DETAILED ACTION
This communication is responsive to Amendment filed 01/14/2026.
Claims 1-20 are pending in this application. In the Amendment, claims 1, 8 and 15 are amended. This action is made Final.
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 Arguments
Applicant's arguments filed 01/14/2026 have been fully considered but they are not persuasive.
Applicant argued Dotan fails to teach "determining, from the observation layer data source, a screen layout comprising spatial arrangements of concurrently displayed interface elements; determining an impact of the screen layout on execution of the plurality of executable processes from the dependency map," as recited by currently amended independent claim 1, and as similarly recited by independent claims 8 and 15.
The Examiner respectfully disagrees as Dotan teaches “determining, from the observation layer data source, a screen layout comprising spatial arrangements of concurrently displayed interface elements” (Dotan, para.58, 95, 102, 104, 126, presentation component uses contextual info to determine how/(how much) content is presented); “determining an impact of the screen layout on execution of the plurality of executable processes from the dependency map” (Dotan, para.58, 63, 94, 104, presentation component determines when to present notifications); and “modification to the screen layout” (Dotan, para.8, 30, 98, 126, modified user experience includes presenting/withholding content).
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 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Perumalla et al. (“Perumalla”, US 2023/0144461) in view of Dotan-Cohen et al. (“Dotan”, US 2017/0140285) in view of Choi et al. (“Choi”, US 2025/0068662) and further in view of Muthu et al. (“Muthu”, US 2025/0335955).
As per claim 1, Perumalla teaches a method comprising:
accessing a knowledge graph that encodes relationships among content items stored for a user account within a content management system according to a plurality of data sources (Perumalla, para.22-25, 56, 61; Fig.1, data sources 150 used to generate knowledge graph 122);
determining, from among the plurality of data sources informing the knowledge graph, an observation layer data source defining data extracted from digital content presented via a client device associated with the user account (Perumalla, para.20, 28, 41-42, 44, data from data sources include browser history, screen time, game, reading activities);
determining, from among the plurality of data sources informing the knowledge graph, a world state data source defining device metrics from sensors of the client device (Perumalla, para.29, 41, 43-44, 59-60, 67, heart rate, temperature, weather; Fig.3, data sources 150 include sensors);
generating, from the knowledge graph, a dependency map linking content items extracted from the plurality of data sources to a plurality of processes that combine to accomplish a target objective (Perumalla, para.26, 32-33, 37-38, 62, activity engine 110 maps current context to stored context to generate recommendations for accomplishing a goal);
generating, for providing to a large language model (Perumalla, Fig.8, model 800; para.69, 76, 83), a coaching prompt comprising instructions including: data encoded in the observation layer data source; the plurality of processes that combine to accomplish the target objective and the content items linked in the dependency map; and the world state data source (Perumalla, para.26-27, 31, 33, 38, 45-48, 51-57, 64-65, activity engine 110 generates recommendations based off of data sources);
generating, utilizing the large language model to process the coaching prompt, a coaching insight that includes a recommendation for modifying time spend associated with the user account (Perumalla, para.25-26, 41, 43, 52, 65, recommend based on activity time; suggestion to reach goals such as not spending time on exercise); and
providing, for display on the client device associated with the user account, the coaching insight that includes the recommendation for modifying time spend (Perumalla, para.31, 38, 55, recommendations thru visual feedback).
However, Perumalla does not explicitly teach generating a dependency map linking digital content items to a plurality of executable processes that combine to accomplish a target objective, the plurality of executable processes being computer processes executable by a computer application; determining, from the observation layer data source, a screen layout comprising spatial arrangements of concurrently displayed interface elements; determining an impact of the screen layout on execution of the plurality of executable processes from the dependency map; and modification to the screen layout. Dotan teaches a method of generating recommendations including generating a dependency map linking digital content items to a plurality of executable processes that combine to accomplish a target objective, the plurality of executable processes being computer processes executable by a computer application (Dotan, para.27-30, 51, 63, 89-91, 110-111, 133, Fig.3, inference engine 360 maps content to executable processes; automatic opening of bank website and Excel file according to predicted user activity pattern); determining, from the observation layer data source, a screen layout comprising spatial arrangements of concurrently displayed interface elements (Dotan, para.58, 95, 102, 104, 126, presentation component uses contextual info to determine how/(how much) content is presented); determining an impact of the screen layout on execution of the plurality of executable processes from the dependency map (Dotan, para.58, 63, 94, 104, presentation component determines when to present notifications); and modification to the screen layout (Dotan, para.8, 30, 98, 126, modified user experience includes presenting/withholding content). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include Dotan’s teaching with Perumalla’s method in order to incorporate recommended device functions to achieve a goal.
