US20200065825A1 - Systems and methods for customer service prediction - Google Patents
Systems and methods for customer service prediction Download PDFInfo
- Publication number
- US20200065825A1 US20200065825A1 US16/112,625 US201816112625A US2020065825A1 US 20200065825 A1 US20200065825 A1 US 20200065825A1 US 201816112625 A US201816112625 A US 201816112625A US 2020065825 A1 US2020065825 A1 US 2020065825A1
- Authority
- US
- United States
- Prior art keywords
- customer
- customer service
- context
- data
- service request
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
- 238000000034 method Methods 0.000 title claims description 36
- 230000006854 communication Effects 0.000 claims abstract description 40
- 238000004891 communication Methods 0.000 claims abstract description 38
- 230000015654 memory Effects 0.000 claims abstract description 19
- 239000000463 material Substances 0.000 claims abstract description 7
- 238000004458 analytical method Methods 0.000 claims abstract description 6
- 230000008569 process Effects 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 14
- 230000009471 action Effects 0.000 claims description 10
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000010801 machine learning Methods 0.000 claims description 5
- 238000003058 natural language processing Methods 0.000 claims description 5
- 230000004044 response Effects 0.000 claims description 4
- 230000002452 interceptive effect Effects 0.000 claims description 3
- 230000001755 vocal effect Effects 0.000 claims 1
- 230000006870 function Effects 0.000 description 11
- 238000012546 transfer Methods 0.000 description 9
- 239000003795 chemical substances by application Substances 0.000 description 8
- 230000000694 effects Effects 0.000 description 7
- 238000013024 troubleshooting Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000003993 interaction Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 239000004065 semiconductor Substances 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013479 data entry Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 239000012925 reference material Substances 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000013518 transcription Methods 0.000 description 1
- 230000035897 transcription Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
- G06Q30/015—Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk
- G06Q30/016—After-sales
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
- G06F16/24575—Query processing with adaptation to user needs using context
-
- G06F17/30528—
-
- G10L15/265—
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
- H04M3/5133—Operator terminal details
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
- H04M3/5183—Call or contact centers with computer-telephony arrangements
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M2203/00—Aspects of automatic or semi-automatic exchanges
- H04M2203/40—Aspects of automatic or semi-automatic exchanges related to call centers
- H04M2203/402—Agent or workforce management
Definitions
- a common pitfall of customer service is high customer service agent turnover. Training customer service agents is both expensive and time consuming, and agents may not remember all of the training materials they are exposed to, leading to longer call times and decreased customer satisfaction. Further, customer service agents may not be familiar with smaller concepts or projects at a large enterprise. The above factors may result in lower sales volume, fewer new customers, or fewer retained customers.
- Disclosed embodiments include a system for providing resource material to a customer service representative (CSR).
- the system may include: a database storing a plurality of resources associated with a plurality of customer service contexts; one or more memories storing instructions; and one or more processors configured to execute the instructions to perform operations.
- the operations may include: receiving data associated with an on-going communication, the on-going communication comprising a customer service request received from a customer; analyzing the data associated with the on-going communication; determining an identity of the customer associated with the communication; determining a context of the request based on the analysis and based on historical data associated with the determined identity; automatically identifying, based on the context, a resource in the database associated with the determined context; and displaying, via a user interface in real-time during the communication, the resource associated with the customer service request.
- FIG. 1 depicts an example of a system environment for generating customer service prediction resources, consistent with the disclosed embodiments
- FIG. 2 depicts an example of a customer device, consistent with the disclosed embodiments
- FIG. 3 depicts an example of a device used by a customer service representative, consistent with the disclosed embodiments
- FIG. 4 shows a diagram of an exemplary facility server, consistent with the disclosed embodiments
- FIG. 5 is a flowchart of an exemplary prediction process, consistent with the disclosed embodiments.
- FIG. 6 is an exemplary customer service portal, consistent with the disclosed embodiments.
- FIG. 7 is an exemplary customer interface, consistent with the disclosed embodiments.
- customer service request will refer to any customer inquiry or problem requiring assistance.
- a customer service request may be troubleshooting an app or website; requesting account modifications, such as an address change, billing assistance; and the like.
- the prediction of a customer service solution in response to a customer service request or based on recent customer activity may result in increased customer satisfaction and retention by decreasing the time to resolve an issue or an inquiry from the customer.
- FIG. 1 is a diagram of a computer system 100 that may be configured to perform one or more software processes that, when executed by one or more processors, perform methods consistent with disclosed embodiments.
- the components and arrangements shown in FIG. 1 are not intended to limit the disclosed embodiments, as the components used to implement the disclosed processes and features may vary.
- system 100 may include a server 102 , a customer device 104 , a representative device 106 , and a database 108 .
- the components of system 100 may communicate directly, through network 110 .
- Other components known to one of ordinary skill in the art may be included in system 100 to perform tasks consistent with the disclosed embodiments.
- Server 102 may enable communication within external computer-based systems including computer system components such as desktop computers, workstations, tablets, hand held computing devices, memory devices, and/or internal network(s) connecting the components.
- computer system components such as desktop computers, workstations, tablets, hand held computing devices, memory devices, and/or internal network(s) connecting the components.
- Customer device 104 may be a personal computing device such as, for example, a general purpose or notebook computer, a mobile device with computing ability, a tablet, a smartphone, a wearable device, or smart watch, or any combination of these computers and/or affiliated components.
- customer device 104 may be a computer system or mobile computer device that is operated by the customer.
- customer device 104 may be a kiosk or automated teller machine (ATM).
- customer device 104 may be a landline telephone or device capable of receiving audio commands or commands via the telephone or device keypad.
- representative device 106 may be a device that is operated by a customer service specialist, representative, or other employee of a business entity.
- Representative device 106 may be a personal computing device such as, for example, a general purpose or notebook computer, a mobile device with computing ability, a tablet, smartphone, a wearable device, or smart watch, or any combination of these computers and/or affiliated components.
- representative device 106 may be a landline telephone or device capable of receiving audio commands or commands via the telephone or device keypad.
- Network 110 may comprise any type of computer networking arrangement used to exchange data.
- network 110 may be the Internet, a private data network, virtual private network using a public network, and/or other suitable connection(s) that enables system 100 to send and receive information between the components of system 100 .
- Network 110 may also include a public switched telephone network (“PSTN”) and/or a wireless cellular network.
- PSTN public switched telephone network
- FIG. 2 is a diagram of a representative device 106 , consistent with disclosed embodiments.
- representative device 106 may include a display 210 , one or more processors 220 , one or more input/output (“I/O”) devices 230 , a transceiver 240 memory 250 , and battery 270 .
- I/O input/output
- Display 210 may include one or more screens such as, for example, liquid crystal display (LCD), plasma, cathode ray tube (CRT), or projected screens. Display may display information such as customer service resources, customer data, and solution information.
- LCD liquid crystal display
- CRT cathode ray tube
- Display may display information such as customer service resources, customer data, and solution information.
- Processor 220 may be one or more known processing devices, such as microprocessors manufactured by IntelTM or AMDTM or licensed by ARM. Processor 220 may constitute a single-core or multiple-core processor that executes parallel processes simultaneously. For example, processor 220 may be a single-core processor configured with virtual processing technologies. In certain embodiments, processor 220 may use logical processors to simultaneously execute and control multiple processes. Processor 220 may implement virtual machine technologies, or other known technologies to provide the ability to execute, control, run, manipulate, store, etc. multiple software processes, applications, programs, etc. In another embodiment, processor 220 may include a multiple-core processor arrangement (e.g., dual, quad core, etc.) configured to provide parallel processing functionalities to allow representative device 106 to execute multiple processes simultaneously. One of ordinary skill in the art would understand that other types of processor arrangements could be implemented that provide for the capabilities disclosed herein.
- processor arrangements e.g., dual, quad core, etc.
