIP Register) message to the network to register to the IMS network with an expiry of 'x' seconds. The network responds with a 200 OK message after processing the received IMS registration message. Further, when the negotiated expiry timer of 'x' seconds about to expire, the UE will trigger a refresh register process and send another register request to the network. The network again processes the request and responds with the 200 OK message.

[0007] Additionally, there are certain locations where the VoNR / VoLTE call failures are high. Therefore, when a call failure happens, the device (for example, the UE) switches to a next available proxy-call session control function (P-CSCF) to make a call success. The P-CSCF corresponds to a central entity in an IMS network that is responsible for registration and location management, session control (for example, voice calls, video calls, instant messaging), security (for example, user authentication and authorization), and policy enforcement.

[0008] Furthermore, a gateway general packet radio services support node packet data network gateway (GGSN / P-GW) includes a list of preconfigured addresses of signaling servers, i.e., P-CSCF. This list is provided to mobile soft switches / user equipment (MSs / UEs) on request. The list is preconfigured per access point name (APN). The GGSN / P-GW can deliver a domain name system (DNS) or P-CSCF addresses to the MS / UE when requested by the MS / UE via a public call office (PCO) or a dynamic host configuration protocol (DHCP) procedures using the relevant DHCP options for internet protocol version 4 or 6 (Ipv4 / Ipv6) DNS and session initiation protocol (SIP) servers.

[0009] Figure 2 illustrates a flowchart depicting steps of a P-CSCF selection process 200, according to a conventional technique.

[0010] The UE sends a request for public data network (PDN) connectivity to the network. The network responds with an available P-CSCF address in order after the PDN connection is done. The UE sends a fresh IMS registration request to the 1stP-CSCF. The network again processes the request and responds with a 200 OK message. Thereafter, the IMS registration is completed.

[0011] Figure 3 illustrates an example scenario 300 depicting the UE stuck in no service in a good service region, according to a conventional technique.

[0012] For instance, there are locations like elevators, tunnels, basements, etc., where a network (for example 5G) cannot reach fully leading to Service Blocks and causing the bad user experience. As discussed, the IMS registration performs require periodic refresh registration to keep the UE bind with an IMS Core network. Thus, when a user is within the above-mentioned limited-service regions and the SIP Refresh Register requests are timed out (Re-Register request sent from UE to P-CSCF gets no response for some time), the PLMN to which the UE is currently attached will get blocked for a minimum of 12 min duration.

[0013] Once the PLMN is blocked, the UE starts searching for next available PLMNs only after 12mins. Hence, if there is no other PLMN available during the refresh registration then the UE will stay in "No Service" condition even after the UE is out of the limited service area. This will lead the UE to lose the network coverage even after the UE is out of the no-network area. Because of this PLMN blocking, the UE will not be able to connect to the IMS network and hence will not be able to make use of any of the IMS services (such as, calls, multimedia messaging, etc.).

[0014] As depicted in Figure 3, when the UE enters no service region (for example, the tunnel) and triggers the refresh registration, the corresponding request gets timed out. The UE then tries for a next P-CSCF and again the request gets timed out. After all P-CSCF's request gets timed out, the PLMN will get blocked for a predefined duration (for example, 12mins). Now even if the UE comes out of that no-service region before 12 minutes pass, the UE will still not be able to register to the IMS network (for about 11 min 30 seconds as in the earlier example). So basically, the UE is in the service region, but is still not able to register to the IMS network because PLMN is blocked and has to wait unnecessarily for 12 min.

[0015] Table 1 shows the 3GPP reference of PLMN blocking, according to the prior art.

[0016] TIMER NUM.TIMER VALUESTATECAUSE OF STARTNORMAL STOPON EXPIRYT3502Default 12 mins. Note 15GMM-REGISTEREDAt registration failure and the attempt counter is equal to 5Transmission of REGISTRATION REQUEST messageInitiation of the registration procedure, if still require

[0017] Figure 4 illustrates an example scenario 400 depicting the UE stuck in a limited-service region, according to a conventional technique.

[0018] As mentioned above, the Vo5G (VoNR) or VoLTE provides a better calling experience. However, there are some locations where call failures happen with a first P-CSCF IP (i.e., currently connected P-CSCF), but not with other P-CSCF IPs. One of the reason for such call failure could be high volume of traffic served by 1st PCSCF IP in certain locations or 1stPCSCF IP. Therefore, the first P-CSCF gets down or not able to support selected services (call, , message, real-time transfer (RTT), etc.) In this case, when the user makes the call using the 1stPCSCF IP (order of IP addresses is maintained and won't change) then call failure chances will be higher. However, at the same time if the user tries to call on the 2nd(or 3rd) PCSCF IP then the call may connect successfully.

[0019] Additionally, when the user enters the limited connectivity area (like elevator, tunnel, metro, etc.) that causes IMS refresh registration failure. The failure of the IMS refresh registration leads to network PLMN blocking for a certain period (which is typically 12 minutes) which results in no service for the device. In no service, none of the communication is possible (internet, calls, messages, etc.) is possible with the network. However, when the user returns to the service area there arises a situation when the time is still running and the PLMN is blocked which will cause no service for the user even when the user is in the serviceable area. Thus, there is a need to avoid the PMLN blocking while moving out of the no-service region and selecting the best P-CSCF.

[0020] Therefore, in light of the above-mentioned challenges, a solution is required to overcome the above-mentioned challenges associated with identifying motion dramatizable regions and motion dramatizable modes in a multimedia stream.

[0021] This summary is provided to introduce a selection of concepts in a simplified format that is further described in the detailed description of the invention. This summary is not intended to identify key or essential inventive concepts of the invention, nor is it intended to determine the scope of the invention.

[0022] According to an aspect of the present disclosure, a method for performing an internet protocol (IP) multimedia subsystem (IMS) refresh registration process by a user equipment (UE) is provided. The method may comprise predicting a time instant when the UE enters a limited service area. The method may comprise determining whether to switch to a new proxy-call session control function (P-CSCF) based on a call status of the UE with a current P-CSCF. The method may comprise initiating the IMS refresh registration process prior to the predicted time instant. The IMS refresh registration process may comprise triggering, a refresh register process request based on determining not to switch to the new P-CSCF. The IMS refresh registration process may comprise triggering a new IMS register process request to switch to the new P-CSCF based on determining to the new P-CSCF.

[0023] The time instant when the UE enters the limited service area may be is predicted based on one or more predefined parameters, wherein the one or more predefined parameters comprises at least one of a location of the UE (502), one or more network characteristics, and one or more device characteristics.

[0024] Determining whether to switch to the new P-CSCF based on a current call status may comprises determining, using an Artificial Intelligence (AI) model, that one or more P-CSCFs are available with higher coverage with respect to the current P-CSCF, wherein the AI model is trained based on historical data associated with a set of predefined call parameters corresponding to a plurality of P-CSCFs at at least one given location.

[0025] Triggering the new IMS register process request to switch to the new P-CSCF may comprises triggering a fresh IMS registration request with the new P-CSCF with an expiry header set to a predefined time duration which is greater than a refresh registration duration when the call status is bad. Triggering the new IMS register process request to switch to the new P-CSCF may comprises triggering a refresh register with the current P-CSCF with an expiry header set to the predefined time duration greater than the refresh registration duration.

[0026] The set of predefined call parameters may comprise at least one of call drop rates, real-time transport protocol (RTP) packet drop rates, and call setup failure errors, corresponding to a given location.