While Perumalla teaches non-text data and text conversations to be inputted into the language model (Perumalla, para.27, conversation 410), the method of Perumalla and Dotan does not explicitly teach the coaching prompt comprising textual instructions including: text describing data encoded in the observation layer data source, text describing the plurality of processes and the content items linked in the dependency map, text describing the world state data source, and text describing the impact of the screen layout. Choi teaches a method of generating prompts comprising textual instructions including: text describing data encoded in the observation layer data source (Choi, para.17-18, 33, 50, 67, 74, audio-visual data/state/software app information; current activity), text describing the plurality of processes and the content items linked in the dependency map (Choi, para.17-18, 50, 53, 67, 71, 74, object relationships, context), and text describing the world state data source (Choi, para.17-19, 33, 50, 55-56, 67, 74, sensor data) and text describing the impact of the screen layout (Choi, para.17-18, 33, 50, 67, 74, audio-visual data/state/software app information; current activity). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include Choi’s teaching with the method of Perumalla and Dotan in order to incorporate text and non-text information to provide for a personalized context-aware interaction (Choi, para.67).
Furthermore, the method of Perumalla, Dotan and Choi does not teach generating a weighted combination of the dependency map and the knowledge graph indicating respective emphasis levels for impacting processing of text describing the dependency map and the knowledge graph by large language models; and generating, for providing to a large language model a coaching prompt by determining quantities and placement of dependency-map text and knowledge-graph text within the coaching prompt according to the weighted combination. Muthu teaches a method of generating responses using a LLM including generating a weighted combination of the text indicating respective emphasis levels for impacting processing of text by large language models and generating, for providing to a large language model a coaching prompt by determining quantities and placement of text within the coaching prompt according to the weighted combination (Muthu, para.50, 52-54, attention weights determine text importance input into LLM). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include Muthu’s teaching with the method of Perumalla, Dotan and Choi in order to enhance the LLM to generate targeted responses that are more reliable and insightful (Muthu, para.65).
As per claim 2, the method of Perumalla, Dotan, Choi and Muthu teaches the method of claim 1, wherein determining the observation layer data source comprises determining a relationship between a first content item and a second content item presented via the client device (Perumalla, para.23, 61, 69-70 content nodes and connectors form a relationship).
As per claim 3, the method of Perumalla, Dotan, Choi and Muthu teaches the method of claim 1, further comprising generating, based on the dependency map, the coaching prompt to include instructions from a content item linked to accomplishing an executable process from among the plurality of executable processes (Perumalla, para.26, 32-33, 37-38, 62, activity engine 110 maps current context to stored context to generate recommendations for accomplishing a goal).
As per claim 4, the method of Perumalla, Dotan, Choi and Muthu teaches the method of claim 1, wherein determining the world state data source comprises:
determining, for the client device associated with the user account, the device metrics indicating operating system settings and physical measurements from device sensors (Dotan, para.46, 53, 57, 114, device characteristics like OS determines context); and
determining environmental metrics indicating environmental surroundings of the client device (Perumalla, para.29, 41, 43-44, 59-60, 67, temperature, weather, IoT signals; Fig.3, data sources 150 include sensors).
As per claim 5, the method of Perumalla, Dotan, Choi and Muthu teaches the method of claim 1, wherein generating the coaching prompt comprises:
generating first instruction language from one or more content items extracted via the observation layer data source (Perumalla, para.26, 31, 33, 38, 45-48, 51-57, 64-65, activity engine 110 generates recommendations based off of data sources);
generating second instruction language from one or more of device metrics or environment metrics extracted via the world state data source (Perumalla, para.26, 31, 33, 38, 45-48, 51-57, 64-65, activity engine 110 generates recommendations based off of data sources); and
combining the first instruction language and the second instruction language into the coaching prompt (Perumalla, para.26, 31, 33, 38, 45-48, 51-57, 64-65, activity engine 110 generates recommendations based off of combination of data sources).