- I/O devices 230 may include one or more devices that allow representative device 106 to receive input from a customer service representative or other user.
- I/O devices 230 may include, for example, one or more pointing devices, keyboards, buttons, switches, touchscreen panels, cameras, barcode scanners, radio frequency identification (RFID) tag reader, and/or microphones.
- RFID radio frequency identification
- Memory 240 may include a volatile or non-volatile, magnetic, semiconductor, solid-state, tape, optical, removable, non-removable, or other type of storage device or tangible (i.e., non-transitory) computer-readable medium that stores one or more program(s) 242 , such as app(s) 244 , and data 246 .
- Data 246 may include, for example, customer account information, recent customer activity, predicted customer service solutions, and/or relevant customer service resources.
- Program(s) 242 may include operating systems (not shown) that perform known operating system functions when executed by one or more processors.
- the operating systems may include Microsoft WindowsTM, UnixTM, LinuxTM AndroidTM and AppleTM operating systems, Personal Digital Assistant (PDA) type operating systems, such as Microsoft CETM, or other types of operating systems.
- PDA Personal Digital Assistant
- disclosed embodiments may operate and function with computer systems running any type of operating system.
- Representative device 106 may also include communication software that, when executed by a processor, provides communications with network 110 , such as Web browser software, tablet, or smart hand held device networking software, etc.
- Program(s) 242 may also include app(s) 244 , such as an interactive voice response (IVR) and/or touch-tone data entry (TDE) program which, when executed, gather initial information from a customer about a customer service request. For example, a customer making a customer service request via land-line telephone may be prompted to navigate through an automated menu and to provide details such as the nature of their request and/or their account number by speaking into the telephone or through by various numbers on the keypad.
- IVR interactive voice response
- TDE touch-tone data entry
- FIG. 3 shows a diagram of an exemplary customer device 104 , consistent with disclosed embodiments.
- customer device 104 may include a display 310 , I/O device(s) 320 , a processor 330 , a memory 340 having stored thereon data 346 and one or more programs 342 , such as app(s) 344 (e.g., a financial services app), and an antenna 350 .
- apps e.g., a financial services app
- Display 310 may include one or more devices for displaying information, including but not limited to, liquid crystal displays (LCD), light emitting diode (LED) screens, organic light emitting diode (OLED) screens, and other known display devices.
- LCD liquid crystal displays
- LED light emitting diode
- OLED organic light emitting diode
- I/O devices 320 may include one or more devices that allow customer device 104 to send and receive information. I/O devices 320 may include, for example, a pointing device, keyboard, buttons, switches, microphones, and/or a touchscreen panel. I/O devices 320 may also include one or more communication modules (not shown) for sending and receiving information from other components in system 100 by, for example, establishing wired or wireless connectivity (via antenna 350 ) between customer device 104 to network 110 , or by establishing direct wired or wireless connections between customer device 104 and other components of system 100 . Direct connections may include, for example, BluetoothTM, Bluetooth LETM, WiFi, near field communications (NFC), or other known communication methods which provide a medium for transmitting data between separate devices.
- wireless connections may include, for example, BluetoothTM, Bluetooth LETM, WiFi, near field communications (NFC), or other known communication methods which provide a medium for transmitting data between separate devices.
- Processor(s) 330 may be one or more known computing devices, such as those described with respect to processor 220 in FIG. 2 .
- Memory 340 may be a volatile or non-volatile, magnetic, semiconductor, tape, optical, removable, non-removable, or other type of storage device or tangible (i.e., non-transitory) computer-readable medium such as those described with respect to memory 240 in FIG. 2 .
- FIG. 4 shows a diagram of an exemplary facility server 130 , consistent with disclosed embodiments.
- facility server 130 may be a local server within facility system 102 .
- facility server 130 may include one or more distributed computer systems capable of performing distributed computing functions, cloud computing services and functions, and interface-related functions consistent with disclosed embodiments.
- facility server 130 may operate in conjunction with network server 130 .
- network server 160 may operate alone, and facility server 130 may be replaced by a network connection to network 150 and/or local network 110 .
- network server 160 may perform all functions associated with the disclosed methods.
- facility server 130 may operate alone, without network server 160 .
- facility system 102 may operate as a standalone system, in which facility server 130 performs all functions associated with the disclosed methods.
- facility server 130 performs all functions associated with the disclosed methods.
- facility server 130 may connect to multiple facilities located in different geographical locations.
- facility server 160 may collect data from multiple facilities to evaluate performance times in different facilities, improve the accuracy of expected completion times for different types of tasks using one or more statistical/data regression algorithms, and predict future utilization of one or more of the facilities.
- server 102 may include one or more processor(s) 420 , one or more memories storing programs 440 (including, for example, a real-time data processing module 442 , a historical data processing module 444 , a context determination module 446 , and/or a prediction module 448 ), data 450 , and an internal database 460 .
- Program 440 including, for example, a real-time data processing module 442 , a historical data processing module 444 , a context determination module 446 , and/or a prediction module 448 ), data 450 , and an internal database 460 .
- Server 102 may be a single server or may be configured as a distributed computer system including multiple servers or computers that interoperate to perform one or more of the processes and functionalities associated with the disclosed embodiments.
- Processor(s) 420 may be one or more known computing devices, such as those described with respect to processor 220 in FIG. 2 .
- server 102 may include one or more storage devices configured to store information used by processor 420 (or other components) to perform certain functions related to the disclosed embodiments.
- server 102 may include memory 430 that includes instructions to enable processor 420 to perform operations by executing one or more applications, such as server applications, an electronic transaction application, an account status application, network communication processes, and any other type of application or software known to be available on computer systems.
- the instructions, application programs, etc. may be stored in internal database 460 or external database 108 (shown in FIG. 1 ) in communication with server 102 , such as one or more databases or memories accessible over network 110 .
- Database 460 or external storage may be a volatile or non-volatile, magnetic, semiconductor, tape, optical, removable, non-removable, or other type of storage device or tangible (i.e., non-transitory) computer-readable medium.
- server 102 may include memory 430 that includes instructions that, when executed by processor 420 , perform one or more processes consistent with the functionalities disclosed herein. Methods, systems, and articles of manufacture consistent with disclosed embodiments are not limited to separate programs or computers configured to perform dedicated tasks.
- server 102 may include memory 430 that may include one or more programs 440 to perform one or more functions of the disclosed embodiments.
- processor 420 may execute one or more programs located remotely from system 100 .
- server 102 may access one or more remote programs, that, when executed, perform functions related to disclosed embodiments.
- Programs 440 stored in memory 430 and executed by processor(s) 420 may include one or more of a real-time data processing module 442 , a historical data processing module 444 , a context determination module 446 , and a prediction module 448 .
- Real-time data processing module 442 may gather, analyze, and transmit data collected in real-time during a customer service request.
- Real-time data may include (IVR) data or a natural language translation of a customer telephone interaction with a customer service representative.
- Real-time data may also include text input, via a customer service interface or web chat, from the customer and/or customer service agent.
- Real-time data may include data such as a category of the customer service request (e.g., troubleshooting, account information, other inquiries, etc.), a customer account number, and/or data directly input by the representative via a customer service interface.
- Historical data processing module 444 may gather, analyze, and/or transmit historical data stored on database 108 .
- Historical data may refer to data associated with a particular customer or account of the customer making the request, or may refer to global customer service data. Historical data may include statistical data on customer service requests and request outcomes (e.g., if a similar request was resolved and how the request was resolved). For example, historical data may include a ranking, input by a customer via an interface, indicating to what degree a customer service representative successfully resolved the customer's customer service request. Historical data may also include data collected for a specific customer indicating the customer's past account actions or activities (e.g., web site sign-on's, withdrawals, deposits, transfers, etc.). In some embodiments, historical data may refer to data from one or more customers or a subset of customers. In some embodiments, historical data may refer to data from one specific customer.
