Patent Application
20180097940
Aspects of embodiments of the present invention relate to a system and method for dynamic generation and optimization of process flows for a customer contact center.
In order to remain competitive in the modern commerce system, many businesses remain constantly vigilant of evolving consumer demands, and strive to provide customers with the high quality products and services that they desire. To that end, many businesses employ contact centers that include automated systems and representatives of the business to process transactions and/or service the needs of their customers.
In order to improve efficiencies and reduce costs, contact center systems may employ automated systems to handle at least some portion of communication sessions with customers. For example, a contact center system may deploy an interactive voice response (IVR) system to enable the contact center to collect information about a customer and to determine an appropriate routing strategy, communication path, or execution strategy for the customer. Such systems may require a customer to navigate through a series of IVR menu options or an automated self-service portal, which enables the contact center to reduce employee or agent overhead, but may lead to additional effort on the part of customers who must spend time navigating the automated system. Additionally, such systems are typically inflexible and only allow customers to traverse one of a finite number of predetermined communication paths or execution strategies. Furthermore, the possible information that can be provided by a customer at each step in an IVR system may be limited to only a few discrete options, and the customer may lack the ability to indicate a desire to resolve multiple issues in the same communication session. Thus, for various reasons, related art IVR systems may create inherent inefficiencies in terms of customer time. Additionally, related art contact center systems may lead to inefficient use of contact center resources.
The above information discussed in this Background section is only for enhancement of understanding of the background of the described technology and therefore it may contain information that does not constitute prior art that is already known to a person having ordinary skill in the art.
Embodiments of the present invention are directed to systems and methods for anticipating and preloading data in a customer contact center.
According to some embodiments of the present invention, in a system for dynamically generating an execution flow for a customer contact center, the system includes: a switch; a processor coupled to the switch; and a memory coupled to the processor, wherein the memory stores instructions that, when executed by the processor, cause the processor to: receive customer input related to an ongoing communication session; perform natural language processing on the customer input to identify a plurality of intent parameters including a customer objective; generate an execution flow for achieving the customer objective based on the plurality of intent parameters; and transmit a signal to the switch for routing the ongoing communication session to a contact center resource according to the execution flow.
According to some example embodiments, the customer objective includes a plurality of customer objectives, and wherein the instructions further cause the processor to identify a plurality of execution steps for each of the plurality of customer objectives.
According to some example embodiments, the instructions further cause the processor to consolidate redundant steps for the plurality of customer objectives to generate consolidated steps.
According to some example embodiments, the instructions further cause the processor to generate the execution flow based on the consolidated steps.
According to some example embodiments, the instructions further cause the processor to identify customer profile data based on the customer input.
According to some example embodiments, the instructions further cause the processor to identify customer interaction history data based on the customer input.
According to some example embodiments, the instructions further cause the processor to optimize the execution flow according to contact center resources.
According to some example embodiments, optimizing the execution flow comprises selecting the execution flow from among a plurality of potential execution flows having a cost that is less than other ones of the potential execution flows.
According to some example embodiments, optimizing the execution flow comprises selecting the execution flow from among a plurality of execution flows based on the execution flow having a number of intermediate operations that is less than that of other ones of the execution flows.
According to some example embodiments, the instructions further cause the processor to: retrieve a domain model graph corresponding to the customer contact center, the domain model graph comprising a plurality of interconnected nodes; match the intent parameters including the customer objective to corresponding ones of the interconnected nodes; and generate the execution flow by selecting a path from among a plurality of potential paths for achieving the customer objective.
According to some example embodiments, the interconnected nodes correspond to intermediate steps for achieving the customer objective and comprise preprogrammed modules for executing the intermediate steps.
According to some example embodiments of the present invention, in a method for dynamically generating an execution flow for a customer contact center, the method includes: receiving, by a processor, customer input related to an ongoing communication session; performing, by the processor, natural language processing on the customer input to identify a plurality of intent parameters including a customer objective; generating, by the processor, an execution flow for achieving the customer objective based on the plurality of intent parameters; and transmitting, by the processor, a signal to a switch for routing the ongoing communication session to a contact center resource according to the execution flow.
According to some example embodiments, the customer objective includes a plurality of customer objectives, and the method further includes identifying, by the processor, a plurality of execution steps for each of the plurality of customer objectives.
According to some example embodiments, the method further includes consolidating, by the processor, redundant steps for the plurality of customer objectives to generate consolidated steps.
According to some example embodiments, the method further includes generating, by the processor, the execution flow based on the consolidated steps.
According to some example embodiments, the method further includes identifying, by the processor, customer interaction history data based on the customer input.
