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 .
Status of Claims
Claims 1, 14, and 18 have been amended.
Claims 1-20 are currently pending and have been examined.
Response to Applicant's Remarks
35 U.S.C. § 101
Applicant’s remarks, see Page(s) 11-14, filed 12 January 2026, with respect to the 35 U.S.C. § 101 rejections, have been fully considered, but are not persuasive.
Applicant submits that the claims of the current application do not recite an abstract idea because the claims recite a specific technical solution that uses particular technology and inputs to achieve a specific technical effect, in particular using specific information to determine customer intent and utilizing large language models to summarize encounters and aid in ranking support documents.
Examiner respectfully disagrees. The claims continue to recite(s) a system and series of steps for summarizing support encounters and support documents and routing a customer’s support request based on the determined intent of the customer, which under broadest reasonable interpretation, is analogous to concepts performed in the human mind and managing personal interactions between people. These concepts are grouped as mental processes and certain methods of organizing human activity.
The limitation(s) of, ‘receiving, from the customer, a request for a support encounter’; ‘determining an intent of the customer, the intent indicative of an issue experienced by the customer’; ‘filtering a set of possible intents…’; ‘routing the customer to a support agent based on the determined intent’; ‘generating…one or more summaries of one or more previous support encounters involving the customer’; ‘providing, to the support agent, the one or more summaries of the one or more previous support encounters’; ‘determining,…one or more support documents related to the issue experienced by the customer’; ‘generating…a summary of each of the one or more support documents’; ‘providing the generated one or more summaries of the one or more support documents to the support agent’, as drafted, recite a process that, under broadest reasonable interpretation, is/are mental processes and certain methods of organizing human activity. Accordingly, the claim(s) recite(s) an abstract idea.
The judicial exception is not integrated into a practical application. In particular, the claim(s) recite(s) the additional element(s) of ‘a processor’, ‘a first large language model’, ‘a second large language model’, ‘a non-volatile computer-readable storage medium’, ‘a non-transitory computer-readable storage medium’, ‘at least one data processor’, ‘querying a device database’. These additional elements are recited at a high-level of generality such that in conjunction with the abstract limitations, they amount to no more than:
mere instructions to apply the exception using generic computer components (i.e., generic computer components performing generic computer functions) (‘a processor’, ‘a non-volatile computer-readable storage medium’, ‘a non-transitory computer-readable storage medium’, ‘at least one data processor’). In their broadest reasonable interpretation, the additional element(s) comprise(s) only a processor, instructions in memory, a display, a receiver, and a transmitter, being used to implement the functions of the abstract idea. Accordingly, the claims do not amount to more than a recitation of the words "apply it" (or an equivalent) or more than mere instructions to implement an abstract idea or other exception in a generic computing environment (see MPEP 2106.05(f) Mere Instructions to Apply an Exception). Thus, even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application and the claim(s) is/are directed to the judicial exception.
generally linking the use of the judicial exception to a particular technological environment or field of use (‘a first large language model’, ‘a second large language model’, ‘querying a device database’).
Applicant further submits that the recited approach provides a technical improvement at least because it reduces computational resources required by reducing the number of possible intents using retrieved device information.
Examiner respectfully disagrees, as the claim limitations are not indicative of integration into a practical application, such as an improvement to the functioning of a computer or other technical field, as considered below in view of MPEP 2106. In particular, an improvement in the judicial exception itself is not an improvement in technology. Applicant’s improvement in this case is not an improvement to the functioning of a computer, or to any other technology or technological field.
The following are examples of eligible subject matter based on technological improvements: see, e.g., McRO, 837 F.3d at 1315 ("The claimed process uses a combined order of specific rules that renders information into a specific format that is then used and applied to create desired results: a sequence of synchronized, animated characters."); Finjan, Inc. v. Blue Coat Sys., Inc., 879 F.3d 1299, 1304 (Fed. Cir. 2018) (finding patent eligible a claim drawn to a behavior-based virus scan that protects against viruses that have been "cosmetically modified to avoid detection by code-matching virus scans"); Enfish, 822 F.3d at 1330, 1333 (discussing patent eligible claims directed to "an innovative logical model for a computer database" that included a self-referential table allowing for greater flexibility in configuring databases, faster searching, and more effective storage); CardioNet, LLC v. InfoBionic, Inc., 955 F.3d 1358, 1368 (Fed. Cir. 2020) (explaining that the claims at issue focus on a specific means for improving cardiac monitoring technology; they are not "directed to a result or effect that itself is the abstract idea and merely invoke generic processes and machinery" (quoting McRO, 837 F.3d at 1314)).