As per claim 6, the method of Perumalla, Dotan, Choi and Muthu teaches the method of claim 1, further comprising:
utilizing a software connector to extract content data from a computer application used by the user account via an application integration with the computer application (Perumalla, para.25, data extracted from different applications); and
generating the coaching prompt to include instruction language based on the content data extracted using the software connector (Perumalla, para.26, 31, 33, 38, 45-48, 51-57, 64-65, activity engine 110 generates recommendations based off of data sources).
As per claim 7, the method of Perumalla, Dotan, Choi and Muthu teaches the method of claim 1, wherein determining the observation layer data source comprises determining pixel values at various coordinate locations of a display screen at a particular time stamp including metadata indicating content item identifiers associated with the pixel values (Dotan, para.102-104, presentation component determines how, when or what format content is presented on display).
As per claim 8, Perumalla teaches a system comprising:
at least one processor (Perumalla, para.87; Fig.9, processor 916); and
a non-transitory computer readable medium comprising instructions (Perumalla, para.87; Fig.9, memory 928) that, when executed by the at least one processor, cause the system to:
access a knowledge graph that encodes relationships among content items stored for a user account within a content management system according to a plurality of data sources (Perumalla, para.22-25, 56, 61; Fig.1, data sources 150 used to generate knowledge graph 122);
determine, from among the plurality of data sources informing the knowledge graph, an observation layer data source defining data extracted from digital content presented via a client device associated with the user account (Perumalla, para.28, 41-42, 44, data from data sources include browser history, screen time, game, reading activities);
determine, from among the plurality of data sources informing the knowledge graph, a world state data source defining device metrics and environmental metrics of the client device (Perumalla, para.29, 41, 43-44, 59-60, 67, heart rate, temperature, weather; Fig.3, data sources 150 include sensors);
generating, from the knowledge graph, a dependency map linking content items extracted from the plurality of data sources to a plurality of processes that combine to accomplish a target objective (Perumalla, para.26, 32-33, 37-38, 62, activity engine 110 maps current context to stored context to generate recommendations for accomplishing a goal);
generate, for providing to a large language model (Perumalla, Fig.8, model 800; para.69, 76, 83), a coaching prompt comprising instructions including: data encoded in the observation layer data source; the plurality of executable processes and the content items linked in the dependency map; and the world state data source (Perumalla, para.26, 31, 33, 38, 45-48, 51-57, 64-65, activity engine 110 generates recommendations based off of data sources);
generating, utilizing the large language model to process the coaching prompt, a coaching insight that includes a recommendation for modifying time spend associated with the user account (Perumalla, para.25-26, 41, 43, 52, recommend based on activity time; suggestion to reach goals such as not spending time on exercise); and
providing, for display on the client device associated with the user account, the coaching insight that includes the recommendation for modifying time spend (Perumalla, para.31, 38, 55, recommendations thru visual feedback).
However, Perumalla does not explicitly teach generating a dependency map linking digital content items to a plurality of executable processes that combine to accomplish a target objective, the plurality of executable processes being computer processes executable by a computer application; determining, from the observation layer data source, a screen layout comprising spatial arrangements of concurrently displayed interface elements; determining an impact of the screen layout on execution of the plurality of executable processes from the dependency map; and modification to the screen layout. Dotan teaches a system of generating recommendations including generating a dependency map linking digital content items to a plurality of executable processes that combine to accomplish a target objective, the plurality of executable processes being computer processes executable by a computer application (Dotan, para.27-30, 51, 63, 89-91, 110-111, 133, Fig.3, inference engine 360 maps content to executable processes; automatic opening of bank website and Excel file according to predicted user activity pattern); determining, from the observation layer data source, a screen layout comprising spatial arrangements of concurrently displayed interface elements (Dotan, para.58, 95, 102, 104, 126, presentation component uses contextual info to determine how/(how much) content is presented); determining an impact of the screen layout on execution of the plurality of executable processes from the dependency map (Dotan, para.58, 63, 94, 104, presentation component determines when to present notifications); and modification to the screen layout (Dotan, para.8, 30, 98, 126, modified user experience includes presenting/withholding content). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include Dotan’s teaching with Perumalla’s system in order to incorporate recommended device functions to achieve a goal.
