Systems and methods for knowledge article generation

Abstract

Described herein are methods, systems, and media for implementing a knowledge article generation logic pipeline using methodology comprising: providing a plurality of functional modules comprising a first module, a second module and a third module that operate in a cascade configuration; using the first module to process a plurality of service tickets by extracting a plurality of intents from the plurality of service tickets; using the second module to group the plurality of service tickets based at least in part on the plurality of extracted intents; and using the third module to process a plurality of ticket group resolution files associated with a plurality of groups of service tickets and generate a knowledge article for each group of service tickets.

Description

SYSTEMS AND METHODS FOR KNOWLEDGE ARTICLE GENERATIONCROS S-REFERENCE

[0001] This application claims the benefit of U.S. Application No. 18 / 980,124, filed December 13, 2023.BACKGROUND

[0002] Generative artificial intelligence (Al) is artificial intelligence capable of generating text, images, or other media, using generative models. Advances in transformer-based deep neural networks have enabled a number of generative Al systems notable for accepting natural language prompts as input. One such type of model, a large language model (LLM), is a deep learning algorithm that can recognize, summarize, translate, predict and generate text and other forms of content based on knowledge gained from massive datasets. LLMs cans improve enterprise operations, making them more efficient, accurate, and personalized.SUMMARY

[0003] In one aspect, disclosed herein are computer-implemented methods for implementing a knowledge article generation logic pipeline, the method comprising: (a) providing a plurality of functional modules comprising a first module, a second module and a third module that operate in a cascade configuration; (b) using the first module to process a plurality of service tickets by extracting a plurality of intents from the plurality of service tickets; (c) using the second module to group the plurality of service tickets based at least in part on the plurality of intents extracted in (b); and (d) using the third module to process a plurality of ticket group resolution files associated with a plurality of groups of service tickets from (c) and generate a knowledge article for each group of service tickets.

[0004] In some embodiments, the first module processes the plurality of service tickets by generating a summary for each service ticket using at least in part a ticket title and a ticket description. In some embodiments, the first module further extracts the plurality of intents associated a plurality of corresponding primary entities, based at least in part on the summary generated for each service ticket. In further embodiments, the first module further clusters the plurality of intents based on the plurality of corresponding primary entities, and groups the clustersof intents by similarity of intent associated with primary entity. In further embodiments, the second module groups the plurality of service tickets into the plurality of groups of service tickets, wherein each group of service tickets comprises a set of service tickets that have similar intents referring to a same primary entity. In further embodiments, wherein the set of service tickets in each group of service tickets have semantically similar intents referring to the same primary entity. In still further embodiments, the second module extracts a plurality of resolutions for each group of service tickets, and saves the plurality of resolutions into a ticket group resolution file for each group of service tickets. In still further embodiments, the third module processes each group of service tickets based at least in part on an intent, a primary entity and a ticket group resolution file, to generate the knowledge article for each group of service tickets. In still further embodiments, the knowledge article for each ticket group resolution file comprises one or more user issues and agent resolutions. In still further embodiments, the one or more user issues and agent resolutions conform to style and / or formatting guidelines or templates that are provided or defined by a customer. In some embodiments, at least one of the first module, the second module or the third module comprises a large language model (LLM).

[0005] In another aspect, disclosed herein are computer-implemented systems comprising at least one processor and instructions causing the at least one processor to perform operations, the system comprising: a plurality of functional modules that are configured to operate in a cascade configuration, wherein the plurality of functional modules comprises a first module, a second module and a third module, wherein the first module is configured to process a plurality of service tickets by extracting a plurality of intents from the plurality of service tickets; wherein the second module is configured to group the plurality of service tickets based at least in part on the plurality of intents extracted by the first module; and wherein the third module is configured to process a plurality of ticket group resolution files associated with a plurality of groups of service tickets obtained from the second module and generate a knowledge article for each group of service tickets.

[0006] In some embodiments, the first module is configured to process the plurality of service tickets by generating a summary for each service ticket using at least in part a ticket title and a ticket description. In some embodiments, the first module is further configured to extract the plurality of intents associated a plurality of corresponding primary entities, based at least in part on the summary generated for each service ticket. In further embodiments, the first module isfurther configured to cluster the plurality of intents based on the plurality of corresponding primary entities, and groups the clusters of intents by similarity of intent associated with primary entity. In further embodiments, the second module is configured to group the plurality of service tickets into the plurality of groups of service tickets, wherein each group of service tickets comprises a set of service tickets that have similar intents referring to a same primary entity. In further embodiments, the set of service tickets in each group of service tickets have semantically similar intents referring to the same primary entity. In further embodiments, the second module is configured to extract a plurality of resolutions for each group of service tickets, and save the plurality of resolutions into a ticket group resolution file for each group of service tickets. In still further embodiments, the third module is configured to process each group of service tickets based at least in part on an intent, a primary entity and a ticket group resolution file, to generate the knowledge article for each group of service tickets. In still further embodiments, the knowledge article for each ticket group resolution file comprises one or more user issues and agent resolutions. In still further embodiments, the one or more user issues and agent resolutions conform to style and / or formatting guidelines or templates that are provided or defined by a customer. In some embodiments, at least one of the first module, the second module or the third module comprises a large language model (LLM).

[0007] In yet another aspect, disclosed herein are one or more non-transitory computer-readable storage media encoded with instructions executable by one or more processors to provide an application comprising: (a) providing a plurality of functional modules comprising a first module, a second module and a third module that operate in a cascade configuration; (b) using the first module to process a plurality of service tickets by extracting a plurality of intents from the plurality of service tickets; (c) using the second module to group the plurality of service tickets based at least in part on the plurality of intents extracted in (b); and (d) using the third module to process a plurality of ticket group resolution files associated with a plurality of groups of service tickets from (c) and generate a knowledge article for each group of service tickets.BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The novel features of the disclosure are set forth with particularity in the appended claims. A better understanding of the features and advantages of the present disclosure will be obtainedby reference to the following detailed description that sets forth illustrative embodiments, in which the principles of the disclosure are utilized, and the accompanying drawings of which:

[0009] FIG. 1 shows a non-limiting example of a computing device; in this case, a device with one or more processors, memory, storage, and a network interface, per one or more embodiments herein;

[0010] FIG. 2 shows a first diagram of an exemplary technology stack, per one or more embodiments herein;

[0011] FIG. 3 shows a second diagram of an exemplary technology stack; in this case, a technology stack with large language model (LLM) emphasis;

[0012] FIG. 4 shows a diagram of an exemplary method of prompt registration configured at an admin console through an LLM gateway, per one or more embodiments herein;

