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 .
Remarks
This Office Action is responsive to Applicants' Amendment filed on August 3, 2026, in which claims 1-3, 7-9, 13, and 14 are currently amended. Claims 1-18 are currently pending.
Response to Arguments
Applicant’s arguments with respect to rejection of claims 1-18 under 35 U.S.C. 101 based on amendment have been considered, however, are not persuasive.
With respect to Applicant's arguments on p. 7 of the Remarks submitted 8/3/2026 that "the human mind is not equipped for processing data relating to such a computer process," Examiner respectfully disagrees. Examiner asserts that the human mind is well equipped to and routinely describes computer processes in natural language.
With respect to Applicant's arguments on p. 7 of the Remarks submitted 8/3/2026 that the claims require the steps to be generated "using a large language model," Examiner respectfully disagrees. The claim limitations recite "generating a natural language representation of one or more automation steps or performing the activity using a large language model based on the instructions" which, grammatically, appears to amount to generating a prompt that is compatible with a large language model (for performing the activity) rather than using the large language model to generate the natural language representation. Even if the claim were directed towards using a large language model to generate the natural language representation, this amounts to mere instructions to apply the judicial exception using generic computer components.
With respect to Applicant's arguments on pp. 8-9 of the Remarks submitted 8/3/2026 that the claims present a technical improvement, Examiner respectfully disagrees. Applicant's arguments are that the technical improvement is "reducing the time needed to create automations for the process mining activities". First, Examiner notes (MPEP 2106.05(a) also recites "An important consideration in determining whether a claim improves technology is the extent to which the claim covers a particular solution to a problem or a particular way to achieve a desired outcome, as opposed to merely claiming the idea of a solution or outcome."). Secondly, Applicant's arguments on p. 8 of the Remarks submitted 8/3/2026 that the perceived technical improvement is achieved through using the large language model to generate the natural language steps. While Examiner does not necessarily agree that the instant claims are currently directed towards this interpretation (as noted above), Examiner notes that the instant specification suggests that this is merely a task of replacing a human in the loop with a "large language model" ([¶0002] "discovered process mining processes are not able to be directly and automatically translated to a robot implementation. Instead, a user must manually analyze and define each step in the processes for automating such processes via RPA") which appears to confirm that the claims are directed towards a mental process being applied with a generic computer component (the large language model) which does not provide a practical application (MPEP 2106.07(a)(II) "employing well-known computer functions to execute an abstract idea, even when limiting the use of the idea to one particular environment, does not integrate the exception into a practical application").
For at least these reasons and those further detailed below, Examiner asserts that it is reasonable and appropriate to maintain the rejection under 35 USC 101.
Applicant’s arguments with respect to rejection of claims 1-18 under 35 U.S.C. 102 based on amendment have been considered, however, are not persuasive.
With respect to Applicant's arguments on p. 11 of the Remarks submitted 8/3/2026 that Gorrono "does not teach or suggest the "natural language representation of one or more automation steps for performing the activity"," Examiner respectfully disagrees. Gorrono explicitly discloses ([¶0056] " an automation is designed based on the natural language input. In step 304, an automation workflow may be generated based at least on the natural language input to design the automation."). With respect to Applicant's arguments "the automation workflow is not a "natural language representation of one or more automation steps.") Examiner notes that this is not what the instant claims require, in fact the instant claims never once recite the term "workflow" or functionally infer that an automation workflow is a natural language representation. With respect to the claim language “generating a natural language representation of one or more automation steps for performing the activity using a large language model based on the instructions” Gorrono explicitly discloses ([¶0056] "an automation is designed based on the natural language input. In step 304, an automation workflow may be generated based at least on the natural language input to design the automation.").
With respect to Applicant's arguments on p. 11 of the Remarks submitted 8/3/2026 that Gorrono does not "teach or suggest at least "generating a natural language representation of one or more automation steps ... based on ... the one or more names of the one or more source systems from which at least a part of the computer process was extracted via process mining," Examiner respectfully disagrees. Gorrono explicitly discloses ([¶0028] "configured to take the natural language input description provided by the user" [¶0039] "consider that a user enters natural language input of “I want to store email attachments to OneDrive” in workflow generator GUI 116. One result of this input is that workflow generator GUI 116 displays the one or more steps to generation the automation for storing the user's email attachments to OneDrive® (see exemplary description of FIGS. below).") where OneDrive is interpreted as the name of one or more source system from which at least a part of the process was extracted, such that the natural language representation is clearly "based on" the one or more names of the one or more source systems from which at least a part of the computer process was extracted via process mining. With respect to Applicant's arguments on p. 12 of the Remarks submitted 8/3/2026 that the explicit natural language prompt in Gorrono ([¶0028] “I want to store email attachments to OneDrive”) does not identify OneDrive, Examiner respectfully disagrees. The prompt explicitly and objectively identifies OneDrive and Gorrono explicitly and repeatedly identifies Outlook as one of the systems ([¶0033] " Local application 122 may be any type of local application/service, such as but not limited to, a database application (e.g., QuickBooks®, a Microsoft® Excel® spreadsheet), a messaging application (e.g., Microsoft® Outlook®)" [¶0067] "user input 406 indicates that the user desires to utilize a workflow to create an automation that automatically saves attachments received by email to a user's storage account, here OneDrive® from Microsoft Corp. of Redmond, WA. Accordingly, step display element 502 is labeled as “On new email” and input field 504 is pre-populated with “Inbox,” which may correspond to Outlook® from Microsoft Corp. of Redmond, WA, as the user may be authenticated currently to their Outlook® account. Additionally, user input 406 may specify “Outlook” as the email service/application in some scenarios" [¶0081] "the user may enter an email address for their Outlook® account into input field 802." [¶0086] "a user's NL input includes an email program/service, e.g., Outlook®, and includes performing an action on items in the user's Inbox, the logical expressions of the intermediate language enable a determination of parameters, e.g., “Inbox,” such as: IF “Outlook”, THEN SELECT PARAMETER “Inbox” for received email."). Applicant is respectfully reminded that cited prior art references must be considered in their entirety and not only the cited sections (MPEP 2141.02(VI)).
With respect to Applicant’s arguments on p. 12 of the Remarks submitted 8/3/2026 that “the cited portions of Gorrono do not teach or suggest at least “generating a natural language representation of one or more automation steps … based on … the name of the activity,” Examiner respectfully disagrees. Gorrono discloses, ([¶0039] "store email attachments to OneDrive" [¶0067] "step display element 502 is labeled as “On new email” and input field 504 is pre-populated with “Inbox,” which may correspond to Outlook® from Microsoft Corp. of Redmond, WA, as the user may be authenticated currently to their Outlook® account." [¶0070] " A step display element includes one or more sub-steps and/or one or more input fields, in some aspects. Step display element 506 includes a sub-step display element 506-1 for file creation, as relates to the example for user input 406 and its “attachments” and “OneDrive” portions").
PNG
media_image1.png
598
962
media_image1.png
Greyscale
FIG. 5 of US20230333827A1
In FIG. 5 elements 502 and 506 of Gorrono you can see that the activity names are explicitly part of the generated natural language representations of one or more automation steps for performing the activity using a large language model. With respect to Applicant’s arguments on p. 13 of the Remarks submitted 8/3/2026 that “the label is not used for generating one or more steps of the automation workflow,” while Examiner does not necessarily agree, this point is moot as the instant claims do not require this either. The instant claims recite “generating a natural language representation of one or more automation steps for performing the activity using a large language model based on the instructions, the description of the computer process, the one or more names of the one or more source systems, and the name of the activity.” Where “On new email” is clearly a natural language representation of an automation step preceding “Apply to each attachment on the email” and the generating a natural language representation of said steps is objectively based on the name of the activity.
For at least these reasons and those further detailed below, Examiner asserts that it is reasonable and appropriate to maintain the rejection under 35 USC 102.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-18 are rejected under U.S.C. §102(a)(1) as being anticipated by Gorrono (US20230333827A1).
Regarding claim 1, Gorrono teaches A computer-implemented method comprising:([Abstract] "Methods for generating automations via natural language processing are performed by computing systems")
receiving one or more prompts defining 1) instructions,([Abstract] "Natural language input is received from a user interface" [¶0028] "users can describe in plain language what they want to automate" [¶0039] "consider that a user enters natural language input of “I want to store email attachments to OneDrive” in workflow generator GUI 116. One result of this input is that workflow generator GUI 116 displays the one or more steps to generation the automation for storing the user's email attachments to OneDrive® (see exemplary description of FIGS. below)." The users natural language prompt gives instructions to generate an automation that stores email attachments to OneDrive)
2) a description of a computer process, ([¶0028] "configured to take the natural language input description provided by the user" [¶0039] "consider that a user enters natural language input of “I want to store email attachments to OneDrive” in workflow generator GUI 116. One result of this input is that workflow generator GUI 116 displays the one or more steps to generation the automation for storing the user's email attachments to OneDrive® (see exemplary description of FIGS. below)." The prompt is not merely a command word, it describes the process to automate in natural language)
3) one or more names of one or more source systems from which at least a part of the computer process was extracted via process mining, ([¶0028] "configured to take the natural language input description provided by the user" [¶0039] "consider that a user enters natural language input of “I want to store email attachments to OneDrive” in workflow generator GUI 116. One result of this input is that workflow generator GUI 116 displays the one or more steps to generation the automation for storing the user's email attachments to OneDrive® (see exemplary description of FIGS. below)." Outlook is interpreted as the name of one or more source system from which at least a part of the process was extracted)
and 4) a name of an activity of the computer process;([¶0039 ] "store email attachments to OneDrive" [¶0067] "step display element 502 is labeled as “On new email” and input field 504 is pre-populated with “Inbox,” which may correspond to Outlook® from Microsoft Corp. of Redmond, WA, as the user may be authenticated currently to their Outlook® account." [¶0070] " A step display element includes one or more sub-steps and/or one or more input fields, in some aspects. Step display element 506 includes a sub-step display element 506-1 for file creation, as relates to the example for user input 406 and its “attachments” and “OneDrive” portions" Gorrono's prompt and generated steps identify activity names/labels "store email attachments," "on new email," and "file creation.")
generating a natural language representation of one or more automation steps to be performed ([¶0056] " an automation is designed based on the natural language input. In step 304, an automation workflow may be generated based at least on the natural language input to design the automation. The automation workflow includes one or more steps to design and build an automation that includes one or more operations" [¶0057] "a user interface is populated with parameters for operations of the automation, the parameters derived from the natural language input. In aspects herein, a step(s) of the workflow is provided to the user interface. For instance, and as described herein, a step(s) of the workflow is/are displayed to a user via the GUIs [...] The steps correspond to the automation operations desired by the user, and represent the automation workflow generally. For example, and as described, some input fields for a given step are automatically populated (also “pre-populated” herein) with a parameter value(s) based on the NL input (e.g., in the example scenario “I want to store email attachments to OneDrive,” the first step may have auto-populated fields for an email application “inbox”), while some other fields for the same or a different step are populated based on value “inbox,” as well as here on the NL input “attachments” (e.g., “attachments” may be auto-populated, along with “attachment name” and “attachment content” parameters)" Gorrono explicitly generates a natural language robotic automation process workflow to display to the user based on the users natural language input using the LLM)
for performing the activity using a large language model ([¶0029] "generating automations, flows, bots, etc" [¶0031] "workflow generator 106 and an automation library 118 that stores steps for automations, flows, bots, etc." [¶0056] " an automation is designed based on the natural language input. In step 304, an automation workflow may be generated based at least on the natural language input to design the automation. The automation workflow includes one or more steps to design and build an automation that includes one or more operations" Gorrono explicitly generates a natural language robotic automation process workflow to display to the user based on the users natural language input using the LLM)
based on the instructions, ([Abstract] "Natural language input is received from a user interface" [¶0028] "users can describe in plain language what they want to automate" [¶0039] "consider that a user enters natural language input of “I want to store email attachments to OneDrive” in workflow generator GUI 116. One result of this input is that workflow generator GUI 116 displays the one or more steps to generation the automation for storing the user's email attachments to OneDrive® (see exemplary description of FIGS. below)." The users natural language prompt gives instructions to generate an automation that stores email attachments to OneDrive)
the description of the computer process,([¶0028] "configured to take the natural language input description provided by the user" [¶0039] "consider that a user enters natural language input of “I want to store email attachments to OneDrive” in workflow generator GUI 116. One result of this input is that workflow generator GUI 116 displays the one or more steps to generation the automation for storing the user's email attachments to OneDrive® (see exemplary description of FIGS. below)." The prompt is not merely a command word, it describes the process to automate in natural language)
the one or more names of the one or more source systems, ([¶0028] "configured to take the natural language input description provided by the user" [¶0039] "consider that a user enters natural language input of “I want to store email attachments to OneDrive” in workflow generator GUI 116. One result of this input is that workflow generator GUI 116 displays the one or more steps to generation the automation for storing the user's email attachments to OneDrive® (see exemplary description of FIGS. below)." OneDrive is interpreted as the name of one or more source system from which at least a part of the process was extracted)
and the name of the activity; and([¶0039 ] "store email attachments to OneDrive" [¶0067] "step display element 502 is labeled as “On new email” and input field 504 is pre-populated with “Inbox,” which may correspond to Outlook® from Microsoft Corp. of Redmond, WA, as the user may be authenticated currently to their Outlook® account." [¶0070] " A step display element includes one or more sub-steps and/or one or more input fields, in some aspects. Step display element 506 includes a sub-step display element 506-1 for file creation, as relates to the example for user input 406 and its “attachments” and “OneDrive” portions" Gorrono's prompt and generated steps identify activity names/labels "store email attachments," "on new email," and "file creation.")
outputting the natural language representation of the one or more automation steps for performing the activity.([¶0057] "a user interface is populated with parameters for operations of the automation, the parameters derived from the natural language input. In aspects herein, a step(s) of the workflow is provided to the user interface" [¶0057] "provide the steps to a user device, e.g., a browser or the like, for display to the user. Steps may be displayed together in a single screen, or separately in multiple screens" the intermediate representations of the steps displayed to the user by Gorrono are explicitly natural language text).
Regarding claim 2, Gorrono teaches The computer-implemented method of claim 1, further comprising: generating one or more RPA (robotic process automation) steps to be performed by one or more RPA robots based on the natural language representation of the one or more automation steps.(Gorrono [¶0056] " an automation is designed based on the natural language input. In step 304, an automation workflow may be generated based at least on the natural language input to design the automation. The automation workflow includes one or more steps to design and build an automation that includes one or more operations" [¶0057] "a user interface is populated with parameters for operations of the automation, the parameters derived from the natural language input. In aspects herein, a step(s) of the workflow is provided to the user interface. For instance, and as described herein, a step(s) of the workflow is/are displayed to a user via the GUIs [...] The steps correspond to the automation operations desired by the user, and represent the automation workflow generally. For example, and as described, some input fields for a given step are automatically populated (also “pre-populated” herein) with a parameter value(s) based on the NL input (e.g., in the example scenario “I want to store email attachments to OneDrive,” the first step may have auto-populated fields for an email application “inbox”), while some other fields for the same or a different step are populated based on value “inbox,” as well as here on the NL input “attachments” (e.g., “attachments” may be auto-populated, along with “attachment name” and “attachment content” parameters)" Gorrono explicitly generates robotic automation process workflow).
Regarding claim 3, Gorrono teaches The computer-implemented method of claim 2, wherein generating one or more RPA steps to be performed by the one or more RPA robots based on the natural language representation of the one or more automation steps comprises:(Gorrono [¶0056] " an automation is designed based on the natural language input. In step 304, an automation workflow may be generated based at least on the natural language input to design the automation. The automation workflow includes one or more steps to design and build an automation that includes one or more operations" [¶0057] "a user interface is populated with parameters for operations of the automation, the parameters derived from the natural language input. In aspects herein, a step(s) of the workflow is provided to the user interface. For instance, and as described herein, a step(s) of the workflow is/are displayed to a user via the GUIs [...] The steps correspond to the automation operations desired by the user, and represent the automation workflow generally. For example, and as described, some input fields for a given step are automatically populated (also “pre-populated” herein) with a parameter value(s) based on the NL input (e.g., in the example scenario “I want to store email attachments to OneDrive,” the first step may have auto-populated fields for an email application “inbox”), while some other fields for the same or a different step are populated based on value “inbox,” as well as here on the NL input “attachments” (e.g., “attachments” may be auto-populated, along with “attachment name” and “attachment content” parameters)" Gorrono explicitly generates a natural language robotic automation process workflow to display to the user based on the users natural language input using the LLM)
generating the one or more RPA steps using a machine learning based model. (Gorrono [¶0056] " Steps to design and build automations are stored in automation library 224, and are determined by workflow logic generator 212 based at least on the NL inputs (e.g., by receiving the natural language input at the machine learning NL model").
Regarding claim 4, Gorrono teaches The computer-implemented method of claim 2, further comprising: performing the one or more RPA steps by the one or more RPA robots to perform the activity.(Gorrono [¶0042] "During runtime of the automation/flow, the automation may invoke operation of one or more local or network-based applications associated with the automation/flow steps 120 of the automation. Each flow step 120 may receive input data from or transmit output data to the one or more local or network-based applications").
Regarding claim 5, Gorrono teaches The computer-implemented method of claim 1, wherein the description of the process is generated using a machine learning based model.(Gorrono [¶0028] "Users are enabled to speak or type in natural language what they want to automate, and aspects described herein generate for them the automation flow that performs it. In some aspects, by way of example and not limitation, a GPT-3 model that has been fined-tuned is configured to take the natural language input description provided by the user" [¶0039] "consider that a user enters natural language input of “I want to store email attachments to OneDrive” in workflow generator GUI 116. One result of this input is that workflow generator GUI 116 displays the one or more steps to generation the automation for storing the user's email attachments to OneDrive® (see exemplary description of FIGS. below)." [¶0056] " Steps to design and build automations are stored in automation library 224, and are determined by workflow logic generator 212 based at least on the NL inputs (e.g., by receiving the natural language input at the machine learning NL model").
Regarding claim 6, Gorrono teaches The computer-implemented method of claim 1, wherein the large language model receives as input the one or more prompts (Gorrono [Abstract] "Natural language input is received from a user interface" [¶0028] "users can describe in plain language what they want to automate" [¶0039] "consider that a user enters natural language input of “I want to store email attachments to OneDrive” in workflow generator GUI 116. One result of this input is that workflow generator GUI 116 displays the one or more steps to generation the automation for storing the user's email attachments to OneDrive® (see exemplary description of FIGS. below)." The users natural language prompt gives instructions to generate an automation that stores email attachments to OneDrive)
and generates as output the natural language representation of the one or more steps.(Gorrono [¶0057] "a user interface is populated with parameters for operations of the automation, the parameters derived from the natural language input. In aspects herein, a step(s) of the workflow is provided to the user interface" [¶0057] "provide the steps to a user device, e.g., a browser or the like, for display to the user. Steps may be displayed together in a single screen, or separately in multiple screens" the intermediate representations of the steps displayed to the user by Gorrono are explicitly natural language text).
Regarding claim 7, claim 7 is directed towards a system for performing the method of claim 1. Therefore, the rejection applied to claim 1 also applies to claim 7. Claim 7 also recites additional elements a memory storing computer program instructions; and at least one processor configured to execute the computer program instructions, the computer program instructions configured to cause the at least one processor to perform operations of: (Gorrono [¶0047] "Processor 204 and memory 206 may respectively be any type of processor circuit(s) and memory that is described herein, and/or as would be understood by a person of skill in the relevant art(s) having the benefit of this disclosure. Processor 204 and memory 206 may each respectively comprise one or more processors or memories, different types of processors or memories, remote processors or memories, and/or distributed processors or memories. Processor 204 may be multi-core processors configured to execute more than one processing thread concurrently, and cores of processor 204 may be grouped with portions of memory 206 as processing resources allocated for hosting services and/or for generating automations via natural language processing. Processor 204 may comprise circuitry that is configured to execute computer program instructions such as, but not limited to, aspects of workflow generator 208, which may be implemented as computer program instructions, as described herein.").
Similarly, regarding claims 8-12, claims 8-12 are directed towards a system for performing the methods of claims 2-6, respectively. Therefore, the rejections applied to claims 2-6 also apply to claims 8-12.
Regarding claim 13, claim 13 is directed towards a computer readable media for performing the method of claim 1. Therefore, the rejection applied to claim 1 also applies to claim 13. Claim 13 also recites additional elements A non-transitory computer-readable medium storing computer program instructions, the computer program instructions, when executed on at least one processor, cause the at least one processor to perform operations comprising: (Gorrono [¶0047] "Processor 204 and memory 206 may respectively be any type of processor circuit(s) and memory that is described herein, and/or as would be understood by a person of skill in the relevant art(s) having the benefit of this disclosure. Processor 204 and memory 206 may each respectively comprise one or more processors or memories, different types of processors or memories, remote processors or memories, and/or distributed processors or memories. Processor 204 may be multi-core processors configured to execute more than one processing thread concurrently, and cores of processor 204 may be grouped with portions of memory 206 as processing resources allocated for hosting services and/or for generating automations via natural language processing. Processor 204 may comprise circuitry that is configured to execute computer program instructions such as, but not limited to, aspects of workflow generator 208, which may be implemented as computer program instructions, as described herein.").
Similarly, regarding claims 14-18, claims 14-18 are directed towards a computer readable media for performing the methods of claims 2-6, respectively. Therefore, the rejection applied to claims 2-6 also applies to claims 14-18.
Conclusion
THIS ACTION IS MADE FINAL. 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 extension fee 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 SIDNEY VINCENT BOSTWICK whose telephone number is (571)272-4720. The examiner can normally be reached M-F 7:30am-5:00pm 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, Miranda Huang can be reached on (571)270-7092. 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.
/SIDNEY VINCENT BOSTWICK/Examiner, Art Unit 2124