According to some example embodiments, the method further includes optimizing, by the processor, the execution flow according to contact center resources.
According to some example embodiments, optimizing the execution flow includes selecting the execution flow from among a plurality of potential execution flows having a cost that is less than other ones of the potential execution flows.
According to some example embodiments, the method further includes: retrieving, by the processor, a domain model graph corresponding to the customer contact center, the domain model graph comprising a plurality of interconnected nodes; matching, by the processor, the intent parameters including the customer objective to corresponding ones of the interconnected nodes; and generating, by the processor, the execution flow by selecting a path from among a plurality of potential paths for achieving the customer objective.
According to some example embodiments of the present invention, in a system for dynamically generating an execution flow for a customer contact center, the system includes: means for receiving customer input related to an ongoing communication session; means for performing natural language processing on the customer input to identify a plurality of intent parameters including a customer objective; means for generating an execution flow for achieving the customer objective based on the plurality of intent parameters; and means for transmitting a signal to a switch for routing the ongoing communication session to a contact center resource according to the execution flow.
A more complete appreciation of the present invention, and many of the attendant features and aspects thereof, will become more readily apparent as the invention becomes better understood by reference to the following detailed description when considered in conjunction with the accompanying drawings in which like reference symbols indicate like components, wherein:
The present invention is described in one or more embodiments in the following description with reference to the figures, in which like numerals represent the same or similar elements. While the invention is described in terms of the best mode for achieving the invention's objectives, it will be appreciated by those skilled in the art that it is intended to cover alternatives, modifications, and equivalents as may be included within the spirit and scope of the invention as defined by the appended claims and their equivalents as supported by the following disclosure and drawings.
Generally, modern contact centers are staffed with agents or employees who serve as an interface between an organization, such as a company, and outside entities, such as customers. For example, human sales agents at contact centers may assist customers in making purchasing decisions and may receive purchase orders from those customers. Similarly, human support agents at contact centers may assist customers in solving problems with products or services provided by the organization. Interactions between contact center agents and outside entities (customers) may be conducted by speech voice (e.g., telephone calls or voice over IP or VoIP calls), video (e.g., video conferencing), text (e.g., emails or text chat), or through other media.
In order to remain competitive, however, businesses constantly strive to provide high quality service to customers while keeping prices low. Employing and training dozens, hundreds, or even thousands of live human agents to handle interactions with customers adds additional overhead costs to the business, which may eventually be passed on to consumers in the form of higher prices for the products or services sold by the business.
Accordingly, embodiments of the present invention are directed to improving efficiency and productivity during interactions, while simultaneously improving the customer experience. Embodiments of the present invention are also directed to providing efficiencies and speed for the various computer resources invoked during such interactions. For example, embodiments of the present invention provide systems and methods for dynamic generation and optimization of process flows or execution strategies for a customer contact center. According to some embodiments, such dynamically generated and optimized process flows or execution strategies may be generated based on arbitrary or natural language customer input of requests for handling one or more specific problem domains.
In the various embodiments, the terms interaction and communication are used generally to refer to any real-time and non-real time interaction that uses any communication channel including, without limitation telephony calls (PSTN or VoIP calls), emails, vmails (voice mail through email), video, chat, screen-sharing, text messages, social media messages, web real-time communication (e.g. WebRTC calls), and the like.
According to one example embodiment, the contact center 102 includes resources (e.g. personnel, computers, and telecommunication equipment) to enable delivery of services via telephone or other communication mechanisms. Such services may vary depending on the type of contact center, and may range from customer service to help desk, emergency response, telemarketing, order taking, and the like.
Customers, potential customers, or other end users (collectively referred to as customers or end users, e.g., end user 106) desiring to receive services from the contact center 102 or the business 104 may initiate an inbound communication to the contact center 102 via their end user devices 108a-108c (collectively referenced as electronic device 108).
Each of the electronic devices 108 may be a communication device conventional in the art, such as, for example, a telephone, wireless phone, smart phone, personal computer, electronic tablet, and/or the like, that is configured to engage in communications with other electronic devices. Users operating the electronic devices 108 may initiate, manage, and respond to telephone calls, emails, chats, text messaging, web-browsing sessions, and other multi-media transactions.
Inbound and outbound communications from and to the electronic devices 108 may traverse the telephone, cellular, and/or data communication network 110 depending on the type of device that is being used. For example, the communications network 110 may include a private or public switched telephone network (PSTN), local area network (LAN), private wide area network (WAN), and/or public wide area network such as, for example, the Internet. The communications network 110 may also include a wireless carrier network including a code division multiple access (CDMA) network, global system for mobile communications (GSM) network, and/or any 3G or 4G network conventional in the art.