- Context determination module 446 may receive data from the real-time data processing module 442 and the historical data processing module 444 .
- the context determination module 446 may use data to determine the context of a customer service request. For example, if a customer calls an entity's customer service helpline and navigates through an automated menu by selecting a help category such as “Website Troubleshooting,” IVR or keypad data received from the customer to make the selection may be received by the context determination module 446 from the real-time data processing module 442 .
- Context determination module 446 may use this data along with speech-to-text data from the customer's telephone conversation with the representative to identify one or more keywords associated with the customer's problem or request.
- Context determination module 446 may compile a list of keywords or phrases describing the problem presented by the customer.
- the context determination module 446 may also use historical data, such as prior account activity by the customer or previous, similar customer requests that have been successfully resolved.
- Prediction module 448 may receive data indicating the context of a customer service request from the context determination module 446 . Based on the received context data, historical data, and real-time data, the prediction module 448 may generate a prediction, in real-time, of how to resolve the customer service request. Prediction module 448 may use the keywords or phrases generated by the context module 446 to query a database (e.g., database 108 or 460 ) for problems and resolutions and/or reference materials associated with the generated context. For example, if the context is determined to be a technical problem with a mobile application, the prediction module 448 may generate a list of resources for troubleshooting the application.
- a database e.g., database 108 or 460
- This list may be displayed to a customer using an ATM or kiosk, may be displayed to a customer via a graphical user interface on a customer device 104 , or may be displayed via graphical user interface on a representative device 106 to a representative assisting a customer via telephone or web chat.
- prediction module 448 may predict future servicing needs of the customer based on the determined context and customer account activity. For example, the context determination module 446 may determine that a customer has attempted to transfer funds between accounts and visited the website help page. In this example, prediction module 448 may generate a prediction that the customer is having trouble completing a balance transfer and identify appropriate resources to assist the customer service representative in troubleshooting the issue with the customer. Prediction module 448 may also predict sales opportunities. For example, if the customer consistently pays off the balance of a credit card with a low limit, prediction module 448 may identify credit cards with higher limits or rewards programs to offer to the customer.
- memory 430 may store data 450 including data associated with customer service resources, common customer service requests, historical data, data derived from historical data such as trends, patterns, and correlative relationships.
- memory 430 and database 460 may include one or more memory devices that store data and instructions used to perform one or more features of the disclosed embodiments.
- Memory 430 and database 460 may also include any combination of one or more databases controlled by memory controller devices (e.g., server(s), etc.) or software, such as document management systems, Microsoft SQL databases, SharePoint databases, OracleTM databases, SybaseTM databases, or other relational databases.
- FIG. 5 is a flowchart of an exemplary prediction process 500 .
- prediction process 500 may generate and display resources for resolving a customer service request.
- prediction process 500 may produce one or more graphical user interfaces or other resources for guiding a customer service representative during a sales call, to offer one or more relevant products to a customer based on the customer's historical data.
- Process 500 is discussed below as being performed by a server, e.g., server 102 .
- data associated with a customer service request may be received from a customer during a communication with a customer service representative, e.g., a web chat and/or telephone call.
- a customer service request may be received via a user interface on a mobile application, at a kiosk, and/or at an ATM.
- Data associated with the request may include one or more of audio data, text data, interactive voice response data, and the like.
- the system 100 may receive IVR data, data input in real-time by a customer service agent indicating the nature of the request, or real-time audio data received via a customer's telephone conversation with a customer service agent.
- Real-time data may also include data received via a user interface.
- the system may determine an identity of the customer.
- the identity of the customer may, for example, be an account number, name, security code, or the like, associating the customer to an existing account.
- the system may use the identity to request historical data from one or more databases. The system may determine the identity of the customer based on, for example, the parsed audio or text data received during the customer service interaction.
- system 100 may analyze the data associated with the customer initiating the customer service request.
- system 100 may receive raw data from one or more networked sources, and clean and/or normalize the data.
- audio data may be received and transcribed, e.g., using NLP or other known audio data processing techniques to generate textual data from received audio data.
- the system may use an algorithm, natural language processing (NLP) software, or other method known to one of skill in the art to parse the data and to determine, for example, one or more features of the data.
- NLP natural language processing
- Features may include, for example, call duration, common customer inquiries, keywords received as part of the request, and the like.
- the system may analyze audio data using NLP and identifying keywords such as, for example, “transfer,” “international,” and/or “website.”
- a context of the customer service request may be determined, for example, by context determination module 446 , based on the analyzed data and/or on historical data collected prior to the customer service request.
- real-time data may include the selection of an “Account Help” option by a customer via an automated telephone menu, and historical data for the customer may indicate that the customer has tried to log-in to a mobile application unsuccessfully during the past 24 hours.
- the context may be determined to be “Account Log-in Help.”
- System 100 may use one or more of a machine learning process or neural network to determine a context. For example, classification techniques may be used to classify one or more characteristics associated with the context.
- At least one context may be identified using a neural network trained, using a machine learning system, using a pattern recognition system, and so forth.
- the system 100 may also have a machine analysis algorithm incorporated such that a library of known contexts may be updated each time a customer contacts a customer service representative.
- a person of ordinary skill in the art will recognize other methods for identifying one or more contexts based on received data that remain consistent with the present disclosure.
- system 100 may determine a context using word recognition to identify words and/or phrases associated with one or more contexts.
- system 100 may pass one or more audio transcriptions to a neural network to identify one or more contexts.
- a neural network may determine a probability of a context based on received input data, and/or may determine a proximity of the context.
- a convolutional neural network may receive audio data to determine customer tone. Customer tone may be used to identify resources to display to the customer service, such as de-escalation techniques, sales offers, and/or a prompt to contact a senior representative or manager.
- the system may combine information received as audio input with historical account information.
- a customer request received over the telephone may include the phase “transfer.” If system 100 determines that historical customer data indicates that the customer recently set up a new account, system 100 may determine the context to be that the customer wishes to transfer funds to the new account. Historical data may indicate that the customer has previously made several transfers to another customer's account, and thus, the combination of audio and historical data may indicate that the context is that the customer is attempting to transfer funds to another person's account.
- the prediction module 448 may identify resources in a database associated with the context of the customer service request.
- resources may include a guide detailing how the customer may reset their password or steps to take to authenticate the customer if an unauthorized user is attempting to access the account.
- the prediction may be based on resources that have yielded resolutions for customers with similar request based on the generated context of the request.
- Resources may be retrieved from a remote database or cloud system. In some embodiments, the types of retrieved resources may depend on the type of customer service request detected. For example, if a request is received via a kiosk, the resource may include displayed instructions targeted toward a customer. In another example, if the request is received via telephone, e.g., from a customer directly interacting with a customer service agent, the resources may be internal documents targeted towards a customer service representative.
- prediction module 448 may identify one or more resources based on results of previous customer interactions. In some embodiments, results of previous interactions may be calculated based on an individual customer. In other embodiments, predictions may be made based on customer data aggregated based on one or more customer characteristics, e.g., demographic information, account balance, late payment history, number of financial services used, etc. Predicted resources may include, for example, information about an incentive program or white glove treatment. For example, if a customer's historical data correlates to a future context of closing an account, a predicted resource may be one or more incentive programs. In some embodiments, incentive programs may be ranked based on the probability of a positive outcome, e.g., how likely it is that the incentive will prevent the customer from closing the account.
- the resources identified by prediction module 448 may be displayed to the customer or customer service representative via a user interface.
- the resources are displayed on a customer device 104 such as, for example, a mobile device, kiosk, ATM, or computing device.
- the resources may be displayed to a customer service representative, via a user interface, in real-time during a customer service communication.
- FIG. 6 is an exemplary customer service portal 600 .
- Customer service portal 600 may be accessed by a customer service representative in real-time on a device, e.g., representative device 106 , connected to network 110 .
- Customer service portal 600 may display information including the customer service representative name 602 , the customer name and account number 604 , and recent customer activity 606 .