[0027] The method may comprise predicting a time duration for which the UE (502) is in the limited service area. The method may comprise updating the refresh registration duration based at least on the predicted time duration.

[0028] The limited service area prediction by the UE may be indicative of input values received, including a speed of a device, direction in which the device is heading, a tilt angle, and a signal frequency.

[0029] Determining whether to switch to the new P-CSCF based on the current call status may comprise predicting, using an AI model, a reference signal received power (RSRP) value to assess quality of the current P-CSCF coupled to the UE (502), wherein the AI model is trained by feeding data parameters indicative of distance between an evolved node-B (eNB) and the UE, an angle of transmitting a signal from the eNB, a frequency band, a height ratio between the eNB and the UE.

[0030] The method may comprise transmitting a refresh expiry timer to a network for further registrations.

[0031] The method may comprise updating, based on receiving a refresh registration request, records to prevent a Public Land Mobile Network (PLMN) blocking during the limited service area of the UE.

[0032] The method may comprise performing an early refresh registration based on predicting that the UE (502) is heading towards a no service region to avoid PLMN blocking.

[0033] The refresh registration request is triggered based on a predicted movement trajectory towards the limited service area.

[0034] According to an aspect of the present disclosure, a user equipment (UE) for performing an internet protocol (IP) multimedia subsystem (IMS) refresh registration process is provided. The UE may comprise memory storing instructions; and at least one processor communicatively coupled with the memory. The instructions, when executed by the at least one processor, may cause the UE to predict a time instant when the UE enters a limited service area. The instructions, when executed by the at least one processor, may cause the UE to determine whether to switch to a new proxy-call session control function (P-CSCF) based on a call status of the UE with a current P-CSCF. The instructions, when executed by the at least one processor, may cause the UE to initiate the IMS refresh registration process prior to the predicted time instant, The IMS refresh registration process may comprise triggering a refresh register process request based on determining not to switch to the new P-CSCF. The IMS refresh registration process may comprise triggering a new IMS register process request to switch to the new P-CSCF based on determining to switch to the new P-CSCF.

[0035] According to an aspect of the present disclosure, a non-transitory computer readable storage medium storing instructions is provided. The instructions, when executed by at least one processor of a user equipment (UE), may cause the UE (502) to predict a time instant when the UE enters a limited service area. The instructions, when executed by the at least one processor, may cause the UE to determine whether to switch to a new proxy-call session control function (P-CSCF) based on a call status of the UE with a current P-CSCF. The instructions, when executed by the at least one processor, may cause the UE to initiate the IMS refresh registration process prior to the predicted time instant, The IMS refresh registration process may comprise triggering a refresh register process request based on determining not to switch to the new P-CSCF. The IMS refresh registration process may comprise triggering a new IMS register process request to switch to the new P-CSCF based on determining to switch to the new P-CSCF.

[0036] To further clarify the advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which is illustrated in the appended drawing. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting its scope. The invention will be described and explained with additional specificity and detail with the accompanying drawings.

[0037] These and other features, aspects, and advantages of the present invention will become better understood when the following detailed description is read with reference to the accompanying drawings in which like characters represent like parts throughout the drawings, wherein:

[0038] Figure 1 illustrates a flowchart depicting steps of an IMS refresh registration process by a UE, according to a conventional technique;

[0039] Figure 2 illustrates a flowchart depicting steps of a P-CSCF selection process, according to a conventional technique;

[0040] Figure 3 illustrates an example scenario depicting the UE stuck in no service in a good service region, according to a conventional technique;

[0041] Figure 4 illustrates an example scenario depicting the UE stuck in a limited-service region, according to a conventional technique;

[0042] Figure 5 illustrates a schematic block diagram of a user equipment for performing an internet protocol (IP) multimedia subsystem (IMS) refresh registration process, according to one or more embodiments of the present disclosure;

[0043] Figure 6 illustrates a sequence flow of the IMS refresh registration process by the UE, according to one or more embodiments of the present disclosure;

[0044] Figure 7 illustrates a sequence flow of the IMS refresh registration process by the UE to avoid the PLMN blocking in limited-service case, according to one or more embodiments of the present disclosure;

[0045] Figure 8 illustrates an exemplary scenario depicting the IMS refresh registration process when the UE is moving towards the limited-service case, according to one or more embodiments of the present disclosure;

[0046] Figure 9 illustrates a flowchart depicting process steps of artificial intelligence (AI) model activation with IMS refresh registration process, according to one or more embodiments of the present disclosure;

[0047] Figure 10 illustrates another exemplary scenario depicting the IMS refresh registration process when the UE is moving towards and out of the limited-service case, according to one or more embodiments of the present disclosure;

[0048] Figure 11 illustrates a flowchart depicting process steps of the IMS refresh registration process to avoid PLMN blocking, according to one or more embodiments of the present disclosure;

[0049] Figure 12 illustrates an exemplary scenario depicting an internet protocol (IP) server selection for best proxy-call session control function (P-CSCF) when the UE is moving towards the limited-service case, according to one or more embodiments of the present disclosure;

[0050] Figure 13 illustrates a flowchart depicting process steps of the server selection process, i.e., P-CSCF when the UE is moving towards the limited-service case, according to one or more embodiments of the present disclosure;

[0051] Figure 14 illustrates a sequence flow of the server selection process i.e., P-CSCF when the UE is moving towards the limited-service case, according to one or more embodiments of the present disclosure;

[0052] Figure 15 illustrates a schematic workflow of the AI model to predict good or bad coverage area, according to one or more embodiments of the present disclosure;

[0053] Figure 16 illustrates a schematic workflow depicting an implementation of the AI model to avoid the PLMN blocking and the server selection process in limited-service case, according to one or more embodiments of the present disclosure;

[0054] Figure 17 illustrates an exemplary scenario depicting the implementation of the AI model, according to one or more embodiments of the present disclosure;

[0055] Figure 18 illustrates a flowchart depicting steps of dataset preparation by the AI model, according to one or more embodiments of the present disclosure;

[0056] Figure 19 illustrates a detailed schematic workflow depicting the implementation of the AI model to avoid the PLMN blocking and the server selection process in limited-service case, according to one or more embodiments of the present disclosure;

[0057] Figure 20 illustrates a basic architecture of a neural network for training the AI model, according to one or more embodiments of the present disclosure;

[0058] Figure 21 illustrates another detailed architecture of the neural network for training the AI model, according to one or more embodiments of the present disclosure;

[0059] Figure 22 illustrates an exemplary scenario depicting the user entering a metro tunnel and facing limited connectivity, according to one or more embodiments of the present disclosure; and

[0060] FIG. 23 illustrates a flowchart depicting a method for performing the IMS refresh registration process by the UE, according to one or more embodiments of the present disclosure.

[0061] Further, skilled artisans will appreciate those elements in the drawings are illustrated for simplicity and may not have necessarily been drawn to scale. For example, the flow charts illustrate the method in terms of the most prominent steps involved to help and improve understanding of aspects of the present disclosure. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the drawings by conventional symbols, and the drawings may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the drawings with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.

[0062] It should be understood at the outset that although illustrative implementations of the embodiments of the present disclosure are illustrated below, the present invention may be implemented using any number of techniques, whether currently known or in existence. The present disclosure should in no way be limited to the illustrative implementations, drawings, and techniques illustrated below, including the exemplary design and implementation illustrated and described herein, but may be modified within the scope of the appended claims along with their full scope of equivalents.