According to one example embodiment, the contact center 102 includes a switch/media gateway 112 coupled to the communications network 110 for receiving and transmitting telephony interactions between end users and the contact center 102. The switch/media gateway 112 may include a telephony switch or communication switch configured to function 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. In this regard, the switch 112 may include an automatic call distributor, a private branch exchange (PBX), an IP-based software switch, and/or any other switch with specialized hardware and software configured to receive Internet-sourced interactions and/or telephone network-sourced interactions from a customer, and route those interactions to, for example, an agent telephony device. In this example, the switch/media gateway establishes a voice path/connection (not shown) between the calling customer and the agent telephony device, by establishing, for example, a connection between the customer's telephony device and the agent telephony device.
According to one example embodiment of the invention, the switch is coupled to a call controller 118 which may, for example, serve as an adapter or interface between the switch and the remainder of the routing, monitoring, and other communication-handling components of the contact center.
The call controller 118 may be configured to process PSTN calls, VoIP calls, and the like. For example, the call controller 118 may be configured with computer-telephony integration (CTI) software for interfacing with the switch/media gateway and contact center equipment. In one embodiment, the call controller 118 may include a session initiation protocol (SIP) server for processing SIP calls. According to some example embodiments, the call controller 118 may, for example, extract data about the customer interaction such as the caller's telephone number, often known as the automatic number identification (ANI) number, or the customer's internet protocol (IP) address, or email address, and communicate with other CC components in processing the interaction.
According to one example embodiment of the invention, the system further includes an interactive media response (IMR) server 122, which may also be referred to as a self-help system, virtual assistant, or the like. The IMR server 122 may be similar to an interactive voice response (IVR) server, except that the IMR server 122 is not restricted to voice, but may cover a variety of media channels including voice. Taking voice as an example, however, the IMR server may be configured with an IMR script for querying customers on their needs. For example, a contact center for a bank may tell customers, via the IMR script, to “press 1” if they wish to get an account balance. If this is the case, through continued interaction with the IMR server 122, customers may complete service without needing to speak with an agent. The IMR server 122 may also ask an open ended question such as, for example, “How can I help you?” and the customer may speak or otherwise enter a reason for contacting the contact center. The customer's response may then be used by a routing server 124 to route the call or communication to an appropriate contact center system 102 resource.
If the communication is to be routed to an agent, the call controller 118 interacts with the routing server (also referred to as an orchestration server) 124 to find an appropriate agent for processing the interaction. The selection of an appropriate agent for routing an inbound interaction may be based, for example, on a routing strategy employed by the routing server 124, and further based on information about agent availability, skills, and other routing parameters provided, for example, by a statistics server 132. The processing logic of the routing/orchestration server 124 may be rules driven, and may leverage, for example, intelligent workload distribution protocols and various business rules for routing the interactions.
In some embodiments, the routing server 124 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 contact center to resolve any customer issues, and the like. The database may be managed by any database management system conventional in the art, such as Oracle, IBM DB2, Microsoft SQL server, Microsoft Access, PostgreSQL, MySQL, FoxPro, NoSQL, SQLite, and the like, and may be stored in a mass storage device 126. The routing server 124 may query the customer information from the customer database via an ANI or any other information collected by the IMR 122.
Once an appropriate agent is identified as being available to handle a communication, a connection may be made between the customer and an agent device 130a-130c (collectively referenced as 130) of the identified agent. Collected information about the customer and/or the customer's historical information may also be provided to the agent device for aiding the agent in better servicing the communication. In this regard, each agent device 130 may include a telephone adapted for regular telephone calls, VoIP calls, and the like. The agent device 130 may also include a computer for communicating with one or more servers of the contact center and performing data processing associated with contact center operations, and for interfacing with customers via voice and other multimedia communication mechanisms.
The contact center system may also include a multimedia/social media server 154 for engaging in media interactions other than voice interactions with the end user devices 108. The media interactions may be related, for example, to email, vmail (voice mail through email), chat, video, text-messaging, web, social media, co-browsing, and the like. In this regard, the multimedia/social media server 154 may take the form of any IP router conventional in the art with specialized hardware and software for receiving, processing, and forwarding multi-media events. According to some embodiments, the multimedia/social media server 154 may be configured to maintain chat conversations, generate chat transcripts, and determine whether or not a chat communication is completed (e.g., based on timeout or by a customer closing a chat window). Additionally, the multimedia/social media server 154 may be configured to keep a chat session alive even when a particular chat server instance crashes, and also process or facilitate chat transfers and conference sessions.