[0013] FIG. 5 shows a non-limiting example of a graphic user interface (GUI); in this case, a GUI for an admin console showing artificial intelligence (Al) service desk features;

[0014] FIG. 6 shows a non-limiting example of a GUI; in this case, a GUI for an admin console showing Al ops desk features;

[0015] FIG. 7 shows a non-limiting example of a GUI; in this case, a GUI for an admin console showing Al support intelligence features; and

[0016] FIG. 8 shows a non-limiting example of a logical architecture for an Al pipeline to generate knowledge articles from tickets.DETAILED DESCRIPTION

[0017] Described herein, in certain embodiments, are computer-implemented methods for implementing a knowledge article generation logic pipeline, the method comprising: (a) providing a plurality of functional modules comprising a first module, a second module and a third module that operate in a cascade configuration; (b) using the first module to process a plurality of service tickets by extracting a plurality of intents from the plurality of service tickets; (c) using the second module to group the plurality of service tickets based at least in part on the plurality of intents extracted in (b); and (d) using the third module to process a plurality of ticket group resolutionfiles associated with a plurality of groups of service tickets from (c) and generate a knowledge article for each group of service tickets.

[0018] Also described herein, in certain embodiments, are computer-implemented systems comprising at least one processor and instructions causing the at least one processor to perform operations, the system comprising: a plurality of functional modules that are configured to operate in a cascade configuration, wherein the plurality of functional modules comprises a first module, a second module and a third module, wherein the first module is configured to process a plurality of service tickets by extracting a plurality of intents from the plurality of service tickets; wherein the second module is configured to group the plurality of service tickets based at least in part on the plurality of intents extracted by the first module; and wherein the third module is configured to process a plurality of ticket group resolution files associated with a plurality of groups of service tickets obtained from the second module and generate a knowledge article for each group of service tickets.

[0019] Also described herein, in certain embodiments, are one or more non-transitory computer- readable storage media encoded with instructions executable by one or more processors to provide an application comprising: (a) providing a plurality of functional modules comprising a first module, a second module and a third module that operate in a cascade configuration; (b) using the first module to process a plurality of service tickets by extracting a plurality of intents from the plurality of service tickets; (c) using the second module to group the plurality of service tickets based at least in part on the plurality of intents extracted in (b); and (d) using the third module to process a plurality of ticket group resolution files associated with a plurality of groups of service tickets from (c) and generate a knowledge article for each group of service tickets.Terms and Definitions

[0020] Unless otherwise defined, all technical terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.

[0021] As used herein, the singular forms “a,” “an,” and “the” include plural references unless the context clearly dictates otherwise. Any reference to “or” herein is intended to encompass “and / or” unless otherwise stated.

[0022] As used herein, the term “about” in some cases refers to an amount that is approximately the stated amount, in some cases near the stated amount by 10%, 5%, or 1%, including increments therein, and in some cases, in reference to a percentage, refers to an amount that is greater or less the stated percentage by 10%, 5%, or 1%, including increments therein.

[0023] As used herein, the phrases “at least one,” “one or more,” and “and / or” are open-ended expressions that are both conjunctive and disjunctive in operation. For example, each of the expressions “at least one of A, B and C,” “at least one of A, B, or C,” “one or more of A, B, and C,” “one or more of A, B, or C” and “A, B, and / or C” means A alone, B alone, C alone, A and B together, A and C together, B and C together, or A, B and C together.

[0024] Reference throughout this specification to “some embodiments,” “further embodiments,” or “a particular embodiment,” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, the appearances of the phrase “in some embodiments,” or “in further embodiments,” or “in a particular embodiment” in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.Computing Systems

[0025] Referring to FIG. 1, a block diagram is shown depicting an exemplary machine that includes a computer system 100 (e.g., a processing or computing system) within which a set of instructions can execute for causing a device to perform or execute any one or more of the aspects and / or methodologies for static code scheduling of the present disclosure. The components in FIG. 1 are examples only and do not limit the scope of use or functionality of any hardware, software, embedded logic component, or a combination of two or more such components implementing particular embodiments.

[0026] Computer system 100 may include one or more processors 101, a memory 103, and a storage 108 that communicate with each other, and with other components, via a bus 140. The bus 140 may also link a display 132, one or more input devices 133 (which may, for example, include a keypad, a keyboard, a mouse, a stylus, etc.), one or more output devices 134, one or more storage devices 135, and various tangible storage media 136. All of these elements may interface directly or via one or more interfaces or adaptors to the bus 140. For instance, the various tangible storagemedia 136 can interface with the bus 140 via storage medium interface 126. Computer system 100 may have any suitable physical form, including but not limited to one or more integrated circuits (ICs), printed circuit boards (PCBs), mobile handheld devices (such as mobile telephones or PDAs), laptop or notebook computers, distributed computer systems, computing grids, or servers.

[0027] Computer system 100 includes one or more processor(s) 101 (e.g., central processing units (CPUs) or general purpose graphics processing units (GPGPUs)) that carry out functions. Processor(s) 101 optionally contains a cache memory unit 102 for temporary local storage of instructions, data, or computer addresses. Processor(s) 101 are configured to assist in execution of computer readable instructions. Computer system 100 may provide functionality for the components depicted in FIG. 1 as a result of the processor(s) 101 executing non-transitory, processor-executable instructions embodied in one or more tangible computer-readable storage media, such as memory 103, storage 108, storage devices 135, and / or storage medium 136. The computer-readable media may store software that implements particular embodiments, and processor(s) 101 may execute the software. Memory 103 may read the software from one or more other computer-readable media (such as mass storage device(s) 135, 136) or from one or more other sources through a suitable interface, such as network interface 120. The software may cause processor(s) 101 to carry out one or more processes or one or more steps of one or more processes described or illustrated herein. Carrying out such processes or steps may include defining data structures stored in memory 103 and modifying the data structures as directed by the software.

[0028] The memory 103 may include various components (e.g., machine readable media) including, but not limited to, a random access memory component (e.g., RAM 104) (e.g., static RAM (SRAM), dynamic RAM (DRAM), ferroelectric random access memory (FRAM), phasechange random access memory (PRAM), etc.), a read-only memory component (e.g., ROM 105), and any combinations thereof. ROM 105 may act to communicate data and instructions unidirectionally to processor(s) 101, and RAM 104 may act to communicate data and instructions bidirectionally with processor(s) 101. ROM 105 and RAM 104 may include any suitable tangible computer-readable media described below. In one example, a basic input / output system 106 (BIOS), including basic routines that help to transfer information between elements within computer system 100, such as during start-up, may be stored in the memory 103.

