DETAILED ACTION
Introduction
This office action is in response to Applicant’s amendment filed on May 8, 2026.
Claims 1, 3, 8, 9 and 11 have been amended. Claims 2, 4, 5, 10, 12 and 13 have been cancelled. Claims 1, 3, 6-9, 11 and 14-15 are pending in the application. As such, claims 1, 3, 6-9, 11 and 14-15 have been examined.
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 .
Drawings
The drawings were received on July 25, 2024. The drawings were amended on August 16, 2024. These drawings have been accepted and considered by the Examiner.
Response to Amendments and Arguments
In view of the amendments to the claims, the amendments to claims 1, 3, 8, 9 and 11, have been acknowledged and entered.
In view of the amendments to the claims, the objections to the claims, have been withdrawn.
In view of the amendments to the claims, the rejections to the claims under 35 U.S.C. 112(b) have been withdrawn.
In view of the amendments to the claims, the rejections to the claims under 35 U.S.C. 101 have been withdrawn.
In view of the amendments to the claims, the rejections to the claims under 35 U.S.C. 103 have been withdrawn.
In light of the amendments to the claims, new grounds for rejection for claims 1, 3, 6-9, 11 and 14-15, under 35 U.S.C. 103 are provided in the response below. New grounds for rejection is based at least upon the following new elements:
receiving a task prompt which is a text expressing a building information modeling (BIM)design authoring task to be performed with a natural language, from a user;
acquiring structured data from aa
acquiring a design result from BIM design software by inputting the acquired structured data to the BIM design software,
wherein:
a purpose of the BIM design authoring task includes generation of a BIM object or modification of a second BIM object,
in the acquiring of structured data, a purpose, a target BIM object, and a necessary property of the BIM design authoring task are identified by the generative natural language model and the structure data is acquired thereby, and
the generative natural language model is finely tuned so as to output the structured data which is understandable by the BIM design software from the natural language input.
Applicant’s arguments, received on May 8, 2026, regarding the prior art rejections under 35 U.S.C 103 have been fully considered.
Applicant’s arguments with respect to claims 1, 3, 6-9, 11 and 14-15 have been considered, are directed to the newly amended matter in the claims, are not considered to be persuasive, and are addressed accordingly in the updated rejection rationale below.
Claim Objections
Claims 3 and 11 are objected to because of the following informalities:
Claims 3 and 11 depend from cancelled claims 2 and 10. Examiner believes this to be a clerical error and they are intended to depend from claims 1 and 9.
Appropriate correction is required.
Claim Rejections - 35 USC § 103
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 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, 3, 6-9, 11 and 14-15 are rejected under 35 U.S.C. 103 as being unpatentable over Vierra (US Patent Pub. No. 20240370595 A1, as supported by 63/499,884 filed 5/3/2023), in view of Watson et al. (US Patent Pub. No. 20240319970 A1), hereinafter Watson, in view of Moghaddam et al. (US Patent Pub. No. 20250095008 A1) hereinafter Moghaddam, in view of Kumar et al. (US Patent Pub. No. 20230281358 A1) hereinafter Kumar.
Regarding claims 1 and 9, Vierra teaches a design automation method and apparatus (Vierra in [0002] teaches using machine learning algorithms for generating interior design plans),
comprising:
[claim 9 only] an input/output interface (Vierra in [0146] teaches using input/output interfaces)
receiving a task [prompt] which is a text expressing a [building information modeling (BIM)] design authoring task to be performed [with a natural language] (Vierra in [0110, Fig. 3] teaches a task includes a specific activity or action item that needs to be completed as part of the interior design project)
and
[claim 9 only] a processor (Vierra in [0146] teaches using a computer which includes a processor)
acquiring a design result from [BIM] design software by inputting [the acquired structured data] to the [BIM] design software (Vierra in [0118] teaches the machine learning model generates an interior design plan based on various inputs, and the resulting 3D model provides a detailed, virtual visualization of the physical space, including its layout, furniture arrangement, materials, and colors).
Vierra teaches the task and expressing a design authoring task.
Vierra does not teach, however, Watson teaches
receiving a [task] prompt which is a text [expressing a [building information modeling (BIM)] design authoring task] to be performed with a natural language, from a user (Watson in [0006] teaches receiving an inquiry (prompt) from a user, and using a language model to generate corresponding executable code, and in [0009] teaches the information may include a respective textual description);
acquiring structured data from
wherein:
a purpose of the [BIM design authoring task] includes generation of a [BIM] object or modification of a second [BIM] object (Watson in [0092, Fig. 9] teaches generating dynamic dashboards (an object)),
in the acquiring of structured data, a purpose, a target BIM object, and a necessary property of the [BIM design authoring task] are identified by the [generative natural language model and the structure data is acquired thereby] (Watson in [0092, Fig. 9] teaches generating dynamic dashboards (purpose), and freely moved around as an floating object to a new position on the screen each container (target object), such as top five items or type of chart (necessary property)).
Watson is considered to be analogous to the claimed invention because it is in the same field of using a language model to generate corresponding executable code. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Vierra further in view of Watson to allow for generation of executable code by a language model, based on an inquiry into the language model. Motivation to do so would allow for different output types, such as single answers, tables, graphs, or any other structured output medium that is generated through code (JSON, .csv, etc.) as an optional instruction to follow (Watson [0082]).
Vierra, as modified above, teaches the generative natural language model, outputting the structured data, the BIM design software, and the natural language input.
Vierra, as modified above, does not teach, however Moghaddam teaches
wherein the [generative natural language model] is finely tuned the [generative natural language model] is finely tuned so as to [output the structured data which is understandable by the BIM design software from the natural language input] (Moghaddam in [0005] teaches fine-tuning a pre-trained natural language processing model).
Moghaddam is considered to be analogous to the claimed invention because it is in the same field of using pre-trained natural language processing models. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Vierra, as modified above, further in view of Moghaddam to allow for fine-tuning a pre-trained natural language processing model. Motivation to do so would allow for an iterative cycle where design concepts and user feedback are automated and integrated in parallel with the concept development process, thereby providing the design team with more data to better assess and select valuable concepts (Moghaddam [0031]).
Vierra, as modified above, teaches the design authoring task, the design software, and the object.
Vierra, as modified above, does not teach, however Kumar teaches
a building information modeling (BIM) design authoring task (Kumar in [0161] teaches the computing device may analyze the BIM data by analyzing data from one or more of: floor plans of a construction project, a construction schedule for the construction project, a list of associated tasks in business process workflow for the construction project, a list of dependencies associated with the construction project, material requirements for the construction project, and labor needs for the construction project),
BIM design software (Kumar in [0131] teaches using an existing third-party design/BIM software),
a BIM object (Kumar in [0147] teaches using a generic BIM object or category).
Kumar is considered to be analogous to the claimed invention because it is in the same field of using design/BIM software. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Vierra, as modified above, further in view of Kumar to allow for using a generic BIM object. Motivation to do so would allow for enabling a product simulation and allows a user to visualize a physical product taking shape and provide the ability to introspect and visually modify the physical product that is being configured (Kumar [0103]).
Regarding claims 3 and 11, Vierra, as modified above, teaches the design automation method and apparatus according to claims 2 and 10 [claims 1 and 9].
Vierra, as modified above, teaches the BIM design authoring task, the BIM object, and the generative natural language model.
Vierra, as modified above, does not teach, however Watson further teaches
wherein when the purpose of the [BIM design authoring task] is to modify the [BIM] object (Watson in [0084] teaches a user may provide follow-up instructions to update the dynamically generated content, either to change the style, display, type of output, or to provide further guidance),
information about user may provide follow-up instructions to update the dynamically generated content, either to change the style, display, type of output, or to provide further guidance).
Watson is considered to be analogous to the claimed invention because it is in the same field of using a language model to generate corresponding executable code. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Vierra, as modified above, further in view of Watson to allow for updating dynamic dashboards. Motivation to do so would allow for different output types, such as single answers, tables, graphs, or any other structured output medium that is generated through code (JSON, .csv, etc.) as an optional instruction to follow (Watson [0082]).
Regarding claims 6 and 14, Vierra, as modified above, teaches the design automation method and apparatus according to claims 1 and 9.
Vierra, as modified above, does not teach, however Watson further teaches
wherein the structured data has a previously defined data schema structure (Watson in [0082] teaches the prompt can allow for different output types, such as single answers, tables, graphs, or any other structured output medium that is generated through code (JSON, .csv, etc.) as an optional instruction to follow).
Watson is considered to be analogous to the claimed invention because it is in the same field of using a language model to generate corresponding executable code. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Vierra, as modified above, further in view of Watson to allow for outputting structured output. Motivation to do so would allow for different output types, such as single answers, tables, graphs, or any other structured output medium that is generated through code (JSON, .csv, etc.) as an optional instruction to follow (Watson [0082]).
Regarding claims 7 and 15, Vierra, as modified above, teaches the design automation method and apparatus according to claims 6 and 14.
Vierra, as modified above, does not teach, however Watson further teaches
wherein the structured data is a database table, Excel sheets, JSON, or XML data (Watson in [0082] teaches the prompt can allow for different output types, such as single answers, tables, graphs, or any other structured output medium that is generated through code (JSON, .csv, etc.) as an optional instruction to follow).
Watson is considered to be analogous to the claimed invention because it is in the same field of using a language model to generate corresponding executable code. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Vierra, as modified above, further in view of Watson to allow for outputting tables or JSON code. Motivation to do so would allow for different output types, such as single answers, tables, graphs, or any other structured output medium that is generated through code (JSON, .csv, etc.) as an optional instruction to follow (Watson [0082]).
Regarding claim 8, Vierra, as modified above, teaches the design automation method of claim 1.
Vierra, as modified above, does not teach, however Watson further teaches
computer program which is stored in a non-transitory computer readable storage medium to allow a computer to execute (Watson in [0037] teaches using one or more non-transitory computer readable media having instructions stored thereon, and instructions include executable code that, when executed by one or more processors, cause the processors to carry out steps necessary).
Watson is considered to be analogous to the claimed invention because it is in the same field of using a language model to generate corresponding executable code. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Vierra, as modified above, further in view of Watson to allow for using one or more non-transitory computer readable media. Motivation to do so would allow for different output types, such as single answers, tables, graphs, or any other structured output medium that is generated through code (JSON, .csv, etc.) as an optional instruction to follow (Watson [0082]).
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 PAUL J. MUELLER whose telephone number is (571)272-1875. The examiner can normally be reached M-F 9:00am-5:00pm (Eastern).
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, Daniel C. Washburn can be reached at 571-272-5551. 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.
PAUL MUELLER
Examiner
Art Unit 2657
/PAUL J. MUELLER/Examiner, Art Unit 2657
/DANIEL C WASHBURN/Supervisory Patent Examiner, Art Unit 2657
Prosecution Insights