Patent Application
20240147216
The present invention generally relates to communications, and more specifically, to intelligent subscriber identity module (SIM) switching for user equipment (UE) devices.
A SIM allows user equipment (UE), such as mobile devices, desktop computers with appropriate hardware, vehicle telecommunications systems, etc., to be identified and authenticated on a network. The UE is identified by the international mobile subscriber identity (IMSI) number associated with the SIM. The SIM identifies which service provider network that the UE connects with.
Network service providers may provide customers with a device with a preinstalled SIM for their network, or users may insert a SIM for the network into their own device. The SIM may also be associated a phone number for the device. A SIM may be a physical SIM (pSIM) or an embedded SIM (eSIM). A pSIM is a physical card that is inserted into an associated slot in the UE. An eSIM, on the other hand, is a digital version of a pSIM including a profile that can be downloaded to a mobile device to provide functionalities of a pSIM.
Currently, fifth generation (5G) devices with dual SIM support are available where UE can utilize a pair of SIMs, whether physical SIMs, eSIMs, or one of each. However, switching between SIMs is not performed intelligently or optimally. Accordingly, an improved and/or alternative approach may be beneficial.
Certain embodiments of the present invention may provide solutions to the problems and needs in the art that have not yet been fully identified, appreciated, or solved by current communications technologies, and/or provide a useful alternative thereto. For example, some embodiments of the present invention pertain to intelligent SIM switching for UE devices.
In an embodiment, an intelligent subscriber management server includes memory storing computer program instructions configured to facilitate roaming intelligent SIM switching for a plurality of UE devices and at least one processor configured to execute the computer program instructions. The computer program instructions are configured to cause the at least one processor to monitor traffic from the plurality of UE devices routed through home network infrastructure via a radio access network (RAN) of the home network infrastructure, or routed through the home network infrastructure from carrier network infrastructure of another carrier. The computer program instructions are also configured to cause the at least one processor to determine that a UE device of the plurality of UE devices should switch from switch from a current SIM or SIM profile to a different SIM or SIM profile in accordance with a policy. The computer program instructions are further configured to cause the at least one processor to instruct the UE device of the plurality of UE devices to switch to the different SIM or SIM profile.
In another embodiment, a computer-implemented method for facilitating roaming intelligent SIM switching for a plurality of UE devices includes monitoring, by an intelligent subscriber management server, traffic from the plurality of UE devices routed through home network infrastructure via a RAN of the home network infrastructure, or routed through the home network infrastructure from carrier network infrastructure of another carrier. The computer-implemented method also includes determining, by the intelligent subscriber management server, that a UE device of the plurality of UE devices should switch from switch from a current SIM or SIM profile to a different SIM or SIM profile in accordance with a policy. The computer-implemented method further includes instructing the UE device of the plurality of UE devices to switch to the different SIM or SIM profile, by the intelligent subscriber management server.
In yet another embodiment, a non-transitory computer-readable medium stores a computer program for facilitating roaming intelligent SIM switching for a plurality of UE devices. The computer program is configured to cause at least one processor to monitor traffic from the plurality of UE devices routed through home network infrastructure via a RAN of the home network infrastructure, or routed through the home network infrastructure from carrier network infrastructure of another carrier. The computer program is also configured to cause the at least one processor to determine that a UE device of the plurality of UE devices should switch from switch from a current SIM or SIM profile to a different SIM or SIM profile in accordance with a policy taking into account locations of the plurality of UE devices, hardware capabilities of the plurality of UE devices, compatibility of the plurality of UE devices with carrier networks associated with a plurality of SIMs or SIM profiles, services that the plurality of UE devices are configured to use, carrier networks that are available in respective locations of the plurality of UE devices, network quality criteria, subscription criteria, cost criteria, or any combination thereof. The computer program is further configured to cause the at least one processor to instruct the UE device of the plurality of UE devices to switch to the different SIM or SIM profile. The policy is predictive and uses deterministic logic based on observations over time, probabilistic logic of one or more artificial intelligence (AI)/machine learning (ML) models, or both, and/or the computer program is configured to determine the policy based on the one or more AI/ML models.
In order that the advantages of certain embodiments of the invention will be readily understood, a more particular description of the invention briefly described above will be rendered by reference to specific embodiments that are illustrated in the appended drawings. While it should be understood that these drawings depict only typical embodiments of the invention and are not therefore to be considered to be limiting of its scope, the invention will be described and explained with additional specificity and detail through the use of the accompanying drawings, in which:
Unless otherwise indicated, similar reference characters denote corresponding features consistently throughout the attached drawings.
Some embodiments pertain to intelligent SIM switching for UE devices. The UE may have multiple SIMs for multiple carrier networks (i.e., mobile network operators (MNOs) that provide wireless network infrastructure, such as radio access networks (RANs)) or a universal SIM. It may be desirable to switch between SIMs for various reasons, such as based on network quality criteria, subscription criteria, agreement criteria between MNOs, etc. These criteria may inform a policy for determining which SIM to use.