- Customer service portal 600 may also display previous customer service requests 608 from the same customer.
- customer service portal 600 may display predicted solutions 610 and useful resources 612 based on the output from prediction module 448 . Predicted solutions may include steps to take to resolve the customer request or contact information of representatives able to solve the customer's request.
- Useful resources may include customer service representative training materials, troubleshooting guides, and/or specific product information.
- Information displayed on customer service portal 600 may better help the customer service representative to assist the customer by providing links to resources or guides that the representative may be unfamiliar with or may have forgotten since training.
- Customer service portal 600 may update in real-time with predicted solutions as
- FIG. 7 is an exemplary customer interface 700 .
- Customer interface 700 may be displayed on a mobile device, kiosk, or ATM. Customer interface 700 may require a customer to sign into their account by providing details such as a password, personal identification number, or credit/debit card. Customer interface 700 may display the customer name and account number 702 associated with the customer. Customer interface 700 may display a prompt 704 , based on detected customer activity via an app, website, or directly at a kiosk, asking if the customer is trying to complete a specific action, e.g., make a transfer, make a deposit, check an account balance, etc. Customer interface 700 may also display a help button 706 to connect the customer with a customer service representative or to receive further input from the customer regarding their request.
- a prompt 704 based on detected customer activity via an app, website, or directly at a kiosk, asking if the customer is trying to complete a specific action, e.g., make a transfer, make a deposit, check an account balance, etc.
- Customer interface 700 may also
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Telephonic Communication Services (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Description
- A common pitfall of customer service is high customer service agent turnover. Training customer service agents is both expensive and time consuming, and agents may not remember all of the training materials they are exposed to, leading to longer call times and decreased customer satisfaction. Further, customer service agents may not be familiar with smaller concepts or projects at a large enterprise. The above factors may result in lower sales volume, fewer new customers, or fewer retained customers.
- In the following description, certain aspects and embodiments of the present disclosure will become evident. It should be understood that the disclosure, in its broadest sense, could be practiced without having one or more features of these aspects and embodiments. It should also be understood that these aspects and embodiments are merely exemplary.
- Disclosed embodiments include a system for providing resource material to a customer service representative (CSR). The system may include: a database storing a plurality of resources associated with a plurality of customer service contexts; one or more memories storing instructions; and one or more processors configured to execute the instructions to perform operations. The operations may include: receiving data associated with an on-going communication, the on-going communication comprising a customer service request received from a customer; analyzing the data associated with the on-going communication; determining an identity of the customer associated with the communication; determining a context of the request based on the analysis and based on historical data associated with the determined identity; automatically identifying, based on the context, a resource in the database associated with the determined context; and displaying, via a user interface in real-time during the communication, the resource associated with the customer service request.
- It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only, and are not restrictive of the disclosed embodiments, as claimed.
- The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate several embodiments and, together with the description, serve to explain the disclosed principles. In the drawings:
-
FIG. 1 depicts an example of a system environment for generating customer service prediction resources, consistent with the disclosed embodiments; -
FIG. 2 depicts an example of a customer device, consistent with the disclosed embodiments; -
FIG. 3 depicts an example of a device used by a customer service representative, consistent with the disclosed embodiments; -
FIG. 4 shows a diagram of an exemplary facility server, consistent with the disclosed embodiments; -
FIG. 5 is a flowchart of an exemplary prediction process, consistent with the disclosed embodiments; -
FIG. 6 is an exemplary customer service portal, consistent with the disclosed embodiments; and -
FIG. 7 is an exemplary customer interface, consistent with the disclosed embodiments. - Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings and disclosed herein. Wherever convenient, the same reference numbers will be used throughout the drawings to refer to the same or like parts.
- The present disclosure describes advanced technical solutions for predicting customer service requests, solutions, and resolution resources. As used herein, “customer service request” will refer to any customer inquiry or problem requiring assistance. For example, a customer service request may be troubleshooting an app or website; requesting account modifications, such as an address change, billing assistance; and the like. The prediction of a customer service solution in response to a customer service request or based on recent customer activity may result in increased customer satisfaction and retention by decreasing the time to resolve an issue or an inquiry from the customer.
- Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings and disclosed herein. Wherever convenient, the same reference numbers will be used throughout the drawings to refer to the same or like parts.
-
FIG. 1 is a diagram of acomputer system 100 that may be configured to perform one or more software processes that, when executed by one or more processors, perform methods consistent with disclosed embodiments. The components and arrangements shown inFIG. 1 are not intended to limit the disclosed embodiments, as the components used to implement the disclosed processes and features may vary. - As shown in
FIG. 1 ,system 100 may include aserver 102, a customer device 104, arepresentative device 106, and adatabase 108. The components ofsystem 100 may communicate directly, throughnetwork 110. Other components known to one of ordinary skill in the art may be included insystem 100 to perform tasks consistent with the disclosed embodiments. -
Server 102 may enable communication within external computer-based systems including computer system components such as desktop computers, workstations, tablets, hand held computing devices, memory devices, and/or internal network(s) connecting the components. - Customer device 104 may be a personal computing device such as, for example, a general purpose or notebook computer, a mobile device with computing ability, a tablet, a smartphone, a wearable device, or smart watch, or any combination of these computers and/or affiliated components. In some embodiments, customer device 104 may be a computer system or mobile computer device that is operated by the customer. In some embodiments, customer device 104 may be a kiosk or automated teller machine (ATM). In some embodiments, customer device 104 may be a landline telephone or device capable of receiving audio commands or commands via the telephone or device keypad.
- In some embodiments,
representative device 106 may be a device that is operated by a customer service specialist, representative, or other employee of a business entity.Representative device 106 may be a personal computing device such as, for example, a general purpose or notebook computer, a mobile device with computing ability, a tablet, smartphone, a wearable device, or smart watch, or any combination of these computers and/or affiliated components. In some embodiments,representative device 106 may be a landline telephone or device capable of receiving audio commands or commands via the telephone or device keypad. - Network 110 may comprise any type of computer networking arrangement used to exchange data. For example,
network 110 may be the Internet, a private data network, virtual private network using a public network, and/or other suitable connection(s) that enablessystem 100 to send and receive information between the components ofsystem 100. Network 110 may also include a public switched telephone network (“PSTN”) and/or a wireless cellular network. -
FIG. 2 is a diagram of arepresentative device 106, consistent with disclosed embodiments. As shown,representative device 106 may include adisplay 210, one ormore processors 220, one or more input/output (“I/O”)devices 230, atransceiver 240 memory 250, and battery 270. -
Display 210 may include one or more screens such as, for example, liquid crystal display (LCD), plasma, cathode ray tube (CRT), or projected screens. Display may display information such as customer service resources, customer data, and solution information. -
Processor 220 may be one or more known processing devices, such as microprocessors manufactured by Intel™ or AMD™ or licensed by ARM.Processor 220 may constitute a single-core or multiple-core processor that executes parallel processes simultaneously. For example,processor 220 may be a single-core processor configured with virtual processing technologies. In certain embodiments,processor 220 may use logical processors to simultaneously execute and control multiple processes.Processor 220 may implement virtual machine technologies, or other known technologies to provide the ability to execute, control, run, manipulate, store, etc. multiple software processes, applications, programs, etc. In another embodiment,processor 220 may include a multiple-core processor arrangement (e.g., dual, quad core, etc.) configured to provide parallel processing functionalities to allowrepresentative device 106 to execute multiple processes simultaneously. One of ordinary skill in the art would understand that other types of processor arrangements could be implemented that provide for the capabilities disclosed herein. - I/
O devices 230 may include one or more devices that allowrepresentative device 106 to receive input from a customer service representative or other user. I/O devices 230 may include, for example, one or more pointing devices, keyboards, buttons, switches, touchscreen panels, cameras, barcode scanners, radio frequency identification (RFID) tag reader, and/or microphones. -
Memory 240 may include a volatile or non-volatile, magnetic, semiconductor, solid-state, tape, optical, removable, non-removable, or other type of storage device or tangible (i.e., non-transitory) computer-readable medium that stores one or more program(s) 242, such as app(s) 244, anddata 246.Data 246 may include, for example, customer account information, recent customer activity, predicted customer service solutions, and/or relevant customer service resources. - Program(s) 242 may include operating systems (not shown) that perform known operating system functions when executed by one or more processors. By way of example, the operating systems may include Microsoft Windows™, Unix™, Linux™ Android™ and Apple™ operating systems, Personal Digital Assistant (PDA) type operating systems, such as Microsoft CE™, or other types of operating systems. Accordingly, disclosed embodiments may operate and function with computer systems running any type of operating system.
