DETAILED ACTION
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 .
Response to Amendment
The reply filed on 4/9/2026 has been entered.
Claims 1, 8, and 15 have been amended, claims 5, 12, and 19 have been canceled, and no claims have been added.
Claims 1-4, 6-11, 13-18, and 20 are pending with claims 1, 8, and 15 as independent claims.
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, 3, 4, 6, 8, 10, 11, 13, 15, 17, 18, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Morales (US 12,282,733, filed 9/20/2023) in view of Fordyce et al. (US 2010/0280963, hereinafter as Fordyce).
Claim 1. A system for auto-filling a consignment recalling template, comprising:
a processor; a memory storing program instructions which, when executed by the processor, Morales discloses in [Description, Para. 64] “Electronic system 600 includes a bus 605, processing unit(s) 610, a system memory 615, a read-only memory 620, a permanent storage device 625, input devices 630, output devices 635, and a network 640.” (emphasis added), causes the processor to:
provide a User Interface (UI) to one or more entities, said UI displaying a template and a plurality of objects for selection by the entity, wherein [the entity distributes products to one or more end users]; Morales discloses in [Description, Para. 27] “the fully automated AI autofill grant application response generation process 100 provides the generated question (in text/word form) and the information retrieved from the USI vectors as prompt query data to feed as a prompt for the LLM (at 135). After submitting the question and the USI vector data as a prompt, the fully automated AI autofill grant application response generation process 100 determines (at 140) whether the prompt is accepted or rejected. When the question and USI vector data is rejected as a prompt, the fully automated AI autofill grant application response generation process 100 displays the rejection and informs the user to try again or answer manually (at 155). In some embodiments, the user can try again by selecting the icon of the tool in the user interface, or may select an API service to connect and submit again.” (emphasis added) examiner note: the grant application may be displayed template as shown in fig. 3.
Morales does not explicitly disclose
the entity distributes products to one or more end users. However, Fordyce, in an analogous art, discloses in [claims 1-2] “the sending of the recall message further comprises sending the recall message for delivery to a logical address selected from the group consisting of: a logical address of each said issuer of each said account used to conduct one of the transactions to purchase one of the recalled products; and a logical address of each said account holder of each said account used to conduct one of the transactions to purchase one of the recalled products.” (emphasis added) examiner note: the account holder may be the end user,
identify at least one product to be recalled from the one or more end users; further Fordyce discloses in [claims 1-2] “identify each said transaction where the purchased item was one of the recalled products”. (emphasis added).
generate at least one recalling prompt based on auto-filled template; and send the generated recalling prompt to the one or more end users. Also, Fordyce discloses in [0060] “Product Recall Service 630, via the network 612, can facilitate real time alerts that can be generated from POS transactional data and prior registrations of account holders with Product Recall Service 630. These `e-alerts` provide both consumer safety and limitations on products liability of manufacturers, and suppliers such as distributors and wholesalers, and retailers by providing real time warnings. Each such warning can include information about defective and dangerous products that have been purchased by a consumer, and the warning or e-alert can be electronically delivered to a logical address of the consumer or the issuer of an account of the consumer, such as via a cellular telephone or a mobile web enable computing device.” (emphasis added).
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teaching of Morales with the teaching of Fordyce because “Manufacturers who recall a product go through a laborious, expensive process in attempts to contact customers who are likely to have purchased its products in order to let them know that the product has been recalled, should be returned, and/or is not safe to use or consume… a recall notification service.” Fordyce [Background].
select at least one object from the plurality of objects, the object representing a field associated with the template; Morales discloses in [Detailed Description, Para. 21] “The semi-automated AI autofill grant application process and the associated autofill grant application response generation and user supplied information extraction processes… if the user hovers over or selects a form element text input field in the application form web page, the element will be highlighted by the extension in a way that distinctly visually identifies it as being related to the extension.” (emphasis added),
retrieve, based on the selection of the at least one object, metadata associated with the field corresponding to the at least one object; Morales discloses in [Detailed Description, Para. 9-11 and 31] “the terms “online application form”, “application form”, “application”, “form”, “grant application”, “grant form”, etc., are intended to apply to fillable forms for applications of any sort, not limited to only grant application forms… upon selection of the interactive context tool for the current field, the automated context-specific code artifacts collection process 200 automatically collects code artifacts corresponding to the current field (at 230). The code artifacts may be HTML code snippets extracted from a source HTML file for the online application form.” (emphasis added) examiner note: the code artifact may be metadata collected (or retrieved) associated with the current selected field (object) of the fillable online application as a template,
perform tokenization of textual data of the field, the metadata associated with the field, and text of the template; Morales discloses in [Detailed Description, Para. 32-36] “the automated context-specific code artifacts collection process 200 identifies related and/or relevant code (with respect to the current field) by traversing the entire code base in the source HTML file for the online application form (at 240)… in traversing the entire code base, the automated context-specific code artifacts collection process 200 identifies any code that is related or contextually relevant to the question being asked or information being requested for the current field (at 240)… After completing the traversal of the code base (with identification of related/relevant code, if any) with respect to the current field information (at 240), the automated context-specific code artifacts collection process 200 again traverses the code of the full online application form (seeking beyond related/relevant code for the current field only) and identifies any form-wide related or contextually relevant code (at 250). When related/relevant code is identified with respect to the current field and/or when form-wide related/relevant code is identified in the code base of the entire online application form (individually and collectively referred to as the “identified related/relevant code”), the automated context-specific code artifacts collection process 200 adds the identified related/relevant code to the collected code artifacts (at 260), which were previously collected (at 230) with respect to the current field only.” (emphasis added) examiner note: the metadata may also include the “code artifact” corresponding to the current field (text of the field), the “context-specific code artifacts” may be the metadata associated with the current field, and “code of the full online application form” may be the text of the template. So, process 200 may represent tokenization process that identifies the code artifact of the current filed, any code artifacts relevant to the current field, and the code of the full online application form,
determine using a machine learning model a semantic similarity or vector similarity between the field and the metadata associated with the field based on the tokenized data; Morales discloses in [Detailed Description, Para. 24-27 and 38] “the fully automated AI autofill grant application response generation process 100 converts the text/words of the generated question into numerical form-again, by using the embedding model, which captures the semantic meaning of the text/words of the question by assigning similar vectors to semantically related or contextually similar text… After converting the question to a vector representation, the fully automated AI autofill grant application response generation process 100 uses the vector representation of the question to (i) identify semantically relevant information from the user supplied information (USI) and then (ii) select/retrieve USI vectors that are similar vectors/records of the USI information (at 130)… The backend server 335 also utilizes the vector transformation and comparison module for at least two operations, namely (i) to transform the question from textual word form to a vector in numerical form for machine processing (at 380) and (ii) to identify semantically relevant information from USI vectors (with numerically-represented USI records) of the program profile by comparing the USI vectors to the question vector (at 385). Finally, the composite question output unit of the backend server 335 provides (at 390) the formulated question and the USI information (of the most similar USI vectors/records) to the prompt input interface 365 of the AI system 350, which itself passes on to the LLM 355 as the prompt input.” (emphasis added) examiner note: assigning similar vector semantically relevant or contextually similar text to the generated question may indicate formulating USI vector similar to vector formulated to the generated question associated with the current field. In other words, the autofill process is determining an answer (to entered to the current field) by identifying information from the USI (as the answer) to match the current field,
retrieve, based on the selection on the at least one object, one or more data corresponding to the at least one object from a database; Morales discloses in [Detailed Description, Para. 15] “fully automated AI autofill grant application response generation process automatically reviews question fields in the grant application by identifying, extracting, and collecting relevant code artifacts associated with each field, interprets the question being asked or information being requested by each field of the grant application (referred to as the “question”), converts the question into a numerical vector or data, searches, in the data storage and databases or other archival data (hereinafter referred to individually and collectively as the “data sources”), for relevant personalized user supplied information (USI) which relates to the question and is personalized for the user or the entity seeking the grant, retrieves USI vectors corresponding to the relevant information found during the search among the data sources, generates a response to the question, by an AI system with LLM and NPL, and automatically enters the generated response into an input area of the field for the question in the grant application.” (emphasis added) examiner note: response as data corresponding to an object from database may be retrieved in order fill the corresponding field,