In some embodiments, a rules engine is used to determine whether to switch SIMs and the associated carrier networks in accordance with a policy. The rules engine may apply business logic to determine the networks and configuration to be used. In some embodiments, the rules engine may take into account the location, UE device capabilities and compatibility with the carrier networks, the services that the UE uses, which carrier networks are available in the location, network quality criteria, subscription criteria, cost criteria, etc. The rules engine then returns the network to which the UE should switch.
For example, if a user has a subscription that uses the lowest cost carrier network that is available, the policy may cause the UE to always use the SIM for the lowest cost available carrier network that meets certain minimum quality criteria (e.g., a minimum signal strength, signal-to-noise ratio (SNR) signal to interference and noise ratio (SINR), etc.). If a user has a high tier subscription, on the other hand, the SIM for the highest quality available carrier network may be selected. More complex, tiered policies are also possible. For instance, certain carrier networks may be preferred in certain areas, different carrier networks and their SIMs may be preferred for different services (e.g., there may be a list of preferred carrier networks for voice and short message service (SMS) and another list of preferred carrier networks for data services), artificial intelligence (AI)/machine learning (ML) models may be employed (e.g., to predict congestion at different times of the day/week/month, network quality, weather impacts, etc.), etc.
Some embodiments may be reactive or predictive. Reactive embodiments may switch SIMs based on detected criteria, such as a drop in signal strength below a minimum threshold or detection that a local RAN for a carrier has gone down, a change in the location of the UE, detection that an antenna of the UE is no longer working such that a certain band can no longer be used, etc. Predictive embodiments, on the other hand, may use deterministic logic based on observations over time and/or probabilistic logic in the form of AI/ML models. Such predictive approaches may be more beneficial for cars, drone delivery networks, etc. However, any suitable UE device, such as smart phones, personal computers, etc., may benefit from predictive techniques without deviating from the scope of the invention.
In some embodiments, the policy that is used may be determined for the current UE conditions using AI/ML models. For instance, AI/ML models may be used to learn that when a certain policy to prefer a certain carrier SIM that has less cost for a brand associated with the smart phone is used in a first area, users tend to cancel their subscriptions and switch carriers at a high rate. However, in a second another area, the number of cancellations is low. The AI/ML model may intelligently recommend that a policy that tends not to recommend the lower cost carrier be used in the first area and a policy that recommends a higher cost carrier be used in the second area.
In order to enable and inform the intelligent SIM switching logic, information regarding current conditions detected by the UE device (e.g., the location, the signal strength, SNR, SINR, etc. for detected networks at the location, which SIM profiles are available for the UE, UE hardware capabilities (e.g., supported bands), etc.) may be provided to the network infrastructure for the carrier that is implementing the intelligent SIM switching. Server-side logic may then be employed to analyze network loading and congestion, subscription information, carrier contract information, apply AI/ML models, etc. in real time or near-real time and make a choice regarding which SIM identity to use at a given time.
In some embodiments, active network metrics are captured from UE devices to gain insight into the performance of different carrier networks and build network data profiles over time, as well as current performance in real time or near-real time. This information may be used to identify trends for the carrier networks, to provide training data to train/retrain AI/ML models, etc.
In some embodiments, different policy rules may be weighted. For instance, for a lower cost subscription, a relatively heavy static weight may be applied to the priority of selecting the lowest cost network. Another weight may be applied to network quality metrics that decreases as network quality decreases (e.g., a linear, exponential, or step function tied to signal strength, SNR, SINR, congestion, etc.). In certain embodiments, weights for various criteria may be learned and provided by AI/ML models.
In some embodiments, a SIM for a certain carrier network may be selected by default if that carrier network is available and meets certain minimum quality criteria at the UE location. In certain embodiments, different rules may be applied to different brands, and these rules may at least partially depend on the hardware capabilities of the given carrier network. In some embodiments, the rules could be venue based if there is a managed private network. For instance, customers may prefer the managed private network over other networks.
To perform intelligent SIM switching, radio connections to available RANs for each SIM are maintained in accordance with a list of carrier networks. This list is provided to the modem of the UE to scan and connect to the RANs. If a carrier network is not available, the carrier network is dropped from the scan list. Conversely, if a carrier network becomes available, the carrier network is added to the scan list. The UE periodically checks which carrier networks are available such that an updated list is maintained for the UE location.
In some embodiments, the primary roaming network in the SIM profile configures the UE with the optimum parameters for the initial network that the UE connects to at activation. Multiple considerations, such as the location of the subscriber, the network loading, the quality of the services, etc., may be taken into account for the initial network selection decision in some embodiments. For instance, if the UE is purchased at an AT&T® store or a Verizon® store, the UE may be optimally configured for that network initially. In other words, software and hardware of the UE would be optimized for that carrier. If optimized for AT&T®, the UE may not support band n71 and outer bands, and AT&T® may also have a priority list for the bands it supports, a certain packet size that it uses, etc.