While Perumalla teaches non-text data and text conversations to be inputted into the language model (Perumalla, para.27, conversation 410), the system of Perumalla and Dotan does not explicitly teach the coaching prompt comprising textual instructions including: text describing data encoded in the observation layer data source, text describing the plurality of processes and the content items linked in the dependency map, text describing the world state data source, and text describing the impact of the screen layout. Choi teaches a system of generating prompts comprising textual instructions including: text describing data encoded in the observation layer data source (Choi, para.17-18, 33, 50, 67, audio-visual data/state/software app information; current activity), text describing the plurality of processes and the content items linked in the dependency map (Choi, para.17-18, 50, 53, 67, 71, object relationships, context), and text describing the world state data source (Choi, para.17-19, 33, 50, 55-56, 67, sensor data) and text describing the impact of the screen layout (Choi, para.17-18, 33, 50, 67, 74, audio-visual data/state/software app information; current activity). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include Choi’s teaching with the system of Perumalla and Dotan in order to incorporate text and non-text information to provide for a personalized context-aware interaction (Choi, para.67).
Furthermore, the system of Perumalla, Dotan and Choi does not teach generating a weighted combination of the dependency map and the knowledge graph indicating respective emphasis levels for impacting processing of text describing the dependency map and the knowledge graph by large language models; and generating, for providing to a large language model a coaching prompt by determining quantities and placement of dependency-map text and knowledge-graph text within the coaching prompt according to the weighted combination. Muthu teaches a system of generating responses using a LLM including generating a weighted combination of the text indicating respective emphasis levels for impacting processing of text by large language models and generating, for providing to a large language model a coaching prompt by determining quantities and placement of text within the coaching prompt according to the weighted combination (Muthu, para.50, 52-54, attention weights determine text importance input into LLM). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include Muthu’s teaching with the system of Perumalla, Dotan and Choi in order to enhance the LLM to generate targeted responses that are more reliable and insightful (Muthu, para.65).
As per claim 9, the system of Perumalla, Dotan, Choi and Muthu teaches the system of claim 8, further comprising instructions that, when executed by the at least one processor, cause the system to generate the coaching prompt instructing the large language model to generate a coaching insight comprising a recommendation for modifying time spend of the user account based on the observation layer data source and the world state data source (Perumalla, para.25-26, 41, 43, 52, recommend based on activity time; suggestion to reach goals such as not spending time on exercise).
As per claim 10, the system of Perumalla, Dotan, Choi and Muthu teaches the system of claim 8, wherein determining the observation layer data source comprises determining pixel values at various coordinate locations of a display screen including metadata indicating content item identifiers associated with the pixel values (Dotan, para.102-104, presentation component determines how or what format content is presented on display).
As per claim 11, the system of Perumalla, Dotan, Choi and Muthu teaches the system of claim 8, further comprising instructions that, when executed by the at least one processor, cause the system to:
determine the world state data source by determining the device metrics indicating one or more of device temperature, movement, or orientation from sensors of the client device (Perumalla, para.29, 41, 43-44, 59-60, 67, heart rate, temperature, weather; Fig.3, data sources 150 include sensors); and
generate the coaching prompt from the device metrics determined from the sensors of the client device (Perumalla, para.26, 31, 33, 38, 45-48, 51-57, 64-65, activity engine 110 generates recommendations based off of data sources).
As per claim 12, the system of Perumalla, Dotan, Choi and Muthu teaches the system of claim 8, further comprising instructions that, when executed by the at least one processor, cause the system to:
determine the world state data source by determining, for the client device, environmental metrics (Perumalla, para.29, 41, 43-44, 59-60, 67, wearable feeds, weather; Fig.3, data sources 150 include sensors) indicating one or more of lighting conditions, ambient noise, or physical position of the client device relative to a user (Dotan, para.41-42, GPS); and
generate the coaching prompt from the environmental metrics of the client device (Perumalla, para.26, 31, 33, 38, 45-48, 51-57, 64-65, activity engine 110 generates recommendations based off of data sources).