[0063] The term "some", "one or more embodiment", "one or more example embodiments", as used herein is defined as "one, or more than one, or all." Accordingly, the terms "one," "more than one," "more than one, but not all" or "all" would all fall under the definition of "some." The term "some embodiments" may refer to one embodiment, several embodiments, or to all embodiments. Accordingly, the term "some embodiments" is defined as meaning "one embodiment, or more than one embodiment, or all embodiments."

[0064] The terminology and structure employed herein are for describing, teaching, and illuminating some embodiments and their specific features and elements and do not limit, restrict, or reduce the spirit and scope of the claims or their equivalents.

[0065] More specifically, any terms used herein such as but not limited to "includes," "comprises", "has", "have", and grammatical variants thereof do not specify an exact limitation or restriction and certainly do not exclude the possible addition of one or more features or elements, unless otherwise stated, and must not be taken to exclude the possible removal of one or more of the listed features and elements, unless otherwise stated with the limiting language "must comprise" or "needs to include."

[0066] Whether or not a certain feature or element was limited to being used only once, either way, it may still be referred to as "one or more features", "one or more elements", "at least one feature" or "at least one element." Furthermore, the use of the terms "one or more" or "at least one" feature or element does not preclude there being none of that feature or element unless otherwise specified by limiting language such as "there needs to be one or more ..." or "one or more element is required."

[0067] The terms "A or B," "at least one of A or / and B," or "one or more of A or / and B" used in the various embodiments of the present disclosure include any and all combinations of words enumerated with it. For example, "A or B," "at least one of A and B," or "at least one of A or B" means (1) including at least one A, (2) including at least one B, or (3) including both at least one A and at least one B.

[0068] Although the terms such as "first" and "second" used in various embodiments of the present disclosure may modify various elements of various embodiments, these terms do not limit the corresponding elements. For example, these terms do not limit an order and / or importance of the corresponding elements. These terms may be used for the purpose of distinguishing one element from another element. For example, a first user device and a second user device all indicate user devices and may indicate different user devices. For example, a first element may be named a second element without departing from the scope of right of various embodiments of the present disclosure, and similarly, a second element may be named a first element.

[0069] The expression "configured to (or set to)" used in various embodiments of the present disclosure may be replaced with "suitable for," "having the capacity to," "designed to," "adapted to," "made to," or "capable of" according to the situation. The term "configured to (set to)" does not necessarily mean "specifically designed to" as hardware. Instead, the expression "apparatus configured to . . . " may mean that the apparatus is "capable of . . . " along with other devices or parts in a certain situation. For example, "a processor configured to (set to) perform A, B, and C" may be a dedicated processor, for example, an embedded processor, for performing a corresponding operation, or a generic-purpose processor, for example, a Central Processing Unit (CPU) or an application processor (AP), capable of performing a corresponding operation by executing one or more software programs stored in a memory device.

[0070] A term "module" used in the present document may imply a unit including, for example, one of hardware, software, and firmware or a combination of two or more of them. The "module" may be interchangeably used with a term such as a unit, a logic, a logical block, a component, a circuit, and the like. The "module" may be a minimum unit of an integrally constituted component or may be a part thereof. The "module" may be a minimum unit for performing one or more functions or may be a part thereof. The "module" may be mechanically or electrically implemented. For example, the "module" of the present disclosure may include at least one of an Application-Specific Integrated Circuit (ASIC) chip, a Field-Programmable Gate Arrays (FPGAs), and a programmable-logic device, which are known or will be developed, and which perform certain operations.

[0071] Unless otherwise defined, all terms, and especially any technical and / or scientific terms, used herein may be taken to have the same meaning as commonly understood by one having ordinary skill in the art.

[0072] The embodiments herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting embodiments that are illustrated in the accompanying drawings and detailed in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein.

[0073] As is traditional in the field, embodiments may be described and illustrated in terms of modules that carry out a described function or functions. These modules, which may be referred to herein as units or blocks or the like, or may include blocks or units, are physically implemented by analog or digital circuits such as logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive electronic components, active electronic components, optical components, hardwired circuits, or the like, and may optionally be driven by firmware and software. The circuits may, for example, be embodied in one or more semiconductor chips, or on substrate supports such as printed circuit boards and the like. The circuits constituting a block may be implemented by dedicated hardware, by a processor (e.g., one or more programmed microprocessors and associated circuitry), or by a combination of dedicated hardware to perform some functions of the block and a processor to perform other functions of the block. Each block of the embodiments may be physically separated into two or more interacting and discrete blocks without departing from the scope of the invention. Likewise, the blocks of the embodiments may be physically combined into more complex blocks without departing from the scope of the invention.

[0074] The accompanying drawings are used to help easily understand various technical features and it should be understood that the embodiments presented herein are not limited by the accompanying drawings. As such, the present disclosure should be construed to extend to any alterations, equivalents, and substitutes in addition to those which are particularly set out in the accompanying drawings. Although the terms first, second, third, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are generally only used to distinguish one element from another.

[0075] Embodiments of the present disclosure will be described below in detail with reference to the accompanying drawings.

[0076] The objective of the present disclosure is to provide a method and a system for performing an internet protocol (IP) multimedia subsystem (IMS) refresh registration process by a user equipment (UE). The present disclosure proposes a solution for the IMS services, i.e., avoiding public land mobile network (PLMN) blocking and best proxy-call session control function (P-CSCF) selection. The present discourse employs an artificial intelligence (AI) model to predict low coverage areas based on user movement and performs early refresh register even before entering those areas to avoid PLMN blocking. Further, the present disclosure modifies, by the application of the AI model, the refresh registration time interval, which is 30 minutes generally, to 'x' minutes which is greater than a predicted time of the no service duration. For instance, a user is moving in the direction of a tunnel, i.e., the low-coverage area. When the user is inside a tunnel and the UE triggers refresh registration, since the UE is under the low service area, the refresh register will get timed out and the chances of PLMN blocking is higher. Therefore, to avoid this issue, the AI model predicts that a low service area is approaching when the user is moving toward the tunnel. The AI model notifies the UE to trigger an early refresh register even before entering the tunnel so that refresh registration can be successful. Also, the AI model predicts the duration of no service area, so that in refresh registration, the expiry time is set as some 'x' higher than the duration of no service.

[0077] The present disclosure also employs the AI model to predict as per user movement and historical data for the selection of the best P-CSCF. The AI model may predict when to switch to other P-CSCFs to avoid any call failures or call drops. For instance, as mentioned in the above example, now to further improve user experience, based on the AI model prediction of low service area, the AI model also checks whether the current P-CSCF has higher chances of call fail / call drops. The AI model then switches to the next P-CSCF and performs fresh IMS registration instead of refresh registration so to have less chance of call fail / call drops.

[0078] Figure 5 illustrates a block diagram depicting a schematic workflow of a user equipment (UE) 502 for performing an internet protocol (IP) multimedia subsystem (IMS) refresh registration process, according to one or more embodiments of the present disclosure.

[0079] In an embodiment, the UE 502 may be communicatively coupled to a server 500 via a network 522. The UE 502, the server 500 and the network 522 may be referred to as a system. The UE 502 may be configured to perform the IMS refresh registration process. The UE 502 may include a processor 504, a display 506, one or more sensors 510 including a position sensor 508, and a memory 512, which may belong to the UE 502 and may form a part of the UE 502. In an embodiment, the position sensor 508 may be installed on the UE 502, e.g., smart phone, tablet, laptop, computer, or other smart electronic devices that the user may be carrying. In an exemplary embodiment, the sensors 510 may correspond to as one or more sensors, such as a gyroscope sensor, a proximity sensor, and other sensors that may detect an orientation / direction of the UE 502.

[0080] The memory 512 may include an operating system 514, and a database 516 to store data. Further, the UE 502 may include one or more modules 518 that may be configured to perform the steps of the present disclosure using the data stored in the database 516. In an embodiment, each of the modules 518 may be implemented as a hardware unit, a software unit, or a combination thereof. The modules 518 may be outside the memory 512, within the memory 512, or a combination thereof. As illustrated in Figure 5, the modules 518 may include an IMS module 524, an Artificial Intelligence (AI) module 526, and a data collection module 528. The IMS module 524 may include an IMS framework 530 and an IMS stack 532, as shown in Figure 6. The operation of the IMS module 524, the AI module 526, the data collection module 528 will be described in the following detailed description.

[0081] The processor 504 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, the processor 504 may be configured to fetch and execute computer-readable instructions and data stored in the memory 512 and / or the modules 518. At this time, the processor 504 may be a general-purpose processor, such as a central processing unit (CPU), an application processor (AP), or the like, and an AI-dedicated processor such as a neural processing unit (NPU). The processor 504 may control the processing of input data in accordance with a predefined operating rule or artificial intelligence (AI) model stored in the non-volatile memory and the volatile memory, i.e., the memory 512. The predefined operating rule or artificial intelligence model is provided through training or learning. Further, the processor 504 may be operatively coupled to each of the memory, the I / O Interface. The processor 504 may be configured to process, execute, or perform a plurality of operations described herein.

[0082] The memory 512 may include any non-transitory 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 512 is communicatively coupled with the processor to store processing instructions for completing the process. Further, the memory 512 may include the operating system 514 for performing one or more tasks of the system, as performed by a generic operating system 514 in a computing domain. The memory 512 is operable to store instructions executable by the processor 504.

[0083] In some embodiments, the UE 502 may include a set of instructions that can be executed to cause the processor 504 of the UE 502 to perform any one or more of the methods disclosed. The UE 502 may operate as a standalone device or may be connected, e.g., using a network, to other computer systems or peripheral devices.

[0084] In a networked deployment, the UE 502 may operate in the capacity of a server or as a client user computer in a server-client user network environment, or as a peer system in a peer-to-peer (or distributed) network environment. The UE 502 can also be implemented as or incorporated across various devices, such as a personal computer (PC), a tablet PC, a personal digital assistant (PDA), a mobile device, a palmtop computer, a laptop computer, a desktop computer, a communications device, a wireless telephone, a land-line telephone, a web appliance, a network router, switch or bridge, or any other machine capable of executing a set of instructions (sequential or otherwise) that specify actions to be taken by that machine. Further, while a single UE 502 is illustrated, the term "system" shall also be taken to include any collection of systems or sub-systems that individually or jointly execute a set, or multiple sets, of instructions to perform one or more computer functions.

[0085] As discussed, the UE 502 may include the processor 504, e.g., a central processing unit (CPU), a graphics processing unit (GPU), or both. The processor 504 may be a component in a variety of systems. For example, the processor 504 may be part of a standard personal computer or a workstation. The processor 504 may be one or more general processors, digital signal processors, application-specific integrated circuits, field-programmable gate arrays, servers, networks, digital circuits, analog circuits, combinations thereof, or other now known or later developed devices for analyzing and processing data. The processor 504 may implement a software program, such as code generated manually (i.e., programmed).

[0086] As mentioned above, the UE 502 may include the memory 512, such as a memory 512 that can communicate via a bus. The memory 512 may include, but is not limited to, computer-readable storage media such as various types of volatile and non-volatile storage media, including, but not limited to, random access memory, read-only memory, programmable read-only memory, electrically programmable read-only memory, electrically erasable read-only memory, flash memory, magnetic tape or disk, optical media and the like. In one example, memory 512 includes a cache or random-access memory for the processor 504. In alternative examples, the memory 512 is separate from the processor 504, such as a cache memory of a processor, the system memory, or other memory. The memory 512 may be an external storage device or database for storing data. The memory 512 is operable to store instructions 506 executable by the processor 504. The functions, acts or tasks illustrated in the figures or described may be performed by the programmed processor 504 for executing the instructions 506 stored in the memory 512. The functions, acts or tasks are independent of the particular type of instructions set, storage media, processor or processing strategy and may be performed by software, hardware, integrated circuits, firmware, micro-code and the like, operating alone or in combination. Likewise, processing strategies may include multiprocessing, multitasking, parallel processing and the like.

[0087] As shown, the UE 502 may or may not further include the display 506, such as a liquid crystal display (LCD), an organic light-emitting diode (OLED), a flat panel display, a solid-state display, a cathode ray tube (CRT), a projector, a printer or other now known or later developed display device for outputting determined information. The display 506 may act as an interface for the user to see the functioning of the processor 504, or specifically as an interface with the software stored in the memory 512.

[0088] The present invention contemplates a computer-readable medium that includes memory 512 having executable instructions responsive to a propagated signal so that a device connected to the network 522 can communicate voice, video, audio, images, or any other data over the network 522. Further, the instructions 512 may be transmitted or received over the network 522 via the communication interface or port 120. The communication interface 120 may be a part of the processor 504 or maybe a separate component. The communication interface 120 may be created in software or maybe a physical connection in hardware. The communication interface 120 may be configured to connect with the network 522, external media, the display 514, or any other components in UE 502, or combinations thereof. The connection with the network 522 may be a physical connection, such as a wired Ethernet connection or may be established wirelessly as discussed later. Likewise, the additional connections with other components of the UE 502 may be physical or may be established wirelessly.

[0089] The network 522 may include wired networks, wireless networks, Ethernet AVB networks, or combinations thereof. The wireless network may be a cellular telephone network, an 802.11, 802.16, 802.20, 802.1Q or WiMax network. Further, the network 522 may be a public network, such as the Internet, a private network, such as an intranet, or combinations thereof, and may utilize a variety of networking protocols now available or later developed including, but not limited to, TCP / IP based networking protocols. The UE 502 may not be limited to operation with any particular standards and protocols. For example, standards for Internet and other packet-switched network transmissions (e.g., TCP / IP, UDP / IP, HTML, and HTTP) may be used.

[0090] The processor 504 may be configured to predict a time instant (T) when the UE 502 enters a limited coverage area (e.g. limited service area). Further, the processor 504 may be configured to determine whether to switch to a new proxy-call session control function (P-CSCF) based at least on a call status of the UE 502 with a current P-CSCF. Further, the processor 504 may be configured to initiate the IMS refresh registration process prior to the predicted time instant (T). Further, the processor 504, by the IMS refresh registration process, may be configured to trigger a refresh register process request based on determining that there is no need to switch to the new P-CSCF. Further, the processor 504, by the IMS refresh registration process, may be configured to trigger a new IMS register process request to switch to the new P-CSCF based on determining that there is a need to switch to the new P-CSCF. The predicting the time instant when the UE 502 enters the limited coverage area is based at least on one or more predefined parameters. Examples of the predefined parameters may include, but are not limited to, a location of the UE 502, one or more network characteristics, and one or more device characteristics.

[0091] In an embodiment, the processor 504, when the determining whether to switch to the new P-CSCF based on a current call status, may be configured to determine, by the AI module 526, that one or more P-CSCFs are available with high coverage as compared to the current P-CSCF. The AI module 526 may also be referred to as an AI model 526. The AI model 526 trained based on historical data associated with a set of predefined call parameters corresponding to a plurality of P-CSCF at a given location. The set of predefined call parameters comprises at least one of, call drop rates, real-time transport protocol (RTP) packet drop rates, and call setup failure errors, corresponding to a given location.

[0092] In an embodiment, the processor 504, when the triggering the new IMS register process request to switch to the new P-CSCF, may be configured to trigger a fresh IMS registration request with the new P-CSCF with an expiry header set to a predefined time duration which is greater than a refresh registration duration when the call status is bad. Further, the processor 508, when the triggering the new IMS register process request to switch to the new P-CSCF, may be configured to trigger a refresh register with the current P-CSCF with an expiry header set to the predefined time duration greater than the refresh registration duration.

[0093] In an embodiment, the processor 504 may be configured to predict a time duration for which the UE 502 is in the limited coverage area and updating the refresh registration duration based at least on the predicted time duration. The limited coverage area prediction by the UE 502 is indicative of input values received, including the speed of a device, direction in which the device is heading, a tilt angle, and a signal frequency.

[0094] In an embodiment, the processor 504 when determining whether to switch to a different P-CSCF based on the current call status may be configured to predict, by the AI model, a reference signal received power (RSRP) value to assess quality of the current P-CSCF coupled to the UE 502. The AI model 526 is trained by feeding data parameters indicative of distance between an evolved node-B (eNB) and the UE 502, an angle of transmitting a signal from the eNB, a frequency band, a height ratio between the eNB and the UE 502.

[0095] In an embodiment, the processor 504 may be configured to transmit a refresh expiry timer to the network for further registrations. In an embodiment, the processor 504 may be configured to update, based on received the refresh registration request, records to prevent a Public Land Mobile Network (PLMN) blocking during the limited coverage area of the UE 502. In an embodiment, the processor 504 may be configured to perform an early refresh registration based on the prediction that the UE 502 is heading towards a no service region to avoid the PLMN blocking. In an embodiment, the processor 504 may be configured to trigger the refresh registration request based on a predicted movement trajectory towards the limited coverage area.

[0096] Figure 6 illustrates a sequence flow 600 of an IMS refresh registration process by the UE, according to one or more embodiments of the present disclosure.

[0097] In an embodiment, the IMS module 524 may be configured to perform the IMS refresh registration on the UE 502 by transmitting and receiving predictions from the AI model 526. The IMS module 524 may include the IMS framework 530 communicatively coupled to the AI model 526, and the IMS stack 532 coupled to the network 522.

[0098] At step 602, the AI model 526 may receive user's input, e.g., height, distance of the UE 502 from evolved node B (eNB), tilt angle etc, to predict limited service. At step 604, the AI model 526 communicates with an IMS framework 530 and the AI model 526 transmits prediction for signal strength to the IMS framework 530.

[0099] At step 606, the AI model 526 transmits predicting duration of expected low coverage, e.g., 'y' seconds / minutes / hours to the IMS framework 530. Further, at step 608, the AI model 526 may transmit check for call status to the IMS framework 530. In one case, at step 610, the UE 502 performs the check for call status and if call status is bad, the IMS model 524 is configured to trigger a fresh IMS registration with a different P-CSCF.

[0100] At step 612, the IMS stack 532 may be configured to transmit the IMS register with refresh duration of 'x' greater than 'y' to the network 522. At step 614, the network 522 responds with SIP 200 OK.

[0101] In another case, at step 616, the UE 502 performs the check for call status and if call status is good, the IMS model 524 is configured to trigger a refresh registration with the same P-CSCF. At step 618, the IMS stack 532 may be configured to transmit refresh register with refresh duration 'x' greater than 'y' to the network. At step 620, the network 522 responds with SIP 200 OK, i.e., the refresh registration is successful.

[0102] In an embodiment, the AI model 526 may take input from a cloud storage database which may be continuously storing data of the UE's 502 location information, e.g., a distance from the eNB, a ratio of height of device to that height of the eNB from an access service license (ASL), a tilt angle etc. Further, the AI model 526 may detect low coverage area based on input values, i.e., stored on the cloud storage database by predicting reference signal received power (RSRP) values. The AI model 526 may also predict the duration for which the UE 502 may be in low service area as 'y'.

[0103] As discussed above, the AI model 526 may check for call status for decision of P-CSCF switching. It may be noted that call status means the overall chance / probability for call drop / setup failure in a given location for current P-CSCF. The AI model 526 may look into historical data for call drop rate, real-time packet (RTP) drop rate, call setup failure rate for current P-CSCF in given location. In a case, when the AI model 526 finds other P-CSCF with better call stats, then call status for current P-CSCF may be declared as bad otherwise good.

[0104] In an embodiment, the UE 502 does initial IMS registration when the UE 502 may be first booted up to connect to the network 522 or in case of any RAT change (NR, LTE, VoWiFi). In an embodiment, the refresh registration may be done periodically (generally ~30 min) before expiry to update UE's 502 registration status.

[0105] Figure 7 illustrates a sequence flow 700 of the IMS refresh registration process on the UE 502 to avoid the PLMN blocking in limited-service case, according to one or more embodiments of the present disclosure.

[0106] The UE 502 may be communicatively coupled with the server or network 522. The UE 502 may transmit initial register request to the network 522. The network 522 responds with 200 OK. In an embodiment, the refresh register may be triggered here only after the AI model 526 predicts no service region ahead. The AI model 526 may predict that no service area is approaching based on input values (D3, HR, tilt angle, frequency etc.). Further, after getting this indication from the AI model 526, the IMS module 524 may be configured to trigger the refresh register prior to entering in no service area. After, the refresh register is successful and before entering in No service area, the PLMN blocking will be avoided.

[0107] Further, once the UE 502 comes out of no service area, the UE 502 may have all IMS services registered and hence can make calls or any other service.

[0108] Figure 8 illustrates an exemplary scenario 800 depicting the IMS refresh registration process when the UE 502 is moving towards the limited-service case, according to one or more embodiments of the present disclosure.

[0109] In an exemplary embodiment, when UE 502 is moving in the direction of tunnel, i.e., no service region, the AI model 526 may predict that there is no service area ahead and indicates the IMS module 524 to trigger early refresh register to avoid the PLMN blocking in no service area. Further, when the UE 502 comes out of the no service area to a service area, the PLMN may not block the UE 502.

[0110] Figure 9 illustrates a flowchart 900 depicting process steps of the AI model 526 activation with IMS refresh registration process, according to one or more embodiments of the present disclosure.

[0111] The AI model 526 may be configured to be installed on the UE 502 to predict low coverage area and avoid block of the UE 502 from the PLMN. In an embodiment, the AI model 526 may be automatically activated when a signal strength of the UE 502 is below a threshold, i.e., 75% and when the UE 502 comes in motion, i.e., the user is moving, or any call failure / call drop occurs.

[0112] At step 902, the IMS service is booted up when the signal strength of the UE 502 goes below the threshold, i.e., 75%. When the UE's position is static or when signal strength is not dropping below 75%, the AI model 526 may not get activated. This will help in saving unnecessary power consumption by the AI model 526.

[0113] At step 904, the AI model 526 may be configured to detect motion / call failure / call drop of the UE 502. In one case, the UE is static and no motion or call failure or call drop is detected, the AI model 526 will be redirected back to step 904 to continuously detect status of the UE, i.e., the UE is in motion and the signal strength goes below 75% and call failure / call drop is detected. In another case, the UE 502 is in motion or call failure or call drop is detected, the AI model 526 may proceed to step 906, to start predicting the RSRP values for 100 meters in all direction.

[0114] At step 908, the AI model 526 may determine whether the signal strength is good. In one case, the AI model 526 may predict that the signal strength is good, then the AI model 526 may keep on checking for next 100 m. In other case, when the predicted signal strength is bad, the AI model 526 may proceed further to notify IMS module 524 to trigger early Refresh Register, at step 910.

[0115] Figure 10 illustrates another exemplary scenario 1000 depicting the IMS refresh registration process when the UE 502 is moving towards and out of the limited-service case, according to one or more embodiments of the present disclosure.

[0116] The UE 502 may be configured to dynamically calculate a refresh duration when the user is moving towards the low service or no service area. In an embodiment, the refresh duration may be negotiated during refresh registration process, e.g., with the normal duration chances of another register expiry inside limited connectivity region is higher, so the refresh duration which is higher than the expected duration of limited / low connectivity is selected. The AI model 526 predicts the duration of the limited connectivity based on the previous history in the given location, i.e., when the user is going into limited connectivity region for 'y' seconds, then refresh duration may be some 'x' which is higher than 'y', so that chances of triggering another refresh register inside limited connectivity region is less. Further, determining this 'x' may be based on historical data, the AI model 526 may be trained on historical data and therefore, the AI model 526 may select / choose 'x'.

[0117] Figure 11 illustrates a flowchart 1100 depicting process steps of the IMS refresh registration process to avoid PLMN blocking, according to one or more embodiments of the present disclosure. As discussed in conjunction with the flowchart 900, the AI model 526 may be activated based on the signal strength of the UE 502 and the other parameters.

[0118] The steps 902 to 908 as discussed above in conjunction with Figure 10 are same for the flowchart 1200, At step 908, when the AI model 526 detects that the signal strength of the UE 502 is not good. The AI model 526 may proceed further to have limited connectivity duration prediction, e.g., 'y', at step 1102. In an example, when the predicted signal strength is bad, the AI model 526 may then predict the duration for which the UE 502 may be in limited coverage area, based on that refresh register may get triggered with refresh duration higher than predicted limited coverage duration, e.g., 'x' > 'y' at step 1104.

[0119] Figure 12 illustrates an exemplary scenario 1200 depicting an internet protocol (IP) server selection for best P-CSCF when the UE 502 is moving towards the limited-service case, according to one or more embodiments of the present disclosure.

[0120] The best PCSCF or IP server may be selected when the AI model 526 detects limited connectivity and initial registration to a newly selected IP is done. In an embodiment, the UE 502 may be generally provided with more than one addresses by an operator, i.e., the network 522. However, switching between IP addresses happens only when the failure is encountered.

[0121] The UE 502 is currently on call and moving in the direction of low service area. The AI model 526 may detect the motion and predict that current P-CSCF has higher call drop rates in the region approaching, based on a 100 m prediction. The AI model 526 may indicate the IMS module 524 about the prediction and the IMS module 524 may do a fresh IMS registration with 2ndP-CSCF in the back end. In this way, the chances of better call quality experience may be improved.

[0122] Figure 13 illustrates a flowchart 1300 depicting process steps of the server selection process, i.e., P-CSCF when the UE 502 is moving towards the limited-service case, according to one or more embodiments of the present disclosure. Figure 14 is described in conjunction with Figures 10-13.

[0123] The steps 902 to 908 of Figure 9 as discussed above in conjunction with Figure 10 are same for the flowchart 1300. For the sake of brevity, the when the AI model 526 detects that the signal strength of the UE 502 is not good. The AI model 526 may proceed further to step 1302 to determine whether P-CSCF switching is required. In an embodiment, the AI model 526 may check for call status of current P-CSCF to determine whether the P-CSCF switching is needed or not. In one case, the AI model 526 determines that the P-CSCF switching is needed, then the AI model 526 may proceed to step 1304 to trigger an initial IMS registration with best P-CSCF or register with the best P-CSCF. In another case, the AI model 526 determines that the P-CSCF switching is not needed, then the AI model 526 may proceed to step 1306 to trigger refresh registration with same P-CSCF or refresh register with the same P-CSCF.

[0124] Figure 14 illustrates a sequence flow 1400 of the server selection process i.e., P-CSCF when the UE 502 is moving towards the limited-service case, according to one or more embodiments of the present disclosure.

[0125] The UE 502 may be communicatively coupled with the server or network 522. The UE 502 may transmit the initial register with the 1stP-CSCF to the network 522. The network 522 responds to the UE 502 with 200 OK. The AI model 526 may predict that no service area is approaching based on input values (D3, HR, tilt angle, frequency etc.). Further, the AI model 526 may check whether there may be a need of P-CSCF switching based on previous data. In this case, the AI model 526 may notify the IMS module 524 to switch P-CSCF as current P-CSCF has bad call quality experience. The UE 502 may transmit a new fresh IMS registration may be triggered with best P-CSCF to the network 522. The network 522 responds with 200 OK to the UE 502. The UE 502 may be registered with best P-CSCF with better overall call quality experience.

[0126] Figure 15 illustrates a schematic workflow of the AI model 526 to predict good or bad coverage area on the UE 502, according to one or more embodiments of the present disclosure.

[0127] The AI model 526 may be configured to predict the low network or coverage area for the UE 502 to avoid PLMN blocking and process best P-CSCF, i.e., IP server for the UE 502. The AI model 526 may be trained on one or more parameters. The one or more parameters may include the tilt angle, the height ratio of the eNB and the UE 502, a three-dimensional (3D) distance between the eNB and the UE 502, frequency band and the signal propagation path between the eNB and the UE 502. The AI mode 526 may also be referred to as an IMS AI Model or low coverage detector AI that is trained to predict GOOD or BAD coverage area for the UE 502.

[0128] In some embodiments, different machine learning (ML) models, such as, support vector machine, regression trees, ensemble trees, etc., may be used for training on this dataset. For the UE 502 location, the AI model 526 may consider the one or more parameters and predict the RSRP values which may evaluate the quality of cellular coverage of the UE 502 at that location. In an embodiment, for validation of the AI model 526 performance, Root Mean Square Error (RMSE) may be used to compare the predicted value of RSRP and actual value of RSRP.

[0129] Figure 16 illustrates a schematic workflow 1600 depicting an implementation of the AI model 526 to avoid the PLMN blocking and the server, i.e., P-CSCF selection process in limited-service case, according to one or more embodiments of the present disclosure.

[0130] The network 522 may be communicatively coupled to the IMS module 524 via a modem 1602. The IMS module 524 may, in one embodiment, include the AI model 526, a call module 1604, an IMS registration module 1606. The IMS module 524 may be communicatively coupled to a cloud storage 1608. The cloud storage 1608 may contain a dataset 1610 for training the AI model 526. The IMS registration module 1606 may be configured to switch P-CSCF refresh register.

[0131] In an embodiment, the UE 502 may periodically retrieve data required for training of the AI model 526 from the cloud storage 1608. The AI model 526 may be trained using cloud data stored periodically. Further, retrained AI model may be referred to as an updatable IMS back to IMS module 524. The IMS module 524 may include the AI model 526, in one example. The AI model 526 may take user information, i.e., location, RTP data stats etc. Further, the AI model 526 may be configured to make prediction about low / no service region based on an updated dataset on which the AI model 526 is trained, i.e., based on the user information.

[0132] The AI model 526 may notify the IMS Registration Module 1606 of upcoming low / no service area. Based on the prediction, the IMS module 524 may trigger early refresh registration or P-CSCF switching. Further, the IMS module 524 may then interact with the modem 1602 to send Registration request via SIP messages. The modem 1602 may send the SIP registration packets received from the IMS module 524 to the network 522. The network 522 may then respond back to the modem 1602, and in turn the modem 1602 may send the response back to the IMS module 524 as SIP messages.

[0133] In an embodiment, to avoid the PLMN blocking due to SIP Register timeout, the UE 502 may perform early refresh registration when service is dropping, and the UE 502 is in motion. The early refresh registration may be indicated by the AI model 526. The AI model 526 may indicate the IMS module 524 that the UE 502 is heading towards no service region based on the prediction by the AI model 526. The IMS module 524 may trigger refresh registration beforehand so that PLMN will not get blocked. Further, the AI model 526 may also predict the expected duration of the UE 502 in low coverage region, based on that, the UE 502 may negotiate the refresh expiry timer (say 'x') higher than the duration of the UE 502 in low coverage area.

[0134] Figure 17 illustrates an exemplary scenario 1700 depicting the implementation of the AI model 526, according to one or more embodiments of the present disclosure.

[0135] The AI model 526 may be trained on the dataset 1610 which may include the one or more parameters. For example, a parameter D3may correspond to 3D distance between the eNB antenna and the UE 502. The purpose of the D3may be to get signal travel distance from a transmitter (Tx) to a receiver (Rx). Another parameter HRmay correspond to a height ratio of the eNB antenna to the height of the UE 502 at above sea level (ASL). The purpose of the HRmay be to get effective height ratio of the Tx and the Rx. Another parameter tilt may be an angle of transmitting signal from the eNB antenna to the UE 502. The purpose of the tilt is to get tilt angle of signal transmission from the eNB antenna to the location of the UE 502. Another parameter frequency corresponds to a use of frequency bands which are dedicated for 4G or 5G spectrum. The purpose of the frequency parameter is to get real RSRP reading in multiband measurement. Another parameter observation corresponds to status of signal propagation path between the eNB antenna and the UE 502. The purpose of the observation is to classify the signal status either loss of signal (LOS) or No Loss of signal (NLOS).

[0136] The UE 502 may act as the Rx and the eNB antenna may act as the Tx. The UE 502 may be at a distance of D2from the network 522 Tx, and height of the Tx may be T1and the UE 502 may be at a height of T2from the ground. The shortest distance between the Tx and the Rx may be calculated from the following equation:

[0137] (1)

[0138] (2)

[0139] Figure 18 illustrates a flowchart 1800 depicting steps of dataset preparation by the AI model 526, according to one or more embodiments of the present disclosure.

[0140] The AI model 526 may be trained on the dataset 1610 to predict the low coverage area and to avoid PLMN blocking.

[0141] At step 1902, the AI model 526 may collect parameters using some tool or drive test. The AI model 526 may be configured to retrieve the eNB technical specification. At step 1904, the AI model 526 may calculate derivative parameters. At step 1906, the AI model 526 may be configured for dataset preparation. At step 1908, the AI model 526 may be configured to remove outlier.

[0142] In some embodiment, before data preparation is done, data cleaning need to be done. The data collected at static conditions need to be removed to ensure data is free from any error. After completing data cleaning process, the UE 502 location may be extracted in.csv fileformat. The extracted location may be used as reference input to generate data parameters, for example, two-dimensional (2D) distance between the eNB antenna and the UE 502, height of eNB antenna at the ASL, height of the UE 502 at the ASL, tilt angle, i.e., angle of signal transmission from the eNB antenna to the UE 502, signal propagation path status between the eNB antenna and the UE 502.

[0143] Figure 19 illustrates a detailed schematic workflow 1900 depicting the implementation of the AI model 526 to avoid the PLMN blocking and the server selection process in limited-service case, according to one or more embodiments of the present disclosure.

[0144] In an embodiment, all data will get pushed to the cloud data storage 1608 periodically. The IMS module 524 may include the data collection module 528 to store the one or more parameters or the dataset 1610. The AI model 526 may take data stored on the cloud storage 1608 and may get trained on that periodically. The retrained AI model 526 may get pushed to the IMS module 524 in the UE 502 periodically.

[0145] Figure 20 illustrates a basic architecture of a neural network 2000 for training the AI model

[0146] 526, according to one or more embodiments of the present disclosure.

[0147] The AI model 526 architecture may include an input layer 2002, a hidden layer 2004 and an output layer 2006. The hidden layer 2002 may include 40 hidden layers. The input layer 2002 may be a starting point where the information enters the network 522. The number of neurons in the input layer 2002 matches with the number of features in the data. The hidden layer 2004 may be a brainstorming session. The information passed from the input layer 2002 gets manipulated and transformed. The hidden layer 2004 may include a single layer or many hidden layers. Each neuron in the hidden layer receives information from the previous layer and combines the received information with the knowledge, e.g., stored as weights 'w', and passes the outcome to the next layer. The output layer 2006 corresponds to a layer where a final answer comes out and the number of neurons at the output layer 2006 depends on the task.

[0148] Figure 22 illustrates another detailed architecture of the neural network 2000 for training the AI model 526, according to one or more embodiments of the present disclosure.

[0149] The neural network 2100 may include the AI model 526 communicatively coupled to the network 522 via the modem 1602. As discussed earlier, the AI model 526 may be configured to be activated when the signal strength is below the threshold, i.e., 75%, and may be configured to detect signal strength, low coverage duration and call status of the UE 502. The AI model 526 may be coupled with the IMS registration module 1606, the call module 1604, SMS. The IMS registration module 1606, the call module 1604, SMS may form a native stack.

[0150] Figure 23 illustrates an exemplary scenario 2200 depicting the user entering a metro tunnel and facing limited connectivity, according to one or more embodiments of the present disclosure.

[0151] The present disclosure may predict those limited coverage areas even before encountering the situation. In order to predict the limited service, the AI model 526 may be embedded into IMS Service. As illustrated, the user is in (X,Y,Z) location, then after 100 meters towards the tunnel, the AI model 526 check signal condition in all the directions. If suppose the user is going in 'B' direction, i.e., metro tunnel, and limited service is predicted by model, then actions are taken at IMS to perform refresh register. If the AI model 526 predicts higher call fails or call dropping in 'B' direction then P-CSCF switching may be done and initial IMS Registration may be performed on best P-CSCF.

[0152] Figure 23 illustrates a flowchart depicting a method 2300 for performing the IMS refresh registration process by the UE 502, according to one or more embodiments of the present disclosure.

[0153] At step 2302, the method 2300 may include predicting, by the UE 502, the time instant (T) the UE 502 enters the limited coverage area. In an embodiment, predicting the time instant when the UE enters the limited coverage area is based at least on one or more predefined parameters. The one or more predefined parameters comprises at least one of, a location of the UE, one or more network characteristics, and one or more device characteristics.