The UE then dynamically reconfigures itself based on the actual network that the UE is attached to. For instance, if the UE initially configured for the AT&T® network switches to T-Mobile®, the UE settings may be changed so n71 is supported, n41 is used for better throughput, etc. Thereafter, the policy (e.g., the network quality, the service grade, the device location, the subscription, etc.) drives dynamic reconfiguration of the UE.
Intelligent, dynamic SIM switching occurs when the UE is actively used by the subscriber after the initial activation of the UE and may take into account temporal and geographic factors (e.g., typical network loading at certain times and locations, which may be learned by one or more AI/ML models). Depending on the time of day, for example, the quality of the services required by the user might drive the decision to switch the network. Alternatively, when the user travels to a certain location, such as a university campus, a subway tunnel, a business location, etc., a specific network may provide the best service to the user.
For a voice supporting device, switching requires a number porting processes. Hence, from user experience perspective, a data-only device is most practical since switching can be done without user intervention. For voice devices, dual SIM dual standby (DSDS) may be used since the voice service can stay on an initially provisioned network on one SIM while data networks can be switched on the other SIM as desired. See, for example, U.S. patent application Ser. No. 18/174,216. Alternatively, a data voice application, such as WhatsApp®, may be used on data-only devices, which allows any desired data network to be selected. In such a case, a carrier grade voice service (Internet Protocol (IP) Multimedia Subsystem (IMS) voice is the only current way to guarantee voice quality) is sacrificed in lieu of seamless network switching.
Currently, the network order information is static and fixed. However, some embodiments update the network for voice and/or data dynamically, depending on the aforementioned conditions. This operation can be achieved by updating the configuration in a given SIM, but conceptually, it can be achieved by switching the SIM as well. Such techniques may be applicable to both single SIM and multi-SIM devices (e.g., DSDS devices).
Carrier network infrastructure 130, 132, 134 and home network infrastructure 136 may include computing systems and other equipment associated with pass-through edge data centers (PEDCs), breakout edge data centers (BEDCs), regional data centers (RDCs), national data centers (NDCs), etc. Carrier network infrastructure 130, 132, 134 and home network infrastructure 136 may provide various network functions (NFs) and other services. For instance, BEDCs may break out User Plane Function (UPF) data traffic (UPF-d) and provide cloud computing resources and cached content to UE 110, such as providing NF application services for gaming, enterprise applications, etc. RDCs may provide core network functions, such as UPF for voice traffic (UPF-v) and Short Message Service Function (SMSF) functionality. NDCs may provide a Unified Data Repository (UDR) and user verification services, for example. Other network services that may be provided may include, but are not limited to, IMS+telephone answering service (TAS) functionality, IP-SM gateway (IP-SM-GW) functionality (the network functionality that provides the messaging service in the IMS network), enhanced serving mobile location center (E-SMLC) functionality, policy and charging rules function (PCRF) functionality, mobility management entity (MME) functionality, signaling gateway (SGW) control plane (SGW-C) and user data plane (SGW-U) ingress and egress point functionality, packet data network gateway (PGW) control plane (PGW-C) and user data plane (PGW-U) ingress and egress point functionality, home subscriber server (HSS) functionality, UPF+PGW-U functionality, access and mobility management (AMF) functionality, HSS+unified data management (UDM) functionality, session management function (SMF)+PGW-C functionality, short message service center (SMSC) functionality, and/or policy control function (PCF) functionality. It should be noted that additional and/or different network functionality may be provided without deviating from the present invention. The various functions in these systems may be performed using dockerized clusters in some embodiments.
The intelligent SIM switching process in some embodiments may be initiated by intelligent subscriber management server 150 via control messages delivered through a regular Internet connection of UE 110, for example. For instance, if UE 110 is using SIM 112 for RAN 120 and carrier network infrastructure 130, and intelligent subscriber management server 150 would like to switch UE 110 to a different carrier network, or UE 110 detects that the connection characteristics for RAN 120 have degraded to poor quality (e.g., signal strength, SNR, and/or SINR have fallen below certain minimum quality thresholds), UE 110 may switch SIMs and connect to a different carrier network based on the control messages, or may switch to another network itself if the home network cannot be reached. Alternatively, UE 110 may reach home network infrastructure 136 and intelligent subscriber management server 150 through the Internet 140 (connection not shown) or through another carrier network. However, in some embodiments, the home network may be a mobile virtual network operator (MVNO). In such embodiments, home network infrastructure 136 may be used for data services and carrier network infrastructure 130, 132, 134 may be used for voice services. Intelligent subscriber management server 150 may be one or more of its own servers, and potentially other network infrastructure. However, in some embodiments, intelligent subscriber management server 150 is part of home network infrastructure 136.
In some embodiments, a policy for the UE implemented on intelligent subscriber management server 150 may determine that UE 110 should switch to a different carrier network. For instance, if the policy indicates that UE 110 should switch to carrier 2, intelligent subscriber management server 150 sends control messages to UE 110 via the Internet 140 or RAN 126 to switch to carrier 2. UE 110 then switches to SIM 114 (potentially downloading SIM 114 responsive to the control messages), connects to carrier network 2, and begins using RAN 122 and carrier network infrastructure 132 for services.