[0029] Fixed storage 108 is connected bidirectionally to processor(s) 101, optionally through storage control unit 107. Fixed storage 108 provides additional data storage capacity and may also include any suitable tangible computer-readable media described herein. Storage 108 may be used to store operating system 109, executable(s) 110, data 111, applications 112 (application programs), and the like. Storage 108 can also include an optical disk drive, a solid-state memory device (e.g., flash-based systems), or a combination of any of the above. Information in storage 108 may, in appropriate cases, be incorporated as virtual memory in memory 103.

[0030] In one example, storage device(s) 135 may be removably interfaced with computer system 100 (e.g., via an external port connector (not shown)) via a storage device interface 125. Particularly, storage device(s) 135 and an associated machine-readable medium may provide nonvolatile and / or volatile storage of machine-readable instructions, data structures, program modules, and / or other data for the computer system 100. In one example, software may reside, completely or partially, within a machine-readable medium on storage device(s) 135. In another example, software may reside, completely or partially, within processor(s) 101.

[0031] Bus 140 connects a wide variety of subsystems. Herein, reference to a bus may encompass one or more digital signal lines serving a common function, where appropriate. Bus 140 may be any of several types of bus structures including, but not limited to, a memory bus, a memory controller, a peripheral bus, a local bus, and any combinations thereof, using any of a variety of bus architectures. As an example and not by way of limitation, such architectures include an Industry Standard Architecture (ISA) bus, an Enhanced ISA (EISA) bus, a Micro Channel Architecture (MCA) bus, a Video Electronics Standards Association local bus (VLB), a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, an Accelerated Graphics Port (AGP) bus, HyperTransport (HTX) bus, serial advanced technology attachment (SATA) bus, and any combinations thereof.

[0032] Computer system 100 may also include an input device 133. In one example, a user of computer system 100 may enter commands and / or other information into computer system 100 via input device(s) 133. Examples of an input device(s) 133 include, but are not limited to, an alpha-numeric input device (e.g., a keyboard), a pointing device (e.g., a mouse or touchpad), a touchpad, a touch screen, a multi-touch screen, a joystick, a stylus, a gamepad, an audio input device (e.g., a microphone, a voice response system, etc.), an optical scanner, a video or still imagecapture device (e.g., a camera), and any combinations thereof. In some embodiments, the input device is a Kinect, Leap Motion, or the like. Input device(s) 133 may be interfaced to bus 140 via any of a variety of input interfaces 123 (e.g., input interface 123) including, but not limited to, serial, parallel, game port, USB, FIREWIRE, THUNDERBOLT, or any combination of the above.

[0033] In particular embodiments, when computer system 100 is connected to network 130, computer system 100 may communicate with other devices, specifically mobile devices and enterprise systems, distributed computing systems, cloud storage systems, cloud computing systems, and the like, connected to network 130. Communications to and from computer system 100 may be sent through network interface 120. For example, network interface 120 may receive incoming communications (such as requests or responses from other devices) in the form of one or more packets (such as Internet Protocol (IP) packets) from network 130, and computer system 100 may store the incoming communications in memory 103 for processing. Computer system 100 may similarly store outgoing communications (such as requests or responses to other devices) in the form of one or more packets in memory 103 and communicated to network 130 from network interface 120. Processor(s) 101 may access these communication packets stored in memory 103 for processing.

[0034] Examples of the network interface 120 include, but are not limited to, a network interface card, a modem, and any combination thereof. Examples of a network 130 or network segment 130 include, but are not limited to, a distributed computing system, a cloud computing system, a wide area network (WAN) (e.g., the Internet, an enterprise network), a local area network (LAN) (e.g., a network associated with an office, a building, a campus or other relatively small geographic space), a telephone network, a direct connection between two computing devices, a peer-to-peer network, and any combinations thereof. A network, such as network 130, may employ a wired and / or a wireless mode of communication. In general, any network topology may be used.

[0035] Information and data can be displayed through a display 132. Examples of a display 132 include, but are not limited to, a cathode ray tube (CRT), a liquid crystal display (LCD), a thin film transistor liquid crystal display (TFT-LCD), an organic liquid crystal display (OLED) such as a passive-matrix OLED (PMOLED) or active-matrix OLED (AMOLED) display, a plasma display, and any combinations thereof. The display 132 can interface to the processor(s) 101, memory 103, and fixed storage 108, as well as other devices, such as input device(s) 133, via the bus 140. Thedisplay 132 is linked to the bus 140 via a video interface 122, and transport of data between the display 132 and the bus 140 can be controlled via the graphics control 121. In some embodiments, the display is a video projector. In some embodiments, the display is a head-mounted display (HMD) such as a VR headset. In further embodiments, suitable VR headsets include, by way of non-limiting examples, HTC Vive, Oculus Rift, Samsung Gear VR, Microsoft HoloLens, Razer OSVR, FOVE VR, Zeiss VR One, Avegant Glyph, Freefly VR headset, and the like. In still further embodiments, the display is a combination of devices such as those disclosed herein.

[0036] In addition to a display 132, computer system 100 may include one or more other peripheral output devices 134 including, but not limited to, an audio speaker, a printer, a storage device, and any combinations thereof. Such peripheral output devices may be connected to the bus 140 via an output interface 124. Examples of an output interface 124 include, but are not limited to, a serial port, a parallel connection, a USB port, a FIREWIRE port, a THUNDERBOLT port, and any combinations thereof.

[0037] In addition or as an alternative, computer system 100 may provide functionality as a result of logic hardwired or otherwise embodied in a circuit, which may operate in place of or together with software to execute one or more processes or one or more steps of one or more processes described or illustrated herein. Reference to software in this disclosure may encompass logic, and reference to logic may encompass software. Moreover, reference to a computer-readable medium may encompass a circuit (such as an IC) storing software for execution, a circuit embodying logic for execution, or both, where appropriate. The present disclosure encompasses any suitable combination of hardware, software, or both.

[0038] Those of skill in the art will appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality.

[0039] The various illustrative logical blocks, modules, and circuits described in connection with the embodiments disclosed herein may be implemented or performed with a general purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate ortransistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration.

[0040] The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by one or more processor(s), or in a combination of the two. A software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In the alternative, the processor and the storage medium may reside as discrete components in a user terminal.

[0041] In accordance with the description herein, suitable computing devices include, by way of non-limiting examples, cloud computing platforms, distributed computing platforms, server clusters, server computers, desktop computers, laptop computers, notebook computers, subnotebook computers, netbook computers, and netpad computers.

[0042] In some embodiments, the computing device includes an operating system configured to perform executable instructions. The operating system is, for example, software, including programs and data, which manages the device’s hardware and provides services for execution of applications. Those of skill in the art will recognize that suitable server operating systems include, by way of non-limiting examples, FreeBSD, OpenBSD, NetBSD®, Linux, Apple® Mac OS X Server®, Oracle® Solaris®, Windows Server®, and Novell® NetWare®. Those of skill in the art will recognize that suitable personal computer operating systems include, by way of non-limiting examples, Microsoft® Windows®, Apple® Mac OS X®, UNIX®, and UNIX-like operating systems such as GNU / Linux®. In some embodiments, the operating system is provided by cloud computing. Those of skill in the art will also recognize that suitable mobile smartphone operatingsystems include, by way of non-limiting examples, Nokia® Symbian® OS, Apple® iOS®, Research In Motion® BlackBerry OS®, Google® Android®, Microsoft® Windows Phone® OS, Microsoft® Windows Mobile® OS, Linux®, and Palm® WebOS®.Non-transitory Computer Readable Storage Medium

[0043] In some embodiments, the platforms, systems, media, and methods disclosed herein include one or more non-transitory computer readable storage media encoded with a program including instructions executable by the operating system of an optionally networked computing device. In further embodiments, a computer readable storage medium is a tangible component of a computing device. In still further embodiments, a computer readable storage medium is optionally removable from a computing device. In some embodiments, a computer readable storage medium includes, by way of non-limiting examples, CD-ROMs, DVDs, flash memory devices, solid state memory, magnetic disk drives, magnetic tape drives, optical disk drives, distributed computing systems including cloud computing systems and services, and the like. In some cases, the program and instructions are permanently, substantially permanently, semipermanently, or non-transitorily encoded on the media.Computer Programs

[0044] In some embodiments, the platforms, systems, media, and methods disclosed herein include at least one computer program, or use of the same. A computer program includes a sequence of instructions, executable by one or more processor(s) of the computing device’s CPU, written to perform a specified task. Computer readable instructions may be implemented as program modules, such as functions, objects, Application Programming Interfaces (APIs), computing data structures, and the like, which perform particular tasks or implement particular abstract data types. In light of the disclosure provided herein, those of skill in the art will recognize that a computer program may be written in various versions of various languages.

[0045] The functionality of the computer readable instructions may be combined or distributed as desired in various environments. In some embodiments, a computer program comprises one sequence of instructions. In some embodiments, a computer program comprises a plurality of sequences of instructions. In some embodiments, a computer program is provided from one location. In other embodiments, a computer program is provided from a plurality of locations. In various embodiments, a computer program includes one or more software modules. In variousembodiments, a computer program includes, in part or in whole, one or more web applications, one or more mobile applications, one or more standalone applications, one or more web browser plug-ins, extensions, add-ins, or add-ons, or combinations thereof.Software Modules

[0046] In some embodiments, the platforms, systems, media, and methods disclosed herein include software, server, and / or database modules, or use of the same. In view of the disclosure provided herein, software modules are created by techniques known to those of skill in the art using machines, software, and languages known to the art. The software modules disclosed herein are implemented in a multitude of ways. In various embodiments, a software module comprises a file, a section of code, a programming object, a programming structure, a distributed computing resource, a cloud computing resource, or combinations thereof. In further various embodiments, a software module comprises a plurality of files, a plurality of sections of code, a plurality of programming objects, a plurality of programming structures, a plurality of distributed computing resources, a plurality of cloud computing resources, or combinations thereof. In various embodiments, the one or more software modules comprise, by way of non-limiting examples, a web application, a mobile application, a standalone application, and a distributed or cloud computing application. In some embodiments, software modules are in one computer program or application. In other embodiments, software modules are in more than one computer program or application. In some embodiments, software modules are hosted on one machine. In other embodiments, software modules are hosted on more than one machine. In further embodiments, software modules are hosted on a distributed computing platform such as a cloud computing platform. In some embodiments, software modules are hosted on one or more machines in one location. In other embodiments, software modules are hosted on one or more machines in more than one location.Databases

[0047] In some embodiments, the platforms, systems, media, and methods disclosed herein include one or more databases, or use of the same. In view of the disclosure provided herein, those of skill in the art will recognize that many databases are suitable for storage and retrieval of for example, service tickets, knowledge article, model, eligibility, user, and fulfillment object information. In various embodiments, suitable databases include, by way of non-limitingexamples, relational databases, non-relational databases, object oriented databases, object databases, entity-relationship model databases, associative databases, XML databases, document oriented databases, and graph databases. Further non-limiting examples include SQL, PostgreSQL, MySQL, Oracle, DB2, Sybase, and MongoDB. In some embodiments, a database is Internet-based. In further embodiments, a database is web-based. In still further embodiments, a database is cloud computing-based. In a particular embodiment, a database is a distributed database. In other embodiments, a database is based on one or more local computer storage devices.LLM Technology Stack

[0048] FIGS. 2 and 3 show diagrams of an exemplary Large Language Model (LLM) Technology Stack. In some embodiments, the LLM stack herein can be deployed, scaled and operated both in public clouds (AWS, GCP, Azure, etc.) on an Infrastructure Layer 290 and locally (on-premise) using the Kubernetes container orchestration platform.

[0049] In some embodiments, the LLM stack herein embeds a plurality of large foundational models (LFMs) 280, including both closed-source LFMs 281 via an API layer 230 integrated with LFMs, and open-source LFMs 282 via the LFM deployment and execution in secure Kubernetes containers. Non-limiting examples of closed-source LFM providers which are integrated with The LLM stack herein via APIs are Azure OpenAI (complete and chat APIs for GPT-3, GPT-3.5, and GPT-4), OpenAI (complete and chat APIs for GPT-3, GPT-3.5 and GPT-4), Google Vertex Al (PaLM-2). Non-limiting examples of open-source LFM are FLAN-T5, OpenAssistant, RoBERTa, MiniLM, and MPNet.

[0050] In some embodiments, the LLM stack herein enables a developer to choose from a pool of supported LFM / LLM models using a catalog, or to integrate a new LFM / LLM model using the LLM Gateway. In some embodiments, the LLM Gateway Toolkit allows the developer to select the LFM provider of choice, either from a catalog or by selecting “New LFM’ (in which case he needs to provide the LFM Provider URL and the API Credentials to establish a successful connection), create a new LLM Group, which is a logical folder associated to the developer, and simply upload the new LLM models in the LLM group.

[0051] The LLM stack herein provides the developer with the flexibility of choosing both the LFM framework and a customer-specific LLM model 250 for any given task based on the different LLM services needed to operate a conversational Al assistant. As a result, in some embodiments,developers can develop end to end LLM workflows or LLM services 260 which comprise more than one task by choosing a specific LFM / LLM model for each specific task to be executed in the pipeline.

[0052] In some embodiments, developers can calibrate each model per their objectives to deliver a high level of precision and accuracy. In some embodiments, LLM stack herein allows the developer to calibrate the mode using the below behaviors:

[0053] Zero-shot Learning: The developer can use the pre-trained LLM model as-is. Examples of such tasks are language detection, language translation, sentiment detection, emotion detection, etc.

[0054] Few-shots Learning (e.g., prompt engineering or inference-time tuning): In some embodiments, the developer guides the model to the desired output by providing the LLM model with few examples and instructions. In some embodiments, this calibration model does not alter the underlying parameters of the LLM models.

[0055] Instruction-based Fine-Tuning: This method may provide a higher level of precision and accuracy than zero-shot or few-shot learnings. In some embodiments, in this method, the developer trains the model using specialized datasets, which are high-quality human-generated prompt / response pairs specifically designed for instruction tuning LLMs. In some embodiments, this method of calibration acts deeper in the LLM model by updating the internal parameters used by the model. The model fine-tuning is the most advanced calibration method and may require both computing resources for training and supervised, high-quality and extensive datasets to generate the prompt / response sentence pairs for training.

[0056] In some embodiments, the Large Language Model (LLM) technology stack herein can operate in multiple industry verticals (e.g., logistics, healthcare, wealth management, retailers, banking, airlines, and insurance) and enterprise domains 270 (e.g., IT, HR, legal and compliance, finance, supply chain management, facilities). The Enterprise Domain LLMs are LLM models which have been extensively fine-tuned using prompt / response sentence pairs extracted from Enterprise Domain Packs (EDPs). In some embodiments, each Enterprise Domain Pack comprises a domain-specific ontology, which is an extensive set of entity classes, entity names, entity synonymous like entity expansions, and abbreviations (initialisms, acronymous, shortenings and contractions) and domain-specific taxonomy, which is an extensive set of intents (and intentphrases) associated to each entity of the ontology. Each domain EDP may comprise hundreds of thousands to millions of intent phrases.

[0057] In some embodiments, the Large Language Model (LLM) technology stacks herein use pre-packaged and fine-tuned a large pool of domain-specific LLM Services 260 using one or more EDPs. The LLM Services 260 may be available to developers in a Service LLM catalog. In some embodiments, the developer uses the LLM Services 260 via an API, or can select or drag / drop / chain them into a conversational workflow using a studio to build complete experiences around a service.

[0058] In some embodiments, the LLM stack herein provides a further level of LLM model customization beyond the calibration offered via the instruction-fine tuning and EDP. The Large Language Model (LLM) technology stack herein offers special learning pipelines, which act on the specific customer datasets (e.g., tickets, knowledge articles, call transcripts, etc.) which may automatically extract entities and intents which are very specific to the customer (e.g., within the domain of operation). In some embodiments, this custom-specific knowledge is then used to generate custom-specific prompt / responses which may then be used to execute a second round of instruction-based fine tuning on a proprietary Enterprise Domain LLMs, which may be fine-tuned using only the domain-specific EDPs. Exemplary proprietary Al Learning pipelines directly linked to instruction-based fine-tuning pf LLM models are listed below:

[0059] Tickets Learning Pipeline: Iteratively and continuously processes tickets and automatically extracts the main entities and associated intents. By grouping tickets tagged with the same pair of intents and entities, the pipeline may automatically generate intent phrases capturing the language diversity used by the specific customer to express the same concept.

[0060] Conversation Learning Pipeline: Iteratively and continuously processes user requests and calls transcripts, and automatically extracts the main entities and associated intents. By grouping conversations tagged with the same pair of intent and entity, the pipeline may automatically generate intent phrases capturing the language diversity used by the specific customer to express the same concept.

[0061] Knowledge Learning Pipeline: Processes ingested customer knowledge articles and may automatically extract the main entities, associated intents and large set of intent phrases from each article.

[0062] Ontology Generation: Consumes all the entity-based learning from the different pipelines, may automatically discover expansions, abbreviations, and relationships among the entities, and organizes all the entities into an ontology graph which may be made available as a catalog.

[0063] Taxonomy Generation: Consumes all the intent-based learning from the different pipelines and may automatically organize all semantic similar intents into a multi-category multilevel intent taxonomy which is made available as a catalog.

[0064] In some embodiments, the LLM stack herein provides an LLM evaluation level 240, which the user with a set of toolkits and APIs that developers can use to evaluate the performance of the LLM models herein. Developers can access toolkits and APIs for development, testing and benchmarking the following: prompt engineering (e.g., few shots learning), fine tuning, Model Selection via LLM catalog and LLM Gateway, model performance ranking which automatically scores the models against the same dataset to automatically stack rank LFM / LLM models based on the accuracy achieved, and manage customer datasets for instruction-fine tuning models.

[0065] In some embodiments, the LLM stack herein offers a comprehensive Orchestration and Deployment Layer 220 that is used to allocate and deploy resources (including servers, virtual machines, networking, security and storage), monitor software lifecycle operations, and recover from error conditions. In some embodiments, the LLM stack herein offers a large diversity of channels 210 to interface with users like Slack, Microsoft Teams, Cisco WebEx, Zoom, SMS / MMS, Email and Voice), Administrator Portal, Form Intercept and Agent Widgets.

[0066] In some embodiments, prompts can have a separate LLM Provider, internal or external (e.g., OpenAI, Bard, etc.). Input Variables can be passed into prompts (e.g. Chat history). In some embodiments, prompt groups and / or prompt chaining is implemented as well.

[0067] In some embodiments, per FIG. 4, an LLM provider is registered through a LLM Gateway by an Admin UI console 410. In some embodiments, prompts are added that will be used mainly for preconfigured Tasks through the LLM Gateway 420 (e.g., an Admin UI console). In some embodiments, calling the registered prompts can be performed by using a prompt for the main NLU path by inserting them inside the Pre-Handling Flow, or as an auxiliary capacity, by adding prompts inside a flow (e.g., using the new LLM action). In the example shown, a first prompt group 430 comprises a provider URL 431 and the associated credentials 432, a first prompt 433,and a second prompt 434. As shown, the first prompt 433 and the second prompt 434 of the first prompt group 430 are sent to an OpenAI LLM provider 450. Further, a second prompt group 440 is sent based on its provider URL (not shown), to a custom external LLM 460. In some embodiments, the LLM Gateway 420 determines, based on the prompt, the provider URL 431, the associated credentials 432, or any combination thereof whether to send the prompt to the OpenAI LLM provider 450 or to the custom external LLM 460. In some embodiments, the LLM Gateway 420 sends the prompt to the OpenAI LLM provider 450 for general prompts that can be answered by the OpenAI LLM provider 450. In some embodiments, the LLM Gateway 420 sends prompts specific to an organization, an application, or other specialized department to the custom external LLM 460.

[0068] In some embodiments, technology stack described herein includes an administrative (or admin) console. In further embodiments, the admin console includes a front-end interface, such as a GUI. In still further embodiments, the GUI includes features allowing an admin user to review and configure features of the technology described herein. By way of example, in some embodiments, per FIG. 5, a GUI for an admin console 500 includes navigation elements allowing a user to access, by way of examples, analytics, users, requests, intents, Al workflows, knowledge bases, service catalogs, ontologies, campaigns, tickets, Al assist, Al observatory, Al discovery, Al lens, Al workbench, gen Al learning, an audit trail, and settings. Further, in some embodiments, per FIG. 5, a GUI for an admin console 500 includes an Al service deck feature providing access to data pertaining to, for example, resolution rates 505, escalation rates 510, total sessions 515, new users 520, average session duration 525, employee satisfaction score 530, total requests 535, resolved requests 540, unresolved requests 545, and average conversation duration 550. By way of further example, in some embodiments, per FIG. 6, a GUI for an admin console 600 includes an Al ops feature providing access to data pertaining to, for example, active service outages 605, triage verified major incidents 610, triage watchlist major incidents 615, impacted business services 620, impacted applications 625, and impacted systems 630. By way of still further example, in some embodiments, per FIG. 7, a GUI for an admin console 700 includes an support intelligence feature providing access to data pertaining to, for example, total active tickets 705, escalated tickets 710, highly likely to escalate tickets 715, likely to escalate tickets 720, escalation deflection rate 725, and mean time to recovery, repair, respond, or resolve (MTTR) 730.Overview

[0069] Described herein, in some embodiments, is a knowledge article generation logic pipeline comprising a plurality of functional modules comprising a first module, a second module and a third module that operate in a cascade configuration. In some embodiments, the first module is configured to process a plurality of service tickets by extracting a plurality of intents from the plurality of service tickets. In some cases, the second module is configured to group the plurality of service tickets based at least in part on the plurality of intents extracted. In some cases, the third module is configured to process a plurality of ticket group resolution files associated with a plurality of groups of service tickets. In further cases, the third module is configured to generate a knowledge article for each group of service tickets.

[0070] Functional component modules include, by way of non-limiting examples:

[0071] Tickets to Knowledge Article Generation Logical Pipeline. Referring to Fig. 8, in some embodiments, an exemplary logical architecture 800 for an Al pipeline to generate knowledge articles from tickets is shown. In some embodiments, the Al pipeline to generate knowledge articles from tickets comprises three functional modules (A), (B) and (C) which operate in cascade. In some cases, the three function modules proceed in the order the first functional model (A), followed by the second functional model (B), and then followed by the third functional model (C). In alternative embodiments, the operation of the functional models (A), (B), and (C) comprise any order of operation (e.g., (B) then (C) then (A), (C) then (A) then (B), etc.).

[0072] In the example of Fig. 8, the first functional module (A) 802 comprises the Summarization & Intent Extraction module (A) 802. In some embodiments, the summarization & intent extraction module (A) 802 processes each service ticket 801 by first summarizing the ticket 801 (e.g., using ticket title and ticket description) to generate a ticket summary. In further embodiments, the summarization & intent extraction module 802 extracts the ticket intents 803 with the corresponding primary entity from the ticket summary.

[0073] Further, in the example of Fig. 8, a second module (B) 804 groups all the service tickets 801 which have similar intents 803 referring to the exact same primary entity. Moreover, in the example of Fig. 8, for each group of tickets, the second module (B) 804 extracts the resolutions (e.g., resolution notes populated by service agents when the service ticket was successfully close) and saves the resolutions into a ticket group resolution file 805. Further, in the example of Fig. 8, each resolution file 805 is then processed by the third module (C) 807. In further embodiments,the third module (C) 807 generates a knowledge article (“KBs”) 808. In even further embodiments, the KBs 808 cover the user issues and agent resolutions by following the style and formatting guidelines provided by the customer 806.

[0074] Summarization & Intent Extraction Module (A). In some embodiments, the Al pipeline to generate knowledge articles from tickets comprises a summarization & intent extraction module (A) 802 LLM. In certain embodiments, the summarization & intent extraction module (A) 802 LLM processes the ticket 801 in its totality. In further embodiments, the summarization & intent extraction module (A) 802 LLM processes the ticket title and description and generates a summary. In even further embodiments, the summarization & intent extraction module (A) 802 LLM extracts the primary intent. In some cases, the summarization & intent extraction module (A) 802 LLM extracts the corresponding primary entity. In further embodiments, the summarization & intent extraction module (A) 802 LLM produces an output 803 comprising the ticket summary. In further embodiments, the summarization & intent extraction module (A) 802 LLM produces an output 803 comprising the ticket 801 primary intent(s) and corresponding primary entities. In further embodiments, the summarization & intent extraction module (A) 802 LLM produces an output 803 comprising a plurality of ticket intents 803 (e.g., a list of ticket intents).

[0075] In some embodiments, the summarization & intent extraction module (A) 802 LLM comprises the first module (e.g., the first functional model) to operate in cascade. In some embodiments, the first module processes the plurality of service tickets 801 by generating a summary for each service ticket. In some cases, the first module processes the plurality of service tickets 801 by generating a summary for each service ticket using at least in part a ticket title and a ticket description.

[0076] In some cases, the first module further extracts the plurality of intents associated to a plurality of corresponding primary entities. In some instances, the first module further extracts the plurality of intents associated to a plurality of corresponding primary entities based at least in part on the summary generated for each service ticket.

[0077] In some cases, the first module further clusters the plurality of intents to generate a cluster of intents. In some instances, the first module clusters the plurality of intents based on the plurality of corresponding primary entities. In even further embodiments, the first module groups the clusters of intents by similarity of intent associated with a primary entity.

[0078] Summarization & Intent Extraction Module (B). In some embodiments, the Al pipeline to generate knowledge articles from tickets comprises a summarization & intent extraction module (B) 804 LLM. In certain embodiments, the summarization & intent extraction module (B) 804 LLM comprises a tickets grouping and resolution extraction 804 LLM.

[0079] In further embodiments, the tickets grouping and resolution extraction 804 LLM first clusters the intents 803 based on the primary entity of reference. In further embodiments, the tickets grouping and resolution extraction 804 LLM groups tickets by the similarity of intent associated to the entity. In further embodiments, each group of tickets extracted is represented by tickets which have semantically similar intents. In further embodiments, the semantically similar intents refer precisely to the exact same entity. In further embodiments, the tickets grouping and resolution extraction 804 LLM produces an output 805. In further embodiments, the output 805 comprises the ticket group resolution files 805. In further embodiments, the output 805 comprises each group of tickets extracted. In even further embodiments, each group of tickets extracted is represented by tickets which have semantically similar intents. In further embodiments, the semantically similar intents refer precisely to the exact same entity.

[0080] In some embodiments, the Al pipeline to generate knowledge articles from tickets comprises a summarization & intent extraction module (B) 804 LLM. In further embodiments, the a summarization & intent extraction module (B) 804 LLM comprises the second module (e.g., the second functional model) to operate in cascade. In some cases, the second module groups the plurality of service tickets 801 into the plurality of groups of service tickets. In further instances, each group of service tickets comprises a set of service tickets that haves semantically similar intents. In even further embodiments, each set of service tickets refer to a same primary entity.

[0081] In some cases, the second module extracts a plurality of resolutions for each group of service tickets. In some instances, the second module saves the plurality of resolutions into a ticket group resolution file 805 for each group of service tickets. In further embodiments, the second module is configured to output 805 a plurality of ticket group resolution files 805.

[0082] LLM Model to Generate Knowledge Article Using Customer Formatting Guidelines. In some embodiments, the Al pipeline to generate knowledge articles from tickets comprises a LLM Model to Generate Knowledge Article Using Customer Formatting Guidelines (C) 807.

[0083] In some embodiments, the LLM Model to Generate Knowledge Article Using Customer Formatting Guidelines (C) 807 processes each group of tickets. In further embodiments, the LLM Model to Generate Knowledge Article Using Customer Formatting Guidelines (C) 807 is configured to receive as an input the intent and the primary entity 803 for each group in the plurality of groups of service tickets. In even further embodiments, the LLM Model to Generate Knowledge Article Using Customer Formatting Guidelines (C) 807 is configured to receive as an input the plurality of ticket group resolution files 805. In even further embodiments LLM Model to Generate Knowledge Article Using Customer Formatting Guidelines (C) 807 generates a knowledge article 808. In even further embodiments, the LLM Model to Generate Knowledge Article Using Customer Formatting Guidelines (C) 807 may be configured to take as an input specific customer defined guidelines 806. In even further embodiments, the specific customer defined guidelines 806 define how to write a knowledge article 808. In even further embodiments, the specific customer defined guidelines 806 comprise a customer writing style. In even further embodiments, the specific customer defined guidelines 806 comprise an article template to be used (e.g., via examples).

[0084] In some embodiments, the LLM Model to Generate Knowledge Article Using Customer Formatting Guidelines (C) 807 comprises the third module (e.g., the first functional model) to operate in cascade. In some cases, the third module processes each group of service tickets. In some instances, the third module processes each group of service tickets based at least in part on a ticket intent 803. In some cases, the third module processes each group of service tickets. In some instances, the third module processes each group of service tickets based at least in part on an a primary entity. In some cases, the third module processes each group of service tickets. In some instances, the third module processes each group of service tickets based at least in part on an a ticket group resolution file 805. In some instances, the third module generates the knowledge article 808 for each group of service tickets. In some cases, the knowledge article 808 for each ticket group resolution file 805 comprises one or more user issues. In some instances, the knowledge article 808 for each ticket group resolution file 805 comprises one or more agent resolutions. In some instances, the one or more user issues conform to style and / or formatting guidelines. In some instances, the one or more user issues conform to templates that are provided or defined by a customer. In some instances, the one or more agent resolutions conform to style 1and / or formatting guidelines or templates that are provided or defined by a customer. In further embodiments, at least one of the first module, the second module or the third module comprises a large language model (LLM).EXAMPLES

[0085] The following illustrative examples are representative of embodiments of the software applications, systems, and methods described herein and are not meant to be limiting in any way.Example 1 — Summarization & Intent Extraction from Tickets LLM Prompt

[0086] The following is an exemplary prompt for summarization and intent extraction from tickets:

[0087] Act as a Customer Service Agent for ScompanyName ("XXX") who has deep knowledge about ScompanySupportURL ("XXX"). I am giving you my past conversations SpastConversation (conversations between user and agent organized in chronological order). I am also giving you my new request SnewRequest.

[0088] I want you to process my new request SnewRequest and my past conversations SpastConversation using the Instructions below and provide your response in a JSON-formatted response (SresponseJSON):

[0089] {

[0090] "request to process" : string,

[0091] }

[0092] Follow step-by-step the Instructions below to process my new request SnewRequest:

[0093] Instruction 1. Familiarize yourself with the entities and associated intents related to ScompanyName using the knowledge support documentation in ScompanySupportURL.

[0094] Instruction 2. Summarize my past conversation SpastConversation by retaining the important details related to the main problem reported by the user. Avoid retaining in your past conversation summary any reference to a type of greetings, or any request to contact / connect / speak / chat / talk / forward / transfer to customer support or live agent or agent or representative or customer service or tech support or human or person or someone or operator or live operator.Then process my new request SnewRequest using the summary of the past conversation and extract a complete and actionable primary intent and associated entity of reference.

[0095] Instruction 3. Determine if the primary intent is a type of greetings, or a request to contact / connect / speak / chat / talk / forward / transfer to customer support or live agent or agent or representative or customer service or tech support or human or person or someone or operator or live operator. If this is the case, save "Null" in "request to process". Otherwise, concatenate the primary intent and the primary entity (if different than agent, human, representative, someone, live agent, customer service, tech support or operator or live operator) together, transform it into a direct and actionable intent using no more than 7 words when possible, and save it to "request to process".

[0096] The past conversation SpastConversation is "XXX".

[0097] The new request SnewRequest is "XXX".

[0098] My SresponseJSON is:Example 2 — Generation of Knowledge Article Using Customer Formatting Guidelines

[0099] The following is an exemplary prompt for generation of knowledge article using customer formatting guidelines:

[0100] I am giving you a set of resolutions ("SgroupResolutions") which are all related to the same ticket resolution group name SrequestName.

[0101] I want you to generate a well-written knowledge article that can be used by users to resolve similar user requests in the future. Save your response in SrequestArticle.

[0102] The article shall use a template and writing style similar to $KB Sample.

[0103] The user request SrequestName is: "XXX". The ticket group resolution file SgroupResolutions is: “XXX”. The SrequestArticle is:

[0104] Below, we show an example of output of this prompt when using the following parameters:

[0105] SrequestName: “troubleshooting microphone issues for zoom”.

[0106] SgroupResolutions:

[0107] “

[0108] Zoom is failing to detect your microphone, hence you need to unplug the device and plug it back in.

[0109] you have a device which is not supported. Check https: / / support.zoom.us / hc / en- us / articles / 360026690212 for the list of supported devices

[0110] Check audio settings. Sign in to the Zoom desktop client. Click your profile picture, then click Settings. Click the Audio tab. Under Speaker, you can do the following: Test your speaker. Select the speaker you want to use in the drop-down menu. Use the Output Volume slider to increase or decrease the output volume. Under Microphone, you can do the following: Test your microphone. Select the microphone you want to use in the drop-down menu. Use the Input Volume slider to increase or decrease the input volume.

[0111] "

[0112] The outputted KB article auto-generated and saved into SrequestArticle is:

[0113] {

[0114] " dataSourceld": 4,

[0115] " documentUrl" : "",

[0116] " documentTitle": "Troubleshooting Microphone Issues with Zoom",

[0117] " sections": [

[0118] " {\"title\":\" Troubleshooting Microphone Issues withZoom\",\"source\":\"\",\"answerContents\":[{\"text\":\"If your microphone is not working with Zoom, there are a few steps you can take to resolve the issue. Follow the troubleshooting steps below to get your microphone working again.?'}]",

[0119] " { / "title / ":?' Step 1: Unplug and Replug theMicrophone / " ,?'answerContents / ":[{ / "text / ": / "The first step is to unplug your microphone from your computer and then plug it back in. Sometimes, a simple reset can fix any connection issues and get your microphone working again.?'}]",

[0120] " { / "title?' : / " Step 2: Check Device Compatibility?', / "answerContents / " : [ { / "text / " :?'Make sure that your microphone is supported by Zoom. You can check the list of supported devices onthe Zoom website at [link]. If your microphone is not on the list, it may not work properly with ZoomA"}]",

[0121] " {\" title?' " Step 3: Check Audio Settings in Zoom\",\"answerContents\":[{\"text\"A"l. Sign in to the Zoom desktop clientAn2. Click your profile picture, then click SettingsAn3. Click the Audio tabAn4. Under Speaker, you can do the following:\n - Test your speakerAn - Select the speaker you want to use in the drop-down menuAn - Use the Output Volume slider to increase or decrease the output volumeAn5. Under Microphone, you can do the following :\n - Test your microphone.\n - Select the microphone you want to use in the drop-down menu.\n - Use the Input Volume slider to increase or decrease the input volumeA"}]"

[0122] ]

[0123] }

[0124] While preferred embodiments of the present disclosure have been shown and described herein, it will be obvious to those skilled in the art that such embodiments are provided by way of example only. Numerous variations, changes, and substitutions will now occur to those skilled in the art without departing from the disclosure. It should be understood that various alternatives to the embodiments of the disclosure described herein may be employed in practicing the disclosure.

Claims

CLAIMSWHAT IS CLAIMED IS:

1. A computer- implemented method for implementing a knowledge article generation logic pipeline, the method comprising:(a) providing a plurality of functional modules comprising a first module, a second module and a third module that operate in a cascade configuration;(b) using the first module to process a plurality of service tickets by extracting a plurality of intents from the plurality of service tickets;(c) using the second module to group the plurality of service tickets based at least in part on the plurality of intents extracted in (b); and(d) using the third module to process a plurality of ticket group resolution files associated with a plurality of groups of service tickets from (c) and generate a knowledge article for each group of service tickets.

2. The method of claim 1, wherein in (b), the first module processes the plurality of service tickets by generating a summary for each service ticket using at least in part a ticket title and a ticket description.

3. The method of claim 2, wherein in (b), the first module further extracts the plurality of intents associated a plurality of corresponding primary entities, based at least in part on the summary generated for each service ticket.

4. The method of claim 3, wherein in (b), the first module further clusters the plurality of intents based on the plurality of corresponding primary entities, and groups the clusters of intents by similarity of intent associated with primary entity.

5. The method of claim 1, wherein in (c), the second module groups the plurality of service tickets into the plurality of groups of service tickets, wherein each group of service tickets comprises a set of service tickets that have similar intents referring to a same primary entity.

6. The method of claim 5, wherein the set of service tickets in each group of service tickets have semantically similar intents referring to the same primary entity.

7. The method of claim 5, wherein in (c), the second module extracts a plurality of resolutions for each group of service tickets, and saves the plurality of resolutions into a ticket group resolution file for each group of service tickets.

8. The method of claim 1, wherein in (d), the third module processes each group of service tickets based at least in part on an intent, a primary entity and a ticket group resolution file, to generate the knowledge article for each group of service tickets.

9. The method of claim 1, wherein the knowledge article for each ticket group resolution file comprises one or more user issues and agent resolutions.

10. The method of claim 9, wherein the one or more user issues and agent resolutions conform to style and / or formatting guidelines or templates that are provided or defined by a customer.

11. The method of claim 1, wherein at least one of: the first module, the second module, and the third module comprises a large language model (LLM).

12. A computer- implemented system comprising at least one processor and instructions causing the at least one processor to perform operations, the system comprising: a first module, a second module, and a third module configured to operate in a cascade configuration; wherein the first module is configured to process a plurality of service tickets by extracting a plurality of intents from the plurality of service tickets; wherein the second module is configured to group the plurality of service tickets based at least in part on the plurality of intents extracted by the first module; and wherein the third module is configured to process a plurality of ticket group resolution files associated with a plurality of groups of service tickets obtained from the second module and generate a knowledge article for each group of service tickets.

13. The system of claim 12, wherein at least one of: the first module, the second module, and the third module comprises a large language model (LLM).

14. One or more non-transitory computer- readable storage media encoded with instructions executable by one or more processors to provide an application comprising:(a) a first module processing a plurality of service tickets by extracting a plurality of intents from the plurality of service tickets;(b) a second module grouping the plurality of service tickets based at least in part on the plurality of extracted intents; and(c) a third module (i) processing a plurality of ticket group resolution files associated with a plurality of groups of service tickets and (ii) generating a knowledge article for each group of service tickets; wherein the first module, the second module, and the third module operate in a cascade configuration.

15. The media of claim 14, wherein at least one of: the first module, the second module, and the third module comprises a large language model (LLM).

Images