Response to Amendment
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 .
This action is responsive to amendment filed on 6/5/26. Claims 1-20 are presented for examination.
This application has a provisional priority of 4/5/24. This application is further a CIP of 18/628,553 with an earlier filing dated 4/7/23. The CIP however does not teach or fairly suggest the subject matter of the pending application and the priority date is therefore NOT effective against the pending claims. For purposes of this application, the earlies effective date is 4/5/24.
Abstract analysis:
Claims 1 and 20 process a natural language input using a language model to generate strategy map nodes, process the strategy map nodes and a strategy map to determine a mapping of the strategy map nodes to the strategy map, process user input to generate an updated mapping of the strategy map nodes, and apply the updated mapping to the strategy map to generate an updated strategy map comprises practical application in the field of improved querying using a language model.
Claim 11 claims an application executing on a computer processor comprising the same steps as method claim 1 and is therefore also statutory and comprises practical application in the field of improved querying using a language model.
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.
Claim(s) 1-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Baldua USPN. 2025/0110957 in view of Venkataraman et al (USPN. 2023/0061899, herein “Venka”).
Regarding claims 1, 11 and 20, Baldua discloses a method, system comprising a processor and application, and non-transitory medium performing the method comprising (fig. 1A, par. 45, applications 102, query 104, and plan generatioin using large language model 116):
receiving natural language input (fig. 1, query 104-106 and par. 48, Baldua);
processing the natural language input using a language model to generate strategy map nodes (fig. 1, LLM 116 and query planning system 110, pars. 48-49, context with classification prompt used by the LLM to determine input classification 118 and intent. Note that the instant application teaches the strategy map nodes may be objects at par. 38);
processing the strategy map nodes and a strategy map to determine a mapping of the strategy map nodes to the strategy map (fig. 1, item 120, par. 54, “configures a plan generation prompt 122 based on the input classification 118 produced by the (LLM) 116”. Note that graphs and portions of graphs are present see par. 145) and to identify one or more nodes comprising one or more of an overdue node and a regular cadence node (fig. 6, pars. 143-146, entities 632 and graph 634, “activities relating to the entities connected by the edges”, mappings and relationships such as activities performed or to do, which is equated to identifying nodes comprising at least a regular cadence node, Baldua). To the degree that Baldua does not explicitly teach overdue node, Venka teaches identifying overdue project tasks (par. 66, “automatically monitor and update resource allocations and project plans to account for delays from overdue project tasks”, Venka). It would have been obvious to one of ordinary skill in the art before the effective filing date to integrate overdue activities in Baldua graphs as done in Venka system (fig. 6, items 632 and 634, Baldua). One would have been motivated to integrate overdue nodes/activities to “compute various types of relationship weights, affinity scores, similarity measurements, and/or statistics between, among, or relating to entities” by using graph based data structures (par. 143, Baldua).
Baldua integrated with Venka teach,
processing user input received responsive to the one or more nodes to map updates provided in the user input to performance indicators of one or more objects in the strategy map to generate an updated mapping of the strategy map nodes (figs. 6 and 7A, , pars. 145, knowledge graph 634 can be updated based on changes and updates to the stored data, the updated updates reflect updated strategy maps of nodes, Baldua), and
applying the updated mapping to the strategy map to generate an updated strategy map (pars. 145-146, updated graphs with mappings between different pieces of data, entities and relationships, Baldua) and,
transmitting a confirmation message identifying changes made to the strategy map based on the user input (par. 148, feedback and message exchange between apps and user input, Baldua).
2. Baldua integrated with Venka teach, processing the updated strategy map to identify an off track node using the language model and transmitting an off track message based on the off track node (figs. 6 and 7, pars. 174 and 192, performance metric associated with LLM and threshold value, wherein a prompt is submitted based on the performance metric value and context. The different mappings may comprise different nodes of a graph, see par. 144. Messages are exchanged, par. 148. Note off track node is a strategy map node that meets a desired threshold, see par. 64 instant publication, Baldua).
3. Baldua integrated with Venka teach, processing the strategy map to identify a regular cadence node using the language model; and transmitting a regular cadence message based on the regular cadence node (figs. 6 and 7 , the different mappings may comprise different nodes of a graph, see par. 144. Messages are exchanged, par. 148. In addition, type/different version or large language models comprise different maps, Baldua).
4. Baldua integrated with Venka teach, processing the strategy map to identify an overdue node using the language model and transmitting an overdue message based on the overdue node (graphs and portions of graphs are automatically updated based on time or changes to data hence update may be overdue, see par. 145, Baldua).
5. Baldua integrated with Venka teach, using a retrieval augmented generation system to detect a duplicate between the strategy map nodes and existing strategy map nodes within the strategy map (pars. 147-148, subset and superset entity graph structures comprise duplicate/overlapping graphs, the graphs/subgraphs are used for similarity measurements and statistical concepts, Baldua); sending an update request when the duplicate does not have an update within an update threshold and sending an update notification when the update is within the update threshold (figs. 6 and 7, pars. 174 and 192, performance metric associated with LLM and threshold value, wherein a prompt is submitted based on the performance metric value and context. Messages are exchanged, par. 148, Baldua).
6. Baldua integrated with Venka teach, storing the strategy map nodes in a graph database and in a relational database (par. 159, the strategy plans are stored in graph structures and relational databases); processing a query using the graph database when the query does not identify a project node in the strategy map and processing the query using the relational database when the query identifies the project node in the strategy map (fig. 7A, item 710 Yes and No, pars. 171 and 173, data graphs are processed based on the need to generate a plan, and are processed differently, Baldua).
7. Baldua integrated with Venka teach, wherein processing the natural language input further comprises extracting semantic relationships from the natural language input using the language model (fig. 6, pars. 64 and 66, relationships are extracted from social graph relevant to query, Baldua).
8. Baldua integrated with Venka teach, displaying the updated mapping in an interactive graphical user interface; and adjusting an adaptive layout of the strategy map responsive to the updated mapping (fig. 5A and 6, interface 612 and query planning 680 using entity graphs 632, see pars. 119-120, view and refine system generated modified version of search and mapping information, par. 144 where different data are represented by different mappings, Baldua).
9. Baldua integrated with Venka teach, wherein the strategy map comprises a pillar object and a project object, and wherein the pillar object is stored at a first location in data storage and references the project object stored at a second location in the data storage (par. 199, retrieve data related to the query taxonomy using an entity graph by traversing different locations and join data from two or more data resources, wherein pillar objects are data object related to the query in different locations, Baldua).
10. Baldua integrated with Venka teach, processing the user input received as voice input through a user interface to update the mapping (fig. 1, item 116, par. 67-69, language models are trained on and used by dynamic query planning systems using audio, by the use of GPT models like BERT, Baldua).
System claims 12-19 comprise substantially the same subject matter as method claims 2-10 and are therefore rejected on the merits.
Response to Arguments
Applicant’s arguments with respect to claim(s) 1-20 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure in the field of searching using plan optimization:
USPN. 2025/0258819: fig. 3, par. 65, large language models
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 MARCIN R FILIPCZYK whose telephone number is (571)272-4019. The examiner can normally be reached M-F 7-4 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, Kavita Stanley can be reached at 571-272-8352. 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.
September 4, 2026
/MARCIN R FILIPCZYK/Primary Examiner, Art Unit 2153
Prosecution Insights