Representative device 106 may also include communication software that, when executed by a processor, provides communications withnetwork 110, such as Web browser software, tablet, or smart hand held device networking software, etc. - Program(s) 242 may also include app(s) 244, such as an interactive voice response (IVR) and/or touch-tone data entry (TDE) program which, when executed, gather initial information from a customer about a customer service request. For example, a customer making a customer service request via land-line telephone may be prompted to navigate through an automated menu and to provide details such as the nature of their request and/or their account number by speaking into the telephone or through by various numbers on the keypad.
-
FIG. 3 shows a diagram of an exemplary customer device 104, consistent with disclosed embodiments. As shown, customer device 104 may include adisplay 310, I/O device(s) 320, aprocessor 330, amemory 340 having stored thereondata 346 and one ormore programs 342, such as app(s) 344 (e.g., a financial services app), and anantenna 350. -
Display 310 may include one or more devices for displaying information, including but not limited to, liquid crystal displays (LCD), light emitting diode (LED) screens, organic light emitting diode (OLED) screens, and other known display devices. - I/
O devices 320 may include one or more devices that allow customer device 104 to send and receive information. I/O devices 320 may include, for example, a pointing device, keyboard, buttons, switches, microphones, and/or a touchscreen panel. I/O devices 320 may also include one or more communication modules (not shown) for sending and receiving information from other components insystem 100 by, for example, establishing wired or wireless connectivity (via antenna 350) between customer device 104 tonetwork 110, or by establishing direct wired or wireless connections between customer device 104 and other components ofsystem 100. Direct connections may include, for example, Bluetooth™, Bluetooth LE™, WiFi, near field communications (NFC), or other known communication methods which provide a medium for transmitting data between separate devices. - Processor(s) 330 may be one or more known computing devices, such as those described with respect to
processor 220 inFIG. 2 . -
Memory 340 may be a volatile or non-volatile, magnetic, semiconductor, tape, optical, removable, non-removable, or other type of storage device or tangible (i.e., non-transitory) computer-readable medium such as those described with respect tomemory 240 inFIG. 2 . -
FIG. 4 shows a diagram of an exemplary facility server 130, consistent with disclosed embodiments. In some embodiments, facility server 130 may be a local server withinfacility system 102. In such embodiments, facility server 130 may include one or more distributed computer systems capable of performing distributed computing functions, cloud computing services and functions, and interface-related functions consistent with disclosed embodiments. In some embodiments, facility server 130 may operate in conjunction with network server 130. In other embodiments, network server 160 may operate alone, and facility server 130 may be replaced by a network connection to network 150 and/orlocal network 110. In such embodiments, network server 160 may perform all functions associated with the disclosed methods. In other embodiments, facility server 130 may operate alone, without network server 160. In such embodiments,facility system 102 may operate as a standalone system, in which facility server 130 performs all functions associated with the disclosed methods. Those of ordinary skill in the art will appreciate that the computing arrangements are not limited to these examples, and that other embodiments may include one or more alternate configurations of computing systems capable of performing functions associated with the disclosed embodiments. - In some embodiments, facility server 130 may connect to multiple facilities located in different geographical locations. In such embodiments, facility server 160 may collect data from multiple facilities to evaluate performance times in different facilities, improve the accuracy of expected completion times for different types of tasks using one or more statistical/data regression algorithms, and predict future utilization of one or more of the facilities.
- As shown in
FIG. 4 ,server 102 may include one or more processor(s) 420, one or more memories storing programs 440 (including, for example, a real-timedata processing module 442, a historicaldata processing module 444, a context determination module 446, and/or a prediction module 448),data 450, and aninternal database 460.Server 102 may be a single server or may be configured as a distributed computer system including multiple servers or computers that interoperate to perform one or more of the processes and functionalities associated with the disclosed embodiments. - Processor(s) 420 may be one or more known computing devices, such as those described with respect to
processor 220 inFIG. 2 . - In some embodiments,
server 102 may include one or more storage devices configured to store information used by processor 420 (or other components) to perform certain functions related to the disclosed embodiments. In one example,server 102 may includememory 430 that includes instructions to enableprocessor 420 to perform operations by executing one or more applications, such as server applications, an electronic transaction application, an account status application, network communication processes, and any other type of application or software known to be available on computer systems. Alternatively or additionally, the instructions, application programs, etc. may be stored ininternal database 460 or external database 108 (shown inFIG. 1 ) in communication withserver 102, such as one or more databases or memories accessible overnetwork 110.Database 460 or external storage may be a volatile or non-volatile, magnetic, semiconductor, tape, optical, removable, non-removable, or other type of storage device or tangible (i.e., non-transitory) computer-readable medium. - In one embodiment,
server 102 may includememory 430 that includes instructions that, when executed byprocessor 420, perform one or more processes consistent with the functionalities disclosed herein. Methods, systems, and articles of manufacture consistent with disclosed embodiments are not limited to separate programs or computers configured to perform dedicated tasks. For example,server 102 may includememory 430 that may include one or more programs 440 to perform one or more functions of the disclosed embodiments. Moreover,processor 420 may execute one or more programs located remotely fromsystem 100. For example,server 102 may access one or more remote programs, that, when executed, perform functions related to disclosed embodiments. - Programs 440 stored in
memory 430 and executed by processor(s) 420 may include one or more of a real-timedata processing module 442, a historicaldata processing module 444, a context determination module 446, and aprediction module 448. Real-timedata processing module 442 may gather, analyze, and transmit data collected in real-time during a customer service request. Real-time data may include (IVR) data or a natural language translation of a customer telephone interaction with a customer service representative. Real-time data may also include text input, via a customer service interface or web chat, from the customer and/or customer service agent. Real-time data may include data such as a category of the customer service request (e.g., troubleshooting, account information, other inquiries, etc.), a customer account number, and/or data directly input by the representative via a customer service interface. - Historical
data processing module 444 may gather, analyze, and/or transmit historical data stored ondatabase 108. Historical data may refer to data associated with a particular customer or account of the customer making the request, or may refer to global customer service data. Historical data may include statistical data on customer service requests and request outcomes (e.g., if a similar request was resolved and how the request was resolved). For example, historical data may include a ranking, input by a customer via an interface, indicating to what degree a customer service representative successfully resolved the customer's customer service request. Historical data may also include data collected for a specific customer indicating the customer's past account actions or activities (e.g., web site sign-on's, withdrawals, deposits, transfers, etc.). In some embodiments, historical data may refer to data from one or more customers or a subset of customers. In some embodiments, historical data may refer to data from one specific customer. - Context determination module 446 may receive data from the real-time
data processing module 442 and the historicaldata processing module 444. The context determination module 446 may use data to determine the context of a customer service request. For example, if a customer calls an entity's customer service helpline and navigates through an automated menu by selecting a help category such as “Website Troubleshooting,” IVR or keypad data received from the customer to make the selection may be received by the context determination module 446 from the real-timedata processing module 442. Context determination module 446 may use this data along with speech-to-text data from the customer's telephone conversation with the representative to identify one or more keywords associated with the customer's problem or request. Context determination module 446 may compile a list of keywords or phrases describing the problem presented by the customer. The context determination module 446 may also use historical data, such as prior account activity by the customer or previous, similar customer requests that have been successfully resolved. -
Prediction module 448 may receive data indicating the context of a customer service request from the context determination module 446. Based on the received context data, historical data, and real-time data, theprediction module 448 may generate a prediction, in real-time, of how to resolve the customer service request.Prediction module 448 may use the keywords or phrases generated by the context module 446 to query a database (e.g.,database 108 or 460) for problems and resolutions and/or reference materials associated with the generated context. For example, if the context is determined to be a technical problem with a mobile application, theprediction module 448 may generate a list of resources for troubleshooting the application. This list may be displayed to a customer using an ATM or kiosk, may be displayed to a customer via a graphical user interface on a customer device 104, or may be displayed via graphical user interface on arepresentative device 106 to a representative assisting a customer via telephone or web chat. - In some embodiments,
prediction module 448 may predict future servicing needs of the customer based on the determined context and customer account activity. For example, the context determination module 446 may determine that a customer has attempted to transfer funds between accounts and visited the website help page. In this example,prediction module 448 may generate a prediction that the customer is having trouble completing a balance transfer and identify appropriate resources to assist the customer service representative in troubleshooting the issue with the customer.Prediction module 448 may also predict sales opportunities. For example, if the customer consistently pays off the balance of a credit card with a low limit,prediction module 448 may identify credit cards with higher limits or rewards programs to offer to the customer. - In some embodiments,
memory 430 may storedata 450 including data associated with customer service resources, common customer service requests, historical data, data derived from historical data such as trends, patterns, and correlative relationships. - In some embodiments,
memory 430 anddatabase 460 may include one or more memory devices that store data and instructions used to perform one or more features of the disclosed embodiments.Memory 430 anddatabase 460 may also include any combination of one or more databases controlled by memory controller devices (e.g., server(s), etc.) or software, such as document management systems, Microsoft SQL databases, SharePoint databases, Oracle™ databases, Sybase™ databases, or other relational databases. -
FIG. 5 is a flowchart of anexemplary prediction process 500. In some embodiments,prediction process 500 may generate and display resources for resolving a customer service request. In another embodiment,prediction process 500 may produce one or more graphical user interfaces or other resources for guiding a customer service representative during a sales call, to offer one or more relevant products to a customer based on the customer's historical data.Process 500 is discussed below as being performed by a server, e.g.,server 102. - In
step 502, data associated with a customer service request may be received from a customer during a communication with a customer service representative, e.g., a web chat and/or telephone call. In some embodiments, a customer service request may be received via a user interface on a mobile application, at a kiosk, and/or at an ATM. Data associated with the request may include one or more of audio data, text data, interactive voice response data, and the like. For example, thesystem 100 may receive IVR data, data input in real-time by a customer service agent indicating the nature of the request, or real-time audio data received via a customer's telephone conversation with a customer service agent. Real-time data may also include data received via a user interface. - In some embodiments, for example, if the customer service interaction occurs via telephone, at
step 503, the system may determine an identity of the customer. The identity of the customer may, for example, be an account number, name, security code, or the like, associating the customer to an existing account. In some embodiments, the system may use the identity to request historical data from one or more databases. The system may determine the identity of the customer based on, for example, the parsed audio or text data received during the customer service interaction. - In
step 504,system 100 may analyze the data associated with the customer initiating the customer service request. In some embodiments,system 100 may receive raw data from one or more networked sources, and clean and/or normalize the data. In some embodiments, audio data may be received and transcribed, e.g., using NLP or other known audio data processing techniques to generate textual data from received audio data. - In some embodiments, for example, the system may use an algorithm, natural language processing (NLP) software, or other method known to one of skill in the art to parse the data and to determine, for example, one or more features of the data. Features may include, for example, call duration, common customer inquiries, keywords received as part of the request, and the like. For example, the system may analyze audio data using NLP and identifying keywords such as, for example, “transfer,” “international,” and/or “website.”
- In
step 506, a context of the customer service request may be determined, for example, by context determination module 446, based on the analyzed data and/or on historical data collected prior to the customer service request. For example, real-time data may include the selection of an “Account Help” option by a customer via an automated telephone menu, and historical data for the customer may indicate that the customer has tried to log-in to a mobile application unsuccessfully during the past 24 hours. In this scenario, the context may be determined to be “Account Log-in Help.”System 100 may use one or more of a machine learning process or neural network to determine a context. For example, classification techniques may be used to classify one or more characteristics associated with the context. In some embodiments, at least one context may be identified using a neural network trained, using a machine learning system, using a pattern recognition system, and so forth. Thesystem 100 may also have a machine analysis algorithm incorporated such that a library of known contexts may be updated each time a customer contacts a customer service representative. A person of ordinary skill in the art will recognize other methods for identifying one or more contexts based on received data that remain consistent with the present disclosure. - In some embodiments,
system 100 may determine a context using word recognition to identify words and/or phrases associated with one or more contexts. In another embodiment,system 100 may pass one or more audio transcriptions to a neural network to identify one or more contexts. In addition, a neural network may determine a probability of a context based on received input data, and/or may determine a proximity of the context. In another embodiment, a convolutional neural network may receive audio data to determine customer tone. Customer tone may be used to identify resources to display to the customer service, such as de-escalation techniques, sales offers, and/or a prompt to contact a senior representative or manager. The system may combine information received as audio input with historical account information. For example, a customer request received over the telephone may include the phase “transfer.” Ifsystem 100 determines that historical customer data indicates that the customer recently set up a new account,system 100 may determine the context to be that the customer wishes to transfer funds to the new account. Historical data may indicate that the customer has previously made several transfers to another customer's account, and thus, the combination of audio and historical data may indicate that the context is that the customer is attempting to transfer funds to another person's account. - In
step 508, theprediction module 448 may identify resources in a database associated with the context of the customer service request. For example, resources may include a guide detailing how the customer may reset their password or steps to take to authenticate the customer if an unauthorized user is attempting to access the account. The prediction may be based on resources that have yielded resolutions for customers with similar request based on the generated context of the request. Resources may be retrieved from a remote database or cloud system. In some embodiments, the types of retrieved resources may depend on the type of customer service request detected. For example, if a request is received via a kiosk, the resource may include displayed instructions targeted toward a customer. In another example, if the request is received via telephone, e.g., from a customer directly interacting with a customer service agent, the resources may be internal documents targeted towards a customer service representative. - In some embodiments,
prediction module 448 may identify one or more resources based on results of previous customer interactions. In some embodiments, results of previous interactions may be calculated based on an individual customer. In other embodiments, predictions may be made based on customer data aggregated based on one or more customer characteristics, e.g., demographic information, account balance, late payment history, number of financial services used, etc. Predicted resources may include, for example, information about an incentive program or white glove treatment. For example, if a customer's historical data correlates to a future context of closing an account, a predicted resource may be one or more incentive programs. In some embodiments, incentive programs may be ranked based on the probability of a positive outcome, e.g., how likely it is that the incentive will prevent the customer from closing the account. - In
step 510, the resources identified byprediction module 448 may be displayed to the customer or customer service representative via a user interface. In some embodiments, the resources are displayed on a customer device 104 such as, for example, a mobile device, kiosk, ATM, or computing device. In some embodiments, the resources may be displayed to a customer service representative, via a user interface, in real-time during a customer service communication. -
FIG. 6 is an exemplarycustomer service portal 600.Customer service portal 600 may be accessed by a customer service representative in real-time on a device, e.g.,representative device 106, connected tonetwork 110.Customer service portal 600 may display information including the customer servicerepresentative name 602, the customer name andaccount number 604, andrecent customer activity 606.Customer service portal 600 may also display previous customer service requests 608 from the same customer. In some embodiments,customer service portal 600 may display predictedsolutions 610 anduseful resources 612 based on the output fromprediction module 448. Predicted solutions may include steps to take to resolve the customer request or contact information of representatives able to solve the customer's request. Useful resources may include customer service representative training materials, troubleshooting guides, and/or specific product information. Information displayed oncustomer service portal 600 may better help the customer service representative to assist the customer by providing links to resources or guides that the representative may be unfamiliar with or may have forgotten since training.Customer service portal 600 may update in real-time with predicted solutions as more data is received from the customer or representative. -
FIG. 7 is anexemplary customer interface 700.Customer interface 700 may be displayed on a mobile device, kiosk, or ATM.Customer interface 700 may require a customer to sign into their account by providing details such as a password, personal identification number, or credit/debit card.Customer interface 700 may display the customer name andaccount number 702 associated with the customer.Customer interface 700 may display a prompt 704, based on detected customer activity via an app, website, or directly at a kiosk, asking if the customer is trying to complete a specific action, e.g., make a transfer, make a deposit, check an account balance, etc.Customer interface 700 may also display ahelp button 706 to connect the customer with a customer service representative or to receive further input from the customer regarding their request. - While illustrative embodiments have been described herein, the scope thereof includes any and all embodiments having equivalent elements, modifications, omissions, combinations (e.g., of aspects across various embodiments), adaptations and/or alterations as would be appreciated by those in the art based on the present disclosure. For example, the number and orientation of components shown in the exemplary systems may be modified. Further, with respect to the exemplary methods illustrated in the attached drawings, the order and sequence of operations may be modified, and operations may be added or deleted. For example, in some embodiments, some of the steps may be performed as parallel operations. Other modifications are also contemplated.
- Thus, the foregoing description has been presented for purposes of illustration. It is not exhaustive and is not limiting to the precise forms or embodiments disclosed. Modifications and adaptations will be apparent to those skilled in the art from consideration of the specification and practice of the disclosed embodiments.
- The claims are to be interpreted broadly based on the language used in the claims and not limited to examples described in the present specification, which are non-exclusive. For example, aspects of the disclosed embodiments are described as being associated with data stored in memory, and one skilled in the art will appreciate that these aspects can be stored on and executed from many types of tangible computer-readable media, such as secondary storage devices, like hard disks, floppy disks, or CD-ROM, or other forms of RAM or ROM. Accordingly, the disclosed embodiments are not limited to the above described examples, but instead are defined by the appended claims in light of their full scope of equivalents.
Claims (19)
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US16/112,625 US20200065825A1 (en) | 2018-08-24 | 2018-08-24 | Systems and methods for customer service prediction |
US17/964,683 US11810128B2 (en) | 2018-08-24 | 2022-10-12 | Systems and methods for customer service prediction |
US18/454,750 US20230394491A1 (en) | 2018-08-24 | 2023-08-23 | Systems and methods for customer service prediction |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US16/112,625 US20200065825A1 (en) | 2018-08-24 | 2018-08-24 | Systems and methods for customer service prediction |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US17/964,683 Continuation US11810128B2 (en) | 2018-08-24 | 2022-10-12 | Systems and methods for customer service prediction |
Publications (1)
Publication Number | Publication Date |
---|---|
US20200065825A1 true US20200065825A1 (en) | 2020-02-27 |
Family
ID=69586222
Family Applications (3)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/112,625 Abandoned US20200065825A1 (en) | 2018-08-24 | 2018-08-24 | Systems and methods for customer service prediction |
US17/964,683 Active US11810128B2 (en) | 2018-08-24 | 2022-10-12 | Systems and methods for customer service prediction |
US18/454,750 Pending US20230394491A1 (en) | 2018-08-24 | 2023-08-23 | Systems and methods for customer service prediction |
Family Applications After (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US17/964,683 Active US11810128B2 (en) | 2018-08-24 | 2022-10-12 | Systems and methods for customer service prediction |
US18/454,750 Pending US20230394491A1 (en) | 2018-08-24 | 2023-08-23 | Systems and methods for customer service prediction |
Country Status (1)
Country | Link |
---|---|
US (3) | US20200065825A1 (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20200104858A1 (en) * | 2018-09-28 | 2020-04-02 | Element Ai Inc. | Method and system for proactively increasing customer satisfaction |
US10839335B2 (en) | 2018-12-13 | 2020-11-17 | Nice Ltd. | Call center agent performance scoring and sentiment analytics |
US11005995B2 (en) * | 2018-12-13 | 2021-05-11 | Nice Ltd. | System and method for performing agent behavioral analytics |
US11165900B2 (en) * | 2019-10-25 | 2021-11-02 | Uniphore Technologies Inc. | Automated real-time call summarization |
US20220103510A1 (en) * | 2019-10-30 | 2022-03-31 | Liveperson, Inc. | Message rerouting from an e-mail environment to a messaging environment |
US20230267475A1 (en) * | 2022-02-24 | 2023-08-24 | The Toronto-Dominion Bank | Systems and methods for automated context-aware solutions using a machine learning model |
US11789595B1 (en) * | 2020-06-29 | 2023-10-17 | United Services Automobile Association (Usaa) | Integrated smart graphical user interface for customer management systems |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20230015321A1 (en) * | 2021-07-09 | 2023-01-19 | Flipkart Internet Private Limited | System and method for generating a response to a user query |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6965868B1 (en) * | 1999-08-03 | 2005-11-15 | Michael David Bednarek | System and method for promoting commerce, including sales agent assisted commerce, in a networked economy |
US20090028183A1 (en) * | 2007-06-07 | 2009-01-29 | Landers William P | Platform for communicating across multiple communication channels |
US20090192838A1 (en) * | 2008-01-25 | 2009-07-30 | At&T Labs | System and method for optimizing response handling time and customer satisfaction scores |
US20100076816A1 (en) * | 2008-09-25 | 2010-03-25 | Michael Phillips | Dynamic interactive survey system and method |
US20100114654A1 (en) * | 2008-10-31 | 2010-05-06 | Hewlett-Packard Development Company, L.P. | Learning user purchase intent from user-centric data |
US20130293363A1 (en) * | 2012-05-02 | 2013-11-07 | Jpmorgan Chase Bank, N.A. | Alert Optimization System and Method |
US20140025379A1 (en) * | 2012-07-20 | 2014-01-23 | Interactive Intelligence, Inc. | Method and System for Real-Time Keyword Spotting for Speech Analytics |
US20140055880A1 (en) * | 2011-09-30 | 2014-02-27 | Oracle International Corporation | Data adapters for storage tape analytics system |
US20140067391A1 (en) * | 2012-08-30 | 2014-03-06 | Interactive Intelligence, Inc. | Method and System for Predicting Speech Recognition Performance Using Accuracy Scores |
US20140143157A1 (en) * | 2012-11-21 | 2014-05-22 | Verint Americas Inc. | Design and Analysis of Customer Feedback Surveys |
US20150262069A1 (en) * | 2014-03-11 | 2015-09-17 | Delvv, Inc. | Automatic topic and interest based content recommendation system for mobile devices |
US9858340B1 (en) * | 2016-04-11 | 2018-01-02 | Digital Reasoning Systems, Inc. | Systems and methods for queryable graph representations of videos |
US20180288453A1 (en) * | 2017-04-04 | 2018-10-04 | Verizon Patent And Licensing Inc. | Proactively providing content for content distribution networks |
US20190272296A1 (en) * | 2018-03-02 | 2019-09-05 | Thoughtspot, Inc. | Natural Language Question Answering Systems |
Family Cites Families (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10684350B2 (en) * | 2000-06-02 | 2020-06-16 | Tracbeam Llc | Services and applications for a communications network |
US6889222B1 (en) * | 2000-12-26 | 2005-05-03 | Aspect Communications Corporation | Method and an apparatus for providing personalized service |
US6714939B2 (en) * | 2001-01-08 | 2004-03-30 | Softface, Inc. | Creation of structured data from plain text |
US20040230572A1 (en) * | 2001-06-22 | 2004-11-18 | Nosa Omoigui | System and method for semantic knowledge retrieval, management, capture, sharing, discovery, delivery and presentation |
US7372952B1 (en) * | 2002-03-07 | 2008-05-13 | Wai Wu | Telephony control system with intelligent call routing |
CN100380373C (en) * | 2002-10-29 | 2008-04-09 | 埃里·阿博 | Knowledge system method and apparatus |
US9818136B1 (en) * | 2003-02-05 | 2017-11-14 | Steven M. Hoffberg | System and method for determining contingent relevance |
US7676034B1 (en) * | 2003-03-07 | 2010-03-09 | Wai Wu | Method and system for matching entities in an auction |
US7590589B2 (en) * | 2004-09-10 | 2009-09-15 | Hoffberg Steven M | Game theoretic prioritization scheme for mobile ad hoc networks permitting hierarchal deference |
US9092802B1 (en) * | 2011-08-15 | 2015-07-28 | Ramakrishna Akella | Statistical machine learning and business process models systems and methods |
WO2013158839A1 (en) * | 2012-04-20 | 2013-10-24 | Lithium Technologies, Inc. | System and method for providing a social customer care system |
EP2657893A1 (en) * | 2012-04-26 | 2013-10-30 | Amadeus S.A.S. | System and method of categorizing and ranking travel option search results |
WO2017063092A1 (en) * | 2015-10-17 | 2017-04-20 | Rubikloud Technologies Inc. | System and method for computational analysis of the potential relevance of digital data items to key performance indicators |
CN106557582A (en) * | 2016-11-29 | 2017-04-05 | 宁波亿拍客网络科技有限公司 | A kind of specific markers and application method that identification can be perceived based on computer vision |
-
2018
- 2018-08-24 US US16/112,625 patent/US20200065825A1/en not_active Abandoned
-
2022
- 2022-10-12 US US17/964,683 patent/US11810128B2/en active Active
-
2023
- 2023-08-23 US US18/454,750 patent/US20230394491A1/en active Pending
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6965868B1 (en) * | 1999-08-03 | 2005-11-15 | Michael David Bednarek | System and method for promoting commerce, including sales agent assisted commerce, in a networked economy |
US20090028183A1 (en) * | 2007-06-07 | 2009-01-29 | Landers William P | Platform for communicating across multiple communication channels |
US20090192838A1 (en) * | 2008-01-25 | 2009-07-30 | At&T Labs | System and method for optimizing response handling time and customer satisfaction scores |
US20100076816A1 (en) * | 2008-09-25 | 2010-03-25 | Michael Phillips | Dynamic interactive survey system and method |
US20100114654A1 (en) * | 2008-10-31 | 2010-05-06 | Hewlett-Packard Development Company, L.P. | Learning user purchase intent from user-centric data |
US20140055880A1 (en) * | 2011-09-30 | 2014-02-27 | Oracle International Corporation | Data adapters for storage tape analytics system |
US20130293363A1 (en) * | 2012-05-02 | 2013-11-07 | Jpmorgan Chase Bank, N.A. | Alert Optimization System and Method |
US20140025379A1 (en) * | 2012-07-20 | 2014-01-23 | Interactive Intelligence, Inc. | Method and System for Real-Time Keyword Spotting for Speech Analytics |
US20140067391A1 (en) * | 2012-08-30 | 2014-03-06 | Interactive Intelligence, Inc. | Method and System for Predicting Speech Recognition Performance Using Accuracy Scores |
US20140143157A1 (en) * | 2012-11-21 | 2014-05-22 | Verint Americas Inc. | Design and Analysis of Customer Feedback Surveys |
US20150262069A1 (en) * | 2014-03-11 | 2015-09-17 | Delvv, Inc. | Automatic topic and interest based content recommendation system for mobile devices |
US9858340B1 (en) * | 2016-04-11 | 2018-01-02 | Digital Reasoning Systems, Inc. | Systems and methods for queryable graph representations of videos |
US20180288453A1 (en) * | 2017-04-04 | 2018-10-04 | Verizon Patent And Licensing Inc. | Proactively providing content for content distribution networks |
US20190272296A1 (en) * | 2018-03-02 | 2019-09-05 | Thoughtspot, Inc. | Natural Language Question Answering Systems |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20200104858A1 (en) * | 2018-09-28 | 2020-04-02 | Element Ai Inc. | Method and system for proactively increasing customer satisfaction |
US10839335B2 (en) | 2018-12-13 | 2020-11-17 | Nice Ltd. | Call center agent performance scoring and sentiment analytics |
US11005995B2 (en) * | 2018-12-13 | 2021-05-11 | Nice Ltd. | System and method for performing agent behavioral analytics |
US11165900B2 (en) * | 2019-10-25 | 2021-11-02 | Uniphore Technologies Inc. | Automated real-time call summarization |
US20220103510A1 (en) * | 2019-10-30 | 2022-03-31 | Liveperson, Inc. | Message rerouting from an e-mail environment to a messaging environment |
US11855952B2 (en) * | 2019-10-30 | 2023-12-26 | Liveperson, Inc. | Message rerouting from an e-mail environment to a messaging environment |
US11789595B1 (en) * | 2020-06-29 | 2023-10-17 | United Services Automobile Association (Usaa) | Integrated smart graphical user interface for customer management systems |
US20230267475A1 (en) * | 2022-02-24 | 2023-08-24 | The Toronto-Dominion Bank | Systems and methods for automated context-aware solutions using a machine learning model |
Also Published As
Publication number | Publication date |
---|---|
US11810128B2 (en) | 2023-11-07 |
US20230394491A1 (en) | 2023-12-07 |
US20230030609A1 (en) | 2023-02-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11810128B2 (en) | Systems and methods for customer service prediction | |
US10572516B2 (en) | Method and apparatus for managing natural language queries of customers | |
US10755293B2 (en) | Customer journey prediction and resolution | |
US10069891B2 (en) | Channel accessible single function micro service data collection process for light analytics | |
US20180349474A1 (en) | Method and system for automatic reporting of analytics and distribution of advice using a conversational interface | |
US11520556B2 (en) | Application replication platform | |
US20230089001A1 (en) | Method and system for conversational input device with intelligent crowd-sourced options | |
US20170091666A1 (en) | System framework processor for channel contacts | |
US20220020085A1 (en) | System and method for providing automated predictive information on a user interface | |
US11720905B2 (en) | Intelligent merchant onboarding | |
CA2999184C (en) | Method and apparatus for reserving zero-wait time agent interactions | |
US20230281727A1 (en) | On-demand payroll system and interface | |
US9747175B2 (en) | System for aggregation and transformation of real-time data | |
US20240171679A1 (en) | Systems and methods for generating customized customer service menu | |
US20220067500A1 (en) | Decoupling memory and computation to enable privacy across multiple knowledge bases of user data | |
US20220070265A1 (en) | Determining processing weights of rule variables for rule processing optimization | |
US10664457B2 (en) | System for real-time data structuring and storage | |
US20230267475A1 (en) | Systems and methods for automated context-aware solutions using a machine learning model | |
JP2024514181A (en) | Machine learning-driven real-time data analysis | |
US20230048437A1 (en) | System And Method for Providing Advisory Notifications to Mobile Applications | |
CA3127896A1 (en) | System and method for providing advisory notifications to mobile applications |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: CAPITAL ONE SERVICES, LLC, VIRGINIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:DOUGLAS, LAWRENCE;REEL/FRAME:046704/0770 Effective date: 20180824 |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: FINAL REJECTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: FINAL REJECTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE AFTER FINAL ACTION FORWARDED TO EXAMINER |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: ADVISORY ACTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: FINAL REJECTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE AFTER FINAL ACTION FORWARDED TO EXAMINER |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: ADVISORY ACTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: FINAL REJECTION MAILED |
|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |