Information technology (IT) utilizing artificial intelligence (AI)

AI-powered IT support systems using machine learning models address inefficiencies in manual IT support by enabling rapid, scalable, and efficient resolution of IT issues across multiple client devices.

JP2026539063APending Publication Date: 2026-11-19ATERA NETWORKS LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
JP2026525094
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-10-26
Filing Date
2024-10-28
Publication Date
2026-11-19

AI Technical Summary

Technical Problem

Existing IT support methods rely heavily on human expertise, leading to constrained response times, scalability issues, and inefficiencies in resolving IT issues across multiple client devices.

Method used

A system utilizing AI and machine learning models to automatically identify, determine, and generate solutions to IT problems on remote client devices, leveraging cloud-based resources for scalable and rapid problem resolution.

Benefits of technology

Enables efficient, rapid, and scalable resolution of IT issues without human intervention, overcoming limitations of manual IT support by utilizing high-performance computing and generative ML models to generate effective solution profiles.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2026539063000001_ABST
    Figure 2026539063000001_ABST
Patent Text Reader

Abstract

A system for automatically resolving information technology (IT) problems, comprising multiple client devices, each running its own local IT support agent, and one or more remote servers connected to the multiple client devices via one or more networks and adapted to run an IT support engine. The IT support engine is adapted to receive support requests from the local IT support agents running on one or more client devices to resolve one or more IT problems related to the client devices, collect system data related to the IT problems, and use machine learning models applied to analyze the system data to automatically determine one or more solution profiles containing a set of actions to implement one or more solutions to resolve the IT problems, and to send the solution profiles to one or more agents adapted to automatically execute the set of actions to resolve the IT problems.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] (CROSS-REFERENCE TO RELATED APPLICATIONS) This application is a PCT International Application of U.S. Patent Application No. 18 / 383,947 filed on October 26, 2023, the entire disclosure of which is incorporated herein by reference.

[0002] The present invention, in some embodiments thereof, relates to resolving IT issues associated with remote client devices, and more specifically, but not exclusively, to using artificial intelligence (AI) to automatically resolve IT issues associated with remote client devices.

BACKGROUND ART

[0003] In the modern world, most enterprises, systems, infrastructures, and services are digitized and thus heavily dependent on computing resources.

[0004] Accordingly, IT professional support is an essential need and challenge for most organizations, companies, institutions, etc., to efficiently resolve IT issues encountered by employees, users, customers, subcontractors and the like, to ensure effective, reliable, rapid availability, accessibility and the like of products and services provided by such entities.

[0005] The description of the background art provided herein is for the purpose of generally presenting the context of the present disclosure. To the extent described in this Background Art section, the work of the present inventors, as well as aspects of the description that may not qualify as prior art at the time of filing, are not admitted explicitly or implicitly as prior art to the present disclosure.

SUMMARY OF THE INVENTION

[0006] According to a first aspect of the present invention, a system for automatically resolving information technology (IT) problems is provided, comprising a plurality of client devices, each running its own local IT support agent, and one or more remote servers connected to the plurality of client devices via one or more networks. The one or more remote servers are adapted to run an IT support engine for the following: - Receive assistance requests from a local IT support agent running on one or more of the client devices to resolve one or more IT issues related to one or more client devices. - Collect system data related to one or more IT issues. - Automatically determine one or more solution profiles using one or more machine learning models applied to the analysis of system data. One or more solution profiles contain a set of actions that implement one or more solutions to resolve one or more IT problems. - Send one or more resolution profiles to one or more agents that are adapted to automatically perform a set of actions to resolve one or more IT issues.

[0007] A second aspect of the present invention provides a method for automatically resolving information technology (IT) problems, which includes using an IT assistance engine run by one or more servers that are connected via a network to a plurality of client devices, each running its own local IT assistance agent. The IT assistance engine is adapted to the following: - Receive assistance requests from a local IT support agent running on one or more of the client devices to resolve one or more IT issues related to one or more of the client devices. - Collect system data related to one or more IT issues. - Automatically determine one or more solution profiles using one or more machine learning models applied to the analysis of system data. One or more solution profiles contain a set of actions that implement one or more solutions to resolve one or more IT problems. - Send one or more resolution profiles to one or more agents that are adapted to automatically perform a set of actions to resolve one or more IT issues.

[0008] A third aspect of the present invention provides a client device comprising one or more processors adapted to run a local IT support agent adapted to communicate with a remote IT support engine run by one or more remote servers over one or more networks. The local IT support agent is adapted to: - Identify one or more IT issues related to the client device. - Send a request for assistance to a remote IT support engine to resolve one or more IT problems. - Receive one or more resolution profiles from the remote IT support engine. One or more resolution profiles are automatically determined by the remote IT support engine using one or more machine learning models applied to analyze system data collected by the remote IT support engine in relation to one or more IT problems. One or more resolution profiles include a set of actions that implement one or more solutions to resolve one or more IT problems. - Automate the execution of a set of actions to resolve one or more IT problems.

[0009] In the first, second, and / or third embodiments, further implementations, one or more IT problems relate to one or more of the following: - One or more functional components of one or more client devices. Each of these functional components is implemented via hardware, software, and / or a combination thereof. - One or more remote services that provide services to one or more client devices. - One or more infrastructures that provide services to one or more client devices.

[0010] In further implementations of the first, second, and / or third aspects, at least a portion of the system data is derived from one or more tests performed in accordance with one or more IT problems.

[0011] In the first, second, and / or third embodiments, further implementations, one or more of the tests are defined by one or more machine learning models trained to estimate the usefulness of system data derived from one or more tests in solving one or more IT problems.

[0012] In the first, second, and / or third embodiments, further implementations, one or more agents adapted to automatically perform a set of actions to solve one or more IT problems are members of a group that includes local IT assistance agents run by one or more client devices, and / or one or more remote agents run by one or more servers having access to one or more remote services and / or infrastructure that provide services to one or more of the client devices.

[0013] In further implementations of the first, second, and / or third aspects, the system data includes informational data collected by a local IT support agent running on one or more client devices. The informational data includes one or more operational parameters associated with one or more of the multiple functional components, software applications, services, and / or accounts associated with each client device. Each of the multiple functional components is implemented via hardware, software, and / or a combination thereof.

[0014] In further implementations of the first, second, and / or third embodiments, the system data includes service data collected from one or more remote services that provide services to one or more client devices.

[0015] In further implementations of the first, second, and / or third aspects, system data includes user behavior data collected by a local IT support agent. User behavior data logs user interactions with one or more client devices.

[0016] In further implementations of the first, second, and / or third aspects, the system data includes user input related to one or more IT problems. The user input collected by the local IT support agent is provided by the user of one or more client devices.

[0017] In further implementations of the first, second, and / or third aspects, the IT assistance engine is adapted to apply natural language processing to interpret user input.

[0018] In the optional implementations of the first, second, and / or third embodiments, the IT assistance engine is further adapted to invoke one or more chat interfaces to interact with users of one or more client devices and receive user input.

[0019] In the first, second, and / or third embodiments, further implementations, one or more machine learning models use one or more datasets that associate one or more of multiple solution profiles with each of multiple client device IT problems.

[0020] In further implementations of the first aspect, the second aspect, and / or the third aspect, one or more of the resolution profiles associated with one or more of the plurality of client device IT issues each include a respective set of actions defined by one or more technicians to resolve the one or more IT issues.

[0021] In further implementations of the first aspect, the second aspect, and / or the third aspect, one or more of the machine learning models include one or more generative machine learning models adapted to automatically define a set of actions for resolving one or more IT issues.

[0022] In optional implementations of the first aspect, the second aspect, and / or the third aspect, the IT assistance engine is further adapted to generate a summary of the IT issue based on system data for display by a technician client device used by one or more technicians, to enable the one or more technicians to adjust one or more resolution profiles.

[0023] In optional implementations of the first aspect, the second aspect, and / or the third aspect, the IT assistance engine is further adapted to store system data in one or more online storage resources accessible to one or more technicians using a client device running a web-based graphical user interface.

[0024] In optional implementations of the first aspect, the second aspect, and / or the third aspect, the IT assistance engine is further adapted to estimate the operating state of one or more of the plurality of functional components associated with one or more of the plurality of client devices, based on system data collected in relation to the one or more client devices. Each of the plurality of functional components is a local functional component of one or more of the client devices, and / or a remote functional component that provides services to one or more of the client devices.

[0025] In a further implementation of the first aspect, the second aspect, and / or the third aspect, the local IT assistance agent is implemented by a member of the group consisting of a web page rendered by one or more web browsers, a web application, and / or a local application.

[0026] Other systems, methods, features, and advantages of the present disclosure will become apparent to those skilled in the art upon review of the following drawings and detailed description. All such additional systems, methods, features, and advantages are intended to be included within this description, within the scope of the present disclosure, and protected by the appended claims.

[0027] Unless otherwise defined, all technical and / or scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention pertains. Although methods and materials similar or equivalent to those described herein can be used in the practice or testing of embodiments of the present invention, exemplary methods and / or materials are described below. In case of conflict, the patent specification, including definitions, will control. In addition, the materials, methods, and examples are illustrative only and are not necessarily intended to be limiting.

[0028] Implementation of the methods and / or systems of embodiments of the present invention may include automatically performing or completing selected tasks. Furthermore, according to the actual instrumentation and apparatus of the embodiments of the methods and / or systems of the present invention, several selected tasks may be implemented by hardware, software or firmware, or a combination thereof using an operating system.

[0029] For example, hardware for performing selected tasks according to embodiments of the present invention may be implemented as a chip or circuit. As software, selected tasks according to embodiments of the present invention can be implemented as a set of software instructions executed by a computer using any suitable operating system. In exemplary embodiments of the present invention, one or more tasks according to exemplary embodiments of the method and / or system described herein are performed by a data processor, such as a computing platform for executing a set of instructions. Optionally, the data processor includes volatile memory for storing instructions and / or data, and / or non-volatile storage devices for storing instructions and / or data, such as magnetic hard disks and / or removable media. Optionally, network connectivity is also provided. A display and / or a user input device such as a keyboard or mouse is also optionally provided.

[0030] Further areas of application of this disclosure will become apparent from the detailed description, claims, and drawings. The detailed description and specific examples are for illustrative purposes only and do not limit the scope of this disclosure.

[0031] This disclosure will be better understood from the detailed description and accompanying drawings. [Brief explanation of the drawing]

[0032] [Figure 1] This is a flowchart illustrating an exemplary process for automatically solving IT problems using machine learning models, according to several embodiments of the present invention. [Figure 2A] This is a schematic diagram illustrating an exemplary system for automatically solving IT problems using machine learning models, according to several embodiments of the present invention. [Figure 2B] This is a schematic diagram illustrating an exemplary system for automatically solving IT problems using machine learning models, according to several embodiments of the present invention. [Figure 3]This is a schematic diagram of exemplary components of a system for automatically solving IT problems using machine learning models, according to some embodiments of the present invention. [Figure 4] This is a schematic diagram illustrating an exemplary design of a system for automatically solving IT problems using machine learning models, according to some embodiments of the present invention. [Figure 5] This is a schematic diagram illustrating an exemplary design of a system for automatically solving IT problems using machine learning models, according to some embodiments of the present invention. [Figure 6] This is a schematic diagram illustrating an exemplary design of a system for automatically solving IT problems using machine learning models, according to some embodiments of the present invention. [Figure 7] This is a schematic diagram illustrating an exemplary design of a system for automatically solving IT problems using machine learning models, according to some embodiments of the present invention.

[0033] In drawings, reference numbers may be reused to identify similar and / or identical elements. [Modes for carrying out the invention]

[0034] In some embodiments thereof, the present invention relates to solving IT problems related to remote client devices, and more specifically, to using AI to automatically solve IT problems related to remote client devices, though not exclusively.

[0035] According to some embodiments of the present invention, methods, systems, apparatus, and computer software programs are provided for automatically resolving IT problems related to one or more client devices, such as desktops, laptops, servers, smartphones, tablets, smartwatches, and dedicated client devices.

[0036] In particular, AI in the form of one or more machine learning (ML) models is used to identify, determine, and / or generate solutions to one or more IT problems related to client devices.

[0037] A remote IT support system, typically a cloud-based system, can use one or more ML models, such as neural networks, classifiers, statistical classifiers, or support vector machines (SVMs), adapted to automatically determine and / or generate one or more solution profiles containing a set of actions that implement one or more solutions estimated to resolve each of multiple IT problems associated with one or more client devices.

[0038] Optionally, the IT support system may have access to one or more pre-trained generative ML models, such as ChatGPT® or Bard®, which can be prompted to compute solution profiles for one or more IT problems related to one or more client devices.

[0039] The ML model can determine and / or generate a solution profile based on an analysis of system data related to each IT problem of each client device, which may be collected from the client device and / or from one or more services and / or infrastructure providing services to the client device.

[0040] System data may include, for example, informational data collected by local IT support agents running on each client device, and this informational data may include, for example, one or more operational parameters related to one or more of the multiple functional components of each client device, such as hardware components, software components, and / or combinations thereof. In another example, system data may include informational data and / or service data collected from one or more remote services and / or infrastructure systems that provide services to each client device.

[0041] System data may further include user behavior data collected by local IT support agents, such as user interactions with the human-machine interface (HMI) of each client device, resources accessed by users of each client device (e.g., screens, web pages, applications, menus, etc.), and items selected, clicked, and / or pointed to by users.

[0042] System data may also include user input provided by the user of each client device, in particular user input provided in relation to one or more IT issues associated with each client device.

[0043] The system data associated with each IT problem may be injected into an ML model that can identify one or more root causes of the IT problem according to learned system data patterns, and thus generate one or more solution profiles that implement one or more solutions estimated to effectively solve each IT problem.

[0044] One or more ML models may be trained using one or more training datasets that associate system datasets related to multiple IT problems with each solution profile for solving the IT problems, such as solution profiles that have been used in the past and proven to solve the IT problems, or solution profiles defined by one or more experts (e.g., IT personnel, IT experts, etc.).

[0045] However, optionally, the ML model may include one or more generative ML models that can generate solution profiles based on a learned knowledge base of system data and IT solutions, technologies, protocols, and / or experience, rather than identifying predefined solution profiles.

[0046] Automatically resolving IT issues on client devices can offer significant advantages and benefits over existing IT support methods and systems.

[0047] Firstly, most current IT support methods rely heavily, if not entirely, on the manual skills, expertise, experience, and / or labor of human IT personnel, technicians, and / or specialists. Such manual IT support methods can be severely constrained in terms of response time, resolution time, and scalability due to the inherent limitations of limited human professional IT resources and the human capacity to analyze large amounts of system data.

[0048] By automatically resolving IT issues related to multiple client devices, IT problems can be efficiently resolved automatically without human intervention, thus efficiently overcoming the limitations of existing methods. In this way, IT problems can be resolved quickly with short response times because there is no need to wait for available IT personnel. Furthermore, because IT problems are automatically resolved using high-performance computing resources applied to the analysis of system data, the identification, determination, and / or generation of solution profiles for resolving IT problems can be performed extremely quickly, thus further reducing the overall response time for resolving IT problems.

[0049] Furthermore, because remote IT support systems, typically implemented via cloud resources, can easily scale to use varying amounts of computing and ML resources in response to changing IT support demands, automated IT problem solving can be highly scalable to support a vast number of client devices.

[0050] Furthermore, by applying generative ML models to generate solution profiles for solving IT problems, it is possible to obtain efficient solution profiles that were not previously used or devised, thus improving the performance and / or scope of automated IT support and extending the IT support domain.

[0051] Before describing in detail at least one embodiment of the present invention, it should be understood that the present invention is not necessarily limited in its application to the details of the structure and arrangement of components and / or methods described in the following description and / or shown in the drawings and / or examples. Other embodiments of the present invention are possible, or can be carried out or implemented in various ways.

[0052] As will be understood by those skilled in the art, aspects of the present invention can be embodied as systems, methods, or computer program products. Accordingly, aspects of the present invention can take the form of complete hardware embodiments, complete software embodiments (including firmware, resident software, microcode, etc.), or embodiments combining software and hardware embodiments, all of which are generally referred to herein as “circuits,” “modules,” or “systems.” Furthermore, aspects of the present invention can take the form of computer program products embodied in one or more computer-readable media in which computer-readable program code is embodied.

[0053] Any combination of one or more computer-readable media may be used. A computer-readable storage medium may be a tangible device capable of holding and storing instructions for use by an instruction execution device. A computer-readable storage medium may be, but is not limited to, electronic storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination thereof. A non-exhaustive list of more specific examples of computer-readable storage media includes portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disk read-only memory (CD-ROM), digital multipurpose disks (DVDs), memory sticks, floppy disks, mechanically encoded devices such as punched cards or grooved raised structures on which instructions are recorded, and any suitable combination thereof. The computer-readable storage media used herein should not be interpreted as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses passing through optical fiber cables), or transient signals themselves, such as electrical signals transmitted through wires.

[0054] Computer program code, including computer-readable program instructions embodied on a computer-readable medium, may be transmitted using any suitable medium, including but not limited to wireless, wired, fiber optic cable, RF, or any suitable combination thereof.

[0055] The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to each computing / processing device, or to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include copper transmission cables, optical transmission fibers, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface within each computing / processing device receives computer-readable program instructions from the network and transfers the computer-readable program instructions for storage in a computer-readable storage medium within each computing / processing device.

[0056] Computer-readable program instructions for performing the operation of the present invention may be written in any combination of one or more programming languages, such as assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, and state setting data, or they may be source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk and C++, and conventional procedural programming languages ​​such as the C programming language or similar programming languages.

[0057] Computer-readable program instructions can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or wide area network (WAN), or it may be connected to an external computer (for example, via the Internet using an Internet service provider). In some embodiments, electronic circuits, including, for example, programmable logic circuits, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), can execute computer-readable program instructions by utilizing state information of the computer-readable program instructions to personalize the electronic circuit in order to perform aspects of the present invention.

[0058] Aspects of the present invention will be described herein with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present invention. It will be understood that each block in the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0059] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, segment, or part of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative embodiments, the functions described in the blocks may be executed in an order different from the order shown in the figures. For example, two blocks shown consecutively may actually be executed substantially simultaneously, or these blocks may sometimes be executed in reverse order depending on the functions they relate to. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs a specified function or operation, or a combination of dedicated hardware and computer instructions.

[0060] Referring to the drawings, Figure 1 is a flowchart illustrating an exemplary process of automatically solving IT problems using a machine learning model, according to several embodiments of the present invention.

[0061] The exemplary process 100 may be executed by a local IT support agent run by one or more client devices to resolve one or more IT issues related to each client device.

[0062] In particular, a local IT support agent can collaborate with a remote IT support engine, which is run by one or more remote systems, servers, and / or services, to perform exemplary processes 120, i.e., using AI, i.e., using one or more ML models, to solve IT problems related to client devices.

[0063] The local IT support agent for each client device can issue one or more support requests to report one or more IT issues related to that client device. These one or more IT issues might relate, for example, to one or more functional components of each client device. Alternatively, they might relate to one or more services and / or infrastructure providing services to each client device.

[0064] In response to support requests received from the local IT support agent on each client device, the IT support engine can collect system data related to the reported IT problem. This system data may be collected, for example, from each client device, or from one or more systems, platforms, and / or services providing services to each client device.

[0065] The IT support engine can apply one or more ML models to the collected data to automatically determine one or more solutions that are estimated to solve an IT problem. The IT support engine can further calculate a set of actions and / or instructions to implement the solutions and send that set to one or more agents that are employed to automatically execute the set of actions in an attempt to solve the IT problem.

[0066] An agent adapted to receive and execute a set of actions to resolve an IT problem may include, for example, a local IT assistance agent run by each client device. In another example, one or more other agents, for example, an agent deployed in one or more of the systems, platforms, and / or services that provide services to each client device, may be adapted to perform an exemplary process 140 to receive and automatically execute a set of actions to resolve an IT problem.

[0067] See also Figures 2A and 2B, which are schematic diagrams of exemplary systems for automatically solving IT problems using machine learning models, according to some embodiments of the present invention.

[0068] As shown in Figure 2A, the exemplary IT support system 200 can be adapted to support one or more client devices (remote machines) 202, such as desktops, laptops, servers, smartphones, tablets, smartwatches, and dedicated client devices, in order to solve IT problems related to the client device 202.

[0069] A client device 202 may typically be associated with a user 204 who uses, operates, and / or interacts with the client device 202. However, one or more of the client devices 202 may be adapted to operate without human intervention, for example, as a server, network equipment unit (e.g., gateway, router, switch, etc.), security system and / or service (e.g., firewall service, IT system, etc.).

[0070] The client device 202 may have network connectivity to connect to one or more networks, which are network 206 as specified below herein, including one or more wired and / or wireless networks such as a local area network (LAN), wireless LAN (WLAN, e.g., Wi-Fi®), wide area network (WAN), metropolitan area network (MAN), cellular network, and the internet.

[0071] Optionally, one or more of the client devices 202 may connect to the network 206 via one or more infrastructure systems 208, such as network equipment systems, units and / or services, including gateways, routers, and switches, or security systems and / or services, including firewalls, access control units and / or services.

[0072] The client device 202 can communicate with the IT support system 200 via the network 206 to report any IT problems it may encounter and optionally receive commands from the IT support system 200 to automatically resolve these IT problems.

[0073] Additionally, one or more client devices 202 may communicate via network 206 with one or more remote services 210, such as email services, organizational accounts, databases, virtual private network (VPN) services, customer relationship management (CRM) systems, subscription accounts (e.g., video conferencing, social media, financial services, etc.).

[0074] As shown in Figure 2B, the IT support system 200, for example, a server, processing node, or cluster of processing nodes, may include a network interface 230 for connecting to the network 206, a processor 232 for executing processes 120, and a storage device 234 (program store) for storing data and / or code.

[0075] The network interface 230 may include one or more wired and / or wireless network interfaces, ports, and / or links, which are implemented by hardware, software, firmware, and / or a combination thereof for connecting to the network 206.

[0076] The same or different processors 232 may include one or more processing nodes and / or cores, optionally arranged for parallel processing, as a cluster and / or as one or more multicore processors.

[0077] The storage device 234 may include one or more non-temporary persistent storage devices, such as ROM, flash arrays, solid-state drives (SSDs), and hard drives (HDDs). The storage device 234 may also include one or more volatile devices, such as RAM components and caches. Optionally, the storage device 234 may further include one or more network storage devices accessible via the network interface 230, such as storage servers, network-accessible storage devices (NAS), network drives, and database servers.

[0078] The processor 232 can execute one or more software modules, such as processes, scripts, applications, (device) drivers, agents, utilities, tools, operating systems (OS), plugins, and add-ons, which are stored in a non-temporary medium (program store) such as a storage device 234 and each of these software modules contains multiple program instructions that are executed by one or more processors, including the processor 232.

[0079] The processor 212 can optionally integrate, utilize, and / or facilitate the integration of one or more hardware elements (modules) into and / or utilization of the IT support system 200, such as circuits, components, integrated circuits (ICs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), graphics processing units (GPUs), artificial intelligence (AI) accelerators, and the like.

[0080] Therefore, the processor 232 can execute one or more functional modules implemented using one or more software modules, one or more hardware modules, and / or a combination thereof.

[0081] For example, the processor 232 may run an IT assistance engine 220 to execute a process 120 for automatically determining a solution to an IT problem related to one or more of the client devices 202. In another example, the processor 232 may run one or more ML models to support the IT assistance engine 220, such as a neural network (NN), classifier, statistical classifier, or support vector machine (SVM) adapted to automatically determine one or more solutions to each of several IT problems related to one or more of the client devices 202.

[0082] Optionally, the IT support system 200, in particular the processor 232, may run one or more agents 224, which are designated remote agents, to support the resolution of one or more IT problems related to one or more client devices 202, for example, by collecting system data related to an IT problem and performing actions to resolve the IT problem, as described in detail below herein. Optionally, the remote agents 224 run by the IT support system 200 may be integrated with the IT support engine 220 so that they can be deployed, started, and / or run as a single package.

[0083] It should be noted that each of the functional modules executed by processor 232, such as the IT support engine 220 and the remote agent 224, may be executed by processor 232 in such a way that any one or more processors of processor 232 can execute one or more and / or parts of the functional modules, or can optionally not be involved in the execution of any of the functional modules.

[0084] Optionally, the IT support system 200 can communicate with the client devices 202 via the network 202 to solve one or more IT problems related to one or more of the client devices 202, and may be utilized by one or more cloud computing services, platforms and / or infrastructure provided by one or more vendors, such as Google Cloud®, Microsoft Azure®, Amazon Web Services (AWS®), and Elastic Compute Cloud (EC2), IBM Cloud, etc., such as Infrastructure as a Service (IaaS), Platform as a Service (PaaS), and Software as a Service (SaaS).

[0085] Optionally, one or more of the remote services 210 and / or one or more of the infrastructure systems 208 may also run one or more remote agents 224 to execute process 140 to support the resolution of one or more IT problems related to one or more client devices 202, for example, by collecting system data related to one or more IT problems and taking actions to resolve one or more IT problems.

[0086] The remote agent 224 may be designed, implemented, and / or deployed to support the resolution of one or more IT problems using one or more integration, migration, and / or development methods, techniques, and / or means. For example, one or more remote agents 224 may be implemented and / or deployed using one or more plug-in modules or add-on packages that include IT problem-solving functionality. In another example, one or more remote agents 224 may be designed using one or more software development kits (SDKs) that include IT problem-solving functionality.

[0087] Each client device 202 may include a network interface 240, such as a network interface 230 for connecting to the network 206; a processor 242, such as a processor 232 for executing process 100; and a storage device 244, such as a storage device 234 (program store) for storing data and / or code.

[0088] One or more of the client devices 202, in particular a client device 202 associated with and operated by each user 204, may further include one or more user interfaces, namely a human-machine interface (HMI) for interacting with the user 204, such as a keyboard, mouse, touchscreen, touchpad, pointing device, display, speaker, earphone, microphone, haptic interface (e.g., fingerprint reader), etc., a user interface 246.

[0089] As described for network interface 230, network interface 240 may include one or more wired and / or wireless network interfaces, ports, and / or links, which are implemented by hardware, software, firmware, and / or a combination thereof for connecting to network 206.

[0090] Furthermore, similar to processor 232, the device may include one or more processing nodes and / or cores of the same or different type of processor 242, optionally arranged as a cluster and / or as one or more multi-core processors for parallel processing. The storage device 244 may include one or more non-volatile components, such as ROM, flash arrays, SSDs, etc., and / or one or more volatile components, such as RAM devices and cache components, etc.

[0091] The processor 242 can execute one or more software modules, each containing multiple program instructions stored in a non-temporary medium (program store) such as the memory device 234 and executed by one or more processors such as the processor 232. Optionally, one or more processors 242 in the client devices 202 can integrate, utilize, and / or facilitate the integration and / or utilization of one or more hardware elements (modules), such as circuits, components, ICs, ASICs, FPGAs, DSPs, GPUs, AI accelerators, etc., into and / or utilized by each client device 202.

[0092] Therefore, the processor 242 can execute one or more functional modules implemented using one or more software modules, one or more hardware modules, and / or a combination thereof. For example, the processor 242 of each client device 202 can execute an IT support agent 222 to execute a process 100 for solving IT problems associated with each client device 202.

[0093] The local IT support agent 222 may be implemented on each of the client devices using one or more architectures, designs, and / or deployments.

[0094] For example, a local IT support agent 222 run by one or more of the client devices 202 may include a standalone local application run by each client device 202, particularly by the processor 242 of each client device 202. In another example, the local IT support agent 222 run by one or more of the client devices 202 may be implemented by a web application, for example, hosted by one or more remote resources in the IT support system 200, and loaded and executed by the processor 242 of each client device 202. In yet another example, the local IT support agent 222 run by one or more of the client devices 202 may include, for example, a web browser (e.g., Chrome®, Edge®, Firefox®, etc.) adapted to load and render one or more web pages hosted by one or more remote resources in the IT support system 200 that implements the logic of the local IT support agent 222.

[0095] The local IT support agent 222 may include and / or visualize a user interface for interacting with the user 204, which may be presented and used via the user interface 246 of the client device 202. This user interface may include a visual interface such as a graphical user interface (GUI), an audio input and / or playback interface, a haptic interface, and so on. Furthermore, one or more of the user interfaces, for example, a GUI, may be implemented as a local GUI, a web-based GUI, and / or a combination thereof, depending on the architecture and / or deployment of the local IT support agent 222.

[0096] Each of the functional modules executed by the processor 242 of each client device 202, such as the IT support agent 222, may be executed by the processor 242 of each client device 202 in such a way that any one or more processors of the processor 242 may execute one or more and / or parts of the functional modules, or may optionally not be involved in the execution of any of the functional modules.

[0097] Each client device 202 may include one or more functional components 248, for example, N functional components 248(1) to 248(n) that are utilized by hardware, software, firmware, and / or a combination thereof to provide the functionality of each client device. Naturally, the functional components 248 may include a network interface 240, a processor 242, and a storage device 244.

[0098] The functional component 248 may include one or more hardware components, such as a network device, a memory device, a processing circuit, or a communication cable. In another example, the functional component 248 may include one or more software components (modules) executed by the processor 242 and / or one or more other functional components 248 of the client device 202, such as the Android® OS, a communication application (e.g., a communication stack), a remote access agent (e.g., a web browser, a VPN agent, a web application, a local CRM agent), a control application (e.g., an IoT management tool, an infrastructure monitor, and a control agent). In yet another example, the functional component 248 may include a combination of one or more hardware components and one or more software components.

[0099] Optionally, one or more technicians 254, such as IT personnel, IT specialists, or administrators, may use one or more client devices 252, such as client device 202, to connect to the network 206 and interact with the IT support engine 220. Optionally, one or more technicians 254 using client devices 252 may further access one or more client devices 202, one or more remote services 210, and / or one or more infrastructure systems 208.

[0100] For brevity, processes 100, 120, and 140 are described as solutions to an IT problem related to a single client device 202. However, as may be apparent to those skilled in the art, process 100 may be performed by multiple client devices 202, and process 120, and optionally process 140, may be replicated, extended, and / or scaled to solve IT problems related to multiple client devices 202, so this should not be construed as an limitation.

[0101] As shown in 102, the process 100 executed by the local IT support agent 222 of the client device 202 begins with the local IT support agent 222 identifying one or more IT problems related to the client device 202.

[0102] An IT problem may relate to one or more malfunctions and / or issues encountered in relation to the client device 202 and / or its associated user 204. In particular, an IT problem may relate to one or more of the functional components 248 of the client device 202, one or more software applications run by the client device 202, one or more services accessed by the client device 202, one or more accounts associated with the client device 202, and so on. Furthermore, since at least a portion of an IT problem may relate to the interaction and communication between the client device 202 and one or more remote services 210, an IT problem may also relate to one or more of the infrastructure systems 208.

[0103] For example, a specific IT issue may be associated with the inability of user 204 associated with a client device to log in to and / or access their account using their credentials, regardless of whether the account is for a remote service 210 (e.g., email service, remote desktop, cloud service, etc.) and / or a local account for an application and / or service (e.g., secure service, encrypted document, etc.) running locally by the client device 202. In another example, a specific IT issue may be associated with the inability of client device 202 to access network 206 and / or a specific remote service 210. In yet another example, a specific IT issue may be associated with the failure of an invocation of one or more applications or agents, such as a VPN client, a text editing application, or a simulation model.

[0104] However, IT issues are not limited to problems and / or malfunctions related to client device 202. Rather, IT issues may further include one or more requests to add, include, extend, remove, and / or manipulate the capabilities, functions, and / or features of client device 202, and / or make them available to the relevant user 204. For example, a particular IT issue may relate to a request to add the relevant user 204 to a specific administrative group. In another example, a particular IT issue may relate to installing and configuring a VPN agent on client device 202. In yet another example, a particular IT issue may relate to a request to create a new account for user 204 in one or more remote services 210, or to change the credentials of one or more accounts, etc.

[0105] IT problems can be identified by the local IT support agent 222 using one or more methods, techniques, and / or algorithms.

[0106] For example, user 204 can interact with local IT support agent 222 to report one or more IT problems. For this purpose, user 204 can interact with local IT support agent 222 via one or more HMI interfaces, such as the GUI of user interface 246. In another example, one or more functional components 248, such as applications, agents, device drivers, etc., can report malfunctions to local IT support agent 222 via one or more system calls, OS routines, application programming interface (API) functions, etc. In yet another example, local IT support agent 222 can detect one or more IT problems by continuously and / or periodically monitoring one or more functional components 248, one or more remote services 210, and / or one or more infrastructure systems 208. For example, local IT support agent 222 can probe one or more functional components 248 and issue one or more system calls or API calls, etc., to determine their functional and / or operational status accordingly. In another example, the local IT support agent 222 may send one or more messages, requests, and / or signals to one or more of the services 210 and / or infrastructure systems 208 to evaluate their availability, connectivity, functionality, etc., and to determine their functional and / or operational status accordingly.

[0107] As shown in 104, the local IT support agent 222 can send support requests, such as messages, packets, and alerts, via the network 206 to the IT support system 200, in particular the IT support engine 220, to report identified IT problems and request support to resolve the IT problems.

[0108] As shown in 122, the IT support engine 220 can receive support requests sent from the client device 202 by the local IT support agent 222.

[0109] As shown in 124, in response to receiving a support request, the IT support engine 220 can collect system data related to the IT problem reported in the support request.

[0110] System data may include informational data collected by the local IT support agent 222 and transmitted to the IT support engine 220, for example, as shown in 106. The informational data collected by the local IT support agent 222 may include, for example, one or more operational parameters relating to one or more of the multiple functional components 248 of the client device 202, such as hardware components, software components, and / or combinations thereof. For example, the informational data collected by the local IT support agent 222 may include one or more operational parameters, state data, and / or settings of one or more functional components such as a network adapter, processing device, network port, application, and communication protocol. In another example, the informational data collected by the local IT support agent 222 may include one or more operational parameters, state data, credentials, and settings of one or more accounts (e.g., user accounts in a remote system) and / or services (e.g., a mail server) accessed by the client device 202.

[0111] In another example, system data may include informational data, specifically service data collected from one or more remote services 210 (e.g., mail servers, CRM systems, online financial services, etc.) or one or more infrastructure systems 208 (e.g., routers, gateways, etc.). Such informational data may include, for example, one or more operational parameters, state data, and / or settings related to one or more of the remote services 210 and / or infrastructure systems 208. For example, informational data related to a particular remote service 210, such as a mail server, may include, for example, availability, responsiveness, access latency, access port settings, etc. In another example, informational data related to a particular infrastructure system 208, such as a gateway, may include, for example, one or more network parameters defined in the router, such as domain, address range, protocol support, etc.

[0112] This informational data related to the remote service 210 and / or infrastructure system 208 is collected by a remote agent 224 deployed and executed by one or more of the remote service 210 and / or infrastructure system 208, as shown in 142, for example, and transmitted by the remote agent 224 to the IT support engine 220 via the network 206. In another example, the IT support engine 220 can access one or more of the remote service 210 and / or infrastructure system 208 to directly obtain at least some informational data related to one or more of the remote service 210 and / or infrastructure system 208.

[0113] Furthermore, at least a portion of the system data may be derived by one or more tests performed on system tests, checks, and / or probes (health checks) to collect system data, such as informational data. Such tests may include, for example, functional tests on functional components that may be relevant to the reported IT problem, such as one or more of the functional components 248, one or more of the remote services 210, and one or more of the infrastructure systems 208. One or more of the tests performed to collect, acquire, and / or derive system data may be performed automatically, for example, by the IT support engine 220 and / or local IT support agent 222 directly communicating with one or more hardware and / or software components of the resource being tested. However, one or more tests may include interaction with user 204, thereby instructing user 204 via user interface 246 to perform one or more actions and / or operations to support the execution of one or more test procedures for collecting, deriving, and / or identifying system data that may be useful and / or relevant in relation to the reported IT problem. Such system data may include, for example, informational data derived from tests, user input provided by user 204 in response to commands, and combinations thereof.

[0114] Therefore, the IT support engine 220 can initiate and / or instruct the initiation of one or more system tests in order to collect system data, for example, informational data related to the IT problem. For example, suppose the reported IT problem is related to a network connectivity issue. In such a case, the IT support engine 220 can initiate one or more tests, for example, hardware test procedures, on one or more network controllers of the client device 202 in order to collect informational data related to the network hardware.

[0115] In another example, the IT support engine 220 may initiate one or more software and / or protocol-level tests, such as "ping" or "open socket," to collect informational data related to the connection status of the client device 202.

[0116] In another example, system data may include user behavior data collected by the local IT support agent 222, particularly user behavior data that may be related to reported IT problems. User behavior data may capture, record, and / or log interactions between the associated user 204 and the client device 202 and / or content rendered by the client device 202. For example, user behavior data may include interactions between user 204 and the HMI of the user interface 246, accessed resources (e.g., screens, web pages, applications, menus, etc.), selected items (e.g., clicked and / or pointed icons, links, menu items, etc.). For example, assuming user 204 interacts with the client device 202 to engage, use, and / or operate one or more applications, such as an email application, an electrical design tool, a software programming suite, etc., user behavior data collected by the local IT support agent 222 may include interactions between user 204 and the applications via the user interface 246, such as mouse movements, keyboard strokes, and voice commands. User behavior data may further include timing data, such as the speed of interactive actions (mouse, keyboard, etc.) and the time gap between interactions. User behavior data may also be logged over time of the interactions of the relevant user 204, and the interactions can be arranged in order according to their timing and sequence.

[0117] In another example, system data may include user input related to reported IT problems, provided by one or more users 204 of client device 202. User input may be collected, for example, by a local IT support agent 222 and transmitted to the IT support engine 220 via the network 206. Optionally, in deployments where the local IT support agent 222 is implemented by a web application, a web-based GUI, and / or a web page executed by the IT support engine 220 and rendered by the local IT support agent 222, the IT support engine 220 can collect user input provided by users 204.

[0118] Optionally, the IT support engine 220 and / or the local IT support agent 222 may be adapted to invoke one or more chat interfaces, such as a GUI-based chatbot or a voice-based chatbot, to interact with the user 204 of the client device 202 and receive user input.

[0119] User input may include, for example, a description of an IT problem identified and / or encountered by user 204 using client device 202. In another example, user input may include one or more contextual details related to the IT problem identified and / or encountered by user 204, such as the operating mode of one or more functional components 248, one or more attributes of the execution environment of client device 202, such as suspected effects, phenomena, and / or signs, one or more execution goals and / or targets of the functional components 248, and the execution load of client device 202.

[0120] The IT support engine 220 can apply natural language processing (NLP) to interpret user input. For example, the IT support engine 220 can analyze user input and / or parts thereof by applying one or more NLP algorithms to identify the user input.

[0121] Optionally, user input may be provided by user 204 in response to one or more queries and / or questions presented to user 204 via user interface 246 by, for example, local IT support agent 222 and / or IT support engine 220. For example, the IT support engine 220 can generate one or more guiding questions that may be presented to user 204 by local IT support agent 222 via user interface 246, depending on the reported IT problem.

[0122] System data collected by the IT support engine 220 in relation to one or more IT problems, such as the scope of the data, the type of data, and the details of the data, may be predefined by one or more technicians, such as IT technicians 254. In another example, system data collected by the IT support engine 220 in relation to one or more IT problems may be defined by the IT support engine 220 or by one or more IT technicians 254 based on knowledge and / or experience formed from past IT problem solving using other IT tools, etc.

[0123] Optionally, system data (type, scope, parameters, etc.) collected by the IT assistance engine 220 in relation to one or more IT problems and / or parts thereof may be learned and / or predicted over time using one or more ML models adapted and / or trained to identify system data patterns related to one or more of the IT problems and to learn which system data may be relevant to deriving possible solutions for each IT problem. Such ML models are described in more detail later in step 126. In such cases, at least some of the system data collected by the IT assistance engine 220 may be indicated, directed, and / or identified by one or more of the trained ML models. For example, suppose a reported IT problem is related to the inability to access a particular shared drive and / or folder. In such a case, the IT assistance engine 220 may collect system data such as informational data defined, identified, and / or directed by one or more ML models trained to learn which system data may be relevant, useful, and / or beneficial in determining the root cause of the access problem and determining possible solutions for solving the access problem.

[0124] Furthermore, the IT support engine 220 can initiate, execute, and / or launch one or more system checks, tests, and / or probes (health checks) defined, directed, and / or proposed by one or more ML models that can be further adapted and / or trained to determine which tests may generate system data that may be relevant to deriving possible solutions for solving one or more IT problems. For example, suppose a reported IT problem is related to a malfunction in an application run by a client device 202 to retrieve data from a remote network resource, such as a database. In such a case, the IT support engine 220 can execute one or more tests (health checks) indicated, defined, and / or directed by one or more ML models, which presume that these tests may generate system data, such as informational data, that may be useful and / or beneficial in determining the root cause of a data retrieval problem and determining possible solutions for solving the access problem. For example, the ML model may determine and / or infer, based on learned data patterns related to an IT problem, that access privilege tests and / or queries performed to test the credentials used by client devices 202 to access the database and their access rights can yield system data useful in determining the potential root cause of the access problem. Thus, the IT support engine 220 can initiate access privilege tests and / or queries in accordance with the instructions and / or suggestions received from the ML model.

[0125] As shown in 126, the IT support engine 220 can automatically determine one or more solution profiles using one or more ML models applied to analyze the collected system data. Each solution profile may include a set of actions that implement one or more solutions to resolve the reported IT problem.

[0126] According to some embodiments, the IT support engine 220 can inject system data into one or more ML models, such as neural networks, classifiers, and SVMs, which are adapted to learn multiple system data patterns typical of IT problems related to the client device 202.

[0127] ML models can be further adapted to predict and / or estimate one or more solutions to an IT problem and, accordingly, generate one or more solution profiles that include a set of actions to implement the solutions estimated to solve the IT problem.

[0128] Therefore, an ML model applied to multiple system datasets collected in relation to multiple IT problems can estimate and / or predict one or more root causes of IT problems that are characterized, i.e., can be reflected by, and / or can trigger, each system dataset, respectively. The ML model can be further adapted accordingly to generate one or more solution profiles that implement one or more solutions predicted to resolve the estimated root causes and thus resolve the IT problems. In particular, the ML model can be applied to a feature vector, each containing multiple features extracted from each of the system datasets by one or more feature extraction engines, which are interchangeable feature extractors.

[0129] The feature extractor may be used as one or more independent ML models, such as neural networks, and / or integrated as one or more layers of one or more neural networks that facilitate the ML models themselves.

[0130] Thus, by using an ML model applied to system data collected in relation to the IT problem reported by the local IT support agent 222, one or more solution profiles can be automatically determined that implement one or more solutions estimated to resolve the reported IT problem. Specifically, the ML model may be applied to a feature vector containing multiple features extracted by a feature extractor from the system data collected in relation to the reported IT problem. In deployments where the feature extractor is integrated and / or utilized by the ML model, the collected system data may be directly injected into the ML model.

[0131] ML models can be trained in one or more supervised training sessions, unsupervised training sessions, and / or semi-supervised training sessions using one or more training datasets containing multiple training samples. Training samples may include, for example, annotated (labeled) training samples for supervised training, unlabeled training samples for unsupervised training, and / or combinations of labeled and unlabeled training samples for semi-supervised training.

[0132] Each training sample may contain its own system dataset, and each system dataset is optionally associated with one or more IT problems having root causes characterized by its own system dataset.

[0133] Furthermore, at least some of the training samples, such as labeled training samples, may associate one or more of several solution profiles with each of several IT problems associated with a client device, such as client device 202. Thus, an ML model trained with such training samples can adapt, reconcile, and / or evolve to learn which solution profile can be applied to solve each IT problem.

[0134] For example, one or more resolution profiles may be associated with one or more IT problems based on past experience in which solutions and actions applied and performed to solve the IT problems were recorded in the process. Thus, each of the previously recorded resolution profiles for successfully solving one or more IT problems, in particular the set of actions in each resolution profile, can be associated with each IT problem and used to train an ML model.

[0135] In another example, one or more solution profiles associated with one or more IT problems may include a set of actions defined by one or more technicians, such as IT personnel, specialists, or administrators, to solve each respective IT problem. For example, one or more sets of actions in a solution profile may be derived from a record of actions previously applied by one or more technicians to solve one or more IT problems. In yet another example, one or more sets of actions in a solution profile may be estimated by one or more technicians to solve one or more IT problems.

[0136] The ML model may optionally be used by a script and adapted to automatically determine and / or select one or more resolution profiles containing a set of actions retrieved from one or more resolution repositories, such as a database. Optionally, the ML model may be adapted to determine and / or select one or more resolution profiles for one or more IT problems based on accounts associated with client device 202, such as user 204's account, accounts assigned to client device 202, and accounts in the organization to which client device 202 and / or user 204 are associated. Each account may be associated with one or more respective resolution profiles, each containing a set of actions presumed to resolve the reported IT problem.

[0137] Optionally, the ML models may include one or more generative ML models adapted to automatically define a set of estimated, predicted, and / or selected resolution profile actions to resolve the IT problem reported by the local IT support agent 222.

[0138] Generative ML models can be pre-trained and adapted to generate one or more solution profiles that are not duplicates of previous solution profiles that have been applied in the past and / or estimated by engineers to solve one or more IT problems. Rather, based on historical knowledge and data, generative ML models can estimate, predict, infer, and / or derive one or more sets of actions to implement one or more solutions that are estimated to solve one or more IT problems, and generate one or more solution profiles accordingly.

[0139] According to one embodiment, the ML models used by the IT-assisted engine 220 may include one or more online AI services, such as ChatGPT or Bard, that use one or more pre-trained generative ML models, infrastructure, and / or architectures adapted to provide answers in response to natural language queries, also known as prompts.

[0140] For example, an IT support engine 220 communicating with an online generative ML model using its APIs via network 206 can inject one or more prompts (queries) into the online generative ML model that include system data collected in relation to an IT problem reported by a local IT support agent 222. In response, the online generative ML model may estimate the root cause of the IT problem and generate one or more solution profiles that include one or more sets of actions that implement one or more solutions estimated and / or predicted to resolve the IT problem.

[0141] As shown in 128, the IT support engine 220 can send one or more resolution profiles generated, inferred, and / or determined by the ML model to one or more agents adapted to automatically execute a set of actions in the resolution profile to automatically resolve an IT problem related to the client device 202.

[0142] For example, as shown in 108, the IT support engine 220 can send one or more resolution profiles to a local IT support agent 222 run by the client device 202. As shown in 110, the local IT support agent 222 can apply the set of actions from the received resolution profile to resolve the IT problem.

[0143] For example, suppose an IT problem related to client device 202 is a network connectivity issue, which the ML model estimates, based on system data, is caused by a malfunction and / or problem in the client device 202's network interface. Furthermore, suppose a specific resolution profile determined using the ML model includes a set of actions such as reconfiguring, resetting, or updating the network interface. In such a case, the IT support engine 220 may send the specific resolution profile to a local IT support agent 222, which can perform the set of actions on client device 202 to resolve the network connectivity issue.

[0144] Optionally, one or more sets of actions in a resolution profile may include instructions for user 204 of client device 202 to perform one or more actions. For example, suppose the IT problem associated with client device 202 is a network connectivity problem, which the ML model estimates, based on system data, is caused by a critical failure in the network interface connecting client device 202 to network 206 via a network cable. Furthermore, suppose a particular resolution profile determined using the ML model includes a set of actions for connecting the network cable to a different network interface on client device 202. In such a case, the set of actions in the particular resolution profile may include instructions for user 204 to disconnect the network cable from the currently connected network interface and connect the cable to the other network interface.

[0145] In another example, as shown in 144, the IT support engine 220 can send one or more of the resolution profiles to one or more of the remote agents 224, which are run by one or more of the infrastructure systems 224, and which can apply the set of actions of the received resolution profiles to resolve the IT problem, as shown in 146.

[0146] For example, suppose an IT problem related to client device 202 is a network connectivity problem, which the ML model estimates, based on system data, is caused by a problem and / or misconfiguration of a specific infrastructure device 208, such as a gateway connecting client device 202 to network 206. Furthermore, suppose a specific resolution profile determined using the ML model includes a set of actions to reconfigure, reset, and / or update the gateway. In such a case, the IT assistance engine 220 can send the specific resolution profile to a remote agent 224, which is run by the router, and which can perform the set of actions on the gateway to resolve the network connectivity problem of client device 202.

[0147] In another example, as also shown in 142 and 146, the IT support engine 220 can send one or more of the resolution profiles to one or more of the remote agents 224, which are run by one or more of the remote services 210, and which can apply the set of actions of the received resolution profiles to resolve the IT problem.

[0148] For example, suppose an IT problem related to client device 202 is an access problem to a specific remote service 210, such as a restricted access database, which the ML model infers from system data is caused by, for example, a failure to update the credentials of user 204 of client device 202 in the restricted access database. Furthermore, suppose a specific resolution profile determined using the ML model includes querying a specific access control database and / or record to determine whether user 204 is permitted to access the restricted access database, and if so, a set of actions to update the access control module of the restricted access database to include user 204's credentials. In such a case, the IT support engine 220 can send the specific resolution profile to a remote agent 224 run by the restricted access database, which can, for example, execute a set of actions to resolve the access problem of user 204 using client device 202.

[0149] In another example, as shown in 130, the IT support engine 220 may send a specific resolution profile to a remote agent 224, which is run by the IT support engine 220 and optionally has access to remote services and / or infrastructure that are presumed to be the source of an IT problem. For example, if it is presumed that an access failure problem is caused by an access control database / record and access control module, and assuming that the IT support engine 220 has the authority to access and manipulate (write, adjust, etc.) these modules, the IT support engine 220 may perform a set of actions to resolve the access problem for user 204 using client device 202.

[0150] In another example, the IT support engine 220 may send multiple resolution profiles to multiple agents, such as a local IT support agent 222 and one or more remote agents 224, or multiple remote agents 224. Each agent may automatically execute its own set of actions in the resolution profile so that the agents can collaboratively resolve IT issues related to the client device 202.

[0151] For example, suppose an IT problem related to client device 202 is a network connectivity issue, which the ML model estimates, based on system data, is caused by a misconfiguration of ports on client device 202 and a specific infrastructure device 208, such as a gateway connecting client device 202 to network 206. Furthermore, suppose the solution determined using the ML model involves reconfiguring the port numbers on client device 202 and the gateway to be the same port. In such a case, the IT support engine 220 can send a first resolution profile containing a set of actions for reconfiguring the port number on client device 202 to the local IT support agent 222, and a second resolution profile containing a set of actions for reconfiguring the port number on the gateway to the remote agent 224, which is run by the gateway. The local IT support agent 222 and the remote agent 224 can each execute the set of actions in their respective resolution profiles to jointly resolve the network connectivity issue of client device 202.

[0152] Optionally, one or more actions defined by one or more of the resolution profiles may require the approval of user 204 associated with client device 202. In such cases, entities performing the set of actions defined by the resolution profile, such as a local IT support agent 222, a remote agent 224, and / or the IT support engine 220, may prompt user 204 to request approval of the action before performing it. For example, suppose one or more actions in a particular resolution profile require accessing, retrieving, and / or using personal data associated with user 204, such as credentials or personal information, user 204 may be asked to approve and / or authorize such actions.

[0153] Optionally, the IT support engine 220 may store at least a portion of the system data collected in connection with one or more IT problems related to the client device 202. In particular, the IT support engine 220 may store the system data and / or a portion thereof in one or more online storage resources accessible via the network 206 to one or more of the technicians 254 using the client device 252.

[0154] For example, the IT support engine 220 can establish, create, and / or update a ticketing system controlled by one or more ticketing engines that tracks, collects, and stores one or more support tickets containing data related to IT problems reported by client devices 202. The IT support engine 220 can further update one or more support tickets for IT problems to include additional data related to each IT problem, such as a set of solutions, resolution profiles, and / or actions generated and / or determined by an ML model to resolve each IT problem.

[0155] Optionally, the IT support engine 220 may be further adapted to generate IT problem summaries for one or more IT problems related to the client device 202, based on system data collected in relation to each IT problem. For example, an IT problem summary for one or more IT problems may include system data related to each IT problem and / or parts thereof. In another example, an IT problem summary for one or more IT problems may further include solutions and / or solution profiles that were decided, selected, and / or generated to resolve each IT problem.

[0156] Optionally, the IT support engine 220 may apply one or more generative ML models, language models, and / or NLP algorithms to generate an IT problem summary of one or more IT problems related to the client device 202.

[0157] Each of the technician's client devices 252 may run one or more software modules that include and / or visualize a user interface that enables the technician 254 to view, browse, search, and / or access system data related to stored data, such as IT issues, support tickets, IT issue summaries, etc. For example, one or more of the client devices 252 used by one or more of the technicians 254 may run a GUI, such as a local GUI, a web-based GUI, and / or a combination thereof, to enable the technician 254 to access stored data.

[0158] Optionally, one or more technicians 254 using client device 252 may adjust one or more of the solution profiles generated and / or determined by the ML model for one or more IT problems related to client device 202. The technicians 254 may scrutinize the solution profiles via a GUI, such as a web-based GUI, and adjust the solution profiles by, for example, changing one or more actions, or deleting, adding, and / or replacing one or more actions.

[0159] Optionally, the IT support engine 220 may be adapted to check whether a reported IT problem has been resolved by a set of actions defined by a resolution profile applied to resolve the problem. For example, after a resolution profile has been applied to resolve an IT problem, the IT support engine 220 may collect and analyze additional system data related to and / or indicating the IT problem in order to determine, evaluate, and / or confirm that the reported IT problem has been resolved. For example, suppose a particular reported IT problem is related to a network connectivity issue in client device 202. In such a case, after one or more resolution profiles have been applied to resolve the problem, the IT support engine 220 can collect additional system data indicating the network connectivity of client device 202 and accordingly determine whether the network connectivity issue has been resolved.

[0160] Furthermore, if the reported IT problem is not resolved by the resolution profile, the IT support engine 220 may optionally generate one or more additional resolution profiles based on additional system data collected in relation to the IT problem, as described in steps 124 and 126 of process 120, in order to attempt to resolve the IT problem, and may instruct the engine to apply the additional resolution profiles as described in steps 110, 130 and / or 146.

[0161] Please refer to Figure 3, which shows a schematic diagram of exemplary components of a system for automatically solving IT problems using machine learning models, according to some embodiments of the present invention.

[0162] A local IT support agent, such as a local IT support agent 222, may be run by a client device, such as a client device 202, used by a related user, such as a user 204, to resolve one or more IT problems related to the client device 202. In particular, when the local IT support agent 222 detects one or more IT problems, it may request an IT support engine, such as an IT support engine 220, to resolve the identified IT problems.

[0163] An IT support engine 220, which is run by an IT support system such as an IT support system 200, can apply one or more ML models 302 adapted to automatically identify, infer, derive, and / or determine one or more solution profiles that include a set of actions that implement one or more solutions estimated to resolve an IT problem reported by a local IT support agent 222.

[0164] Optionally, the IT support engine 220 and / or ML model 302 may determine one or more solutions according to a solution database that stores possible solutions for multiple IT problems that have been applied in the past and have proven to successfully resolve the IT problem at least partially.

[0165] Depending on the circumstances, user 204 may interact with local IT support agent 222 and / or IT support engine 220, for example, via a user interface such as a GUI, optionally via a web-based GUI 312, to provide user input and optionally receive commands to support the resolution of IT problems.

[0166] Optionally, one or more technicians, such as technician 254 using a client device such as client device 252, may also interact with the IT assistance engine 220 to help resolve one or more IT issues related to one or more client devices 202 used by each user 204. Typically, technician 254 may have access to a ticketing system 310 controlled by one or more ticketing engines that track, collect, and store multiple support tickets containing data related to IT issues reported by client devices 202. Thus, technician 254 can retrieve data related to reported IT issues, including active IT issues currently being processed, and track, monitor, and / or coordinate one or more solutions determined by the IT assistance engine 220 to resolve one or more of the logged IT issues.

[0167] Optionally, the IT support engine 220 may be further adapted to monitor and estimate the operational status (health) of one or more functional components associated with one or more of the multiple client devices 202. The monitored functional components may include one or more local functional components, such as the functional component 248 of each client device 202. In another example, the monitored functional components may include one or more remote functional components of a system, platform, and / or service that provides services to each client device 202. For example, the remote functional components may include one or more functional components of one or more remote services 210 that provide services to each client device 202. In yet another example, the remote functional components may include one or more functional components of one or more infrastructure systems 208 that provide services to each client device 202.

[0168] For this purpose, the IT support engine 220 can collect system data, such as informational data related to one or more client devices, and in particular system data related to one or more functional components related to one or more of the multiple client devices 202.

[0169] System data collected for health check evaluation (i.e., type, scope, parameters, settings, details, etc.) may be predefined and / or learned by the IT support engine 220, in particular by an AI model, according to historical system data patterns identified as indicating proper and / or failed operation of functional components. Optionally, system data and / or informational data, such as data type, data scope, operation parameters, settings, details, etc., may be adjusted, selected, and / or defined according to an organizational knowledge base established, accumulated, and / or learned over time by one or more organizations, such as a company, research institute, office, etc., to which the user 204 and / or client device 202 are associated.

[0170] To evaluate the operating state of functional components, the IT support engine 220 can collect system data according to one or more operating modes. For example, the IT support engine 220 can collect system data related to one or more client devices, in particular system data related to one or more functional components related to one or more of the multiple client devices 202, periodically, continuously, and / or on demand, i.e., in response to a trigger.

[0171] The IT support engine 220 can analyze collected system data using, for example, one or more ML models to evaluate whether monitored functional components operate as expected according to appropriate execution patterns, or whether the system data may indicate one or more potential defects or IT problems.

[0172] For effective monitoring and estimation (health check) of the operational status of one or more of the multiple functional components associated with the client device 202, the IT support engine 220 may need to interact with one or more of the remote agents 224, for example, by collecting system data used to estimate the operational status and applying one or more actions to resolve one or more potential problems. As previously stated herein, the remote agents 224 may be designed, implemented, and / or deployed to support this operational status evaluation using one or more integration, migration, and / or development methods, techniques, and / or means, such as plug-in modules, add-on packages, SDKs, etc., which include operational status evaluation monitoring, logic, and / or control functions.

[0173] The IT support engine 220 and the local IT support agent 222 may be designed, built, deployed, and / or operated according to one or more design architectures and implementation configurations.

[0174] Please refer here to Figures 4, 5, 6, and 7, which are schematic diagrams illustrating exemplary designs of systems for automatically solving IT problems using machine learning models, according to some embodiments of the present invention.

[0175] As shown in Figure 4, an exemplary local IT support agent, such as the local IT support agent 222, which is executed by a client device such as client device 202, may be implemented using multiple functional modules, in particular software modules such as, for example, IT widgets, local agents, agent command packages, user behavior packages, and one or more other packages.

[0176] The local IT support agent 220 can communicate with exemplary cloud-based IT support engines, such as the IT support engine 220 which is composed of multiple functional modules, particularly software modules, an IT interface engine adapted to control interactions with associated users such as client devices 202 and users 204, and an IT logic engine which includes the core logic of the IT support engine 220.

[0177] The IT widget may be adapted, for example, to facilitate a user interface such as a GUI for interacting with user 204 and receiving user input, particularly user input provided in relation to one or more IT issues concerning a client device. The IT widget may be further adapted to send user input provided by the user to a remote IT support engine 220, in particular an IT interface engine that facilitates a chat engine driving the GUI interface in the IT widget.

[0178] The IT interface engine may be further adapted to deliver, transfer, and / or transmit user input to the IT logic engine, which includes the core logic of the IT support engine 220, and thus to collect system data related to IT issues related to the client device and to communicate with one or more AI models, such as the ML model 302.

[0179] The user behavior package can log user interactions between the user and the client device and / or content presented by the client device, particularly user interactions related to one or more IT issues associated with the client device, and send the user behavior data to the IT logic engine.

[0180] The IT logic engine can collect informational data, including system data related to one or more IT issues associated with a client device, such as user input, user behavior data, and operational data related to one or more functional components of one or more services that provide services to the client device.

[0181] The AI ​​model may be adapted to determine a solution profile for solving IT problems related to client devices based on system data received from an IT logic engine. In particular, the IT logic engine can issue queries (prompts, requests) to the AI ​​model that may include IT problems, especially system data related to those IT problems. Based on the received IT problems, the AI ​​model can generate embeddings that may include feature vectors containing features (values) extracted from the received system data.

[0182] Embeddings, i.e., feature vectors generated by an AI model, may be used by an IT logic engine and / or AI model to perform semantic search in an IT solution space to identify one or more best-matching feature vectors related to solutions for IT problems. The matching vectors can indicate that the relevant solutions can be applied to solve the IT problems characterized and / or mapped by their respective system data.

[0183] The IT logic engine can send a solution profile—which compares one or more solutions estimated by the AI ​​model, particularly the actions to implement the solutions—to the local agent and / or IT widgets of client devices that can take action to resolve the IT problem.

[0184] As previously stated herein, the operational state (health) of one or more functional components associated with a client device may be estimated independently of IT issues, for example, continuously, periodically, and / or in response to a trigger.

[0185] For this purpose, the agent command package may be adapted to collect system data, such as informational data and user behavior data, independently of IT issues, and to transmit the collected system data to the IT logic engine. Optionally, the agent command package may collect system data according to instructions of the IT logic engine, which can define system data requirements according to operational status (health) checks defined for client devices.

[0186] Based on user input received from IT widgets and system data received from agent command packages, which are optionally combined, the IT logic engine can optionally use an AI model to estimate the operational state, i.e., health, of one or more functional components associated with the client device.

[0187] As shown in Figure 5, users can optionally interact with a cloud-based IT assistance engine, particularly an IT interface engine, via a user portal that functions as a Tier 1 chat interface, rather than via an IT widget run on a client device. Furthermore, users can access the user portal using a different client device than the one to which the IT issue relates. The AI ​​assistance engine may also maintain a ticketing module, such as a database, record, or system, that stores multiple support tickets tracking multiple IT issues related to multiple client devices. One or more users can view, browse, review, and optionally update one or more of these support tickets via the user portal.

[0188] As shown in Figure 6, one or more human technicians, such as technician 254, using each client device, such as client device 252, can access the IT support engine. For example, technician 254 may launch a management application on client device 252 that can run a ticket copilot engine, enabling the technician to access one or more support tickets to track, intervene in, and / or follow up on one or more IT issues.

[0189] As shown in Figure 7, a cloud-based IT support engine, particularly an IT logic engine, may be constructed from multiple software modules, each designed and adapted to perform its respective functions. At least some of the software modules may communicate with each other to transfer data between them. For example, a health check module may define operational status (health) checks for execution by one or more client devices, and optionally also define the types and scope of system data to be collected and distribute them to the client device's agent command package. In another example, a solutions module may be deployed to identify, determine, and / or select one or more solutions from a solutions space that are estimated to effectively resolve each IT problem associated with a client device. In yet another example, a behavior analyzer may be run that analyzes user behavior data logged by, for example, a client device's user behavior package and provides insights into possible solutions for resolving one or more IT problems associated with one or more client devices.

[0190] The descriptions of various embodiments of the present invention are presented for illustrative purposes only and are not intended to be exhaustive or limitful to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the embodiments described. The terms used herein have been selected to best describe the principles, practical applications, or technical improvements to the technologies available on the market of the embodiments, or to enable those skilled in the art to understand the embodiments disclosed herein.

[0191] It is anticipated that many related systems, methods, and computer programs will be developed during the term of the patent granted based on this application, and the scope of the terms client devices, ML models, and pre-trained generative models is intended to a priori include all such new technologies.

[0192] As used herein, the term "approximately" means ±10%.

[0193] The terms "comprise," "comprising," "include," "including," and "have," and their conjugations, mean "include but not limited to these." This term encompasses the terms "consist of" and "essentially become from."

[0194] The phrase "essentially derived from" means that the composition or method may include additional components and / or steps, but only if the additional components and / or steps do not substantially alter the basic and novel features of the claimed composition or method.

[0195] As used herein, the singular forms "a," "an," and "the" include plural references unless otherwise explicitly indicated by the context. For example, the terms "compound" or "at least one compound" may include multiple compounds, including mixtures thereof.

[0196] The term “exemplary” is used herein to mean “serving as an example, case, or illustration.” Any embodiment described as “exemplary” should not necessarily be construed as being preferable or advantageous to other embodiments, nor should it be construed as precluding the incorporation of features from other embodiments.

[0197] The term “optionally” is used herein to mean “provided in some embodiments and not in other embodiments.” Any particular embodiment of the present invention may include several “optionally” features, provided that such features do not conflict with each other.

[0198] Throughout this application, various embodiments of the present invention may be presented in range form. It should be understood that the range form description is for convenience and brevity only and should not be interpreted as an inflexible limitation on the scope of the invention. Therefore, the range description should be considered to specifically disclose all possible subranges and the individual numbers within those ranges. For example, a range description such as 1-6 should be considered to specifically disclose subranges such as 1-3, 1-4, 1-5, 2-4, 2-6, 3-6, and the individual numbers within those ranges, e.g., 1, 2, 3, 4, 5, and 6. This applies regardless of the width of the range.

[0199] Where a numerical range is indicated herein, it always means that it includes any cited number (fraction or integer) within the indicated range. The phrases “the range between” the first indicated number and the second indicated number, and “the range from” the first indicated number to the second indicated number, are used interchangeably herein and mean that they include the first indicated number and the second indicated number, as well as all fractions and integers between them.

[0200] For clarity, certain features of the Invention described in the context of separate embodiments may be provided in combination in a single embodiment. Conversely, various features of the Invention described in the context of a single embodiment for brevity may also be provided separately, in any suitable partial combination, or as appropriate in any other described embodiment of the Invention. Certain features described in the context of different embodiments should not be considered essential features of those embodiments unless the embodiments are unable to function without those elements.

[0201] While the present invention has been described in conjunction with its specific embodiments, it is evident that many alternative, modified, and variant forms are apparent to those skilled in the art. Therefore, it is intended that all such alternative, modified, and variant forms, which fall within the spirit and broad scope of the appended claims, are encompassed.

[0202] All publications, patents, and patent applications referenced herein are incorporated herein by reference in their entirety, as if each individual publication, patent, or patent application were specifically and individually referenced when it is mentioned that they are incorporated herein by reference. Furthermore, any citation or specification of any reference in this application should not be construed as an acknowledgment that such reference is available as prior art of the present invention. Section headings, insofar as they are used, should not necessarily be construed as restrictive. Furthermore, any priority documents of this application are incorporated herein by reference in their entirety.

[0203] The term "non-temporary computer-readable medium" does not include temporary electrical or electromagnetic signals that propagate through a medium (such as on a carrier wave). Non-exclusive examples of non-temporary computer-readable mediums include non-volatile memory circuits (such as flash memory circuits, erasable programmable read-only memory circuits, or mask read-only memory circuits), volatile memory circuits (such as static random-access memory circuits or dynamic random-access memory circuits), magnetic storage media (such as analog or digital magnetic tapes or hard disk drives), and optical storage media (such as CDs, DVDs, and Blu-ray discs).

[0204] The term “set” generally refers to a group of one or more elements. The elements of a set do not necessarily have to share any common property or be of the same kind. The phrase “at least one of A, B, and C” should be interpreted as meaning a non-exclusive OR (A OR B OR C) and not as “at least one of A, at least one of B, and at least one of C.” The phrase “at least one of A, B, or C” should be interpreted as meaning a non-exclusive OR (A OR B OR C).

Claims

1. A system for automatically solving information technology (IT) problems, Multiple client devices, each running its own local IT support agent, At least one remote server is connected to the plurality of client devices via at least one network in a communicable manner, The at least one remote server is equipped with, The local IT support agent, which is run by at least one of the plurality of client devices, receives a request for assistance to resolve at least one IT problem related to the at least one client device. Collect system data related to at least one of the aforementioned IT problems, Using at least one machine learning model applied to analyze the system data, at least one solution profile is automatically determined, which includes a set of actions that implement at least one solution to solve the at least one IT problem. Send the at least one resolution profile to at least one agent that is adapted to automatically execute the set of actions to solve the at least one IT problem. A system adapted to run an IT support engine.

2. The aforementioned at least one IT problem is, The aforementioned at least one client device comprises at least one of a plurality of functional components, each of which is implemented via hardware, software, and / or a combination thereof. At least one remote service that provides services to the aforementioned at least one client device, At least one infrastructure providing services to the aforementioned at least one client device, The system according to claim 1, relating to at least one of the following.

3. The system according to claim 1, wherein at least a portion of the system data is derived from at least one test performed in accordance with the at least one IT problem.

4. The system according to claim 3, wherein the at least one test is defined by at least one machine learning model trained to estimate the usefulness of system data derived from the at least one test in solving the at least one IT problem.

5. The system according to claim 1, wherein the at least one agent adapted to automatically perform the set of actions to solve the at least one IT problem is a member of a group comprising the local IT support agent run by the at least one client device and the at least one remote agent run by the at least one server having access to the at least one remote service and / or infrastructure that provides services to the at least one client device.

6. The system according to claim 1, wherein the system data includes information data collected by the local IT support agent, the information data includes at least one operational parameter, software application, service, and / or account related to at least one client device, each of the plurality of functional components being implemented via hardware, software, and / or a combination thereof.

7. The system according to claim 1, wherein the system data includes service data collected from at least one remote service that provides services to the at least one client device.

8. The system according to claim 1, wherein the system data includes user behavior data collected by the local IT support agent, and the user behavior data logs user interactions with the at least one client device.

9. The system according to claim 1, wherein the system data includes user input related to the at least one IT problem, and the user input collected by the local IT support agent is provided by the user of the at least one client device.

10. The system according to claim 9, wherein the IT support engine is adapted to apply natural language processing to interpret the user input.

11. The system according to claim 9, wherein the IT support engine is further adapted to invoke at least one chat interface to interact with the user of the at least one client device and receive the user input.

12. The system according to claim 1, wherein the at least one machine learning model uses at least one dataset that associates at least one of a plurality of solution profiles with each of a plurality of client device IT problems.

13. The system according to claim 12, wherein at least one of the resolution profiles associated with at least one of the plurality of client device IT problems comprises each set of actions defined by at least one technician to solve the at least one IT problem.

14. The system according to claim 1, wherein the at least one machine learning model includes at least one generative machine learning model adapted to automatically define the set of actions for solving the at least one IT problem.

15. The system according to claim 1, wherein the IT support engine is further adapted to generate an IT problem summary based on the system data for display on a technician client device used by at least one technician, thereby enabling the at least one technician to adjust the at least one solution profile.

16. The system according to claim 1, wherein the IT support engine is further adapted to store the system data in at least one online storage resource accessible to at least one technician using a client device running a web-based graphical user interface.

17. The system according to claim 1, wherein the IT support engine is further adapted to estimate the operating state of at least one of a plurality of functional components associated with at least one of the plurality of client devices based on system data collected in relation to the at least one client device, and each of the plurality of functional components is a local functional component of the at least one client device and / or a remote functional component that provides services to the at least one client device.

18. The system according to claim 1, wherein the local IT support agent is implemented by a member of a group consisting of a web page, a web application, and a local application, which are rendered by at least one web browser.

19. A method for automatically solving information technology (IT) problems, This involves using an IT support engine run by at least one server, which is connected to multiple client devices, each running its own local IT support agent, via at least one network. The IT support engine includes, The local IT support agent, which is run by at least one of the plurality of client devices, receives a request for assistance to resolve at least one IT problem related to the at least one client device. Collect system data related to at least one of the aforementioned IT problems, Using at least one machine learning model applied to analyze the system data, at least one solution profile is automatically determined, which includes a set of actions that implement at least one solution to solve the at least one IT problem. Send the at least one resolution profile to at least one agent that is adapted to automatically execute the set of actions to solve the at least one IT problem. A method adapted to that.

20. It is a client device, At least one processor adapted to run a local IT assistance agent adapted to communicate with a remote IT assistance engine run by at least one remote server via at least one network. The local IT support agent is equipped with, Identify at least one IT problem related to the client device, A request for assistance to solve at least one of the aforementioned IT problems is sent to the remote IT support engine. The remote IT support engine receives at least one solution profile, the at least one solution profile being automatically determined by the remote IT support engine using at least one machine learning model applied to analyze system data collected by the remote IT support engine in relation to the at least one IT problem, and the at least one solution profile including a set of actions for implementing at least one solution to solve the at least one IT problem. The set of actions is automatically executed to solve at least one of the aforementioned IT problems. Client devices that are adapted to this.