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 .
DETAILED ACTION
Introduction
This office action is in response to Applicant’s submission filed on 12/3/2024. As such, claims 1-20 have been examined.
Subject Matter Eligibility
Examiner Comment Regarding Patent Subject Matter Eligibility under 35 U.S.C. 101
Independent claims 1, 14 and 20 involve a system/method/computer-readable storage media for monitoring robotic process automation (RPA) and troubleshooting. While some steps could be perform by a human, however, parsing large volume of digital data in real time and transforming large volume of data into vectors and performing search of vector database could not practically be performed as an abstract idea such as a mental process under the broadest reasonable interpretation (BRI). Accordingly, the independent claims and their dependents by virtue of their dependency, are directed towards patent eligible subject matter under step 2A prong 1, therefore the claims are patent eligible.
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.
Claims 1, 4, 7, 10-12, 14, 16-17, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Wang (US 20250258654), in view of Kunnath (US 20210133078), further in view of Puram (US 20240394323), and furthermore in view of Saudagar (US 20240064343).
Regarding Claim 1, Wang discloses: 1. A system comprising: memory; ([0072] Example 1 includes a computer-implemented method performed by a computer system having a memory) and one or more processors ([0072] and at least one hardware processor,) in communication with the memory and configured to:
receive, via a user interface, ([0018] The software development platform 110 may be configured to enable a user of the computing device 105 to create application software through graphical user interfaces and configuration,)
perform a search of the vector database based on the user query to obtain a set of vectorized log data associated with the at least one RPA tool; ([0033] In some example embodiments in which the analysis data comprises an analysis of input and output parameters of the artifact 320, the generating of the analysis data may comprise obtaining key-value pairs for the input and output parameters of the artifact 320 from a manifest file of the artifact 320, obtaining a list of vector embeddings from a vector database of vector embeddings corresponding to documentation for robotic process automation software based on a querying of the vector database using the key-value pairs of the input and output parameters of the artifact 320, and generating an analysis generation prompt based on the manifest file of the artifact 320 and the list of vector embeddings, where the analysis generation prompt is configured to instruct the large language model 140 to generate the analysis of the input and output parameters of the artifact 320 using the manifest file of the artifact 320 and the list of vector embeddings. The analyzer component 120 may then obtain the analysis of the input and output parameters of the artifact 320 based on the analysis generation prompt using the large language model 140, such as by sending the analysis generation prompt to the large language model 140.)
generate a prompt based on the user query and the set of vectorized log data; ([0033] In some example embodiments in which the analysis data comprises an analysis of input and output parameters of the artifact 320, the generating of the analysis data may comprise obtaining key-value pairs for the input and output parameters of the artifact 320 from a manifest file of the artifact 320, obtaining a list of vector embeddings from a vector database of vector embeddings corresponding to documentation for robotic process automation software based on a querying of the vector database using the key-value pairs of the input and output parameters of the artifact 320, and generating an analysis generation prompt based on the manifest file of the artifact 320 and the list of vector embeddings, where the analysis generation prompt is configured to instruct the large language model 140 to generate the analysis of the input and output parameters of the artifact 320 using the manifest file of the artifact 320 and the list of vector embeddings. The analyzer component 120 may then obtain the analysis of the input and output parameters of the artifact 320 based on the analysis generation prompt using the large language model 140, such as by sending the analysis generation prompt to the large language model 140.)
generate, by one or more generative artificial intelligence (AI) models based on the prompt, one or more insights related to the at least one RPA tool; ([0033] In some example embodiments in which the analysis data comprises an analysis of input and output parameters of the artifact 320, the generating of the analysis data may comprise obtaining key-value pairs for the input and output parameters of the artifact 320 from a manifest file of the artifact 320, obtaining a list of vector embeddings from a vector database of vector embeddings corresponding to documentation for robotic process automation software based on a querying of the vector database using the key-value pairs of the input and output parameters of the artifact 320, and generating an analysis generation prompt based on the manifest file of the artifact 320 and the list of vector embeddings, where the analysis generation prompt is configured to instruct the large language model 140 to generate the analysis of the input and output parameters of the artifact 320 using the manifest file of the artifact 320 and the list of vector embeddings. The analyzer component 120 may then obtain the analysis of the input and output parameters of the artifact 320 based on the analysis generation prompt using the large language model 140, such as by sending the analysis generation prompt to the large language model 140.)
Wang does not disclose stream log data in real-time from a plurality of data storage containers associated with a plurality of robotic process automation (RPA) tools;
Kunnath discloses: stream log data in real-time from a plurality of data storage containers associated with a plurality of robotic process automation (RPA) tools; ([0038] At step 402, job execution data of one or more jobs in the RPA system is determined based on logs of the RPA system. In one embodiment, the job execution data is additionally or alternatively determined based on metadata of jobs, such as, e.g., the current status of jobs, triggers that jobs having a suspended status are waiting for, or any other suitable metadata of jobs. As used herein, job execution data of a job refers to any data relating to the execution of the job. Various examples of job execution data of jobs are shown in FIGS. 5-10, which are described in further detail below. The job execution data of the jobs may be determined in substantially real time.) Also see para 0040.
Wang and Kunnath are considered analogous art. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Wang to combine the teaching of Kunnath for the above mentioned feature, because the method described enable real time tracking and centralized dashboard where user or admin can view issue and progress (Kunnath, [0038]).
Wang and Kunnath do not disclose a user query that identifies at least one RPA tool of the plurality of RPA tools;
Puram discloses: a user query that identifies at least one RPA tool of the plurality of RPA tools; ([0050] Web application elements handler service 404 may use the specified test automation tool to determine the programming language that is to be used in generating the handler classes. For example, if user 408a specifies SELENIUM as the test automation tool, web application elements handler service 404 can generate the handler classes for the selected elements in JAVA.)
Wang/Kunnath/Puram are considered analogous art. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Wang and Kunnath to combine the teaching of Puram for the above mentioned feature, because the method described enable user to select the tool that best suited their needs (Puram, [0050]).
Wang/Kunnath/Puram do not disclose the following features.
Saudagar discloses: transform in real-time, by one or more embedding models, the log data into vectors for storage in a vector database; ([0027] For example, the converting unit 308 converts the search keyword into a search vector, which may be used for subsequent searching processes. For example, the converting unit 308 converts a mix text of a live streaming program into an attribute vector, which corresponds to the live streaming program. The converting process may be performed in a real time manner such that, whenever the mix text varies, the corresponding attribute vector varies accordingly. The attribute vector may vary according to contents of the corresponding live streaming program while the live streaming program is being distributed. The attribute vector would be stored in the attribute vector database 204. In some embodiments, the converting unit 308 converts the mix texts for all available live streaming programs into their respective attribute vectors, and store the attribute vectors into the attribute vector database 204.)
and transmit the one or more insights to a user device for display. ([0050] In step S322, information of live streaming programs, whose corresponding attribute texts result in text matching results greater than the threshold (in step S320), is provided/transmitted to the user terminal. The user terminal thereby displays the text matching result to the user. In some embodiments, contextual matching results displayed in step S316 and text matching results displayed in step S322 may share mutual live streaming programs. In some embodiments, contextual matching results displayed in step S316 and text matching results displayed in step S322 may deliver different live streaming programs.)
Wang/Kunnath/Puram/Saudagar are considered analogous art. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Wang/Kunnath/Puram to combine the teaching of Saudagar for the above mentioned feature, because vector based approach takes context into consideration especially in semantic matching/retrieval application (Saudagar, [0027]).
Regarding Claim 4, Wang/Kunnath/Puram/Saudagar discloses: all the elements of claim 1,
Kunnath further discloses: wherein to stream the log data in real-time, ([0059] to show real-time resource bottlenecks.)
the one or more processors are configured to: stream RPA log data from logs generated by each RPA tool of the plurality of RPA tools; ([0059] User interface 1000 depicts workflow view 1002 and summary view 1004. Summary view 1004 indicates the number of pending jobs, running jobs, and idle jobs. As shown in FIG. 10, summary view 1004 indicates that there are 2 pending jobs, 1 running job, and 1 idle job. Workflow view 1002 depicts a visualization of the document processing workflow (e.g., long running workflow) of a particular job with status information corresponding to one or more activities of the workflow for Job 1. Workflow view 1002 may show workflows for other jobs via icons 1006. For example, a user may interact with icons 1006 to show workflows for a previous job or a next job in workflow view 1002. As shown in FIG. 10, workflow view 1002 indicates that RobotName01_1 completed the classify email activity in 1 minute, RobotName01_2 completed the extract claim activity in 3 minutes,) [The user interface visualizes workflow activities and durations executed by specific RPA tools (RobotName01_1, RobotName01_2), which inherently requires processing their underlying log and state data.]
and stream system log data from logs generated by each system of a plurality of disparate systems instructed to perform operations by the plurality of RPA tools. ([0059] and UserName01_1 assigned to activity claim approval form and has been waiting (i.e., idle) for 2 hours.) [The system processes tracking data from an external environment or application where a human (UserName01_1) interacts, showing cross-platform system/user bottlenecks.]
Where the rationale for the combination would be similar to the one already provided.
Regarding Claim 7, Wang/Kunnath/Puram/Saudagar discloses: all the elements of claim 1,
Saudagar further discloses: wherein to perform the search of the vector database, the one or more processors are configured to: transform, by the one or more embedding models, the user query to a series of vectors; ([0027] For example, the converting unit 308 converts the search keyword into a search vector, which may be used for subsequent searching processes. For example, the converting unit 308 converts a mix text of a live streaming program into an attribute vector, which corresponds to the live streaming program. The converting process may be performed in a real time manner such that, whenever the mix text varies, the corresponding attribute vector varies accordingly.)
and perform a semantic search on the vector database using the series of vectors of the user query. ([0027] For example, the converting unit 308 converts the search keyword into a search vector, which may be used for subsequent searching processes. For example, the converting unit 308 converts a mix text of a live streaming program into an attribute vector, which corresponds to the live streaming program. The converting process may be performed in a real time manner such that, whenever the mix text varies, the corresponding attribute vector varies accordingly. The attribute vector may vary according to contents of the corresponding live streaming program while the live streaming program is being distributed. The attribute vector would be stored in the attribute vector database 204. In some embodiments, the converting unit 308 converts the mix texts for all available live streaming programs into their respective attribute vectors, and store the attribute vectors into the attribute vector database 204.)
Where the rationale for the combination would be similar to the one already provided.
Regarding Claim 10, Wang/Kunnath/Puram/Saudagar discloses: all the elements of claim 1,
Puram further discloses: wherein to identify the at least one RPA tool, the user query includes at least one of a name, ([0050] Web application elements handler service 404 may use the specified test automation tool to determine the programming language that is to be used in generating the handler classes. For example, if user 408a specifies SELENIUM as the test automation tool, web application elements handler service 404 can generate the handler classes for the selected elements in JAVA. If a different test automation tool is specified, web application elements handler service 404 can generate handler classes for the elements in a programming language supported by or compatible with the specified test automation tool. For example, if user 408a or any of other users 408 (e.g., user 408b) selects one or more elements and specifies VISUAL STUDIO as the test automation tool, web application elements handler service 404 can generate the handler classes for the selected elements in C #.)[although the reference identify a test automation tool instead of RPA tool, but RPA tool is already disclose by the other reference cited, Kunnath.] Where the rationale for the combination would be similar to the one already provided.
Regarding Claim 11, Wang/Kunnath/Puram/Saudagar discloses: all the elements of claim 1,
Wang further discloses: wherein the one or more generative AI models comprise one or more question-answering transformer models. ([0019] The analyzer component 120 may be configured to analyze the process and its related artifacts. The analyzer component 120 may traverse the hierarchical structure of this process and generate analysis data for each artifact in the process. The analysis component 120 may generate the analysis data by using metadata to generate an analysis generation prompt, which may be used to instruct the large language model 140 to generate the analysis data for the artifact.)
Regarding Claim 12, Wang/Kunnath/Puram/Saudagar discloses: all the elements of claim 1,
Wang further discloses: wherein the one or more generative AI models comprise one or more large-language models (LLMs), and wherein to generate the one or more insights, the one or LLMs are configured to generate one or more natural language insights related to the at least one RPA tool. ([0019] The analyzer component 120 may be configured to analyze the process and its related artifacts. The analyzer component 120 may traverse the hierarchical structure of this process and generate analysis data for each artifact in the process. The analysis component 120 may generate the analysis data by using metadata to generate an analysis generation prompt, which may be used to instruct the large language model 140 to generate the analysis data for the artifact.)
Regarding Claim 14, it is a method claim that recites elements similar to claim 1, therefore the rationale applied in rejection of claim 1 is equally applicable.
Regarding Claim 16, it is a method claim that recites elements similar to claim 4, therefore the rationale applied in rejection of claim 4 is equally applicable.
Regarding Claim 17, it is a method claim that recites elements similar to claim 7, therefore the rationale applied in rejection of claim 7 is equally applicable.
Regarding Claim 20, Wang discloses: 20. Non-transitory computer-readable storage media comprising instructions that, when executed, cause one or more processors to: ([0013] The methods or embodiments disclosed herein may be implemented as a computer system having one or more modules (e.g., hardware modules or software modules). Such modules may be executed by one or more hardware processors of the computer system. In some example embodiments, a non-transitory machine-readable storage device can store a set of instructions that, when executed by at least one processor, causes the at least one processor to perform the operations and method steps discussed within the present disclosure.) As for the rest of the claim, they recite elements of Claim 1, therefore the rationale applied in rejection of Claim 1 is similarly applicable.
Claims 2 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Wang (US 20250258654), in view of Kunnath (US 20210133078), further in view of Puram (US 20240394323), and furthermore in view of Saudagar (US 20240064343) and Zhong (US 20210303638).
Regarding claim 2, Wang/Kunnath/Puram/Saudagar disclose all the elements of claim 1,
Wang/Kunnath/Puram/Saudagar do not teach wherein the one or more processors are configured to continuously update the vector database based on the real-time streaming and transformation of the log data.
Zhong discloses: wherein the one or more processors are configured to continuously update the vector database based on the real-time streaming and transformation of the log data. ([0081] Subsequent responses by the user to output 234 (e.g., clicks, likes, saves, shares, ignores, dismisses, hides, etc.), may, in turn, be used to generate events that are fed back into the system via event streams 200 and used to update embedding model 208, entity embeddings 226, clusters 224, hierarchy 222, match scores 246, standardized entities 232, and/or output 234 related to input string 230.)
Wang/Kunnath/Puram/Saudaga/Zhong are considered analogous art. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of teachings to combine with the teaching of Zhong for the above mentioned feature, because the method describe enable machine learning system to adapt to changes instantly (Zhong, [0081]).
Claim 15 are a method claims that corresponds to claims 2 and is rejected under similar rationale.
Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over Wang (US 20250258654), in view of Kunnath (US 20210133078), further in view of Puram (US 20240394323), and furthermore in view of Saudagar (US 20240064343), Zhong (US 20210303638) and Kasturi (US 20250139142).
Regarding Claim 3, Wang/Kunnath/Puram/Saudagar/Zhong disclose all the elements of claim 2,
Wang/Kunnath/Puram/Saudagar/Zhong do not teach wherein the one or more processors are further configured to fine-tune the one or more generative AI models based on the continuously updated vector database.
Kasturi discloses: wherein the one or more processors are further configured to fine-tune the one or more generative AI models based on the continuously updated vector database. ([0064] An updated vector database is coupled to a fine-tuning system to determine if the LLM service model should be further fine-tuned.)
Wang/Kunnath/Puram/Saudagar/Zhong/Kasturi are considered analogous art. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of teachings to combine with the teaching of Kasturi for the above mentioned feature, because the method describe enable continuous knowledge update is provided to the LLM which would naturally lead to more accurate responses and less hallucinations (Kasturi, [0064]).
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over Wang (US 20250258654), in view of Kunnath (US 20210133078), further in view of Puram (US 20240394323), and furthermore in view of Saudagar (US 20240064343), and Peterson (US 20250294036).
Regarding Claim 5, Wang/Kunnath/Puram/Saudagar disclose all the elements of claim 1,
Wang/Kunnath/Puram/Saudagar do not teach wherein the one or more processors are configured to store the vectors of the log data in the vector database organized by one or more attributes of the log data.
Peterson discloses: wherein the one or more processors are configured to store the vectors of the log data in the vector database organized by one or more attributes of the log data. ([0042] According to various embodiments, continuing from the transformation and storage of log data into a vector database, the present technology advances to categorization and vectorization of log buckets. Specific categories, such as “malware downloads” and “brute force login attempt,” are assigned to these buckets. This categorization may be critical in various embodiments as this categorization represents the consolidated knowledge distilled from the diverse and previously uncorrelated log data.)
Wang/Kunnath/Puram/Saudagar/Peterson are considered analogous art. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of teachings to combine with the teaching of Peterson for the above mentioned feature, because utilizing an innovative approach to identify and categorize similarities within historical log data, the present technology streamlines the process of log analysis (Peterson, [Abstract]).
Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over Wang (US 20250258654), in view of Kunnath (US 20210133078), further in view of Puram (US 20240394323), and furthermore in view of Saudagar (US 20240064343), Peterson (US 20250294036) and Applicant supplied reference, application publication of Crane (US 20220357940).
Regarding Claim 6, Wang/Kunnath/Puram/Saudagar/Peterson disclose all the elements of claim 5,
Wang/Kunnath/Puram/Saudagar/Peterson do not teach wherein the one or more attributes of the log data include a name or an identifier of the at least one RPA tool for which the log data was generated by the at least one RPA tool itself and by one or more disparate systems instructed to perform operations by the at least one RPA tool.
Crane discloses: wherein the one or more attributes of the log data include a name or an identifier of the at least one RPA tool for which the log data was generated by the at least one RPA tool itself and by one or more disparate systems instructed to perform operations by the at least one RPA tool. ([0164] Record 804 is a rule that indicates a failure type of “2” and a description of “server unreachable”. Thus, the failure type is that of a bot that was unable to communicate with a server. The bot name is “rpa_bot1” and the correspondent node address is 10.0.2.2 (again consistent with log file 700). Thus, a matching failure prediction will contain the text of or references to the failure type, bot name, and/or correspondent node address. Applying this rule to a matching failure prediction, may result in automated repair controller 610 causing execution of a script to restart “rpa_bot1”, restart the server at 10.0.2.2, or cause “rpa_bot1” to attempt the transaction with another correspondent node address. For example, the service that “rpa_bot1” is attempting to access may have moved to a different IP address, and this IP address may be provided to the bot.) [the reference discloses failure state involving a remote server (node 10.0.2.2) which is entirely separate from the bot, yet intrinsically tied to the bot's workflow. This remote server's unreachability likely generated server-side logs, corroborating the bot-side logs in 700.]
Wang/Kunnath/Puram/Saudagar/Peterson/Crane are considered analogous art. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of teachings to combine with the teaching of Crane for the above mentioned feature, because the system recognizes the bot ID, the server IP, and applies a rule to execute an automated script to restart the failing components or update the server routing table dynamically (Crane, [0164]).
Claims 8-9, and 18-19 are rejected under 35 U.S.C. 103 as being unpatentable over Wang (US 20250258654), in view of Kunnath (US 20210133078), further in view of Puram (US 20240394323), and furthermore in view of Saudagar (US 20240064343), and Grigore (US 20250199777).
Regarding claim 8, Wang/Kunnath/Puram/Saudagar disclose all the elements of claim 1,
Wang/Kunnath/Puram/Saudagar do not teach wherein to generate the prompt, the one or more processors are configured to: transform the set of vectorized log data into text of log data associated with the at least one RPA tool, including log data generated by the at least one RPA tool itself and by one or more disparate systems instructed to perform operations by the at least one RPA tool; and build the prompt requesting the one or more insights related to the at least one RPA tool based on the user query and the text of the log data associated with the at least one RPA tool.
Grigore discloses: wherein to generate the prompt, the one or more processors are configured to: transform the set of vectorized log data into text of log data associated with the at least one RPA tool, including log data generated by the at least one RPA tool itself and by one or more disparate systems instructed to perform operations by the at least one RPA tool; ([0029] To address such issues, the smart handler may pause the automation, look at where the automation is in the RPA workflow and what is on the screen, look at system logs, look at an initial definition of the automation, process automation documents, etc. This is done using a cognitive AI layer (e.g., incorporating generative AI) that can also include design time information in some embodiments, such as what the automation is intended to do (e.g., send an email, submit a form, complete a spreadsheet, etc.). In some embodiments, the smart handler may seek to undo the operations that were performed by the automation, such as returning the computing system to the original state and reversing the operations of the automation, rolling back the operations, rollback a database commit, etc..)[analyze the system logs and process automation documents requires transforming raw vectorized log data into text that AI can read. External system logs like database or application states reads on disparate systems interacting with the RPA]
and build the prompt requesting the one or more insights related to the at least one RPA tool based on the user query and the text of the log data associated with the at least one RPA tool. ([0029] To address such issues, the smart handler may pause the automation, look at where the automation is in the RPA workflow and what is on the screen, look at system logs, look at an initial definition of the automation, process automation documents, etc. This is done using a cognitive AI layer (e.g., incorporating generative AI) that can also include design time information in some embodiments, such as what the automation is intended to do (e.g., send an email, submit a form, complete a spreadsheet, etc.).) [cognitive AI layer is a generative model that process prompt to address user query.]
Wang/Kunnath/Puram/Saudagar/Grigore are considered analogous art. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of teachings to combine with the teaching of Grigore for the above-mentioned feature, because an improved and/or alternative approach to RPA workflow development at design time and/or executing automations at runtime may be beneficial (Grigore, [Background]).
Regarding claim 9, Wang/Kunnath/Puram/Saudagar disclose all the elements of claim 1,
Wang/Kunnath/Puram/Saudagar do not teach wherein the one or more insights generated by the one or more generative AI models comprise at least one of: one or more issues related to the at least one RPA tool identified in the user query, at least one root cause of the one or more issues, or one or more predicted solutions to resolve the one or more issues.
Grigore discloses: wherein the one or more insights generated by the one or more generative AI models comprise at least one of: one or more issues related to the at least one RPA tool identified in the user query, ([0029] To address such issues, the smart handler may pause the automation, look at where the automation is in the RPA workflow and what is on the screen, look at system logs, look at an initial definition of the automation, process automation documents, etc. This is done using a cognitive AI layer (e.g., incorporating generative AI) that can also include design time information in some embodiments, such as what the automation is intended to do (e.g., send an email, submit a form, complete a spreadsheet, etc.). In some embodiments, the smart handler may seek to undo the operations that were performed by the automation, such as returning the computing system to the original state and reversing the operations of the automation, rolling back the operations, rollback a database commit, etc. For instance, the smart handler may: (1) suggest code changes that bypass failures, but keeping the underlying logic of the automation; (2) provide application change suggestions to bypass issues, but keep the underlying business logic; (3) provide business rule suggestions to improve the execution of the workflow in terms of performance and/or return on investment (ROI), which may essentially be process improvement suggestions based on execution data; (4) provide test cases that should be added for failure situations to be detected faster in the future; or (5) any combination thereof.)
at least one root cause of the one or more issues, ([0029] This is done using a cognitive AI layer (e.g., incorporating generative AI) that can also include design time information in some embodiments, such as what the automation is intended to do (e.g., send an email, submit a form, complete a spreadsheet, etc.). In some embodiments, the smart handler may seek to undo the operations that were performed by the automation, such as returning the computing system to the original state and reversing the operations of the automation, rolling back the operations, rollback a database commit, etc. For instance, the smart handler may: (1) suggest code changes that bypass failures, but keeping the underlying logic of the automation; (2) provide application change suggestions to bypass issues, but keep the underlying business logic; (3) provide business rule suggestions to improve the execution of the workflow in terms of performance and/or return on investment (ROI), which may essentially be process improvement suggestions based on execution data; (4) provide test cases that should be added for failure situations to be detected faster in the future; or (5) any combination thereof.)
or one or more predicted solutions to resolve the one or more issues. ([0029] In some embodiments, the smart handler may seek to undo the operations that were performed by the automation, such as returning the computing system to the original state and reversing the operations of the automation, rolling back the operations, rollback a database commit, etc. For instance, the smart handler may: (1) suggest code changes that bypass failures, but keeping the underlying logic of the automation; (2) provide application change suggestions to bypass issues, but keep the underlying business logic; (3) provide business rule suggestions to improve the execution of the workflow in terms of performance and/or return on investment (ROI), which may essentially be process improvement suggestions based on execution data; (4) provide test cases that should be added for failure situations to be detected faster in the future; or (5) any combination thereof.)
Where the rationale for the combination would be similar to the one already provided.
Claim 18 are a method claims that corresponds to claims 8 and is rejected under similar rationale.
Claim 19 are a method claims that corresponds to claims 9 and is rejected under similar rationale.
Claim 13 is rejected under 35 U.S.C. 103 as being unpatentable over Wang (US 20250258654), in view of Kunnath (US 20210133078), further in view of Puram (US 20240394323), and furthermore in view of Saudagar (US 20240064343), and Kasturi (US 20250139142).
Regarding claim 13, Wang/Kunnath/Puram/Saudagar disclose all the elements of claim 1,
Wang further discloses: wherein the user interface comprises ([0019] The analyzer component 120 may be configured to analyze the process and its related artifacts. The analyzer component 120 may traverse the hierarchical structure of this process and generate analysis data for each artifact in the process. The analysis component 120 may generate the analysis data by using metadata to generate an analysis generation prompt, which may be used to instruct the large language model 140 to generate the analysis data for the artifact.)Also see para 0101, transmission using network interface device.
Wang/Kunnath/Puram/Saudagar do not teach conversational window of a chatbot.
Kasturi discloses: conversational window of a chatbot. ([0022] FIG. 13A is a diagram of a chat user interface with a virtual agent for the service provider virtual communication system.)
Wang/Kunnath/Puram/Saudagar/Kastuir are considered analogous art. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of teachings to combine with the teaching of Kasturi for the above-mentioned feature, because there are a number of advantages to the disclosed embodiments. The Enterprise AI software provides a validated AI platform that has been purpose-built to extract predictive and prescriptive insights from unstructured textual, sensor, and procedural data in the automotive aftermarket and service business (Kasturi, [0092]).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure: Ragukumar (US 20250200073) – discloses method/system for implementing LLM to extract customized insights from log data. See Abstract, and figs 1-15 for additional details.
Jangala, V. K. (2020). Monitoring and observability tools for cloud-based enterprise systems. International Journal of Trend in Research and Development, 7(2), 311-317. – teaches a comprehensive review of observability and monitoring solutions for complex, distributed enterprise cloud environments, outlining strategies to transition from basic monitoring to proactive observability. It evaluates leading commercial and open-source tools like Prometheus and Datadog, while covering the telemetry pillars of metrics, logs, and traces to address enterprise challenges like data volume and alert fatigue. See Abstract and figs on page 2, 3 and 5 for additional details.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Philip H Lam whose telephone number is (571)272-1721. The examiner can normally be reached 9 AM-3 PM Pacific time.
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, Bhavesh Mehta can be reached on 571-272-7453. 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.
/PHILIP H LAM/ Examiner, Art Unit 2656
Prosecution Insights