Entity allocation in automatic problem resolution

Abstract

Various systems and methods are presented herein relating to automatically identifying one or more entities for allocation to resolve a problem and / or removing entities from groups of entities allocated to resolve a problem. The problem may relate to an information technology / computer-based environment. The entity may be a subject expert having professional knowledge identified as relating to the question. A summary of questions and activities related to solving the questions may be automatically generated and provided to entities that are online after a project is ongoing to solve the questions. By implementing automatic distribution / removal of entities, the solution efficiency is improved.

Description

Background Art

[0001] The subject disclosure relates to automatically identifying and engaging entities to assist in resolving problems in an information technology (IT) environment. Summary of the invention

[0002] The following presents a summary of the invention to provide a basic understanding of one or more embodiments described herein. The summary of the invention is not intended to identify key or important elements, or to indicate any scope of different embodiments and / or any scope of the claims. The sole purpose of the summary of the invention is to present some concepts in a simplified form as a prelude to the more detailed description presented herein.

[0003] In one or more embodiments described herein, systems, devices, computer-implemented methods, methods, apparatus, and / or computer program products are presented that facilitate automatic identification of entities to be assigned or removed as involved in problem solving.

[0004] According to one or more embodiments, a system for assigning or revoking an entity's participation in problem solving is provided. The system may include: a memory operably coupled to the system, wherein the memory stores computer executable components; and a processor that executes 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 a problem; and based on the first content, identify second content in at least one previous problem solution, wherein 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 for solving the problem. In an embodiment, the first content may be included in an initial compilation of information about the problem. In another embodiment, the problem may be an event in an information technology system.

[0005] In another embodiment, the computer executable components may further include a recommending entity component configured to identify third content related to the problem, wherein the third content may be a digital entry submitted by the first entity when attempting to solve the problem. The recommending entity component may be further configured to, based on the third content, identify a second entity to participate in solving the problem; and assign the second entity to solve the problem. The recommending entity component may be further configured to identify fourth content, wherein the fourth content is generated in a digital conversation between the first entity and the second entity, wherein the digital conversation is related to solving the problem. Based on the fourth content, the recommending entity component may be further configured to: identify a third entity to participate in solving the problem; and further assign the third entity to join the first entity and the second entity to solve the problem.

[0006] In another embodiment, the computer executable components may further include a summary component configured to: identify a first time, wherein the first time is a time when the third entity is assigned to solve the problem; further identify a second time, wherein the second time is a time when the problem solving is initiated; further determine activities performed by the first entity and the second entity in solving 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 summary component may further be configured to: receive an operational role of the third entity; and configure the summary based on the operational role of the third entity.

[0007] In another embodiment, the first entity, the second entity, and the third entity are included in an entity group assigned to solve the problem. In another embodiment, the computer executable components further include a revoking entity component configured to: further monitor the digital conversation between the entity group to identify a time period during which a first entity in the entity group has not participated in the conversation; determine whether the time period exceeds a threshold time period, and remove the first entity from the entity group based on the time period exceeding the threshold time period.

[0008] In another embodiment, the recommend entity component may be further configured to: further monitor the digital conversation between the second entity and the third entity; determine that the digital conversation is related to the first entity; and further reassign the first entity to the problem solving entity group.

[0009] In another embodiment, the summary component can be further configured to: (a) identify a third time, wherein the third time is the time when the first entity is removed from the group of entities assigned to solve the problem; (b) identify a fourth time, wherein the fourth time is the current time when the problem is being solved by the second entity and the third entity; (c) determine activities performed by the second entity and the third entity in solving 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.

[0010] In another embodiment, the revocation entity component can be configured to: further monitor the digital conversation between the entity groups to identify a number of consecutive messages in the digital conversation during which a first entity in the entity group did not generate a message in the digital conversation; further determine whether the number of consecutive messages exceeds a threshold message number; and based on the number of consecutive messages exceeding the threshold message number, remove the first entity from the entity group assigned to resolve the issue.

[0011] In other embodiments, the elements described in conjunction with the disclosed system may be implemented in different forms, such as a computer-implemented method, a computer program product, or other forms. In one embodiment, a computer-implemented method may be performed by a device operably coupled to a processor, wherein the computer-implemented method may include: identifying a first entity to initiate resolution of a current problem, wherein the first entity may be identified based on a previous problem to which the first entity was previously assigned being similar to the previous problem; and assigning the first entity to initiate resolution of the current problem, wherein the current problem involves performance of an information technology operation.

[0012] In another embodiment, the computer-implemented method may further include: parsing digital content created by the first entity when attempting to solve the problem; reviewing one or more previous activities, wherein the previous activities involve the second entity; determining that the one or more previous activities involve the digital content; and further recommending that the second entity assist the first entity in solving the problem.

[0013] In another embodiment, the computer-implemented method may further include: monitoring the activities of the first entity and the second entity in attempting to resolve the problem; comparing the activities of the second entity in attempting to resolve the problem; determining that the second entity is no longer participating in attempting to resolve the problem; and further revoking the second entity's participation in resolving the problem. In an embodiment, determining that the second entity is no longer participating in attempting to resolve the problem may be based on at least one of a period of inactivity or an amount of digital content generated.

[0014] The computer-implemented method may further include: determining an engagement time, wherein the engagement time may be a time when the second entity joined the first entity to attempt to solve the problem. The computer-implemented method may further include: determining unobserved activities performed by the first entity between initiation of problem solving and the engagement time, wherein the unobserved activities are activities performed by at least the first entity in solving the problem; further generating a summary of the unobserved activities; and further providing the summary of the unobserved activities to the second entity.

[0015] Another embodiment may further include a computer program product stored on a non-transitory computer-readable medium and including machine-executable instructions, wherein in response to the machine-executable instructions being executed, it causes the machine to perform operations, the operations comprising: identifying a first entity to initiate resolution of a current problem, wherein the first entity is identified based on a previous problem previously assigned to the first entity being similar to the current problem, wherein the current problem involves the performance of an information technology operation.

[0016] In another embodiment, the operation may further include: parsing digital content created by the first entity when attempting to resolve the problem; reviewing one or more previous activities, wherein the previous activities involve the second entity; determining that the one or more previous activities involve the digital content; and further recommending that the second entity assist the first entity in resolving the problem.

[0017] In another embodiment, the operation may further include: monitoring the activities of the first entity and the second entity in attempting to resolve the problem; comparing the activities of the second entity in attempting to resolve the problem; determining that the second entity is no longer involved in attempting to resolve the problem; and further revoking the second entity's participation in resolving the problem.

[0018] In another embodiment, the operations may further include: determining an engagement time, wherein the engagement time is a time when the second entity joins the first entity to attempt to resolve the problem; and further determining unobserved activities performed by the first entity between initiation of the problem resolution and the engagement time, wherein the unobserved activities are activities 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 activities, wherein the summary is generated based on the operational role of the second entity; and providing the summary of the unobserved activities to the second entity. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] One or more embodiments are described below in the detailed description section with reference to the following drawings:

[0020] Figure 1 A system is shown that can be used to automatically assign one or more entities to assist in problem resolution in an IT environment in accordance with one or more embodiments.

[0021] Figure 2 is a schematic diagram providing a high-level overview of a dataset modified for application in a fusion language model according to one or more embodiments presented herein.

[0022] Figure 3 A schematic diagram is presented illustrating operations of respective components to automatically identify and recommend one or more entities to initiate problem resolution in accordance with one or more embodiments.

[0023] Figure 4 A diagram is presented illustrating operation of respective components to automatically recommend adding one or more entities to solve a problem in accordance with one or more embodiments.

[0024] Figure 5

[0013] Diagrams are presented illustrating operation of respective components to automatically identify and revoke participation of one or more entities in resolving a problem in accordance with one or more embodiments.

[0025] Figure 6is a diagram illustrating processing of one or more messages using an associated entity as part of a corresponding recommend entity operation / undo entity operation according to one or more embodiments.

[0026] Figure 7 is a diagram illustrating processing of one or more messages using an associated entity as part of a corresponding recommend entity operation / undo entity operation according to one or more embodiments.

[0027] Figure 8 is a schematic diagram illustrating summary generation for an entity according to an embodiment.

[0028] Fig. 9 A computer-implemented method for automatically assigning entities to projects and / or removing entities from projects to resolve issues is shown in accordance with one or more embodiments.

[0029] Fig.10 A computer-implemented method for automatically initially assigning entities to projects to resolve issues is shown in accordance with one or more embodiments.

[0030] Fig.11 A computer-implemented method for automatically recommending / assigning entities to projects to solve problems is shown in accordance with one or more embodiments.

[0031] Fig.12 A computer-implemented method for automatically generating a summary of unobserved activities of an entity during problem solving is presented in accordance with one or more embodiments.

[0032] Fig.13 A computer-implemented method for automatically removing an entity currently assigned to a project to resolve an issue is shown in accordance with one or more embodiments.

[0033] Fig.14 Depicted is an example schematic block diagram of a computing environment with which the disclosed subject matter may interact / be implemented, at least in part, in accordance with various aspects and embodiments of the subject disclosure. DETAILED DESCRIPTION

[0034] The following detailed description is merely illustrative and is not intended to limit the application or use of the embodiments and / or embodiments. In addition, it is not intended to be bound by any express and / or implied information presented in any of the foregoing background technology parts, summary of the invention parts and / or specific embodiments parts.

[0035] One or more embodiments are now described with reference to the accompanying drawings, wherein the same reference numerals are used to refer to the same elements throughout. In the following description, for the purpose of explanation, many specific details are set forth in order to provide a more thorough understanding of one or more embodiments. However, it is apparent that in various cases, one or more embodiments may be practiced without these specific details.

[0036] The range An and 1-i are used herein to indicate corresponding multiple devices, components, statements, attributes, etc., where n and i are any positive integers.

[0037] Solving problems / incidents in an IT environment / system can often be labor-intensive and inefficient. For example, in conventional IT operations, when an operational problem is detected, many entities (e.g., subject matter experts, developers, database administrators, network administrators, etc.) may be assigned to solve the problem, wherein such assignment may involve random assignment of the respective entities.

[0038] The application of various automated artificial intelligence (AI) (also known as AIOps) and machine learning (ML) techniques, technologies, operations, processes, etc. can assist in collecting data related to the problem and generating a "story" to provide information about aspects such as: What is the problem? Where is the problem detected (e.g., fault location), and which systems / services are affected by the problem? Similarly, however, poor implementation of subject matter experts, etc. may still lead to inefficient / costly problem solving. For example, due to the randomness of how entities are selected to solve the problem, the team of subject matter experts may be too large in terms of the number of team members, and further, some team members may have skill sets that are useful for solving the relevant parts of the problem, but at other times, these team members may have little to no involvement in solving the problem, but these team members are still included in the team to solve the problem. As a result, team members may be unnecessarily kept up to speed on / informed about how to solve the problem, when in fact, their attention can be focused on other matters that are no longer related to the solution of the above-mentioned problem.

[0039] Therefore, by way of non-limiting example, the following approaches would be helpful when the problem arises:

[0040] (a) only entities that are directly involved in problem solving to some degree (e.g., by initiating conflict resolution when a problem is detected) are brought online;

[0041] (b) when problem solving is ongoing, entities (e.g., necessary subject matter experts) are brought into the team as needed and are quickly informed of the work that has been done to solve the problem to date;

[0042] (c) the involvement of a particular entity in the problem-solving process is effectively curtailed / withdrawn when the particular expertise of that entity is no longer involved in solving the problem, for example so that the entity can work on other problems; and

[0043] (d) If an entity was previously involved in a project, has temporarily stopped participating in the project (e.g., has withdrawn its participation), and its participation is now required again, the entity can be recruited and quickly notified of the work that was done to resolve the issue while it was not involved.

[0044] 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., where the AIOps component further reviews the story to automatically determine one or more entities that may be assigned to resolve the problem. During problem resolution, any discussions between the various entities regarding problem resolution may be further analyzed / reviewed (e.g., by the various AIOps components) to determine whether the following situations arise: (a) another entity with the necessary skills should be involved in resolving the problem, and / or (b) an entity that is currently assigned to the project but no longer has relevant input in the project is allowed to leave the project to perform other tasks. If at any time an entity joins the team, e.g., was not initially involved in the project and / or rejoined the project, and therefore may not be aware of the work performed during its absence, an overview of the work performed may be provided to the entity to enable the entity to focus its attention on the problem as quickly as possible.

[0045] It should be understood that while the various embodiments presented herein relate to resolving issues / incidents in an IT environment / system, the various embodiments are not limited thereto and may be applied to any operation / process that can assign / remove entities to / from tasks based on identifying one or more entities associated with a task / function. In addition, while the various embodiments are directed to entities that are people, the entities may be in any applicable form. For example, the entity may be an automated process that can be employed / revoked as needed to resolve the issue.

[0046] Now turning to the attached figure, Figure 1 A system 100 is shown that can be used 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 problems 105 that have been identified as needing to be addressed / resolved, where the problems 105 can be in an initial unresolved state, an unresolved problem 105U, and a subsequent problem resolution state 105R. Activities associated with resolving a problem 105U are also referred to herein as "projects." Figure 1As shown, resolution of problem 105 may require applying / inputting unresolved problem 105U into a problem resolution system (IRS) 110, wherein IRS 110 may include various computer-executable components, techniques, processes, etc., which are configured to assist in resolving problem 105U, for example, by intelligently assigning and revoking one or more entities from participating in resolving problem 105, for example, by converting unresolved problem 105U into resolved problem 105R.

[0047] Figure 1 A high-level description of the configuration / operation of the IRS 110 and corresponding communicatively coupled components included therein is presented, wherein various embodiments are further described / explained in the subsequent figures / description.

[0048] As shown, the IRS 110 may include a problem resolution component (IRC) 115, wherein the IRC 115 may be configured to identify respective entities (e.g., subject matter experts) to be included / excluded from participating in one or more phases / processes / operations of implementing the resolved problem 105R. The IRC 115 may be communicatively coupled and further configured to utilize various other components, operations, processes, etc. in solving the problem 105. In an embodiment, a conversation component may be utilized to compile / archive one or more conversations 126A-n related to solving the problem 105U. In an embodiment, one or more conversations 126A-n may be conducted between respective entities 136A-n involved in attempting to implement the resolved problem 105R (e.g., at respective times). As further described, the conversations 126A-n may include more than one conversation topic / subject, e.g., the conversations 126A-n may include a collection of threads 127A-n, wherein, for example, a first thread 127A has a subject directed to network latency, and a second thread 127B has a subject directed to how to receive / process client data. As further described, the topics / themes of the respective threads 127A-n may be isolated and used to identify / determine which entities 136A-n should participate in resolving the problem 105U, when the participation of the entities 136A-n should occur, the focus of attention of the respective entities 136A-n, etc.

[0049] The IRC 115 may also be coupled to an initial entity component 135. The initial entity component 135 may be configured to review the problem information 106A-n and further configured to identify the respective entities 136A-n to initially recruit / engage / engage in the initial stages of resolving the unresolved problem 105U. As further described, the initial entity component 135 may be configured to identify the respective entities 136A-n by matching previous problems 138A-n (e.g., content, parameters, activities, etc.) that the respective entities 136A-n have addressed with circumstances related to the unresolved problem 105U, as detailed in the problem information 106A-n.

[0050] The question component 139 may reside and operate from within the IRS 110, reside and operate from within one or more components communicatively coupled in the IRS 110, or reside and operate from outside the IRS 110. The question component 139 may be configured to compile information and generate previous question 138A-n information. In addition, during and after solving the problem 105U, the question component 139 may be configured to compile information about the corresponding activities / utterances / conversations, etc. generated by the corresponding entities 136A-n when solving the problem 105U and update the previous question 138A-n information to ensure that the previous question 138A-n information includes the most recent problem solving activities performed by the corresponding entities for future use in identifying and recommending entities to be added to subsequent problem solving projects. In an embodiment, the status component 170 may be used to update the status of the problem 105U. For example, state component 170 may be configured to receive input indicating that issue 105U has been resolved, which is updated to resolved issue 105R, and further, instructions may be sent from state component 170 instructing issue component 139 to update prior issue 138A-n information using issue resolution activities performed by the corresponding entity during resolution of issue 105U.

[0051] like Figure 1 As shown, in an embodiment, the IRC 115 may also be communicatively coupled to a recommend entity component 140 and a withdraw entity component 145. As further described, as the attempt to solve the problem 105U proceeds, 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 recommend entity component 140 regarding whether an entity 136A-n having skills / knowledge relevant to the current state / situation of the problem 105U should be added to the team solving the problem 105U. In another embodiment, the IRC 115 may similarly be communicatively coupled to a withdraw entity component 145, which is configured to make a determination regarding whether an entity 136A-n currently participating in the project should be withdrawn from the project work. In an embodiment, the summary component 150 may be configured to generate one or more summaries 152A-n, wherein the summaries 152A-n may be provided to the entity 136A-n regarding the work performed so far in the attempt to solve the problem 105U.

[0052] When an unresolved issue 105U becomes resolved to create a resolved issue 105R, the resolved issue 105R may be received at the state component 170. In an embodiment, the entity 136A-n may generate a notification indicating that the issue 105R has been implemented (e.g., as part of a conversation 126), whereupon the state component 170 may be configured to initiate an update of the previous issue 138A-n to include the conversation 126A-n / thread 127A-n associated / generated with the resolution of the issue 105U / 105R. Updating the previous issue 138A-n with the conversation 126A-n / thread 127A-n enables the activities of the corresponding entity 136A-n to be updated for review during the resolution of a subsequent / future issue 105F.

[0053] like Figure 1 As shown, the IRS 110 may further include a computer system 180. The computer system 180 may include a memory 184 storing corresponding computer executable components (e.g., IRC 115, conversation component 120, initial entity component 135, recommended entity component 140, revoked entity component 145, summary component 150, etc.), and further includes a processor 182 configured to execute the computer executable components stored in the memory 184. The memory 184 may be further configured to store any of the question information 106A-n, conversations 126A-n, threads 127A-n, information about entities 136A-n, previous questions 138A-n, summaries 152A-n, unresolved questions 105U, resolved questions 105R, questions 105, thresholds 520A-n (as described later), etc. The computer system 180 may further include a human-machine interface (HMI) 186 (e.g., display, graphical user interface (GUI)), which may be configured to present various information including unresolved questions 105U, resolved questions 105R, dialogues 126A-n, etc. according to various embodiments presented herein. The HMI 186 may include an interactive display / screen 187 to present various information. The computer system 180 may further include an I / O component 188 for receiving and / or sending corresponding questions 105U / 105R, dialogues 126A-n, etc.

[0054] In the description Figure 1 Prior to the operation and / or configuration of the corresponding components presented in the description, an example scenario of problem solving is presented in combination with the interaction of the corresponding components. Figure 2 The example scenario 200 shows a problem being detected and various entities being automatically assigned to resolve the problem.

[0055] Figure 2Schematic diagram 200 presents a high-level overview of a dataset 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 actions / steps 1-13.

[0056] At 200-1, an issue occurs, unresolved issue 105U. Unresolved issue 105U may have data / information 106A associated therewith, wherein information 106A details what is currently known about unresolved issue 105U, e.g., the issue is a network delay identified in network #6, impacting electronic payment services, where payment backlogs are of concern. In an embodiment, information 106A may be generated by an AIOps component (e.g., issue component 139) configured to compile information 106A into a story, wherein the AIOps component may be located internal to IRS 110 (e.g., the AIOps component receives information about issue 105U and further compiles the information to create information 106A) or external to IRS 110 (e.g., receives information 106A in compiled form).

[0057] At 200-2, the initial entity component 135 can be configured to review the information 106A and further recommend one or more entities 136A-n to be initially assigned to resolve the problem 105U. As further described, the initial entity component 135 can review previous problems 138A-n in which the respective entities 136A-n have participated, thereby identifying prospective entities 136A-n to be assigned to resolve the unresolved problem 105U.

[0058] At 200-3, entity 136A participates in solving problem 105U. Entity 136A generates a dialogue 126A that provides an initial assessment of the situation regarding problem 105U. Dialogue 126A may be in any suitable manner, such as email, electronic event log, etc., where dialogue 126A is in a format that can be automatically reviewed. In an embodiment, corresponding dialogues 126A-n may be compiled / organized into channels / workspaces / repositories so that dialogues 126A-n include / contain any / all comments, threads, discourses, conversations, topics, team reviews, activities, actions, projects, etc. related to solving unresolved problems 105U.

[0059] At 200-4, the dialog component 120 reviews the dialog 126A, and based on text matching, etc., the dialog component 120 identifies one or more sub-problems about the problem 105U that are related to the knowledge / skill set of the entity 136B, and based on this, the dialog component 120 recommends that the entity 136B join the entity 136A to solve the problem 105U.

[0060] At 200-5, the entity 136B generates a further dialog 126A, eg, "Router not responding," etc.

[0061] At 200-6, the dialog component 120 reviews the continuous dialog 126A and identifies one or more sub-problems regarding the problem 105U that are related to the knowledge / skill set of the entity 136C, and based on this, the dialog component 120 recommends that the entity 136C join the entities 136A and 136B to form the entity group assigned to solve the problem 105U.

[0062] At 200-7, the entity 136C generates further dialog 126A, for example, to determine why the router is not responding, etc.

[0063] At 200-8, the withdraw entity component 145 reviews the continuous conversation 126A, and based on the identification that (a) entity 136C is solving the problem, (b) entity 136A has not participated in solving the problem / lack of conversation activity for a period of time, and similarly, the withdraw entity component 145 automatically recommends that the presence of entity 136A in the entity group be withdrawn / terminated due to entity 136A's recent lack of participation in solving the problem 105U. Therefore, entity 136A is removed from solving the problem 105U.

[0064] At 200-9, a further conversation 126A is conducted between entities 136C and 136B regarding solving problem 105U. During this time, the content of conversation 126A (e.g., threads 127A-n) can be continuously reviewed / evaluated by both withdraw entity component 145 and recommend entity component 140 to determine whether the entity's participation in solving problem 105U should be withdrawn and / or whether entity 136A-n should be added to the group of entities solving problem 105U.

[0065] At 200-10, the recommend entity component 140 determines that a sub-problem has occurred that the entity 136A may be able to solve based on the review of the conversation 126A. Therefore, the recommend entity component 140 recommends that the entity 136A rejoin the group of entities (e.g., entities 136B and 136C) assigned to solve the problem 105U. The entity 136A is reassigned to assist in solving the problem 105U.

[0066] At 200-11, as previously described, during a time period when entity 136A was not involved in solving problem 105U, summary component 150 may be configured to identify activities / content generated that entity 136A was unaware of (e.g., in a conversation between entities 136B and 136C). Based on the unobserved activities / content, summary component 150 may be configured to generate summary 152A, with content that enables entity 136A to be quickly brought in to accelerate understanding of progress regarding solving problem 105U. In addition, based on knowing the role / expertise of entity 136A, summary component 150 may be further configured to generate summary 152A so that summary 152A is customized for entity 136A, for example, portions of the summary that are specifically related to entity 136A may be highlighted, portions of the summary that are not related to entity 136A may be omitted, and the like.

[0067] At 200-12, entity 136A rejoins the group of entities (e.g., entities 136B and 136C), generating further activity (e.g., further conversations 126A, other conversations 126B-n, further threads 127A-n, etc.), which can be further reviewed by recommend entity component 140, withdraw entity component 145, compiled by conversation component 120, etc. Thus, 136A-n entities can participate / be brought online to solve 105U problem and / or withdrawn from solving 105U problem.

[0068] At 200-13, in accordance with the foregoing, the problem 105U becomes a resolved problem 105R. In an embodiment, the previous problem data 138A-n may be updated (e.g., via the problem component 139, the initial entity component 135, the data update component, etc.) with various activities, conversations 126A-n, etc. conducted by the respective entities 136A-n that participated in the resolved problem 105R. The updated previous problem data 138A-n may be used when assigning entities 136A-n to future unresolved problems 105.

[0069] Go to Figure 3, schematic diagram 300 illustrates operations for automatically identifying and recommending one or more entities to initiate resolution of an issue according to one or more embodiments by respective components. As previously described, the IRS 110 may include an initial entity component 135 configured to review data / information 106A-n related to an unresolved issue 105U, and further identify / recommend one or more entities 136A-n to initiate a process of resolving the issue 105U. The initial entity component 135 may be communicatively coupled to the IRC 115, wherein the IRC 115 may be configured to utilize the initial entity component 135 to initiate assignment of resolution of the issue 105U to respective initial entities 136A-n. The IRC 115 may be configured to employ the initial entity component 135 based on, for example, receiving information 106A-n (e.g., from an external source or generated internally), receiving a notification (not shown) that the issue 105U has been detected / identified, and the like. In an embodiment, the initial entity component 135 may include a similarity component 310 that is configured to determine / identify the closeness of one or more content items in the information data 106A to previous issues 138A-n that the corresponding entity 136A-n has previously participated in. The similarity component 310 may be configured to determine similarities based on text, semantics, textual summaries, etc. between various items of interest (e.g., pairing of current issue information 106A-n and previous issue information 138A-n). In an example embodiment, the similarity component 310 may be a Bidirectional and Autoregressive Transformer (BART) model architecture, however, it should be understood that any suitable model / AI technique / AI architecture may be utilized to identify the entity 136A-n assigned to solve the issue 105U based on the previous issues 138A-n that the corresponding entity 136A-n has handled.

[0070] like Figure 3 As shown, the information 106A-n related to the unresolved question 105U can be compared with data related to previous questions 138A-n in which the corresponding entity 136A-n has participated. Figure 3 136A-n is identified as N-IR (New Issue Report), while data related to previous issues 138A-n is identified as P-IR (Previous Issue Report), such that information 106A-n in previous issue 138A associated with entity 136A is identified as P-IR1, data in previous issue 138B associated with entity 136B is identified as P-IR2, data in previous issue 138C associated with entity 136C is identified as P-IR3, and data in previous issue 138n associated with entity 136n is identified as P-IR nEtc. It should be appreciated that the PI-R data related to previous issues 138A-n may include a single previous issue / event that the entities 136A-n previously participated in, or multiple previous issues that the entities 136A-n previously participated in. For example, P-IR1 may include a single previous issue or multiple previous issues for the entity 136A.

[0071] like Figure 3 As shown, the similarity component 310 can be configured to compare new problem reports with previous problem reports (e.g., N-IR and P-IR). 1-n ), and further for the corresponding pairs N-IR:P-IR1, N-IR:P-IR2, N-IR:P-IR3...N-IR:P-IR n Provides similarity score S1-S N .like Figure 3 As further shown in FIG. 1 , the similarity component 310 can be further configured to use similarity scores S1-S N To generate the corresponding pairs N-IR:P-IR1, N-IR:P-IR2, N-IR:P-IR3…N-IR:P-IR n 330 (e.g., a "k" ranking) of similarities to the unsolved problem 105U, and based thereon, identifying one or more entities 136A-n having prior experience that is potentially / directly relevant to the unsolved problem 105U that can be assigned by the initial entity component 135 to solve the problem 105U (e.g., based on Figure 2 , action 200-2). For example, relative to the one with lower similarity score S D Entity 136D is recommended to have the highest similarity score S F Entity 136F makes the first content in N-IR and P-IR D The second item in the .

[0072] Go to Figure 4, schematic diagram 400 illustrates the operation of automatically recommending one or more entities to be added to resolve the problem according to one or more embodiments. As previously described, the IRS 110 may include a recommend entity component 140 configured to review the conversations 126A-n and the corresponding interactions between one or more entities 136A-n currently (or previously) involved in resolving the problem 105U, and based thereon, the recommend entity component 140 may be further configured to identify / recommend one or more entities 136A-n to join the entity group for resolving the problem 105U. The recommend entity component 140 may be communicatively coupled to the IRC 115, wherein the IRC 115 may be configured to utilize the recommend entity component 140 in generating and adding / conducting the corresponding conversations 126A-n. For example, when entity 136A generates a comment about the problem 105U in the conversation 126A-n, the recommend entity component 140 may be configured to automatically parse the new comment to identify / determine whether another entity (e.g., entity 136B) should be brought online to assist in resolving the problem 105U.

[0073] like Figure 4 As shown, for example, based on the dialog component 120 capturing corresponding comments / statements / actions performed by the various entities 136A-n involved in solving the problem 105U, the dialog 126A has been generated. Figure 4 The example sentences presented in are taken from Figure 2 105U. Although the example presented for the dialogue 126A is simple and includes a small number of statements, it should be understood that the dialogue 126A can be highly complex and include many statements, content, actions, comments, etc. generated by or related to the actions performed by the corresponding entities 136A-n in solving the problem 105U, etc. Therefore, considering that the dialogue component 120 can compile / generate the dialogue 126A from many sources / data / comments / etc., the dialogue 126A can include multiple threads 127A-n (further labeled C1-C 107 below) of dialogue topics / issues / themes / etc. n ). For example, conversation 126A may include a discussion between two entities 136A and 136B regarding router operations associated with problem 105U (eg, captured by conversation component 120), while another discussion between entities 136A and 136C is about how to process electronic payments.

[0074] As further shown, the recommendation entity component 140 can further include a conversation disassembly component 410, wherein the conversation disassembly component 410 can be configured to review / parse the entire conversation 126A captured / compiled by the conversation component 120, and further identify / extract the corresponding threads 127A-n of the corresponding topics in the conversation 126A. The conversation disassembly component 410 can utilize any suitable technology, such as AI / ML technology, algorithms, models, architectures, etc., to enable the corresponding threads 127A-n to be identified / disassembled.

[0075] exist Figure 4 In the example scenario shown, the conversation disassembly component 410 has identified various conversation threads 127A-n, wherein the corresponding threads 127A-n are Figure 4 Identified as C1, C2, ...C n In addition, each conversation thread C1, C2, ...C n Further presented as a series of entities E 1-n Pair with Message M 1-n , where each message in the corresponding conversation thread is a reply / response to a previous message, e.g., M2 is the entity's response to M1, M3 is the entity's response to M2, etc.

[0076] For each thread 127A-n / C1, C2, ...C n The context is based on or generated from the corresponding response and message pair. For example, for recommending an entity {E3 i} is based on the previous entity and message pairing [(E1 i ,E2 i ),(M1 i ,M2 i )].

[0077] In an embodiment, for each conversation thread C i , the total number of context-response pairs = {(C i Message in M 1-i total number of) - 1, so the total number of response pairs is greater than the number of messages M in a particular thread. 1-n The total number is one less.

[0078] Once the various threads 127A-n / C have been identified 1-n and the corresponding entity E 1-n and message M 1-n Pairing, can be a variety of threads 127A-n / C 1-nThe AI ​​architecture is applied to an AI architecture that has been previously trained using previous conversations 126A-n and threads 127-n. As further described, the same AI architecture can be utilized to create the entity identifier component 420 as well as the revocation component (entity identifier component 530). Thus, the goal of training the AI ​​architecture to form the entity identifier component 420 is to identify entities 136A-n (e.g., entity E3) to be recommended and involved in solving the problem 105U. Therefore, based on the use of conversations 126A-n and threads 127A-n / C 1-n Trained on previous instances of the problem 105U, the recommended entity component 140 (eg, operating as a trained recommended entity model) can subsequently identify / recommend one or more entities 136A-n to join the set of entities that solve the problem 105U.

[0079] According to the above content, Figure 4 1 shows how the AI ​​architecture can be trained to create an entity identifier component 420, and further, how the threads 127A-n of the current ongoing conversation 126A can be disassembled from the conversation 126A and how entities 136A-n can be identified from the previous sequence of resource and message pairings. Thus, when the current conversation 126A is applied to the previously trained entity identifier component 420, the entity identifier component 420 combines the corresponding entity E based on the various threads 127A-n in the current conversation 126A. 1-n and message M 1-n The pairing is used to identify the entities 136A-n.

[0080] As previously described, the same underlying architecture may be utilized to create the recommendation entity component 140 and the withdrawal entity component 145 . Figure 5 Schematic diagram 500 illustrates operation of respective components to automatically identify and revoke participation of one or more entities in resolving a problem in accordance with one or more embodiments.

[0081] As previously in Figure 4 As described in, various threads 127A-n can be disassembled from conversations 126A-n so that one or more entities 136A-n can be identified as potentially useful in solving problem 105U, wherein recommend entity component 140 is configured to automatically identify and recommend the determined entities 136A-n. In alternative applications, revoke entity component 145 can also use the determined information about one or more entities 136A-n to identify that the corresponding entity is no longer involved in solving problem 105U, and therefore, revoke entity component 145 can be configured to remove the identified entity from the project of solving problem 105U.

[0082] Figure 5Schematic diagram 500 depicts an example process / operation for converting corresponding words / sentences into mathematical representations that enable corresponding recommendation and revocation operations to be performed according to one or more embodiments.

[0083] Based on the foregoing description regarding identifying corresponding entities 136A-n in conversation 126A, entities 136A-n that have previously participated in the project to solve problem 105U but are no longer involved in the project (e.g., whose particular skills / knowledge are not relevant to the ongoing situation regarding problem 105U) can be identified and removed from the group of entities 136A-n that solve problem 105U.

[0084] In an embodiment, the undo entity component 145 can be configured to identify the last message / action (e.g., entity 136A posted a message) with which the entity (e.g., entity 136A) is associated. In an embodiment, the undo entity component 145 can include an activity component 510 in combination with the previously mentioned conversation teardown component 410. As previously described, the conversation teardown component 410 can be configured to identify / tear down the corresponding threads 127A-n / C1-C2 in the conversation 126A. n Activity component 510 may be configured to identify the last message / activity involving entity 136A and further identify the most recent message / activity in conversation 126A. Activity component 510 may be configured to further determine the time since the last message was posted (e.g., E3 1 :M3 1 is the last message posted by entity 136A) and the most recent message in conversation 126A (e.g., entity 136A is not involved in E n 1 :M n 1 message) and / or the current time.

[0085] Additionally, activity component 510 can be assigned activity threshold 520, where activity threshold 520 is a defined time period for which entity 136A-n activity is measured. Thus, and in the event that time T is equal to or greater than the value of activity threshold 520, revoke entity component 145 can be configured to revoke entity 136A's participation / interaction with the project, where time T relates to entity 136A's activity.

[0086] In another embodiment, from the identified message (E3 1 :M3 1 ) to a subsequent message (e.g., the latest / previous message E in a conversation 126A-n) n 1 :M n 1) can be determined by the revoking entity component 145, and in the event that the message count NM is equal to or greater than the defined message count (e.g., where the threshold 520D is the message count threshold), the revoking entity component 145 can be configured to revoke the entity 136A's participation / interaction with the project. It should be understood that any suitable method / technique can be utilized to determine that the entity 136A-n is not participating in the project, such as time, message count, etc.

[0087] With respect to identifying entities 136A-n, recommending entity component 140 may include entity identifier component 420, and revoking entity component 145 may include entity identifier component 530, wherein reference Figure 6 and Figure 7 The operation of the entity identifier component 420 / 530 is further described.

[0088] Figure 6 and Figure 7 A schematic diagram of example operations for mathematically representing conversations / messages / threads and entities to enable similarity analysis and the like to be performed, such as by recommend entity component 140 and / or withdraw entity component 145 , is presented.

[0089] Figure 6 Schematic diagram 600 shows the processing of one or more messages using associated entities as part of a corresponding recommended entity operation / undo entity operation according to one or more embodiments. As shown, a message M (e.g., where the message M is included in a conversation 126A-n / thread 127A-n) is processed by a tokenizer 610 (or other applicable operation / processing), and the tokenizer 610 is configured to separate a sentence (e.g., an utterance / digital input made by an entity 136A in a conversation 126A) into corresponding words W1-n. In an example embodiment, the tokenizer 610 can be further configured to apply the corresponding words to a long short-term memory network (LSTM) operation 620A-n, and the message embedding component 630 can be configured to embed the corresponding words W in the sentence. 1-n The corresponding LSTM values ​​are combined to create an embedding value V, where V is a mathematical representation (e.g., a vector representation) of the message M.

[0090] Figure 7 Schematic diagram 700 shows the processing of one or more messages using associated entities as part of a corresponding recommended entity operation / undo entity operation according to one or more embodiments. As further shown, each entity 136A-n can also be mathematically represented as an entity sequence E R = [E1 E2...E n-1 ], where E RThe entity context (also called resource context) of the entity 136A-n involved in generating a series of messages (eg, in a conversation 126A-n, thread 127A-n). R can be applied to the sentence state LSTM (S-LSTM) 720 (or other applicable operations / processing) to generate V E , where V E Is to generate a message M in the conversation 126A-n / thread 127A-n of interest 1-n A mathematical representation (eg, a vector representation) of the respective entities 136A-n involved.

[0091] As further shown, corresponding messages M generated by corresponding entities 136A-n in one or more threads 127A-n of interest in conversations 126A-n. 1-n can be processed to generate corresponding message contexts M1, M2, ... M n-1 Mathematical representation of V C (eg, vector representation). As shown, the corresponding S-LSTM process 730A-n (or other applicable operations / processes) can be configured to sequentially combine the message contexts M1, M2, ..., M n-1 To generate V C .

[0092] As further shown, mathematically, V E (Entity) and V C (Message Context) can be applied to messages that are configured to generate E i A feed-forward classifier 740 (or other applicable operation / processing) wherein E i Entities 136A-n that may be automatically recommended for addition to the set of entities 136A-n for solving problem 105U (e.g., where Figure 6 and Figure 7 The operations depicted in the example form part of the entity identifier component 420 in the recommended entity component 140), or are automatically withdrawn from the group of entities 136A-n (where Figure 6 and Figure 7 The operations depicted in form part of the entity identifier component 530 in the revoking entity component 145) are entities 136A-n currently in the project responsible for resolving the issue 105U.

[0093] As previously described, a first entity (eg, entity 136H) may join the ongoing process to resolve issue 105U, and further, a second entity (eg, entity 136R) that previously assisted in resolving issue 105U but was subsequently withdrawn may rejoin the project.

[0094] Figure 8Schematic diagram 800 shows summary generation for an entity according to an embodiment. As shown, reference Figure 1 , the summary component 150 can be communicatively coupled to the recommending entity component 140 and / or the withdrawing entity component 145, and further communicatively coupled to the IRC 115. The summary component 150 can be configured to determine a time period during which the entity 136R or 136H was not participating in the project, and further configured to generate summaries 152A-n including unobserved content. The summary component 150 can further include an artifact summarizer 820 configured to summarize the various artifacts 810A-n. The summary component 150 can further include a complete conversation summarizer 830 configured to generate summaries 152A-n compiled from the corresponding artifacts 810A-n, and in another embodiment, generate summaries 152A-n customized to the role / requirements of the receiving entity 136A-n.

[0095] As previously described, the conversation 126A may include multiple threads 127A-n (e.g., topics, themes, etc.), where the threads 127A-n may be further categorized / presented as artifacts 810A-n, such as (a) evidence 810A related to the problem 105U, (b) actions 810B performed by the corresponding entity 136A-n in solving the problem 105U, (c) investigations 810C performed by the corresponding entity 136A-n in solving the problem 105U, (d) any identified solutions 810D, etc. The summary component 150 may generate summaries 152A-n, which include one or more summaries for the corresponding threads 127A-n for the time period when the entity 136A-n was absent from the project. For example, for an entity 136H that was absent from the project but was brought in when the solution of the problem 105U was in progress. In another example, entity 136R initially participates in a project, later withdraws from the project (eg, by withdrawing entity component 145 ), and rejoins the project (eg, by recommending entity component 140 ).

[0096] Thus, profile 152H for entity 136H will provide a summary of various threads 127A-n from the time the project was initiated until the time entity 136H joined the project, while profile 152R will provide a summary of various threads 127A-n during the time period when entity 136R was withdrawn from the project. The role / knowledge of the respective entity 136A-n receiving the respective profile 152A-n can be provided to the profile component 150, enabling the profile component 150 to tailor / personalize the respective profile 152A-n to the focus of the receiving entity 136A-n.

[0097] In an embodiment, the summarization component 150 may include a large language model (LLM) or a similar component configured to summarize the corresponding message M in a particular thread. 1-n, and corresponding messages M of the set of threads 127A-n associated with solving the problem 105U 1-n In embodiments, summaries 152A-n may have multiple levels of content, for example, each of threads 127A-n / artifacts 810A-n may be summarized individually and further provided as a summary combining the respective threads 127A-n / artifacts into a single summary 152A-n.

[0098] It should be understood that the various operations presented throughout this disclosure are merely examples of corresponding AI and ML operations and techniques, and any suitable technology may be utilized according to the various embodiments presented herein, including but not limited to any of LSTM, deep learning algorithms, sequential neural networks, sequential neural networks that implement persistent information, recurrent neural networks (RNNs), Bidirectional Encoder Representations Based on Transformers (BERT) models, Bidirectional and Autoregressive Transformers (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, etc. For example, according to Figure 4 and Figure 5 , the operations of the corresponding recommendation and revocation components / models are simple examples of how the corresponding content of the conversations 126A-n and the entities 136A-n associated therewith can be mathematically represented and processed to implement recommendation and / or revocation operations. Therefore, any suitable operations / techniques / processes can be utilized to facilitate any corresponding operations / processes presented herein. For example, any suitable operations / techniques / processes can be utilized to facilitate the automatic identification of one or more entities 136A-n as part of an automatic recommendation or revocation operation. In addition, although the recommendation model and revocation model depicted herein are depicted as using the same underlying mathematical methods, various embodiments are not limited to this, and the recommendation model and revocation model can also utilize different techniques.

[0099] Language models, LSTM, BART, etc. can be formed using highly complex neural networks, for example, including billions of weighted parameters. The training of LSTM can be performed using a data set, where the data set can be formed using any suitable technology, such as the question component 139 generating previous question information 138A-n for the corresponding entity (to be used by the recommended entity component 140 / revoked entity component 145, the summary component 150, the initial entity component 135, the dialogue component 120, etc.), the dialogue component 120 compiling dialogues 126A-n, etc. The data set can be obtained from many sources, for example, collected by an IT enterprise, provided by a client, provided by a third party, etc. In addition, the data set can include text, alphanumeric, numeric, single words, phrases, short sentences, long sentences, images, audio, etc. Fine-tuning of the LM can include applying the data set to the LM, adjusting the LM accordingly by applying the data set, so that, for example, the weights in the LM are adjusted by applying the data set.

[0100] Fig. 9 Method 900 illustrates a computer-implemented method for automatically assigning an entity to a project for problem resolution and / or removing an entity from the project in accordance with one or more embodiments.

[0101] At 910, data / information regarding previous problems (e.g., previous problems 138A-n) that have been previously handled / 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 described, the problem component may reside and operate within the problem resolution system (e.g., IRS 110) / in one of the communicatively coupled components included within the IRS, or the problem component may reside and operate external to the IRS.

[0102] At 920 , data / information regarding unresolved questions (eg, unresolved questions 105U) may also be compiled and stored by the question component (eg, as information 106A-n in memory 184 ).

[0103] At 930, the content of the unresolved issue information can be reviewed to determine whether one or more entities have previously handled one or more issues related to the unresolved issue. For example, an initial entity component (e.g., initial entity component 135) can review the unresolved issue information issue and extract one or more content (e.g., elements, actions, parameters, activities, etc.) about the unresolved issue. The one or more content can be compared with one or more content in previous issues involved by the corresponding entity. In the event that the entity has been involved in a previous issue that has similarities to the current unresolved issue (e.g., the first content related to the unresolved issue matches / similar to the second content related to the current unresolved issue), the initial entity component can be configured to automatically select the identified entity and assign the entity to resolve the unresolved issue, where the identified entity can operate as a single individual or as part of an initially formed group / team to resolve the unresolved issue.

[0104] At 940, as one or more entities work to resolve the issue, a conversation component (e.g., conversation component 120) may be configured to compile various emails, statements, utterances, activities, etc. generated / performed by the one or more entities while working to resolve the issue, where the various emails, activity statements, actions, etc. may be compiled in a conversation regarding resolving the issue (e.g., conversation 126A).

[0105] As previously described, the conversation can include various conversation threads (e.g., threads 127A-n) about different topics / topics related to the unresolved issues. A conversation disassembly component (e.g., conversation disassembly component 410) can be configured to identify and extract / disassemble various threads from the conversation, where the threads can be used to recommend entities to / remove entities from the project. As previously described, the location and / or implementation of the disassembly component can be at any one of the conversation component, the recommend entity component (e.g., recommend entity component 140), and / or the revoke entity component (e.g., revoke entity component 145).

[0106] At 950, as previously described, the recommend entity component can be configured to analyze the corresponding thread to automatically identify entities with skills that can be applicable to solving the current sub-problem / activity in the problem. The recommend entity component can be configured to recommend entities based on a comparison and match of the content of one or more threads with previous problem information of the corresponding entity.

[0107] At 960, when an entity is assigned to assist with problem solving, a summary component (e.g., summary component 150) can be configured to determine a time period during which the entity was absent from the ongoing problem solving. The summary component can be further configured to generate a summary for the entity (e.g., summary 152A-n), wherein the summary provides a summary of various communications, actions, etc. performed during the time period during which the entity was absent from the problem solving. The summary can be customized to the needs of the entity (e.g., the skill set of the entity) so that the entity can be quickly brought in to accelerate understanding of the current status of the problem solving and the work performed to date in attempting to solve the problem.

[0108] At 970, as previously described, while the recommend entity component is used to identify / recruit one or more entities to be assigned to the project, the remove entity component can be configured to analyze the corresponding thread to automatically identify entities that are no longer involved in resolving the problem, even if the entity is currently assigned to resolve the problem. The remove entity component can be configured to remove the entity based on a duration (e.g., measured based on time T, measured based on message volume NM, etc.) that the identified entity has not been involved in the project, where the duration exceeds a defined value (e.g., threshold 520A-n).

[0109] At 980, it can be determined whether the unresolved issue has been resolved (e.g., turned into resolved issue 105R). In response to determining that no, the issue has not been resolved, method 900 can proceed to 990 to further analyze the unresolved issues to be performed, and further return to 940 to further add / remove entities to the project.

[0110] Furthermore, at 980, in response to determining that yes, the problem has been solved, method 900 can proceed to 995, whereupon corresponding activities, conversations, problems, etc. can be respectively compiled for the participation of corresponding entities in the project, wherein a previous problem database (e.g., previous problems 138A-n) is updated (e.g., by problem component 139) as entities participate in solving problems. Thus, in the event that the previous problem database is updated, the updated information can be utilized to determine one or more initial entities and / or recommended entities for solving future problems.

[0111] Fig.10 Method 1000 illustrates a computer-implemented method for automatically initially assigning entities to projects to resolve issues in accordance with one or more embodiments.

[0112] At 1010, information about a current issue (eg, unresolved issue 105U) can be received at the system (eg, by IRS 110, issue component 139, etc.) In an embodiment, the current issue can be an operational event in an information technology system.

[0113] At 1020 , the current problem information can be parsed (eg, by problem component 139 ) to identify content, actions, etc. that can be performed by various entities (eg, any of entities 136A-n) having corresponding skill sets / knowledge regarding solving the problem.

[0114] At 1030, a previous question (e.g., previous question 138A-n) can be obtained by an initial entity component (e.g., initial entity component 135), where the previous question has associated activities / utterances / conversations, etc. performed by a corresponding entity (e.g., any of entities 136A-n) during resolution of the previous question, where the corresponding entity can be used to handle / resolve the current question.

[0115] At 1040, the initial entity component may be configured to parse the current question and the previous question to identify / generate one or more pairs between the current question information in the current question and the previous question information in the previous question. As previously described, the first data in the current question information (e.g., N-IR, new question report in information 106A) may be associated with the corresponding second data in the previous question information associated with the corresponding entity (e.g., P-IR 1-n , previous issue report in previous issue 138a-n) pairing.

[0116] At 1050, the corresponding similarity between the current question information and the previous question information can be determined by a similarity component (eg, similarity component 310). In an embodiment, the corresponding current question information and previous question information pair N-IR:P-IR can be represented using a vector representation 1-n .

[0117] At 1060, based on the corresponding pairing N-IR:P-IR 1-n The corresponding vector proximity between them can generate a corresponding similarity score (e.g., K score) for each pair.

[0118] At 1070, pair N-IR:P-IR 1-n can be composed of similarity components based on their corresponding similarity scores (e.g., S1-S n ), and further identified by the similarity component a corresponding entity associated with each pairing. Thus, the likelihood of a single entity's skill set being relevant to solving a problem can be determined based on the entity's corresponding position in the ranked similarity scores. For example, a high similarity score for a pairing indicates that the entity associated with the pairing is likely to have skills applicable to solving the current problem, while a low similarity score for the pairing indicates that the entity associated with the pairing is likely to have few, if any, skills applicable to solving the problem.

[0119] At 1080 , the initial entity component can be further configured to recommend entities with the highest (or higher) similarity scores to be initially assigned to assist in solving the current problem.

[0120] Fig.11 Method 1100 illustrates a computer-implemented method for automatically recommending / assigning entities to projects to solve problems in accordance with one or more embodiments.

[0121] At 1110, a dialog component (e.g., dialog component 120) may be configured to compile ongoing activities / utterances / digital dialogs / digital inputs / entries performed while solving the current problem, and further generate a dialog (e.g., as dialogs 126A-n) based on the compiled information. The dialog component may be configured to continuously update the dialog as new activities / inputs are generated / received.

[0122] At 1120, the conversation can be broken down by a conversation breakup component (e.g., conversation breakup component 410) to identify one or more threads (e.g., threads 127A-n) included in the conversation, wherein the one or more threads can be respectively associated with various topics, themes, etc., as described above.

[0123] At 1130, the thread can be applied to a recommend entity component (e.g., recommend entity component 140), where the recommend entity component may have been previously trained using one or more datasets that include sequences of utterances, actions, etc. between various entities when solving a problem. By training the recommend entity component using the one or more datasets, the recommend entity component (e.g., a mathematical model) can be configured to predict subsequent entities based on previous sequences of corresponding utterances and the corresponding entities that generated them.

[0124] At 1140 , based on previous training of the recommend entity component, the recommend entity component can be configured to recommend entities recognized in the current conversation / thread, as well as the entities that created them, as a function of a training data set on previous utterances, etc.

[0125] At 1150, the recommended entity can be assigned to the problem-solving project.

[0126] Fig.12 Method 1200 illustrates a computer-implemented method for automatically generating a summary of activities not observed by an entity during problem resolution in accordance with one or more embodiments.

[0127] At 1210, a notification can be received at a summary component (e.g., summary component 150) that an entity (e.g., entity 136A-n) has been assigned to resolve an issue (e.g., issue 105U). The entity can be assigned as part of an automatic entity recommendation operation performed by a recommend entity component (e.g., recommend entity component 140), wherein the notification can be generated and sent by the recommend entity component and received / processed by the summary component, wherein the notification further identifies the entity to join the group of one or more entities assigned to resolve the issue.

[0128] At 1220, the summary component can be configured to identify / determine the duration and / or amount of activity performed by one or more entities involved in resolving the problem.As previously mentioned with respect to the operation and functionality of the initial entity component 135, an entity can be assigned to resolve the problem upon initiation of an activity. However, as previously described, (a) an entity may be assigned to resolve an issue after prior activity has already been performed, e.g., resolution of an issue has been ongoing for 30 minutes, one hour, one day, etc., or (b) an entity was previously assigned to resolve an issue, was de-assigned from resolving the issue at some later point in time (e.g., by de-assign entity component 145) (e.g., due to inactivity), but was subsequently re-assigned to resolve the issue (e.g., based on a recommendation from recommend entity component 140). For both scenarios (a) and (b), the recommended entity will not observe activity when the entity they recommended is absent from the team resolving the issue. Thus, for scenario (a), the duration / activity not observed by the recommended entity will be activity performed from the time the project was initiated until the time the recommended entity joins the project. Additionally, for scenario (b), the duration / activity not observed by the returning entity will be activity performed from the time the entity was de-assigned from the project until the time the entity returns to the project.

[0129] At 1230, the corresponding unobserved content can be identified by the summary component. In an embodiment, the unobserved content of the conversation (e.g., where the unobserved content is considered to be a conversation 126B, where the conversation 126B is part of the entire conversation 126A conducted since the project was initiated) can include various topics / artifacts (e.g., threads 127A-n, artifacts 810A-n) related to topics such as problem indicators, entity activities, entity investigations, problem resolution, etc., as previously described.

[0130] At 1240 , in an embodiment, an artifact summarizer (eg, artifact summarizer 820 ) may be configured to generate respective summaries ( 152A-n), where each summary may be related to one or more of the artifacts.

[0131] At 1250, the summary component can further include a complete conversation summarizer (e.g., complete conversation summarizer 830) configured to incorporate one or more of the artifact summaries into a general / comprehensive summary that provides a summary level as required by a particular entity (e.g., the summary component 150 is provided with role information about the entity of interest). Thus, from the same unobserved content, a first comprehensive summary (e.g., summary 152X) is generated for a first entity, and a second comprehensive summary (e.g., summary 152Y) is generated for a second entity, where the first entity and the second entity have different roles / skill sets / information requirements.

[0132] At 1260, the summary component is configured to provide the respective summary to the respective entity for which the summary has been generated.

[0133] Fig.13 Method 1300 illustrates a computer-implemented method for automatically removing an entity currently assigned to a project to resolve an issue in accordance with one or more embodiments.

[0134] At 1310 , a dialog component (eg, dialog component 120 ) can be configured to compile activities performed in solving the current problem, and further generate a dialog from the compiled information (eg, as dialogs 126A-n).

[0135] At 1320, a conversation (e.g., conversation 126A) can be disassembled by a conversation disassembly component (e.g., conversation disassembly component 410) to identify one or more threads (e.g., threads 127A-n) included in the conversation, wherein the one or more threads can be respectively associated with various topics, themes, etc., as described above.

[0136] At 1330, the thread may be applied to a revocation entity component (e.g., revocation entity component 145), wherein the revocation entity component may have undergone prior training using one or more data sets including sequences of utterances, actions, etc. between various entities when solving a problem. By training the revocation entity component using one or more data sets, the revocation entity component (e.g., a mathematical model) may be configured to recognize corresponding utterances, etc. in corresponding threads disassembled from a current conversation (e.g., current conversation 126A), and further recognize corresponding entities that generated the corresponding utterances.

[0137] At 1340, a threshold (e.g., threshold 520A) may be defined / applied to revoking the entity component, where the threshold may be any suitable measurement that may be used to determine entity inactivity, such as the time T for activity in a conversation to occur, the number of messages NM that the entity needs to participate in, etc.

[0138] At 1350, the last utterance of the entity may be identified by the revocation entity component in conjunction with the most recent utterance (or utterance of interest, such as a specific utterance that occurred 20 minutes ago). The revocation entity component may be further configured to identify parameters, such as the time T that the entity has been inactive. IN , identify the number of messages NM where the entity has been inactive IN wait.

[0139] At 1360 , a difference between the determined parameter and the threshold value can be determined by an activity component (eg, activity component 510 ), where the activity component can be configured to determine T IN Is it equal to or exceeds T, NM? IN Whether it is equal to or exceeds NM, etc.

[0140] At 1370, in response to determining that the determined parameter is less than the threshold, method 1600 can return to 1310 to further determine the entity activity or lack of activity to be determined. In an embodiment, the dialog can be updated by the dialog component so that future inactivity states can be determined based on the recent activity / digital input of the corresponding entity (e.g., entity 136A-n).

[0141] At 1370, in response to determining that the determined parameter equals / exceeds the threshold, method 1300 can proceed to 1380, whereupon the entity's participation in the project can be revoked by the revoke entity component. As previously described, the recommend entity component can then determine that the entity should rejoin the project to resolve the issue.

[0142] As used herein, the terms "inference," "reasoning," "determining," and the like generally refer to the process of reasoning or inferring the state of a system, environment, and / or user from a set of observations captured via events and / or data. For example, inference can be employed to identify a particular context or action, or a probability distribution over states can be generated. Inference can be probabilistic—that is, a probability distribution over states of interest is computed based on a consideration of data and events. Inference can also refer to techniques used 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, whether or not the events are closely related in time, and whether the events and data come from one or more event and data sources.

[0143] According to various embodiments presented herein, various components included in IRS 110, IRC 115, dialog component 120, initial entity component 135, recommended entity component 140, revocation entity component 145, summary component 150, etc. may include AI and ML as well as reasoning techniques and technologies that employ probabilistic and / or statistical-based analysis to predict or infer actions that a user desires to be automatically performed. Various embodiments presented herein may utilize various machine learning-based schemes to perform various aspects thereof. For example, the following processes can be facilitated via the automatic classifier system and process: a process for determining one or more entities 136A-n to be initially assigned to a project (e.g., by IRC 115 in conjunction with initial entity component 135), a process for compiling and disassembling threads (e.g., threads 127A-n) / activities regarding solving a problem (e.g., problem 105U) (e.g., by IRC 115 in conjunction with conversation component 120), a process for determining and recommending entities to be added to a project (e.g., by IRC 115 in conjunction with recommend entity component 140), a process for determining and recommending entities to be removed from a project (e.g., by IRC 115 in conjunction with revoke entity component 145), a process for determining a time period during which an entity was absent from a project, determining project content that the entity is unaware of and generating a summary of that content, etc., as previously described herein.

[0144] A classifier is a function that maps an input attribute vector x = (x1, x2, x3, x4, xn) to a class label class(x). The classifier can also output the confidence that the input belongs to the class, i.e., f(x) = confidence(class(x)). This classification can use probabilistic and / or statistical analysis (e.g., taking into account the analysis utility and cost factors) to predict or infer the actions that the user expects to be automatically performed (e.g., assigning / removing entities to solve the problem, and operations related to it).

[0145] Support vector machines (SVMs) are examples of classifiers that can be used. SVMs operate by finding hypersurfaces in the space of possible inputs, separating triggering input events from non-triggering events in an optimal manner. Intuitively, this allows the classification of test data that is close to but not identical to the training data to be correct. Other directed and undirected model classification methods include, for example, naive Bayes, Bayesian networks, decision trees, neural networks, fuzzy logic models, and probabilistic classification models that provide different independent patterns can be used. Classification as used herein includes statistical regression for developing priority models.

[0146] As will be readily appreciated from the subject specification, various embodiments may employ classifiers that are explicitly trained (e.g., via generic training data) as well as implicitly trained (e.g., via observing user behavior, receiving external information). For example, an SVM is configured via a learning or training phase within a classifier constructor and feature selection module. Thus, the classifier can be used to automatically learn and perform a number of functions, including but not limited to, for example, determining the probability of a problem that has been previously processed that is similar to an unsolved problem according to predetermined criteria.

[0147] As described above, inferences can be made and automated actions performed based on a number of pieces of information. For example, whether conversations 126A-n and threads 127A-n have been correctly generated / assembled / identified by conversation component 120, corresponding entities 136A-n have been correctly identified to be initially included (e.g., by initial entity component 135), recommended for subsequent inclusion (e.g., by recommend entity component 140), removed from the project (e.g., by withdraw entity component 145), accurate / useful / relevant summaries 152A-n created (e.g., by summaries component 150), etc., so that issue 105U can be quickly resolved, wherein entity groups 136A-n can be efficiently assigned / removed as the project team attempts to resolve the issue.

[0148] Example applications and usage

[0149] Fig.14 The following discussion is intended to provide a means by which this paper can be implemented in Figures 1 to 13 A brief, general description of a suitable computing environment 1400 for one or more embodiments described in the disclosure is provided. For example, various aspects of the disclosure are described by narrative text, flow charts, block diagrams of computer systems, and / or block diagrams of machine logic included in computer program product (CPP) embodiments. With respect to any flow chart, depending on the technology involved, the operations may be performed in an order different from the order shown in a given flow chart. For example, again depending on the technology involved, two operations shown in consecutive flow chart blocks may be performed in reverse order, as a single integrated step, simultaneously, or in a manner that at least partially overlaps in time.

[0150] Computer program product embodiments ("CPP embodiments" or "CPP") are terms used in this disclosure to describe any collection of one or more storage media (also referred to as "media") collectively included in a collection of one or more storage devices that collectively include machine-readable code corresponding to instructions and / or data for performing the computer operations specified in a given CPP claim. A "storage device" is any tangible device that can retain and store instructions for use by a computer processor. Without limitation, a computer-readable storage medium may be 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 foregoing. Some known types of storage devices that include these media include: magnetic disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), static random access memories (SRAM), compact disk read-only memories (CD-ROMs), digital versatile disks (DVDs), memory sticks, floppy disks, mechanical encoding devices (such as punch cards or pits / ridges formed in a major surface of an optical disk), or any suitable combination of the foregoing. As the term is used in this disclosure, computer-readable storage media should not be construed as storage in the form of transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides, light pulses through fiber-optic cables, 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 point during normal operation of the storage device, such as during access, defragmentation, or garbage collection, but this does not make the storage device transitory because data is not transitory when stored.

[0151] The computing environment 1400 includes an example of an environment for executing at least some of the computer code involved in performing the inventive methods and embodiments presented herein, such as automatically recommending and revoking entities to assist in resolving problems (e.g., problem 105U to create 105R) by an IRS (e.g., IRS 110 and subcomponents) by applying 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 processor group 1410 (including processing circuit 1420 and cache 1421), communication structure 1411, volatile memory 1412, persistent storage device 1413 (including operating system 1422 and block 1480, as identified above), peripheral device group 1414 (including user interface (UI) device group 1423, storage device 1424, and Internet of Things (IoT) sensor group 1425), and network module 1415. Remote server 1404 includes remote database 1430. The public cloud 1405 includes a gateway 1440 , a cloud orchestration module 1441 , a host physical machine group 1442 , a virtual machine group 1443 , and a container group 1444 .

[0153] Computer 1401 may take the form of a desktop computer, laptop computer, tablet computer, smart phone, smart watch or other wearable computer, mainframe computer, quantum computer, or any other form of computer or mobile device now known or to be developed in the future that is capable of running programs, accessing a network, or querying a database (such as remote database 1430). As is well understood in the field of computer technology, and depending on the technology, the execution of the computer-implemented method may be distributed among multiple computers and / or among multiple locations. On the other hand, in this presentation of computing environment 1400, the detailed discussion focuses on a single computer (specifically, computer 1401) to keep the presentation as simple as possible. Computer 1401 may be located in the cloud, even if it is not in the cloud. Fig.14 On the other hand, except to the extent that it can be explicitly indicated, computer 1401 need not be in the cloud.

[0154] Processor group 1410 includes one or more computer processors of any type known now or developed in the future. Processing circuit 1420 may be distributed over multiple packages (e.g., multiple coordinated integrated circuit chips). Processing circuit 1420 may implement multiple processor threads and / or multiple processor cores. Cache 1421 is a memory located in the processor chip package and is typically used for data or code that should be quickly accessed by threads or cores running on processor group 1410. Cache memory is typically organized into multiple levels depending on the relative proximity to the processing circuit. Alternatively, some or all of the caches for the processor group may be located "off chip". In some computing environments, processor group 1410 may be designed to work with qubits and perform quantum computing.

[0155] Computer readable program instructions are typically loaded onto computer 1401 to cause processor group 1410 of computer 1401 to perform a series of operating steps to implement a computer-implemented method, such that the instructions so executed will instantiate the method specified in the flowchart and / or narrative description of the computer-implemented method included in this document (collectively referred to as the "inventive method"). 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 processor group 1410 to control and direct the execution of the inventive method. In computing environment 1400, at least some of the instructions for executing the inventive method may be stored in block 1480 in persistent storage device 1413.

[0156] Communications fabric 1411 is the signaling pathways that allow the various components of computer 1401 to communicate with each other. Typically, the fabric is made of switches and conductive pathways, such as those that make up a bus, a bridge, physical input / output ports, etc. Other types of signal communication pathways may be used, such as fiber optic communication pathways 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 type random access memory (RAM) or static type RAM. Typically, this volatile memory is characterized by random access, but this is not required unless explicitly indicated. In computer 1401, volatile memory 1412 is located in a single package and internal to computer 1401, but alternatively or additionally, volatile memory can be distributed over multiple packages and / or located externally relative to computer 1401.

[0158] Persistent storage 1413 is any form of non-volatile storage for computers known now or to be developed in the future. The non-volatility of the storage means that the stored data is maintained regardless of whether power is supplied to the computer 1401 and / or directly to the persistent storage 1413. Persistent storage 1413 may be a read-only memory (ROM), but typically at least a portion of the persistent storage allows data to be written, deleted, and rewritten. Some common forms of persistent storage include disks and solid-state storage devices. Operating system 1422 may take several forms, such as various known proprietary operating systems or open source portable operating system interface type operating systems using a kernel. The code included in block 1480 typically includes at least some of the computer codes involved in executing the method of the present invention.

[0159] The peripheral device group 1414 includes a group of peripheral devices of the computer 1401. The data communication connection between the peripheral device and other components of the computer 1401 can be implemented in various ways, such as a Bluetooth connection, a near field communication (NFC) connection, a connection by a cable (such as a universal serial bus (USB) type cable), a plug-in type connection (e.g., a secure digital (SD) card), a connection through a local area network, and even a connection through a wide area network (such as the Internet). In various embodiments, the UI device group 1423 may include components such as a display screen, a speaker, a microphone, a wearable device (such as goggles and smart watches), a keyboard, a mouse, a printer, a touchpad, a game controller, and a tactile device. The storage device 1424 is an external storage device (such as an external hard drive) or a pluggable storage device (such as an SD card). The storage device 1424 can be persistent and / or volatile. In some embodiments, the storage device 1424 can take the form of a quantum computing storage device for storing data in the form of quantum bits. In embodiments where computer 1401 needs to have a large amount of storage (e.g., computer 1401 locally stores and manages a large database), this storage can be provided by a peripheral storage device designed to store extremely large amounts of data, such as a storage area network (SAN) shared by multiple geographically distributed computers. IoT sensor group 1425 consists of sensors that can be used in IoT applications. For example, one sensor can be a thermometer, while another sensor can be a motion detector.

[0160] The network module 1415 is a collection of computer software, hardware, and firmware that allows the computer 1401 to communicate with other computers via the WAN 1402. The network module 1415 may include hardware such as a modem or a Wi-Fi signal transceiver, software for packetizing and / or depacketizing data for communication network transmission, and / or web browser software for transmitting data via the Internet. In some embodiments, the network control function and the network forwarding function of the network module 1415 are performed on the same physical hardware device. In other embodiments (e.g., embodiments utilizing software defined networks (SDN)), the control function and the forwarding function of the network module 1415 are performed on physically separated devices, so that the control function manages several different network hardware devices. Computer-readable program instructions for executing the method of the present invention can generally be downloaded to the computer 1401 from an external computer or an external storage device via a network adapter card or a network interface included in the network module 1415.

[0161] WAN 1402 is any wide area network (e.g., the Internet) capable of transmitting computer data over non-local distances by any technology known now or to be developed in the future for transmitting computer data. In some embodiments, WAN 1402 may be replaced and / or supplemented by a local area network (LAN) designed to transmit 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 fibers, 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 an enterprise operating computer 1401), and may take any of the forms discussed above in connection with computer 1401. EUD 1403 typically receives data that assists and is useful from the operation of computer 1401. For example, in the hypothetical case where computer 1401 is designed to provide recommendations to an end-user, the recommendations would typically be transmitted from network module 1415 of computer 1401 to EUD 1403 via WAN 1402. In this manner, EUD 1403 may 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 helpful 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 historical data, then this historical data may be provided to computer 1401 from 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 capabilities, without the need for direct and active management of the computing resources of public cloud 1405 at scale. Direct and active management of the 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 the host physical machine group 1442, which is the totality of physical computers in and / or available to public cloud 1405. Virtual computing environments (VCEs) are typically in the form of virtual machines from virtual machine group 1443 and / or containers from container group 1444. It should be understood that these VCEs can be stored as images and can be transferred between various physical machine hosts as images or after instantiation of the VCEs. Cloud orchestration module 1441 manages the transmission and storage of images, deploys new instantiations of VCEs, and manages active instantiation of VCE deployments. Gateway 1440 is a collection of computer software, hardware, and firmware that allows public cloud 1405 to communicate over WAN 1402 .

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

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

[0167] The embodiments described herein may be directed to one or more of a system, method, apparatus, and / or computer program product at any possible level of integrated technical detail. A computer program product may include a computer-readable storage medium (or medium) having computer-readable program instructions thereon for causing a processor to perform aspects of one or more embodiments described herein. A computer-readable storage medium may be a tangible device that can retain and store instructions used 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 foregoing. A non-exhaustive list of more specific examples of computer-readable storage media may further include the following items: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disc (DVD), a memory stick, a floppy disk, a mechanical encoding device (such as a punched card or a raised structure in a groove on which instructions are recorded), and / or any suitable combination of the foregoing. As used herein, computer-readable storage media should not be interpreted as transitory signals per se, such as radio waves and / or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides and / or other transmission media (e.g., light pulses through fiber optic cables), and / or electrical signals transmitted through wires.

[0168] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium and / or an external computer or an external storage device to a corresponding computing / processing device via a network (e.g., the Internet, a local area network, a wide area network, and / or a wireless network). The network may include copper transmission cables, optical transmission fibers, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives computer-readable program instructions from the network, and forwards the computer-readable program instructions to be stored in a computer-readable storage medium in the corresponding computing / processing device. The computer-readable program instructions for performing the operations of one or more embodiments described herein may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcodes, firmware instructions, state setting data, configuration data of an integrated circuit, and / or source code and / or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, and / or procedural programming languages ​​such as "C" programming languages ​​and / or similar programming languages. The computer-readable program instructions may be executed entirely on the computer, partially on the computer, as a separate 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 case, the remote computer may be connected to the computer via any type of network, including a local area network (LAN) and / or a wide area network (WAN), and / or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In one or more embodiments, electronic circuits including, for example, programmable logic circuits, field programmable gate arrays (FPGAs), and / or programmable logic arrays (PLAs) may execute computer-readable program instructions to personalize the electronic circuits by utilizing state information of the computer-readable program instructions so as to perform aspects of one or more embodiments described herein.

[0169] The various aspects of one or more embodiments described herein are described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to one or more embodiments described herein. It should be understood that each block of the flowchart illustration and / or block diagram and the combination of blocks in the flowchart illustration and / or block diagram can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer and / or other programmable data processing device to manufacture a machine, so that instructions executed by a processor of a computer or other programmable data processing device can create a component for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, which can instruct a computer, a programmable data processing device and / or other equipment to implement functions in a specific manner, so that a computer-readable storage medium having instructions stored therein can include a product, which includes instructions that can implement various aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram. Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, and / or other devices to cause a series of operational actions to be performed on the computer, other programmable apparatus, and / or other devices to produce a computer-implemented process, so that the instructions executed on the computer, other programmable apparatus, and / or other devices implement the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0170] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and / or operations of the system, computer-implemented method and / or computer program product according to one or more embodiments described herein. In this regard, each block in the flowchart or block diagram may represent a module, segment and / or portion of an instruction, which includes one or more executable instructions for implementing a specified logical function. In one or more alternative embodiments, the functions indicated in the block may not occur in the order indicated in the figure. For example, two blocks shown in succession may be executed substantially simultaneously, and / or these blocks may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block illustrated in the block diagram and / or flowchart and / or the combination of blocks in the block diagram and / or flowchart can be implemented by a dedicated hardware-based system that can perform a specified function and / or action 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 scenario of computer executable instructions of a computer program product running on one and / or multiple computers, those skilled in the art will recognize that one or more embodiments of the present invention may also be implemented at least in part in parallel with one or more other program modules. Typically, a program module includes routines, programs, components, and / or data structures that perform specific tasks and / or implement specific abstract data types. In addition, the above-mentioned computer-implemented method can be practiced using other computer system configurations, including single-processor and / or multi-processor computer systems, small computing devices, large computers, and computers, handheld computing devices (e.g., PDAs, phones), and / or microprocessor-based or programmable consumer and / or industrial electronic devices. The illustrated aspects may also be practiced in a distributed computing environment, where tasks are performed by remote processing devices linked through a communication network. However, one or more (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 local and remote memory storage devices.

[0172] As used in this application, the terms "component", "system", "platform" and / or "interface" may refer to and / or may include computer-related entities or entities related to an operating machine having one or more specific functions. The entities described herein may be 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, a processor, an object, an executable file, an execution thread, a program, and / or a computer running on a processor. As an illustration, both an application running on a server and a server may be a component. One or more components may reside within a process and / or an execution thread, and a component may be located on one computer and / or distributed between two or more computers. In another example, each component may be executed from various computer-readable media having various data structures stored thereon. Components may communicate via local and / or remote processes, such as according to signals having one or more data packets (e.g., data from a component that interacts with another component in a local system, a distributed system, and / or other systems across a network such as the Internet via a signal). As another example, a component may be a device having a specific function provided by a mechanical component operated by an electrical or electronic circuit, which is operated by a software and / or firmware application executed by a processor. In this case, the processor may be internal and / or external to the device and may execute at least a portion of a software and / or firmware application. As yet another example, the component may be a device that provides a specific functionality through an electronic component without a mechanical component, where the electronic component may include a processor and / or other units for executing software and / or firmware that at least partially imparts the functionality to the electronic component. In one aspect, the component may emulate the electronic component via, for example, a virtual machine within 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 natural inclusive arrangement. That is, if X employs A; X employs B; or X employs both A and B, then "X employs A or B" is satisfied under any of the foregoing instances. In addition, the articles "a" and "an" used in this specification and the drawings should generally be interpreted as meaning "one or more" unless otherwise specified or clear from the context to point to the singular form. As used herein, the terms "example" and / or "exemplary" are used to indicate use as an example, instance, or illustration. For the avoidance of doubt, the subject matter described herein is not limited to these examples. In addition, any aspect or design described herein as "example" and / or "exemplary" is not necessarily to be interpreted as preferred or advantageous over other aspects or designs, nor is it meant to exclude equivalent exemplary structures and techniques known to those of ordinary skill in the art.

[0174] When used in this specification, the term "processor" can refer to substantially any computing processing unit and / or device, including but not limited to: a single-core processor; a single processor with software multi-threaded execution capability; a multi-core processor; a multi-core processor with software multi-threaded execution capability; a multi-core processor with hardware multi-threading technology; a parallel platform; and / or a parallel platform with distributed shared memory. In addition, a processor can 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. In addition, the processor can utilize nanoscale architectures, such as, but not limited to, transistors, switches, and / or gates based on molecules and quantum dots, in order to optimize space usage and / or enhance the performance of related devices. The processor can be implemented as a combination of computing processing units.

[0175] In this document, terms such as "repository", "storage device", "data repository", "data storage device", "database" and any other information storage component substantially related to the operation and function of the component are used to refer to a "memory component", an entity implemented in a "memory", or a component that includes a memory. The memory and / or memory components described herein may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. By way of illustration 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., RAM) (e.g., ferroelectric RAM (FeRAM)). Volatile memory may include RAM, which may, for example, act as external cache memory. By way of illustration and not limitation, RAM may be available in many forms, such as synchronous RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), direct Rambus RAM (DRRAM), direct Rambus dynamic RAM (DRDRAM), and / or Rambus dynamic RAM (RDRAM). Additionally, the memory components of the systems and / or computer-implemented methods described herein are intended to include, but are not limited to, including these and / or any other suitable types of memory.

[0176] What has been described above includes only examples of systems and computer-implemented methods. Of course, for the purpose 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 will recognize that many further combinations and / or permutations of one or more embodiments are possible. In addition, to the extent that the terms "including," "having," "having," and the like are used in the specific embodiments, claims, appendices, and / or drawings, these terms are intended to be inclusive in a manner similar to the term "comprising" as "comprising" is interpreted when used as a transitional word in a claim.

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

Claims

1. A system comprising: a memory operably coupled to the system, wherein the memory stores computer-executable components; as well as A processor executes the computer executable components stored in the memory, wherein the computer executable components include: The initial entity component is configured as: Identify the first content related to the problem; identifying, based on the first content, second content in at least one previous problem solution, wherein the first content and the second content are similar; identifying a first entity associated with the second content; and The first entity is assigned to initiate a process for resolving the problem.

2. The system of claim 1, wherein the first content is included in an initial compilation of information about the problem.

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

4. The system of claim 1, wherein the computer executable components further comprise a recommendation entity component, wherein the recommendation entity component is configured to: identifying third content related to the problem, wherein the third content is a digital entry submitted by the first entity in an attempt to resolve the problem; Based on the third content, identifying a second entity to participate in solving the problem; as well as The second entity is assigned to resolve the problem.

5. The system according to claim 4, wherein the recommendation entity component is further configured to: identifying fourth content, wherein the fourth content was generated in a digital conversation between the first entity and the second entity, wherein the digital conversation is related to solving the problem; Based on the fourth content, identifying a third entity to participate in solving the problem; as well as The third entity is assigned to join the first entity and the second entity to resolve the problem.

6. The system of claim 5, wherein the computer executable components further comprise a summary component configured to: identifying a first time, wherein the first time is a time when the third entity is assigned to resolve the issue; identifying a second time, wherein the second time is a time when resolution of the issue is initiated; determining activities performed by the first entity and the second entity in solving the problem between the first time and the second time; generating a summary of the activities performed by the first entity and the second entity between the first time and the second time; as well as The summary is provided to the third entity.

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

8. The system of claim 5, wherein the first entity, the second entity, and the third entity are included in a group of entities assigned to solve the problem, wherein the computer executable components further include a revoke entity component configured to: further monitoring the digital conversation between the group of entities to identify a time period during which the first entity in the group of entities has not participated in the conversation; determining whether the time period exceeds a threshold time period; and Based on the time period exceeding the threshold time period, the first entity is removed from the group of entities.

9. The system according to claim 8, wherein the recommendation entity component is further configured to: further monitoring the digital conversation between the second entity and the third entity; determining that the digital conversation is related to the first entity; and The first entity is reassigned to the group of entities that solve the problem.

10. The system of claim 9, wherein the summary component is further configured to: identifying a third time, wherein the third time is a time to remove the first entity from the group of entities assigned to resolve the issue; identifying a fourth time, wherein the fourth time is a current time at which the problem is resolved by the second entity and the third entity; determining activities performed by the second entity and the third entity in solving the problem between the third time and the fourth time; generating a second summary of the activities performed by the second entity and the third entity between the third time and the fourth time; as well as The second summary is provided to the first entity.

11. The system of claim 5, wherein the first entity, the second entity, and the third entity are included in a group of entities assigned to solve the problem, wherein the computer executable components further include a revoke entity component configured to: 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; as well as Based on the consecutive number of messages exceeding the threshold number of messages, the first entity is removed from the group of entities assigned to resolve the issue.

12. A computer-implemented method performed by a device operatively coupled to a processor, wherein the method comprises: identifying a first entity to initiate resolution of a current problem, wherein the first entity is identified based on a previous problem to which the first entity was previously assigned being similar to the current problem; as well as The first entity is assigned to initiate resolution of the current issue, wherein the current issue involves performance of an information technology operation.

13. The computer-implemented method of claim 12, further comprising: parsing digital content created by the first entity in attempting to solve the problem; reviewing one or more previous activities, wherein the previous activities involve a second entity; determining that the one or more prior activities relate to the digital content; as well as The second entity is recommended to assist the first entity in resolving the problem.

14. The computer-implemented method of claim 13, further comprising: monitoring activities of the first entity and the second entity in attempting to resolve the problem; comparing the activities of the second entity in attempting to solve the problem; determining that the second entity is no longer involved in attempting to resolve the issue; as well as The second entity is removed from participating in resolving the issue.

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

16. The computer-implemented method of claim 13, further comprising: determining an engagement time, wherein the engagement time is a time when the second entity joins the first entity to attempt to resolve the issue; determining unobserved activities performed by the first entity between initiation of solving the problem and the engagement time, wherein the unobserved activities are activities performed by at least the first entity in solving the problem; generating a summary of the unobserved activities; as well as The summary of the unobserved activity is provided to the second entity.

17. A computer program product comprising machine executable instructions, wherein in response to the machine executable instructions being executed, it causes a machine to perform the method according to any one of claims 12 to 16.

Images