For roaming, UE 110 may use RAN 120, 122, or 124 and respective carrier network infrastructure 130, 132, or 134 to route all traffic (e.g., voice/SMS, data, and subscriber management traffic) to home network infrastructure 136, and vice versa. For instance, if UE 110 is connected to RAN 120, the traffic flow for data traffic from UE 110 to home network infrastructure 136 would be UE 110 to RAN 120 to carrier 1 network infrastructure 130 to home network infrastructure 136 to the Internet 140. As such, the roaming scenario does not necessarily involve SIM switching. However, if UE 110 has a connection available to the Internet 140 (not shown), UE 110 may communicate with carrier network infrastructure 136 for voice/SMS and subscriber management traffic via the Internet 140 without going through another carrier network in some embodiments. UE 110 may also send data traffic to and receive data traffic from the Internet 140 directly.
In scenarios where two or more SIMs are used, such as is the case for UE 110, SIM 118 (which is used for voice in this case) could roam into carrier network 1 once SIM 118 loses home network coverage (not involving SIM switching). However, the SIM used for data (SIM 114 or SIM 116 in this case) could be switched. The operation in roaming may be the same as the home network situation except for situations such as the DSDS case, where one SIM is attached to a carrier network for voice and SMS (e.g., carrier network 1) and the other SIM is switched among the remaining carriers. In the single SIM case, this SIM switches among the carrier networks, with a preference for cannier network 1, where communications could be home routed. The other carrier networks (carrier network 2 . . . carrier network/V) are not home routed.
Any number of SIMs may be used without deviating from the scope of the invention, so long as the UE supports them.
The carrier application determines which SIMs to use for different services in some embodiments, such as one SIM for data and another SIM for voice and SMS. However, in certain embodiments, only a single SIM is switched to. The carrier application may also help to facilitate download of the eSIM profile when an eSIM is used.
The carrier configuration for the brand for the SIM to switch to is returned at 315, including the brand name and carrier certificate array 320. The access point names (APNs) for the brand are added at 325 and a customization service is started at 330. The customization service operations 335 include obtaining the brand preloaded contacts, the brand wallpaper, and the application enablement/disablement settings.
The network configuration is then started at 340. The configuration operations 345 may include retrieving an activation code, configuring the UE for the bands used by the network MNO, configuring the packet size to that used by the MNO, and downloading a policy for the user's subscription to be used on the UE side. The policy may govern which MNO the UE uses for which services and under what conditions in some embodiments. The UE then operates with the MNO(s) that it switched to at 350 using the SIM(s) for those MNO(s).
UE 410 configures itself to switch to CN 1420. In some embodiments, this may include downloading an eSIM for CN 1420. In the case of an eSIM, a device carrier application with the correct privileges, such as that of
In some embodiments, the pSIM can operate in a similar manner to the eSIM if the pSIM is loaded with the eSIM profile. If the pSIM is loaded with the conventional pSIM profile, SIM switching would mean physically removing one pSIM and inserting another pSIM. Hence, it is beneficial to load the pSIM with the desired eSIM profile to have SIM switching work with the same pSIM.
Currently, there are two choices—a consumer eSIM profile and a machine-to-machine (M2M) eSIM profile. The major technical difference between the two is that the consumer eSIM uses a PULL model (i.e., the device/client is put in control for profile management and the LPA plays the role in the device), whereas an M2M eSIM profile uses a PUSH model (i.e., control occurs at the backend/server). An M2M eSIM profile may be used on a pSIM in some embodiments, and the server/backend (e.g., the SM-DP) may use SMS to control the eSIM profile.
UE 410 requests to attach to CN 1420, and CN 1420 attaches UE 410 to the network. CN 1420 notifies UE 410 that the attachment was successful, and UE 410 informs home network/intelligent subscriber management server 440 that the SIM switch was successful. UE 410 then uses CN 1420 for communications services.
UE 410 configures itself to switch to CN 1420. UE 410 requests to attach to CN 1, 420, and CN 1420 attaches UE 410 to the network. CN 1420 notifies UE 410 that the attachment was successful, and UE 410 informs home network/intelligent subscriber management server 440 that the SIM switch was successful. UE 410 then uses CN 1420 for communications services.
UE 410 configures itself to switch to CN 1420. UE 410 requests to attach to CN 1420 and CN N 430, and CN 1420 and CN N 430 attach UE 410 to their respective networks. CN 1420 and CN N 430 notify UE 410 that the attachment was successful, and UE 410 informs home network/intelligent subscriber management server 440 that the SIM switches were successful. UE 410 then uses CN 1420 for voice and SMS and CN N 430 for data.
UE 410 configures itself to switch to CN 1420. UE 410 requests to attach to CN 1420 and CN N 430, and CN 1420 and CN N 430 attach UE 410 to their respective networks. CN 1420 and CN N 430 notify UE 410 that the attachment was successful, and UE 410 informs home network/intelligent subscriber management server 440 that the SIM switches were successful. UE 410 then uses CN 1420 for voice and SMS and CN N 430 for data.
