How inbound interactions are routed
The method and system in contact centers use historical data analysis to predict workload demand, enhancing resource allocation and performance metrics through accurate load forecasting.
Patent Information
- Application Number
- JP2021511538
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Priority Date
- 2018-09-11
- Filing Date
- 2019-09-10
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2039-09-10
AI Technical Summary
Existing contact center systems struggle to accurately predict workload demand, leading to inefficient resource allocation and suboptimal performance metrics.
A method and system for predicting load demand in contact centers using historical data analysis, including deriving adjacency graphs, sequence zeros, and stage histories, to forecast future volumes and resources needed, incorporating a recursive algorithm and time series prediction.
Enhances capacity planning and resource allocation by providing accurate load demand forecasts, improving service level agreements and customer satisfaction.
Smart Images

Figure 0007538114000005 
Figure 0007538114000006 
Figure 0007538114000007
Abstract
Description
[Technical field]
[0001] The present invention relates generally to telecommunications systems and methods, and contact center staffing. More specifically, the present invention relates to a contact center Routing inbound interactions in Regarding.
[0002] (CROSS REFERENCE TO RELATED APPLICATIONS) This application claims the benefit of U.S. Provisional Patent Application No. 62 / 729,856, entitled “METHOD AND SYSTEM TO PREDICT WORKLOAD DEMAND IN A CUSTOMER JOURNEY APPLICATION,” filed in the U.S. Patent and Trademark Office on September 11, 2018, the contents of which are incorporated herein by reference. Summary of the Invention
[0003] A system and method for predicting load demand in customer flow line applications is presented. Using historical information from analysis of flow lines, journey moments can be aggregated through various stages. Probability distribution vectors can be approximated for various paths connecting multiple stages. The stability of such probability distributions can be determined by statistical methods. Prediction of future volumes progressing through multiple stages can be determined through a recursive algorithm after applying a time series forecasting algorithm at an initial stage. Once future volumes are predicted at all stages, future loads can be estimated to better utilize capacity planning and scheduling to address such demands and achieve a performance index along a cost function.
[0004] In one embodiment, a method for forecasting load demand for resource planning in a contact center environment is presented, the method including: extracting historical data from a database, the historical data including a plurality of tier levels representing times when contact center resources service the tier levels in a customer's flow line; pre-processing the historical data, the pre-processing further including, for each tier level, deriving an adjacency graph, deriving sequence zero, and deriving a tier history; determining a tier forecast using the pre-processed historical data and building a forecast model; and deriving a forecasted load demand using the built model.
[0005] The stage level includes the focus of the customer journey and the transitions from each stage of the customer journey. Extracting is triggered by one of a user action, a scheduled job, and a queue request from another service. The adjacency graph models the graph connections between the stages. Sequence zero includes the first stage in the chain of sequence progression. The stage history includes characteristics of each stage including history vector counts, discard rates, and probability vector matrices.
[0006] The staged forecasting further includes running a flushing algorithm that performs iterations of the historical data to flush the volume through multiple stages and time periods, obtaining a remaining portion by setting aside a portion of the historical data for validation, using the remaining portion to build and train a forecast model, and calibrating the forecast model. Flushing the volume includes working backwards one period from the forecast start date and repeating each iteration incrementing each period by one.
[0007] The predicted load demand includes the load generated from a volume of interactions as a customer progresses through stages in the customer's journey, including predicted abandonments, and further includes the resources required to handle the predicted load in order to deliver the contact center's KPI metrics targets.
[0008] In another embodiment, a method for forecasting load demand for resource planning in a contact center environment is presented, the method including: extracting historical data from a database, the historical data including a plurality of tier levels representing actions of contact center resources to service the tier levels in a customer's journey; pre-processing the historical data, the pre-processing further including, for each tier level, deriving an adjacency graph, deriving sequence zero, and deriving a tier history; determining a tier forecast using the pre-processed historical data and building a forecast model; and deriving a forecasted load demand using the built model.
[0009] In another embodiment, a system for forecasting load demand for resource planning in a contact center environment is presented, the system comprising: a processor; and a memory in communication with the processor, the memory storing instructions that, when executed by the processor, cause the processor to extract historical data from a database, the historical data including a plurality of tier levels representing times when contact center resources service the tier levels in a customer's flow line; pre-processing the historical data, the pre-processing further including, for each tier level, deriving an adjacency graph, deriving a sequence zero, and deriving a tier history; determining a tier forecast using the pre-processed historical data and building a forecast model; and deriving a forecasted load demand using the built model.
[0010] In another embodiment, a system for forecasting load demand for resource planning in a contact center environment is presented, the system comprising: a processor; and a memory in communication with the processor, the memory storing instructions that, when executed by the processor, cause the processor to extract historical data from a database, the historical data including a plurality of tier levels representing actions of contact center resources to service the tier levels in a customer's path; pre-processing the historical data, the pre-processing further including, for each tier level, deriving an adjacency graph, deriving sequence zeros, and deriving a tier history; determining a tier forecast using the pre-processed historical data and building a forecast model; and deriving a predicted load demand using the built model. [Brief description of the drawings]
[0011] [Figure 1] FIG. 1 illustrates one embodiment of a communications infrastructure.
[0012] [Diagram 2] FIG. 1 illustrates an embodiment of a workforce management architecture.
[0013] [Diagram 3] 1 is a flow chart illustrating an embodiment of a process for developing a model for load demand forecasting.
[0014] [Figure 4A] 1 is a directed graph representation of one embodiment of movement lines.
[0015] [Figure 4B] 1 is an embodiment of an adjacency graph representation.
[0016] [Figure 4C] 1 is an embodiment of an adjacency graph representation.
[0017] [Diagram 5] 4 is a flow diagram illustrating one embodiment of a process for deriving sequence zero.
[0018] [Figure 6] 1 is a flow chart illustrating one embodiment of a process for deriving a stage history.
[0019] [Figure 7] 1 is a flow chart illustrating one embodiment of a process for demand flushing.
[0020] [Figure 8A] FIG. 1 illustrates an embodiment of a computing device.
[0021] [Figure 8B] FIG. 1 illustrates an embodiment of a computing device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0022] For the purposes of promoting an understanding of the principles of the invention, reference will now be made to the embodiments illustrated in the drawings and specific language will be used to describe the same. Notwithstanding the above, it will be understood that no limitation of the scope of the invention is intended. Any changes and further modifications in the described embodiments, and any further applications of the principles of the invention as described herein, are contemplated as would normally occur to one skilled in the art to which the invention pertains.
[0023] Customer interaction management in a contact center environment involves managing interactions between parties, e.g., customer and agent, customer and bot, or a mix of both. This can occur across any number of channels in the contact center, and can track and target the best possible resource (agent or self-service) based on skill and / or any number of parameters. Reporting can be performed on channel interactions in real time or historically. All interactions a customer has related to the same service, need, or purpose can be described as a customer's journey. Analysis around a customer's journey is sometimes referred to herein and in the art as "journey analysis." For example, if a customer browses an online store of company A, logs in with their credentials to make a purchase, and then calls company A's customer support line within a period of time from that online purchase action, it is likely that the customer is calling about that online purchase (e.g., asking why an item was not shipped, upgrading to next day delivery, canceling an order, etc.). In this example, all interactions a customer has made comprise one journey. A "trajectory analysis" platform may be used to analyze a customer's end-to-end path through interactions with a given entity (eg, website, business, contact center, IVR) over a period of time.
[0024] Being able to determine in advance whether the majority of calls made through a customer support line are related to shipping inquiries provides Company A with the opportunity to take proactive action, such as sending notifications to customers via a channel (e.g., email, SMS, callback, etc.) In this example, Company A may send order confirmations, tracking numbers, and / or possible shipping method upgrades.
[0025] Recognizing and proactively acting on moments in a customer's journey can provide better customer service and outcomes. The need to visually and statistically report on the sequence of events as a customer progresses through the stages is also important to businesses planning resources through forecasting resource demand and load.
[0026] Contact Center Systems
[0027] FIG. 1 illustrates an embodiment of a communications infrastructure generally designated 100. For example, FIG. 1 illustrates a system for supporting a contact center in providing contact center services. A contact center may be an in-house facility to a business or enterprise for providing services to the enterprise in performing sales and service functions related to products and services available through the enterprise. In another aspect, the contact center may be operated by a third-party service provider. In an embodiment, the contact center may be operated as a hybrid system in which some components of the contact center system are hosted on the contact center premises and other components are hosted remotely (e.g., in a cloud-based environment). The contact center may be located on equipment dedicated to the enterprise or third-party service provider and / or in a remote computing environment, such as, for example, a private or public cloud environment with infrastructure to support multiple contact centers for multiple enterprises. Various components of the contact center system may also be distributed across various geographic locations and computing environments and not necessarily contained in a single location, computing environment, or even computing device.
[0028] The components of the communications infrastructure, generally designated 100, include a number of end user devices 105A, 105B, 105C, a communications network 110, a switch / media gateway 115, a call controller 120, an IMR server 125, a routing server 130, a storage device 135, a statistics server 140, a number of agent devices 145A, 145B, 145C including work bins 146A, 146B, 146C, one of which may be associated with a contact center administrator or supervisor 145D, a multimedia / social media server 150, a web server 155, an iXn server 160, a UCS 165, a reporting server 170, and a media service 175.
[0029] In one embodiment, a contact center system manages resources (e.g., workers, computers, telecommunications equipment, etc.) to enable the delivery of services over the telephone or other communications mechanisms. Such services may vary depending on the type of contact center and range from customer service to help desk, emergency response, telemarketing, order taking, etc.
[0030] Customers, potential customers, or other end users (collectively referred to as customers or end users) desiring to receive service from the contact center can initiate inbound communications (e.g., telephone calls, emails, chats, etc.) to the contact center via end user devices 105A, 105B, and 105C (collectively referred to as 105). Each of the end user devices 105 may be a communication device conventional in the art, such as a telephone, wireless telephone, smart phone, personal computer, electronic tablet, laptop, etc., to name a few non-limiting examples. A user operating the end user device 105 can initiate, manage, and respond to telephone calls, emails, chats, text messages, web browsing sessions, and other multimedia transactions. For simplicity, three end user devices 105 are shown in 100, although any number may be present.
[0031] Inbound and outbound communications from and to the end user device 105 may traverse a network 110 depending on the type of device being used. The network 110 may include communication networks for telephone, cellular, and / or data services, including, by way of non-limiting example, a private or public switched telephone network (PSTN), a local area network (LAN), a private wide area network (WAN), and / or a public WAN such as the Internet. The network 110 may also include wireless carrier networks, including code division multiple access (CDMA) networks, Global System for Mobile Communications (GSM) networks, or any wireless network / technology conventional in the art, including, but not limited to, 3G, 4G, LTE, etc.
[0032] In one embodiment, the contact center system includes a switch / media gateway 115 coupled to the network 110 for transmitting and receiving telephone calls between end users and the contact center. The switch / media gateway 115 may include a telephone switch or a communication switch configured to act as a central switch for agent-level routing within the center. The switch may be a hardware switching system or a soft switch implemented via software. For example, the switch 115 may include an automatic call distributor, a private branch exchange (PBX), an IP-based software switch, and / or any other switch having dedicated hardware and software configured to receive Internet-sourced and / or telephone network-sourced interactions from a customer and route these interactions, for example, to an agent telephone or communication device. In this example, the switch / media gateway establishes a voice path / connection (not shown) between the calling customer and the agent telephone device, for example, by establishing a connection between the customer telephone device and the agent telephone device.
[0033] In one embodiment, the switch is coupled to a call controller 120, which may act as, for example, an adapter or interface between the switch and other communication processing components of the contact center, such as routing, monitoring, etc. The call controller 120 may be configured to process PSTN calls, VoIP calls, etc. For example, the call controller 120 may be configured with computer telephony integration (CTI) software for interfacing with the switch / media gateway and the contact center equipment. In one embodiment, the call controller 120 may include a session initiation protocol (SIP) server for processing SIP calls. The call controller 120 may also extract data regarding the customer interaction, such as the caller's telephone number (e.g., automatic number identification (ANI) number), the customer's Internet Protocol (IP) address, or email address, and communicate with other components of the system 100 in processing the interaction.
[0034] In one embodiment, the system 100 further includes an interactive media response (IMR) server 125. The IMR server 125 may also be referred to as a self-help system, a virtual assistant, or the like. The IMR server 125 may be similar to an interactive voice response (IVR) server, except that the IMR server 125 is not limited to voice, but may also cover a variety of media channels. In an embodiment illustrating voice, the IMR server 125 may be configured with IMR scripts to query the customer's needs. For example, a bank contact center may tell a customer via an IMR script that if the customer wants to retrieve their account balance, they should "press 1." Through continued interaction with the IMR server 125, the customer may be able to complete the service without needing to speak to an agent. The IMR server 125 may also ask open-ended questions such as "How can I help you?", and the customer may speak or otherwise input the reason for contacting the contact center. The customer's response may be used by the routing server 130 to route the call or communication to the appropriate contact center resource.
[0035] If the communication is to be routed to an agent, the call controller 120 interacts with a routing server (also referred to as an orchestration server) 130 to find a suitable agent to handle the interaction. The selection of a suitable agent to route the inbound interaction may be based on, for example, a routing strategy used by the routing server 130, and may further be based on information about agent availability, skills, and other routing parameters provided, for example, by a statistics server 140.
[0036] In one embodiment, the routing server 130 may query a customer database, which stores information about existing clients, such as contact information, service level agreement (SLA) requirements, nature of previous customer contacts, and actions taken by the contact center to resolve any customer issues. The database may be, for example, Cassandra or any NoSQL database and may be stored on the mass storage device 135. The database may also be a SQL database and may be managed by any database management system, such as, for example, Oracle, IBM DB2, Microsoft SQL Server, Microsoft Access, PostgreSQL, to name a few non-limiting examples. The routing server 130 may query the customer database for customer information via the ANI or any other information collected by the IMR server 125.
[0037] Once a suitable agent is identified as available to handle the communication, a connection may be made between the customer and the identified agent's agent device 145A, 145B, and / or 145C (collectively referred to as 145). Although three agent devices are shown in FIG. 1 for simplicity, any number of devices may be present. Collected information regarding the customer and / or customer history information may also be provided to the agent device to assist the agent in better servicing the communication, as well as to a contact center administrator / supervisor device 145D, including scheduling staff to handle the load. In this regard, each device 145 may include a telephone adapted for regular telephone calls, VoIP calls, and the like. The devices 145 may also include a computer for communicating with one or more servers of the contact center, performing data processing associated with contact center operations, and interacting with customers via voice and other multimedia communication mechanisms.
[0038] The contact center system 100 may also include a multimedia / social media server 150 for engaging in media interactions other than voice interactions with the end user devices 105 and / or a web server 155. The media interactions may relate to, for example, email, voicemail (voicemail over email), chat, video, text messaging, web, social media, co-browsing, etc. The multimedia / social media server 150 may take the form of any IP router conventional in the art, with specialized hardware and software for receiving, processing, and forwarding multimedia events.
[0039] The web server 155 may include, for example, social networking site hosts for various known social networking sites to which end users may join, such as Facebook, Twitter, Instagram, to name a few non-limiting examples. In one embodiment, the web server 155 is shown as part of the contact center system 100, but the web server may also be provided by a third party and / or maintained outside the contact center premises. The web server 155 may also provide web pages for businesses supported by the contact center system 100. End users may browse the web pages and obtain information about the products and services of the businesses. The web pages may also provide mechanisms for contacting the contact center via, for example, web chat, voice calls, email, web real-time communications (WebRTC), etc. Widgets may be deployed on websites hosted on the web server 155.
[0040] In one embodiment, deferrable interactions / activities may also be routed to contact center agents in addition to real-time interactions. Deferrable interactions / activities may include back office tasks or tasks that may be performed offline, such as responding to emails, letters, attending training, or other activities that do not require real-time communication with customers. The interaction (iXn) server 160 interacts with the routing server 130 to select an appropriate agent to handle the activity. Once assigned to an agent, the activity may be pushed to the agent or may appear in the agent's work bins 146A, 146B, 146C (collectively 146) as tasks to be completed by the agent. The agent's work bins may be implemented via any data structure conventional in the art, such as, for example, linked lists, arrays, etc. In one embodiment, the work bins 146 may be maintained, for example, in a buffer memory of each agent device 145.
[0041] In one embodiment, the mass storage device 135 may store one or more databases relating to agent data (e.g., agent profiles, schedules, etc.), customer data (e.g., customer profiles), interaction data (e.g., details of each interaction with a customer, including but not limited to, reason for the interaction, disposition data, wait times, processing times, etc.), etc. In another embodiment, some of the data (e.g., customer profile data) may be maintained in a customer relationship management (CRM) database hosted on the mass storage device 135 or elsewhere. The mass storage device 135 may take the form of a hard disk or disk array, as is conventional in the art.
[0042] In one embodiment, the contact center system may include a Universal Contact Server (UCS) 165 configured to retrieve information stored in a CRM database and direct information to be stored in the CRM database. The UCS 165 may also be configured to facilitate maintaining customer preference history and interaction history, capture and store data regarding comments from agents, customer communication history, and the like.
[0043] The contact center system may also include a reporting server 170 configured to generate reports from the data aggregated by the statistics server 140. Such reports may include near real-time or historical reports regarding resource status, such as, for example, average wait times, relaxation rates, agent occupancy, etc. Reports may be generated automatically or in response to a specific request from a requester (e.g., an agent / administrator, a contact center application, etc.).
[0044] The contact center system may also include a Workforce Management (WFM) server 180. The WFM server automatically synchronizes configuration data and serves as the main data and application service source and locator for the WFM clients. The WFM server 180 supports GUI applications accessible from any of the agent devices 145, such as access to a contact center movement analysis platform, and the contact center admin / supervisor device 145D for contact center management. The WFM server 180 communicates with the statistics server 140 and may communicate with a configuration server (not shown) for configuration purposes. In one embodiment, the WFM server 180 may also communicate with a data aggregator 184, a builder 185, a web server 155, and a daemon 182. This is described in more detail in FIG. 2 below.
[0045] Each of the various servers in FIG. 1 may include one or more processors that execute computer program instructions and interact with other system components to perform the various functions described herein. The computer program instructions are stored in a memory implemented using standard memory devices such as, for example, a random access memory (RAM). The computer program instructions may also be stored on other non-transitory computer readable media such as, for example, a CD-ROM, a flash drive, etc. Although the functionality of each server is described as being provided by a particular server, those skilled in the art should understand that the functionality of the various servers may be combined or integrated into a single server, or the functionality of a particular server may be distributed among one or more other servers without departing from the scope of embodiments of the present invention.
[0046] In one embodiment, the terms "interaction" and "communication" are used interchangeably and generally refer to any real-time and non-real-time interaction using any communication channel, including, but not limited to, phone calls (PSTN or VoIP calls), email, vmail, video, chat, screen sharing, text messages, social media messages, WebRTC calls, etc.
[0047] Media services 175 may provide audio and / or video services to support contact center functions such as IVR or IMR system prompts (e.g., playing audio files), music on hold, voicemail / single-party recording, multi-party recording (e.g., audio and / or video calls), voice recognition, dual-tone multi-frequency (DTMF) recognition, fax, audio and video transcoding, Secure Real-Time Transport Protocol (SRTP), audio conferencing, video conferencing, coaching (e.g., support for a coach to listen to an interaction between a customer and an agent, and support for a coach to provide comments to an agent without the customer hearing the comments), call analysis, and keyword spotting.
[0048] In one embodiment, the premises-based platform product may provide access and control of components of the system 100 via a user interface (UI) present on the agent devices 145A-C. A graphical application generator program may be integrated within the premises-based platform product, which allows users to create programs (handlers) that control various interaction processing operations within the premises-based platform product.
[0049] As mentioned above, a contact center may operate as a hybrid system in which some or all components are remotely hosted, such as in a cloud-based environment. For convenience, aspects of an embodiment of the present invention are described below with respect to providing modular tools from a cloud-based environment to components housed on premises.
[0050] 2 is a diagram illustrating an embodiment of a workforce management architecture in general. Components may include a supervisor device 145D, an agent device 145, a web server 155, a WFM server 180, a daemon 181, an API 182, a data aggregator 183, a builder 184, a storage device 135, and a statistics server 140.
[0051] The web server 155 is hosted on a servlet container and includes a server application that can provide content for multiple web browser-based user interfaces (e.g., one UI may be for agents and another for supervisors). After logging in, the appropriate interface opens. The supervisor UI allows supervisors to access features such as calendar management, forecasting, scheduling, real-time agent adherence, contact center performance statistics, setting up email notifications, and reporting. The agent UI allows for distribution of schedule information (e.g., from manager to employee) and provides agents with proactive scheduling capabilities such as entering schedule preferences, planned time off, schedule guidance, trades, etc.
[0052] The WFM Server 180 automatically synchronizes configuration data and acts as the main data and application service source and locator for the WFM clients. The WFM Server 180 is the hub, connecting to the other components in the architecture.
[0053] The WFM daemon 181 is a daemon that can be configured to send email notifications to agents and supervisors. The API 182 can facilitate integration, changes to objects, and retrieval of information between the web server 155 and the WFM server 180.
[0054] The data aggregator 183 collects historical data from the statistics server 140 and provides real-time agent adherence information to the supervisor device 145D via the WFM server 180. Through the connection between the data aggregator 183 and the statistics server 140, a single point of interaction is provided between the WFM architecture and the contact center 100. The builder 184 uses information from the data aggregator 183 to build a schedule.
[0055] Web server 155 provides content for the web browser based GUI application and generates reports upon request from a user of supervisor device 145D. WFM server 180, daemon 181, data aggregator 183, builder 184, and web server 155 support the GUI application. Database 135 stores all relevant configuration, forecast, scheduling, agent adherence, performance, and historical data. Components of the WFM architecture may connect directly to the database as shown in FIG. 2, or indirectly through WFM server 180. The WFM architecture may operate in a single site environment or across a multi-site enterprise.
[0056] 3 is a flow chart illustrating one embodiment of a process for creating a model of load demand forecasting, generally designated 300. The model may be used by the WFM server 180 to generate a forecast of load demand for the contact center environment 100, and can generate an output that is used by a supervisor / administrator to allocate resources within the contact center.
[0057] In operation 305, historical data is extracted. Extraction may be performed by code written to output the desired data. The extraction code may operate from within the workforce management application (FIG. 2) and be utilized via a button in the user interface. The extractor extracts stage information document objects (similar to tables in a database) from the database 135. The filters used by the extractor are the same as those specified by the user above. The data extractor may be triggered by a user action on the front end, as described, or may be triggered from the back end. For example, the extractor may exist as a batch service on the back end triggered by a scheduled CRON job, and the data provided may be stored at an endpoint such as a cloud object storage like Amazon S3. In another embodiment, the extractor may exist as a batch service on the back end triggered by a queued request from another service.
[0058] The historical data has several requirements. For example, the stage level must be the closest proxy for agent load since the end goal of demand forecasting is capacity planning. Capacity planning includes the load generated from the volume of interactions as the customer moves through the stages and the resources (e.g., Full-Time Equivalent (FTE) agents) required to handle the load for the purpose of delivery of specific KPI indicator goals (e.g., service level, NPS, abandonment). In one embodiment, the movement analysis data to be extracted must be at the filter level where the output stage proximate to the time agent is actually served to the stage. This can be either platform or event-based and can be specified by the user through a user interface. The stage level can be predefined by the administrator or user customizable. In one embodiment, the stage level is the focus for the customer's movement and the transitions from each state in the movement. These can depend on the purpose of what information is to be collected from the customer's movement. Also, there can be multiple paths within the movement. The predefined stages can also include groupings of actions, and there can be any number of actions within a stage. In one embodiment, the extracted stage level may not be tied to an agent's time. Instead, the extracted stage level may be tied to an action taken within a stage. For example, as a customer progresses through the stages, an action may be to send a product sample to the customer upon completion of a stage in the journey.
[0059] The historical data must contain the required data elements, which include: movement type name, movement type ID, customer ID, stage, sequence, status date, end date, and time progression. The movement type name is a string data type that describes the type of movement, such as "load request". The movement type ID is a string data type that contains a unique ID that identifies the movement type. The customer ID is a string data type that contains a unique ID that identifies the customer. The stage is a string data type that contains the stage name. This field may be dynamic depending on the filters of the labeling strategy selected by the user. The sequence is an integer data type that contains the number of stages the customer is in. For example, the first stage may start with zero, the next stage is one, and so on.
[0060] A stage may be a portion of a customer journey that occurs in a numbered sequence that is customizable to the business based on a specific portion of the journey (e.g., filling out a form, credit check, processing an application, making a payment, etc.) and that can vary in order based on preference. A stage may be an intermediate stage in a journey, but the same stage in another journey may be "sequence zero."
[0061] The start date is a date data type that contains the start date / time when the customer begins a particular stage, for example 12 / 23 / 15 00:00 or 01 / 19 / 16 14:20. The end date is a date data type that contains the end date / time when the customer ends / exits a particular stage, for example 01 / 06 / 16 00:00 or 01 / 24 / 16 18:56. The time lapse may be an integer data type that contains the number between the end date and the start date. This must be a positive number since the end date is always greater than or equal to the start date.
[0062] In one embodiment, the historical data output may be in UTF-8 encoded CSV format or JSON files / streams and should be accessible to Python and Java classes.
[0063] The historical data should also include distinguishable tags when a customer abandons the journey at a particular stage.Control is passed to operation 310 and process 300 continues.
[0064] In operation 310, the historical data is pre-processed. Pre-processing includes various preliminary calculations performed on the historical data. The output of the pre-processing step is used in the stage prediction process algorithm. Pre-processing includes deriving an adjacency graph, deriving sequence zero (including calculating discard rates for each sequence and generating volume predictions for each sequence zero stage), and deriving stage history.
[0065] In a first pre-processing step, an adjacency graph is derived. To capture the relationships between the movement line moments, a graph representation may be used that models the inter-stage connections in the platform. Each movement line moment is a sequence or stage that a customer progresses through from start to finish. FIG. 4A is a directed graph representation of one embodiment of a movement line, generally designated 400. In FIG. 4A, the initial stage of the entire movement line is represented as v0, while the end stage is represented as v5. The intermediate (or transition) stages that a customer may pass through during the movement line are represented as v1, v2, v3, and v4. An abandonment state is also associated with each stage to pool customers who are considered to have abandoned the movement line and exited the stage after a certain period of time. The arrows between stages represent the connections in the analysis and may be modeled in an adjacency graph. The adjacency graph models the peripheral edges and nodes (forward and backward adjacent) for the intended stage. Each forward adjacent node has its own forward and backward adjacent nodes connected to it. A back-neighbor node also has its own front-neighbor and back-neighbor nodes. All connections in the graph can be deduced by iterating through the adjacency graph list, starting with the left-most neighboring stage, then its back-neighbor, then the next back-neighbor, and so on. Figures 4B and 4C are examples of adjacency graphs from the customer journey shown in Figure 4A. In Figure 4B, stage v0 has no front-neighbors and is empty. The back-neighbors of v0 are v1 and v2. In Figure 4C, which represents stage v3, v1 is a front-neighbor. The back-neighbors of v3 are v4 and v5. Only two adjacency graphs are shown for simplicity, but others are possible for the trajectory 400. In another example from the customer trajectory 400, stage v1 may have v0 as a front-neighbor and v3 as a back-neighbor. Stage v2 may have v0 as a front-neighbor and v4 as a back-neighbor. Stage v4 may have stages v2 and v3 as its forward neighbors and v5 as its backward neighbor. Stage v5 may have stages v3 and v4 as its forward neighbors, but may not have a backward neighbor. An adjacency graph may be added for each stage of the movement line.
[0066] In another pre-processing step, a sequence zero is derived. A sequence zero can be described as the stage where a customer begins their journey. It is the first stage in the progression of a sequence. A stage may be an intermediate stage in a journey, but the same stage may be sequence zero in another journey. Thus, being a sequence zero stage does not preclude it from being an intermediate stage. FIG. 5 is a flow chart illustrating one embodiment of a process, generally designated 500, for deriving a sequence zero. The sequence zero and its information are derived from the extracted historical data as follows:
[0067] A prediction length of the desired period T is set (502). This includes how far in advance a prediction is desired. All distinct "sequence=0"s are identified from the historical data and saved in a sequence zero list. For each stage in the sequence zero list, the timestamps of the calls / interactions from the historical data are obtained and saved as a time series (504). At the same time, from the historical data, for each stage in the sequence zero list, the average duration of customers spent in that stage across all interactions is determined (506). Next, for each stage in the sequence zero list, the standard deviation of the duration of customers spent in that stage is determined (508). Then, for each stage in the sequence zero list, a "discard duration threshold" is determined (510). This can be determined using:
[0068]
number
[0069] where k can be anywhere between 1.0 and positive infinity, depending on how aggressive the algorithm should classify / tag interactions that have been waiting "too long" as being discarded (from the pool of legitimate interactions).
[0070] For each stage in the sequence zero list, any interaction(s) having a duration greater than a set "discard duration threshold" are tagged (512). These tagged interactions are counted as "discarded." The total number of interactions tagged as discarded is then counted for each stage in the sequence zero list (514).
[0071] Next, for each stage in the sequence zero list, a discard rate is determined 516, which can be expressed as:
[0072]
number
[0073] Determine 518 the net total volume history for all steps in the sequence zero list using the following:
[0074] Net total volume history of stage i = total volume history of stage i * (1-stage i abandonment rate)
[0075] Finally, the demand forecasting engine may be run using the net total volumes as history (training data for the forecasting model) (520). For each stage in the sequence zero list, a volume time series forecast result for sequence zero is obtained. The calculation result is stored as sequence zero (522). The engine takes in the historical time series data to be forecasted (e.g., interaction volumes) and performs feature engineering on the data. Feature engineering includes data summarization and aggregation, data cleanup (missing data faults, leading and trailing zeroing, etc.), outlier detection, pattern detection, and selecting the best method to use given the patterns found to minimize forecast error by cross-validation.
[0076] To obtain higher accuracy, i.e., weekly, daily, hourly, and 5 / 15 / 30 minute granularities, multiple time dimension tiers can be forecast. Lower granularity forecasts (e.g., weekly) are used as a baseline, and higher granularity forecasts are made via distributions such as daily, hourly, and higher granularity distributions utilizing forecast distributions that connect data from lower to higher granularity. A number of commonly used statistical forecasting methodologies such as ARIMA or Holt-Winter's can be considered along with custom, proprietary ones. The best method is selected using multi-fold cross-validation. The criteria used can be based on customer scoring, which is a combination of accuracy and overall horizontal accuracy.
[0077] In another pre-processing step, a stage history is derived from the extracted history data. Each stage has its own stage history characteristics, consisting of history vector counts, discard rates, and a probability vector matrix. Every stage has an "in" and / or "out" history volume for each stage, which can be summarized in a matrix or vector representation of the volume counts. Each stage may also have a proportion of its volume history that enters the stage but does not progress to a subsequent adjacent stage. This is counted against the discards at that stage. Figure 6 is a flow chart illustrating one embodiment for deriving a stage history, generally designated 600.
[0078] Distinct stages are identified (602). For each stage, a daily volume time series is added (604). The average duration of each stage is determined (606). For each stage, the standard deviation of all interaction durations is determined (608). For each stage, a duration discard threshold is determined (610). Any interaction or interactions with durations exceeding a set "duration discard threshold" are tagged (612). For each stage, total discards are determined (614). Then, for each stage, a discard rate is calculated (616). This can be done using:
[0079]
number
[0080] The daily volume time series for all stage-to-stage combinations are input (618). Because these volumes into and out of stages can occur throughout time (e.g., daily), they can be represented as time series data. determines (620) a probability vector using:
[0081]
number
[0082] The vectors and discard rates are stored as a stage history for each stage of the movement line. The vectors are used to add a probability vector matrix to every start-end stage combination in the entire movement line using the previously determined adjacency graph results. Control is passed to operation 315 and process 300 continues.
[0083] In operation 315, a flushing algorithm is performed. Operation 315 cannot be performed without performing operation 310. Referring to FIG. 4A, an example motion line may include stages v0, v1, v3, and v5. A probability vector may be derived, for example, from such a motion line.
[0084] Vector A may be a representation from stage v0 to stage v1. Vector B may be a representation from stage v1 to stage v3. Vector C may be a representation from stage v3 to stage v5. Interactions from stage v0 to stage v1 may wait one day before 100% of them move to stage v1. From stage v1, no interactions move to stage v3 in one day. Instead, 100% of the interactions move to stage v3 on day 2. From stage v3, no interactions move to stage v5 in one day. 50% of the interactions may move from stage v3 to stage v5 on day 2 and 50% on day 3. FIG. 7 is a flow chart diagram illustrating one embodiment of a process for demand flushing generally designated 700. First, a forecast length is determined (702). In this example, a nine-day forecast is generated. Then, a forecast start date is set (704), which in this example starts from day 0 to day 8. Set iteration i = 0 706. The iterations of the flushing algorithm can be exemplified as follows:
[0085] Iteration #0: During the sequence zero algorithm, all pre-processed stages are run through the prediction engine to obtain predicted volumes for stage v0 (708). In one embodiment, for all sequence zero stages, volume predictions and net discard of volume predictions are obtained from sequence zero. Five days of historical data for each of stages v0, v1, v3, and stage v5 are used to obtain stage predictions (710). Stage predictions are set with values from sequence zero.
[0086] It is determined whether all of the iterations have been run for the predicted length. In this example, if all of the iterations have not been run for the predicted length, the iteration is incremented by one (714) and the next unprocessed stage is set as the current processed stage (718), so that all stages are processed (732). A stage prediction from the previous iteration is obtained and cloned into the iteration's stage prediction (720a), and then a net discard of the volume prediction is determined for all stages of the iteration (722a). A history vector (from the pre-processing algorithm) of the stage history is obtained at the same time (720b), and all stage histories are looped through the obtained history vector (722b). A probability vector is obtained from the stage history (724). Then, looping through each time series point of the net discard of the volume prediction, the elapsed time is determined as the difference between the time series timestamp and the predicted start date (726a). If the elapsed time matches the probability vector time index and the end point matches the current stage, the volume is flushed by multiplying the volume value by the probability value (728a). At the same time, the elapsed time using the history vector is also determined (726b), and the volumes are flushed to determine the elapsed time (728b), looping through each time series point in the history vector and determining the elapsed time as the difference between the time series timestamp and the forecast start date. The value is waited for a certain period of time, and if some, if not all, volumes qualify for flushing (determined by the probability vector distribution), they are flushed. The flushed values for the current iteration are stored in a stage prediction matrix (730). When all of the stages have been processed (732) and all of the iterations of the prediction length have been performed (712), a final stage prediction matrix is obtained (734). The final stage prediction matrix should contain the final volume state for all stages over the entire forecast period starting from the forecast date. Continuing with the above example, the following describes the processing of the iterations involving the traffic line 400.
[0087] Iteration #1: The interaction reaches stage v0 on day 0.
[0088] Iteration #2: Interactions from stage v0·day 0 flow into stage v1·day 1 with 100% probability according to probability vector A. The predicted value of stage v0 as the sequence zero stage is input.
[0089] Iteration #3: Interactions from stage v0·day 1 flow into stage v1·day 2 with 100% probability according to probability vector A. The predicted value of stage v0 on day 2 as the sequence zero stage is input.
[0090] Iteration #4: Interactions from stage v0·day 2 flow 100% into stage v1·day 3 according to probability vector A. The predicted value of stage v0 on day 3 as the sequence zero stage is entered. Interactions that were in stage v1 on day 1 and have been there for 2 days are now eligible to flow fully into stage v3 according to probability vector B.
[0091] Iteration #5: Interactions from stage v0 on day 3 flow 100% into stage v1·day 4 according to probability vector A. The predicted value of stage v0·day 4 as the sequence zero stage is entered. Interactions that were in stage v1 on day 2 and have been there for 2 days are now eligible to flow fully into stage v3 according to probability vector B.
[0092] Iteration #6: Interactions from stage v0·day 4 flow 100% into stage v1·day 5 according to probability vector A. The predicted value of stage v0·day 5 as the sequence zero stage is entered. An interaction that was in stage v1 on day 3 and has been there for 2 days is now fully eligible to flow into stage v3 according to probability vector B. An interaction that was in stage v3 on day 3 and has been there for 2 days is now 50% eligible to flow into stage v5 according to probability vector C.
[0093] Iteration #7: Interactions from stage v0·day 5 flow 100% into stage v1·day 6 according to probability vector A. The forecast for stage v0·day 6 as the sequence zero stage is input. Interactions that were in stage v1 on day 4 and have been there for 2 days are now fully eligible to flow into stage v3 according to probability vector B. Interactions that were in stage v3 on day 4 and have been there for 2 days are now 50% eligible to flow into stage v5 according to probability vector C. Additionally, of the 50% of interactions that were in stage v3 on day 3 and have been there for 3 days, 50% are now also eligible to flow into v5 according to probability vector C.
[0094] Iteration #8: Interactions from stage v0·day 6 flow 100% into stage v1·day 7. The forecast for stage v0·day 7 as the sequence zero stage is entered. Interactions in stage v1 on day 5 that have been there for 2 days are now fully eligible to flow into stage v3 with probability vector B. Interactions in stage v3 on day 5 that have been there for 2 days are now 50% eligible to flow into stage v5 with probability vector C. Additionally, of the 50% of interactions in stage v3 on day 4 that have been there for 3 days, 50% are now also eligible to flow into v5 with probability vector C.
[0095] Iteration #9: Interactions from stage v0·day 7 flow 100% into stage v1·day 8 according to probability vector A. The predicted value of stage v0·day 7 as the sequence zero stage is input. Interactions that were in stage v1 on day 6 and have been there for 2 days are now fully eligible to flow into stage v3 according to probability vector B. Interactions that were in stage v3 on day 6 and have been there for 2 days are now 50% eligible to flow into stage v5 according to probability vector C. Additionally, of the 50% of interactions that were in stage v3 on day 5 and have been there for 3 days, 50% of them are now also eligible to flow into v5 according to probability vector C.
[0096] For simplicity, the above example shown with iterations 0 through 9 ignored historical data prior to day 0 (before the forecast start date) to convey the idea of flushing volumes through multiple stages and periods. If historical data prior to day 0 is used, each iteration must consider volumes from the historical data series and perform the same "volume flushing" process on those volumes, starting from the forecast start data going backwards 1 period, 2 periods, 3 periods, etc. The same probability vectors apply.
[0097] Control is passed to operation 320 and the process 300 continues.
[0098] At operation 320, the model is validated. A portion of the historical data is set aside for validation. For example, 10% may be set aside. The other 90% of the historical data is used to train / build the model. This model is then used to generate predictions and compared to the set aside data. The average prediction error is determined and can be used as a KPI. The prediction may be determined by subtracting the actual value from the predicted value. This is done for each data point. The average is taken over all data points to get the average prediction error. Cross-validation is performed where the set aside historical data is from different time periods or ranges and the training data is from subsets from different time periods. The average prediction error is also determined for each of the cross-validation scenarios. The standard deviation of the error may also be presented. Control is passed to operation 325 and process 300 continues.
[0099] In operation 325, the model is calibrated and the process ends. Once the validation step is complete, a recalibration of the predictive model is performed to minimize the prediction error. This can be done using any standard procedure known in the art.
[0100] In one embodiment, the model includes load generated from the volume of interactions as the customer progresses through the stages and includes predicted abandonments in the customer's journey. Predictions made using the model include resources (e.g., FTEs) required to handle the load to deliver the contact center's KPI metric goals (e.g., service level, NPS, abandonments). The model may be applied to the contact center's journey analytics platform.
[0101] Computer Systems
[0102] In one embodiment, each of the various servers, controllers, switches, gateways, engines, and / or modules (collectively referred to as servers) of the illustrated figures is implemented via hardware or firmware (e.g., ASICs), as will be appreciated by those skilled in the art. Each of the various servers may be a process or thread running on one or more processors, executing computer program instructions in one or more computing devices (e.g., FIG. 8A, FIG. 8B), and interacting with other system components to perform the various functions described herein. The computer program instructions are stored in a memory that may be implemented in the computing device using standard memory devices such as, for example, RAM. The computer program instructions may also be stored in other non-transitory computer readable media such as, for example, CD-ROM, flash drive, etc. Those skilled in the art should appreciate that a computing device may be implemented via firmware (e.g., application specific integrated circuits), hardware, or a combination of software, firmware, and hardware. Those skilled in the art should also appreciate that the functionality of the various computing devices may be combined or integrated into a single computing device, or the functionality of a particular computing device may be distributed among one or more other computing devices without departing from the scope of the exemplary embodiments of the present invention. A server may be a software module, which may also simply be referred to as a module. The set of modules in a contact center may include servers and other modules.
[0103] The various servers may be located on on-site computing devices in the same physical location as the contact center agents, or may be located off-site in a different geographic location, e.g., a remote data center connected to the contact center via a network such as the Internet. Furthermore, some of the servers may be located in on-site computing devices at the contact center while other servers may be located in off-site computing devices, or servers providing redundant functionality may be provided via both on-site and off-site computing devices to provide better fault tolerance. In some embodiments, functionality provided by servers located on off-site computing devices may be accessed and provided via a virtual private network (VPN) as if such servers were on-site, or functionality may be provided using Software as a Service (SaaS) to provide functionality over the Internet using various protocols, such as by exchanging data using encoding in Extensible Markup Language (XML) or JSON.
[0104] 8A and 8B are diagrams illustrating an embodiment of a computing device, generally designated 800, that may be used in embodiments of the present invention. Each computing device 800 includes a CPU 805 and a main memory unit 810. As shown in FIG. 8A, the computing device 800 may also include a storage device 815, a removable media interface 820, a network interface 825, an input / output (I / O) controller 830, one or more display devices 835A, a keyboard 835B, and a pointing device 835C (e.g., a mouse). The storage device 815 may include, but is not limited to, storage for an operating system and software. As shown in FIG. 8B, each computing device 800 may also include additional optional elements, such as a memory port 840, a bridge 845, one or more additional I / O devices 835D, 835E, and a cache memory 850 in communication with the CPU 805. The input / output devices 835A, 835B, 835C, 835D, and 835E may be collectively referred to herein as 835.
[0105] The CPU 805 is any logic circuit that responds to and processes instructions from the main memory unit 810. It may be implemented, for example, in an integrated circuit in the form of a microprocessor, microcontroller, or graphics processing unit, or in a field programmable gate array (FPGA) or application specific integrated circuit (ASIC). The main memory unit 810 may be one or more memory chips that store data and allow any storage location to be directly accessed by the central processing unit 805. As shown in FIG. 8A, the central processing unit 805 communicates with the main memory 810 via a system bus 855. As shown in FIG. 8B, the central processing unit 805 may also communicate directly with the main memory 810 via a memory port 840.
[0106] In one embodiment, the CPU 805 may include multiple processors and may provide functionality for the concurrent execution of instructions or the concurrent execution of a single instruction on one or more pieces of data. In one embodiment, the computing device 800 may include a parallel processor having one or more cores. In one embodiment, the computing device 800 comprises a shared memory parallel device having multiple processors and / or multiple processor cores that access all available memory as a single global address space. In another embodiment, the computing device 800 is a distributed memory parallel device having multiple processors that each access only local memory. The computing device 800 may have both some memory that is shared and some memory that may only be accessed by a particular processor or subset of processors. The CPU 805 may include a multi-core microprocessor that combines two or more independent processors in a single package, e.g., in a single integrated circuit (IC). For example, the computing device 800 may include at least one CPU 805 and at least one graphics processing unit.
[0107] In one embodiment, CPU 805 provides single instruction multiple data processing (SIMD) capabilities, e.g., the capability for simultaneous execution of a single instruction on multiple data. In another embodiment, some processors within CPU 805 may provide the capability for simultaneous execution of multiple instructions on multiple data (MIMD). CPU 805 may also use any combination of SIMD and MIMD cores within a single device.
[0108] FIG. 8B illustrates an embodiment in which the CPU 805 communicates directly with the cache memory 850 through a secondary bus, sometimes referred to as a backside bus. In other embodiments, the CPU 805 communicates with the cache memory 850 using a system bus 855. The cache memory 850 typically has a faster response time than the main memory 810. As shown in FIG. 8A, the CPU 805 communicates with various I / O devices 835 through a local system bus 855. Various buses can be used as the local system bus 855, including, but not limited to, a Video Electronics Standards Association (VESA) local bus (VLB), an Industry Standard Architecture (ISA) bus, an Extended Industry Standard Architecture (EISA) bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI Extended (PCI-X) bus, a PCI-Express bus, or a NuBus. For embodiments in which the I / O device is a display device 835A, the CPU 805 may communicate with the display device 835A via an Advanced Graphics Port (AGP). Figure 8B illustrates an embodiment of a computer 800 in which the CPU 805 communicates directly with an I / O device 835E. Figure 8B also illustrates an embodiment in which local bus and direct communication are mixed. The CPU 805 communicates with an I / O device 835D using a local system bus 855 while communicating directly with the I / O device 835E.
[0109] A wide variety of I / O devices 835 may be present in computing device 800. Input devices include one or more keyboards 835B, a mouse, a trackpad, a trackball, a microphone, and a drawing board, to name a few non-limiting examples. Output devices include a video display device 835A, speakers, and a printer. The I / O controller 830 shown in FIG. 8A may control one or more I / O devices, such as, for example, a keyboard 835B and a pointing device 835C (e.g., a mouse or optical pen).
[0110] 8A, computing device 800 may support one or more removable media interfaces 820, such as a floppy disk drive, a CD-ROM drive, a DVD-ROM drive, a tape drive of various formats, a USB port, a Secure Digital or COMPACT FLASH™ memory card port, or any other device suitable for reading data from read-only media, or for reading data from or writing data to read-write media. I / O device(s) 835 may be a bridge between the system bus 855 and the removable media interface 820.
[0111] The removable media interface 820 may be used, for example, to install software and programs. The computing device 800 may further include a storage device 815, such as one or more hard disk drives or hard disk drive arrays, for storing an operating system and other related software, and for storing application software programs. Optionally, the removable media interface 820 may also be used as a storage device. For example, the operating system and software may be executed from a bootable medium, such as a bootable CD.
[0112] In one embodiment, the computing device 800 may include or be connected to multiple display devices 835A, each of which may be the same or different type and / or form. Thus, any of the I / O devices 835 and / or I / O controllers 830 may include any type and / or form of suitable hardware, software, or combination of hardware and software to support, enable, or provide for the connection to and use of multiple display devices 835A by the computing device 800. For example, the computing device 800 may include any type and / or form of video adapter, video card, drivers, and / or libraries for interfacing, communicating, connecting, or otherwise using the display devices 835A. In one embodiment, the video adapter may include multiple connectors for interfacing to the multiple display devices 835A. In another embodiment, the computing device 800 may include multiple video adapters, each video adapter connected to one or more of the display devices 835A. In other embodiments, one or more of the display devices 835A may be provided by one or more other computing devices connected to the computing device 800, for example, via a network. These embodiments may include any type of software designed and constructed to use a display device of another computing device as a second display device 835A for computing device 800. Those skilled in the art will recognize and understand the various ways and embodiments in which computing device 800 may be configured to have multiple display devices 835A.
[0113] The embodiment of a computing device generally shown in Figures 8A and 8B may operate under the control of an operating system, which controls the scheduling of tasks and access to system resources. Computing device 800 may be running any operating system, any embedded operating system, any real-time operating system, any open source operating system, any proprietary operating system, any operating system for mobile computing devices, or any other operating system capable of running on a computing device and performing the operations described herein.
[0114] Computing device 800 may be any workstation, desktop computer, laptop or notebook computer, server machine, computer on a steering wheel, mobile phone or other portable telecommunications device, media playback device, gaming system, mobile computing device, or any other type and / or form of computing, telecommunications, or media device capable of communicating and having sufficient processor power and memory capacity to perform the operations described herein. In some embodiments, computing device 800 may have different processors, operating systems, and input devices consistent with the device.
[0115] In other embodiments, computing device 800 is a mobile device. Examples may include a Java-enabled mobile phone or personal digital assistant (PDA), a smartphone, a digital audio player, or a portable media player. In one embodiment, computing device 800 includes a combination of devices, such as a mobile phone combined with a digital audio player or a portable media player.
[0116] The computing device 800 may be one of multiple machines connected by a network or may include multiple machines so connected. A network environment may include one or more local machines, client nodes, client machines, client computers, client devices, endpoints, or endpoint nodes that communicate with one or more remote machines (which may also be generally referred to as server machines or remote machines) over one or more networks. In one embodiment, a local machine has the ability to function as both a client node seeking access to resources provided by a server machine and a server machine providing access to hosted resources for other clients. The network may be a LAN or WAN link, a broadband connection, a wireless connection, or a combination of any or all of the above. Connections may be established using a variety of communication protocols. In one embodiment, the computing device 800 communicates with other computing devices 800 through any type and / or form of gateway or tunneling protocol, such as Secure Sockets Layer (SSL) or Transport Layer Security (TLS). A network interface may include a built-in network adapter, such as a network interface card, suitable for interfacing the computing device to any type of network with which it can communicate and performing the operations described herein. The I / O device may be a bridge between the system bus and an external communication bus.
[0117] In one embodiment, the network environment may be a virtual network environment in which various components of the network are virtualized. For example, the various machines may be virtual machines implemented as software-based computers running on physical machines. The virtual machines may share the same operating system. In other embodiments, different operating systems may run on each virtual machine instance. In one embodiment, a "hypervisor" type of virtualization is implemented in which multiple virtual machines run on the same host physical machine, each functioning as if they had their own dedicated box. The virtual machines may also run on different host physical machines.
[0118] Other types of virtualization are contemplated, such as, for example, the network (e.g., via Software Defined Networking (SDN)). Functions, such as the Session Border Controller function and other types of functions, may also be virtualized, such as, for example, via Network Functions Virtualization (NFV).
[0119] In one embodiment, the use of LSH to automatically discover carrier audio messages within a large set of pre-connected audio recordings may be applied to support processes of media services for contact center environments, for example, this can help support call analysis processes for contact centers and eliminate the need for humans to listen to a large set of voice recordings to discover new carrier audio messages.
[0120] While the invention has been illustrated and described in detail in the drawings and foregoing description, it is to be considered as illustrative and not of limiting character, with the understanding that only the preferred embodiment has been shown and described, and that all equivalents, changes and modifications which come within the spirit of the invention as described herein and / or by the following claims are desired to be protected.
[0121] Accordingly, the appropriate scope of the present invention should be determined only by the broadest interpretation of the appended claims so as to embrace all such modifications and all equivalent relationships as illustrated in the drawings and described herein.
Claims
1. 1. A method for routing inbound interactions from an end user device to an agent device in a contact center environment using a computer system including a processor, comprising: the processor: performing, by a routing server operably coupled to the network, selecting an agent device for routing the inbound interaction using routing parameters provided by a statistics server operably coupled to the network, the routing parameters being calculated from historical data; The selection may be extracting, by the processor operatively coupled to the network, from a database operatively coupled to the network, the historical data including information identifying a customer's path, a stage representing an identified portion of the path, an elapsed time representing time spent in that portion, a path moment representing a stage through which the customer progresses from start to finish, and a sequence representing a stage in the path in which the customer is present; preprocessing the history data, so that the preprocessed data constitutes a probability vector approximating a stage path; deriving an adjacency graph based on the history data, which models the connectivity of each stage in the flow line; deriving sequence zero as the stage at which the customer starts their flow line; and deriving a stage history including an abandonment rate representing the ratio of input to output at each modeled stage; determining a stage forecast using the pre-processed historical data and building a forecast model; selecting an agent by the processor based on the predictive model; routing, by the routing server, the inbound interaction to the agent device of the selected agent; establishing a connection between the end user device and the agent device; The step prediction running an algorithm that iterates through the historical data to flush volumes determined by the probability vector through multiple stages and time periods; obtaining a residual portion by setting aside a portion of the historical data for validation; using the remaining portion to build and train the predictive model; calibrating the predictive model; For a given stage of the motion line moment, the adjacency graph is determined by a process of modeling the edges and nodes of the periphery; The sequence zero is determined as the first stage of the sequence in the flow line; determining, for each stage corresponding to sequence zero, the discard ratio, which is the ratio of the discard volume of the stage to the total volume entering the stage, by tagging interactions having the elapsed time greater than a duration threshold determined from the elapsed time as discarded; The probability vector is determined by finding a probability value from the i-th stage to the j-th stage, which is the ratio of the total volume from the i-th stage to the total volume exiting the i-th stage, where i and j are different integers identifying a stage. method.
2. The method of claim 1 , wherein the stages include a focus of the customer's journey and transitions from each stage of the customer's journey.
3. The method of claim 1 , wherein the extracting is triggered by one of a user action, a scheduled job, and a queue request from another service.
4. The method of claim 1 , wherein sequence zero comprises the first stage in a chain of sequence progression.
5. The method of claim 1 , wherein the stage history includes characteristics of each stage including a history vector count, a discard rate, and a probability vector matrix.
Citation Information
Patent Citations
Predicting device using neural network
JP2001236337A
Apparatus and method for preparing production and physical distribution schedule, apparatus and method for controlling production and physical distribution process, computer program, and computer-readable storage medium
JP2007206877A
Required staff number calculation device, required staff number calculation method, and program
JP2015167279A
System and method for generating forecasts and analysis of contact center behavior for planning purposes
US20140219436A1
