DETAILED ACTION
Status of Claims
The following is a final office action in response to the amendment filed February 12, 2026. Claims 1-20 are currently pending and have been examined.
Notice of Pre-AIA or AIA Status
The present application is being examined under the pre-AIA first to invent provisions.
Response to Arguments
Applicant's prior art arguments have been fully considered but they are not persuasive.
Applicant contends that the combination of Ortega and Zhang does not disclose selecting, based on application of an attribute selection model to the group of attributes, a subset of attributes from the group, by: inputting a prompt to a large language model, the prompt including the item category, an identifier of each attribute of the group, a description of each attribute of the group, and a request to select a specific number of attributes from the group of attributes, and selecting the attributes output by the large language model as the subset of attributes from the group
Ortega, though does indeed teach:
selecting, based on application of an attribute selection model to the group of attributes, a subset of attributes from the group, by: (Ortega: column 3 lines 63-68 - For instance, some or all of the matching products in the "software" category may have an "operating system" attribute that indicates the type of operating systems these products run on, while products falling outside the "software" category likely will not include this attribute);
selecting the attributes output by the model as the subset of attributes from the group (Ortega: column 3 lines 63-68 - The three particular attributes (category, brand, and memory type) included in the search refinement section 14 in this example are a small subset of the collection of item attributes that could potentially be used to refine the search. This is because the search results span many different product categories (electronics, music downloads, software, etc.), and because the attributes tend to vary widely across these product categories.);
Ortega does not expressly disclose inputting a prompt to a large language model, the prompt including the item category, an identifier of each attribute of the group, a description of each attribute of the group, and a request to select a specific number of attributes from the group of attributes. Zhang discloses inputting a prompt to a large language model, the prompt including the item category, an identifier of each attribute of the group, a description of each attribute of the group, and a request to select a specific number of attributes from the group of attributes (Zhang: Figure 2 - prompt a large language model).
Ortega and Zhang do not expressly disclose the prompt including the item category, an identifier of each attribute of the group, a description of each attribute of the group, and a request to select a specific number of attributes from the group of attributes. However these differences are only found in the nonfunctional descriptive material and are not functionally involved in the steps recited. The steps would be performed the same regardless of the type of prompt data. This descriptive material will not distinguish the claimed invention from the prior art in terms of patentability, see In re Gulack, 70 F.2d 1381, 1385, 217 USPQ 401 (Fed. Cir. 1983); In re Lowry, 32 F.3d 1579, 32 USPQ2d 1031 (Fed. Cir. 1994).
The combination of Ortega and Zhang thereby teaches the claimed limitations.
Applicant contends that the prior art references do not contain any motivation that they be combined. In response to applicant's argument that there is no motivation to combine the references, the examiner recognizes that obviousness can only be established by combining or modifying the teachings of the prior art to produce the claimed invention where there is some teaching, suggestion, or motivation to do so found either in the references themselves or in the knowledge generally available to one of ordinary skill in the art. See In re Fine, 837 F.2d 1071, 5 USPQ2d 1596 (Fed. Cir. 1988) and In re Jones, 958 F.2d 347, 21 USPQ2d 1941 (Fed. Cir. 1992). Additionally, the Examiner notes that the teaching-suggestion-motivation test is no longer the sole test of obviousness and further notes that, when references unite old elements with no change in their respective function and yield predictable results, the claimed subject matter is obvious under KSR [See KSR, 127 S.Ct. at 1741, 82 USPQ2d at 1396].
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s invention to have modified the method and apparatus of Ortega to have included inputting a prompt to a large language model, the prompt including the item category, an identifier of each attribute of the group, a description of each attribute of the group, and a request to select a specific number of attributes from the group of attributes, and, as taught by Zhang because it would provide more accurate results (Zhang: column 1).
Subject Matter Eligibility
Applicant respectfully submits that the pending claim is directed to patent-eligible subject matter under 35 U.S.C. §101. Although the claim recites receiving item data and presenting information to a user, the claim integrates any such abstract idea into a practical application at least because the claimed method uses a structured prompt to a large language model to automatically select a subset of item attributes corresponding to an identified item category, and generates a user interface based on that model-driven selection. The ordered combination of limitations improves computer functionality by automating attribute selection that previously relied on manual curation or rule-based systems, and by dynamically configuring interface content based on the model output. This constitutes a specific improvement to computer interfaces rather than a mere presentation of information. Accordingly, the claim recites significantly more than an abstract idea and is patent-eligible under Step 2A Prong Two, and additionally satisfies Step 2B because it recites non-conventional use of a large language model to determine interface content.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103(a) which forms the basis for all obviousness rejections set forth in this Office action:
(a) A patent may not be obtained though the invention is not identically disclosed or described as set forth in section 102 of this title, if the differences between the subject matter sought to be patented and the prior art are such that the subject matter as a whole would have been obvious at the time the invention was made to a person having ordinary skill in the art to which said subject matter pertains. Patentability shall not be negatived by the manner in which the invention was made.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103(a) are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1, 3-5, 10, 12-14, 18, and 20 are rejected under 35 U.S.C. 103(a) as being unpatentable over Ortega et al (US 8,260,771 B2) in view of Zhang et al (US 12,019,663 B1).
Regarding claims 1, 10, and 18, Ortega discloses method, performed at a computer system comprising a processor and a computer-readable storage medium, comprising:
receiving a request from a user device to display an interface, the interface including an item along with a plurality of additional items; (Ortega: column 1 lines 60-67 - These item attributes and any associated attribute values are then presented to the user (typically on a search results page) in a selectable form such that the user can interactively narrow the search.);
identifying an item category for the item (Ortega: column 3 lines 43-50 - In this particular example, the search refinement section 14 includes three sets of search refinement hyperlinks 16, 18, and 20, with each set corresponding to a particular item attribute. The "category" links 16 correspond to respective values of a "category" attribute, and are selectable by the user to narrow the search to corresponding product categories.);
selecting a group of attributes corresponding to the identified item category (Ortega: column 4 lines 4-8 - For instance, some or all of the matching products in the "software" category may have an "operating system" attribute that indicates the type of operating systems these products run on, while products falling outside the "software" category likely will not include this attribute);
selecting, based on application of an attribute selection model to the group of attributes, a subset of attributes from the group, by: (Ortega: column 3 lines 63-68 - For instance, some or all of the matching products in the "software" category may have an "operating system" attribute that indicates the type of operating systems these products run on, while products falling outside the "software" category likely will not include this attribute);
selecting the attributes output by the model as the subset of attributes from the group (Ortega: column 3 lines 63-68 - The three particular attributes (category, brand, and memory type) included in the search refinement section 14 in this example are a small subset of the collection of item attributes that could potentially be used to refine the search. This is because the search results span many different product categories (electronics, music downloads, software, etc.), and because the attributes tend to vary widely across these product categories.);
generating the interface for display to the user, the interface displaying the item and, in conjunction with the item, the selected subset of attributes for the item category of the item; and sending the generated interface to the user device, wherein sending the generated interface to the user device causes the user device to display the generated interface (Ortega: Figure 1A and 1B).
Ortega does not expressly disclose inputting a prompt to a large language model, the prompt including the item category, an identifier of each attribute of the group, a description of each attribute of the group, and a request to select a specific number of attributes from the group of attributes. Zhang discloses inputting a prompt to a large language model, the prompt including the item category, an identifier of each attribute of the group, a description of each attribute of the group, and a request to select a specific number of attributes from the group of attributes (Zhang: Figure 2 - prompt a large language model).
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s invention to have modified the method and apparatus of Ortega to have included inputting a prompt to a large language model, the prompt including the item category, an identifier of each attribute of the group, a description of each attribute of the group, and a request to select a specific number of attributes from the group of attributes, and, as taught by Zhang because it would provide more accurate results (Zhang: column 1).
Ortega and Zhang do not expressly disclose the prompt including the item category, an identifier of each attribute of the group, a description of each attribute of the group, and a request to select a specific number of attributes from the group of attributes. However these differences are only found in the nonfunctional descriptive material and are not functionally involved in the steps recited. The steps would be performed the same regardless of the type of prompt data. This descriptive material will not distinguish the claimed invention from the prior art in terms of patentability, see In re Gulack, 70 F.2d 1381, 1385, 217 USPQ 401 (Fed. Cir. 1983); In re Lowry, 32 F.3d 1579, 32 USPQ2d 1031 (Fed. Cir. 1994).
Regarding claim 3 and 12, Ortega and Zhang teach or suggest all the limitations of claims 1 and 10 as noted above. Zhang further discloses wherein inputting the description of an attribute of the group comprises inputting a text description of the attribute of the group and a data type of the attribute of the group (Zhang: column 5 lines 34-41 - At 206, a large language model is prompted based on the query. The prompt includes request for the LLM to generate a plurality of subtopics related to the query and a corresponding plurality of keywords for each of the plurality of subtopics. A number of subtopics related to the query may be specified by a user via the prompt. A number of keywords for each of the subtopics may be specified by the user via the prompt)
Ortega and Zhang do not expressly disclose t inputting a text description of the attribute of the group and a data type of the attribute of the group. However these differences are only found in the nonfunctional descriptive material and are not functionally involved in the steps recited. The steps would be performed the same regardless of the type of data. This descriptive material will not distinguish the claimed invention from the prior art in terms of patentability, see In re Gulack, 70 F.2d 1381, 1385, 217 USPQ 401 (Fed. Cir. 1983); In re Lowry, 32 F.3d 1579, 32 USPQ2d 1031 (Fed. Cir. 1994).
Regarding claim 4 and 13, Ortega and Zhang teach or suggest all the limitations of claims 3 and 12 as noted above.
Ortega and Zhang do not expressly disclose wherein inputting the prompt further comprises inputting one or more characteristics of the user. However these differences are only found in the nonfunctional descriptive material and are not functionally involved in the steps recited. The steps would be performed the same regardless of the type of data. This descriptive material will not distinguish the claimed invention from the prior art in terms of patentability, see In re Gulack, 70 F.2d 1381, 1385, 217 USPQ 401 (Fed. Cir. 1983); In re Lowry, 32 F.3d 1579, 32 USPQ2d 1031 (Fed. Cir. 1994).
Regarding claim 5 and 14, Ortega and Zhang teach or suggest all the limitations of claims 4 and 13 as noted above.
Ortega and Zhang do not expressly disclose wherein inputting the one or more characteristics of the user comprises inputting one or more values of attributes of items the user included in orders fulfilled by the computer system with at least a threshold frequency. However these differences are only found in the nonfunctional descriptive material and are not functionally involved in the steps recited. The steps would be performed the same regardless of the type of data. This descriptive material will not distinguish the claimed invention from the prior art in terms of patentability, see In re Gulack, 70 F.2d 1381, 1385, 217 USPQ 401 (Fed. Cir. 1983); In re Lowry, 32 F.3d 1579, 32 USPQ2d 1031 (Fed. Cir. 1994).
Allowable Subject Matter
Claims 2, 6-9, 11, 15-17, and 19 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
In addition to the prior art cited above, the most pertinent prior art with regards to claims 2, 6-9, 11, 15-17, and 19 includes:
PTO-892 - Measuring User Engagement Attributes in Social Networking Application
Fang et al (US 2025/0245246 A1) teaches SYSTEMS AND METHODS FOR OPTIMAL LARGE LANGUAGE MODEL ENSEMBLE ATTRIBUTE EXTRACTION.
Mandayam et al (US 11,494,686 B1) teaches Artificial intelligence system for relevance analysis of data stream items using similarity groups and attributes.
Liu et al (US 10,861,077 B1) teaches Machine, process, and manufacture for machine learning based cross category item recommendations.
Sakaue nor any of the other cited references teach, suggest, or otherwise render obvious applying the engagement model to each training example of the training dataset to generate a predicted probability of the user performing the specific action with one or more items of the training item category having the value for the training attribute; scoring the engagement model using a loss function and the label of the training example; updating one or more parameters of the engagement model by backpropagation based on the scoring until one or more criteria are satisfied; and selecting the subset of attributes of the group based on the scores.
Additionally, the Examiner notes that when read as a whole, the claims would not have been obvious over the evidence obtained throughout prosecution. Moreover, even assuming arguendo that such features are present in the prior art, the combination of elements as recited in would not have been obvious over the evidence at hand because any combination of the evidence at hand would only result from a substantial reconstruction of Applicant’s claims using improper hindsight.
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 date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KATHLEEN G PALAVECINO whose telephone number is (571)270-1355. The examiner can normally be reached M-F 9-4.
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, Jeffrey Smith can be reached at (571) 272-6763. 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.
KATHLEEN GAGE PALAVECINO
Primary Examiner
Art Unit 3688
/KATHLEEN PALAVECINO/Primary Examiner, Art Unit 3688