It should be noted that a subset of SIMs may be switched without deviating from the scope of the invention. For instance, only one of the SIMs may be switched in the examples of
Per the above, AI/ML may be used to improve the intelligent SIM switching system of some embodiments. Various types of AI/ML models may be trained and deployed without deviating from the scope of the invention. For instance,
Neural network 800 also includes a number of hidden layers. Both DLNNs and shallow learning neural networks (SLNNs) usually have multiple layers, although SLNNs may only have one or two layers in some cases, and normally fewer than DLNNs. Typically, the neural network architecture includes an input layer, multiple intermediate layers, and an output layer, as is the case in neural network 800.
A DLNN often has many layers (e.g., 10, 50, 200, etc.) and subsequent layers typically reuse features from previous layers to compute more complex, general functions. A SLNN, on the other hand, tends to have only a few layers and train relatively quickly since expert features are created from raw data samples in advance. However, feature extraction is laborious. DLNNs, on the other hand, usually do not require expert features, but tend to take longer to train and have more layers.
For both approaches, the layers are trained simultaneously on the training set, normally checking for overfitting on an isolated cross-validation set. Both techniques can yield excellent results, and there is considerable enthusiasm for both approaches. The optimal size, shape, and quantity of individual layers varies depending on the problem that is addressed by the respective neural network.
Returning to
Hidden layer 2 receives inputs from hidden layer 1, hidden layer 3 receives inputs from hidden layer 2, and so on for all hidden layers until the last hidden layer provides its outputs as inputs for the output layer. It should be noted that numbers of neurons I, J, K, and L are not necessarily equal, and thus, any desired number of layers may be used for a given layer of neural network 800 without deviating from the scope of the invention. Indeed, in certain embodiments, the types of neurons in a given layer may not all be the same.
Neural network 800 is trained to assign a confidence score to appropriate outputs. In order to reduce predictions that are inaccurate, only those results with a confidence score that meets or exceeds a confidence threshold may be provided in some embodiments. For instance, if the confidence threshold is 80%, outputs with confidence scores exceeding this amount may be used and the rest may be ignored.
It should be noted that neural networks are probabilistic constructs that typically have confidence score(s). This may be a score learned by the AI/ML model based on how often a similar input was correctly identified during training. Some common types of confidence scores include a decimal number between 0 and 1 (which can be interpreted as a confidence percentage as well), a number between negative co and positive co, a set of expressions (e.g., “low,” “medium,” and “high”), etc. Various post-processing calibration techniques may also be employed in an attempt to obtain a more accurate confidence score, such as temperature scaling, batch normalization, weight decay, negative log likelihood (NLL), etc.
“Neurons” in a neural network are implemented algorithmically as mathematical functions that are typically based on the functioning of a biological neuron. Neurons receive weighted input and have a summation and an activation function that governs whether they pass output to the next layer. This activation function may be a nonlinear thresholded activity function where nothing happens if the value is below a threshold, but then the function linearly responds above the threshold (i.e., a rectified linear unit (ReLU) nonlinearity). Summation functions and ReLU functions are used in deep learning since real neurons can have approximately similar activity functions. Via linear transforms, information can be subtracted, added, etc. In essence, neurons act as gating functions that pass output to the next layer as governed by their underlying mathematical function. In some embodiments, different functions may be used for at least some neurons.
An example of a neuron 810 is shown in
This summation is compared against an activation function ƒ (x) to determine whether the neuron “fires”. For instance, ƒ (x) may be given by:
The output y of neuron 810 may thus be given by:
In this case, neuron 810 is a single-layer perceptron. However, any suitable neuron type or combination of neuron types may be used without deviating from the scope of the invention. It should also be noted that the ranges of values of the weights and/or the output value(s) of the activation function may differ in some embodiments without deviating from the scope of the invention.
A goal, or “reward function,” is often employed. A reward function explores intermediate transitions and steps with both short-term and long-term rewards to guide the search of a state space and attempt to achieve a goal (e.g., finding the best carrier for a give service, determining a timing strategy for turning on a SIM radio in order to save power, determining when the network is likely to be congested, etc.).
During training, various labeled data is fed through neural network 800. Successful identifications strengthen weights for inputs to neurons, whereas unsuccessful identifications weaken them. A cost function, such as mean square error (MSE) or gradient descent may be used to punish predictions that are slightly wrong much less than predictions that are very wrong. If the performance of the AI/ML model is not improving after a certain number of training iterations, a data scientist may modify the reward function, provide corrections of incorrect predictions, etc.
Backpropagation is a technique for optimizing synaptic weights in a feedforward neural network. Backpropagation may be used to “pop the hood” on the hidden layers of the neural network to see how much of the loss every node is responsible for, and subsequently updating the weights in such a way that minimizes the loss by giving the nodes with higher error rates lower weights, and vice versa. In other words, backpropagation allows data scientists to repeatedly adjust the weights so as to minimize the difference between actual output and desired output.