The web servers 120 may include, for example, social interaction site hosts for a variety of known social interaction sites to which an end user may subscribe, such as, for example, Facebook, Twitter, and the like. In this regard, although in the embodiment of
According to one example embodiment of the invention, in addition to real-time interactions, deferrable (also referred to as back-office or offline) interactions/activities may also be routed to the contact center agents. Such deferrable activities may include, for example, responding to emails, responding to letters, attending training seminars, or any other activity that does not entail real time communication with a customer. In this regard, an interaction (iXn) server 156 interacts with the routing server 124 for selecting an appropriate agent to handle the activity. Once assigned to an agent, an activity may be pushed to the agent, or may appear in the agent's workbin 136a-136c (collectively referenced as 136) as a task to be completed by the agent. The agent's workbin may be implemented via any data structure conventional in the art, such as, for example, a linked list, array, and/or the like. The workbin 136 may be maintained, for example, in buffer memory of each agent device 130.
According to one example embodiment of the invention, the mass storage device(s) 126 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 reason for the interaction, disposition data, time on hold, handle time, etc.), and the like.
According to one embodiment, some of the data (e.g. customer profile data) may be maintained in a customer relations management (CRM) database hosted in the mass storage device 126 or elsewhere. The mass storage device may take form of a hard disk or disk array, flash memory, magnetic table, or other suitable mass storage device as is conventional in the art, for storing information used as part of the contact center system 100 and the contact center system 100.
According to some embodiments, the contact center system 102 may include a universal contact server (UCS) 127, configured to retrieve information stored in the CRM database and direct information to be stored in the CRM database. For example, the UCS 127 may be utilized as part of the contact center system 100 to facilitate maintaining a history on how well a particular contact center resource, tool, agent, etc., functions for a given customer or interaction topic as a reference for interactions. The UCS 127 may also be configured to facilitate maintaining a history of customers' preferences. Additionally, the UCS 127 may be configured to capture and store data regarding comments from agents, customer communication history, and the like.
The contact center system 100 may additionally include a knowledge management server 150 for facilitating interactions between customers operating the end user devices 108a-108c and a knowledge system 152 (which may be included as part of the contact center 102, or may be operated remotely by a third party). The knowledge management server 152 is a computer system capable of receiving questions and providing answers as output. According to some example embodiments, the knowledge system may be embodied as IBM Watson®. Of course, any other knowledge system may be used as will be appreciated by a person having ordinary skill in the art. In some embodiments, the knowledge system 152 is an artificially intelligent computer system capable of answering questions posed in natural language by retrieving information from information sources such as encyclopedias, dictionaries, newswire articles, literary works, or other documents submitted to the knowledge system 152 as reference materials, as is well known in the art.
Referring again to the routing/orchestration server 124, this server is configured to work with the various other components of the contact center system 100 for orchestrating the handling of interactions based on a routing strategy utilized by the particular contact center. Depending on the type of routing strategy (flow) generated for a particular route point of the contact center (e.g. a particular dialed number), and depending on the specific values of parameters set for the routing strategy, different options, media treatments, and routing is performed for the interaction. The routing may involve invoking different media channels as determined by the generated flow. For example, the flow may call for multi-modal interaction where two or more media channels are invoked in parallel. In this regard, the orchestration server 124 is configured to transmit message (e.g. SIP messages) to different servers including a SIP server, chat server, email server, and the like, depending on the type of media channel that is invoked.
The contact center system 100 may also include a reporting server 134 configured to generate reports from data aggregated by the statistics server 132. Such reports may include near real-time reports or historical reports concerning the state of resources, such as, for example, average waiting time, abandonment rate, agent occupancy, and the like. The reports may be generated automatically or in response to specific requests from a requestor (e.g. agent/administrator, contact center application, and/or the like).
According to some embodiments of the present invention, the contact center system may further include an execution strategy server 160 for managing automated communications with end users 106 operating end user devices 108 to determine customer intent and generate an execution plan based on the customer intent. According to one embodiment, the execution strategy server 160 may be in electronic communication with the other resources of the contact center system 100. For example, the execution strategy server 160 may be coupled to the interaction server 156, statistics server 132, knowledge management server 150, and orchestration server 124 for generating and executing an execution strategy.
Throughout the present Specification, the terms “execution strategy,” “execution flow,” “execution path,” and “execution plan” are used interchangeably to refer to a flow of steps executed as part of a communication session between components or resources of a contact center system and a customer operating a customer communication device.