In contrast, the claims of the current application are similar to gathering and analyzing information using conventional techniques and displaying the result (TLI Communications, 823 F.3d at 612-13, 118 USPQ2d at 1747-48), wherein the courts have indicated not to be sufficient to show an improvement to technology.
To show that the involvement of a computer assists in improving the technology, the claims must recite the details regarding how a computer aids the method, the extent to which the computer aids the method, or the significance of a computer to the performance of the method. Merely adding generic computer components to perform the method is not sufficient. Thus, the claim must include more than mere instructions to perform the method on a generic component or machinery to qualify as an improvement to an existing technology (see MPEP 2106.05(a)).
Instead, the claims recite the following additional elements: ‘a processor’, ‘a first large language model’, ‘a second large language model’, ‘a non-volatile computer-readable storage medium’, ‘a non-transitory computer-readable storage medium’, ‘at least one data processor’, ‘querying a device database’. These additional elements are recited at a high-level of generality such that in conjunction with the abstract limitations, they amount to no more than:
mere instructions to apply the exception using generic computer components (i.e., generic computer components performing generic computer functions) (‘a processor’, ‘a non-volatile computer-readable storage medium’, ‘a non-transitory computer-readable storage medium’, ‘at least one data processor’). In their broadest reasonable interpretation, the additional element(s) comprise(s) only a processor, instructions in memory, a display, a receiver, and a transmitter, being used to implement the functions of the abstract idea. Accordingly, the claims do not amount to more than a recitation of the words "apply it" (or an equivalent) or more than mere instructions to implement an abstract idea or other exception in a generic computing environment (see MPEP 2106.05(f) Mere Instructions to Apply an Exception). Thus, even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application and the claim(s) is/are directed to the judicial exception.
generally linking the use of the judicial exception to a particular technological environment or field of use (‘a first large language model’, ‘a second large language model’, ‘querying a device database’).
35 U.S.C. § 103
Applicant’s remarks, see Page(s) 14, filed 12 January 2026, with respect to the 35 U.S.C. § 103 rejections, have been fully considered, but are moot in view of the new grounds of rejection provided below, as necessitated by the claim amendments.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claim(s) 1-20 is/are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Claim(s) 1, 14, and 18 recite(s) a system and series of steps for summarizing support encounters and support documents and routing a customer’s support request based on the determined intent of the customer, which under broadest reasonable interpretation, is analogous to concepts performed in the human mind and managing personal interactions between people. These concepts are grouped as mental processes and certain methods of organizing human activity.
The limitation(s) of, ‘receiving, from the customer, a request for a support encounter’; ‘determining an intent of the customer, the intent indicative of an issue experienced by the customer’; ‘filtering a set of possible intents…’; ‘routing the customer to a support agent based on the determined intent’; ‘generating…one or more summaries of one or more previous support encounters involving the customer’; ‘providing, to the support agent, the one or more summaries of the one or more previous support encounters’; ‘determining,…one or more support documents related to the issue experienced by the customer’; ‘generating…a summary of each of the one or more support documents’; ‘providing the generated one or more summaries of the one or more support documents to the support agent’, as drafted, recite a process that, under broadest reasonable interpretation, is/are mental processes and certain methods of organizing human activity. Accordingly, the claim(s) recite(s) an abstract idea.
The judicial exception is not integrated into a practical application. In particular, the claim(s) recite(s) the additional element(s) of ‘a processor’, ‘a first large language model’, ‘a second large language model’, ‘a non-volatile computer-readable storage medium’, ‘a non-transitory computer-readable storage medium’, ‘at least one data processor’, ‘querying a device database’. These additional elements are recited at a high-level of generality such that in conjunction with the abstract limitations, they amount to no more than:
mere instructions to apply the exception using generic computer components (i.e., generic computer components performing generic computer functions) (‘a processor’, ‘a non-volatile computer-readable storage medium’, ‘a non-transitory computer-readable storage medium’, ‘at least one data processor’). In their broadest reasonable interpretation, the additional element(s) comprise(s) only a processor, instructions in memory, a display, a receiver, and a transmitter, being used to implement the functions of the abstract idea. Accordingly, the claims do not amount to more than a recitation of the words "apply it" (or an equivalent) or more than mere instructions to implement an abstract idea or other exception in a generic computing environment (see MPEP 2106.05(f) Mere Instructions to Apply an Exception). Thus, even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application and the claim(s) is/are directed to the judicial exception.
generally linking the use of the judicial exception to a particular technological environment or field of use (‘a first large language model’, ‘a second large language model’, ‘querying a device database’).
Claim(s) 2-13, 15-17, 19, and 20 further recite(s) the system and series of steps for summarizing support encounters and support documents and routing a customer’s support request based on the determined intent of the customer, which under broadest reasonable interpretation, is analogous to concepts performed in the human mind and managing personal interactions between people. These concepts are grouped as mental processes and certain methods of organizing human activity. Accordingly, the claim(s) recite(s) an abstract idea.
The judicial exception is not integrated into a practical application. In particular, the claim(s) recite(s) the additional element(s) of ‘a sentiment model’, ‘a first sentiment analysis model’, ‘a second sentiment analysis model’, ‘a text-based sentiment analysis model’, ‘an audio-based sentiment analysis model’. These additional elements are recited at a high-level of generality such that in conjunction with the abstract limitations, they amount to no more than generally linking the use of the judicial exception to a particular technological environment or field of use.
Furthermore, the claims recite(s) the additional elements of receiving and transmitting data. These limitations are recited at a high level of generality (i.e., as a general means of receiving and transmitting data), and amount to mere data transmission, which is a form of insignificant extra-solution activity. Thus, the claim(s) is/are directed to the abstract idea.
As discussed above, the additional elements amount to mere data transmission, which is a form of insignificant extra-solution activity. As detailed in MPEP 2106, a conclusion that an additional element is insignificant extra-solution activity in Step 2A should be re-evaluated in Step 2B. Here, the reception and transmission of data was considered to be extra-solution activity in Step 2A, and thus it is re-evaluated in Step 2B to determine if it is more than what is well-understood, routine, conventional activity in the field.
The generic functions of receiving and transmitting data are considered to be well‐understood, routine, and conventional elements previously known to the industry, because the functions can be summarized as the generic computer functions of receiving or transmitting data over a network. This is similar to how ‘using the Internet to gather data’ was found to be a well-known, routine, and conventional function in the decision of Intellectual Ventures I LLC v. Symantec Corp. (Fed. Cir. 2015) (see MPEP 2106.05(d)(II) Elements That the Courts Have Recognized as Well-Understood, Routine, Conventional Activity in Particular Fields). Thus, these elements amount to well‐understood, routine, and conventional elements previously known to the industry, which does not add significantly more, and therefore remains insignificant extra-solution activity even upon reconsideration. Even when considered in combination, these additional elements represent mere instructions to apply an exception and insignificant extra-solution activity, which do not provide an inventive concept, and therefore, the claim(s) is/are not eligible.
As analyzed above in step 2A prong 2, the limitations as an ordered combination, are merely applying the abstract idea in a generic computing environment. In addition, the claims do not improve functionality of a computer or improve any other technology. Thus, claims 1-20 are ineligible as the claims do not recite additional elements which result in significantly more than the abstract idea itself.
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.
Claim(s) 1, 2, 4-8, 14, 15, and 17-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sotiriou (U.S. Patent App. Pub. No. 20250069086), in view of Hawes (U.S. Patent App. Pub. No. 20140052645), in further view of Mahindru (U.S. Patent App. Pub. No. 20220405315).
In regards to claim 1, Although Sotiriou teaches A method for issue mitigation for a customer of a telecommunications service comprising: receiving, from the customer, a request for a support encounter (Sotiriou: ¶64-67 disclose the customer may choose to escalate the communication by making an inbound communication request), the reference does not explicitly state wherein the request comprises a device identifier used to retrieve device information from a database and determine customer intent.
However, Sotiriou and Hawes together teach:
wherein the request comprises a device identifier associated with the customer (Hawes: ¶29, ¶51-54, ¶62, ¶88 disclose receiving a support/service request from a customer wherein the request comprises relevant metadata, such as a customer device serial number);
querying a device database using the device identifier to retrieve device information comprising at least one of: a device manufacturer, a device model, or an operating system of the device (Hawes: ¶29, ¶45, ¶51-54, ¶57, ¶62, ¶88 disclose using the customer device serial number to retrieve device information from a database);
determining an intent of the customer, the intent indicative of an issue experienced by the customer, wherein the intent is determined using data related to the request for the support encounter (Sotiriou: ¶24-25, ¶28 disclose analyze the context (e.g., the text-based transcript of the communication session) to generate a statement explaining the intent of the customer in invoking the communication session) and the retrieved device information, wherein determining the intent comprises filtering a set of possible intents based on the retrieved device information in order to reduce a number of intents evaluated (Hawes: ¶29, ¶51-57, ¶62, ¶88 disclose using the device information to narrow the topic or issue and narrow the solution options);
routing the customer to a support agent based on the determined intent (Sotiriou: ¶24-26, ¶66-68 disclose a user or customer may be routed to a human agent who is selected by identifying agent traits or characteristics that are best suited for the specific customer, the intent of the customer, the sentiment expressed or identified);
generating, using a first large language model, one or more summaries of one or more previous support encounters involving the customer, wherein an input to the first large model comprises information related to the one or more previous support encounters (Sotiriou: ¶24-28, ¶60-62, ¶71, ¶78-81, ¶87, ¶102 disclose instruct the LLM to perform specific tasks, such as generating customer profile summaries, identifying next-best actions, or analyzing conversation transcripts for sentiment, topics, and key themes);
providing, to the support agent, the one or more summaries of the one or more previous support encounters (Sotiriou: ¶60-62, ¶65, ¶77 disclose the customer profile summary aims to equip the agent with a quick overview of the customer's background, preferences, and the nature of their inquiry or issue).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the device identifier and device database, as taught by Hawes, into the system and method of Sotiriou. One of ordinary skill in the art would have been motivated to make this modification in order to “improve techniques for providing technical support and services to customers” (Hawes: ¶6).