The backpropagation algorithm is mathematically founded in optimization theory. In supervised learning, training data with a known output is passed through the neural network and error is computed with a cost function from known target output, which gives the error for backpropagation. Error is computed at the output, and this error is transformed into corrections for network weights that will minimize the error.
In the case of supervised learning, an example of backpropagation is provided below. A column vector input x is processed through a series of N nonlinear activity functions ƒi between each layer i=1, . . . , N of the network, with the output at a given layer first multiplied by a synaptic matrix Wi, and with a bias vector bi added. The network output o, given by
o=ƒ
N(WNƒN-1(WN-1ƒN-2( . . . ƒ1(W1x+b1) . . . )+bN-1)+bN) (4)
In some embodiments, o is compared with a target output t, resulting in an error E=−½∥o−t∥2, which is desired to be minimized.
Optimization in the form of a gradient descent procedure may be used to minimize the error by modifying the synaptic weights Wi for each layer. The gradient descent procedure requires the computation of the output o given an input x corresponding to a known target output t, and producing an error o−t. This global error is then propagated backwards giving local errors for weight updates with computations similar to, but not exactly the same as, those used for forward propagation. In particular, the backpropagation step typically requires an activity function of the form pj(nj)=ƒj′(nj), where nj is the network activity at layer j (i.e., nj=Wjoj-1+bj) where oj=ƒj (nj) and the apostrophe ' denotes the derivative of the activity function ƒ.
The weight updates may be computed via the formulae:
where o denotes a Hadamard product (i.e., the element-wise product of two vectors), T denotes the matrix transpose, and oj denotes ƒj (Wjoj-1+bj), with o0=x. Here, the learning rate η is chosen with respect to machine learning considerations. Below, η is related to the neural Hebbian learning mechanism used in the neural implementation. Note that the synapses W and b can be combined into one large synaptic matrix, where it is assumed that the input vector has appended ones, and extra columns representing the b synapses are subsumed to W.
The AI/ML model may be trained over multiple epochs until it reaches a good level of accuracy (e.g., 97% or better using an F2 or F4 threshold for detection and approximately 2,000 epochs). This accuracy level may be determined in some embodiments using an F1 score, an F2 score, an F4 score, or any other suitable technique without deviating from the scope of the invention. Once trained on the training data, the AI/ML model may be tested on a set of evaluation data that the AI/ML model has not encountered before. This helps to ensure that the AI/ML model is not “over fit” such that it performs well on the training data, but does not perform well on other data.
In some embodiments, it may not be known what accuracy level is possible for the AI/ML model to achieve. Accordingly, if the accuracy of the AI/ML model is starting to drop when analyzing the evaluation data (i.e., the model is performing well on the training data, but is starting to perform less well on the evaluation data), the AI/ML model may go through more epochs of training on the training data (and/or new training data). In some embodiments, the AI/ML model is only deployed if the accuracy reaches a certain level or if the accuracy of the trained AI/ML model is superior to an existing deployed AI/ML model. In certain embodiments, a collection of trained AI/ML models may be used to accomplish a task. This may collectively allow the AI/ML models to enable semantic understanding to better predict event-based congestion or service interruptions due to an accident, for instance.
Some embodiments may use transformer networks such as SentenceTransformers™, which is a Python™ framework for state-of-the-art sentence, text, and image embeddings. Such transformer networks learn associations of words and phrases that have both high scores and low scores. This trains the AI/ML model to determine what is close to the input and what is not, respectively. Rather than just using pairs of words/phrases, transformer networks may use the field length and field type, as well.
Natural language processing (NLP) techniques such as word2vec, BERT, GPT-3, Open AI, etc. may be used in some embodiments to facilitate semantic understanding. Other techniques, such as clustering algorithms, may be used to find similarities between groups of elements. Clustering algorithms may include, but are not limited to, density-based algorithms, distribution-based algorithms, centroid-based algorithms, hierarchy-based algorithms. K-means clustering algorithms, the DB SCAN clustering algorithm, the Gaussian mixture model (GMM) algorithms, the balance iterative reducing and clustering using hierarchies (BIRCH) algorithm, etc. Such techniques may also assist with categorization.
If the AI/ML model fails to meet a desired confidence threshold at 940, the training data is supplemented and/or the reward function is modified to help the AI/ML model achieve its objectives better at 950 and the process returns to step 920. If the AI/ML model meets the confidence threshold at 940, the AI/ML model is tested on evaluation data at 960 to ensure that the AI/ML model generalizes well and that the AI/ML model is not over fit with respect to the training data. The evaluation data includes information that the AI/ML model has not processed before. If the confidence threshold is met at 970 for the evaluation data, the AI/ML model is deployed at 980. If not, the process returns to step 950 and the AI/ML model is trained further.
Computing system 1000 further includes a memory 1015 for storing information and instructions to be executed by processor(s) 1010. Memory 1015 can be comprised of any combination of random access memory (RAM), read-only memory (ROM), flash memory, cache, static storage such as a magnetic or optical disk, or any other types of non-transitory computer-readable media or combinations thereof. Non-transitory computer-readable media may be any available media that can be accessed by processor(s) 1010 and may include volatile media, non-volatile media, or both. The media may also be removable, non-removable, or both.
Additionally, computing system 1000 includes a communication device 1020, such as a transceiver, to provide access to a communications network via a wireless and/or wired connection. In some embodiments, communication device 1020 may be configured to use Frequency Division Multiple Access (FDMA), Single Carrier FDMA (SC-FDMA), Time Division Multiple Access (TDMA), Code Division Multiple Access (CDMA), Orthogonal Frequency Division Multiplexing (OFDM), Orthogonal Frequency Division Multiple Access (OFDMA), Global System for Mobile (GSM) communications, General Packet Radio Service (GPRS), Universal Mobile Telecommunications System (UMTS), cdma2000, Wideband CDMA (W-CDMA), High-Speed Downlink Packet Access (HSDPA), High-Speed Uplink Packet Access (HSUPA), High-Speed Packet Access (HSPA), Long Term Evolution (LTE), LTE Advanced (LTE-A), 802.11x, Wi-Fi, Zigbee, Ultra-WideBand (UWB), 802.16x, 802.15, Home Node-B (HnB), Bluetooth, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Near-Field Communications (NFC), fifth generation (5G), New Radio (NR), any combination thereof, and/or any other currently existing or future-implemented communications standard and/or protocol without deviating from the scope of the invention. In some embodiments, communication device 1020 may include one or more antennas that are singular, arrayed, phased, switched, beamforming, beamsteering, a combination thereof, and or any other antenna configuration without deviating from the scope of the invention.
Processor(s) 1010 are further coupled via bus 1005 to a display 1025, such as a plasma display, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, a Field Emission Display (FED), an Organic Light Emitting Diode (OLED) display, a flexible OLED display, a flexible substrate display, a projection display, a 4K display, a high definition display, a Retina® display, an In-Plane Switching (IPS) display, or any other suitable display for displaying information to a user. Display 1025 may be configured as a touch (haptic) display, a three-dimensional (3D) touch display, a multi-input touch display, a multi-touch display, etc. using resistive, capacitive, surface-acoustic wave (SAW) capacitive, infrared, optical imaging, dispersive signal technology, acoustic pulse recognition, frustrated total internal reflection, etc. Any suitable display device and haptic I/O may be used without deviating from the scope of the invention.
A keyboard 1030 and a cursor control device 1035, such as a computer mouse, a touchpad, etc., are further coupled to bus 1005 to enable a user to interface with computing system 1000. However, in certain embodiments, a physical keyboard and mouse may not be present, and the user may interact with the device solely through display 1025 and/or a touchpad (not shown). Any type and combination of input devices may be used as a matter of design choice. In certain embodiments, no physical input device and/or display is present. For instance, the user may interact with computing system 1000 remotely via another computing system in communication therewith, or computing system 1000 may operate autonomously.
Memory 1015 stores software modules that provide functionality when executed by processor(s) 1010. The modules include an operating system 1040 for computing system 1000. The modules further include an intelligent SIM switching module 1045 that is configured to perform all or part of the processes described herein or derivatives thereof. Computing system 1000 may include one or more additional functional modules 1050 that include additional functionality.
One skilled in the art will appreciate that a “computing system” could be embodied as a server, an embedded computing system, a personal computer, a console, a personal digital assistant (PDA), a cell phone, a tablet computing device, a quantum computing system, or any other suitable computing device, or combination of devices without deviating from the scope of the invention. Presenting the above-described functions as being performed by a “system” is not intended to limit the scope of the present invention in any way, but is intended to provide one example of the many embodiments of the present invention. Indeed, methods, systems, and apparatuses disclosed herein may be implemented in localized and distributed forms consistent with computing technology, including cloud computing systems. The computing system could be part of or otherwise accessible by a local area network (LAN), a mobile communications network, a satellite communications network, the Internet, a public or private cloud, a hybrid cloud, a server farm, any combination thereof, etc. Any localized or distributed architecture may be used without deviating from the scope of the invention.
It should be noted that some of the system features described in this specification have been presented as modules, in order to more particularly emphasize their implementation independence. For example, a module may be implemented as a hardware circuit comprising custom very large scale integration (VLSI) circuits or gate arrays, off-the-shelf semiconductors such as logic chips, transistors, or other discrete components. A module may also be implemented in programmable hardware devices such as field programmable gate arrays, programmable array logic, programmable logic devices, graphics processing units, or the like.
A module may also be at least partially implemented in software for execution by various types of processors. An identified unit of executable code may, for instance, include one or more physical or logical blocks of computer instructions that may, for instance, be organized as an object, procedure, or function. Nevertheless, the executables of an identified module need not be physically located together, but may include disparate instructions stored in different locations that, when joined logically together, comprise the module and achieve the stated purpose for the module. Further, modules may be stored on a computer-readable medium, which may be, for instance, a hard disk drive, flash device, RAM, tape, and/or any other such non-transitory computer-readable medium used to store data without deviating from the scope of the invention.
Indeed, a module of executable code could be a single instruction, or many instructions, and may even be distributed over several different code segments, among different programs, and across several memory devices. Similarly, operational data may be identified and illustrated herein within modules, and may be embodied in any suitable form and organized within any suitable type of data structure. The operational data may be collected as a single data set, or may be distributed over different locations including over different storage devices, and may exist, at least partially, merely as electronic signals on a system or network.
The UE device receives instructions from the rules engine (e.g., of the UE device or of a home network of the UE device) to switch from the current SIM or SIM profile to a different SIM or SIM profile at 1140. In some embodiments, the instructions may include more than one SIM (e.g., one SIM for voice and SMS and another SIM for data). The rules engine is configured to determine which SIM(s) or SIM profile(s) from a plurality of SIMs or SIM profiles that the UE device should switch to in accordance with the policy. Responsive to the instructions from the rules engine, the UE device configures itself for the different SIM(s) or SIM profile(s) and associated carrier(s) at 1150. The UE device is then switched to the other SIM(s) or SIM profile(s) for communications services provided by the associated carrier(s) at 1160.
In some embodiments, the rules engine is configured to take into account a location of the UE device, hardware capabilities of the UE device, compatibility of the UE device with carrier networks associated with the plurality of SIMs or SIM profiles, services that the UE device is configured to use, carrier networks that are available in a location of the UE device, network quality criteria, subscription criteria, cost criteria, or any combination thereof, when determining which SIM or SIM profile from the plurality of SIMs or SIM profiles to switch to. In certain embodiments, the rules engine selects a SIM or SIM profile of the plurality of SIMs or SIM profiles with a lowest cost available carrier network that meets minimum quality criteria or a highest quality according to quality criteria. In some embodiments, the policy is a tiered policy comprising a carrier network preference order based on location or a preference for different carrier networks for different services. In certain embodiments, the policy is reactive and the rules engine is configured to cause the UE to switch to the different SIM or SIM profile based on a drop in signal strength below a minimum threshold, detection that a RAN for a carrier of the current SIM or SIM profile has gone down, a change in a location of the UE, detection that an antenna of the UE is no longer working such that a band can no longer be used, or any combination thereof.
In some embodiments, the policy is predictive and uses deterministic logic based on observations over time, probabilistic logic of one or more AI/ML models, or both. In certain embodiments, the rules engine is configured to determine the policy based on one or more artificial AI/ML models. In some embodiments, the rules engine is configured to analyze network loading and congestion, subscription information, carrier contract information, or any combination thereof, to determine which SIM(s) or SIM profile(s) from the plurality of SIMs or SIM profiles to switch to.
The process steps performed in
The computer program(s) can be implemented in hardware, software, or a hybrid implementation. The computer program(s) can be composed of modules that are in operative communication with one another, and which are designed to pass information or instructions to display. The computer program(s) can be configured to operate on a general purpose computer, an ASIC, or any other suitable device.
It will be readily understood that the components of various embodiments of the present invention, as generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations. Thus, the detailed description of the embodiments of the present invention, as represented in the attached figures, is not intended to limit the scope of the invention as claimed, but is merely representative of selected embodiments of the invention.
The features, structures, or characteristics of the invention described throughout this specification may be combined in any suitable manner in one or more embodiments. For example, reference throughout this specification to “certain embodiments,” “some embodiments,” or similar language means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, appearances of the phrases “in certain embodiments,” “in some embodiment,” “in other embodiments,” or similar language throughout this specification do not necessarily all refer to the same group of embodiments and the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
It should be noted that reference throughout this specification to features, advantages, or similar language does not imply that all of the features and advantages that may be realized with the present invention should be or are in any single embodiment of the invention. Rather, language referring to the features and advantages is understood to mean that a specific feature, advantage, or characteristic described in connection with an embodiment is included in at least one embodiment of the present invention. Thus, discussion of the features and advantages, and similar language, throughout this specification may, but do not necessarily, refer to the same embodiment.
Furthermore, the described features, advantages, and characteristics of the invention may be combined in any suitable manner in one or more embodiments. One skilled in the relevant art will recognize that the invention can be practiced without one or more of the specific features or advantages of a particular embodiment. In other instances, additional features and advantages may be recognized in certain embodiments that may not be present in all embodiments of the invention.
One having ordinary skill in the art will readily understand that the invention as discussed above may be practiced with steps in a different order, and/or with hardware elements in configurations which are different than those which are disclosed. Therefore, although the invention has been described based upon these preferred embodiments, it would be apparent to those of skill in the art that certain modifications, variations, and alternative constructions would be apparent, while remaining within the spirit and scope of the invention. In order to determine the metes and bounds of the invention, therefore, reference should be made to the appended claims.
This application claims the benefit of U.S. Provisional Patent Application No. 63/421,119 filed Oct. 31, 2022. The subject matter of this earlier filed application is hereby incorporated by reference in its entirety.
| Number | Date | Country | |
|---|---|---|---|
| 63421119 | Oct 2022 | US |