Although the execution strategy server 160 is depicted in the embodiment of
The various servers of
According to some example embodiments, the execution strategy server 160 may be configured with a natural language processing module or engine 170 for facilitating or coordinating natural language communications between the customer 106 and the contact center system. According to some example embodiments, the natural language processing module 170 may operate to receive the customer's user input or signals from the end user device 108 during a communication session, for example, after minimal prompting to the user. For example, the execution strategy server 160 (or any other suitable component of the contact center system 100, such as the IMR 122) may transmit a signal or automated voice communication to the customer 106 through the end user device 108 asking the customer to describe their objective (e.g., “how may I help you today?”).
The natural language processing module 170 may then parse the user's input using any suitable natural language processing (NLP) algorithm or strategy to identify various parts of speech and parameters of the customer's objective. The user input may be free speech or text (e.g., natural language speech or text). In the example where the user input is free speech, the module 170 may process the speech to find key phrases, and the key phrases may be matched with speech recognition grammar to identify on or more pre-stored categories of user intent/objective. Thus, embodiments of the present invention enable customers (e.g., users) to provide customer input in the form of natural language or free speech or text to the contact center system. The customer input may include various personal information, customer history data, and the like, as well as an objective or even a plurality of objectives, each of which can be parsed and identified by the contact center system. Accordingly, embodiments of the present invention may enable customers to avoid traversing numerous steps in an interactive voice response menu, for example, to more quickly and more conveniently provide information to the contact center system. Additionally, the contact center system is enabled, as will be described in more detail below, to obtain multiple customer objectives quickly and prior to generating an execution strategy, which may facilitate more efficient use of resources and lower costs to the contact center, as well as increased time efficiency for both the customer and the contact center. Furthermore, as described in more detail below, embodiments of the present invention may utilize a hybrid system with free speech or natural language speech or text and predefined or preprogrammed steps for achieving IMR building blocks for facilitating specific scenarios and conversations or objectives. For example, a certain type of service or conversation objective may utilize certain user data. Accordingly, embodiments of the present invention may a predefined or preprogrammed IMR building block for collecting the relevant user data. User data that is already known, for example, from initial free speech user input or archived customer profile data could be prepopulated, and the IMR building block may collect only the remaining data. Additionally, embodiments of the present invention are configured to generate additional predefined IMR building blocks for collecting relevant data or information from users based on analyzing previous conversations and one or more business needs. An execution strategy generator and/or optimizer 174 may also be included as part of the execution strategy server 160. Based on the parameters of the customer's one or more objectives, the execution strategy generator 174 may operate to generate and/or optimize an execution strategy or execution flow for achieving the customer's one or more objectives. According to some example embodiments, the execution strategy generator 174 is configured to identify the user's one or more objectives based on the natural language processing, and dynamically generate an execution plan or execution flow to achieve the one or more objectives.
According to some embodiments, during an initial free speech conversation the system may identify multiple corresponding services or conversation objectives to be achieved. The execution strategy generator 174 may identify dependencies between the services or conversation objectives, for example, a first service or objective should be performed prior to a second service or objective, whereas a third service or objective is independent of the first two services or objectives and can be processed in parallel. Additionally, according to embodiments of the present invention, the execution strategy generator 174 may identify a best matching media type for a given service or conversation objective and generate an execution strategy according to the matching media type, which may also be influenced or dependent upon a user's preferences.
According to some embodiments, a plurality of predefined or predetermined objectives or actions that the contact center system 100 is configured to handle are stored in memory, for example, in the database 126. For any given customer objective, the execution strategy generator 174 may identify or retrieve (e.g., from memory 126) one or more intermediate steps or actions to occur for achieving the objective. For example, achieving an objective may involve various intermediate steps for obtaining additional information from the customer such as personal identifying information or authentication information, purchase history information, personal preferences about various products or services, and the like. Additionally, achieving an objective may involve various intermediate steps for obtaining additional information from other contact center resources (e.g., the memory 126, stat server 132, etc.) as well as external or third party resources (e.g., third party clouds, knowledge system 152, etc.).
The intermediate steps for achieving the objective may be represented and pre-stored in memory (e.g., memory 126) in association with the objective and generated using any suitable language or framework conventional in the art, such as, for example, Artificial Intelligence Markup Language (AIML), SCXML, or the like.
By identifying the intermediate steps necessary to achieve a customer's objective, the execution strategy generator 174 then operates to generate an execution strategy or flow by organizing the steps into an appropriate order based on a logical progression of steps. For example, for any given customer objective, certain steps must occur before other steps, while the order of some steps may vary depending on different execution path variations. The execution strategy may be generated using any of various languages and frameworks conventional in the art such as, for example, AIML, SCXML, or the like, to interconnect the intermediate steps according to the design of the execution strategy.
