Prosecution Insights
Last updated: April 18, 2026
Application No. 18/618,737

REAL-TIME USER RESPONSE MODIFICATIONS FOR CUSTOMER INTERACTIONS

Non-Final OA §102§103
Filed
Mar 27, 2024
Examiner
TIEU, BINH KIEN
Art Unit
2694
Tech Center
2600 — Communications
Assignee
Salesforce Inc.
OA Round
1 (Non-Final)
87%
Grant Probability
Favorable
1-2
OA Rounds
2y 5m
To Grant
97%
With Interview

Examiner Intelligence

Grants 87% — above average
87%
Career Allow Rate
809 granted / 931 resolved
+24.9% vs TC avg
Moderate +10% lift
Without
With
+9.8%
Interview Lift
resolved cases with interview
Typical timeline
2y 5m
Avg Prosecution
25 currently pending
Career history
956
Total Applications
across all art units

Statute-Specific Performance

§101
6.1%
-33.9% vs TC avg
§103
43.9%
+3.9% vs TC avg
§102
26.5%
-13.5% vs TC avg
§112
4.1%
-35.9% vs TC avg
Black line = Tech Center average estimate • Based on career data from 931 resolved cases

Office Action

§102 §103
DETAILED ACTION Claim Rejections - 35 USC § 102 The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action: A person shall be entitled to a patent unless – (a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention. Claims 1, 12 and 19 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Shabat et al. (US 2024/0203404). Regarding claim 1, Shabat et al. (hereinafter “Shabat”) teaches a method for data processing at an utterance modification system, comprising: receiving, from a first user, a first utterance during an interactive conversation session between the first user and a second user (i.e., a dialogue session between two or more participants, such as between an automated assistant of a user (as a first user) associated with the device 240 and a human representative 220 (as a second user), as shown in figure 2 (para. [0033]), wherein the spoken utterance of audio data 150 is provided by a single speaker or the first user (para. [0034]), such as the user associated with the device 240 requests (via a utterance request) the automated assistant at the client device 240 to make a reservation for Burger Palace (para. [0044])); receiving, from the second user in response to the first utterance and during the interactive conversation session, a second utterance comprising a first set of content (i.e., the spoken utterance is provided by other speaker, such as the second user when the audio data is captured as part of the conversation between at least two participants (para. [0034]), such as spoken utterance 201 from the human representative 220 saying “Thank you for calling Burger Palace. How can I help you?” wherein the intent of the spoken utterance of <ask for purpose of call> corresponds to the transcription of “How can I help you?” etc., is a first set of content (para. [0046]-[0047]; transmitting, to a large language model (LLM), a prompt comprising the second utterance and one or more prompt parameters associated with the second user (i.e., the automated assistant receives the audio data of the utterance 201 with one or more prompt parameter, i.e., <ask for purpose of call> or “How can I help you?”, etc.; para. [0047]-[0048] or one or more text encodings included one or more audio embeddings representing semantic information in the spoken utterance captured in the audio data input; para. [0030]); receiving, from the LLM in response to the prompt, a third utterance (i.e., a synthesized utterance 204 saying “I’d like to make a reservation.”) comprising a second set of content (i.e., to make a reservation) that is based at least in part on the first set of content (“How can I help you”), the second set of content being associated with a target user tone that is based at least in part on the one or more prompt parameters (i.e., generating the synthesized audio as a target user tone of the automated assistance of the device 240; para. [0048]-[0049]); and transmitting, to the first user in response to the first utterance, the third utterance during the interactive conversation session (i.e., transmitting the synthesized audio to the human representative 220 via the client device 230 during the conversation session (para. [0048] and [0050])). Regarding claim 12, Shabat teaches an utterance modification system (i.e., computer system 510, as shown in figure 5) for data processing, comprising: one or more memories storing processor-executable code (i.e., storage subsystem 524 stores programming and data constructs; para. [0084]); and one or more processors (i.e., processor 514) coupled with the one or more memories and individually or collectively operable to execute the code to cause the utterance modification system to: receive, from a first user, a first utterance during an interactive conversation session between the first user and a second user (i.e., a dialogue session between two or more participants, such as between an automated assistant of a user (as a first user) associated with the device 240 and a human representative 220 (as a second user), as shown in figure 2 (para. [0033]), wherein the spoken utterance of audio data 150 is provided by a single speaker or the first user (para. [0034]), such as the user associated with the device 240 requests (via a utterance request) the automated assistant at the client device 240 to make a reservation for Burger Palace (para. [0044])); receive, from the second user in response to the first utterance and during the interactive conversation session, a second utterance comprising a first set of content (i.e., the spoken utterance is provided by other speaker, such as the second user when the audio data is captured as part of the conversation between at least two participants (para. [0034]), such as spoken utterance 201 from the human representative 220 saying “Thank you for calling Burger Palace. How can I help you?” wherein the intent of the spoken utterance of <ask for purpose of call> corresponds to the transcription of “How can I help you?” etc., is a first set of content (para. [0046]-[0047]; transmit, to a large language model (LLM), a prompt comprising the second utterance and one or more prompt parameters associated with the second user (i.e., the automated assistant receives the audio data of the utterance 201 with one or more prompt parameter, i.e., <ask for purpose of call> or “How can I help you?”, etc.; para. [0047]-[0048] or one or more text encodings included one or more audio embeddings representing semantic information in the spoken utterance captured in the audio data input; para. [0030]); receive, from the LLM in response to the prompt, a third utterance (i.e., a synthesized utterance 204 saying “I’d like to make a reservation.”) comprising a second set of content (i.e., to make a reservation) that is based at least in part on the first set of content (“How can I help you”), the second set of content being associated with a target user tone that is based at least in part on the one or more prompt parameters (i.e., generating the synthesized audio as a target user tone of the automated assistance of the device 240; para. [0048]-[0049]); and transmit, to the first user in response to the first utterance, the third utterance during the interactive conversation session (i.e., transmitting the synthesized audio to the human representative 220 via the client device 230 during the conversation session (para. [0048] and [0050])). Regarding claim 19, Shabat teaches a non-transitory computer-readable medium storing code for data processing (i.e., the storage subsystem 524 as shown in figure 5; para. [0084]), the code comprising instructions executable by one or more processors to: receive, from a first user, a first utterance during an interactive conversation session between the first user and a second user (i.e., a dialogue session between two or more participants, such as between an automated assistant of a user (as a first user) associated with the device 240 and a human representative 220 (as a second user), as shown in figure 2 (para. [0033]), wherein the spoken utterance of audio data 150 is provided by a single speaker or the first user (para. [0034]), such as the user associated with the device 240 requests (via a utterance request) the automated assistant at the client device 240 to make a reservation for Burger Palace (para. [0044])); receive, from the second user in response to the first utterance and during the interactive conversation session, a second utterance comprising a first set of content (i.e., the spoken utterance is provided by other speaker, such as the second user when the audio data is captured as part of the conversation between at least two participants (para. [0034]), such as spoken utterance 201 from the human representative 220 saying “Thank you for calling Burger Palace. How can I help you?” wherein the intent of the spoken utterance of <ask for purpose of call> corresponds to the transcription of “How can I help you?” etc., is a first set of content (para. [0046]-[0047]; transmit, to a large language model (LLM), a prompt comprising the second utterance and one or more prompt parameters associated with the second user (i.e., the automated assistant receives the audio data of the utterance 201 with one or more prompt parameter, i.e., <ask for purpose of call> or “How can I help you?”, etc.; para. [0047]-[0048] or one or more text encodings included one or more audio embeddings representing semantic information in the spoken utterance captured in the audio data input; para. [0030]); receive, from the LLM in response to the prompt, a third utterance (i.e., a synthesized utterance 204 saying “I’d like to make a reservation.”) comprising a second set of content (i.e., to make a reservation) that is based at least in part on the first set of content (“How can I help you”), the second set of content being associated with a target user tone that is based at least in part on the one or more prompt parameters (i.e., generating the synthesized audio as a target user tone of the automated assistance of the device 240; para. [0048]-[0049]); and transmit, to the first user in response to the first utterance, the third utterance during the interactive conversation session (i.e., transmitting the synthesized audio to the human representative 220 via the client device 230 during the conversation session (para. [0048] and [0050])). 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 9 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Shabat et al. (US 2024/0203404) in view of Bayardelle (US 2025/0300950). Regarding claims 9 and 18, Shabat teaches all subject matters as claimed above, except for the feature of wherein the one or more prompt parameters include a tone parameter. However, Bayardelle teaches system and method comprising a dynamic expression service 1026 of user input message processing logic, as shown in figure 10, which is configured to adjust one or more parameters resulting in a determination of a numerical value for a predetermined set of emotion and tone parameters, such as emotions of happiness, sadness, anger, etc. (para. [0100]). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the feature of wherein the one or more prompt parameters include a tone parameter, as taught by Bayardelle, into view of Shabat in order to output the better third utterance with emotion. Allowable Subject Matter Claims 2-8, 10-11, 13-17 and 20 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. Conclusion The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Darey et al. (US 2025/002573) teaches methods, system and computer programs comprising a large language model (LLM) for using an LLM-based conversation engine to treat a mental health disorder. The method includes obtaining data corresponding to a communication from a user device, determining a current user context based on the obtained data, determining based on the determined user context, whether to invoke the LLM, and based on a determination to invoke the LLM: determining a prompt that is to be provided to the LLM based on the determined user context, providing input data to the LLM, the input data comprising (i) the obtained data and (ii) the determined prompt, obtaining output data, generated by the LLM based on the LLM processing the provided input data, indicating a classification of the provided input data, and using the obtained output data to determine a therapeutic treatment for the user. Yannam et al. (US 11,050,885) teaches When a customer initiates an interaction with an interactive voice response ("IVR") system, the customer may need to be transferred to a live agent. Apparatus and methods may formulate timing information for integrating a live agent into an interaction controlled by an artificial intelligence ("AI") engine. The system may integrate machine generated responses into a customer interaction controlled by a live agent. The system may formulate timing information for intercepting the live agent with responses generated by the AI engine. The system may formulate the timing information using interactional analytics and preferences of a specific customer. Any inquiry concerning this communication or earlier communications from the examiner should be directed to BINH TIEU whose telephone number is (571)272-7510. The examiner can normally be reached on 9-5. The Examiner’s fax number is (571) 273-7510 and E-mail address: BINH.TIEU@USPTO.GOV. Examiner interviews are available via telephone or 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, FAN S. TSANG can be reached on (571) 272-7547. Any response to this action should be mailed or handed carry deliveries to: Commissioner of Patents and Trademarks 401 Dulany Street Alexandria, VA 22314 Or faxed to: (571) 273-8300 Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (FAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the FAIR system, see fitp://nair-direct.usoto.aqev. If you have any questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). /Binh Kien Tieu/Primary Examiner, Art Unit 2694 Date: December 2025
Read full office action

Prosecution Timeline

Mar 27, 2024
Application Filed
Dec 10, 2025
Non-Final Rejection — §102, §103
Mar 25, 2026
Examiner Interview Summary
Mar 25, 2026
Applicant Interview (Telephonic)
Mar 30, 2026
Response Filed

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12603111
AUDIO GUESTBOOK SYSTEMS AND METHODS
2y 5m to grant Granted Apr 14, 2026
Patent 12598223
Dynamic Teleconference Content Item Distribution to Multiple Devices Associated with a User
2y 5m to grant Granted Apr 07, 2026
Patent 12592994
REAL-TIME USER SCREENING OF MESSAGES WITHIN A COMMUNICATION PLATFORM
2y 5m to grant Granted Mar 31, 2026
Patent 12592740
WIRELESS COMMUNICATION DEVICE AND WIRELESS COMMUNICATION METHOD
2y 5m to grant Granted Mar 31, 2026
Patent 12573198
COMMUNICATION SYSTEM, OUTPUT DEVICE, COMMUNICATION METHOD, OUTPUT METHOD, AND OUTPUT PROGRAM
2y 5m to grant Granted Mar 10, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

AI Strategy Recommendation

Get an AI-powered prosecution strategy using examiner precedents, rejection analysis, and claim mapping.
Powered by AI — typically takes 5-10 seconds

Prosecution Projections

1-2
Expected OA Rounds
87%
Grant Probability
97%
With Interview (+9.8%)
2y 5m
Median Time to Grant
Low
PTA Risk
Based on 931 resolved cases by this examiner. Grant probability derived from career allow rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month