As per claim 13, the system of Perumalla, Dotan, Choi and Muthu teaches the system of claim 8, further comprising instructions that, when executed by the at least one processor, cause the system to:
determine the observation layer data source by determining a relationship between a first content item and a second content item presented via the client device (Perumalla, para.23, 61, 69-70 content nodes and connectors form a relationship); and
generate the coaching prompt based on the relationship between the first content item and the second content item (Perumalla, para.26, 32-33, 37-38, 62, activity engine 110 maps current context to stored context to generate recommendations).
As per claim 14, the system of Perumalla, Dotan, Choi and Muthu teaches the system of claim 8, further comprising instructions that, when executed by the at least one processor, cause the system to:
determine a user interaction data source that defines user account activity with content items stored within the content management system (Perumalla, para.28, 41-42, 44, data from data sources include browser history, screen time, game, reading activities); and
generate the coaching prompt based on the user account activity with the content items (Perumalla, para.26, 32-33, 37-38, 62, activity engine 110 maps current context to stored context to generate recommendations).
Claim 15 is similar in scope to claim 1, and is therefore rejected under similar rationale.
As per claim 16, the medium of Perumalla, Dotan, Choi and Muthu teaches the non-transitory computer readable medium of claim 15, further comprising instructions that, when executed by the at least one processor, cause the at least one processor to:
determine, from a user interaction data source associated with the user account, the target objective for the user account, wherein the target objective is accomplishable by performing the plurality of executable processes (Perumalla, para.26, 31, 33, 38, 45-48, 51-57, 64-65, activity engine 110 stores goals and associated recommendations; Dotan, para.51, series of interactions); and
generate the coaching prompt to include instructions for performing an executable process from among the plurality of executable processes combinable to accomplish the target objective (Perumalla, para.26, 31-33, 37-38, 45-48, 51-57, 62, 64-65, activity engine 110 maps current context to stored context to generate recommendations for accomplishing a goal based off of combination of data sources; Dotan, para.51, series of interactions).
As per claim 17, the medium of Perumalla, Dotan, Choi and Muthu teaches the non-transitory computer readable medium of claim 15, further comprising instructions that, when executed by the at least one processor, cause the at least one processor to determine the world state data source by determining, based on readings from the sensors of the client device, environmental metrics (Perumalla, para.29, 41, 43-44, 59-60, 67, wearable feeds, weather; Fig.3, data sources 150 include sensors) indicating lighting conditions, ambient noise, and physical position of the client device relative to a user (Dotan, para.41-42, GPS).
As per claim 18, the medium of Perumalla, Dotan, Choi and Muthu teaches the non-transitory computer readable medium of claim 15, further comprising instructions that, when executed by the at least one processor, cause the at least one processor to generate the knowledge graph from the observation layer data source and the world state data source (Perumalla, para.22-25, 56, 61; Fig.1, data sources 150 used to generate knowledge graph 122).
As per claim 19, the medium of Perumalla, Dotan, Choi and Muthu teaches the non-transitory computer readable medium of claim 18, further comprising instructions that, when executed by the at least one processor, cause the at least one processor to generate a dependency map from the knowledge graph by indicating content items stored in the content management system that include data corresponding to a series of executable processes for accomplishing a target objective (Perumalla, para.26, 32-33, 37-38, 62, activity engine 110 maps current context to stored context to generate recommendations for accomplishing a goal; Dotan, para.51, series of interactions).
As per claim 20, the medium of Perumalla, Dotan, Choi and Muthu teaches the non-transitory computer readable medium of claim 19, further comprising instructions that, when executed by the at least one processor, cause the at least one processor to generate the coaching prompt from the dependency map to include at least a portion of the data corresponding to the series of executable processes (Perumalla, para.26, 31-33, 37-38, 45-48, 51-57, 62, 64-65, activity engine 110 maps current context to stored context to generate recommendations for accomplishing a goal based off of data sources).
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.
Inquiries
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SAJEDA MUHEBBULLAH whose telephone number is (571)272-4065. The examiner can normally be reached Mon-Tue/Thur-Fri 10am-8pm.
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, William L Bashore can be reached on 571-272-4088. 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.
/S.M./
Sajeda MuhebbullahExaminer, Art Unit 2174
/WILLIAM L BASHORE/ Supervisory Patent Examiner, Art Unit 2174 /WILLIAM L BASHORE/Supervisory Patent Examiner, Art Unit 2174