DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Amendment
The Amendment filed 06/09/2026 has been entered. New claims 16-20 have been added. Therefore, claims 1-20 remain pending in this application.
Response to Arguments
Applicant’s arguments, filed on 06/09/2026, concerning the 35 U.S.C. 112 rejection, have been fully considered and are persuasive. Therefore, this rejection has been withdrawn. Applicant’s arguments concerning the 35 U.S.C. 101 rejection, the 35 U.S.C. 102 rejection, and the 35 U.S.C. 103 rejection have been fully considered but are not persuasive.
With respect to the 35 U.S.C. 101 rejection, on pages 10-14, the Applicant asserts that the amended claims require a specific technical implementation where role-specific analysis policies are integrated into prompts for the text generation system, thereby they are not able to be practically performed in the human mind. They further state that amended limitation requires automatic root cause identification and a specific visual display implementation that correlates IT system elements to the failure, which is a concrete technical improvement to IT system failure investigation that cannot be performed mentally. The Applicant asserts that the amended claims are not directed to mere observation, evaluation, judgement, or opinion that could be performed mentally because the combination of technical features represents a specific technical implementation that improves the functioning of IT system failure investigation. They further assert that the claims as amended integrate the alleged abstract idea into a practical application by providing a specific technical solution for IT system failure investigation. The claims recite role-specific viewpoints that define analysis policies integrated into prompts, automatic root cause identification based on findings, and visual display with indicators correlating elements to failures. They cite the USPTO’s December 5, 2025 Memorandum on Subject Matter Eligibility, states that the claims recite a specific combination of technical steps that collectively solve a technical problem. They also assert that the claims as a whole are directed to a practical technological solution for IT system failure investigation.
The Examiner respectfully disagrees. The original claims, and the claims as amended, are merely utilizing computer devices, in this specific case “a processor”, “a storage device coupled to the processor”, “a network interface coupled to the processor”, “an IT system”, “a text generation system”, and “a natural language processing model”, as tools to perform a method which is directed to an abstract idea. The claim, under its broadest reasonable interpretation, recites a system and method for selecting a scope where an IT failure has occurred, identifying elements to be investigated based on the scope information, obtaining observation data, writing text that includes viewpoint information relating to a scope, the elements, observation data, and instructions to output findings related to the IT failure, obtaining a response to this text, and thereby identifying the cause of the IT problem. This is an abstract idea in the form of certain methods of organizing human activity (i.e. mental processes such as observation, evaluation, judgement, and opinion). The steps of receiving all the necessary information and data concerning an IT failure, identifying elements to be investigated, obtaining observation data, writing text containing all the necessary information, receiving an output to the text, and identifying the cause of the IT problem could be performed by a human using pen and paper or by purely mental reasoning, save for the recitation of generic computing components. Further, the claims do not integrate the judicial exception into a practical application. The recitation of “a processor”, “a storage device coupled to the processor”, “a network interface coupled to the processor”, “an IT system”, “a text generation system”, and “a natural language processing model” are generic instructions to perform the abstract idea on a computer or using computer devices and does not impose a meaningful limit on the judicial exception. The “a processor”, “a storage device coupled to the processor”, “a network interface coupled to the processor”, “an IT system”, “a text generation system”, and “a natural language processing model” are recited as such high-levels of generality and are merely used as tools to perform the abstract idea faster or more efficiently. With respect to the claim of technological improvement, it seems the Applicant is merely restating the premise without providing much more. While the claims do not need to explicitly recite improvements shown in the Specification, the claim must be evaluated to ensure that the claim itself reflects the disclosed improvements. Based on the plain reading of the claim itself, there is no reasonable improvement to the functioning of the generic computer components, the IT system itself, the data manipulation, or to any other technology or technical field. The claims do not include any additional elements that amount to significantly more than the judicial exception. The claims, as written and amended, do not include more than mere instructions to perform the abstract method using generic computer components. Hence, Applicant’s arguments are not persuasive.
With respect to the 35 U.S.C. 102 rejection, on pages 14-16, of claims 1, 5, and 9 under Ranga Prasad et al. (US Application Publication No. 2025/0265468), hereinafter referred to as Ranga Prasad, the Applicant has amended to incorporate limitations that are very similar to those recited in existing claim 2, which was not rejected under 35 U.S.C. 102. Ranga Prasad fails to disclose specific to a role having administrative authority of the IT system and from a perspective corresponding to the role. This argument has been fully considered and is persuasive. Therefore, this rejection is withdrawn.
With respect to the 35 U.S.C. 103 rejection, on pages 16-20, of claims 2-4 and 10-12 under Ranga Prasad, in view of Wang et al. (US Patent No. 12,511,594), hereinafter referred to as Wang, claims 6-7 and 13-14 under Ranga Prasad, in view of Guo et al. (US Patent No. 12,368,745), hereinafter referred to as Guo, and claims 8 and 15 under Ranga Prasad, in view of Guo, and further in view of Padmanabhan et al. (US Patent Application Publication No. 2025/0005299), hereinafter referred to as Padmanabhan, the Applicant asserts that neither Ranga Prasad nor Wang discloses or teaches the amended limitations of claims 1, 2, and 9. The Applicant also asserts that neither Ranga Prasad nor Guo discloses or teaches the amended limitations of claims 6-7 and 13-14. They also assert that Padmanabhan fails to cure these aforementioned deficiencies.
Concerning Applicant’s assertion that neither Ranga Prasad nor Wang discloses or teaches the amended limitations of claims 1, 2, and 9, Ranga Prasad Fig. 1 reference characters 124-128 and Ranga Prasad para [0022] states: "A user interface allows manual review and adjustment of system outputs, ensuring flexibility for human judgment.” This excerpt shows a clear teaching of and automatically identify a root cause of the failure based on the obtained findings and display the root cause on an interface with visual indicators correlating the identified at least one of the plurality of elements to the failure. Wang Fig. 6 reference character 612 shows the role and expertise of each team member, which teaches the specific to a role having administrative authority of the IT system, and Wang Fig. 6 reference character 610, 612, and 614 shows the role and expertise of each team member as well as their schedules and assignments, which teaches the from a perspective corresponding to the role. These same excerpts can be used to teach the amended elements of claim 2 and 9 as well.
Concerning Applicant’s assertion that neither Ranga Prasad nor Guo discloses or teaches the amended limitations of claims 6-7 and 13-14, Ranga Prasad para [0047] states "The Incident Validation & Classification Module (150) and the Incident Resolution Validation Module (152) are communicatively coupled to Incident Management 106. The Incident Validation & Classification Module utilizes NLP to analyze and standardize incident descriptions and resolutions," and Ranga Prasad para [0069] states “It utilizes advanced algorithms and techniques to analyze the data semantically.” These both show the text generation system to use natural language processing to identify and based on semantic analysis of the scope and the relation information. Hence, Applicant’s arguments are not persuasive.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claim(s) 1-20 rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. Independent claims 1 and 9 recite “a processor; a storage device coupled to the processor; and a network interface coupled to the processor”, “an IT system formed of a plurality of elements and configured to execute a service”, “a text generation system configured to generate answer text”, “element information for managing observation data”, “relation information for managing relevance”, “scope information that defines a scope”, “refer to the scope information to select the scope in a case where a failure has occurred in the IT system”, “identify at least one of the plurality of elements to be investigated”, “obtain the observation data”, “generate a first prompt”, “obtain the answer text”, and “automatically identify a root cause of the failure”. These limitations, as drafted, are a process that, under a broadest reasonable interpretation, covers the abstract idea of “mental processes” because they cover concepts performed in the human mind, including observation, evaluation, judgement, and opinion. See MPEP 2106.04(a)(2). That is, other than reciting “a processor”, “a storage device coupled to the processor”, “a network interface coupled to the processor”, “an IT system”, “a text generation system”, and “a natural language processing model”, nothing in the claimed elements preclude the steps from practically being performed by a person using generic computer components known within the art to observe and analyze various sources of information relating to an IT system (observation information, relation information, scope information, etc.) and then using the information to write up a prompt to input into a natural language processing model only to receive its output.
This judicial exception is not integrated into a practical application because the additional elements “a processor”, “a storage device coupled to the processor”, “a network interface coupled to the processor”, “an IT system”, “a text generation system”, and “a natural language processing model” are all recited at a high-level of generality. Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Thus, the claims as a whole are directed to an abstract idea (Step 2A, prong two).
Claims 1 and 9 do not include any additional elements that are sufficient to amount to significantly more than the judicial exception because, as discussed above with respect to integration of the abstract idea into a practical applications, the additional elements of “a processor”, “a storage device coupled to the processor”, “a network interface coupled to the processor”, “an IT system”, “a text generation system”, and “a natural language processing model” amount to no more than mere instructions to apply the exception using generic computer components. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept (Step 2B).
Dependent claims 2-8 and 10-20 are directed to roles and user information of those in the IT system, an interface for presentation of the findings of the system, and generating second and third prompts. That is, nothing in the claimed elements preclude the steps from practically being performed by a person using generic computer components known within the art to observe and analyze various sources of information relating to an IT system (observation information, relation information, scope information, etc.) and then using the information to write up a prompt to input into a natural language processing model only to receive its output. Even when considered individually and in combination, the additional elements in claims 1-20 represent mere instructions to implement an abstract idea or other exception on a computer and insignificant extra-solution activity, which do not provide an inventive concept (Step 2B).
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-5, 9-12, and 16-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ranga Prasad et al. (US Application Publication No. 2025/0265468), hereinafter referred to as Ranga Prasad, in view of Wang et al. (US Patent No. 12,511,594), hereinafter referred to as Wang.
Regarding claim 1, Ranga Prasad discloses a computer system, comprising: a processor; a storage device coupled to the processor ("This method begins with a system, which includes a processor and memory, receiving incident data," Ranga Prasad para [0021]); and a network interface coupled to the processor (Ranga Prasad para [0038]), the computer system being coupled to: an IT system formed of a plurality of elements and configured to execute a service (Ranga Prasad Fig. 1 reference character 101);
and a text generation system configured to generate answer text through use of a natural language processing model in accordance with a prompt that instructs execution of a language processing task ("The Generative AI Inference Module (GAIM) (154) is a core aspect of the solutions provided herein and processes text data, from the Incident Validation & Classification Module (150) and the Incident Resolution Validation Module (152), using LLMs to generate insights, continuously refining its outputs," Ranga Prasad para [0048]), the computer system holding: element information for managing observation data obtained from the IT system (Ranga Prasad Fig. 1 reference characters 106 and 108);
relation information for managing relevance between the plurality of elements (Ranga Prasad Fig. 1 reference character 110);
and scope information that defines a scope representing a range of an investigation in a failure investigation for the IT system (Ranga Prasad Fig. 1 reference characters 108-116), the scope information storing data in which the scope and a viewpoint of analysis in the failure investigation for the IT system are associated with each other ("This method begins with a system, which includes a processor and memory, receiving incident data," Ranga Prasad para [0021] and Ranga Prasad Fig. 1 reference character 106), the viewpoint defining a policy of analysis (Ranga Prasad para [0010], IT service management practices concern who, and of what authority, interacts with what problems or incidents), wherein the computer system is configured to: refer to the scope information to select the scope in a case where a failure has occurred in the IT system (Ranga Prasad Fig. 1 reference character 150);
identify at least one of the plurality of elements to be investigated based on the relation information and the selected scope ("Incident Diagnosis (112) involves investigating the cause," Ranga Prasad para [0045]);
obtain the observation data relating to the identified at least one of the plurality of elements from the element information (Ranga Prasad Fig. 1 reference character 150);
generate a first prompt, which includes, as text, the viewpoint corresponding to the selected scope as an instruction for analyzing the observation data (Ranga Prasad para [0052]), the identified at least one of the plurality of elements, and the obtained observation data, and which instructs to output findings relating to the failure in the IT system, and input the first prompt to the text generation system ("The Incident Validation & Classification Module (150) and the Incident Resolution Validation Module (152) are communicatively coupled to Incident Management 106. The Incident Validation & Classification Module utilizes NLP to analyze and standardize incident descriptions and resolutions," Ranga Prasad para [0047] and "The Generative AI Inference Module (GAIM) (154) is a core aspect of the solutions provided herein and processes text data, from the Incident Validation & Classification Module (150) and the Incident Resolution Validation Module (152), using LLMs to generate insights, continuously refining its outputs," Ranga Prasad para [0048]);
[[ and ]] obtain the answer text including the findings from the text generation system ("The GAIM is also communicatively coupled to the Problem Prevention Recommendation Module (156) and the Problem Calculation Module (158). The Problem Probability Calculation Module assesses incidents for specific items or applications to score potential problem probabilities. The Problem Prevention Recommendation Module examines root causes to offer process improvement recommendations," Ranga Prasad para [0049]);
and automatically identify a root cause of the failure based on the obtained findings and display the root cause on an interface with visual indicators correlating the identified at least one of the plurality of elements to the failure (Ranga Prasad Fig. 1 reference characters 124-128 and "A user interface allows manual review and adjustment of system outputs, ensuring flexibility for human judgment," Ranga Prasad para [0022]).
However, Ranga Prasad fails to disclose specific to a role having administrative authority of the IT system and from a perspective corresponding to the role.
Wang teaches a system and method for management in collaborative version control.
Wang teaches specific to a role having administrative authority of the IT system (Wang Fig. 6 reference character 612);
from a perspective corresponding to the role (Wang Fig. 6 reference character 610, 612, and 614).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Ranga Prasad’s disclosure of an incident and problem management data system utilizing generative artificial intelligence and large language models by including Wang’s teaching of assigning certain issues/failures and roles to certain users who are better suited for fixing said issues/failures. Certain team members might specialize in particular aspects within their field; therefore, it would have been obvious to assign issues/failures to those who are better equipped to deal with them. This would improve the average time it takes to fix issues/failures while also increasing the effectiveness of the system and method as a whole.
Regarding claim 2, Ranga Prasad, in view of Wang, discloses all of the limitations of claim 1. Ranga Prasad further discloses wherein the computer system is configured to: generate, in a case of automatically performing the failure investigation for the IT system, the first prompt wherein each first prompt includes the viewpoint defining the policy of analysis and input the first prompt to the text generation system ("The Generative AI Inference Module (GAIM) (154) is a core aspect of the solutions provided herein and processes text data, from the Incident Validation & Classification Module (150) and the Incident Resolution Validation Module (152), using LLMs to generate insights, continuously refining its outputs," Ranga Prasad para [0048] and "It starts with identifying root causes, then utilizes the Generative AI Inference Module (GAIM) to derive insights (602), leading to the identification of process gaps," Ranga Prasad para [0079], shows an output from the GAIM);
and generate the first prompt and input the first prompt to the text generation system ("The Generative AI Inference Module (GAIM) (154) is a core aspect of the solutions provided herein and processes text data, from the Incident Validation & Classification Module (150) and the Incident Resolution Validation Module (152), using LLMs to generate insights, continuously refining its outputs," Ranga Prasad para [0048] and "It starts with identifying root causes, then utilizes the Generative AI Inference Module (GAIM) to derive insights (602), leading to the identification of process gaps," Ranga Prasad para [0079], shows an output from the GAIM).
However, Ranga Prasad fails to disclose wherein the data includes a role being administrative authority of the IT system, wherein the computer system holds user information for managing the role assigned to a user, for each of a plurality of roles specific to the corresponding role; in a case of performing the failure investigation for the IT system in accordance with an instruction received from a user, for the role assigned to the user who issued the instruction.
Wang teaches wherein the data includes a role being administrative authority of the IT system (Wang Fig. 6 reference character 612), wherein the computer system holds user information for managing the role assigned to a user (Wang Fig. 6 reference character 614),
for each of a plurality of roles specific to the corresponding role (Wang Fig. 6 reference character 612);
in a case of performing the failure investigation for the IT system in accordance with an instruction received from a user ("In embodiments, the issue to be assigned (including the definition of the issue), and any constraints/preferences regarding an assignee are received by issue classifier 120 from the user at 620 and include an issue severity level and a complexity level," Wang col. 12 lines 7-11),
for the role assigned to the user who issued the instruction (Wang Fig. 6 reference character 630).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Ranga Prasad’s disclose of an incident and problem management data system utilizing generative artificial intelligence and large language models by including Wang’s teaching of assigning certain issues/failures and roles to certain users who are better suited for fixing said issues/failures. Certain team members might specialize in particular aspects within their field; therefore it would have been obvious to assign issues/failures to those who are better equipped to deal with them. This would improve the average time it takes to fix issues/failures while also increasing the effectiveness of the system and method as a whole.
Regarding claim 3, Ranga Prasad, in view of Wang, discloses all of the limitations of claim 2. Ranga Prasad further discloses generate and input the first prompt ("The Generative AI Inference Module (GAIM) (154) is a core aspect of the solutions provided herein and processes text data, from the Incident Validation & Classification Module (150) and the Incident Resolution Validation Module (152), using LLMs to generate insights, continuously refining its outputs," Ranga Prasad para [0048] and "It starts with identifying root causes, then utilizes the Generative AI Inference Module (GAIM) to derive insights (602), leading to the identification of process gaps," Ranga Prasad para [0079], shows an output from the GAIM).
However, Ranga Prasad fails to disclose wherein the computer system is configured to: determine an order of the plurality of roles in the case of automatically performing the failure investigation for the IT system; and in accordance with the determined order of the plurality of roles.
Wang teaches wherein the computer system is configured to: determine an order of the plurality of roles in the case of automatically performing the failure investigation for the IT system (Wang Fig. 6 reference character 630 and "In embodiments, at 630 the user has an option to select one of the layers (i.e., search layer 132 or NLP layer 134) via user/manager user interface 310 as the layer from which the assignee will be chosen. Otherwise, the user selects at 630 the more suitable assignee from the two candidate assignees," Wang col. 13 lines 13-18);
and in accordance with the determined order of the plurality of roles (Wang Fig. 6 reference character 630).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Ranga Prasad’s disclose of an incident and problem management data system utilizing generative artificial intelligence and large language models by including Wang’s teaching of assigning certain issues/failures and roles to certain users who are better suited for fixing said issues/failures. Certain team members might specialize in particular aspects within their field; therefore it would have been obvious to assign issues/failures to those who are better equipped to deal with them. This would improve the average time it takes to fix issues/failures while also increasing the effectiveness of the system and method as a whole.
Regarding claim 4, Ranga Prasad, in view of Wang, discloses all of the limitations of claim 2. Ranga Prasad further discloses wherein the computer system is configured to: provide an interface for presenting the findings ("A user interface allows manual review and adjustment of system outputs, ensuring flexibility for human judgment," Ranga Prasad para [0022]);
and present, in a case where an instruction to present the findings is received from a user, the findings obtained through use of the first prompt ("A feedback mechanism collects user evaluations on resolutions and recommendations, guiding the refinement of preventive measures. Additionally, a user interface offers real-time dashboards and analytics, supporting effective monitoring, management, and decision-making by administrators and IT staff," Ranga Prasad para [0024]).
However, Ranga Prasad fails to disclose for the role assigned to the user who issued the instruction.
Wang teaches for the role assigned to the user who issued the instruction (Wang Fig. 6 reference character 630).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Ranga Prasad’s disclose of an incident and problem management data system utilizing generative artificial intelligence and large language models by including Wang’s teaching of assigning certain issues/failures and roles to certain users who are better suited for fixing said issues/failures. Certain team members might specialize in particular aspects within their field; therefore it would have been obvious to assign issues/failures to those who are better equipped to deal with them. This would improve the average time it takes to fix issues/failures while also increasing the effectiveness of the system and method as a whole.
Regarding claim 5, Ranga Prasad, in view of Wang, discloses all of the limitations of claim 1. Ranga Prasad further discloses wherein the computer system is configured to generate, in a case where the findings are stored, the first prompt including the findings (Ranga Prasad Fig. 1 shows reference characters 150 and 152 as inputs to the GAIM, i.e. they are generating a prompt to input to the GAIM and "The Incident Generative AI Inference Module (GAIM) stands as the central component of this solution, utilizing Large Language Models (LLMs) to analyze text data from incidents. It generates insights through advanced processing, continually refining these insights to ensure they are accurate and relevant. This ongoing refinement process enables the system to adapt and improve over time, ensuring that the intelligence it provides is both current and highly applicable to enhancing IT service management practices," Ranga Prasad para [0013]).
As to claim 9, method claim 9 and system claim 1 are related as system and method of using same, with each claimed element’s function corresponding to the system step. Accordingly, claim 9 is similarly rejected under the same rationale as applied above with respect to the system claim.
As to claims 10-12, method claims 10-12 and system claims 2-4 are related as system and method of using same, with each claimed element’s function corresponding to the system step, respectively. Accordingly, claims 10-12 are similarly rejected under the same rationale as applied above with respect to the system claims.
Regarding claim 16, Ranga Prasad, in view of Wang, discloses all of the limitations of claim 1. Ranga Prasad further discloses wherein the relation information comprises dependency relationships between the plurality of elements indicating how failures in one element propagate to other elements in the IT system (Ranga Prasad para [0069]).
Regarding claim 17, Ranga Prasad, in view of Wang, discloses all of the limitations of claim 1. Ranga Prasad further discloses wherein the observation data comprises at least one of log data, performance metrics, or error messages collected from the identified at least one of the plurality of elements of the IT system (Ranga Prasad para [0016]).
Regarding claim 18, Ranga Prasad, in view of Wang, discloses all of the limitations of claim 1. Ranga Prasad further discloses wherein the computer system is configured to iteratively generate additional prompts based on the obtained findings to progressively narrow down the root cause of the failure across the identified at least one of the plurality of elements (“The LLM operates through several iterations, each time refining and validating the results to ensure accuracy and relevance, thereby enhancing the decision-making process within IT service management through deep learning insights. The outputs from the Processing Layer (410) are intricately utilized across the Logical Inference Database (412), Rules Engine (414), and Recommendation System (416),” Ranga Prasad para [0071]).
Regarding claim 19, Ranga Prasad, in view of Wang, discloses all of the limitations of claim 1. Ranga Prasad further discloses wherein the computer system is configured to store the obtained findings in association with the identified at least one of the plurality of elements for use in subsequent failure investigations (Ranga Prasad para [0072] and Fig. 7 reference character 712).
Regarding claim 20, Ranga Prasad, in view of Wang, discloses all of the limitations of claim 1. Ranga Prasad further discloses wherein the scope is selected based on a type of the failure detected in the IT system, and wherein different scopes correspond to different subsets of the plurality of elements to be investigated (Ranga Prasad para [0056]).
Claim(s) 6-7 and 13-14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ranga Prasad, in view of Wang, and further in view of Guo et al. (US Patent No. 12,368,745), hereinafter referred to as Guo.
Regarding claim 6, Ranga Prasad, in view of Wang, discloses all of the limitations of claim 1. Ranga Prasad further discloses wherein the scope included in the data comprises text data ("Initially, the Incident Data Mining module extracts text from all relevant fields of an incident ticket, organizing this data in a logical order for further processing," Ranga Prasad para [0010]), and wherein the computer system is configured to: generate a prompt, which includes text representing the scope and the relation information, and which instructs the text generation system to use natural language processing to identify at least one of the plurality of elements to be investigated based on semantic analysis of the scope and the relation information ("The Incident Validation & Classification Module (150) and the Incident Resolution Validation Module (152) are communicatively coupled to Incident Management 106. The Incident Validation & Classification Module utilizes NLP to analyze and standardize incident descriptions and resolutions," Ranga Prasad para [0047] and “It utilizes advanced algorithms and techniques to analyze the data semantically,” Ranga Prasad para [0069]);
and input the prompt to the text generation system to obtain the answer text including the at least one of the plurality of elements to be investigated ("It starts with identifying root causes, then utilizes the Generative AI Inference Module (GAIM) to derive insights (602), leading to the identification of process gaps," Ranga Prasad para [0079], shows an output from the GAIM).
However, Ranga Prasad fails to disclose that this is a second prompt.
Guo teaches a method and system for using natural language queries to conduct an investigation of a monitored system.
Guo teaches second prompt (Guo Fig. 5 reference character 506);
second prompt (Guo Fig. 5 reference character 506).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Ranga Prasad’s disclose of an incident and problem management data system utilizing generative artificial intelligence and large language models by including Guo’s method of utilizing multiple queries/prompts. Prompting an LLM or a generative model multiple times significantly increases the accuracy of its responses by allowing the model to better and more fully understand the context of the prompt. Adding other information for each prompt, such as the scope and relation information here, would only help to further increase the accuracy of the model’s responses, and therefore would have been an obvious inclusion.
Regarding claim 7, Ranga Prasad, in view of Wang, discloses all of the limitations of claim 1. Ranga Prasad further discloses wherein the computer system is configured to: generate a prompt, which includes the observation data relating to the identified at least one of the plurality of elements, and which instructs to generate text of the observation data (Ranga Prasad Fig. 1 reference characters 106 and 108 and reference characters 150 and 152 being used as inputs, i.e. a prompt, to the GAIM reference character 154); and input the prompt to the text generation system to obtain the answer text including the text of the observation data (Ranga Prasad Fig. 1 reference characters 150 and 152 being used as inputs, i.e. a prompt, to the GAIM reference character 154).
However, Ranga Prasad fails to disclose that this is a third prompt.
Guo teaches second prompt (Guo Fig. 6 reference character 506, if there are more than one second query, that is considered third or more queries);
second prompt (Guo Fig. 6 reference character 506, if there are more than one second query, that is considered third or more queries).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Ranga Prasad’s disclose of an incident and problem management data system utilizing generative artificial intelligence and large language models by including Guo’s method of utilizing multiple queries/prompts. Prompting an LLM or a generative model multiple times significantly increases the accuracy of its responses by allowing the model to better and more fully understand the context of the prompt. Adding other information for each prompt, observation information here, would only help to further increase the accuracy of the model’s responses, and therefore would have been an obvious inclusion.
As to claims 13-14, method claims 13-14 and system claims 6-7 are related as system and method of using same, with each claimed element’s function corresponding to the system step, respectively. Accordingly, claims 13-14 are similarly rejected under the same rationale as applied above with respect to the system claims.
Claim(s) 8 and 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ranga Prasad, in view of Wang, further in view of Guo, and further in view of Padmanabhan et al. (US Patent Application Publication No. 2025/0005299), hereinafter referred to as Padmanabhan.
Regarding claim 8, Ranga Prasad, in view of Wang and further in view of Guo, discloses all of the limitations of claim 7. Ranga Prasad further discloses wherein the computer system is configured to generate the prompt included in the observation data (Ranga Prasad Fig. 1 reference characters 106 and 108 and reference characters 150 and 152 being used as inputs, i.e. a prompt, to the GAIM reference character 154).
However, Ranga Prasad fails to disclose that this is a third prompt after masking some of values.
Guo teaches second prompt (Guo Fig. 6 reference character 506, if there are more than one second query, that is considered third or more queries).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Ranga Prasad’s disclose of an incident and problem management data system utilizing generative artificial intelligence and large language models by including Guo’s method of utilizing multiple queries/prompts. Prompting an LLM or a generative model multiple times significantly increases the accuracy of its responses by allowing the model to better and more fully understand the context of the prompt. Adding other information for each prompt, observation information here, would only help to further increase the accuracy of the model’s responses, and therefore would have been an obvious inclusion.
Padmanabhan teaches a system and method of language model prompt authoring and execution.
Padmanabhan teaches after masking some of values ("In some implementations, the data masker/demasker 214 may mask private data before a prompt is transmitted to a generative language model," Padmanabhan para [0029]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Ranga Prasad’s disclose of an incident and problem management data system utilizing generative artificial intelligence and large language models by including Padmanabhan’s teaching of masking data within a prompt before it is transmitted to a generative language model. This is a critical security technique that is used to prevent sensitive information from leaking into an unsecure environment. This would enable personally identifiable information, credentials, or any other similar data from being exploited, thereby keeping the system safe and intact.
As to claim 15, method claim 15 and system claim 8 are related as system and method of using same, with each claimed element’s function corresponding to the system step, respectively. Accordingly, claim 15 are similarly rejected under the same rationale as applied above with respect to the system claims.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ADAM MICHAEL WEAVER whose telephone number is (571)272-7062. The examiner can normally be reached Monday-Friday, 8AM-5PM EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Richemond Dorvil can be reached at (571) 272-7602. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/ADAM MICHAEL WEAVER/ Examiner, Art Unit 2658
/RICHEMOND DORVIL/ Supervisory Patent Examiner, Art Unit 2658
Prosecution Insights