wherein retrieving the one or more data is based on a similarity score indicating a degree of the semantic similarity or vector similarity; Morales discloses in [Detailed Description, Para. 26, 38, 43] “the fully automated AI autofill grant application response generation process 100 uses the vector representation of the question to (i) identify semantically relevant information from the user supplied information (USI) and then (ii) select/retrieve USI vectors that are similar vectors/records of the USI information (at 130)… the composite question output unit of the backend server 335 provides (at 390) the formulated question and the USI information (of the most similar USI vectors/records) to the prompt input interface 365 of the AI system 350, which itself passes on to the LLM 355 as the prompt input… the server uses the vector representation of the LLM's generated question to identify pieces of semantically relevant USI records in the selected program profile (at 445), followed by the server assessing the similarity of this vector to the vectors of all stored USI information with selection of only the top few records.” (emphasis added) examiner note: the most similar USI vector to the vectors of all stored USI information would indicate similarity score indicating a degree of semantic vector similarity,
auto-fill the selected fields of the template based on the one or more data retrieved from the database; Morales discloses in [Detailed Description, Para. 15] “for relevant personalized user supplied information (USI) which relates to the question and is personalized for the user or the entity seeking the grant, retrieves USI vectors corresponding to the relevant information found during the search among the data sources, generates a response to the question, by an AI system with LLM and NPL, and automatically enters the generated response into an input area of the field for the question in the grant application.” (emphasis added) examiner note: automatically entering the generated response may be auto-filling selected field,
Claims 3, 10, and 17. The rejection of the system of claim 1 is incorporated, wherein the processor is further configured to: provide one or more predetermined templates for selection by the entity. Morales discloses in [Detailed Description, Para. 9] “the terms “online application form”, “application form”, “application”, “form”, “grant application”, “grant form”, etc., are intended to apply to fillable forms for applications of any sort, not limited to only grant application forms.” (emphasis added) examiner note: the fillable forms may be predetermined
Claims 4, 11, and 18. The rejection of the system of claim 1 is incorporated, wherein in the auto-filling of the template based on selection of the object, the processor is further configured to: identify the fields representing the selected object; retrieve one or more data from the database corresponding to the identified field; and auto-fill the template based on retrieved data. Morales discloses in [Detailed Description, Para. 15] “fully automated AI autofill grant application response generation process automatically reviews question fields in the grant application by identifying, extracting, and collecting relevant code artifacts associated with each field, interprets the question being asked or information being requested by each field of the grant application (referred to as the “question”), converts the question into a numerical vector or data, searches, in the data storage and databases or other archival data (hereinafter referred to individually and collectively as the “data sources”), for relevant personalized user supplied information (USI) which relates to the question and is personalized for the user or the entity seeking the grant, retrieves USI vectors corresponding to the relevant information found during the search among the data sources, generates a response to the question, by an AI system with LLM and NPL, and automatically enters the generated response into an input area of the field for the question in the grant application.” (emphasis added) examiner note: interpreting the question being asked about the target field would identify the field and a response or answer may be value relevant to the target field to automatically filled out.
Claims 6, 13, and 20. The rejection of the system of claim 1 is incorporated, wherein the processor is further configured to: Morales does not explicitly disclose generate a plurality of recalling prompts based on the number of end users who are connected to the one or more entities recalling the products. However, Fordyce, in an analogous art, discloses in [0017-0018] “Implementations of a product recall service provide cost effective notifications to consumers that a product they have purchased has been recalled by the manufacturer. In one implementation, manufacturers or suppliers of products manufactured by others, merchants and account holders would be registered as participants in a Product Recall Service (PRS). Each participating merchant would send, for delivery to the PRS, transaction data sufficient to identify each account holder making a purchase from the merchant and their purchased items. Each such purchased item would be part of a transaction conducted on an account issued to the account holder by an issuer, where the transaction was conducted by the merchant with the account holder… Upon notice received by the PRS from a participating supplier, where the notice identifies the supplier's recalled product, the PRS would match the recalled product against transaction data accumulated from participating merchant's transactions in order to locate those participating account holders who had purchased the recalled product. For each such match, contact information about the matching participating account holders would be used to send a notice.” (emphasis added) examiner note: product supplier may be an entity need to be sent a notification about the product recall and consumers may be another entity required to be notified about the product recall as well.
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teaching of Morales with the teaching of Fordyce because “Manufacturers who recall a product go through a laborious, expensive process in attempts to contact customers who are likely to have purchased its products in order to let them know that the product has been recalled, should be returned, and/or is not safe to use or consume… a recall notification service.” Fordyce [Background].
Claim 8. The claim is directed towards a method for implementing the steps of claim 1, therefore is similarly rejected as claim 1.
Claim 15. A non-transitory computer-readable storage medium storing program instructions for auto-filling a consignment recalling template for implementing the steps of claim 1, therefore is similarly rejected as claim 1.
Claims 2, 7, 9, 14, and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Morales and Fordyce as applied to claim 1 above, and further in view of Matic et al. (US 2025/0111136, filed 9/28/2023, hereinafter as Matic).
Claims 2, 9, and 16. The rejection of the system of claim 1 is incorporated, wherein in selecting the at least one object from the plurality of object, the processor is configured to: Morales does not explicitly disclose provide drag and drop function for the selected object at a predetermined location of the User Interface. However, Matic, in an analogous art, discloses in [0003] “The intake interface builder graphical user interface may include a field region configured to display a plurality of field elements and a request editing region configured to receive field elements from the field region in response to a drag-and-drop user input.” (emphasis added) examiner note: the object may be field element such that the user may drag and drop to particular location on a form in order to tailor the form to particular purpose.
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teaching of Morales with the teaching of Matic because “techniques described herein can be used to quickly tailor an intake interface using an administrator tool that can be used to more easily generate new or modified intake flows for an electronic help desk.” Matic [Background].
Claims 7, 14. The rejection of the system of claim 1 is incorporated, wherein the processor is further configured to: Morales does not explicitly disclose enable customization of the User Interface by the one or more entities based on specific end users or specific recalled products. However, Matic, in an analogous art, discloses in [0003] “The intake interface builder graphical user interface may include a field region configured to display a plurality of field elements and a request editing region configured to receive field elements from the field region in response to a drag-and-drop user input.” (emphasis added) examiner note: the object may be field element such that the user may drag and drop to particular location on a form in order to tailor the form to particular purpose.
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teaching of Morales with the teaching of Matic because “techniques described herein can be used to quickly tailor an intake interface using an administrator tool that can be used to more easily generate new or modified intake flows for an electronic help desk.” Matic [Background].
Response to Arguments
Applicant's arguments filed 4/9/2026 have been fully considered but they are not persuasive.
Argument: Applicant argues “Morales and Fordyce either alone or in combination fails to describe, for example, the feature(s) of "select at least one object from the plurality of objects, the object representing a field associated with the template; retrieve, based on the selection of the at least one object, metadata associated with the field corresponding to the at least one object; perform tokenization of textual data of the field, the metadata associated with the field, and text of the template; determine, using a machine learning model, a semantic similarity or vector similarity between the field and the metadata associated with the field based on the tokenized data; retrieve, based on the selection on the at least one object, one or more data corresponding to the at least one object from a database, wherein retrieving the one or more data is based on a similarity score indicating a degree of the semantic similarity or vector similarity; autofill the selected fields of the template based on the one or more data retrieved from the database;" (emphasis added).
Response: the argument to the independent claims appears to be based on amendment including new language. The amendment has been rejected based on information cited in the prior art in record as detailed above.
Argument: Applicant argues “Morales uses similarity to generate answers via an LLM, not to select and map existing database values to predefined template fields based on similarity scores… Morales operates in the context of question-answer generation, where outputs are synthesized text, whereas the amended subject matter of claim 1 performs context-aware mapping of structured enterprise data to template fields, ensuring accuracy and consistency required for regulatory recall workflows.”
Response: Morales teaches in [Detailed Description, Para. 7 and 17-18] “the fully automated AI autofill grant application response generation process automatically reviews question fields in the grant application by identifying, extracting, and collecting relevant code artifacts associated with each field, interprets the question being asked or information being requested by each field of the grant application (referred to as the “question”), converts the question into a numerical vector or data, searches, in the data storage and databases or other archival data (hereinafter referred to individually and collectively as the “data sources”), for relevant personalized user supplied information (USI) which relates to the question and is personalized for the user or the entity seeking the grant, retrieves USI vectors corresponding to the relevant information found during the search among the data sources, generates a response to the question, by an AI system with LLM and NPL, and automatically enters the generated response into an input area of the field for the question in the grant application… the associated autofill grant application response generation and user supplied information extraction processes described in this specification solve such problems by assisting a user in filling out application forms via artificial intelligence (AI) processing in combination with user-provide pre-set information and configuration of one or more data sources where information can be reviewed and retrieved by automated AI processes or partially through AI, such as by assistance of an API used to interface with an LLM, and manually generated pre-set answers to application questions that can be pulled from a database or other available data source… a grant application information extraction process for retrieving data of question and answer pairs as USI information from prior grant applications, converting the USI information to USI vector data, and storing the USI vector data in a USI information and vector database that is accessible to the LLM and backend server.” And in [para. 38] “the composite question output unit of the backend server 335 provides (at 390) the formulated question and the USI information (of the most similar USI vectors/records) to the prompt input interface 365 of the AI system 350, which itself passes on to the LLM 355 as the prompt input. The answer output interface 370 utilizes the API to provide the generated response as input into the current field (the project description field 310).” And in [para. 54] “the grant application information extraction process 500 proceeds to a step at which the API uses an external API service to extract a structured text representation of the uploaded PDF document (at 530).” (emphasis added).
the pre-set answers represent existing database values that the autofill form process may select (map) the most relevant (indicating score) to each form field in the online form application. The user supplied information (USI) may be transformed USI vector data (structured data) to be mapped to structured data of PDF document.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. See PTO-892.
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 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 AHAMED I NAZAR whose telephone number is (571)270-3174. The examiner can normally be reached 10 am to 7 pm Mon-Fri.
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, Stephen Hong can be reached at 571-272-4124. 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.
/AHAMED I NAZAR/Examiner, Art Unit 2178 6/7/2026
/STEPHEN S HONG/Supervisory Patent Examiner, Art Unit 2178
Prosecution Insights