118. For example, a news server and/or a weather server and/or a social media server may indicate power outage events and/or internet outage events, which may affect CPE, and the like.

As will be explained herein, the ML engine 104 may be generally trained to generate, based on the historical data 122 associated with a queue 118, one or more prompts for calls in a hold state in a queue 118. For example, the ML engine 104 may generate, based on the historical data 122 associated with the queue 118-1, one or more prompts for the call 110, and the one or more prompts may be provided, on the call 110, during the hold state, via the server 102 and/or the IVR engine 114.

In particular, the ML engine 104 may attempt to resolve the call 110 before the call 110 is transferred to a terminal 112, for example freeing up processing and/or bandwidth resources at the server 102 (e.g., and/or a terminal 112). In a particular example, when the call 110 in the queue 118-1 is about a technical problem with a router, the ML engine 104 may provide one or more prompts to resolve the technical problem with the router to obviate transferring the call 110 to a terminal 112, and/or to resolve the call 110 such that the call 110 ends before transferring the call 110 to a terminal 112, and/or to reduce a length of time the call 110 is in the queue 118-1. Such prompts may be based on the historical data 122.

For example, the historical data 122 may indicates that a last given number of calls to the queue 118-1 (e.g., 5 calls, 10 calls, 15 calls, amongst other possibilities), and/or a portion thereof, included a particular and/or estimated reason for the calls, such as a particular technical problem with routers, as well as a technical solution that resolved the particular technical problem. In these examples, the one or more prompts may include the particular and/or estimated reason for calls; in particular, the caller 108-1 may be asked, via an initial prompt generated by the ML engine 104, if they are calling about the same particular technical problem with their routers as a last given number of callers 108. When the caller 108-1 indicates, in a response, that they are calling about the same particular technical problem, the technical solution that resolved the particular technical problem with the router may be provided on the call 110.

In some examples, the caller 108-1 may be asked if the technical solution resolved the call 110, and the user 108-1 may indicate “YES” or “NO”, and the like. (e.g., which may alternatively occur via actuation of a button at the calling device 106-1). Or, more generally, the caller 108-1 may be asked if prompts provided on the call 110 resolved the call 110 and/or if the call 110 was successful. Regardless, when the user 108-1 indicates that the call 110 is resolved and/or successful, a transcript of the call 110 may be stored at the historical data 122 and used as a positive training example to better train the ML engine 104. Alternatively, when the user 108-1 indicates that the call 110 is not resolved and/or unsuccessful, a transcript of the call 110 may be stored at the historical data 122 and used as a negative training example to better train the ML engine 104.

Attention is next directed to FIG. 2 which depicts an example schematic diagram of an example computing device 200 and/or engine (interchangeably referred to hereafter as the computing device 200). The computing device 200 is understood to comprise an example structure of the server 102 and/or the ML engine 104 (e.g., and/or the event monitor engine 126). The computing device 200 may comprise any suitable combination of one or more servers and/or engines, one or more cloud computing devices and/or engines, and the like. While depicted as one device, the computing device 200 may comprise one or more computing devices and/or one or more servers and/or one or more cloud computing devices that may be geographically distributed. In some examples, the computing device 200, and/or a portion thereof, may be combined with one or more of the terminals 112

As shown in FIG. 2, the computing device 200 includes at least one controller 202, such as a central processing unit (CPU) or the like. The controller 202 is interconnected with a memory 204 storing an application 206, the memory 204 implemented as a suitable non-transitory computer-readable medium (e.g., a suitable combination of non-volatile and volatile memory subsystems including any one or more of Random Access Memory (RAM), read only memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory, magnetic computer storage, and the like). The controller 202 and the memory 204 are generally comprised of one or more integrated circuits (ICs).

The controller 202 is also interconnected with a communication interface 208, which enables the computing device 200 to communicate with other components of the system 100 (e.g., the client devices 106, the terminals 112, the event sources 128 etc.), though it is understood such communication may occur at least partially locally when components of the system 100 are combined (e.g., the computing device 200 may be partially combined with one or more of the terminals 112). The communication interface 208 therefore may include any necessary components (e.g., network interface controllers (NICs), radio units, and the like) to communicate with other components of the system 100. The specific components of the communication interface 208 may be selected based on upon the nature of networks of the system 100 used by components of the system 100 to communicate, and/or local communication between components of the system 100, and the like. The computing device 200 may also include input and output devices connected to the controller 202, such as keyboards, mice, displays, and the like (not shown).

The components of the computing device 200 mentioned above may be deployed in a single enclosure, or in a distributed format. In some examples, therefore, the computing device 200 includes a plurality of processors, either sharing the memory 204 and communication interface 208, or each having distinct associated memories and communication interfaces. As such, it is understood that the memory 204, and/or a portion of the memory 204, may be internal (e.g., as depicted) or external to the computing device 200; regardless, the controller 202 is understood to have access to the memory 204.

The memory 204 also stores a plurality of computer-readable programming instructions, executable by the controller 202, in the form of various applications, including the application 206.

As will be understood by those skilled in the art, the controller 202 executes the instructions of the application 206 in order to perform a set of operations defined by the instructions contained therein including, but not limited to, the blocks of a method described with respect to FIG. 3. In the description below, the controller 202, and more generally the computing device 200. It will be understood that they are so configured via the execution (by the controller 202) of the instructions of the application 206 stored in the memory 204. Put another way, the computing device 200 may comprise a computer-readable storage medium (e.g., a non-transitory computer-readable storage medium) having stored thereon program instructions that, when executed by the controller 202, causes the controller 202 to perform a set of operations comprising the blocks of the method described with respect to FIG. 3.

Furthermore, when the application 206 is for implementing the ML engine 104, the application 206 may include any suitable combination of one or more machine learning algorithms, which may include machine learning algorithms for implementing a generative artificial intelligence. Such machine learning algorithms may include, but are not limited to: a deep-learning based algorithm; a neural network; a generalized linear regression algorithm; a random forest algorithm; a support vector machine algorithm; a gradient boosting regression algorithm; a decision tree algorithm; a generalized additive model; evolutionary programming algorithms; Bayesian inference algorithms, reinforcement learning algorithms, and the like. However, any suitable machine learning algorithm and/or deep learning algorithm and/or neural network and/or generative artificial intelligence algorithm and/or quantum machine learning algorithm is within the scope of present examples.

While structure of the client devices 106 and the terminals 112 is not described in detail, the client devices 106 and the terminals 112 are understood to have a similar structure as the computing device 200, but adapted for the respective functionality of the client devices 106 and the terminals 112.

Referring to FIG. 3, a flowchart of a method 300 for providing machine learning prompts on a call at a contact center server is depicted. The operations of the method 300 of FIG. 3 correspond to machine readable instructions that are executed by the server 102 and the ML engine 104, for example by the controller 202 and/or respective controllers 202 thereof. In the illustrated example, the instructions represented by the blocks of FIG. 3 may be stored at a memory 204 and/or respective memories 204 of the server 102 and the ML engine 104, for example, as the application 206. The method 300 of FIG. 3 is one way in which the system 100 and/or 102 and/or the ML engine 104 and/or the computing device 200 and/or the controller 202 may be configured. Furthermore, the following discussion of the method 300 of FIG. 3 will lead to a further understanding of the system 100, and its various components.

The method 300 of FIG. 3 need not be performed in the exact sequence as shown and likewise various blocks may be performed in parallel rather than in sequence. Accordingly, the elements of method 300 are referred to herein as “blocks” rather than “steps.” The method 300 of FIG. 3 may be implemented on variations of the system 100 of FIG. 1 and FIG. 4, as well.

Beginning at a block 302, the CC server 102 receives a call, such as the call 110.

At a block 304, the CC server 102 receives, on the call, an indication of a queue 118, of a plurality of queues 118 maintained by the CC server 102, into which to place the call.

At a block 306, the CC server 102 places the call into the queue indicated by the indication, and the call is placed into the queue in a hold state.

At a block 308, the machine learning engine 104 generates, based on historical data associated with the queue 118, one or more prompts for the call.

At a block 310, the CC server 102 provides the one or more prompts on the call during the hold state.

The method 300 is next described with respect to FIG. 4, FIG. 5, FIG. 6, FIG. 7 and FIG. 8, which are substantially similar to FIG. 1, with like components having like numbers. It is further understood in these examples that all the terminals 112 are engaged in calls and/or cannot receive a call, such as the call 110; as such any call received at the server 102, such as the call 110, is to be placed into a queue 118.

Furthermore, as has already been described, the ML engine 104 may comprise a generative artificial intelligence engine. However, any suitable machine learning engine is within the scope of the present specification.

Attention is first directed to FIG. 4, which depicts the call 110 being received (e.g., at the block 302 of the method 300) at the server 102, and in particular at the IVR engine 114. The server 102 and/or the IVR engine 114 is understood to answer the call 110, and the IVR engine 114 may provide one or more answering prompts 402 on the call 110, such as “Hello! Your call is important to us, but all our lines are busy. What are you calling about?”. Optionally, the one or more answering prompts 402 may include categories associated with the queues 118, and indications of buttons to actuate at the calling device 106-1 to select a category; in these examples, the one or more answering prompts 402 may include “Press 1 for technical problems with your router, press 2 for router sales, press 3 for a new account, press 4 for anything else”. Alternatively, and/or in addition, the one or more answering prompts 402 may be generated from historical data associated with the queues 118, for example to determine and/or estimate reasons a previous given number of callers 108 (e.g., 10 callers, 20 callers, 30 callers, amongst other possibilities) called the IVR engine 114, and such reasons may be incorporated into the one or more answering prompts 402. In general, such reasons may correspond to categories associated with the queues 118.

As depicted, he server 102 and/or the IVR engine 114 receives (e.g., at the block 304 of the method 300) on the call 110, an indication 404 of a queue 118 (e.g., of the plurality of queues 118 maintained by the server 102) into which to place the call 110. For example, the indication 404 may comprise voice data of “I am calling about a technical problem with my router” and/or an indication of button actuated at the calling device 106-1 to select one of the aforementioned categories, such as an indication of a button “1” being actuated. When the indication 404 may comprises voice data, the voice data may be converted to text.

Either way, in the present example, the indication 404 may indicate that the call 110 is to be placed into the queue 118-1.

As depicted, the indication 404 (e.g., voice data converted to text and/or an indication of button actuated at the calling device 106-1 to select one of the aforementioned categories) is provided from the IVR engine 114 to the queue engine 116 which determines with which of the queues 118 the indication 404 is associated. For example, as the queue 118-1 may be associated with technical problems with routers, the queue engine 116 may determine that the indication 404 indicates that the call 110 is to be placed into the queue 118-1.

Attention is next directed to FIG. 5, which depicts the call 110 placed (e.g., at the block 306 of the method 300) into the queue 118-1. The call 110 may be placed into the queue 118-1 by the queue engine 116. The call 110 is furthermore understood to be in a hold state (e.g., the call 110 is not transferred to a terminal 112) and placed at an end of the queue 118-1. While other calls in the queue 118-1 (or other queues 118) are not depicted, they are nonetheless understood to be present. Furthermore, the method 300 may be implemented for such calls in the queue 118-1 and/or for such calls in the other queues 118.

While in FIG. 5 the call 110 is not depicted between the calling device 106-1 and the server 102, it is understood that the server 102 maintains the call 110, and continues to communicate with the calling device 106-1 on the call 110, as described herein, while the call 110 is in queue 118-1 and/or in a hold state.

As depicted, for example in response to the call 110 being placed into the queue 118-1, the ML engine 104 receives, as input, the historical data 122 and generates (e.g., at the block 308 of the method 300) one or more prompts for the call 110 including, but not limited to, an initial prompt 502.

The historical data 122 may comprise one or more of:

- Historical caller data associated with previous calls associated with a category of the queue 118-1. For example, such historical caller data may include transcripts of previous calls placed into the queue 118-1 (e.g., and with which the ML engine 104 interacted as described herein). Alternatively, or in addition, historical caller data may comprise transcripts of previous calls transferred to a terminal 112 which indicate that such previous calls were associated with a category of the queue 118-1. Alternatively, or in addition, historical caller data may comprise records of previous calls placed into the queue 118-1 and/or transferred to a terminal 112, which indicate that such previous calls were associated with a category of the queue 118-1. Such historical caller data may indicate reasons for the previous calls, such as technical problems of respective routers of respective callers 108. In some examples, such historical caller data may further indicate how previous calls were successfully resolved, such as technical solutions for the respective routers, of respective callers 108.
- Respective historical data associated with the caller 108-1 on the call 110. For example, such historical data associated with the caller 108-1 on the call 110 may comprise previous transcripts and/or records which indicate previous reasons the caller 108-1 called the server 102, and may comprise technical problems and technical solutions for a router of the caller 108-1. Such historical data associated with the caller 108-1 on the call 110 may include the account data 124, and/or a link and/or an identifier of the account data 124.
- News data associated with a category of the queue 118-1. Such news data may be received from one or more event sources 128 via the event monitor engine 126, and may indicate events (e.g., power outages and/or internet outages, and the like) that may affect a router of the caller 108-1, and the like. Alternatively, and/or in addition, such news data may indicate weather events that may affect a router of the caller 108-1, and the like, such as storms, lightning, and the like. For example, such news data may comprise news server stories indicating such events.
- Social media data associated with the category of the queue 118-1. Similar to the news data, such social media data may be received from one or more event sources 128 via the event monitor engine 126, and may indicate events (e.g., power outages and/or internet outages, and the like) that may affect a router of the caller 108-1, and the like. Alternatively, and/or in addition, such social media may indicate weather events that may affect a router of the caller 108-1, and the like, such as storms, lightning, and the like. For example, such social media data may comprise social media posts indicating such events.

However, the historical data 122 may comprise any suitable historical data 122.

The initial prompt 502 may include one or more estimated reasons for the call 110, for example determined from the historical data 122.

For example, the historical data 122 associated with the queue 118-1 may comprises historical caller data of a given number of previous calls (e.g., 5 calls, 10 calls, 15 calls, amongst other possibilities) that preceded the call 110. Such historical data 122 may indicate that the last given number of previous calls, and/or a portion thereof, and/or a majority portion thereof (e.g., more than half of the last given number of previous calls) were about a particular technical problem, such as a router losing a connection to the internet, setting up a secure network with such a router, and the like.

As depicted, the initial prompt 502 is provided from the ML engine 104 to the server 102. The server 102, and more specifically the IVR engine 114, provides (e.g., at the block 310 of the method 300) the initial prompt 502 to the calling device 106-1. For example, the initial prompt 502 may include one or more estimated reasons for the call 110, for example as estimated from the historical data 122.

For example, the initial prompt 502 may include “Of the last ten callers, six called about losing a connection to the internet, while another four called about setting up a secure network with a router. Are calling about losing a connection to the internet or setting up a secure network with a router?”. In some examples, the initial prompt 502 provided to the calling device 106-1 may further comprise options such a “Press 1 for losing a connection to the internet; Press 2 for setting up a secure network with a router; Press 3 for other issues”, and the like.

In other examples, the initial prompt 502 (and/or other one or more prompts for the call 110) may be further based on respective historical data 122 associated with the caller 108-1 on the call 110. For example, the respective historical data 122 associated with the caller 108-1 may indicate that, in previous calls, the caller 108-1 had called about setting up a secure network with a router. In these examples, the initial prompt 502 may include: “You previously called about setting up a secure network with a router. Press 1 problems with a secure network already set up; Press 2 for setting up a secure network with a router; Press 3 for losing a connection to the internet; Press 4 for other issues”, and the like.

As depicted, the server 102 and/or the IVR engine 114 receives, in response to the initial prompt 502, a selection 504 of an estimated reason, of the one or more estimated reasons, which may include selection of one of the options previously described, or a verbal indication of the selection. For example, when a verbal indication, the selection 504 may include: “I'm calling again about setting up a secure network with my router”, and the like.

Put another way, the method 300 may further comprise: generating, via the machine learning engine 104, an initial prompt, of the one or more prompts, that includes one or more estimated reasons for the call 110; receiving, on the call 110, a selection of an estimated reason, of the one or more estimated reasons; and generating (e.g., as described hereafter), via the machine learning engine 104, the one or more prompts that follow the initial prompt 502, based on the selection 504 of the estimated reason.

Attention is next directed to FIG. 6, which depicts the selection 504 being provided to the ML engine 104, which generates, from the selection 504, and the historical data 122, one or more prompts 602 to attempt to resolve the selected reason. As also depicted in FIG. 6, the call 110 may have moved up in the queue 118-1.

Alternatively, or in addition, the features depicted in FIG. 5 may be optional and the one or more prompts 602 may be provided (e.g., without the selection 504) to resolve an estimated reason for the call 110 which may be based on the category of the queue 118-1 and associated historical data 122. For example, the historical data 122 may indicate that all (and/or a majority) of a previous given number of callers were calling about a given technical problem, and the one or more prompts 602 may be to resolve the same given technical problem. Alternatively, the historical data 122 may indicate that the caller 108-1 has made previous calls about a given technical problem, and the one or more prompts 602 may be resolve the same given technical problem.

Regardless, as depicted, the one or more prompts 602 are provided to the server 102 and provided (e.g., at the block 310 of the method 300) on the call 110, which may result in one or more responses 604 from the caller 108-1, which may again be provided to the ML engine 104 (not depicted) to generate one or more further prompts 602.

For example, continuing with the secure network example, the selection 504 input to the ML engine 104 may indicate the caller 108-1 is trying to set up a secure network with a router, and the one or more prompts 602 may comprise instructions for setting up a secure network using a router. The one or more responses 604 may be to request further details, and/or to indicate whether the setting up of the secure network using a router was successful or not.

In some examples, the one or more prompts 602 may include a final prompt which may include an indication to stay on the call 110 to be connected to a terminal 112 and, optionally, an indication of an estimated time until the call 110 is connected to a terminal 112. Such a final prompt may comprise: “If you need further assistance or have any other questions, please stay on the line, and an agent will be available to help you in minutes”.

In yet further examples such a final prompt may request input from the calling device 106-1 to indicate whether the call 110 was successful or unsuccessful. For example such a final prompt may comprise a request such as: “We'd appreciate if you enter “1” to indicate whether we resolved your issue, or “2” to indicate that your issue was not resolved”.

Put another way, the method 300 may further comprise: generating, via the machine learning engine 104, a final prompt, of the one or more prompts 602, that includes one or more of: an indication that the call 110 is to be transferred to a human-operated terminal 112; an estimated time until a transfer to the human-operated terminal 112; and a request for input from the calling device 106-1 that made the call 110 to indicate whether the call 110 was successful or unsuccessful.

The method 300 may include other features. For example, attention is next directed to FIG. 7, which depicts at least one other call 702 in the queue 118-1 that may have been received prior to the call 110, for example from the calling device 106-M. For example, a number of the calls 110, 702 in the queue 118-1 may be the same as, or less than, a number “M” of the calling devices 106 and respective callers 108. For example, the calls 702 may represent calls to the server 102 by a portion of the calling devices 106 that have been answered and placed in the queue 118-1. The various blocks of the method 300 may be applied to the calls 702.

However, as also depicted in FIG. 7, the event monitor engine 126 provides an indication 704 of an event which may have an aggregate effect on the queue 118-1. The indication 704 of the event is understood to have been determined via communications between the event monitor engine 126 and the event sources 128. In a particular example, such an event may comprise an internet outage, and the like which may, for example cause technical problems with routers.

In these examples, the historical data 122 associated with the queue 118-1 may comprise historical caller data of a given number of the previous calls 702 related to the event. For example, the historical data 122 associated with the queue 118-1 may indicate that a given number of callers 108 have called to report that the internet at their routers went out, which may be due to the internet outage indicated by the indication 704. The historical data 122 associated with the queue 118-1 may further indicate that a number of the calls 702 (e.g., call volume) in the queue 118-1 increased after the internet outage, such that the internet outage had an aggregate effect on the queue 118-1. The historical data 122 associated with the queue 118-1 may further indicate that respective reasons for the calls 702 (e.g., caller behavior) in the queue 118-1 were similar after the internet outage (e.g., callers 108 on the calls 702 may indicate that “My router does not have internet access”), such that the internet outage had a further an aggregate effect on the queue 118-1. Put another way, the historical data 122 may indicate patterns or trends influencing call volumes or caller behavior in the queue 118-1 that may have resulted from the event.

As depicted, the indication 704 of the event may indicate a type of the event, a time of the event, and the like, and/or any other information that may enable the ML engine 104 to determine patterns or trends influencing call volumes or caller behavior that may have resulted from the event.

As depicted, the ML engine 104 may receive the indication 704 of the event as input, along with the historical data 122, and generate the one or more prompts 602 that may be provided to the calling device 106-1, as well as one or more of the other calling devices 106 associated with calls 702 in the queue 118-1, to mitigate the impact of the event on the queue 118-1 during the hold state. For example, the ML engine 104 may determine, from the indication 704 and the historical data 122, that call volumes or caller behavior in the queue 118-1 have respectively increased or changed due to the event being an internet outage. To attempt to mitigate the impact of the event on the queue 118-1, the one or more prompts 602 may comprise: “There has been an internet outage which may be affecting your router; please hang up and call back if the problem persists”. Such a prompt 602 may be provided even if the caller 108-1 is calling about another technical problem (e.g., such as setting up a secure network), for example when the event may interfere with resolving the other technical problem. As depicted, the one or more prompts 602 are provided to the server 102, which provides the one or more prompts 602 to the calling device 106-1, and other calling devices 106 with associated calls 702 in the queue 118-1, such as the calling device 106-M.

Put another way, the method 300 may further comprise: identifying, via the machine learning engine 104, an event having an aggregate effect on the queue 118-1, wherein the historical data 122 associated with the queue 118-1 comprises historical caller data of a given number of previous calls 702, including other calls 702 related to the event, that preceded the call 110; analyzing, via the machine learning engine 104, the historical caller data related to the event to determine patterns or trends influencing call volumes or caller behavior resulting from the event; generating, via the machine learning engine 104, the one or more prompts 602 specifically tailored to address an impact of the event on the queue 118-1 and provide relevant information or assistance to callers 108 affected by the event; and providing, via the CC server 102, the one or more prompts 602 generated to mitigate the impact of the event on the queue 118-1.

Attention is next directed to FIG. 8, which depicts the system 100 with the ML engine 104 in a training mode, for example to better train the ML engine 104 to generate prompts. The example of FIG. 8 may follow from FIG. 6 or FIG. 7 and, as such, the call 110 is understood to have ended and hence the call 110 is no longer in the queue 118-1. As such, processing and bandwidth resources have been made available at the server 102.

As depicted, a transcript 802 of the call 110 has been generated, and may be used as training data 804 to better train the ML engine 104 to generate prompts. It is understood, for example, that the transcript 802 may include the one or more prompts 502, 602, the selection 504, and the one or more responses 604, and/or any other verbal communications (e.g., converted to text) and/or textual communications on the call 110. Alternatively, or in addition, the transcript 802 may be stored at the historical data 122 for further use in training the ML engine 104 and hence, in some examples, as depicted, the historical data 122 may also be used as training data 804. Optionally, when the indication 704 of the event was used to generate the one or more prompts 602, the indication 704 may also be used as training data 804; the optionality of the indication 704 used as training data 804 is depicted in FIG. 8 by way of the indication 704 being in broken lines.

In particular, the server 102 may be configured to determine whether the call 110 was successful or unsuccessful.

For example, as previously described, a final prompt may request input from the calling device 106-1 as to whether the call 110 was successful or unsuccessful. In some examples, receipt of “1” at the server 102 in response to such a request may indicate that the call 110 was successful, and receipt of “0” at the server 102 in response to such a request may indicate that the call 110 was unsuccessful. Alternatively, or in addition, a verbal response may be received from the caller 108-1 indicating that the call 108-1 was successful or unsuccessful. Put another way, an indication received from the calling device 106-1 may indicate whether the call 110 was successful or unsuccessful.

Alternatively, or in addition, the server 102 may determine whether the call 110 was successful or unsuccessful based on one or more a transcript 802 of the call 110, a length of the call 110, and whether the call is transferred to a human-operated terminal 112. For example, again using the secure network example, the transcript 802 of the call 110 may indicate that the call 110 was successful via text such as “Thank you, my secure network is now set up”, and the like; conversely, the transcript 802 of the call 110 may indicate that the call 110 was unsuccessful via text such as “That didn't work, I want to speak to an agent”, and the like.

Hence, when the call 110 is not transferred to a terminal 112 (e.g., the caller 108-1 operates the calling device 106-1 to hang up the call 110), the server 102 may determine that the call 110 is successful. However, when the call 110 is transferred to a terminal 112, the server 102 may determine that the call 110 is unsuccessful.

In yet further examples, a length of the call 110 may indicate whether the call 110 was successful or unsuccessful. For example, when the call 110 is less than a threshold time period, such as a time to provide the one or more prompts 602 to resolve a reason for the call 110 (e.g., such as 1 minute, 2 minutes, 3 minutes, amongst other possibilities, and which may vary depending on a number and/or length of the one or more prompts