System, computer implementation method, and computer program (entity assignment in automated issue resolution)

Abstract

To solve problems that resolving a problem / event in an IT environment / system often needs much labor, and is inefficient, or can be both.SOLUTION: Various systems and methods are presented herein regarding automatically identifying one or more entities for assignment to resolving an issue and / or removing an entity from a group of entities assigned to resolve the issue. The issue can relate to an information technology / computer-based environment. The entities can be subject matter experts, having expertise identified to be related to the issue. A summary of the issue and activity relating to resolving the issue can be automatically generated and supplied to an entity who is being onboarded after the project is underway to resolve the issue. By implementing automated assignment / removal of entities, efficiency of the resolution is improved.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The subject disclosure relates to automatically identifying and engaging entities to assist in solving problems in information technology (IT) environments. Summary of the Invention [Problem to be solved by the invention]

[0002] Resolving problems / events in an IT environment / system can often be both labor-intensive and inefficient. [Means for solving the problem]

[0003] The following presents a summary to provide a basic understanding of one or more embodiments described herein. This summary is not intended to identify key or critical elements or to delineate any scope of different embodiments and / or the claims. The sole purpose of this summary is to present some concepts in a simplified form as a prelude to the more detailed description presented herein.

[0004] In one or more embodiments described herein, systems, devices, computer-implemented methods, methods, apparatus, and / or computer program products are presented that facilitate automatically identifying entities to be assigned or revoked involvement in resolving a problem.

[0005] According to one or more embodiments, a system for assigning or revoking an entity's involvement in solving a problem is provided. The system may comprise a memory operatively coupled to the system, where the memory stores computer-executable components, and a processor for executing the computer-executable components stored in the memory. The computer-executable components may include an initial entity component configured to: identify first content related to the problem; identify second content in at least one prior problem solution based on the first content, where the first content and the second content are similar; further identify a first entity associated with the second content; and further assign the first entity to initiate a process to solve the problem. In an embodiment, the first content may be included in information initially compiled about the problem. In another embodiment, the problem may be an event in an information technology system.

[0006] In another embodiment, the computer-executable components may further include an entity recommendation component configured to identify third content related to the problem, where the third content may be a digital entry submitted by the first entity while attempting to resolve the problem. The entity recommendation component may be further configured to identify a second entity to participate in the resolution of the problem based on the third content, and assign the second entity to resolve the problem. The entity recommendation component may be further configured to identify fourth content, where the fourth content is generated in a digital conversation between the first entity and the second entity, where the digital conversation is related to the resolution of the problem. The entity recommendation component may be further configured to identify a third entity to participate in the resolution of the problem based on the fourth content, and further assign the third entity to join the first entity and the second entity in resolving the problem.

[0007] In a further embodiment, the computer-executable components may further include a summarization component configured to: identify a first time, where the first time is a time that the third entity was assigned to resolving the problem; further identify a second time, where the second time is the time that resolving the problem was initiated; further determine activities performed by the first entity and the second entity in resolving the problem between the first time and the second time; generate a summary of the activities performed by the first entity and the second entity between the first time and the second time; and provide the summary to the third entity. In another embodiment, the summarization component may be further configured to receive an operational role of the third entity; and configure the summary based on the operational role of the third entity.

[0008] In another embodiment, the first entity, the second entity, and the third entity comprise a group of entities assigned to solve the problem. In a further embodiment, the computer-executable components further include an entity revocation component configured to further monitor the digital conversation between the group of entities to identify a period of time during which the first entity in the group of entities does not participate in the conversation, determine whether the period of time exceeds a threshold period of time, and remove the first entity from the group of entities based on the period of time exceeding the threshold period of time.

[0009] In further embodiments, the entity recommendation component may be further configured to further monitor the digital conversation between the second entity and the third entity, determine that the digital conversation involves the first entity, and further reassign the first entity to the group of entities that resolve the problem.

[0010] In further embodiments, the summary component may be further configured to: (a) identify a third time, where the third time is a time allocated to resolving the problem by the first entity excluded from the group of entities; (b) identify a fourth time, where the fourth time is a current time at which resolution of the problem is being performed by the second entity and the third entity; (c) determine activities performed by the second entity and the third entity in resolving the problem between the third time and the fourth time; (d) generate a second summary of the activities performed by the second entity and the third entity between the third time and the fourth time; and (e) provide the second summary to the first entity.

[0011] In another embodiment, the entity revocation component may be configured to further monitor the digital conversation between the group of entities to identify a number of consecutive messages in the digital conversation during which the first entity in the group of entities did not generate a message in the digital conversation, further determine whether the number of consecutive messages exceeds a threshold number of messages, and remove the first entity from the group of entities assigned to solving the problem based on the number of consecutive messages exceeding the threshold number of messages.

[0012] In other embodiments, the elements described in connection with the disclosed system may be embodied in different forms, such as a computer-implemented method, a computer program product, or other forms. In an embodiment, a computer-implemented method may be executed by a device operatively coupled to a processor, where the computer-implemented method may comprise identifying a first entity to initiate a solution to a current problem, where the first entity may be identified based on a previous problem to which the first entity was previously assigned being similar to the current problem, and assigning the first entity to initiate a solution to the current problem, where the current problem relates to the performance of an information technology operation.

[0013] In a further embodiment, the computer-implemented method may further include analyzing digital content created by the first entity while attempting to resolve the problem; identifying one or more prior activities, where the prior activities involve a second entity; determining that the one or more prior activities relate to the digital content; and further recommending that the second entity assist the first entity in resolving the problem.

[0014] In another embodiment, the computer-implemented method may further include monitoring activity of the first entity and the second entity in attempting to solve the problem, comparing activity of the second entity in attempting to solve the problem, determining that the second entity is no longer engaged in attempting to solve the problem, and further canceling the engagement of the second entity in solving the problem. In an embodiment, the determining that the second entity is no longer engaged in attempting to solve the problem may be based on at least one of a period of inactivity or an amount of digital content generated.

[0015] The computer-implemented method may further comprise determining an engaged time, where the engaged time may be the time that the second entity joined the first entity in attempting to solve the problem. The computer-implemented method may further comprise determining unobserved activity undertaken by the first entity between initiation of solving the problem and the engaged time, where the unobserved activity is activity performed by at least the first entity in solving the problem, further generating a summary of the unobserved activity, and further providing the summary of the unobserved activity to the second entity.

[0016] Another embodiment may further include a computer program product stored on a non-transitory computer readable medium and comprising machine executable instructions that, in response to being executed, cause a machine to perform operations including: identifying a first entity to begin solving a current problem, where the first entity is identified based on a previous problem to which the first entity was previously assigned being similar to the current problem; and assigning the first entity to begin solving the current problem, where the current problem relates to performing an information technology operation.

[0017] In further embodiments, the operations may further include analyzing digital content created by the first entity while attempting to resolve the problem; identifying one or more prior activities, where the prior activities involve a second entity; determining that the one or more prior activities relate to the digital content; and further recommending that the second entity assist the first entity in resolving the problem.

[0018] In further embodiments, the operations may further include monitoring activity of the first entity and the second entity in attempting to resolve the problem, comparing activity of the second entity in attempting to resolve the problem, determining that the second entity is no longer engaged in attempting to resolve the problem; and further withdrawing engagement of the second entity in resolving the problem.

[0019] In another embodiment, the operations may further include determining an engaged time, where the engaged time is the time that the second entity joined the first entity in attempting to resolve the problem, further determining unobserved activity undertaken by the first entity between the start of resolution of the problem and the engaged time, where the unobserved activity is activity performed by at least the first entity in resolving the problem. The operations may further include identifying an operational role of the second entity, generating a summary of the unobserved activity, where the summary is generated based on the operational role of the second entity, and providing the summary of the unobserved activity to the second entity. [Brief description of the drawings]

[0020] In the Detailed Description section below, one or more embodiments are described with reference to the following drawings.

[0021] [Figure 1] 1 illustrates a system that may be utilized to automatically assign one or more entities to assist in solving problems in an IT environment, according to one or more embodiments.

[0022] [Diagram 2] FIG. 2 is a schematic diagram providing a high-level overview of a dataset being modified for application in a fusion language model, in accordance with one or more embodiments presented herein.

[0023] [Diagram 3] A schematic diagram illustrating the operation of each component for automatically identifying and recommending one or more entities to initiate a resolution of a problem, according to one or more embodiments, is presented.

[0024] [Figure 4] A schematic diagram illustrating the operation of respective components for automatically recommending the addition of one or more entities to resolve a problem is presented, in accordance with one or more embodiments.

[0025] [Diagram 5] A schematic diagram illustrating the operation of respective components for automatically identifying and revoking the involvement of one or more entities in resolving a problem, according to one or more embodiments, is presented.

[0026] [Figure 6] FIG. 1 is a schematic diagram illustrating the processing of one or more messages having associated entities as part of respective entity recommend / entity retract operations in accordance with one or more embodiments.

[0027] [Figure 7]FIG. 2 is a schematic diagram illustrating the processing of one or more messages having associated entities as part of a respective entity recommendation / entity revocation operation according to one or more embodiments.

[0028] [Figure 8] FIG. 2 is a schematic diagram illustrating summary generation for an entity according to an embodiment.

[0029] [Figure 9] 1 illustrates a computer-implemented methodology for automatically assigning entities to projects for solving problems and / or automatically removing entities from projects for solving problems, according to one or more embodiments.

[0030] [Figure 10] 1 illustrates a computer-implemented methodology for automatically and initially assigning entities to projects to solve problems, according to one or more embodiments.

[0031] [Figure 11] 1 illustrates a computer-implemented methodology for automatically recommending / assigning entities to projects for solving problems, according to one or more embodiments.

[0032] [Figure 12] 1 illustrates a computer-implemented methodology for automatically generating summaries of activity not observed by an entity while resolving a problem, according to one or more embodiments.

[0033] [Figure 13] 1 illustrates a computer-implemented methodology for automatically removing entities currently assigned to a project for resolving a problem, according to one or more embodiments.

[0034] [Figure 14]FIG. 1 illustrates an exemplary schematic block diagram of a computing environment with which the disclosed subject matter may at least partially interact / be implemented, in accordance with various aspects and implementations of the present subject disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0035] The following detailed description is merely illustrative and is not intended to limit the embodiments and / or the application or uses of the embodiments, nor is it intended to be bound by any of the express and / or implied information presented in the preceding Background section or Summary section and / or Detailed Description section.

[0036] One or more embodiments will now be described with reference to the drawings, in which like reference numerals are used to refer to like elements throughout. In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a more thorough understanding of one or more embodiments. However, it will be apparent that in various cases one or more embodiments may be practiced without these specific details.

[0037] The ranges A n and 1-i are used herein to denote a plurality of respective devices, components, statements, attributes, etc., where n and i are any positive integers.

[0038] Resolving problems / events in an IT environment / system can often be both labor intensive and inefficient. For example, in traditional IT operations, when an operational problem is detected, multiple entities (e.g., subject matter experts, developers, database administrators, network administrators, and the like) may be assigned to resolve the problem, whereby such assignment may involve random assignment of each entity.

[0039] Although various automated artificial intelligence (AI) (also known as AIOps) and machine learning (ML) technologies, techniques, operations, processes, etc. can be applied to collect data related to the problem and generate a "story" to provide information on aspects such as what is the problem? where the problem is detected (e.g., fault location), which systems / services are affected by the problem? and similar matters, poor implementation of subject matter experts, etc., can still lead to inefficient / expensive resolution of the problem. For example, a convened team of subject matter experts may be over-represented in terms of number of team members due to the randomness of the way in which entities are selected to troubleshoot the problem, and further, certain team members may have skill sets that are useful for addressing the right parts of the problem, while in other cases, those team members may have little or no involvement in the resolution of the problem, yet such team members are still included in the team working on the problem resolution. Thus, team members may be unnecessarily up-to-date / informed about how the resolution of the problem is going, when in fact their attention may be focused on other matters that are no longer related to the resolution of the said problem.

[0040] Thus, in a non-exhaustive list, if a problem arises, the following advantages are available:

[0041] (a) only the entity / entities that have some level of direct involvement in resolving the issue are brought on board (e.g., from the initiation of dispute resolution when a problem is detected);

[0042] (b) when the resolution of a problem is undertaken, do not include entities (e.g., necessary subject matter experts) in the team until they are needed and promptly report on the work done to date in resolving the problem;

[0043] (c) if the particular expertise of a particular entity is no longer relevant to addressing the issue, then that entity's involvement in the issue-solving process is effectively scaled back / cancelled, e.g., to enable that entity to address other issues; and

[0044] (d) If an entity was previously involved in a project and is temporarily no longer involved in the project (e.g., their involvement was cancelled), and their involvement is now needed again, the entity can be recruited and quickly briefed on the work that was done on resolving the issue while they were not involved.

[0045] According to various embodiments presented herein, the AIOps component may be configured to generate an initial overview / story of the problem and known circumstances, etc., which the AIOps component further reviews to automatically determine one or more entities that may be assigned to resolving the problem. During the resolution of the problem, any discussion between the respective entities toward resolving the problem may be further analyzed / reviewed (e.g., by the respective AIOps components) to determine whether (a) another entity with the requisite skills should be engaged in resolving the problem, and / or (b) whether any entity currently assigned to the project but who no longer has adequate input in the project may leave the project to perform other tasks. At any point in time, for example, when an entity that was not initially involved in the project joins the team and / or rejoins the project and thus may not be aware of the work that was done in their absence, a summary of the work that was done may be provided to the entity to enable the entity to focus their attention on the problem as quickly as possible.

[0046] While various embodiments presented herein relate to resolving problems / events in an IT environment / system, it should be understood that various embodiments are not so limited and may apply to any operation / process that may assign / remove an entity from a task as a function of identifying one or more entities associated with the task / function. Additionally, while various embodiments are directed to entities that are human, the entity may be in any applicable form. For example, the entity may be an automated process that may be utilized / cancelled as needed to resolve the problem.

[0047] Turning now to the drawings, FIG. 1 illustrates a system 100 that may be utilized to automatically assign one or more entities to assist in problem resolution in an IT environment, according to one or more embodiments. The system 100 includes a problem 105 that has been identified as needing to be addressed / resolved, which may be in an initial open state, an open problem 105U, and a subsequent problem resolution state 105R. The activity related to the resolution of the problem 105U is also referred to herein as a "project." As illustrated in FIG. 1, the resolution of the problem 105 may involve the open problem 105U being applied / input to an issue resolution system (IRS) 110, which may include various computer-executable components, techniques, processes, and the like configured to assist in the resolution of the problem 105U, e.g., transition the open problem 105U to a resolved problem 105R, e.g., with intelligent assignment and revocation of the involvement of one or more entities in the resolution of the problem 105.

[0048] FIG. 1 presents a high level description of IRS 110 and the structure / operation of each communicatively coupled component contained therein, various embodiments of which will be further described / illustrated in subsequent figures / descriptions.

[0049] As shown, the IRS 110 may include a problem resolution component (IRC) 115 that may be configured to identify respective entities (e.g., subject matter experts) that are included / excluded from one or more stages / processes / actions involved in achieving the resolved problem 105R. The IRC 115 may be communicatively coupled and further configured to utilize various other components, actions, processes, etc. in the resolution of the problem 105U. In an embodiment, a conversation component may be utilized to compile / archive one or more conversations 126A-n related to the resolution of the problem 105U. In an embodiment, one or more conversations 126A-n may be taking place (e.g., at respective times) between respective entities 136A-n involved in an attempt to achieve the resolved problem 105R. As will be further described, a conversation 126A-n may be comprised of more than one conversational topic / subject, for example, a conversation 126A-n may be comprised of a collection of threads 127A-n, for example, a first thread 127A may have a subject directed to network latency while a second thread 127B may have a subject directed to how client data is received / processed. As will be further described, the topic / subject of each thread 127A-n may be isolated and utilized to identify / determine which entities 136A-n should be involved in solving the problem 105U, when the involvement of the entities 136A-n should occur, the focus of attention of each entity 136A-n, and the like.

[0050] The IRC 115 may be further coupled to an initial entity component 135. The initial entity component 135 may be configured to review the problem information 106A-n and may be further configured to identify respective entities 136A-n that will be initially recruited / engaged / employed in the initial stages of resolving the open problem 105U. As will be further described, the initial entity component 135 may be configured to identify respective entities 136A-n by matching previous problems 138A-n (e.g., content, parameters, activities, etc.) that the respective entities 136A-n have worked on with the context regarding the open problem 105U as detailed in the problem information 106A-n.

[0051] The problem component 139 may reside and operate within the IRS 110, reside and operate within one or more of the communicatively coupled components within the IRS 110, or reside and operate externally to the IRS 110. The problem component 139 may be configured to compile information and generate prior problem 138A-n information. Additionally, during and after the resolution of the problem 105U, the problem component 139 may be configured to compile information regarding each activity / utterance / dialogue / etc. generated by each entity 136A-n in the resolution of the problem 105U, and to update the prior problem 138A-n information to ensure that the prior problem 138A-n information includes recent problem resolution activities performed by each entity for future use in identifying and recommending entities to be added to a subsequent problem resolution project. In an embodiment, the status component 170 may be utilized to update the status of the problem 105U. For example, status component 170 may be configured to receive input indicating that problem 105U has been resolved, the problem may be updated to become resolved problem 105R, and instructions may be sent from status component 170 to instruct problem component 139 to update previous problem 138A-n information with problem resolution activities performed by the respective entities while resolving problem 105U.

[0052] As shown in FIG. 1 , in an embodiment, the IRC 115 may be further communicatively coupled to an entity recommendation component 140 and an entity withdrawal component 145. As will be further described, as the attempt to resolve the problem 105U progresses, one or more conversations 126A-n may be reviewed (e.g., by the conversation component 120) and one or more determinations may be made by the entity recommendation component 140 as to whether an entity 136A-n having appropriate skills / knowledge for the current state / status of the problem 105U should be added to the team resolving the problem 105U. In another embodiment, the IRC 115 may be similarly communicatively coupled to an entity withdrawal component 145 configured to make a determination as to whether an entity 136A-n currently involved in the project should be removed from work on the project. In an embodiment, the summary component 150 may be configured to generate one or more summaries 152A-n, which may be provided to the entity 136A-n regarding work performed thus far in the attempt to resolve the problem 105U.

[0053] When an open problem 105U is resolved to create a resolved problem 105R, the resolved problem 105R may be received by the state component 170. In an embodiment, an entity 136A-n may generate a notification (e.g., as part of a conversation 126) indicating that the problem 105R has been accomplished, and the state component 170 may be configured to initiate an update of the previous problem 138A-n to include the conversation 126A-n / thread 127A-n that was created with / associated with the resolution of the problem 105U / 105R. Updating the previous problem 138A-n with the conversation 126A-n / thread 127A-n allows the activity of the respective entity 136A-n to be updated for review during the resolution of subsequent / future problems 105F.

[0054] 1, the IRS 110 may further include a computer system 180. The computer system 180 may include a memory 184 that stores respective computer-executable components (e.g., the IRC 115, the conversation component 120, the initial entity component 135, the entity recommendation component 140, the entity retraction component 145, the summary component 150, and the like), and a processor 182 configured to execute the computer-executable components stored in the memory 184. The memory 184 may further be configured to store any of the problem information 106A-n, the conversations 126A-n, the threads 127A-n, the information about the entities 136A-n, the previous problems 138A-n, the summaries 152A-n, the open problems 105U, the resolved problems 105R, the problems 105, the thresholds 520A-n (as described below), and the like. The computer system 180 may further include a human machine interface (HMI) 186 (e.g., a display, a graphical-user interface (GUI)) that may be configured to present various information including the open problems 105U, the resolved problems 105R, the conversations 126A-n, and the like, in accordance with various embodiments presented herein. The HMI 186 may include an interactive display / screen 187 for presenting the various information. The computer system 180 may further include an I / O component 188 for receiving and / or transmitting the respective problems 105U / 105R, the conversations 126A-n, and the like.

[0055] Before describing the operation and / or configuration of each of the components presented in Figure 1, an example scenario of problem resolution is presented along with the interaction of each of the components. The example scenario 200 of Figure 2 illustrates a detected problem and various entities that are automatically assigned to resolve the problem.

[0056] 2 presents a high-level overview of a dataset being modified for application in a fusion language model, according to one or more embodiments presented herein. An example scenario is presented as a series of acts / steps 1-13.

[0057] At 200-1, a problem arises, i.e., unresolved problem 105U. Unresolved problem 105U may have data / information 106A associated with it, whereby information 106A details what is currently known about unresolved problem 105U, e.g., that the problem is network latency identified in network #6, which is affecting electronic payment services, and that a backlog of payments is of concern. In an embodiment, information 106A may be generated by an AIOps component (e.g., problem component 139) configured to compile information 106A into a story, which may be located within IRS 110 (e.g., AIOps component receives information about problem 105U and further compiles the information to create information 106A) or may be located external to IRS 110 (e.g., information 106A is received in a compiled form).

[0058] At 200-2, the initial entity component 135 may be configured to review the information 106A and further recommend one or more entities 136A-n to be initially assigned to solving the problem 105U. As will be further described, the initial entity component 135 may review prior problems 138A-n in which the respective entities 136A-n have been involved, thereby identifying candidate entities 136A-n to assign to solving the open problem 105U.

[0059] At 200-3, entity 136A is engaged in resolving problem 105U. Entity 136A generates a conversation 126A that provides an initial assessment of the situation regarding problem 105U. Conversation 126A may be by any suitable means, such as email, electronic incident log, and the like, such that conversation 126A is in a format that allows for automated confirmation. In an embodiment, each conversation 126A-n may be compiled / organized into a channel / workspace / repository such that conversation 126A-n is comprised of / includes any / all comments, threads, utterances, conversations, topics, team comments, activities, actions, projects, etc. related to the resolution of open problem 105U.

[0060] At 200-4, conversation component 120 reviews conversation 126A, and based on text matching and the like, conversation component 120 identifies one or more sub-issues related to problem 105U that are related to the knowledge / skill set of entity 136B, and based thereon, conversation component 120 recommends that entity 136B join entity 136A in resolving problem 105U.

[0061] At 200-5, entity 136B generates further conversation 126A, such as, for example, "router not responding."

[0062] At 200-6, conversation component 120 reviews ongoing conversation 126A and identifies one or more sub-problems regarding problem 105U that relate to the knowledge / skill set of entity 136C, and based thereon, conversation component 120 recommends that entity 136C join entity 136A and entity 136B to form a group of entities assigned to solve problem 105U.

[0063] At 200-7, entity 136C generates a further conversation 126A, for example determining why the router is not responding.

[0064] At 200-8, entity revocation component 145 reviews ongoing conversation 126A and, based on identifying (a) entity 136C resolving the problem, (b) entity 136A not being engaged in resolving the problem over a period of time / lack of conversation activity, and the like, entity revocation component 145 automatically recommends revoking / terminating entity 136A's presence in the entity group due to entity 136A's lack of recent engagement in resolving problem 105U. Accordingly, entity 136A is removed from resolving problem 105U.

[0065] At 200-9, a further conversation 126A takes place between entity 136C and entity 136B regarding the resolution of problem 105U. During this time, the content of conversation 126A (e.g., threads 127A-n) may be continually reviewed / evaluated by both entity retraction component 145 and entity recommendation component 140 to determine whether the entity's involvement in the resolution of problem 105U should be retracted and / or whether entity 136A-n should be added to the group of entities for resolving problem 105U.

[0066] At 200-10, the entity recommendation component 140 determines, based on review of conversation 126A, that a sub-problem has arisen that entity 136A may be able to solve. In response, the entity recommendation component 140 recommends that entity 136A rejoin the group of entities (e.g., entity 136B and entity 136C) assigned to solving problem 105U. Entity 136A once again assumes responsibility for helping solve problem 105U.

[0067] As discussed above at 200-11, for periods during which entity 136A was not engaged in resolving problem 105U, summarization component 150 may be configured to identify activity / content that was generated (e.g., in conversations between entity 136B and entity 136C) that entity 136A was not aware of. Based on the unobserved activity / content, summarization component 150 may be configured to generate summary 152A having content that enables entity 136A to quickly stay up to date on what is happening with respect to resolving problem 105U. Furthermore, based on knowing the role / expertise of entity 136A, summarization component 150 may be further configured to generate summary 152A such that summary 152A is tailored to entity 136A, e.g., portions of the summary that are specifically relevant to entity 136A may be highlighted, portions of the summary that are not relevant to entity 136A may be omitted, and the like.

[0068] At 200-12, entity 136A rejoins the group of entities (e.g., entity 136B and entity 136C) and further activity (e.g., further conversations 126A, other conversations 126B-n, further threads 127A-n, and the like) is generated, which may be further reviewed by entity recommendation component 140, entity retraction component 145, compiled by conversation component 120, and the like. In response, entity 136A-n may be engaged / pulled in to solve problem 105U and / or retracted from solving problem 105U.

[0069] At 200-13, problem 105U is resolved as resolved problem 105R, as described above. In an embodiment, prior problem data 138A-n may be updated (e.g., by problem component 139, initial entity component 135, data update component, and the like) with various activities, conversations 126A-n, etc. undertaken by respective entities 136A-n that were engaged in resolved problem 105R. The updated prior problem data 138A-n may be used when assigning entities 136A-n to future open problems 105.

[0070] Turning to FIG. 3 , a schematic diagram 300 illustrates the operation of each component for automatically identifying and recommending one or more entities to initiate a resolution of a problem, according to one or more embodiments. As previously described, the IRS 110 may include an initiating entity component 135 configured to review data / information 106A-n related to the open problem 105U and further identify / recommend one or more entities 136A-n to initiate a process for resolving the problem 105U. The initiating entity component 135 may be communicatively coupled to the IRC 115, which may be configured to utilize the initiating entity component 135 to initiate an assignment of a resolution of the problem 105U to the respective initiating entity 136A-n. The IRC 115 may be configured to employ the initiating entity component 135, for example, based on receiving information 106A-n (e.g., from an external source or generated internally), receiving a notification (not shown) that the problem 105U has been detected / identified, and the like. In an embodiment, the initial entity component 135 may include a similarity component 310 configured to determine / identify how closely one or more content items in the information data 106A are related to prior problems 138A-n in which the respective entities 136A-n were previously involved. The similarity component 310 may be configured to determine similarity based on text, semantics, text summaries, etc. between various items of interest (e.g., a set of current problem information 106A-n and prior problem information 138A-n). In an exemplary embodiment, the similarity component 310 may be a bidirectional and auto-regressive transformer (BART) model architecture, although it should be understood that any suitable model / AI technique / AI architecture may be utilized to identify the entities 136A-n assigned in solving the problem 105U as a function of the prior problems 138A-n that the respective entities 136A-n have worked on.

[0071] As shown in Figure 3, information 106A-n related to the unresolved issue 105U may be compared to data related to prior issues 138A-n with which the respective entity 136A-n has been involved. The information 106A-n related to the unresolved issue 105U is identified in Figure 3 as a new issue report (N-IR), while the data related to the prior issue 138A-n is identified as a prior issue report (P-IR), such that the information 106A-n in the prior issue 138A associated with entity 136A is a P-IR. 1 The data in the previous issue 138B identified as P-IR and associated with the entity 136B is 2 The data in the previous issue 138C identified as P-IR and associated with entity 136C is 3 The data in the prior issue 138n associated with the entity 136n is identified as P-IR n It should be understood that the PI-R data relating to a prior problem 138A-n may consist of a single prior problem / incident in which the entity 136A-n was previously involved, or may consist of multiple prior problems in which the entity 136A-n was previously involved. 1 may consist of a single prior problem or multiple prior problems for entity 136A.

[0072] As shown in FIG. 3, the similarity component 310 compares n pairs of new and previous problem reports (e.g., N-IR vs. P-IR). 1-n ) and compare the contents of each pair N-IR:P-IR 1 , N-IR:P-IR 2 , N-IR:P-IR 3 ...N-IR:P-IR n Similarity score for S 1 -S n As further shown in FIG. 3, the similarity component 310 may be configured to provide a similarity score S 1-S n Using each pair N-IR:P-IR 1 , N-IR:P-IR 2 , N-IR:P-IR 3 ...N-IR:P-IR n The N-IR may be further configured to generate a similarity ranking 330 (e.g., a “k” ranking) of the unsolved problem 105U based on which to identify one or more entities 136A-n with prior experience potentially / directly related to the unsolved problem 105U that may be assigned to solving the problem 105U by the initial entity component 135 (e.g., according to act 200-2 of FIG. 2). For example, if a first content in the N-IR is a P-IR, D The second content in F The entity 136F having a lower similarity score S D This is preferred over entity 136D, which has

[0073] Turning to FIG. 4, a schematic diagram 400 illustrates the operation of each component for automatically recommending the addition of one or more entities to resolve a problem, according to one or more embodiments. As previously described, the IRS 110 may include an entity recommendation component 140 configured to identify conversations 126A-n and respective interactions between one or more entities 136A-n currently (or previously) involved in resolving the problem 105U, based thereon, the entity recommendation component 140 may be further configured to identify / recommend one or more entities 136A-n for joining the group of entities in resolving the problem 105U. The entity recommendation component 140 may be communicatively coupled to the IRC 115, which may be configured to utilize the entity recommendation component 140 when each conversation 126A-n is generated, added, and deployed. For example, when entity 136A generates a comment in a conversation 126A-n regarding problem 105U, entity recommendation component 140 may be configured to automatically analyze the new comment to identify / determine whether another entity, e.g., entity 136B, should be brought in to assist in resolving problem 105U.

[0074] As shown in FIG. 4, for example, a conversation 126A is generated based on the conversation component 120 capturing respective comments / statements / actions performed by various entities 136A-n involved in the resolution of the problem 105U. The exemplary statements presented in FIG. 4 are taken from the exemplary conversation 126A shown in FIG. 2. Although the presented example of the conversation 126A is simple and includes few statements, it should be understood that the conversation 126A may be very complex and comprised of many statements, content, actions, comments, etc. generated by or related to the actions, etc. performed by the respective entities 136A-n in the resolution of the problem 105U. Thus, considering that the conversation component 120 may compile / generate the conversation 126A from multiple sources / data / comments, etc., the conversation 126A may be divided into multiple threads 127A-n (hereinafter C-n) of conversation topics / themes / subjects / etc. 1 -C n For example, conversation 126A may include a discussion (e.g., captured by conversation component 120) between two entities 136A and 136B regarding the operation of a router associated with problem 105U, while another discussion between entities 136A and 136C concerns how electronic payments are processed.

[0075] As further shown, the entity recommendation component 140 may further include a conversation disentanglement component 410, which may be configured to review / analyze the entirety of the conversation 126A captured / compiled by the conversation component 120 and further identify / extract respective threads 127A-n of respective subjects within the conversation 126A. The conversation disentanglement component 410 may utilize any suitable techniques, such as, for example, AI / ML techniques, algorithms, models, architectures, etc., to enable the respective threads 127A-n to be identified / disentangled.

[0076] In the exemplary scenario shown in FIG. 4, the conversation isolation component 410 identifies various conversation threads 127A-n, each of which is represented by C 1 , C 2 ,...C n Furthermore, each conversation thread C 1 , C 2 ,...C n is a set of entities E 1-n , and a set of messages M 1-n Each message in each conversation thread is a reply / response to a previous message, e.g., M 2 is an entity by M 1 In response to M 3 is an entity by M 2 , etc.

[0077] Each thread 127A-n / C 1 , C 2 ,...C n A context for each response and message pair is generated. For example, 3 i The context for the recommendation of} is the previous pair of entities and messages [(E 1 i , E 2 i ), (M 1 i , M 2 i )].

[0078] In an embodiment, each conversation thread C i For the total number of context response pairs = {(C i Message in M 1-i )-1, so the total number of reply pairs is the sum of the number of messages M 1-n is one less than the total number of

[0079] Various threads 127A-n / C1-n and each entity E 1-n and message M 1-n Once the set of threads is identified, the various threads 127A-n / C 1-n may be applied to an AI architecture previously trained on prior conversations 126A-n and threads 127-n. As will be further described, the same AI architecture may be utilized to create the entity identifier component 420 and associated cancellation component (entity identifier component 530). Thus, the purpose of training the AI ​​architecture to create the entity identifier component 420 is to identify the entities 136A-n (e.g., entities E) that are recommended and engaged in solving the problem 105U. 3 ) to identify conversations 126A-n and threads 127A-n / C. 1-n Based on training on previous instances of the problem 105U, the entity recommendation component 140 (e.g., operating as a trained entity recommendation model) may later identify / recommend one or more entities 136A-n to join a group of entities that solve the problem 105U.

[0080] 4 illustrates how an AI architecture can be trained to create the entity identifier component 420, and further illustrates how threads 127A-n of an ongoing conversation 126A can be separated from the conversation 126A and entities 136A-n can be identified from a prior sequence of resource and message sets. Thus, when the current conversation 126A is applied to the previously trained entity identifier component 420, the entity identifier component 420 will identify each entity E 1-n and message M 1-n , together with the set of , to identify entities 136A-n based on the various threads 127A-n within the current conversation 126A.

[0081] As previously discussed, the same basic architecture may be utilized to create the entity recommendation component 140 and the entity retraction component 145. Diagram 500 of Figure 5 illustrates the operation of each component to automatically identify and retract the involvement of one or more entities in resolving a problem, according to one or more embodiments.

[0082] 4, various threads 127A-n may be separated from conversations 126A-n such that one or more entities 136A-n may be identified as potentially useful in solving problem 105U, and entity recommendation component 140 may be configured to automatically identify and recommend the determined entities 136A-n. In an alternative application, entity withdrawal component 145 may also use the determined information regarding one or more entities 136A-n to identify that the respective entities are no longer participating in solving problem 105U, and thus entity withdrawal component 145 may be configured to exclude the identified entities from the project of solving problem 105U.

[0083] Diagram 500 of FIG. 5 illustrates an example process / operation for converting respective words / statements into mathematical expressions that enable respective recommendation and revocation actions to be performed, according to one or more embodiments.

[0084] The above discussion regarding identifying each entity 136A-n within conversation 126A allows entities 136A-n that were previously involved in the project to solve problem 105U but are no longer engaged in said project (e.g., their particular skills / knowledge are not relevant to the ongoing situation regarding problem 105U) to be identified and removed from the group of entities 136A-n solving problem 105U.

[0085] In an embodiment, the entity retraction component 145 may be configured to identify the last message / action associated with an entity, e.g., entity 136A (e.g., entity 136A posted a message). In an embodiment, the entity retraction component 145 may include an activity component 510 in conjunction with the conversation isolation component 410 described above. As described above, the conversation isolation component 410 may be configured to identify / isolate each thread 127A-n / C1-Cn within the conversation 126A. The activity component 510 may be configured to identify the last message / activity involving entity 136A and further identify the most recent message / activity within the conversation 126A. The activity component 510 may be configured to identify the last message posted (e.g., E 3 1 :M 3 1 was the last message posted by entity 136A), and the most recent message in conversation 126A (e.g., entity 136A posted n 1 :M n 1 The time T from when the message was received (T1 to T2) was not involved in the message until the current time, and / or the current time.

[0086] Additionally, activity component 510 may be assigned an activity threshold 520, which is a defined time period against which activity of entities 136A-n is measured. Accordingly, and if time T is equal to or greater than the value of activity threshold 520, the entity cancellation component 145 may be configured to cancel entity 136A's engagement / interaction with the project, where time T is associated with the activity of entity 136A.

[0087] In another embodiment, the identified message (E 31 :M 3 1 ) to subsequent messages (e.g. the latest / last message in conversation 126A-n, n 1 :M n 1 ) may be determined by entity revocation component 145, and if the message count NM is equal to or greater than the defined message count (e.g., if threshold 520D is the message count threshold), entity revocation component 145 may be configured to revoke entity 136A's engagement / interaction with the project. It should be appreciated that any suitable method / technique may be utilized to determine entity 136A-n's lack of engagement with the project, e.g., time, message count, and the like.

[0088] In relation to identifying entities 136A-n, the entity recommendation component 140 may include an entity identifier component 420 and the entity revocation component 145 may include an entity identifier component 530, the operation of which is further described with reference to Figures 6 and 7.

[0089] 6 and 7 present schematic diagrams of example operations for mathematically representing conversations / messages / threads and entities to enable similarity analysis and the like performed, for example, by entity recommendation component 140 and / or entity revocation component 145.

[0090] 6 illustrates the processing of one or more messages having associated entities as part of respective entity recommendation / revocation operations, according to one or more embodiments. As shown, a message M (e.g., when the message M is included in a conversation 126A-n / thread 127A-n) is processed by a tokenizer 610 (or other applicable operations / processing) configured to partition a statement (e.g., an utterance / digital entry made by an entity 136A in a conversation 126A) into respective words W1-n. In an exemplary embodiment, the tokenizer 610 may be further configured to apply a long short term memory network (LSTM) operation 620A-n to each word, and a message embedding component 630 may be configured to combine the respective LSTM values ​​for each word W1-n in the statement to create an embedding value V, where V is a mathematical representation (e.g., a vector representation) of the message M.

[0091] 7 illustrates the processing of one or more messages having associated entities as part of a respective entity recommend / recall operation, according to one or more embodiments. As further shown, each entity 136A-n may also include a message for an entity E R =[E 1 E 2 ...E n-1 ], where E R E is the entity context (also known as resource context) for an entity 136A-n involved in the generation of a set of messages (e.g., in a conversation 126A-n, a thread 127A-n). R V E , where V E is a message M in a conversation 126A-n / thread 127A-n that is of interest.1-n is a mathematical representation (eg, a vector representation) of each of the entities 136A-n involved in the generation of

[0092] As further shown, each message M generated by a respective entity 136A-n within one or more threads 127A-n that are of interest in a conversation 126A-n 1-n are the respective message contexts M 1 , M 2 , ...M n-1 Mathematical Representation of V C (e.g., a vector representation). As shown, each S-LSTM process 730A-n (or other applicable operation / processing) receives a message context M 1 , M 2 , ...M n-1 By sequentially combining C The signal processing unit may be configured to generate

[0093] As will be further shown, the mathematical expression V E (Entity) and V C (Message context) is E i , where E i represents an entity 136A-n that may either be automatically recommended for addition to the group of entities 136A-n working to solve the problem 105U (for example, when the actions shown in Figures 6 and 7 form part of the entity identifier component 420 within the entity recommendation component 140), or automatically withdraw the entity from the group of entities 136A-n that currently belong to the project responsible for solving the problem 105U (for example, when the actions shown in Figures 6 and 7 form part of the entity identifier component 530 within the entity withdrawal component 145).

[0094] As described above, a first entity (e.g., entity 136H) may join the ongoing process of resolving problem 105U, and further, a second entity (e.g., entity 136R) that previously assisted in resolving problem 105U but was later withdrawn may rejoin the project.

[0095] A schematic diagram 800 of FIG. 8 illustrates summary generation for an entity, according to an embodiment. As shown, referring to FIG. 1, the summary component 150 may be communicatively coupled to the entity recommendation component 140 and / or the entity retraction component 145, and may further be communicatively coupled to the IRC 115. The summary component 150 may be configured to determine a period during which the entity 136R or the entity 136H was not involved in a project, and may further be configured to generate summaries 152A-n including unobserved content. The summary component 150 may further include an artifact summarizer 820 configured to summarize various artifacts 810A-n. The summary component 150 may further include a full conversation summarizer 830 configured to generate summaries 152A-n compiled from the respective artifacts 810A-n, and in further embodiments, generate summaries 152A-n tailored to the role / requirements of the receiving entity 136A-n.

[0096] As mentioned above, the conversation 126A may be comprised of multiple threads 127A-n (e.g., subjects, topics, etc.), whereby the threads 127A-n may be further categorized / presented as deliverables 810A-n, such as (a) symptoms 810A related to the problem 105U, (b) actions 810B performed by the respective entities 136A-n in resolving the problem 105U, (c) investigations 810C performed by the respective entities 136A-n in resolving the problem 105U, (d) any identified solutions 810D, and the like. The summary component 150 may generate summaries 152A-n that include one or more summaries of the respective threads 127A-n for a period during which the entity 136A-n was absent from the project, such as in the case of an entity 136H who was absent from the project but participated when the resolution of the problem 105U was in progress. In another example, entity 136R was initially involved in a project, but was later withdrawn from the project (eg, by entity withdrawal component 145) and rejoined (eg, by entity recommendation component 140) into the project.

[0097] Thus, summary 152H for entity 136H will provide a summary of the various threads 127A-n from the start of the project to the point that entity 136H joined the project, while summary 152R will provide a summary of the various threads 127A-n for the period that entity 136R withdrew from the project. The role / knowledge of each entity 136A-n for receiving each summary 152A-n may be provided to summarization component 150, allowing summarization component 150 to tailor / personalize each summary 152A-n to the focus of the receiving entity 136A-n.

[0098] In an embodiment, the summary component 150 summarizes each message M within a particular thread, as well as across the set of threads 127A-n that are involved in the resolution of the problem 105U. 1-nIn embodiments, summaries 152A-n may have multiple levels of content, e.g., each of threads 127A-n / artifacts 810A-n may be summarized individually and a combined summary of each thread 127A-n / artifact may be provided as a single summary 152A-n.

[0099] It should be understood that the various operations presented throughout this disclosure are merely examples of the respective AI and ML operations and techniques, and that any suitable technique may be utilized in accordance with the various embodiments presented herein, including, in a non-limiting list, any of the following: LSTM, deep learning algorithms, sequential neural networks, sequential neural networks enabling persistent information, recurrent neural networks (RNNs), bidirectional encoder representation from transformers (BERT) models, bidirectional and autoregressive transformer (BART) models, convolutional neural networks (CNNs), neural networks, capsule networks, machine learning algorithms, natural language processing (NLP) techniques, sentiment analysis, bidirectional LSTM (BiLSTM), stacked BiLSTM, and the like. 4 and 5, the operations of the respective recommend and retract components / models are merely examples of how the respective content of the conversations 126A-n and their associated entities 136A-n may be mathematically represented and processed to enable a recommend and / or retract action to be undertaken. Thus, any suitable operations / techniques / technology may be utilized to facilitate any of the respective operations / processes presented herein. For example, any suitable operations / techniques / technology may be utilized to facilitate automatic identification of one or more entities 136A-n as part of an automatic recommend or retract action. Furthermore, although the recommend and retract models presented herein are shown as using the same underlying mathematical approach, various embodiments are not so limited, with the recommend and retract models utilizing different techniques.

[0100] Language models, LSTM, BART, etc., may be formed with highly complex neural networks, including, for example, billions of weighting parameters. Training of the LSTM may be performed on a dataset, which may be formed using any suitable technique, such as a problem component 139 generating prior problem information 138A-n for each entity (for use by the entity recommendation component 140 / entity retraction component 145, summary component 150, initial entity component 135, conversation component 120, and the like), a conversation component 120 compiling conversations 126A-n, and the like. The dataset may be available from many sources, for example, collected by an IT company, provided by a client, provided by a third party, and the like. Furthermore, the dataset may include text, alphanumeric characters, numbers, single words, phrases, short statements, long statements, images, audio, etc. Fine-tuning the LM may include application of the dataset to the LM, and the LM may be adjusted accordingly, such that, for example, weights in the LM are adjusted by application of the dataset.

[0101] Methodology 900 of FIG. 9 illustrates a computer-implemented methodology for automatically assigning entities to and / or removing entities from projects for solving problems, in accordance with one or more embodiments.

[0102] At 910, data / information regarding prior problems (e.g., prior problems 138A-n) previously addressed / involved by one or more entities (e.g., any of entities 136A-n) may be compiled and stored (e.g., in database / memory 184) by a problem component (e.g., problem component 139). As previously mentioned, the problem component may reside and operate from within the problem resolution system (e.g., IRS 110) / one of the communicatively coupled components contained within the IRS, or the problem component may reside and operate external to the IRS.

[0103] At 920, data / information regarding the open problem (eg, open problem 105U) may also be compiled by the problem component and stored (eg, as information 106A-n in memory 184).

[0104] At 930, content of the open problem information may be reviewed to determine whether one or more of the entities have previously worked on one or more issues related to the open problem. For example, an initial entity component (e.g., initial entity component 135) may review the issues of the open problem information and extract one or more contents (e.g., elements, actions, parameters, activities, and the like) related to the open problem. The one or more contents may be compared to one or more contents in a previous problem in which the respective entity was involved. If an entity was involved in a previous problem having similarity to the current open problem (e.g., a first content related to the open problem matches / similar to a second content related to the current open problem), the initial entity component may be configured to automatically select the identified entity and assign the entity to the resolution of the open problem, where the identified entity may act as an individual or as part of a group / team that was initially convened to address the open problem.

[0105] At 940, as one or more entities work to resolve the problem, a conversation component (e.g., conversation component 120) may be configured to compile various emails, statements, utterances, activities, etc. that the one or more entities generate / perform while working to resolve the problem, where the various emails, activity statements, actions, etc. may be compiled into a conversation (e.g., conversation 126A) related to the resolution of the problem.

[0106] As mentioned above, a conversation may include various conversation threads (e.g., threads 127A-n) on different subjects / topics related to an open issue. A conversation isolation component (e.g., conversation isolation component 410) may be configured to identify and extract / isolate various threads from a conversation, where the threads may be utilized to recommend / remove entities from a project. As mentioned above, the location and / or implementation of the isolation component may be any of the conversation components within the entity recommendation component (e.g., entity recommendation component 140) and / or the entity retraction component (e.g., entity retraction component 145).

[0107] At 950, as described above, an entity recommendation component can be configured to analyze each thread and automatically identify entities having skills that may be applicable to a current sub-problem / activity in solving the problem. The entity recommendation component can be configured to recommend entities based on comparing and matching the content of one or more threads with previous problem information for each entity.

[0108] At 960, if an entity is assigned to assist in resolving the problem, a summary component (e.g., summary component 150) can be configured to determine a period of ongoing problem resolution during which the entity was absent. The summary component can be further configured to generate a summary (e.g., summaries 152A-n) for the entity, where the summary provides a summary of various communications, actions, etc., performed during the problem resolution period during which the entity was absent. The summary can be tailored to the needs of the entity, e.g., the entity's skill set, allowing the entity to quickly get up-to-date information regarding the current state of problem resolution and the work performed thus far in an attempt to resolve the problem.

[0109] At 970, at the same time that the entity recommendation component functions to identify / recruit one or more entities for assignment to a project, as described above, the entity withdrawal component may be configured to analyze each thread and automatically identify entities that are no longer engaged in resolving the problem even though the entities are currently assigned to resolving the problem. The entity withdrawal component may be configured to remove entities based on identifying a period (e.g., as measured based on time T, as measured based on message volume NM, etc.) in which the entity has not been engaged in the project, whereby that period exceeds a defined value (e.g., threshold 520A-n).

[0110] At 980, a determination may be made as to whether the open problem has been resolved (e.g., becomes a resolved problem 105R). In response to a determination of "no, the problem has not been resolved," methodology 900 may proceed to 990 for further analysis of the open problem to be performed and may further return to 940 to add / remove entities to / from the project.

[0111] Further, in response to a determination at 980 that "yes, the problem is resolved," methodology 900 may proceed to 995, where each activity, conversation, problem, etc. may be compiled for each entity's involvement in the project, and a prior problem database (e.g., prior problems 138A-n) may be updated (e.g., by problems component 139) with the entities' involvement in resolving the problems. Thus, with the prior problem database updated, the updated information may be utilized to determine one or more initial entities and / or recommended entities for resolving future problems.

[0112] Methodology 1000 of FIG. 10 illustrates a computer-implemented methodology for automatically and initially assigning entities to projects to solve problems, according to one or more embodiments.

[0113] At 1010, information about a current problem (e.g., open problem 105U) may be received in the system (e.g., by IRS 110, problem component 139, and the like). In an embodiment, the current problem may be an operational event in the information technology system.

[0114] At 1020, the current problem information may be analyzed (e.g., by problem component 139) to identify content, actions, etc. that may be performed by various entities (e.g., any of entities 136A-n) with respective skill sets / knowledge regarding problem resolution.

[0115] At 1030, a prior problem (e.g., prior problem 138A-n) may be obtained by an initial entity component (e.g., initial entity component 135), where the prior problem has associated activities / utterances / conversations / etc. performed by a respective entity (e.g., any of entities 136A-n) while resolving the prior problem, and which is available for the respective entity to address / resolve the current problem.

[0116] At 1040, the initial entity component may be configured to analyze the current problem and the previous problem to identify / generate one or more pairs between current problem information in the current problem and previous problem information in the previous problem. As previously described, the first data in the current problem information (e.g., N-IR, new problem report in information 106A) may be matched with the respective second data in the previous problem information associated with the respective entity (e.g., P-IR, 1-n , previous problem report in previous problem 138A-n).

[0117] At 1050, a similarity component (e.g., similarity component 310) may determine a respective similarity between the current problem information and the previous problem information. In an embodiment, each pair of current problem information and previous problem information, N-IR:P-IR 1-n To represent , a vector representation can be used.

[0118] 1060, each pair, N-IR:P-IR 1-n A respective similarity score (eg, K scores) may be generated for each of the pairs based on the respective vector proximities between them.

[0119] 1070, group N-IR:P-IR 1-n are their respective similarity scores (e.g., S 1 -S n) by the similarity component (e.g., as ranking 330), and each entity associated with each pair may be identified by the similarity component. Thus, the potential of each entity's skill set in solving the problem may be determined based on the entity's respective position in the ranked similarity scores. For example, a high similarity score for a pair indicates that the entities associated with the pair are likely to have skills applicable to solving the current problem, while a low similarity score for a pair indicates that the entities associated with the pair are likely to have few, if any, skills applicable to solving the problem.

[0120] At 1080, the initial entity component can be further configured to recommend an entity with the highest (or higher) similarity score to be assigned initially to aid in solving the current problem.

[0121] Methodology 1100 of FIG. 11 illustrates a computer-implemented methodology for automatically recommending / assigning entities to projects for solving problems, according to one or more embodiments.

[0122] At 1110, a conversation component (e.g., conversation component 120) may be configured to compile ongoing activities / utterances / digital conversations / digital inputs / entries occurring in solving the current problem and further generate a conversation (e.g., as conversations 126A-n) from the compiled information. The conversation component may be configured to continually update the conversation as new activities / inputs are generated / received.

[0123] At 1120, the conversation may be separated by a conversation separation component (e.g., conversation separation component 410) to identify one or more threads (e.g., threads 127A-n) included in the conversation, where the one or more threads may each be associated with various topics, subjects, etc., as previously described.

[0124] At 1130, the threads may be applied to an entity recommendation component (e.g., entity recommendation component 140), where the entity recommendation component may have been pre-trained with one or more datasets including sequences of utterances, actions, and the like between respective entities as the problem is solved. By training the entity recommendation component with one or more datasets, the entity recommendation component (e.g., a mathematical model) may be configured to predict subsequent entities based on previous sequences of respective utterances and the respective entities that generated them.

[0125] At 1140, based on prior training of the entity recommendation component, the entity recommendation component can be configured to recommend entities identified in the current conversation / thread as a function of a training dataset of prior utterances etc. and the entities that created them.

[0126] At 1150, the recommended entities may be assigned to a project to solve the problem.

[0127] Methodology 1200 of FIG. 12 illustrates a computer-implemented methodology for automatically generating summaries of activity not observed by an entity while resolving a problem, according to one or more embodiments.

[0128] At 1210, a notification may be received at a summarization component (e.g., summarization component 150) that an entity (e.g., entities 136A-n) has been assigned to solve a problem (e.g., problem 105U). The entity may be assigned as part of an automatic entity recommendation operation performed by an entity recommendation component (e.g., entity recommendation component 140), and the notification may be generated and transmitted by the entity recommendation component and received / processed by the summarization component, where the notification further identifies the entity that joins a group of one or more entities assigned to solve the problem.

[0129] At 1220, the summary component may be configured to identify / determine the duration and / or amount of activity performed by one or more entities involved in resolving the problem. As discussed above with respect to the operation and functionality of the initial entity component 135, an entity may be assigned at the beginning of the activity to resolve the problem. However, again as discussed above, an entity may be assigned to resolve the problem after (a) previous activity has already been undertaken, e.g., when the resolution of the problem has already been in progress for 30 minutes, an hour, a day, etc., or (b) an entity was previously assigned to resolve the problem and was later revoked (e.g., by the entity revocation component 145) from resolving the problem at some later point (e.g., due to inactivity), but is later reassigned to resolve the problem (e.g., based on a recommendation from the entity recommendation component 140). For both scenarios (a) and (b), if the recommended entity is absent from the team resolving the problem, the recommended entity will not observe the activity. Thus, for scenario (a), the duration / activity not observed by the recommended entity is the activity that took place from when the project was started until the time the recommended entity joins the project, and for scenario (b), the duration / activity not observed by the returning entity is the activity that took place from when the entity was withdrawn from the project until the entity rejoins the project.

[0130] Each unobserved content may be identified by the summary component at 1230. In an embodiment, the unobserved content for a conversation (e.g., if the unobserved content is considered to be conversation 126B, which is an entire part of conversation 126A that has taken place since the inception of the project) may include various themes / artifacts (e.g., threads 127A-n, artefacts 810A-n) related to topics such as problem symptoms, entity activity, entity research, problem resolution, and the like, as described above.

[0131] At 1240, in embodiments, a deliverable summarizer (eg, deliverable summarizer 820) may be configured to generate respective summaries (152A-n), each of which may relate to one or more of the deliverables.

[0132] At 1250, the summarization component may further include a full conversation summarizer (e.g., full conversation summarizer 830) configured to combine one or more of the deliverable summaries into a general / omnibus summary that provides a required level of summary for a particular entity (e.g., summarization component 150 is provided with role information for the entities of interest). Thus, from the same unobserved content, a first omnibus summary (e.g., summary 152X) is generated for a first entity, while a second omnibus summary (e.g., summary 152Y) is generated for a second entity, where the first and second entities have different roles / skill sets / information requirements.

[0133] At 1260, the summarization component is configured to provide a respective summary for each entity for which a summary has been generated.

[0134] Methodology 1300 of FIG. 13 illustrates a computer-implemented methodology for automatically removing entities currently assigned to a project to resolve a problem, according to one or more embodiments.

[0135] At 1310, a conversation component (e.g., conversation component 120) can be configured to compile activities performed in solving the current problem and further generate a conversation (e.g., as conversations 126A-n) from the compiled information.

[0136] At 1320, a conversation (e.g., conversation 126A) may be separated by a conversation separation component (e.g., conversation separation component 410) to identify one or more threads (e.g., threads 127A-n) included in the conversation, where the one or more threads may each be associated with various topics, subjects, etc., as previously described.

[0137] At 1330, the threads may be applied to an entity cancellation component (e.g., entity cancellation component 145), where the entity cancellation component may have been pre-trained with one or more data sets including sequences of utterances, actions, and the like between each entity as the problem is solved. By training the entity cancellation component with the one or more data sets, the entity cancellation component (e.g., a mathematical model) may be configured to identify each utterance, etc. in each thread that is separated from the current conversation (e.g., current conversation 126A), and further to identify each entity that generates each utterance.

[0138] At 1340, a threshold (e.g., threshold 520A) may be defined / applied to the entity revocation component, whereby the threshold may be any suitable measure by which an entity may be determined to be inactive, such as the time T during which activity occurs within a conversation, the number of messages NM in which the entity is required to be involved, and the like.

[0139] At 1350, the last utterance by the entity may be identified by the entity retraction component along with the most recent utterance (or an utterance of interest, e.g., a particular utterance that occurred 20 minutes ago). The entity retraction component may receive a parameter, e.g., the time T that the entity was inactive. IN Identifies the number of messages NM for which the entity was inactive. IN , and the like.

[0140] At 1360, the difference between the determined parameter and the threshold value may be determined by an activity component (e.g., activity component 510), whereby the activity component determines T IN is equal to or exceeds T, NM IN is equal to or exceeds NM, and similar conditions.

[0141] At 1370, in response to a determination that the determined parameter is less than the threshold, methodology 1300 may return to 1310 for further determination of the entity's activity, or lack thereof, to be determined. In an embodiment, the conversation may be updated by the conversation component to allow future determinations of inactivity to be made based on recent activity / digital inputs by each entity (e.g., entities 136A-n).

[0142] In response to a determination at 1370 that the determined parameter equals / exceeds the threshold, methodology 1300 may proceed to 1380, where the entity's engagement with the project may be cancelled by the entity cancellation component. As previously described, a subsequent determination may be made by the entity recommendation component that the entity should rejoin the project in resolving the problem.

[0143] As used herein, “infer,” “inference,” “determine,” and similar terms generally refer to the process of reasoning or inferring a state of a system, environment, and / or user from a set of observations captured via events and / or data. Inference may be employed, for example, to identify a specific context or action, or may generate a probability distribution over states. Inference may be probabilistic, that is, computing a probability distribution over states of interest based on a consideration of data and events. Inference may also refer to techniques employed to compose higher-level events from a set of events and / or data. Such inference results in the construction of new events or actions from a set of observed events and / or stored event data, regardless of whether the events are closely correlated in time and whether the events and data are from one or multiple event and data sources.

[0144] According to various embodiments presented herein, various components included in the IRS 110, IRC 115, conversation component 120, initial entity component 135, entity recommendation component 140, entity cancellation component 145, summary component 150, and the like, may include AI and ML and reasoning techniques and technologies that employ probability and / or statistics-based analysis to predict or infer actions that a user may wish to be automatically performed. Various embodiments presented herein may utilize various machine learning-based schemes to perform various aspects thereof. For example, a process for determining one or more entities 136A-n for initial assignment to a project (e.g., by IRC 115 in conjunction with initial entity component 135), a process for compiling and isolating threads (e.g., threads 127A-n) / activity related to the resolution of an issue (e.g., issue 105U) (e.g., by IRC 115 in conjunction with conversation component 120), a process for determining and recommending entities for addition to a project (e.g., by IRC 115 in conjunction with entity recommendation component 140), a process for determining and recommending entities to be removed from a project (e.g., by IRC 115 in conjunction with entity retraction component 145), a process for determining a period of time an entity has been absent from a project and for determining project content that the entity does not recognize and generating a summary of that content (e.g., by IRC 115 in conjunction with summary component 150), and the like, may be facilitated via automatic classifier systems and processes as previously described herein.

[0145] A classifier is a function that maps an input attribute vector x = (x1, x2, x3, x4, xn) to a class label class(x). A classifier may also output a confidence that the input belongs to a class, i.e., f(x) = confidence(class(x)). Such classification may employ probability and / or statistics-based analysis (e.g., considering analysis utility and cost) to predict or infer actions that a user may want to be automatically performed (e.g., assignment / exclusion of entities in problem solving and their associated actions).

[0146] A support vector machine (SVM) is an example of a classifier that may be employed. SVM operates by finding a hypersurface in the space of possible inputs that optimally splits triggering input events from non-triggering events. Intuitively, this makes the classification accurate for test data that is close to, but not identical to, the training data. Other directed and undirected model classification approaches may be employed, including, for example, naive Bayes, Bayesian networks, decision trees, neural networks, fuzzy logic models, and probabilistic classification models that provide different patterns of independence. As used herein, classification includes statistical regression that is utilized to develop models of priority.

[0147] As can be readily appreciated from the subject specification, various embodiments may employ classifiers that are explicitly trained (e.g., by general training data) as well as classifiers that are implicitly trained (e.g., by observing user behavior and receiving external information). For example, an SVM is comprised of a learning or training phase within a classifier constructor and feature selection module. Thus, the classifiers may be used to automatically learn and perform several functions, including, but not limited to, determining the probability that a problem similar to the open problem has been previously addressed according to predefined criteria.

[0148] As discussed above, inferences may be made and automated actions may be taken based on a number of pieces of information, such as whether conversations 126A-n and threads 127A-n are correctly created / combined / identified by conversation component 120 to enable problem 105U to be resolved quickly with groups of entities 136A-n efficiently assigned / removed as project teams attempt to resolve the problem, whether each entity 136A-n is correctly identified for initial entry (e.g., by initial entity component 135), recommended for subsequent entry (e.g., by entity recommendation component 140), removed from the project (e.g., by entity withdrawal component 145), creation of accurate / useful / appropriate summaries 152A-n (e.g., by summary component 150), and the like. Exemplary Applications and Uses

[0149] FIG. 14 and the following discussion are intended to provide a brief, general description of a suitable computing environment 1400 in which one or more embodiments described herein in FIGS. 1-13 may be implemented. For example, various aspects of the disclosure are described by way of explanatory text, flow charts, block diagrams of computer systems, and / or block diagrams of machine logic included in computer program product (CPP) embodiments. For any flow chart, depending on the technology involved, operations may be performed in a different order than shown in a given flow chart. For example, again depending on the technology involved, two operations shown in successive flow chart blocks may be performed in reverse order, as a single integrated step, simultaneously, or in an at least partially overlapping manner in time.

[0150] A computer program product embodiment ("CPP embodiment" or "CPP") is a term used in this disclosure to describe any set of one or more storage media (also referred to as "media") collectively contained within a set of one or more storage devices that collectively contain machine-readable code corresponding to instructions and / or data for performing computer operations specified in a given CPP claim. A "storage device" is any tangible device that can hold and store instructions for use by a computer processor. The computer-readable storage medium may be, but is not limited to, an electronic storage medium, a magnetic storage medium, an optical storage medium, an electromagnetic storage medium, a semiconductor storage medium, a mechanical storage medium, or any suitable combination of the above. Some known types of storage devices that include these media include 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), compact disc read-only memory (CD-ROM), digital versatile disk (DVD), memory stick, floppy disk, mechanically encoded devices (such as punch cards or pits / lands formed on a major surface of a disk), or any suitable combination of the above. Computer-readable storage media, as the term is used in this disclosure, is not to be construed as storage in the form of a transitory signal itself, such as electric waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide, light pulses passing through a fiber optic cable, electrical signals transmitted through wires, and / or other transmission media.As will be appreciated by those skilled in the art, data is typically moved at some occasional time during the normal operation of a storage device, such as during access, defragmentation, or garbage collection, but this does not make the storage device temporary, as the data is not temporary while it is stored.

[0151] Computing environment 1400 comprises an example of an environment for the execution of at least some of the computer code involved in performing the methods and embodiments of the invention presented herein, such as automatically recommending and revoking entities to assist an IRS (e.g., IRS 110 and subcomponents) in resolving a problem (e.g., problem 105U for creating 105R) through application of entity recommendation and revocation code 1480. In an embodiment, entity recommendation and revocation code 1480 may include one or more components included in problem resolution system 110.

[0152] In addition to block 1480, computing environment 1400 includes, for example, computer 1401, wide area network (WAN) 1402, end user device (EUD) 1403, remote server 1404, public cloud 1405, and private cloud 1406. In this embodiment, computer 1401 includes a processor set 1410 (including processing circuitry 1420 and cache 1421), communication fabric 1411, volatile memory 1412, persistent storage 1413 (including operating system 1422 and block 1480, as identified above), peripheral device set 1414 (including user interface (UI) device set 1423, storage 1424, and Internet of Things (IoT) sensor set 1425), and network module 1415. Remote server 1404 includes a remote database 1430. The public cloud 1405 includes a gateway 1440, a cloud orchestration module 1441, a set of host physical machines 1442, a set of virtual machines 1443, and a set of containers 1444.

[0153] Computer 1401 may take the form of a desktop computer, a laptop computer, a tablet computer, a smartphone, a smartwatch or other wearable computer, a mainframe computer, a quantum computer, or any other form of computer or mobile device now known or later developed that can execute a program, access a network, or query a database, such as remote database 1430. As is well understood in the field of computer technology, and depending on the technology, execution of a computer-implemented method may be distributed among multiple computers and / or among multiple locations. However, in this presentation of computing environment 1400, in order to keep the presentation as simple as possible, the detailed discussion focuses on a single computer, specifically computer 1401. Although computer 1401 is not shown in the cloud in FIG. 14, it may be located in the cloud. However, computer 1401 is not required to be in the cloud except to any extent that may be categorically indicated.

[0154] The processor set 1410 includes one or more computer processors of any type now known or developed in the future. The processing circuitry 1420 may be distributed across multiple packages, e.g., multiple tailored integrated circuit chips. The processing circuitry 1420 may implement multiple processor threads and / or multiple processor cores. The cache 1421 is memory located within the processor chip package and is typically used for data or code that should be available for fast access by threads or cores executing on the processor set 1410. Cache memory is typically organized into multiple levels depending on relative proximity to the processing circuitry. Alternatively, some or all of the cache for a processor set may be located "off-chip." In some computing environments, the processor set 1410 may be designed to operate with qubits and perform quantum computing.

[0155] Computer readable program instructions are typically loaded onto the computer 1401 and cause a sequence of operational steps to be executed by the processor set 1410 of the computer 1401, thereby effecting a computer-implemented method, such that the instructions so executed instantiate the methods specified in the computer-implemented method flowcharts and / or descriptions contained herein (collectively, the "methods of the invention"). These computer readable program instructions are stored in various types of computer readable storage media, such as cache 1421 and other storage media discussed below. The program instructions and associated data are accessed by the processor set 1410 to control and direct the execution of the methods of the invention. In the computing environment 1400, at least a portion of the instructions for executing the methods of the invention may be stored in block 1480 in persistent storage 1413.

[0156] Communications fabric 1411 is the signal-conducting pathways that allow the various components of computer 1401 to communicate with one another. Typically, this fabric is made up of switches and conductive pathways, such as those that make up buses, bridges, physical input / output ports, and the like. Other types of signal communication pathways may be used, such as fiber optic and / or wireless communication pathways.

[0157] Volatile memory 1412 is any type of volatile memory now known or developed in the future. Examples include dynamic random access memory (RAM) or static RAM. Typically, volatile memory is characterized by random access, although this is not required unless expressly indicated. In computer 1401, volatile memory 1412 is located in a single package and is internal to computer 1401, although alternatively or additionally, volatile memory may be distributed across multiple packages and / or located external to computer 1401.

[0158] Persistent storage 1413 is any form of non-volatile storage for a computer, now known or developed in the future. The non-volatility of this storage means that the stored data is maintained regardless of whether power is supplied to computer 1401 and / or to persistent storage 1413 directly. Persistent storage 1413 can be read-only memory (ROM), but typically at least a portion of persistent storage allows data to be written, data to be deleted, and data to be rewritten. Some well-known forms of persistent storage include magnetic disks and solid-state storage devices. Operating system 1422 can take several forms, such as various known proprietary operating systems or open source Portable Operating System Interface types that employ a kernel. The code contained in block 1480 typically includes at least a portion of the computer code involved in carrying out the methods of the present invention.

[0159] The peripheral device set 1414 includes a set of peripheral devices of the computer 1401. Data communication connections between the peripheral devices and other components of the computer 1401 can be implemented in various ways, such as Bluetooth connections, Near-Field Communication (NFC) connections, connections made by cable (such as a universal serial bus (USB) type cable), insertion type connections (e.g., secure digital (SD) card), connections made through a local area communication network, and even connections made through a wide area network such as the Internet. In various embodiments, the UI device set 1423 can include components such as display screens, speakers, microphones, wearable devices (such as goggles and smart watches), keyboards, mice, printers, touch pads, game controllers, and haptic devices. The storage 1424 is external storage, such as an external hard drive, or insertable storage, such as an SD card. The storage 1424 can be persistent and / or volatile. In some embodiments, storage 1424 may take the form of a quantum computing storage device for storing data in the form of qubits. In embodiments where computer 1401 is required to have a large amount of storage (e.g., where computer 1401 stores and manages large databases locally), then this storage may be provided by a peripheral storage device designed to store large amounts of data, such as a storage area network (SAN) shared by multiple geographically distributed computers. IoT sensor set 1425 is made up of sensors that may be used in Internet of Things applications. For example, one sensor may be a thermometer and another sensor may be a motion detector.

[0160] The network module 1415 is a collection of computer software, hardware, and firmware that enables the computer 1401 to communicate with other computers over the WAN 1402. The network module 1415 may include hardware such as a modem or Wi-Fi® signal transceiver, software for packetizing and / or depacketizing data for communication network transmission, and / or web browser software for communicating data over the Internet. In some embodiments, the network control and network forwarding functions of the network module 1415 are performed on the same physical hardware device. In other embodiments (e.g., those that utilize Software-Defined Networking (SDN)), the control and forwarding functions of the network module 1415 are performed on physically separate devices such that the control function manages multiple different network hardware devices. Computer readable program instructions for carrying out the methods of the present invention may be downloaded into the computer 1401 through a network adapter card or network interface included in the network module 1415, typically from an external computer or external storage device.

[0161] The WAN 1402 is any wide area network (e.g., the Internet) capable of communicating computer data over non-local distances by any technology now known or later developed for conveying computer data. In some embodiments, the WAN may be replaced and / or supplemented by a local area network (LAN) designed to communicate data between devices located in a local area, such as a Wi-Fi network. WANs and / or LANs typically include computer hardware such as copper transmission cables, optical transmission fiber, wireless transmission, routers, firewalls, switches, gateway computers, and edge servers.

[0162] End-user device (EUD) 1403 is any computer system used and controlled by an end user (e.g., a customer of the business operating computer 1401) and may take any of the forms discussed above in connection with computer 1401. EUD 1403 typically receives useful and useful data from the operation of computer 1401. For example, in a hypothetical case where computer 1401 is designed to provide recommendations to the end user, the recommendations would typically be communicated from network module 1415 of computer 1401 over WAN 1402 to EUD 1403. In this manner, EUD 1403 can display or otherwise present the recommendations to the end user. In some embodiments, EUD 1403 may be a client device, such as a thin client, a heavy client, a mainframe computer, and / or a desktop computer.

[0163] Remote server 1404 is any computer system that provides at least some data and / or functionality to computer 1401. Remote server 1404 may be controlled and used by the same entity that operates computer 1401. Remote server 1404 represents a machine that collects and stores useful and useful data for use by other computers, such as computer 1401. For example, in the hypothetical case where computer 1401 is designed and programmed to provide recommendations based on past data, then this past data may be provided to computer 1401 from a remote database 1430 of remote server 1404.

[0164] Public cloud 1405 is any computer system available for use by multiple entities that provides on-demand availability of computer system resources and / or other computer capabilities, particularly data storage (cloud storage) and computing power, without direct active management at scale. The direct active management of computing resources of public cloud 1405 is performed by computer hardware and / or software of cloud orchestration module 1441. The computing resources provided by public cloud 1405 are typically implemented by virtual computing environments running on various computers that make up host physical machine set 1442 computers within and / or available in public cloud 1405, a universe of physical computers. Virtual computing environments (VCEs) typically take the form of virtual machines from virtual machine set 1443 and / or containers from container set 1444. It is understood that these VCEs may be stored as images and transferred among and between various hosts of physical machines, either as images or after instantiation of the VCEs. The cloud orchestration module 1441 manages the transfer and storage of images, deploys new instantiations of the VCE, and manages active instantiations of the VCE deployment. The gateway 1440 is a collection of computer software, hardware, and firmware that enables the public cloud 1405 to communicate over the WAN 1402.

[0165] Some further description of virtualized computing environments (VCEs) is now provided. A VCE may be stored as an "image." A new active instance of a VCE may be instantiated from an image. Two well-known types of VCEs are virtual machines and containers. A container is a VCE that uses operating system level virtualization. This refers to a feature of an operating system where the kernel allows the existence of multiple isolated user space instances, called containers. These isolated user space instances typically behave as real computers from the perspective of the programs running within them. A computer program running on a normal operating system may utilize all of the resources of that computer, such as connected devices, files and folders, network shares, CPU power, and quantifiable hardware capabilities. However, a program running inside a container may only use the contents of the container and of the devices assigned to the container, a feature known as containerization.

[0166] A private cloud 1406 is similar to a public cloud 1405, except that the computing resources are only available for use by a single enterprise. Although the private cloud 1406 is shown in communication with the WAN 1402, in other embodiments, the private cloud may be completely disconnected from the Internet and only accessible through a local / private network. A hybrid cloud is a composite of multiple clouds of different types (e.g., types of private, community, or public clouds), often each implemented by a different vendor. Each of the multiple clouds remains a separate, discrete entity, but the larger hybrid cloud architecture is bound together by standardized or proprietary technologies that enable orchestration, management, and / or data / application portability between the constituent clouds. In this embodiment, both the public cloud 1405 and the private cloud 1406 are part of a larger hybrid cloud.

[0167] The embodiments described herein may be directed to one or more of a system, a method, an apparatus, and / or a computer program product at any possible level of technical detail of integration. The computer program product may include a computer readable storage medium (or media) having computer readable program instructions for causing a processor to execute aspects of one or more embodiments described herein. A computer readable storage medium may be a tangible device that can hold and store instructions for use by an instruction execution device. A computer readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a superconducting storage device, and / or any suitable combination of the above. A non-exhaustive list of more specific examples of computer readable storage media may also include the following: portable computer diskettes, hard disks, random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), static random access memories (SRAMs), portable compact disk read-only memories (CD-ROMs), digital versatile disks (DVDs), memory sticks, floppy disks, mechanically encoded devices such as punch cards or raised structures in grooves with instructions recorded on them, and / or any suitable combination of the above. Computer readable storage media as used herein shall not be construed as being ephemeral signals per se, such as electric signals transmitted over wires, electromagnetic waves and / or other freely propagating electromagnetic waves, electromagnetic waves propagating through wave guides and / or other transmission media (e.g., light pulses passing through fiber optic cables), and / or electrical signals transmitted over wires.

[0168] The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to the respective computing / processing device and / 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 fiber, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and transfers the computer-readable program instructions to a computer-readable storage medium in the respective computing / processing device for storage. The computer readable program instructions for carrying out the operations of one or more embodiments described herein may be source code and / or object code written in any combination of one or more programming languages, including assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state setting data, configuration data for integrated circuits, and / or procedural programming languages, such as object oriented programming languages, e.g., Smalltalk®, C++, or the like, and / or the “C” programming language, and / or similar programming languages. The computer readable program instructions may be executed entirely on the computer, partially on the computer, as a standalone software package, partially on the computer, and / or partially on a remote computer, or entirely on a remote computer and / or server. In the latter scenario, the remote computer may be connected to the computer through any type of network, including a local area network (LAN) and / or a wide area network (WAN), and / or a connection to an external computer may be made (e.g., through the Internet using an Internet Service Provider).In one or more embodiments, electronic circuitry including, for example, a programmable logic circuit, a field programmable gate array (FPGA), and / or a programmable logic array (PLA) may execute computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry to perform aspects of one or more embodiments described herein.

[0169] Aspects of one or more embodiments described herein are described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to one or more embodiments described herein. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, may be implemented by computer-readable program instructions. These computer-readable program instructions may be provided to a processor of a general purpose computer, a special purpose computer, and / or other programmable data processing apparatus to generate a machine, such that the instructions executing via the processor of the computer or other programmable data processing apparatus may create means for implementing the function / act specified in the block or blocks of the flowchart and / or block diagram. These computer-readable program instructions may also be stored in a computer-readable storage medium that may instruct a computer, a programmable data processing apparatus, and / or other device to function in a particular manner, such that the computer-readable storage medium having instructions stored therein may have an article of manufacture including instructions that may implement aspects of the function / act specified in the block or blocks of the flowchart and / or block diagram. The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, and / or other device and cause a series of operational acts to be executed on the computer, other programmable apparatus, and / or other device to generate a computer-implemented process, whereby the instructions executing on the computer, other programmable apparatus, and / or other device implement the function / acts specified in the block or blocks of the flowcharts and / or block diagrams.

[0170] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and / or operation of possible implementations of systems, computer-implementable methods, and / or computer program products according to one or more embodiments described herein. In this regard, each block in the flowcharts or block diagrams may represent a module, segment, and / or part of instructions, including one or more executable instructions for implementing a specified logical function. In one or more alternative implementations, the functions described in the blocks may occur in a different order than that described in the figures. For example, two blocks shown in succession may be executed substantially simultaneously, depending on the functionality involved, and / or the blocks may be executed in reverse order, depending on the functionality involved. It should also be noted that each block of the block diagrams and / or flowchart diagrams, and / or combinations of blocks in the block diagrams and / or flowchart diagrams, may be implemented by a dedicated hardware-based system that may perform the specified functions and / or acts and / or execute one or more combinations of dedicated hardware and / or computer instructions.

[0171] Although the subject matter has been described above in the general context of computer-executable instructions for a computer program product executing on a computer and / or multiple computers, those skilled in the art will recognize that one or more embodiments herein may also be implemented at least in part in parallel with one or more other program modules. Generally, a program module includes routines, programs, components, and / or data structures that perform particular tasks and / or implement particular abstract data types. Furthermore, the computer-implemented methods described above may be practiced with single-processor and / or multi-processor computer systems, mini-computing devices, mainframe computers, and other computer system configurations, including computers, handheld computing devices (e.g., PDAs, phones), and / or microprocessor-based or programmable consumer and / or industrial electronics. The illustrated aspects may also be practiced in distributed computing environments where tasks are performed by remote processing devices linked through a communications network. However, some, if not all, aspects of one or more embodiments described herein may be practiced on a stand-alone computer. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

[0172] As used herein, terms such as "component," "system," "platform," and / or "interface" may refer to and / or include computer-related entities or entities related to an operating machine having one or more particular functions. The entities described herein may be either hardware, a combination of hardware and software, software, or software in execution. For example, a component may be, but is not limited to, a process running on a processor, a processor, an object, an executable, a thread of execution, a program, and / or a computer. By way of example, both an application running on a server and the server may be a component. One or more components may reside within a process and / or thread of execution, a component may be localized on one computer and / or distributed between two or more computers. In another example, each component may execute from various computer readable media having various data structures stored thereon. Components may communicate via local and / or remote processes, such as by following signals comprising one or more data packets (e.g., data from one component interacting with another component interacting with another system via signals across local systems, distributed systems, and / or networks such as the Internet). As another example, a component may be a device having a particular functionality provided by mechanical parts operated by electrical or electronic circuits operated by software and / or firmware applications executed by a processor. In such cases, the processor may be internal and / or external to the device and may execute at least a portion of the software and / or firmware applications.As yet another example, a component may be a device that provides a particular functionality without mechanical parts through electronic components that may include a processor and / or other means for executing software and / or firmware that provides, at least in part, the functionality of the electronic component. In some aspects, a component may emulate an electronic component via a virtual machine, for example, in a cloud computing system.

[0173] In addition, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or". That is, unless otherwise specified or clear from the context, "X employs A or B" is intended to mean any of the natural inclusive permutations. That is, under any of the above examples, "X employs A or B" is satisfied if X employs A, if X employs B, or if X employs both A and B. Furthermore, the articles "a" and "an" used in the specification of the present subject matter and the accompanying drawings should be construed generally to mean "one or more", unless otherwise specified or clear from the context that the singular form is intended. As used herein, the terms "example" and / or "exemplary" are utilized to mean serving as an example, instance, or illustration. For the avoidance of doubt, the present subject matter described herein is not limited by such examples. Additionally, any aspect or design described herein as "example" and / or "exemplary" is not necessarily to be construed as preferred or advantageous over other aspects or designs, and is not meant to exclude equivalent exemplary structures and techniques known to those skilled in the art.

[0174] As employed in the subject specification, the term "processor" may refer to substantially any computing processing unit and / or device, including, but not limited to, a single-core processor; a single processor with software multithreading execution capability; a multi-core processor; a multi-core processor with software multithreading execution capability; a multi-core processor with hardware multithreading technology; a parallel platform; and / or a parallel platform with distributed shared memory. Additionally, a processor may refer to an integrated circuit, an application specific integrated circuit (ASIC), a digital signal processor (DSP), a field programmable gate array (FPGA), a programmable logic controller (PLC), a complex programmable logic device (CPLD), discrete gate or transistor logic, discrete hardware components, and / or any combination thereof designed to perform the functions described herein. Furthermore, a processor may utilize nanoscale architectures, such as, but not limited to, molecular and quantum dot-based transistors, switches, and / or gates, to optimize space utilization and / or enhance the performance of associated equipment. A processor may be implemented as a combination of computing processing units.

[0175] As used herein, terms such as "memory," "storage," "data store," "data storage," "database," and substantially any other information storage component associated with the operation and functionality of a component are utilized to refer to a "memory component" entity embodied in a "memory" or memory-containing component. The memory and / or memory components described herein may be either volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. By way of example, and not limitation, non-volatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM), flash memory, and / or non-volatile random access memory (RAM) (e.g., ferroelectric RAM (FeRAM). Volatile memory may include, for example, RAM that may act as external cache memory. By way of example, and not limitation, RAM may include synchronous RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), Direct Rambus (DRAM), etc. Memory components may be available in many forms, such as RAM (DRRAM), Direct Rambus Dynamic RAM (DRDRAM), and / or Rambus Dynamic RAM (RDRAM). Additionally, the described memory components of the systems and / or computer-implemented methods herein are intended to include, but are not limited to, these and / or any other suitable types of memory.

[0176] What has been described above includes merely examples of systems and computer-implemented methods. Of course, for purposes of describing one or more embodiments, it is not possible to describe every conceivable combination of components and / or computer-implemented methods, but one of ordinary skill in the art may recognize that many further combinations and / or permutations of one or more embodiments are possible. Moreover, to the extent that "including," "having," "possessing," and similar terms are used in the detailed description, claims, appendices, and / or drawings, such terms are intended to be inclusive in the same manner as the term "comprising" is interpreted when employed as a transitional phrase in the claims.

[0177] The description of various embodiments is presented for purposes of illustration, but is not intended to be exclusive or limited to the embodiments described herein. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein has been selected to best explain the principles, practical applications, and / or technical improvements of the embodiments over technologies found in the marketplace, and / or to enable others skilled in the art to understand the embodiments described herein.

Claims

1. 13. A system comprising: a memory operatively coupled to the system, the memory storing computer-executable components; and A processor that executes the computer-executable components stored in the memory. Equipped with wherein the computer executable components: Identifying the first piece of content related to the problem; identifying a second content in at least one prior problem solution based on the first content, where the first content and the second content are similar; Identifying a first entity associated with the second content; and Assigning the first entity to initiate a process to resolve the problem. have an initial entity component configured as system.

2. The system of claim 1 , wherein the first content is included in initially compiled information about the problem.

3. The system of claim 1 or 2, wherein the problem is an event in an information technology system.

4. The computer executable components include: identifying third content related to the problem, where the third content is a digital entry submitted by the first entity while attempting to resolve the problem; identifying a second entity to participate in solving the problem based on the third content; and Assigning the second entity to solve the problem. The system of claim 1 or 2, further comprising an entity recommendation component configured to:

5. The entity recommendation component: identifying fourth content, where the fourth content is generated in a digital conversation between the first entity and the second entity, where the digital conversation pertains to solving the problem; identifying a third entity to participate in solving the problem based on the fourth content; and assigning the third entity to join the first entity and the second entity in solving the problem. The system of claim 4 further configured to:

6. The computer executable components include: identifying a first time, where said first time is a time that said third entity is assigned to solving said problem; identifying a second time, where the second time is the time that resolution of the problem was initiated; determining activities performed by the first entity and the second entity in resolving the problem during the first time and the second time; generating a summary of the activities performed by the first entity and the second entity during the first time and the second time; and providing said summary to said third entity; The system of claim 5 , further comprising a summary component configured to:

7. The summary component: receiving an operational role for the third entity; and Constructing the summary based on the operational role of the third entity. The system of claim 6 further configured to:

8. the first entity, the second entity, and the third entity constitute a group of entities assigned to solving the problem, and wherein the computer-executable component: further monitoring the digital conversation between the group of entities to identify a period of time during which the first entity within the group of entities is not participating in the digital conversation; determining whether the time period exceeds a threshold time period; and removing the first entity from the group of entities based on the time period exceeding the threshold time period. The system of claim 5 , further comprising an entity revocation component configured to:

9. The entity recommendation component: further monitoring the digital conversation between the second entity and the third entity; determining that the digital conversation relates to the first entity; and reassigning the first entity to the group of entities that solves the problem. The system of claim 8 further configured to:

10. The computer executable components include: identifying a third time, where the third time is a time that the first entity that was removed from the group of entities was assigned to solving the problem; identifying a fourth time, where the fourth time is a current time at which resolution of the problem is being performed by the second entity and the third entity; determining activities performed by the second entity and the third entity in resolving the problem during the third time and the fourth time; generating a second summary of the activities performed by the second entity and the third entity during the third time and the fourth time; and Providing the second summary to the first entity The system of claim 9 , further comprising a summarization component configured to:

11. the first entity, the second entity, and the third entity constitute a group of entities assigned to solving the problem, and wherein the computer-executable component: further monitoring the digital conversation between the group of entities to identify a number of consecutive messages in the digital conversation during which the first entity in the group of entities did not generate a message in the digital conversation; determining whether the number of consecutive messages exceeds a threshold number of messages; and removing the first entity from the group of entities assigned to solving the problem based on the number of consecutive messages exceeding the threshold number of messages. The system of claim 5 , further comprising an entity revocation component configured to:

12. 1. A computer-implemented method executed by a device operatively coupled to a processor, comprising: identifying a first entity to initiate a solution to the current problem, where the first entity is identified based on similarity of a previous problem to which the first entity was previously assigned to the current problem; and assigning said first entity to initiate a solution to said current problem, wherein said current problem relates to the performance of an information technology operation; A computer-implemented method comprising:

13. analyzing digital content created by the first entity while attempting to resolve the problem; identifying one or more prior activities, where the prior activities involve a second entity; determining that the one or more prior activities relate to the digital content; and recommending that the second entity assist the first entity in solving the problem. The computer-implemented method of claim 12 further comprising:

14. monitoring activity of the first entity and the second entity in an attempt to resolve the problem; comparing activity of the second entity in attempting to solve the problem; determining that the second entity is no longer engaged in attempts to resolve the problem; and withdrawing the second entity's involvement in resolving the problem. The computer-implemented method of claim 13 further comprising:

15. 15. The computer-implemented method of claim 14, wherein determining that the second entity is no longer engaged in attempts to resolve the problem is based on at least one of a period of inactivity or an amount of digital content generated.

16. determining an engaged time, wherein the engaged time is the time the second entity joined the first entity in attempting to resolve the problem; determining unobserved activities undertaken by the first entity between the initiation of resolution of the problem and the engagement time, where the unobserved activities are activities performed by at least the first entity in solving the problem; generating a summary of the unobserved activity; and providing the summary of the unobserved activity to the second entity. The computer-implemented method of claim 13 , further comprising:

17. On your computer: identifying a first entity to initiate a solution to the current problem, where the first entity is identified based on similarity of a previous problem to which the first entity was previously assigned to the current problem; and assigning said first entity to initiate a solution to said current problem, wherein said current problem relates to the performance of an information technology operation; A computer program for executing the following:

18. On the computer: analyzing digital content created by the first entity while attempting to resolve the problem; identifying one or more prior activities, where the prior activities involve a second entity; determining that the one or more prior activities relate to the digital content; and recommending that the second entity assist the first entity in resolving the problem.

20. The computer program product of claim 17 further comprising:

19. On the computer: monitoring activity of the first entity and the second entity in an attempt to resolve the problem; comparing activity of the second entity in attempting to solve the problem; determining that the second entity is no longer engaged in attempts to resolve the problem; and cancelling the second entity's involvement in resolving the problem.

20. The computer program product of claim 18 further comprising:

20. On the computer: determining an engaged time, wherein the engaged time is the time the second entity joined the first entity in attempting to resolve the problem; determining unobserved activities undertaken by the first entity between the initiation of resolution of the problem and the engagement time, where the unobserved activities are activities performed by at least the first entity in solving the problem; identifying an operational role of the second entity; generating a summary of the unobserved activity, where the summary is generated based on the operational role of the second entity; and providing the summary of the unobserved activity to the second entity.

20. A computer program according to claim 18 or 19, further comprising the steps of:

Images