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
This action is in response to the claimed amendment filed on 01/17/2026.
Claims 13, 18-19 are canceled. Claims 21-23 are newly added.
Claims 1-12, 14-17, 20-23 are pending.
Response to Arguments
This is in response to the argument remarks filed on 01/17/2026.
Applicant amends the claims with: "analyzing at least a portion of the transcript to
identify, from a plurality of existing projects managed by a computer program development
project management software, a computer program development project associated with the
discussion" , and submitted that:
Schroder fails entirely to anticipate, teach, suggest, or otherwise Schroder merely teaches the development of a single "project," for example via "scrum project planning" facilitated by "GPT-3 .5" (see the first paragraph of page 2 of Schroder), by iteratively adding "the next task we should do" based on "knowledge of where we are and where we want to go" (see the second paragraph of page 2 of Schroder). This is confirmed by Schroder completely lacking any reference to organizing the various "tasks," "requirements," "features," or other aspects of project development according to different "projects." Rather, Schroder teaches the generation, development, refinement, and replication of "tasks" and other aspects of a single project.
The remarks appear submitted that Schroder teaches the operations performed in connection with a single "project plan.", and submitted Schroder fails to teach the claimed “plurality of existing projects managed by a computer program development project management software,” and it also fails entirely to teach, based on analysis of "at least a portion of the transcript," the selection of a single "computer program development project associated with the discussion" that is represented by the "transcript."
Examiner respectfully disagrees. The teachings in Schroder as mapped read on the generic limitations of the Claims.
In view of Applicant’s submitting support in the specification for the amended limitations in the claims, the support specification describes a transcript as discussions of developments teams, and recorded. The discussions might be about features, defects, new things that could be associated with creating new tasks in a software project. Using feature discussions in transcript as prompts. There is not as in the amended limitation in the claims “from a plurality of existing projects”.
For example, in the specification, in text para. 0044, “For example, the provided portions of the project transcript can include a discussion by different team members describing a new feature or a found defect that should be added as a new task to the project.” . "Different team members" cannot be equated to “existing projects” for the submission: “Schroder teaches the generation, development, refinement, and replication of "tasks" and other aspects of a single project.”
It should be noted that a single project could be big or small. A single project could include many teams, and in each team, it might require certain shared tasks, and tasks exchanged in human discussions are formal. Moreover, transcripts are only the records of human discussions; there is nothing novelty about of being included or excluded in the same project or different project. The example shown in the Schroder reference in sec. 4.2 is typical of a transcript, and this transcript is used this transcript for generating a “desired state” in a task (Figures in p. 6).
It should be noted that the Schroder reference also includes the discussion of different teams: See in p. 14, sec. 4.7, last para.
“The whole process of task completion itself can and will be automated, but we consider it more useful to invite domain experts and actual teams to work on the tasks because the results of domain specific expertise is almost certainly going to be much better than either machine or a human working on their own.”. This para shows that the discussions for task completion usually are discussed with domain experts and actual teams to work on the tasks.
Claim Objections
Claims 1, 12, 20 are objected to because the claims added with the limitations of “analyzing at least a portion of the transcript to identify, from a plurality of existing projects managed by a computer program development project management software…” that appears not to be consistent with the support specification discussed in paragraph 0044.
Claim Rejections - 35 USC § 102
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 1-3, 6-11, 12, 14, 17, 20-23 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by
Schroder et al., “Automating Project Planning Using Large Language Models”, 6-2023, arXiv, pages 1-25.
As per Claim 1: Schroder discloses, 1. (Currently Amended) A method, comprising:
Regarding,
receiving a transcript of at least a portion of a discussion associated with a computer program development;
See Sec. 1 Introduction, in p. 1, p. 2: discussing various projects, in p.2, ‘We use GPT-3.5-turbo model with Guidance language as a way to write and execute natural language programs on
GPT-3.5 to accomplish the tasks of scrum project planning.’ (emphasis added), and in sec, 4, Methodology p. 5. Methodology and within the phases in underscore above read on limitation, discussion associated with a computer program development.
Regarding,
analyzing at least a portion of the transcript to identify, from a plurality of existing projects managed by a computer program development project management software,
(See in p. 14, sec. 4.7, last para.
“The whole process of task completion itself can and will be automated, but we consider it more useful to invite domain experts and actual teams to work on the tasks because the results of domain specific expertise is almost certainly going to be much better than either machine or a human working on their own.” (emphasis added))
a computer program development project associated with (*) the discussion;
(Regarding (*), sec. 4.2, p. 6-7, the transcript reads on within the three dots in p. 7, Analyzing to identify… as ‘Requirement identification uses a Guidance language program that is designed to solve for the shortest path between the current situation and the desired situations’ , and program product project development in this manner as JSON ‘Your responses contain only valid JSON.’, SCRUM is as computer program development project management software, as seen in Tittle: an automating project planning.)
Regarding,
providing to a large language model, at least the portion of the transcript and contextual information of the identified computer program development project tracked using the computer program development project management software to identified computer program development discussed during the discussion;
Per above limitation, see sec. 4.1, pages. 5-6, the first Figure in p. 6, as a LLM, it is provided with transcript portions as the three dots, and contextual information of claim as ‘I will provide you with the following information:’ (in sec. 4.2). In this manner, the AutoSCRUM (in Tittle, and discussed in the reference) is as computer program development project management software to generating tasks and subtask (see in the first Figure ‘Tasks’) with “Short Cut”, (See in dot Shortcut Planning) as ‘specification of a task’ .
Regarding,
and based on the generated specification of the task, as part of the identified using the computer program development project management software.
Per above limitations, see the second Figure in p. 6 of sec. 4.1, the flow of Task, each is the result from Chat GPT and “New Current Situation”. It should be noted that Scum Project Planning is a project tracking tool.
As per Claim 2: Regarding,
2. (Currently Amended) The method of claim 1, wherein the task is associated with a new feature to be added or an identified defect of the identified computer program development project tracked using the computer program development project management software.
Per above limitation, see the first Figure, Features identified in Stories as “added”, and the second Figure with “new current situation”, and within all dots in sec. 4.1 ‘Identifying Automation Tasks, it mentions “Acceptance Criteria” , in p. 9, # 4 in Make sure that, ‘4) Prioritize creating new features based on story features which do not already exist in the existing features list’ read on added or an identified defected .
As per Claim 3: Regarding,
3. The method of claim 1, wherein the transcript includes one or more trigger words used to identify the task.
Per above limitation, see the first Figure, Acceptance words from Stories as “trigger words”, and
Identifying Automation Tasks, it mentions “Acceptance Criteria” , in p. 9, # 4 in Make sure that, ‘4) Prioritize creating new features based on story features which do not already exist in the existing features list’ read on trigger words to identify tasks in stories. With ChatGPT, it generates tasks and subtasks from the story.
As per Claim 6: Regarding,
6. (Currently Amended) The method of claim 1, wherein providing to the large language model, at least the portion of the transcript and the contextual information of the identified computer program development project tracked using the computer program development project management software to automatically generate the specification of the task of identified the computer program development discussed during the discussion includes generating a generative artificial intelligence prompt using at least the portion of the transcript and at least a portion of the contextual information of the identified computer program development project.
Per above limitation, in p. 6: “The autoscrum process itself looks like this. The green icons represent parts of the process that we can augment using language models.”. The first Figure in p. 6 is an AutoScrum process, it is computer program development project management software to automatically generate the specification of the task using LLM as from ChatGPT. Where in the Figures, users provide to the Chat GPT the transcript and the contextual information of the computer program development projects as “Current Situation” in the discussions as mentioned (given in Claim 1 above) for generating list of tasks/subtasks
As per Claim 7: Regarding,
7. The method of claim 6, wherein the generative artificial intelligence prompt further includes requirements associated with the specification of the task.
Per above limitation, See Requirement and new current situation prompted to ChatGPT.
As per Claim 8: Regarding,
8. The method of claim 7, wherein the requirements associated with the specification of the task include a title, a description, an acceptance criteria, and an assignment group.
Per Above limitation, see in the first Figure, User Stories, Acceptance Criteria.
As per Claim 9: Regarding,
9. The method of claim 1, wherein the generated specification of the task is associated with a resource prediction for the task.
Per above limitation,: interpreted resource as “Current Situation”, and shortcut as resource prediction for the task, and keeping using ChatGPT, in the second Figure as the generated specification of the task.
As per Claim 10: Regarding,
10. The method of claim 9, wherein the resource prediction is associated with an estimate of an amount of effort required to complete the task.
Per above limitation,: interpreted resource prediction as output from ChatGPT, further see entire Sec. 3, Scrum Overview, start in p. 3. Especially, in backlog, for example in p. 5, “From the product backlog, select the highest priority user stories up to the team's capacity
For each user story, break it down into tasks
Move these user stories to the sprint backlog
Estimate effort for each task (often using story points)” .
As per Claim 11: Regarding,
11. The method of claim 10, wherein the resource prediction is based at least in part on a number of developers and an associated skill level for each of the number of developers utilized to complete the task.
Per above limitation, Especially, skill level is only an abstract, can be interpreted as user experience, team’s capacity, etc., In p. 5, “From the product backlog, select the highest priority user stories up to the team's capacity For each user story, break it down into tasks Move these user stories to the sprint backlog Estimate effort for each task (often using story points)” .
In sec. 4.7: Task Completion: “The tasks that we have now generated correspond to the detailed instructions that must be executed in order to complete the user story. This is the point where we can greatly enhance the user experience further by taking the task that needs to be done and providing additional assistance in the form of domain specific knowledge and information that can be
used to complete the task.”
(emphasis added)
As per claim 23. (New) The method of claim 1, further comprising generating the transcript of at
least a portion of the discussion based on at least one of an audio recording of the discussion or a
video recording of the discussion.
(See “Stories” and the Figures in p.6, and the discussions in meeting “Hold Daily stand-up meeting” as in p. 5. Since the limitation such as “audio recording of the discussion” or “a
video recording of the discussion” is only a narrow limitation of a user story. Moreover, “audio recording” or “video recording” cannot patentable advance over a user story. The reference is with “user story” clearly cover any types of discussions for being recorded “transcript”.)
As per Claims 12, 14, 17, 22: Claims are directed to a system that recites the limitations corresponding to limitations in the method of claims 1-3, 6-10, 23. Claims 12, 14, 17, 22 are rejected with the rationales provided in the claims 1-3, 6-10, 23 above.
As per Claims 20, 21: Claim is directed to a product that recites the limitations corresponding to limitations in the method of claim 1, and claim 23. Claims 20, 23 are rejected with the rationales provided in the claims 1, 23 above.
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 4-5, 15-16 are rejected under 35 U.S.C. 103 as being unpatentable over
Schroder et al., “Automating Project Planning Using Large Language Models”, 6-2023, arXiv, pages 1-25.
As per Claim 4: Regarding,
4. (Currently Amended) The method of claim 3, wherein the one or more trigger words associated with a new feature of the identified computer program development project include one or more of the following:
“enhancement,” “suggestion,” “idea,” “improvement,” “request,” “innovation,” “fine-tuning,” or “optimization.”
Per above limitation, trigger words as the texts in stories, in regards to new change, new current situation, in stories provided to ChatGPT as new feature, but
Schroder does not explicitly use one or more words as follows:
“enhancement,” “suggestion,” “idea,” “improvement,” “request,” “innovation,” “fine-tuning,” or “optimization.”
However these differences of words are only found in the nonfunctional descriptive material and are not functionally involved in the steps recited. The selection of the files in the references would be performed the same regardless of the type of data. Thus, this descriptive material will not distinguish the claimed invention from the prior art in terms of patentability, see In re Gulack, 703 F.2d 1381, 1385, 217 USPQ 401, 404 (Fed. Cir. 1983); In re Lowry, 32 F.3d 1579, 32 USPQ2d 1031 (Fed. Cir. 1994).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing of the application to include one or more of these selected words in the textual stories to produce tasks using ChatGPT of Schroder as data or information because such data or information does not functionally relate to the steps in the method claimed and because the subjective interpretation of the data does not patentably distinguish the claimed invention.
As per Claim 5: Regarding,
5. (Currently Amended) The method of claim 3, wherein the one or more trigger words associated with an identified defect of the identified computer program development project include one or more of the following:
“defect,” “problem,” “malfunction,” “missing,” “issue,” “inconsistency,” “blemish,” “imperfection,” or “bug.”
Per above limitation, trigger words associated with an identified defect, as the texts in stories, provided to ChatGPT for generating tasks, but
Schroder does not explicitly use one or more words as follows:
“defect,” “problem,” “malfunction,” “missing,” “issue,” “inconsistency,” “blemish,” “imperfection,” or “bug.”
However these differences of words are only found in the nonfunctional descriptive material and are not functionally involved in the steps recited. The selection of the files in the references would be performed the same regardless of the type of data. Thus, this descriptive material will not distinguish the claimed invention from the prior art in terms of patentability, see In re Gulack, 703 F.2d 1381, 1385, 217 USPQ 401, 404 (Fed. Cir. 1983); In re Lowry, 32 F.3d 1579, 32 USPQ2d 1031 (Fed. Cir. 1994).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing of the application to include one or more of these selected words in the textual stories to produce tasks using ChatGPT of Schroder as data or information because such data or information does not functionally relate to the steps in the method claimed and because the subjective interpretation of the data does not patentably distinguish the claimed invention.
As per Claims 15-16: Claims are directed to a system that recites the limitations corresponding to limitations in the method of claims 4-5. Claims 15-16 are rejected with the rationales provided in the claims 4-5 above.
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 Ted T Vo whose telephone number is (571)272-3706. The examiner can normally be reached 8am-4:30pm ET.
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, Wei Y Zhen can be reached at (571) 272-3708. 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.
TTV
April 17, 2026
/Ted T. Vo/
Primary Examiner, Art Unit 2191
Prosecution Insights