DETAILED ACTION
This action is responsive to the application filed 9/26/2024.
Claims 1-20 are pending.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Zulfikar, et al., U.S. PGPUB No. 2025/0348521 (“Zulfikar”), in view of Justis, et al., U.S. PGPUB No. 2024/0346432 (“Justis”).
With regard to Claim 1, Zulfikar teaches a computer-implemented method, the method comprising:
transcribing audio data of a current user interaction into text data ([0073] describes that conversation speech is gathered and converted to text);
analyzing the text data using natural language processing to identify a context of the current user interaction ([0074] describes that the speech transcription is taken and the current context determined and stored. [0078] describes that relevant memories are located by generating query embeddings, where [0079] describes that the current context is used in the query to retrieve the relevant memories);
creating one or more prompts for the GenAI model ([0079] describes using the conversation portion in generating a prompt)
querying the GenAI model using the one or more prompts and using one or more existing prompts from a previous user interaction to identify a contextual opportunity for notification ([0079] describes that the current context and user query are used to search for semantically similar previous memories, which are stored from previous conversations as described at [0070]-[0072]. [0080] describes that the query, current context, and retrieved memories are then used to form a prompt to the LLM to generate an answer to a user query); and
notifying a user of the contextual opportunity for notification during the current user interaction ([0080]-[0081] describe that the prompt searches through the memories to identify an answer to a user query. [0085] describes that a user is notified of the answer by providing the answer to a text-to-speech process and playing the answer for the user).
Zulfikar, in view of Justis teaches generating, via a generative artificial intelligence (GenAI) model, one or more summaries of contextually relevant portions of the text data; and creating one or more prompts for the GenAI model based on the one or more summaries. Zulfikar teaches at [0079] that the system uses the most recent conversation to form a query prompt. Justis teaches at [0122] that a system can generate a LLM prompt using a part of a recent conversation; the conversation history can be summarized and the summary used for the prompt.
It would have been obvious to one of ordinary skill in the art at the time this application was filed to modify Zulfikar to provide a summary of a conversation history as a prompt to an LLM as described in Justis. Justis at [0122] describes that a summary can be used in place of a full conversation history in a prompt, as the computational expense of submitting a full conversation grows with the conversation’s size. One of skill in the art would have therefore sought the modification, to improve the functioning of the system of Zulfikar by enabling the inclusion of more of a conversation history in a query, without causing a similar increase in computational burden.
Claim 8 recites a computer system comprising one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions (Zulkifar, Fig. 1) to carry out the method of Claim 1, and is similarly rejected. Claim 15 recites a computer program product, the computer program product comprising: one or more computer-readable tangible storage medium and program instructions (Zulfikar, Fig. 1) that carry out the method of Claim 1, and is likewise rejected.
With regard to Claim 2, Zulfikar teaches that the audio data of the current user interaction is received from an Internet-of-Things (IoT) device of the user. [0045] describes that the user device can be a smartphone, tablet, headset, watch, or other wearable device.
Claim 9 recites a computer system comprising one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions (Zulkifar, Fig. 1) to carry out the method of Claim 2, and is similarly rejected. Claim 16 recites a computer program product, the computer program product comprising: one or more computer-readable tangible storage medium and program instructions (Zulfikar, Fig. 1) that carry out the method of Claim 2, and is likewise rejected.
With regard to Claim 3, Zulfikar teaches that the contextually relevant portions of the text data have a same context as the context of the current user interaction. [0079] describes that the current context used in the query includes the most recent text of the conversation.
Claim 10 recites a computer system comprising one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions (Zulkifar, Fig. 1) to carry out the method of Claim 3, and is similarly rejected. Claim 17 recites a computer program product, the computer program product comprising: one or more computer-readable tangible storage medium and program instructions (Zulfikar, Fig. 1) that carry out the method of Claim 3, and is likewise rejected.
With regard to Claim 4, Zulfikar teaches that the contextual opportunity for notification comprises a portion of transcribed text, and/or its corresponding summary, which was identified, and/or generated, during a previous user interaction, and which is contextually relevant to the context of the current user interaction. [0080] describes that the answer is generated from the relevant memories, where [0070] describes that memories are created from transcribed text from conversations.
Claim 11 recites a computer system comprising one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions (Zulkifar, Fig. 1) to carry out the method of Claim 4, and is similarly rejected. Claim 18 recites a computer program product, the computer program product comprising: one or more computer-readable tangible storage medium and program instructions (Zulfikar, Fig. 1) that carry out the method of Claim 4, and is likewise rejected.
With regard to Claim 5, Zulfikar teaches that contextual relevance of the contextual opportunity for notification is based on a measure of contextual similarity between the contextual opportunity for user notification and the context of the current user interaction. [0079] describes that the memories which are submitted with the query for extracting answer text therefrom are identified by calculating a similarity measure between the current context and stored memories.
Claim 12 recites a computer system comprising one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions (Zulkifar, Fig. 1) to carry out the method of Claim 5, and is similarly rejected. Claim 19 recites a computer program product, the computer program product comprising: one or more computer-readable tangible storage medium and program instructions (Zulfikar, Fig. 1) that carry out the method of Claim 5, and is likewise rejected.
With regard to Claim 6, Zulfikar teaches that presenting the contextual opportunity for notification via the IoT device of the user within an optimized window of time. [0085] describes that the notification is converted to audio and played back for the user through headphones, which are connected to a device such as a smartphone, tablet, or headset as described at [0045]. [0084] describes that answers can be generated in a queryless mode, which minimizes time spent in interactions during conversations.
Claim 13 recites a computer system comprising one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions (Zulkifar, Fig. 1) to carry out the method of Claim 6, and is similarly rejected. Claim 20 recites a computer program product, the computer program product comprising: one or more computer-readable tangible storage medium and program instructions (Zulfikar, Fig. 1) that carry out the method of Claim 6, and is likewise rejected.
With regard to Claim 7, Zulfikar, in view of Justis teaches storing the one or more summaries and the one or more prompts within a user repository of contextualized notes, wherein summaries and prompts stored within the user repository are indexed according to a timestamp or a timeframe of respective user interactions during which they were created. Zulfikar teaches at [0072] that the memories are encoded and stored, along with their text transcription and a timestamp of the start. Justis teaches at [0085] that prompt text can be summarized, and that a prompt which also uses conversation history can use summarized versions of the conversation history.
It would have been obvious to one of ordinary skill in the art at the time this application was filed to modify Zulfikar to use summaries of conversation contexts and histories as prompts to an LLM as described in Justis. Justis at [0122] describes that a summary can be used in place of a full conversation history in a prompt, as the computational expense of submitting a full conversation grows with the conversation’s size. One of skill in the art would have therefore sought the modification, to improve the functioning of the system of Zulfikar by enabling the use of summaries in place of full text, to allow for the use of significant amounts of current and previous conversations without a commensurate increase in computational burden.
Claim 14 recites a computer system comprising one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions (Zulkifar, Fig. 1) to carry out the method of Claim 7, and is similarly rejected.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KEITH D BLOOMQUIST whose telephone number is (571)270-7718. The examiner can normally be reached M-F, 8:30-5 PM.
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, Kieu Vu can be reached at 571-272-4057. 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.
/KEITH D BLOOMQUIST/Primary Examiner, Art Unit 2171
8/5/2026
Prosecution Insights