According to some embodiments, based on the intermediate steps identified for achieving the customer's objective, the execution strategy generator 174 may obtain analytics or status information regarding various contact center resources, and optimize the execution flow (e.g., generate an optimized execution flow) in order to reduce latency between steps, or to optimize demands on contact center resources. According to some embodiments, optimizing the execution flow may include consolidating redundant steps (e.g., steps that are utilized to achieve multiple objectives, such as customer identification or authentication) and/or utilizing any suitable shortest path algorithm, for example, Direct A-Cyclic Graph with positive weights, to identify an optimized execution path from one or more possible variations of execution paths. An optimized execution path may include, for example, a path in which certain steps are performed in parallel rather than serially, thereby reducing overall latency for achieving the customer's objective. An optimized execution path may also include, for example, a path in which the order of certain steps varies from that of other possible execution paths, in order to reduce the burden on certain contact center resources at certain times.
An optimized execution path in the context of a scheduled callback may include, for example, offering timeslots when an expert agent for multiple services or conversation objectives will be available. In the context of a customer wishing to achieve various objectives in which overlapping personal data would be collected to achieve each individual objective, an optimized execution path may include collecting all of the relevant personal data a single time and utilized when needed for the different conversation objectives.
In some embodiments, an optimized execution flow may include processing multiple conversation objectives in parallel, for example, by way of different media channels. Further, in situations in which multiple users request the same or similar knowledge or expert information, the requests may be aggregated into one request and the response may be distributed to each of the customers (e.g., by way of a chat or text-based communication channel).
According to some embodiments, an optimized execution flow may involve arranging or ordering the steps for achieving a particular conversation objective, for example, based on previous communication history, user preferences, agent availability, cross-/up-sell potential offerings, and the like.
Additionally, an optimized execution flow may be configured to have reduced cost with respect to contact-center resources, for example, by selecting sufficiently qualified agents that are paid less than other agents, or by avoiding the use of expensive system or hardware resources if the objective can be achieved through less expensive mechanisms (such as through a simple selection menu as opposed to ASR). An optimized execution flow may additionally be designed to resolve customer objectives during a fewer number of interactions (e.g., during the first communication), thereby avoiding repeated calls.
An interpreter module 176 operating as part of the execution strategy server 160 (or incorporated into another component of the contact center system 100 such as, for example, the orchestration server 124) then operates to interpret and execute the execution strategy generated by the execution strategy server 160.
At 302, the NLP module 170 parses intent parameters from the natural language customer input using any suitable natural language processing algorithm. Intent parameters include, for example, subject, verb, objects, and any other relevant details or data provided by the user. For example, if a user provides natural language input saying “I would like to pay my bill,” the NLP module 170 may identify the subject “I,” the verb “pay,” and the object “bill.” As shown, for example, in
According to some embodiments, the different phases illustrated in
After the one or more customer objectives 402a-402b are identified, the customer contact center system compares (e.g., by the execution strategy generator 174) the identified customer objectives 402a-402b with a plurality of pre-stored or preprogrammed customer objectives 404a-404e stored in memory (e.g., the memory 126). The number of pre-stored or preprogrammed customer objectives is not limited to the number illustrated in
By comparing the customer objectives 402a-402b with the preprogrammed customer objectives 404a-404e, the customer contact center system may identify (e.g., by the execution strategy generator 174) one or more of the preprogrammed customer objectives 404a-404e that matches the customer objectives 402a-402b provided as part of the customer input. For example, in the embodiment illustrated in
Next, as illustrated in
Each of the blocks or nodes 500 through 514 represent various possible nodes or operations in an execution strategy, some of which have relationships or connections with other nodes as illustrated by the arrows. An execution strategy may be generated based on customer input, which may be parsed using natural language processing to identify intent parameters, thereby enabling the system to identify a starting node, an ending node, and intermediate nodes. The system may then generate an execution strategy that follows a path from the starting node to the ending node and passes through the intermediate nodes. In certain situations, various possible execution strategies may be possible, and the system may optimize the execution strategy, for example, by selecting the path passing through the fewest number of nodes, the path having the lowest cost, or by consolidating redundant nodes or aspects of redundant nodes.
Update: customer_provisioning_settings, where userid==“identified user” set call_forward=“415xxxxxxx.”
Thus, the objective may be identified as the customer wishing to update the customer provision or preference settings. Additionally, unique identification data may be used to identify the user (e.g., by way of the phone number from which the customer is calling). Finally, the new setting for call forwarding is to be set to “415xxxxxxx.”
