HK40039789A - Techniques for benchmarking performance in a contact center system - Google Patents

Description

Techniques for benchmarking performance in a contact center system

The application is a divisional application of an invention patent application with the application date of 2017, 5 and 23, and the application name of the invention is 'European Affini Technical Limited liability company', the invention name of the invention is 'technology for performing benchmark test on performance in a contact center system', and the application number of the invention patent application is 201780016552.3.

Cross Reference to Related Applications

This international patent application claims priority from U.S. patent application No.15/176,899, filed on 8/6/2016, the entire contents of which are hereby incorporated by reference.

Technical Field

The present disclosure relates generally to contact centers, and more particularly to techniques for benchmarking (benchmarking) performance in a contact center system.

Background

A typical contact center algorithmically assigns contacts arriving at the contact center to agents that are available to handle the contacts. Sometimes, a contact center may have an agent available and wait for an assignment to an inbound or outbound contact (e.g., a phone call, an internet chat session, an email). At other times, the contact center may have contacts waiting in one or more queues for an agent to become available for distribution.

In some typical contact centers, contacts are assigned to agents that are sorted based on time when the agents become available, and agents are assigned to contacts that are sorted based on time of arrival. This strategy may be referred to as a "first-in-first-out", "FIFO", or "polling" strategy.

Some contact centers may use "performance-based routing" or "PBR" methods to order queues of available agents, or sometimes to order contacts. PBR ordering strategies attempt to maximize the expected outcome of each contact-agent interaction, but generally do not consider uniformly utilizing agents in a contact center.

When the contact center changes from using one pairing policy (e.g., FIFO) to another pairing policy (e.g., PBR), some agents may be available to receive contact while other agents may be talking. If the average agent performance over time is not balanced, the integrity of one pairing strategy may be affected by the unfairness of the other pairing strategy.

In view of the foregoing, it will be appreciated that there may be a need for a system that is capable of benchmarking contact center system performance, including transition management of alternative routing policies, to detect and address unbalanced average agent performance among alternative pairing policies.

Disclosure of Invention

Techniques for benchmarking performance in a contact center system are disclosed. In one particular embodiment, the technique may be realized as a method for benchmarking contact center system performance, comprising: cycling, by at least one computer processor configured to perform contact center operations, between a first contact-agent pairing policy and a second contact-agent pairing policy for pairing contacts with agents in a contact center system; determining, by the at least one computer processor, an agent utilization deviation in a first contact-agent pairing policy, the agent utilization deviation in the first contact-agent pairing policy comprising a difference between a first agent utilization of the first contact-agent pairing policy and a balanced agent utilization; and determining, by the at least one computer processor, a relative performance of the second contact-agent pairing strategy as compared to the first contact-agent pairing strategy based on the agent utilization deviation in the first contact-agent pairing strategy.

According to other aspects of this particular embodiment, the method may further include adjusting, by the at least one computer processor, the target agent utilization of the second contact-agent pairing policy to reduce the agent utilization deviation in the first contact-agent pairing policy.

According to other aspects of this particular embodiment, the method may further include determining, by the at least one computer processor, an average available agent performance for the plurality of agents during at least one transition from the first contact-agent pairing policy to the second contact-agent pairing policy.

According to other aspects of this particular embodiment, the method may further include determining, by the at least one computer processor, an average availability of at least one of the plurality of agents during at least one transition from the first contact-agent pairing policy to the second contact-agent pairing policy.

According to other aspects of this particular embodiment, the method may further include outputting, by the at least one computer processor, a transition management report including an agent utilization deviation of the first contact-agent pairing policy.

In accordance with other aspects of this particular embodiment, the first contact-agent pairing policy may be a performance-based routing policy.

In accordance with other aspects of this particular embodiment, the second contact-agent pairing policy may be an action pairing policy.

In accordance with other aspects of this particular embodiment, the second contact-agent pairing policy may be a hybrid behavior pairing policy, and the hybrid behavior pairing policy may favor a performance-based routing policy.

According to other aspects of this particular embodiment, the method may further include adjusting, by the at least one computer processor, at least one parameter of the second contact-agent pairing policy.

In accordance with other aspects of this particular embodiment, the at least one parameter includes a Kappa parameter for the hybrid behavioral pairing policy.

In accordance with other aspects of this particular embodiment, a first contact-agent pairing policy may target unbalanced agent utilization and a second contact-agent pairing policy may target balanced agent utilization.

In accordance with other aspects of this particular embodiment, the target utilization of the second contact-agent pairing policy may be adjusted at least once at one or more points in time between the transition from the first to the second contact-agent pairing policy and a subsequent transition from the second to the first contact-agent pairing policy.

In another particular embodiment, the techniques may be realized as a system for benchmarking performance in a contact center system comprising at least one processor, wherein the at least one processor is configured to perform the above-described method.

In another particular embodiment, the techniques may be realized as an article of manufacture for benchmarking performance in a contact center system, comprising: a non-transitory processor-readable medium, and instructions stored on the medium; wherein the instructions are configured to be readable from the medium by at least one processor, thereby causing the at least one processor to operate so as to perform the above-described method.

The present disclosure will now be described in more detail with reference to specific embodiments as illustrated in the accompanying drawings. Although the present disclosure is described below with reference to specific embodiments, it should be understood that the present disclosure is not limited thereto. Those of ordinary skill in the art having access to the teachings herein will recognize additional implementations, modifications, and embodiments, as well as other fields of use, which are within the scope of the present disclosure as described herein, and with respect to which the present disclosure may be of significant utility.

Drawings

For a more complete understanding of this disclosure, reference is now made to the drawings, wherein like elements are designated with like numerals. These drawings should not be construed as limiting the present disclosure, but are intended to be exemplary only.

Fig. 1 shows a block diagram of a contact center system according to an embodiment of the present disclosure.

Fig. 2 shows a schematic representation of an agent transition table according to an embodiment of the present disclosure.

Fig. 3 shows a schematic representation of an agent transition table according to an embodiment of the present disclosure.

Fig. 4 illustrates a schematic representation of an agent transition diagram according to an embodiment of the present disclosure.

Fig. 5 illustrates a schematic representation of an agent transition diagram according to an embodiment of the present disclosure.

Figure 6 shows a schematic representation of an agent transition diagram according to an embodiment of the present disclosure,

fig. 7 shows a schematic representation of an agent transition diagram according to an embodiment of the disclosure.

FIG. 8 illustrates a flow diagram of a benchmarking transition management method according to an embodiment of the present disclosure.

Detailed Description

A typical contact center algorithmically assigns contacts arriving at the contact center to agents that are available to handle the contacts. Sometimes, a contact center may have an agent available and wait for an assignment to an inbound or outbound contact (e.g., a phone call, an internet chat session, an email). At other times, the contact center may have contacts waiting in one or more queues for an agent to become available for distribution.

In some typical contact centers, contacts are assigned to agents that are sorted based on time when the agents become available, and agents are assigned to contacts that are sorted based on time of arrival. This strategy may be referred to as a "first-in-first-out", "FIFO", or "polling" strategy. For example, the longest available agent pairing policy preferably selects the available agent that has been available for the longest time.

Some contact centers may use "performance-based routing" or "PBR" methods to order queues of available agents, or sometimes to order contacts. PBR ordering strategies attempt to maximize the expected outcome of each contact-agent interaction, but generally do not consider uniformly utilizing agents in a contact center. Some variations of PBR may include a highest performing agent pairing strategy, preferably selecting the available agent with the highest performance, or a highest performing agent pairing strategy for a type of contact, preferably selecting the available agent with the highest performance for the type of contact paired.

As yet another example, some contact centers may use a "behavioral pairing" or "BP" strategy under which contacts and agents may be intentionally (preferably) paired in a manner that enables subsequent contact-agent pairs to be assigned, such that when all assigned benefits under the BP strategy are aggregated, the benefits of the FIFO and PBR strategies may be outweighed. The BP is designed to encourage balanced utilization of agents within the skilled queue while still improving overall contact center performance beyond that permitted by the FIFO or PBR approach. This is a trivial achievement since BP works on the same calls and the same agents as the FIFO or PBR methods, making substantially uniform use of the agents as provided by the FIFO, still improving overall contact center performance. BP is described, for example, in U.S. patent No.9,300,802, the entire contents of which are incorporated herein by reference. Additional information regarding these and other features of a pairing or matching module (also sometimes referred to as a "SATMAP," "routing system," "routing engine," etc.) is described, for example, in U.S. patent No.8,879,715, which is incorporated herein by reference in its entirety.

In some embodiments, the contact center may periodically switch (or "cycle") between at least two different pairing strategies (e.g., between FIFO and PBR; between PBR and BP; between FIFO, PBR, and BP). In addition, the results of each contact-agent interaction may be logged along with the identification of the pairing policy (e.g., FIFO, PBR, or BP) that has been used to assign the identification of that particular contact-agent pair. By tracking which interaction produces which result, the contact center can measure performance attributable to a first policy (e.g., FIFO) and performance attributable to a second policy (e.g., PBR). In this manner, the relative performance of one strategy may be benchmarked relative to another strategy. Over many switching periods between different pairing strategies, the contact center can more reliably attribute performance gains to one strategy or another. Additional information regarding these and other features of benchmarking pairing strategies is described in, for example, U.S. patent application No.15/131,915 filed on 2016, 4, 20.

When the contact center changes from using one pairing policy (e.g., PBR) to another pairing policy (e.g., BP), some agents may be available to receive the contact while other agents may be interacting with the contact (e.g., in a call). If the average agent performance over time is not balanced, the overall performance of one pairing strategy may be unfairly affected by the other pairing strategy. For example, when a contact center uses PBR to pair contacts and agents, a high performing agent is more likely to be busy interacting with the contact, while a low performing agent is more likely to be idle. Thus, when transitioning from PBR to another pairing strategy such as BP, the average performance of the available agents over time may be lower than the average performance of all agents including both available and busy agents.

Fig. 1 shows a block diagram of a contact center system according to an embodiment of the present disclosure. As shown in fig. 1, the contact center system 100 can include a central switch 110. The central switch 110 may receive an incoming contact (e.g., caller) or support an outgoing connection to the contact via a telecommunications network (not shown). Central switch 110 may include contact routing hardware and software to facilitate routing contacts between one or more contact centers, or to facilitate one or more PBX/ACD or other queuing or switching components within a contact center.

If there is only one contact center, or only one PBX/ACD routing component in the contact center system 100, then the central switch 110 may not be necessary. If more than one contact center is part of contact center system 100, each contact center may include at least one contact center switch (e.g., contact center switches 120A and 120B). Contact center switches 120A and 120B may be communicatively coupled to center switch 110.

Each contact center switch of each contact center may be communicatively coupled to a plurality of agents (or "pools"). Each contact center switch may support a certain number of agent (or "seat") entries at the same time. At any given time, a logged-on agent may be available and waiting to connect to a contact, or a logged-on agent may not be available for a variety of reasons, such as connecting to another contact, performing post-call functions such as recording information about a call, or taking a break.

In the example of fig. 1, central switch 110 sends the contact to one of two contact centers via contact center switch 120A and contact center switch 120B, respectively. Each contact center switch 120A and 120B is shown with two agents, respectively. Agents 130A and 130B may be logged into contact center switch 120A, while agents 130C and 130D may be logged into contact center switch 120B.

The contact center system 100 may also be communicatively coupled to integration services from, for example, third party vendors. In the example of fig. 1, transition management module 140 may be communicatively coupled to one or more switches in a switch system of contact center system 100, such as center switch 110, contact center switch 120A, or contact center switch 120B. In some embodiments, a switch of contact center system 100 may be communicatively coupled to a plurality of benchmarking modules. In some embodiments, the transition management module 140 may be embedded within a component of the contact center system (e.g., embedded in or otherwise integrated with the switch). The transition management module 140 may receive information about agents (e.g., agents 130A and 130B) logged into the switch and information about incoming contacts via another switch (e.g., central switch 110) from the switch (e.g., contact central switch 120A), or, in some embodiments, from a network (e.g., the internet or a telecommunications network) (not shown).

The contact center may include a plurality of paired modules (e.g., a BP module and a FIFO module) (not shown), and one or more of the paired modules may be provided by one or more different vendors. In some embodiments, one or more of the pairing modules may be a component of the transition management module 140 or one or more switches, such as the central switch 110 or the contact central switches 120A and 120B. In some embodiments, the transition management module 140 may determine which pairing module may handle a particular contact pairing. For example, the transition management module 140 may alternate between enabling pairing via the BP module and enabling pairing through the FIFO module. In other embodiments, one pairing module (e.g., a BP module) may be configured to emulate other pairing policies. For example, the transition management module 140 or a conversion management component integrated with the BP component in the BP module can determine whether the BP module can pair BPs or emulate FIFOs for a particular association. In this case, "BP on" may refer to the time when the BP module is applying a BP pairing policy, while "BP off" may refer to other times when the BP module is applying a different pairing policy (e.g., FIFO).

In some embodiments, a single pairing module may be configured to monitor and store information about pairings made under any or all pairing policies, whether the pairing policies are handled by separate modules or if some pairing policies are emulated within the single pairing module. For example, the BP module may observe and record data of FIFO pairings made by the FIFO module, or the BP module may observe and record data of emulated FIFO pairings made by the BP module operating in FIFO emulation mode.

Embodiments of the present disclosure are not limited to benchmarking transition management of only two pairing policies. Instead, benchmark transition management (e.g., of FIFOs, PBRs, and BPs) may be performed on two or more pairing policies.

Fig. 2 shows a schematic representation of an agent transition table 200 according to an embodiment of the present disclosure. In the example of fig. 2, four agents named "Alice," "Bob," "Charlie," and "Donna" may be assigned to a particular queue to interact with a contact. These agent names are for example purposes only; in some embodiments, an anonymous identification number or other identification may be used to represent an agent in a contact center. Furthermore, this highly simplified example shows only four agents. In some embodiments, hundreds of agents, thousands of agents, or more agents may be assigned to a queue and may be illustrated in an agent transition table.

The agent transition table 200 shows five transitions labeled "201", "202", "203", "204", and "205". In some embodiments, each transition may represent a point in time at which the contact center switches from one pairing policy (e.g., FIFO) to another pairing policy (e.g., BP). The transition may occur multiple times per hour (e.g., every 10 minutes, every 15 minutes, every 30 minutes), or more or less frequently within a day, week, month, year, etc. In some embodiments, the transition may be identified by the time at which the transition occurs. For example, transition 201 may occur at time 9:15AM, transition 202 may occur at time 9:45AM, and so on.

At transition 201, the agents Alice and Bob are unavailable, as indicated by the shaded cells. For example, Alice and Bob may be interacting with the contact, or they may otherwise be occupied by post-interaction tasks such as recording sales or archiving customer service reports. Meanwhile, the agents Charlie and Donna are idle or otherwise may connect to the contact as shown by the unshaded cell.

Similarly, at transition 202, the agents Charlie and Donna are busy and the agents Alice and Bob are available. At transition 203, the agents Alice and Charlie are busy, while the agents Bob and Donna are available. At transition 204, agents Bob and Donna are busy, while agents Alice and Charlie are available. At transition 205, agents Bob and Charlie are busy, while agents Alice and Donna are available.

In any single transition, even pairing strategies that target balanced agent utilization (e.g., FIFO and BP, but not PBR) may appear to have skewed utilization at the transition. For example, if Alice has a normalized performance rating of 80, Bob has a rating of 60, Charlie has a rating of 40, and Donna has a rating of 20, then the average performance for all agents is 50. However, the average performance of the available agents (i.e., Charlie and Donna) at transition 201 was 30, lower than average. The average performance of the available agents at the transition 202 was 70, above average. The average performance of the available agents at the transition 203 is 40, below the average level. The average performance of the available agents at the transition 204 is 60, above average.

In some transitions, even pairing strategies (e.g., PBR) targeting unbalanced agent utilization may appear to have balanced utilization at the time of transition. For example, at the transition 205, the average performance of the available agents (i.e., Alice and Donna) is 50.

The average performance of available agents over time (e.g., over a day) over multiple transitions may reflect the statistically expected utilization of a given pairing strategy, despite differences in the average performance of available agents in any single transition. The agent transition table 200 illustrates five transitions 201 and 205, which in some embodiments may not be a statistically significant number of transitions. However, for exemplary purposes, the average available agent performance over the course of the five transitions 201-. In this example, the average available agent performance at the transition in the course of the five transitions 201 and 205 is balanced.

In some embodiments, in addition to or instead of determining the average performance of available agents over one or more transitions, the average availability of individual agents may also be determined and output. For example, in the agent transition table 200, the average availability of each agent per transition 201 and 205 is 60% for Alice (3 out of 5 transitions), 40% for Bob (2 out of 5 transitions), 40% for Charlie (2 out of 5 transitions) and 60% for Donna (4 out of 5 transitions). For pairing strategies that target balanced agent utilization (e.g., FIFO or BP), statistically potentially roughly the same number of times or the same proportion of transitions per agent are available. In this simplified example, where only five transitions 201 and 205 are depicted, the average availability of each agent varies between 40% and 60%. However, the average availability of each agent may statistically converge to the same percentage over time. For example, after 100 transitions, the average availability of each agent may be approximately the same, e.g., 50%, 55%, 60%, etc.

Fig. 3 shows a schematic representation of an agent transition table 300 according to an embodiment of the present disclosure. In contrast to the example of the agent transition table 200 (fig. 2), the agent transition table 300 shows the results that would normally be expected in a contact center using an unbalanced pairing strategy such as PBR. In some embodiments of PBR, the most performing agent (i.e., Alice) may preferably be selected to interact with the contact. Therefore, Alice is never available at any of transitions 301-305. At the same time, the least performing agent (i.e., Donna) is always available at each transition 301-305.

The average performance of the available agents is 30 at transition 301, 40 at transition 302, 30 at transition 303, 20 at transition 304, and 40 at transition 305. The average performance of the available agents during the five transitions 301-305 is (30+40+30+20+ 40)/5-32, which is unbalanced. Over time, the effectiveness of alternative pairing strategies after each transition may be "tainted," biased, or otherwise affected to the extent that the average performance of the available agents indicates a statistically significant amount of deviation in agent utilization, resulting in potentially unfair benchmarking measurements.

In some embodiments, in addition to or instead of determining the average performance of available agents over one or more transitions, the average availability of individual agents may also be determined and output. For example, in the agent transition table 300, the average availability of each agent per transition 301-305 is 0% for Alice (0 out of 5 transitions), 40% for Bob (2 out of 5 transitions), 60% for Charlie (3 out of 5 transitions), and 100% for Donna (5 out of 5 transitions). For pairing strategies that target unbalanced agent utilization (e.g., PBR), certain agents (e.g., agents with lower performance) may be statistically significantly more available than others (e.g., agents with higher performance). Even in this simplified example, illustrating only five transitions 501-505, the average availability of each agent varies significantly between 0% and 100%. Over time, the statistical significance of the change in average availability of each agent may be further confirmed. In this context, unbalanced pairing strategies such as PBR always or almost always hand over a less performing agent to the next pairing strategy (e.g., BP or FIFO), while more performing agents are never or almost never switched over. As described above with reference to average agent quality at one or more transitions, the effectiveness of alternative pairing strategies after each transition may be "tainted," biased, or otherwise affected to the extent that the average availability of agents over time indicates a statistically significant amount of bias in agent utilization, resulting in a potentially unfair benchmarking measure.

Fig. 4 illustrates a schematic representation of an agent transition diagram 400 according to an embodiment of the present disclosure. In the agent transition diagram 400, the x-axis represents a time period. For example, in a week, x ═ 0 may denote the first day, x ═ l denotes the second day, and so on. The y-axis represents the average performance of the available agents in all transitions from the first pairing strategy to the second pairing strategy during a given time period. For example, at x ═ 0 (e.g., day 1), the average performance of the available agents at the time of day's transition is 50. At x-1 (e.g., day 2), the average performance is slightly higher than the average, and at x-3 (e.g., day 4), the average performance is slightly lower than the average. However, the agent transition diagram 400 shows relatively stable average performance over a relatively long period of time (e.g., one week). In some embodiments, the small amount of variability per day may be statistically insignificant, and the overall agent utilization of the first pairing strategy is balanced.

Fig. 5 illustrates a schematic representation of an agent transition diagram 500 according to an embodiment of the present disclosure. In the agent transition chart 500, the overall agent utilization remains stable at about 25 per day, significantly below the average. Thus, the overall agent utilization of the pairing strategy (e.g., PBR) is unbalanced.

When benchmarking between multiple pairing strategies, a first pairing strategy (e.g., PBR) may "contaminate" or otherwise bias the performance of a second pairing strategy (e.g., FIFO or BP). At each transition from PBR to BP, the average performance of the available agents may be significantly lower than the overall average performance (i.e., imbalance) of all the agents assigned to the queue. This "throttled" pool of agents at the beginning of a BP or FIFO cycle may impair the overall performance of the BP or FIFO for that cycle.

Conversely, the average performance of the available agents in each transition from BP or FIFO to PBR may be similar to or equal to the overall average performance (i.e., balance) of all agents assigned to the queue. This balanced seat pool at the beginning of each PBR cycle may enhance the overall performance of the PBR for that cycle, since even a balanced seat pool may be better than a typical seat pool caused by PBR.

Because each PBR cycle may make the agent pool more "dirty" (unbalanced) than it is received, and each BP or FIFO cycle may make the agent pool "cleaner" (balanced) than it is received, some techniques for benchmarking PBRs against BPs or FIFOs may make it appear that a BP or FIFO will perform less well than if a PBR cycle would not dirty its available agent pool at the beginning of each cycle. Therefore, it is helpful to compare the average performance of the available agents at the beginning of the cycle ("first half") with the average performance of the available agents at the end of the cycle ("second half").

Fig. 6 shows a schematic representation of an agent transition diagram 600 according to an embodiment of the present disclosure. The agent transition diagram 600 shows an exemplary first half/second half comparison. At x ═ 0 (e.g., day 1), the difference between the average performance of the available agents transitioning to and from the first pairing strategy over the course of a day is 0. At x ═ 1, the difference is slightly above 0, and at x ═ 3, the difference is slightly below 0, but the overall difference remains close to 0 over the week. Conceptually, the pairing strategy brings each other's pool of agents to approximately the same average performance (e.g., quality).

The mean difference of 0 does not necessarily mean that both pairing strategies are balanced (e.g., the average performance of the available agents is about 50). For example, if the first pairing strategy is PBR _ a with average available agent performance of 25 and the second pairing strategy is PBR _ B with average available agent performance of 25, the difference is still 0. From a benchmarking perspective, two pairing strategies that are unbalanced are acceptable if the degree to which each pairing strategy is unbalanced is approximately the same. In this way, each pairing strategy makes the agent pool as severe as when it was found, and the pairing strategy does not contaminate the other.

Fig. 7 shows a schematic representation of an agent transition diagram 700 according to an embodiment of the present disclosure. The agent transition diagram 700 shows another example of a first half/second half comparison. At x0 (e.g., day 1), the difference between the average performance of the available agents that transition to and from the first pairing strategy in one day is 25. At x 1 the difference is slightly above 25, and at x 3 the difference is slightly below 25, but the total difference over one week remains close to 25. Conceptually, one of the pairing strategies contaminates the agent pool of the other pairing strategy consistently and significantly during the transition. For example, if the first half of the PBR policy always receives a pool of agents with an average performance of 50, and the second half of the PBR policy always provides a pool of agents with an average performance of only 25, then the difference averages 25.

An average difference significantly above 25 does not necessarily mean that any of the pairing strategies are balanced (e.g., the average performance of the available agents is about 50). For example, if the first pairing strategy is PBR _ a with an average available agent performance of 25 and the second pairing strategy is PBR _ B with an average available agent performance of 0, the difference is still 25. The PBR _ B pairing strategy still contaminates the benchmarking, resulting in PBR _ a performing worse than without cycling to PBR _ B, and PBR _ B performing better than without cycling to PBR _ a.

FIG. 8 illustrates a flow diagram of a benchmarking transition management method 800 according to an embodiment of the present disclosure. At block 810, the baseline detection transition management method 800 may begin. The contact center system may cycle through at least two pairing strategies. For example, the contact center system may switch between BP and PBR pairing strategies. In each transition from BP to PBR, or vice versa, the agents available at each transition may be determined.

At block 810, a first average performance of available agents at the transition from a first pairing policy (e.g., BP) to a second pairing policy (e.g., PBR) over time may be determined based on the determination of available agents for each transition and their relative or otherwise normalized performance. The first average performance may also be considered a "first half" measure of the second pairing strategy for that time period.

At block 820, in some embodiments, a second average performance of available agents at the transition from the second pairing policy (e.g., PBR) to the first pairing policy (e.g., BP) over time may be determined based on the determination of available agents for each transition and their relative or otherwise normalized performance. The second average performance may also be considered a "second half" measure of the second pairing strategy for that time period.

At block 830, in some embodiments, an average performance difference between the first and second average performances may be determined. If the difference is equal to or near zero, it may be determined that there is no significant difference between the average performance of the available agents received from or provided to the first pairing strategy during the measured time period. If the difference is greater than zero, it may be determined that the average performance of the available agents provided by the first pairing policy (e.g., BP) is higher than the average performance of the available agents provided by the second pairing policy (e.g., PBR), indicating that the second pairing policy may be polluting the pool of available agents and benchmarks.

At block 840, in some embodiments, a transition management report may be generated. In some embodiments, the transition management report may include the first average performance difference determined at block 810, the second average performance difference determined at block 820, the average performance difference determined at block 840, or any combination thereof. The data may be presented in a variety of formats, including but not limited to, an agent transition table (e.g., agent transition tables 200 and 300 (fig. 2 and 3)) or an agent transition chart (e.g., agent transition charts 400,500,600, and 700 (fig. 4-7)). Reports may be dynamically generated and continuously or periodically updated. The report may include user interface elements for displaying, sorting, filtering, or otherwise selecting which data to display and how to display it. The report may be fully auditable so that the viewer can review the source data for each element. For example, the reporting interface may include a user interface element that displays a list of agent identifiers available at a given transition and their corresponding relative or normalized performance metrics.

At block 850, in some embodiments, at least one parameter of the first or second pairing strategies may be adjusted, for example, to reduce the average performance differential determined at block 830. Reducing or eliminating the non-zero average performance difference may reduce or eliminate the extent to which one pairing strategy inhibits performance or contaminates benchmark testing of a second pairing strategy.

For example, in a contact center system that cycles between PBR and BP, the PBR may inhibit the configuration of the BP with the goal of evenly utilizing the agents. Various techniques allow BP to target uneven utilization of agents. For example, adjusting the "Kappa" parameter may bias the BP toward the PBR in terms of seat utilization. Kappa is described, for example, in U.S. patent application No.14/956,086, the entire contents of which are incorporated herein by reference.

If Kappa is high enough, baseline detection rejection or contamination may be eliminated (e.g., average performance difference of zero). However, in certain circumstances, high Kappa values may reduce overall BP performance. In these cases, it may be desirable to compensate for PBR baseline contamination by having a high initial Kappa value after the transition from PBR to BP, and reduce or eliminate Kappa adjustments (e.g., Kappa reduction from 1.5 to 1.0) within the first 3 minutes, 10 minutes, etc. The rate of this "Kappa decay" can be adjusted to balance the baseline suppression from the PBR with the overall performance of the first half of the BP cycle.

Similarly, it may be desirable to have a high Kappa value prior to the transition from BP to PBR, creating or increasing Kappa adjustment within the last 3 minutes, 10 minutes, etc. (e.g., Kappa increases from 1.0 to 1.5). The rate of this "reverse Kappa decay" can be adjusted to balance the baseline suppression from the PBR with the overall performance in the latter half of the BP cycle.

In a contact center system that cycles between FIFO and BP, the average performance difference can typically be zero, since both FIFO and BP are targeted to balance agent utilization. However, in certain circumstances, it may be desirable or preferable for BP to target unbalanced agent utilization (e.g., Kappa values greater than 1.0). If the BP targets unbalanced agent utilization, the average performance difference compared to the FIFO may not be zero, indicating a baseline detection of throttling or pollution. In these cases, it may be desirable to reduce or eliminate Kappa adjustment (e.g., Kappa reduction from 1.5 to 1.0) within the last 3 minutes, 10 minutes, etc. The rate of this "Kappa decay" can be adjusted to reduce the average performance difference between BP and FIFO to zero while balancing the optimization of overall BP performance.

After block 850, the baseline transition management method 800 may end. In some embodiments, the benchmarking transition management method 800 may return to block 810. In some embodiments, the various steps may be optional, performed in a different order, or performed in parallel with other steps. For example, the adjustment of the at least one parameter at block 850 may be optional or may be performed prior to or concurrently with the generation of the transition management report at block 840.

At this point, it should be noted that benchmarking performance in a contact center system according to the present disclosure as described above may involve, to some extent, processing input data and generating output data. The input data processing and output data generation may be implemented in hardware or software. For example, certain electronic components may be used in a transition management module or similar or related circuitry for implementing functions associated with benchmarking performance in a contact center system in accordance with the present disclosure as described above. Alternatively, one or more processors operating in accordance with instructions may implement the functions associated with benchmarking performance in a contact center system in accordance with the present disclosure as described above. If this is the case, it is within the scope of the disclosure that the instructions may be stored on one or more non-transitory processor-readable storage media (e.g., a magnetic disk or other storage medium) or transmitted to the one or more processors via one or more signals embedded in one or more carrier waves.

The present disclosure is not to be limited in scope by the specific embodiments described herein. Indeed, other various embodiments of the present disclosure and modifications thereof, in addition to those described herein, will be apparent to those of ordinary skill in the art from the foregoing description and accompanying drawings. Accordingly, such other embodiments and modifications are intended to fall within the scope of this disclosure. Moreover, although the present disclosure is described herein in the context of at least one particular implementation in at least one particular environment for at least one particular purpose, those of ordinary skill in the art will recognize that its usefulness is not limited thereto and that the present disclosure may be beneficially implemented in any number of environments for any number of purposes. Accordingly, the claims should be construed in view of the full breadth and spirit of the present disclosure as described herein.

Claims (15)

1. A method for pairing contacts with agents in a contact center system, comprising:

determining, by at least one computer processor communicatively coupled to the contact center system and configured to operate in the contact center system, a first amount of performance mitigation for a first contact-agent pairing strategy through a second contact-agent pairing strategy;

adjusting, by the at least one computer processor, a target agent utilization of the first contact-agent pairing strategy to compensate for at least a portion of the first performance inhibiting amount; and

pairing, by the at least one computer processor, at least one contact with at least one agent in the contact center system using the first contact-agent pairing policy according to the adjusted target agent utilization,

wherein the compensation for the at least a portion of the first performance inhibiting amount optimizes performance of the contact center system.

2. The method of claim 1, further comprising:

generating, by the at least one computer processor, a representation of the relative performance of the contact center system based on the first performance throttling amount using the first contact-agent pairing strategy as compared to the second contact-agent pairing strategy.

3. The method of claim 1, in which the first amount of performance throttling is attributable to a first amount of agent utilization deviation in the second contact-agent pairing strategy.

4. The method as recited in claim 1, wherein determining the first amount of performance throttling comprises:

determining, by the at least one computer processor, an average available agent performance for a plurality of agents during at least one transition from the second contact-agent pairing policy to the first contact-agent pairing policy.

5. The method of claim 1, wherein the first contact-agent pairing policy is a behavioral pairing policy, and

wherein the adjustment to the target agent utilization biases the first contact-agent pairing policy toward a performance-based routing policy.

6. The method of claim 1, wherein the second contact-agent pairing policy is a performance-based routing policy.

7. The method of claim 1, wherein the adjustment to the target agent utilization further comprises:

adjusting, by the at least one computer processor, a Kappa parameter of a hybrid behavior pairing policy.

8. A system for pairing contacts with agents in a contact center system, comprising:

at least one computer processor communicatively coupled to the contact center system and configured to operate in the contact center system, wherein the at least one computer processor is configured to:

determining a first performance throttling amount of the first contact-agent pairing strategy through the second contact-agent pairing strategy;

adjusting a target agent utilization of the first contact-agent pairing strategy to compensate for at least a portion of the first performance inhibiting amount; and

pairing at least one contact with at least one agent in the contact center system using the first contact-agent pairing policy according to the adjusted target agent utilization,

wherein the compensation of the at least a portion of the first performance inhibiting amount optimizes performance of the contact center system.

9. The system of claim 8, wherein the at least one computer processor is further configured to:

generating a representation of the relative performance of the contact center system using the first contact-agent pairing strategy compared to the second contact-agent pairing strategy based on the first performance throttling amount.

10. The system of claim 8, wherein the first amount of performance throttling is attributable to a first amount of agent utilization deviation in the second contact-agent pairing strategy.

11. The system of claim 8, wherein determining the first amount of performance throttling comprises:

determining an average available agent performance for a plurality of agents during at least one transition from the second contact-agent pairing strategy to the first contact-agent pairing strategy.

12. The system of claim 8, wherein the first contact-agent pairing policy is a behavioral pairing policy, and

wherein the adjustment to the target agent utilization biases the first contact-agent pairing policy toward a performance-based routing policy.

13. The system of claim 8, wherein the second contact-agent pairing policy is a performance-based routing policy.

14. The system of claim 8, wherein the adjustment to the target agent utilization comprises adjusting a Kappa parameter of a hybrid behavior pairing policy.

15. An article of manufacture for pairing contacts with agents in a contact center system, comprising:

a non-transitory computer processor readable medium; and

instructions stored on the medium;

wherein the instructions are configured to be readable from the medium by at least one computer processor communicatively coupled to the contact center system and configured to operate in the contact center system, thereby causing the at least one computer processor to operate to:

determining a first performance throttling amount of the first contact-agent pairing strategy through the second contact-agent pairing strategy;

adjusting a target agent utilization of the first contact-agent pairing strategy to compensate for at least a portion of the first performance inhibiting amount; and

pairing at least one contact with at least one agent in the contact center system using the first contact-agent pairing policy according to the adjusted target agent utilization,

wherein the compensation of the at least a portion of the first performance inhibiting amount optimizes performance of the contact center system.