Methods, systems, and articles of manufacture to pair contacts with agents in a contact center system

Abstract

The present disclosure provides a method for pairing contacts with agents in a contact center system, comprising: determining a threshold statistic; determining an ordered set of contacts; determining a first set of statistics corresponding to the ordered set of contacts; determining a second set of statistics corresponding to the ordered set of contacts and based on the first set of statistics; determining a subset of the ordered set of contacts based on the second set of statistics and the threshold statistic; and pairing a selected contact from the subset of the ordered set of contacts with an idle agent based on a pairing strategy, wherein the second set of statistics is based on a cumulative summation of the first set of statistics.

Description

Technical Field

[0001] This disclosure generally relates to allocation strategies, and more specifically, to techniques for matching contacts with agents in a contact center system. Background Technology

[0002] A contact center is a system used to receive or transmit large volumes of contact information, such as voice phone calls, web text chat, emails, and video calls. A contact center can include an outbound contact center that transmits outbound calls and / or an inbound contact center that receives inbound calls. Outbound contact centers are typically used for applications such as selling products, collecting outstanding credit balances, or surveying consumer sentiment. Inbound contact centers are also used for selling or cross-selling products, providing services for customer support or technical support inquiries, retaining customers, upgrading and downgrading services, or for other applications.

[0003] Several allocation strategies can be used to match agents with contacts. In some traditional contact centers, contacts are allocated to agents sequentially based on their arrival time or agent availability. This strategy can be called a first-in-first-out (FIFO) strategy. For example, if a contact center has multiple agents available to receive contacts ("a surplus of agents"), the FIFO strategy will allocate incoming contacts to the agent with the longest waiting time. Similarly, if multiple contacts are waiting to be allocated ("a surplus of contacts"), the FIFO strategy will allocate the longest-waiting contact to the agent who becomes available first. However, FIFO only seeks to balance agent or contact wait times and may not align with other contact center metrics such as revenue generation, increased customer satisfaction, or cost reduction.

[0004] To better optimize other contact center metrics, some contact centers employ alternative agent-customer allocation strategies. One example of this is performance-based routing (“PBR”). In a PBR strategy, if a contact center has multiple agents available to receive calls, incoming calls are assigned to the agent with a history of better performance compared to other available agents. Similarly, if all agents are occupied and many calls are waiting to be assigned, a PBR strategy assigns the calls it identifies as having the highest expected value (highest potential for a successful interaction) to the first agent to become available. However, PBR strategies can skew agent utilization, assigning more calls to some agents than others. Likewise, PBR strategies can have a detrimental effect on calls, meaning some calls may never be assigned to an agent or some agents may be highly overutilized.

[0005] Another example of an allocation strategy is the behavioral pairing (BP) strategy. Compared to the FIFO strategy, the BP strategy seeks to balance agent utilization with customer wait times while still improving contact center metrics. In the BP strategy, contacts are paired with agents in a way that optimizes the overall expected value of all agents and contacts in two queues.

[0006] However, in environments with abundant contacts, contacts may take longer to pair with available agents using a BP (Backup Plan) strategy compared to the time required for pairing in a FIFO (First-In, First-Out) strategy. Therefore, in a BP strategy, some contacts may be more likely to abandon the interaction before connecting to an agent. Consequently, the proportion of contacts that abandon the interaction (“abandonment rate”) in a BP strategy may be higher than in a FIFO strategy.

[0007] To reduce the abandonment rate of the Backpropagation (BP) strategy in environments with excessive communication, U.S. Patent No. 10,509,671 discloses a method for behavior pairing in a task allocation system, wherein a queue of waiting contacts is filtered before applying a pairing strategy. This filtering selects a predetermined number (“N”) of contacts with the longest waiting times from the queue. The filtered set of contacts is called the “top N” subset of contacts. After establishing the top N subset, the contact center can apply the BP strategy only to this subset, thereby excluding the remaining contacts with long waiting times from the queue. This method is also known as the top N strategy.