Although Sotiriou teaches using large language models to summarize transcript documents, the reference does not explicitly teach determining and summarizing support documents based on user intent and previous encounters.
However, Mahindru teaches:
determining, based on at least one of the determined intent or the one or more generated summaries of one or more previous encounters, one or more support documents related to the issue experienced by the customer (Mahindru: ¶27-30, ¶36-37, ¶44, ¶48-50 disclose in response to the user query… technical solution identification module can identify and determine if a solution for the identified technical issue exists within annotated technical solution document repository);
generating, using a second large language model, a summary of each of the one or more support documents, wherein an input to the second large language model comprises a support document of the one or more support documents (Mahindru: ¶14, ¶27-30, ¶36-37, ¶46, ¶48-50 disclose generate a summary for technical document); and
providing the generated one or more summaries of the one or more support documents to the support agent for use by the support agent to mitigate the issue experienced by the customer (Mahindru: ¶48, ¶58 disclose the ranked solutions can be presented to a user (e.g., a customer representative) by solution ranking module and include the summaries).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the support document summarization, as taught by Mahindru, into the system and method of Sotiriou and Hawes. One of ordinary skill in the art would have been motivated to make this modification in order to “assist users to resolve a broad range of technical issues quickly and effectively” (Mahindru: ¶2).
In regards to claim 2, Sotiriou, Hawes, and Mahindru teach the method of claim 1. Sotiriou further teaches wherein generating the one or more summaries of the one or more previous support encounters is performed before determining the intent of the customer, wherein the intent of the customer is determined based on the one or more summaries of the one or more previous support encounters (Sotiriou: ¶24-28, ¶60-62, ¶71, ¶78-81, ¶87, ¶102).
In regards to claim 4, Sotiriou, Hawes, and Mahindru teach the method of claim 1. Mahindru further teaches wherein the generated one or more summaries of the one or more support documents comprise one or more troubleshooting steps contained in the one or more support documents (Mahindru: ¶14, ¶27-30, ¶36-37, ¶44, ¶46, ¶48-50).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the support document summarization, as taught by Mahindru, into the system and method of Sotiriou and Hawes. One of ordinary skill in the art would have been motivated to make this modification in order to “assist users to resolve a broad range of technical issues quickly and effectively” (Mahindru: ¶2).
In regards to claim 5, Sotiriou, Hawes, and Mahindru teach the method of claim 1. Sotiriou further teaches wherein the one or more previous support encounters comprise support encounters across a plurality of channels comprising two or more of telephone support, chat support, email support, or in-person support (Sotiriou: ¶24-28, ¶59-62, ¶71, ¶78-81, ¶87, ¶102).
In regards to claim 6, Sotiriou, Hawes, and Mahindru teach the method of claim 5. Sotiriou further teaches wherein generating the one or more summaries of the one or more previous support encounters comprises: retrieving, from a plurality of data sources, previous support encounter data; converting the previous support encounter data to a standardized format; and generating a merged dataset comprising the converted previous support encounter data (Sotiriou: ¶24-28, ¶36, ¶39, ¶54-55, ¶59-62, ¶71, ¶78-81, ¶87, ¶102).
In regards to claim 7, Sotiriou, Hawes, and Mahindru teach the method of claim 1. Sotiriou further teaches wherein the data related to the request for the support encounters comprises one or more of: public information, internal information, or an intent indicated by the customer, wherein the public information comprises information related to at least one of a weather event, an emergency, a gathering, a software update, or a hardware release, wherein the internal information comprises information related to at least one of a service interruption of the telecommunications service or a customer bill (Sotiriou: ¶24-25, ¶28, ¶64-67).
In regards to claim 8, Sotiriou, