Customer service system with parallel artificial intelligence and augmented reality

Abstract

In example implementations, a method for executing an AI assistant to generate a solution to an issue for a customer service request is provided. The method, executed by a processor, includes receiving a customer service request from a customer, placing the customer service request in a queue, activating an artificial intelligence (AI) assistant while the customer service request is in the queue to collect information associated with the customer and an issue with a product purchased from the enterprise by the customer, executing the AI assistant to generate a solution to the issue, providing the solution to the issue generated by the AI assistant to the customer while the customer service request is in the queue, and routing the customer service request based on whether the solution solved the issue.

Description

CUSTOMER SERVICE SYSTEM WITH PARALLEL ARTIFICIAL INTELLIGENCE AND AUGMENTED REALITYBACKGROUND

[0001] Customer service centers can receive requests from customers who may have an issue with a product that is purchased from an enterprise of the customer service center. Some products may be relatively complicated or difficult to install and may require lengthy discussions with a service technician or representative to help the customer resolve an issue with the product.

[0002] Current work flows for customer service centers are relatively inefficient or ineffective. For example, a customer may call into the customer service center and due to high call volume may have to wait on hold before being connected to a representative. The customer may wait for a relatively long time. In some cases, the customer may decide to disconnect the call before receiving any help.

[0003] In other cases, an automated machine may collect information from the customer while the customer is on hold. However, when the customer is connected to a representative, the customer may be asked to repeat the same information.

[0004] In addition, some conversations may be relatively long. As a result, a representative may have difficulty documenting the call. As a result, knowledge that may have been gained from interacting with the customer may be lost.BRIEF DESCRIPTION OF THE DRAWINGS

[0005] The teaching of the present disclosure can be readily understood by considering the following detailed description in conjunction with theaccompanying drawings, in which:

[0006] FIG. 1 illustrates a block diagram of an example network with a customer service center of an enterprise with an artificial intelligence (AI) assistant of the present disclosure;

[0007] FIG. 2 illustrates a block diagram of an example database or memory with various stored functions of the present disclosure;

[0008] FIG. 3 illustrates an example augmented reality graphical user interface of the present disclosure;

[0009] FIG. 4 illustrates an example method for executing an Al assistant to generate a solution to an issue for a customer service request of the present disclosure;

[0010] FIG. 5 illustrates another example method for executing an Al assistant to generate a solution to an issue for a customer service request of the present disclosure;

[0011] FIG. 6 illustrates another example method for executing an AI assistant to generate a solution to an issue for a customer service request; and

[0012] FIG. 7 illustrates a high-level block diagram of an example computer or apparatus suitable for use in performing the functions described herein.

[0013] To facilitate understanding, identical reference numerals have been used, where possible, to designate identical elements that are common to the figures.DETAILED DESCRIPTION

[0014] Examples described herein provide examples of a method, non-transitory computer readable storage medium, and apparatus for executing an AI assistant to generate a solution to an issue for a customer service request. As discussed above, customer service centers can receive service requests from customers who may have an issue with a product that is purchased from an enterprise of the customer service center. Some products may be relatively complicated or difficult to install and may require lengthy discussions with aservice technician or representative to help the customer resolve an issue with the product.

[0015] For example, some products related to building and construction may be complicated to install or assemble. For example, various types of doors (e.g., garage doors, rolling steel doors, large commercial sectional doors, fire doors, etc.) may be difficult to install or troubleshoot.

[0016] Current work flows for customer service centers are relatively inefficient or ineffective. For example, a customer may call into the customer service center and due to high call volume may have to wait on hold before being connected to a representative. The customer may wait for a relatively long time. In some cases, the customer may decide to disconnect the call before receiving any help.

[0017] In other cases, an automated machine may collect information from the customer while the customer is on hold. However, when the customer is connected to a representative, the customer may be asked to repeat the same information.

[0018] In addition, some conversations may be relatively long. As a result, a representative may have difficult documenting the call. As a result, knowledge that may have been gained from interacting with the customer may be lost.

[0019] The present disclosure provides an improved customer service center that may use an artificial intelligence (AI) assistant to help resolve customer issues. In addition, the improved customer service center may use improved work flows that are more efficient. For example, the AI assistant may be executed in parallel while a customer is waiting on hold in a queue. Thus, the AI assistant may be able to resolve the issue for the customer before the customer is connected to service representative or technician.

[0020] In addition, the AI assistant may be trained using training models that collect information about known issues and associated solutions. The training models maybe continuously updated as new issues and solutions are discovered. Thus, the AI assistants may learn in real-time and continuouslyevolve to help solve customer issues associated with purchased products.

[0021] Lastly, the present disclosure may also leverage virtual reality (VR) or augmented reality (AR). For example, the AI assistant may be used with an AR headset. The AR headset may provide an AR graphical user interface (GUI) to provide visuals for the issues and potential solutions to the issues. The GUI may display collected information, status of the customer in the queue, and the like. Thus, the present disclosure provides an improved customer service center of an enterprise that can leverage AI and / or AR.

[0022] FIG. 1 illustrates a block diagram of a network or system 100. The network 100 may include an Internet protocol (IP) network 102, a call center or customer service center 108, and a plurality of mobile endpoint devices 1121to 112m(hereinafter referred to individually as a mobile endpoint device 112 or collectively as mobile endpoint devices 112).

[0023] In one embodiment, the endpoint devices 112 may be any type of endpoint device. For example, the endpoint devices 112 may be a mobile telephone, a smart phone, a tablet, a laptop computer, a desktop computer, or any other type of devices that can communicatively connect to the IP network 102 and / or customer service center 108.

[0024] In one embodiment, the customer service center (CSC) 108 may include a plurality of service representatives or technicians 1101to 110n(hereinafter referred to individually as a service representative 110 or collectively as service representatives 110). The CSC 108 may be associated with an enterprise or company that sells a product. The service representatives 110 may be live persons that are available to assist customers with product questions, troubleshooting, installation help, and the like.

[0025] In one embodiment, the enterprise may be a construction or building company. In one embodiment, the enterprise may be a manufacturer of building products and / or supplies. In one embodiment, the enterprise may be a manufacturer of barriers or doors (e.g., garage doors, rolling steel doors, fire safety doors, and the like).

[0026] In one embodiment, the IP network 102 may include an application server (AS) 104 and a database (DB) 106. The AS 104 may be a computing system or computer that may execute instructions to perform the functions described herein.

[0027] In one embodiment, the DB 106 may be a non-transitory computer readable storage medium that may store various information. FIG. 2 illustrates an example of the DB 106.

[0028] In one embodiment, the DB 106 may include at least one AI training model 202, a customer service queue 204, and Al customer service instructions 206. The AI training model 202 may be a knowledge database that is used to execute an AI assistant during a customer service call, as described in further details below. The AI training model 202 may store records (e.g., customer response management (CRM) tickets) that were collected over a period of time. The records may indicate different issues that have been reported for various products sold by the enterprise and associated solutions that have resolved previously reported issues.

[0029] In one embodiment, a single AI training model 202 may be used to store all records for all products, issues, and solution. In another embodiment, multiple AI training models 202 may be deployed. For example, a different AI training model 202 may be deployed for each product and / or issue. For example, different AI training model 202 may be used to train the AI assistant on different products, such as, sectional garage doors, rolling doors, and fire safety doors.

[0030] Different AI training models 202 may be used to train the AI assistant on different issues for a particular product. For example, within sectional garage doors, different AI training models 202 may be used to train the AI assistant for defect issues and installation issues. Thus, when the AI assistant is executed, a particular AI assistant for a particular product and issue may be executed to help resolve a customer reported issue.

[0031] Any type of method may be used to train the AI assistant with the AItraining models 202. Example methods may include training with large language models (LLM), neural networks, generative adversarial networks (GAN), reinforcement learning (RL). The AI assistant can be initially trained using the historical data and one of the training methods listed above. Simulations may be run to generate solutions for various issues. The accuracy of the solutions may be reviewed and verified to develop the initial release of the Al assistant. After the Al assistant is released, the AI assistant may automatically evolve using updated data and one of the training methods listed above.

[0032] In one embodiment, the customer service queue 204 may be a holding or waiting queue. For example, as multiple calls or service requests come into the CSC 108, the customer service requests may be held in the customer service queue 204 until a service representative 110 can connect to the call.

[0033] In one embodiment, the AI customer service instructions 206 may store instructions executed by the AS 104 to execute the AI assistant or the functions described herein. In other words, the AI customer service instructions 206 may represent he AI assistant. In addition, the AI customer service instructions 206 may store instructions executed by the AS 104 to perform the functions described in the methods 400, 500, and 600, discussed in further details below.

[0034] It should be noted that the DB 106 may store additional information that is not shown. For example, the DB 106 may store historical CRM records used to train the AI training model 202, new CRM records that are generated after each customer service call, and customer information (e.g., account information, purchase history, log-in information, service history, and the like).

[0035] Referring back to FIG. 1, the mobile endpoint devices 112 may be associated with different customers. The mobile endpoint devices 112 may be a smartphone with a graphical user interface that is capable of making telephone calls, sending text messages, establishing a live chat session, and / or executing applications.

[0036] In one embodiment, each customer may also have a VR or ARheadset 1141to 114m(hereinafter referred to individually as an AR headset 114 or collectively as AR headsets 114). The AR headsets 114 may be communicatively coupled to the mobile endpoint devices 114 or may be standalone communication devices. For example, the AR headset 114 may be able to communicate with the CSC 108 without the need of the mobile endpoint devices 112.

[0037] As discussed in further details below, the AR headsets 114 may be optional. For example, the AR headsets 114 may provide additional context and or support for helping to generate a solution to an issue with a product. For example, the AR headsets 114 may provide images that can be analyzed by the Al assistant to provide further information to the Al assistant in generating a solution to an issue with the product.

[0038] FIG. 3 illustrates an example graphical user interface (GUI) 300 that can be used with the Al assistant. In one embodiment, the GUI may be a VR GUI or an AR GUI. In other words, the GUI 300 may be entirely virtual for a VR GUI, or may include a real image of the product with virtual graphics laid on top of the real image for an AR GUI.

[0039] FIG. 3 illustrates an example of an AR GUI 300. For example, a customer may wear the AR headset 114i and look at a product 302. For example, the product 302 illustrated in FIG. 3 may be a garage door. The customer may have an issue with the product 302. For example, the customer may call the call center 108 (e.g., via the mobile endpoint device 112i or directly with the AR headset 114i ) because product 302 may not be operating properly (e.g., the garage door may not be opening and closing properly).

[0040] In one embodiment, the AR or VR environment may provide additional context or data for the Al assistant to resolve the issue associated with the product 302. For example, in the AR environment, the AI assistant may analyze the product 302 to automatically gather information associated with the product 302 without having to collect the product information from the customer. For example, the product 302 may have a bar code, quick response (QR) code,serial number, and the like that may be visible that contains all of the product information (e.g., manufacture date, manufactured location, lot number, serial number, build of materials, color, and the like). Some product information may still be collected from the customer (e.g., purchase location, purchase date, price, and the like).

[0041] The Al assistant may analyze the product 302 to automatically detect the issue. For example, the AI assistant may access the AR environment and ask the customer to open and close the product 302. The Al assistant may notice an issue with the movement (e.g., a slight delay in movement between adjacent panels, a bulge or deformation in one of the panels, and the like). The captured images may be analyzed to determine possible issues that are stored in the Al training model 202. In some embodiments, the captured images may be directly associated with an issue by the AI assistant based on images stored in the Al training model 202 that were used to train the Al assistant.

[0042] The Al assistant may then highlight the area of the product 302 where the issue is detected (e.g., with an arrow, cursor, a circle, or any other type of visual cue). FIG. 3 illustrates an example, where a message bubble is presented where the issue is detected. The message bubble may include an identification of the issue 304 and a proposed fix 306. The proposed fix 306 may include a solution that is generated by the AI assistant based on the AI training models 202.

[0043] In one embodiment, the GUI 300 may also include customer information 308 and product information 310. The GUI 300 may also include an indictor or message box 310 that tracks a customer’s status in the queue. The GUI 300 may also include an end call button 312. Thus, if the AI assistant provides a solution or fix 306 to resolve the issue 304, then the customer may end the call without having to wait to speak with a service representative 110.

[0044] Returning to FIG. 1, it should be noted that FIG. 1 has been simplified for ease of explanation and may include additional network components that are not shown. For example, the network 100 may include one or more accessnetworks (e.g., a cellular network, a broadband network, and the like) and a core network (e.g., a core network of a telecommunications service provider) to connect a call through the IP network 102 and to an endpoint of one of the service representatives 110 at the call center 108. The network 100 may include network elements such as a firewall, border elements, gateways, routers, switches, and the like.

[0045] In one embodiment, a customer may purchase a product from an enterprise and then have an issue with the product (e.g., a product defect or installation issue). The customer may use the mobile endpoint device 112i to initiate a service request with the CSC 108. The service request may be a call, a live chat session, or any other form of communication. In another embodiment, the AR headset 114 may be used to initiate the service request. The service request may be routed through the AS 104. For example, the AS 104 may determine if all of the service representatives 110 are busy. If so, the AS 104 may redirect the service request to the customer service queue 204 to wait on hold.

[0046] In one embodiment, the AS 104 may activate or execute an AI assistant in parallel while the customer is waiting in the customer service queue 204. The Al assistant may use natural language processing (NLP) models to converse with the customer in a natural dialogue. The Al assistant may interact with the customer to collect information from the customer. In another embodiment, if the service request is initiated from the AR headset 114, the AS 104 may execute the AI assistant rather than directing the service request to the customer service queue 204.

[0047] For example, the information may include customer related information, product related information, and the issue. The customer related information may include the customer name, address, telephone number, and email address. The product related information may include the product name, model number, serial number, where the product was purchased, the purchase date, and the like. The issue may be a verbal description of what is wrong withthe product.

[0048] If multiple Al training models 202 were used, the AI assistant may analyze the product related information and the issue to determine which Al training model 202 to load. For example, the Al assistant may load a particular version of the Al assistant (or particular set of instructions from the Al customer service instructions 206) that is trained on a particular Al training model 202 associated with the particular product and issue that has been identified.

[0049] The AI assistant may then try to work with the customer to resolve the issue automatically while the caller is on hold in the customer service queue 204. This may allow the customer to feel as if they are receiving customer service while they are waiting in the customer service queue 204 and receive a more satisfactory customer service experience.

[0050] In one embodiment, if a service representative 110 becomes available during the AI assistant interaction, the customer may receive an option to interrupt the AI assistant interaction and be connected to the available service representative 110.

[0051] In one embodiment, each AI assistant and customer interaction can provide additional knowledge and information into the AI training models 202. Over time, the AI assistant may evolve and become more knowledgeable regarding various products and issues associated with the product.

[0052] In one embodiment, the customer may call back after a period of time to indicate that a potential solution to an issue did not work. As a result, the AI training model 202 can be periodically pruned to remove solutions associated with a particular issue that was determined to be ineffective or fail to resolve the issue. As a result, the AI training model 202 may be periodically updated to provide a more robust and accurate training model for AI assistant.

[0053] Thus, the AI assistant of the present disclosure may provide a more accurate and efficient experience for a customer when they initiate a service request for a product to a customer service center of an enterprise. The customer service center system may be modified to include the AI assistant ofthe present disclosure. Thus, the process flow of an incoming customer service request may be changed from a linear process where the customer waits in a calling queue to a parallel process that can use the Al assistant to resolve a customer’s issue while waiting in the calling queue.

[0054] In other embodiments, the Al assistant may be used to help service requests that are initiated from an AR headset 114. For example, a customer may be attempting to self-remedy a problem or figure out a solution to a problem with the product on their own and initiate a customer service request. In response, the customer service center system may collect the information related to the steps or information the customer has viewed and initiate the Al assistant to resolve the customer’s issue.

[0055] The Al assistant may continue to evolve with each additional interaction as more data is collected over time. The Al assistant may interact with the customer in parallel while the customer is waiting in the customer service queue 204. Thus, the customer may feel like they are receiving a higher level of customer service while they are waiting on hold. Moreover, if the Al assistant is able to provide them a solution to their issue with the product 302, then the customer may disconnect the call sooner without having to wait for a service representative or technician 110.

[0056] FIG. 4 illustrates a flowchart of an example method 400 for executing an Al assistant to generate a solution to an issue for a customer service request of the present disclosure. In one embodiment, one or more blocks ofthe method 400 may be performed by the system 100 (e.g., the AS 104), or a computer / processor as illustrated in FIG. 7 and discussed below.

[0057] At block 402, the method 400 begins. At block 404, the method 400 receives a customer service request from a customer. For example, a customer may purchase a product from an enterprise or company. The product may be a building product. In one embodiment, the building product may be a garage door, rolling steel door, fire curtain, or any other type of barrier for a building. The customer may be trying to install the product and having difficulty. As aresult, the customer may initiate a customer service request to a customer service center of the enterprise to speak to a service representative for assistance with the installation. The customer service request may be an audio only call, a video call, a live chat session, an exchange of text messages, or any other form of communication with the customer service center.

[0058] At block 406, the method 400 places the customer service request in a queue. In one embodiment, all of the representatives may be on another call. As a result, the customer service request may be placed in a queue to wait for an available representative.

[0059] At block 408, the method 400 activates an artificial intelligence (AI) assistant while the customer service request is in the queue to collect information associated with the customer and an issue with a product purchased from the enterprise by the customer. For example, the Al assistant may be activated simultaneously or at the same time the customer service request is placed in the queue. Said another way, the Al assistant may be activated in parallel with the customer service request being placed in the holding queue.

[0060] At block 410, the method 400 executes the Al assistant to generate a solution to the issue. For example, the Al assistant may collect information from the customer. The interaction with the customer may be conducted in a natural language form using natural language processing (NLP) models.

[0061] In one embodiment, the Al assistant may collect customer information, product information and details about the issue with the product the customer is experiencing. Customer information may include account information, purchase history, log-in information, service history, and the like. Product information may include manufacture date, manufactured location, lot number, serial number, build of materials, color, purchase location, purchase date, price, and the like.

[0062] Details about the issue may include a general description by the customer about the issues they are experiencing. Using the example above, the user may indicate they are having trouble installing the garage door. In an example, they may indicate they are having troubling installing the track guidesand the garage door is not properly opening and closing.

[0063] In one embodiment, the customer may also have an AR headset. The AR headset may load an AR environment or program when the Al assistant is activated. In one embodiment, the Al assistant may communicate with the endpoint device of the customer to determine if the endpoint device has an enterprise issued AR environment application. If the endpoint device has the enterprise issued AR environment downloaded, the Al assistant may send a control signal over the voice call connection to activate the AR environment application. The AR environment application may load an AR environment associated with the enterprise on the AR headset.

[0064] In one embodiment, the AR environment may present a GUI (e.g., the GUI 300 illustrated in FIG. 3). The customer may wear the AR headset while looking at their product (e.g., the garage door). The Al assistant may use the images collected in the AR environment for analysis and to generate possible solutions.

[0065] If the AR environment is used, some of the information that is collected may be done automatically by analyzing the images from the AR environment. For example, the product may have a QR code that can be analyzed by the Al assistant to automatically gather some product information.

[0066] At block 412, the method 400 provides the solution to the issue generated by the Al assistant to the customer while the customer service request is in the queue. For example, Al assistant may provide a solution based on details about the issue provided by the customer. If the issue was not previously known and stored in the Al training models, the Al assistant may ask the customer to hold for the next service representative.

[0067] In one embodiment, if an AR headset is used for the service request, the Al assistant may use the images captured in the AR environment, as discussed above. For example, the Al assistant may analyze the image notice that there is a bulge in the guide track or there is unusual movement in one of the rollers. Based on the analysis, the Al assistant may indicate to the customer thatthe guide track may be defective or that one of the rollers may not be properly secured. The Al assistant may provide a solution to double check a part of the guide track to ensure and / or to check the mechanical connections of the roller to the bracket.

[0068] In one embodiment, if a new part has to be ordered, the Al assistant may automatically order the part for the customer. For example, the Al assistant may receive confirmation from the customer that a part is broken or defective and that replacing the part will resolve the issue.

[0069] The Al assistant may be tied into a system for ordering replacement parts. The Al assistant may automatically generate an order for the part based on the product information collected in block 410, as described above.

[0070] At block 414, the method 400 routes the customer service request based on whether the solution solved the issue. For example, if a solution has been provided and the issue associated with the product is resolved, the customer service call may be ended and the customer service request may be removed from the queue.

[0071] However, if no solution was provided or the Al assistant encounters an issue that has not been previously seen and documented in the Al training models, the customer service request may be routed to the next available representative. The customer may then interact with the representative to resolve the issue. In one embodiment, the Al assistant may provide all of the customer information, the product information, and the details regarding the issue to the representative when the call is transferred. As a result, the customer does not have to repeat the process of providing information to the representative.

[0072] In one embodiment, if the AR environment was used, the service representative may be connected to the AR environment with the customer. Thus, the service representative may also analyze the product, view the images, and the like, to try and generate a solution to the issue. At block 412,the method 400 ends.

[0073] FIG. 5 illustrates a flowchart of an example method 500 for executingan Al assistant to generate a solution to an issue for a customer service request of the present disclosure. In one embodiment, one or more blocks ofthe method 500 may be performed by the system 100, or a computer / processor as illustrated in FIG. 7 and discussed below.

[0074] At block 502, the method 500 begins by receiving a customer service request. For example, a customer may purchase a product from an enterprise or company. The product may be a building product. In one embodiment, the building product may be a garage door, rolling steel door, fire curtain, or any other type of barrier for a building. The customer may be trying to install the product and having difficulty. As a result, the customer may initiate a customer service request to a customer service center of the enterprise to speak to a service representative for assistance with the installation. The customer service request may be an audio only call, a video call, a live chat session, an exchange of text messages, or any other form of communication with the customer service center.

[0075] At block 504, the method 500 places the customer service request in a queue to wait for a service technician. In one embodiment, all of the representatives may be on another call or handling another service request. As a result, the customer service request may be placed in a queue to wait for an available representative.

[0076] In one embodiment, if the customer service request is placed in the queue on hold, the method 500 may simultaneously proceed to block 514 in parallel to execute an Al assistant.

[0077] In one embodiment, block 516 may be optional. For example, at block 516, the method 500 may load an AR environment to work in conjunction with the Al assistant. For example, the customer may download and install an application provided by the enterprise to work in the AR environment. The application may be installed on the mobile endpoint device of the customer to work in conjunction with an AR headset or may be installed directly on the AR headset. As described above, the AR environment may provide images of the product that can beanalyzed by the Al assistant to provide further assistance in determining a solution to resolve the issue associated with the product.

[0078] At block 518, the method 500 may determine if the Al assistant has resolved the issue. If the answer is no, the method 500 may proceed to block 506.

[0079] If the issue is not resolved, the method 500 may proceed to block 506. For example, the customer may be connected to a service representative. In one embodiment, the Al assistant may provide all of the customer information, product information, and the issue to the service representative or technician. As a result, the customer does not have to repeat all of the information provided to the Al assistant in block 514.

[0080] At block 508, the method 500 determines if the issue is resolved by the service technician. If the answer is yes, the method 500 may proceed to block 520 and update the Al training model with the technician generated solution and the associated issue. The method 500 may then proceed to block 510.

[0081] At block 508, if the method 500 determines that the issue is not resolved and no solution could be generated, then the method 500 may proceed to block 510.

[0082] Referring back to block 518, if the answer is yes, the method 500 may proceed to block 520. At block 520, the method 500 may update the Al training model with the solution that was generated for the issue. Training of the Al assistant may be updated with the updated Al training model for subsequent calls. The method 500 may then proceed to block 510.

[0083] At block 510, the method 500 may end the service request. For example, the issue may be resolved by the service representative or the Al assistant or no solution was generated and issue may be left unresolved or escalated to be resolved.

[0084] At block 512, the method 500 completes a customer response management (CRM) ticket to summarize the service request. In one embodiment, the Al assistant may automatically complete and generate the CRMticket. The CRM ticket may summarize the call. For example, the CRM ticket may include the customer information, the product information, the issue, the product, any solutions that were generated, and if any solutions were successful in resolving the issue. The CRM tickets may be stored. Periodically, the stored CRM tickets may be used to further update the Al training models. At block 522, the method 500 ends.

[0085] FIG. 6 illustrates a flowchart of an example method 600 for executing an Al assistant to generate a solution to an issue for a customer service request of the present disclosure, in one embodiment, one or more blocks ofthe method 600 may be performed by the system 100 (e.g., the AS 104), or a computer / processor as illustrated in FIG. 7 and discussed below.

[0086] At block 602, the method 600 begins. At block 604, the method 600 receives a customer service request from an augmented reality graphical user interface (AR GUI) that is used to help a customer resolve an issue with a product. For example, the customer may be using an AR GUI to try and perform self-remedy or generate a solution to the issue by themselves. AR GUI may be a program issued by the enterprise to allow customers to attempt to resolve potential issues independently.

[0087] However, the customer may be unsuccessful in resolving the issue on their own via the AR GUI. As a result, the AR GUI may include a link or button in to allow the customer to initiate a customer service request via the AR GUI.

[0088] At block 606, the method 600 receives information associated with the customer, the product purchased from the enterprise by the customer, and the issue with the product. For example, the information associated with the customer may include account information, purchase history, log-in information, service history, and the like. The information associated with the product may include product name, product model number, product serial number, manufacture date, manufactured location, lot number, serial number, build of materials, color, purchase location, purchase date, price, and the like. The issue with the product may be described by the customer or may be automaticallygenerated by the AR GUI based on interaction with the customer.

[0089] At block 608, the method 600 executes an artificial intelligence (AI) assistant in response to the customer service request using the information that is received to generate a solution to the issue. For example, the Al assistant may attempt to generate a solution. The Al assistant may be trained using model data, as described above.

[0090] At block 610, the method 600 transmits the solution to the AR GUI to be displayed in the AR GUI. For example, the solution may be provided as computer readable instructions that can be executed by the AR headset used by the customer. The instructions may cause the AR GUI to display instructions to execute the solution. The instructions may include graphical prompts that visually show what to adjust, replace, and / or repair on the product.

[0091] In one embodiment, as each step is executed by the customer, the AR GUI may modify the image of the product and the image of the issue as the solution is performed by the customer. For example, if the image of the issue was originally a broken part, the image of the issue may be modified to show a functioning part after the customer replaces the broken part. In another example, if a software update was required for an electronic component, the image of the issue may be modified to show what version number should be shown on a display of the electronic component, and so forth.

[0092] In one embodiment, if the solution does not resolve the issue, a service technician may be connected to the AR GUI. For example, the customer may not end the service request because the issue persists even after the solution generated by the Al assistant is executed. The service technician may generate and provide a technician generated solution. If the technician generated solution resolves the issue, the customer service request may be ended.

[0093] In one embodiment, the Al training model may be updated with the solution generated by the service technician if the Al assistant generated solution was unsuccessful. At block 612, the method 600 ends.

[0094] FIG. 7 depicts a high-level block diagram of a computer that isdedicated to perform the functions described herein. As depicted in FIG. 7, the computer 700 comprises one or more hardware processorelements 702 (e.g., a central processing unit (CPU), a microprocessor, or a multi¬ core processor), a memory 704, e.g., random access memory (RAM) and / or read only memory (ROM), a module 705 for executing an Al assistant to generate a solution to an issue for a customer service request, and various input / output devices 706 (e.g., storage devices, including but not limited to, a tape drive, a floppy drive, a hard disk drive or a compact disk drive, a receiver, a transmitter, a speaker, a display, a speech synthesizer, an output port, an input port and a user input device (such as a keyboard, a keypad, a mouse, a microphone and the like)). Although only one processor element is shown, it should be noted that the computer may employ a plurality of processor elements.

[0095] It should be noted that the present disclosure can be implemented in software and / or in a combination of software and hardware, e.g., using application specific integrated circuits (ASIC), a programmable logic array (PLA), including a field-programmable gate array (FPGA), or a state machine deployed on a hardware device, a computer or any other hardware equivalents, e.g., computer readable instructions pertaining to the method(s) discussed above can be used to configure a hardware processor to perform the steps, functions and / or operations of the above disclosed methods. In one embodiment, instructions and data for the present module or process 705 for executing an Al assistant to generate a solution to an issue for a customer service request (e.g., a software program comprising computer-executable instructions) can be loadedinto memory 704 and executed by hardware processor element 702 to implement the steps, functions or operations as discussed above in connection with the example methods 400, 500, and 600. Furthermore, when a hardware processor executes instructions to perform “operations," this could include the hardware processor performing the operations directly and / or facilitating, directing, or cooperating with another hardware device or component (e.g., a co-processor and the like) to perform the operations.

[0096] The processor executing the computer readable or software instructions relating to the above described method(s) can be perceived as a programmed processor or a specialized processor. As such, the present module 705 for executing an Al assistant to generate a solution to an issue for a customer service request (including associated data structures) of the present disclosure can be stored on a tangible or physical (broadly non-transitory) computer-readable storage device or medium, e.g., volatile memory, non-volatile memory, ROM memory, RAM memory, magnetic or optical drive, device or diskette and the like. More specifically, the computer-readable storage device may comprise any physical devices that provide the ability to store information such as data and / or instructions to be accessed by a processor or a computing device such as a computer or an application server.

[0097] It will be appreciated that variants of the above-disclosed and other features and functions, or alternatives thereof, may be combined into many other different systems or applications. Various presently unforeseen or unanticipated alternatives, modifications, variations, or improvements therein may be subsequently made by those skilled in the art which are also intended to be encompassed by the following claims.

Claims

CLAIMS1. A method, comprising:receiving, by a processor of a customer service center of an enterprise, a customer service request from a customer;placing, by the processor, the customer service request in a queue; activating, by the processor, an artificial intelligence (AI) assistant while the customer service request is in the queue to collect information associated with the customer and an issue with a product purchased from the enterprise by the customer;executing, by the processor, the Al assistant to generate a solution to the issue;providing, by the processor, the solution to the issue generated by the Al assistant to the customer while the customer service request is in the queue; and routing, by the processor, the customer service request based on whether the solution solved the issue.

2. The method of claim 1, wherein the solution generated by the Al assistant solved the issue and the routing comprises:ending, by the processor, the customer service request and removing the customer service request from the queue.

3. The method of claim 2, further comprising:updating, by the processor, an Al training model with the issue with the product and the solution.

4. The method of claim 2, further comprising:generating, by the processor, a customer response report based on the information associated with the customer that was collected, the issue with the product, and the solution to the issue that was generated.

5. The method of claim 1, wherein solution generated by the Al assistant does not solve the issue and the routing comprises:connecting, by the processor, the customer to a service technician; providing, by the processor, the information associated with the customer that was collected, the issue with the product, and the solution to the service technician via the Al assistant.receiving, by the processor, a confirmation that a technician generated solution was provided to the customer; andending, by the processor, the customer service request.

6. The method of claim 5, further comprising:executing, by the processor, the Al assistant to record the conversation between the customer and the service technician and analyze the conversation to determine a technician generated solution; andupdating, by the processor, an Al training model with the issue and the technician generated solution.

7. The method of claim 1, wherein the executing the Al assistant comprises:executing, by the processor, an augmented reality graphical user interface (AR GUI) to display an image of the product, an image of the issue, and an image of the solution generated by the Al assistant.

8. The method of claim 7, wherein the solution generated by the Al assistant does not solve the issue and the routing comprises:connecting, by the processor, a service technician to the AR GUI; displaying, by the processor, the information associated with the customer that was collected, the issue with the product, and the solution generated by the Al assistant in the AR GUI;providing, by the processor, a technician generated solution; andending, by the processor, the customer service request.

9. A non-transitory computer readable medium storing instruction, which when executed by a processor of a customer server center of an enterprise, cause the processor to perform operations, comprising:receiving a customer service request from a customer;placing the customer service request in a queue;activating an artificial intelligence (AI) assistant while the customer service request is in the queue to collect information associated with the customer and an issue with a product purchased from the enterprise by the customer;executing the Al assistant to generate a solution to the issue; providing the solution to the issue generated by the Al assistant to the customer while the customer service request is in the queue; androuting the customer service request based on whether the solution solved the issue.

10. The non-transitory computer readable medium of claim 9, wherein the solution generated by the Al assistant solved the issue and the routing comprises:ending the customer service request and removing the customer service request from the queue.

11. The non-transitory computer readable medium of claim 10, further comprising:updating an Al training model with the issue with the product and the solution.

12. The non-transitory computer readable medium of claim 10, further comprising:generating a customer response report based on the informationassociated with the customer that was collected, the issue with the product, and the solution to the issue that was generated.

13. The non-transitory computer readable medium of claim 9, wherein solution generated by the Al assistant does not solve the issue and the routing comprises:connecting the customer to a service technician;providing the information associated with the customer that was collected, the issue with the product, and the solution to the service technician via the Al assistant.receiving a confirmation that a technician generated solution was provided to the customer; andending the customer service request.

14. The non-transitory computer readable medium of claim 13, further comprising:executing the Al assistant to record the conversation between the customer and the service technician and analyze the conversation to determine a technician generated solution; andupdating an Al training model with the issue and the technician generated solution.

15. The non-transitory computer readable medium of claim 9, wherein the executing the Al assistant comprises:executing an augmented reality graphical user interface (AR GUI) to display an image of the product, an image of the issue, and an image of the solution generated by the Al assistant.

16. The non-transitory computer readable medium of claim 15, wherein the solution generated by the Al assistant does not solve the issue and the routingcomprises:connecting a service technician to the AR GUI;displaying the information associated with the customer that was collected, the issue with the product, and the solution generated by the Al assistant in the AR GUI;providing a technician generated solution; andending the customer service request.

17. A method, comprising:receiving, by a processor of a customer service center of an enterprise, a customer service request from an augmented reality graphical user interface (AR GUI) that is used to help a customer resolve an issue with a product;receiving, by the processor, information associated with the customer, the product purchased from the enterprise by the customer, and the issue with the product;executing, by the processor, an artificial intelligence (AI) assistant in response to the customer service request using the information that is received to generate a solution to the issue; andtransmitting, by the processor, the solution to the AR GUI to be displayed in the AR GUI.

18. The method of claim 17, further comprising:determining, by the processor, that the solution did not resolve the issue; connecting, by the processor, a service technician to the AR GUI; providing, by the processor, a technician generated solution; and ending, by the processor, the customer service request.

19. The method of claim 17, wherein providing, by the processor, the solution in the AR GUI, comprises:providing, by the processor, computer readable instructions to cause theAR GUI to display instructions on executing the solution.

20. The method of claim 19, wherein the computer readable instructions cause the AR GUI to modify an image of the product and the image of the issue as the instructions on executing the solution are performed by the customer.

Images