[0008] However, this strategy ignores the actual time each connection waits in the queue. Therefore, the top N subsets may contain connections with significantly different waiting times. For example, in a top N subset with three connections, the first connection might have waited 100 seconds, the second 2 seconds, and the third 1 second. In this case, all three connections in the top N subset will have the same probability of being assigned in the BP strategy, even though the first connection might be more likely to be abandoned than the second and third. Therefore, while the top N strategy improves upon the BP strategy, the abandonment rate may still be significantly higher.

[0009] Therefore, an improved strategy is needed to match contacts with agents in contact center systems in order to further reduce abandonment rates. Summary of the Invention

[0010] Embodiments of this disclosure provide a method for matching contacts with agents in a contact center system, comprising: determining a threshold statistic; determining an ordered set of contacts; determining a set of first statistics corresponding to the ordered set of contacts; determining a set of second statistics corresponding to the ordered set of contacts and based on the set of first statistics, wherein the set of second statistics is based on the cumulative summation of the set of first statistics; determining a subset of the ordered set of contacts based on the set of second statistics and the threshold statistic; and matching contacts selected from the subset of the ordered set of contacts with available agents based on a matching strategy.

[0011] Optionally, in the above method, the set of the first statistics and the set of the second statistics are based on the waiting time.

[0012] Optionally, in the above method, the threshold statistic is based on the average, maximum, or minimum value of the set of the first statistics.

[0013] Optionally, in the above method, the pairing strategy is BP.

[0014] Optionally, in the above method, the pairing strategy is based on contact priority.

[0015] Embodiments of this disclosure also provide a system for matching contacts with agents in a contact center system, comprising: at least one computer processor connected to an intelligent matching module configured to match contacts with agents in the contact center system, wherein the at least one computer processor is further configured to: determine a threshold statistic; determine an ordered set of contacts; determine a set of first statistics corresponding to the ordered set of contacts; determine a set of second statistics corresponding to the ordered set of contacts and based on the set of first statistics, wherein the set of second statistics is based on a cumulative summation of the set of first statistics; determine a subset of the ordered set of contacts based on the set of second statistics and the threshold statistic; and match contacts selected from the subset of the ordered set of contacts with available agents based on a matching strategy.

[0016] Optionally, in the above system, the set of the first statistics and the set of the second statistics are based on the waiting time.

[0017] Optionally, in the above system, the threshold statistic is based on the average, maximum, or minimum value of the set of the first statistics.

[0018] Optionally, in the above system, the pairing strategy is a BP strategy.

[0019] Optionally, in the above system, the pairing strategy is based on contact priority.

[0020] Embodiments of this disclosure also provide an article of manufacture for matching contacts with agents 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 computer processor connected to an intelligent matching module configured to match contacts with agents in the contact center system, such that the at least one computer processor operates to: determine a threshold statistic; determine an ordered set of contacts; determine a set of first statistics corresponding to the ordered set of contacts; determine a set of second statistics corresponding to the ordered set of contacts and based on the set of first statistics, wherein the set of second statistics is based on a cumulative summation of the set of first statistics; determine a subset of the ordered set of contacts based on the set of second statistics and the threshold statistic; and match contacts selected from the subset of the ordered set of contacts with available agents based on a matching strategy.

[0021] Optionally, in the above-described product, the set of the first statistics and the set of the second statistics are based on the waiting time.

[0022] Optionally, in the above-described product, the threshold statistic is based on the average, maximum, or minimum value of the set of the first statistics.

[0023] Optionally, in the above-described article, the pairing strategy is BP.

[0024] Optionally, in the above-described articles, the pairing strategy is based on contact priority. Attached Figure Description

[0025] Figure 1 This is a schematic diagram illustrating a contact center system according to an embodiment of the present disclosure.

[0026] Figure 2 This is a flowchart illustrating a method for matching contacts with agents in a contact center system according to an embodiment of the present disclosure.

[0027] Figure 3 This is a schematic diagram illustrating a method for pairing contacts with agents in a contact center system according to an embodiment of the present disclosure. Detailed Implementation

[0028] To more clearly illustrate the technical solutions of this disclosure, the accompanying drawings required for the embodiments of the present invention will be briefly described below. Obviously, the following drawings only relate to some embodiments of the present invention. Based on these drawings, those skilled in the art can obtain all other embodiments without creative effort.

[0029] As used herein, the term "module" can be understood to refer to computing software, firmware, hardware, and / or various combinations thereof, which can be configured as components of network elements, computers, and / or systems. A module should not be construed as software not implemented in hardware or firmware or not recorded on a processor-readable storage medium. These modules can be combined, integrated, separated, and / or replicated to support a variety of applications. These modules can be implemented on multiple devices and / or other components, either locally or remotely. Furthermore, these modules can be removed from one device and added to another, and / or contained in two devices.

[0030] Figure 1 This is a schematic diagram of a contact center system according to an embodiment of the present disclosure, and shows an example of a contact center system 100, which may include: an automatic contact distribution (“Automated Contact Distribution” or “ACD”) system 120, an intelligent pairing module 130, and agents 140.

[0031] ACD system 120 can be configured to receive incoming contacts (e.g., callers) 110, or support outgoing connections to contacts via a telecommunications network. The ACD system may include hardware and software for routing contacts to facilitate routing contacts in one or more contact centers. The ACD system may also include queuing or switching components within contact center system 100.

[0032] The intelligent pairing module 130 is connected to the ACD system 120 and is used to pair contacts with agents according to a pairing policy.

[0033] Figure 2 This is a flowchart illustrating a method for matching contacts with agents in a contact center system, including: S201, determining a threshold statistic; S202, determining an ordered set of contacts; S203, determining a set of first statistics corresponding to the ordered set of contacts; S204, determining a set of second statistics corresponding to the ordered set of contacts and based on the set of first statistics, wherein the set of second statistics is based on the cumulative summation of the set of first statistics; S205, determining a subset of the ordered set of contacts based on the set of second statistics and the threshold statistic; and S206, matching contacts selected from the subset of the ordered set of contacts with available agents based on a matching strategy.

[0034] Figure 3 This is a schematic diagram illustrating a method for pairing contacts with agents in a contact center system according to an embodiment of the present disclosure.

[0035] In this implementation, there are five contacts in the queue, ordered according to the duration they have waited to be matched with an agent. A first statistic associated with these contacts is their waiting time. Contact 1, with the longest waiting time, has waited 100 seconds, while contact 5, with the shortest waiting time, has waited 1 second. A second statistic associated with these contacts is the waiting time of each contact plus the sum of the waiting times of all contacts with longer waiting times. For example, the second statistic for contact 2 is 140 seconds, which is the sum of the waiting times of contact 2 and contact 1. A threshold statistic is set to 150 seconds, which is 1.5 times the waiting time of the longest-waiting contact (contact 1). Therefore, contacts 1 and 2 are in a subset because their second statistic is less than the threshold statistic. Contacts 3, 4, and 5 are not in a subset because their second statistic is greater than the threshold statistic.

[0036] Unlike the subsets created by the top N filtering strategies, the cumulative statistics strategy does not allocate a preset number of contacts to subsets. The number of contacts allocated to subsets in the cumulative statistics strategy dynamically changes based on the conditions of the contact center. This difference accounts for the actual waiting time of contacts in the queue, thus reducing the abandonment rate compared to the top N strategies.

[0037] The scope of this disclosure is not limited to the specific embodiments described herein. In fact, various other embodiments and modifications of this disclosure, besides those described herein, will be apparent to those skilled in the art from the foregoing description and drawings. Therefore, such other embodiments and modifications are intended to fall within the scope of this disclosure. Furthermore, although this disclosure has been described herein in the context of at least one specific implementation for at least one specific purpose in at least one specific environment, those skilled in the art will recognize that its usefulness is not limited thereto and that this disclosure can be advantageously practiced in any number of environments for any number of purposes. Therefore, the claims should be interpreted in accordance with the full scope and spirit of this disclosure as set forth herein.

Claims

1. A method for pairing contacts with agents in a contact center system, comprising: determining a threshold statistic; determining an ordered set of contacts, wherein the ordered set of contacts is ordered from longest to shortest duration of time the contact has been waiting to be paired with an agent; determining a set of first statistics corresponding to the ordered set of contacts, wherein the first statistic corresponding to each contact is a wait time for the contact to be paired with an agent; determining a set of second statistics corresponding to the ordered set of contacts and based on the set of first statistics, wherein the second statistic corresponding to each contact is the wait time for the contact and a sum of the wait times for all contacts longer than the wait time for the contact; determining a subset of the ordered set of contacts based on the set of second statistics and the threshold statistic, wherein the threshold statistic is set by the contact center system based on a mean, maximum, or minimum of the set of first statistics, and all contacts for which the second statistic is less than the threshold statistic comprise the subset of the ordered set of contacts; and pairing contacts selected from the subset of the ordered set of contacts with idle agents based on a pairing strategy.

2. The method of claim 1, wherein, The pairing strategy is a BP strategy.

3. The method of claim 1, wherein, The pairing strategy is based on contact priority.

4. A system for pairing contacts with agents in a contact center system, comprising: at least one computer processor connected to an intelligent pairing module configured to pair contacts with agents in a contact center system, wherein the at least one computer processor is further configured to: determine a threshold statistic; determine an ordered set of contacts, wherein the ordered set of contacts is ordered from longest to shortest duration of time the contact has been waiting to be paired with an agent; determine a set of first statistics corresponding to the ordered set of contacts, wherein the first statistic corresponding to each contact is a wait time for the contact to be paired with an agent; determine a set of second statistics corresponding to the ordered set of contacts and based on the set of first statistics, wherein the second statistic corresponding to each contact is the wait time for the contact and a sum of the wait times for all contacts longer than the wait time for the contact; determine a subset of the ordered set of contacts based on the set of second statistics and the threshold statistic, wherein the threshold statistic is set by the contact center system based on a mean, maximum, or minimum of the set of first statistics, and all contacts for which the second statistic is less than the threshold statistic comprise the subset of the ordered set of contacts; and pair contacts selected from the subset of the ordered set of contacts with idle agents based on a pairing strategy.

5. The system of claim 4, wherein, The pairing strategy is a BP strategy.

6. The system of claim 4, wherein, The pairing strategy is based on contact priority.

7. An article of manufacture for pairing contacts with agents 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 computer processor connected to an intelligent pairing module configured to pair contacts with agents in a contact center system, such that the at least one computer processor operates to: determine a threshold statistic; determine an ordered set of contacts, wherein the ordered set of contacts is ordered from longest to shortest duration of waiting for the contacts to be paired with an agent; determine a set of first statistics corresponding to the ordered set of contacts, wherein the first statistic corresponding to each of the contacts is a wait time for the contact to be paired with an agent; determine a set of second statistics corresponding to the ordered set of contacts and based on the set of first statistics, wherein the second statistic corresponding to each of the contacts is the wait time for the contact and a sum of the wait times for all contacts longer than the wait time for the contact; determine a subset of the ordered set of contacts based on the set of second statistics and the threshold statistic, wherein the threshold statistic is set by the contact center system based on a mean, maximum, or minimum of the set of first statistics, and all contacts for which the second statistic is less than the threshold statistic comprise the subset of the ordered set of contacts; and pair the contacts selected from the subset of the ordered set of contacts with idle agents based on a pairing strategy.

8. The article of claim 7, wherein, The pairing strategy is a BP strategy.

9. The article of claim 7, wherein, The pairing strategy is based on contact priority.

Images