In order to parse the natural language sentence of the customer input as described above, the natural language engine may first identify various parts of speech such as the verb “forward,” the noun “calls,” and the contextual string of characters “414xxxxxxx.” The word forward may be a pre-stored or predefined synonym for the action of updating call forward settings. Accordingly, the system may interpret the sentence as follows: ‘forward’=>“update<user preferences>set call forwarding=<context>” according to the existing knowledge of the system. Because the certain data may be unknown, such as “user preferences,” the system may prompt the user to provide such information or retrieve the information from memory, and then insert the information into the rule.
As illustrated in
In the use case illustrated in
According to the use case of
According to some embodiments, the execution strategy server 160 may utilize contact center system analytics and perform an analysis of the next best action, based on customer input. For example,
For the purposes of illustration, assume a customer for a customer contact center system 100 operating on behalf of a telecommunications provider provides the natural language customer input “My internet is slow—please upgrade it to a faster plan.” Using a natural language processing algorithm, the system may identify the customer objective therefore as being a desire to upgrade service. In response to the customer input, the execution strategy server 160 may initiate retrieval of analytics data regarding the customer contact center system 100 to determine possible options for the alternative Internet plan selection. In particular, the execution strategy server 160 may inquire which Internet plans are available given the customer's location, and then identify which plans are available that are faster than the current package the customer owns. Additionally, an analysis may be performed to select the appropriate shipping method for the customer based on shipment duration and cost. According to some embodiments, the contact center system may be configured to operate as an intermediary between multiple systems. For example, the contact center system may be configured to execute a transaction or achieve an objective with a third party cloud system (e.g., by utilizing a publicly accessible application program interface (API)) to place orders of products or services. In the embodiment illustrated in
Continuing from
As discussed above with respect to
Each of the intent parameters 902a-902c is matched to a corresponding node in a domain model graph 904, including a start node 906, an end node 908, and one or more intermediate nodes 910. Based on the matching of the intent parameters 902a-902c to the various nodes, the system may generate an optimized execution strategy 920, as shown in
Thus, embodiments of the present invention are directed to a system for enabling customers to provide natural language input to a contact center system, with minimal prompting by the contact center system, and the contact center system can then dynamically generate an execution strategy for achieving one or more of the customer's objectives. A customer's objective may be determined based on natural language input. In particular, the natural language customer input is parsed into its various components to identify the customer's objective, which is matched to one or more pre-stored or preprogrammed objectives. Each pre-stored or preprogrammed customer objectives has one or more pre-stored or preprogrammed intermediate steps to be executed in order to achieve the objective. Each possible objective capable of being handled by the contact center system, and the steps for achieving those objectives, would be preprogrammed or pre-stored, but the particular order of the steps could vary depending on various factors such as contact center resources and where there are redundancies in achieving multiple objectives. An execution strategy is then generated by stringing together the various steps in a logical order according to these various optimization factors. Finally, the execution strategy is interpreted and executed by the contact center system to achieve the customer's objective.
Accordingly, embodiments of the present invention may operate to increase customer freedom in communicating and achieving customer objectives. Additionally, because customers are given the freedom to articulate their objectives using natural language, customers are also able to also articulate a desire to achieve multiple objectives during the same communication session, thereby enabling the customer contact center to reduce inefficiencies in an execution strategy. For example, for situations in which multiple objectives include the same or similar intermediate steps, such steps may be consolidated to reduce redundancies. Further, steps that are independent from one another may be executed in parallel thereby potentially reducing the overall latency and cost for achieving the customer's objectives.
In one embodiment, each of the various servers, controllers, switches, gateways, engines, and/or modules (collectively referred to as servers) in the afore-described figures is a process or thread, running on one or more processors, in one or more computing devices 1500 (e.g.,
The various servers may be located on a computing device on-site at the same physical location as the agents of the contact center or may be located off-site (or in the cloud) in a geographically different location, e.g., in a remote data center, connected to the contact center via a network such as the Internet. In addition, some of the servers may be located in a computing device on-site at the contact center while others may be located in a computing device off-site, or servers providing redundant functionality may be provided both via on-site and off-site computing devices to provide greater fault tolerance. In some embodiments of the present invention, functionality provided by servers located on computing devices off-site may be accessed and provided over a virtual private network (VPN) as if such servers were on-site, or the functionality may be provided using a software as a service (SaaS) to provide functionality over the internet using various protocols, such as by exchanging data using encoded in extensible markup language (XML) or JavaScript Object notation (JSON).
The central processing unit 1521 is any logic circuitry that responds to and processes instructions fetched from the main memory unit 1522. It may be implemented, for example, in an integrated circuit, in the form of a microprocessor, microcontroller, or graphics processing unit (GPU), or in a field-programmable gate array (FPGA) or application-specific integrated circuit (ASIC). The main memory unit 1522 may be one or more memory chips capable of storing data and allowing any storage location to be directly accessed by the central processing unit 1521. As shown in
A wide variety of I/O devices 1530 may be present in the computing device 1500. Input devices include one or more keyboards 1530a, mice, trackpads, trackballs, microphones, and drawing tablets. Output devices include video display devices 1530c, speakers, and printers. An I/O controller 1523, as shown in
Referring again to
The removable media interface 1516 may for example be used for installing software and programs. The computing device 1500 may further comprise a storage device 1528, 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, a removable media interface 1516 may also be used as the storage device. For example, the operating system and the software may be run from a bootable medium, for example, a bootable CD.
In some embodiments, the computing device 1500 may comprise or be connected to multiple display devices 1530c, which each may be of the same or different type and/or form. As such, any of the I/O devices 1530 and/or the I/O controller 1523 may comprise 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 1530c by the computing device 1500. For example, the computing device 1500 may include any type and/or form of video adapter, video card, driver, and/or library to interface, communicate, connect or otherwise use the display devices 1530c. In one embodiment, a video adapter may comprise multiple connectors to interface to multiple display devices 1530c. In other embodiments, the computing device 1500 may include multiple video adapters, with each video adapter connected to one or more of the display devices 1530c. In some embodiments, any portion of the operating system of the computing device 1500 may be configured for using multiple display devices 1530c. In other embodiments, one or more of the display devices 1530c may be provided by one or more other computing devices, connected, for example, to the computing device 1500 via a network. These embodiments may include any type of software designed and constructed to use the display device of another computing device as a second display device 1530c for the computing device 1500. One of ordinary skill in the art will recognize and appreciate the various ways and embodiments that a computing device 1500 may be configured to have multiple display devices 1530c.
A computing device 1500 of the sort depicted in
The computing device 1500 may be any workstation, desktop computer, laptop or notebook computer, server machine, handheld computer, mobile telephone or other portable telecommunication device, media playing device, gaming system, mobile computing device, or any other type and/or form of computing, telecommunications or media device that is capable of communication and that has sufficient processor power and memory capacity to perform the operations described herein. In some embodiments, the computing device 1500 may have different processors, operating systems, and input devices consistent with the device.
In other embodiments the computing device 1500 is a mobile device, such as a Java-enabled cellular telephone or personal digital assistant (PDA), a smart phone, a digital audio player, or a portable media player. In some embodiments, the computing device 1500 comprises a combination of devices, such as a mobile phone combined with a digital audio player or portable media player.
As shown in
In some embodiments, a central processing unit 1521 provides single instruction, multiple data (SIMD) functionality, e.g., execution of a single instruction simultaneously on multiple pieces of data. In other embodiments, several processors in the central processing unit 1521 may provide functionality for execution of multiple instructions simultaneously on multiple pieces of data (MIMD). In still other embodiments, the central processing unit 1521 may use any combination of SIMD and MIMD cores in a single device.
A computing device may be one of a plurality of machines connected by a network, or it may comprise a plurality of machines so connected.
The computing device 1500 may include a network interface 1518 to interface to the network 1504 through a variety of connections including, but not limited to, standard telephone lines, local-area network (LAN), or wide area network (WAN) links, broadband connections, wireless connections, 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 1500 communicates with other computing devices 1500 via any type and/or form of gateway or tunneling protocol such as Secure Socket Layer (SSL) or Transport Layer Security (TLS). The network interface 1518 may comprise a built-in network adapter, such as a network interface card, suitable for interfacing the computing device 1500 to any type of network capable of communication and performing the operations described herein. An I/O device 1530 may be a bridge between the system bus 1550 and an external communication bus.
According to one embodiment, the network environment of
Other types of virtualization is also contemplated, such as, for example, the network (e.g. via Software Defined Networking (SDN)). Functions, such as functions of the session border controller and other types of functions, may also be virtualized, such as, for example, via Network Functions Virtualization (NFV).
Although this invention has been described in certain specific embodiments, those skilled in the art will have no difficulty devising variations to the described embodiment, which in no way depart from the scope and spirit of the present invention. Furthermore, to those skilled in the various arts, the invention itself herein will suggest solutions to other tasks and adaptations for other applications. It is the applicant's intention to cover by claims all such uses of the invention and those changes and modifications which could be made to the embodiments of the invention herein chosen for the purpose of disclosure without departing from the spirit and scope of the invention. Thus, the present embodiments of the invention should be considered in all respects as illustrative and not restrictive, the scope of the invention to be indicated by the appended claims and their equivalents rather than the foregoing description.