[0154] At step 2304, the method 2300 may include determining, by the UE 502, whether to switch to the new P-CSCF based at least on the call status of the UE with the current P-CSCF.

[0155] At step 2306, the method 2300 may include initiating, by the UE 502, the IMS refresh registration process prior to the predicted time instant (T). At step 2308, the method 2300 may include triggering, by the IMS refresh registration process, a refresh register process request based on determining that there is no need to switch to the new P-CSCF. At step 2310, the method 2300 may include triggering, by the IMS refresh registration process, a new IMS register process request to switch to the new P-CSCF based on determining that there is a need to switch to the new P-CSCF.

[0156] The present disclosure proposes solution to the IMS, i.e., avoiding public land mobile network (PLMN) blocking and best proxy-call session control function (P-CSCF) selection. The present discourse, to avoid PLMN blocking, employs an artificial intelligence (AI) model to predict low coverage areas based on user movement and performs early refresh register even before entering those areas, for example, tunnels, underpasses, etc., to avoid the PLMN blocking due to refresh registration inside the no-service area. Further, the present disclosure by the application of AI model modifies the refresh registration time interval, which is 30 minutes generally, to 'x' minutes which is greater than a predicted time of the no service duration. For instance, a user is moving in a direction of a tunnel, i.e., a low coverage area. When the user is inside tunnel and the UE triggers refresh registration, since the UE is under low service area, refresh register will get timed out and chances of PLMN blocking is more. Therefore, to avoid this issue, the AI model predicts that a low service area is approaching when the user is moving towards the tunnel. The AI model notifies the UE to trigger an early refresh register even before entering the tunnel, so that refresh registration can be successful. Also, the AI model predicts the duration of no service area, so that in refresh registration, expiry time is set as some 'x' higher than the duration of no service.

[0157] Although specific units / modules have been illustrated in the figure and described above, it should be understood that the system may include other hardware modules or software modules or combinations as may be required for performing various functions.

[0158] The various embodiments described above are provided by way of illustration only and should not be construed to limit the scope of the disclosure. Various modifications and changes may be made to the principles described herein without following the example embodiments and applications illustrated and described herein, and without departing from the spirit and scope of the disclosure.

[0159] Those skilled in the art will appreciate that the operations described herein in the present disclosure may be carried out in other specific ways than those set forth herein without departing from essential characteristics of the present invention. The above-described embodiments are therefore to be construed in all aspects as illustrative and not restrictive. The scope of the invention should be determined by the appended claims, not by the above description, and all changes coming within the meaning of the appended claims are intended to be embraced therein.

[0160] The drawings and the forgoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, orders of processes described herein may be changed and are not limited to the manner described herein.

[0161] Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts necessarily need to be performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples. Numerous variations, whether explicitly given in the specification or not, such as differences in structure, dimension, and use of material, are possible. The scope of embodiments is at least as broad as given by the following claims.

[0162] Benefits, other advantages, and solutions to problems have been described above with regard to specific embodiments. However, the benefits, advantages, solutions to problems, and any component(s) that may cause any benefit, advantage, or solution to occur or become more pronounced are not to be construed as a critical, required, or essential feature or component of any or all the claims.

Claims

1.A method for performing an internet protocol, IP, multimedia subsystem, IMS, refresh registration process by a user equipment (UE) (502), the method comprising:predicting (2302) a time instant when the UE (502) enters a limited service area;determining (2304) whether to switch to a new proxy-call session control function, P-CSCF, based on a call status of the UE (502) with a current P-CSCF; andinitiating (2306) the IMS refresh registration process prior to the predicted time instant, wherein the IMS refresh registration process comprising:triggering (2308) a refresh register process request based on determining not to switch to the new P-CSCF; andtriggering (2310) a new IMS register process request to switch to the new P-CSCF based on determining to the new P-CSCF.2.The method of claim 1, wherein the time instant when the UE (502) enters the limited service area is predicted based on one or more predefined parameters, wherein the one or more predefined parameters comprises at least one of a location of the UE (502), one or more network characteristics, and one or more device characteristics.3.The method of claim 1, wherein determining whether to switch to the new P-CSCF based on the current call status comprises:determining, using an Artificial Intelligence, AI, model, that one or more P-CSCFs are available with higher coverage with respect to the current P-CSCF, wherein the AI model is trained based on historical data associated with a set of predefined call parameters corresponding to a plurality of P-CSCFs at at least one given location.4.The method of claim 1, wherein triggering the new IMS register process request to switch to the new P-CSCF, comprises:triggering a fresh IMS registration request with the new P-CSCF with an expiry header set to a predefined time duration which is greater than a refresh registration duration when the call status is bad; andtriggering a refresh register with the current P-CSCF with an expiry header set to the predefined time duration greater than the refresh registration duration.5.The method of claim 3, wherein the set of predefined call parameters comprises at least one of call drop rates, real-time transport protocol, RTP, packet drop rates, and call setup failure errors, corresponding to a given location.6.The method of claim 2, further comprises:predicting a time duration for which the UE (502) is in the limited service area; andupdating the refresh registration duration based at least on the predicted time duration.7.The method of claim 1, wherein the limited service area prediction by the UE (502) is indicative of input values received, including a speed of a device, direction in which the device is heading, a tilt angle, and a signal frequency.8.The method of claim 1, wherein determining whether to switch to the new P-CSCF based on the current call status comprises:predicting, using an AI model (526), a reference signal received power, RSRP, value to assess quality of the current P-CSCF coupled to the UE (502), wherein the AI model (526) is trained by feeding data parameters indicative of distance between an evolved node-B, eNB, and the UE (502), an angle of transmitting a signal from the eNB, a frequency band, a height ratio between the eNB and the UE (502).9.The method of claim 1, further comprising:transmitting a refresh expiry timer to a network for further registrations.10.The method of claim 1, further comprising:updating, based on receiving a refresh registration request, records to prevent a Public Land Mobile Network, PLMN, blocking during the limited service area of the UE (502).11.The method of claim 1, further comprising:performing an early refresh registration based on predicting that the UE (502) is heading towards a no service region to avoid PLMN blocking.12.The method of claim 1, wherein the refresh registration request is triggered based on a predicted movement trajectory towards the limited service area.13.A user equipment, UE, (502) for performing an internet protocol, IP, multimedia subsystem, IMS, refresh registration process, the UE comprising:memory (512) storing instructions; andat least one processor (504) communicatively coupled with the memory (512), wherein the instructions, when executed by the at least one processor (504), cause the UE (502) to:predict a time instant when the UE (502) enters a limited service area;determine whether to switch to a new proxy-call session control function, P-CSCF, based on a call status of the UE (502) with a current P-CSCF; andinitiate the IMS refresh registration process prior to the predicted time instant, wherein the IMS refresh registration process comprising:triggering a refresh register process request based on determining not to switch to the new P-CSCF; andtriggering a new IMS register process request to switch to the new P-CSCF based on determining to switch to the new P-CSCF.14.The UE of claim 13, wherein the instructions, when executed by the at least one processor (504), cause the UE (502) further to be operated according to a method in one of claims 2 to 12.15.A non-transitory computer readable storage medium storing instructions which, when executed by at least one processor (504) of a user equipment, UE, (502), cause the UE (502) to be operated according to a method in one of claims 1 to 12.

Images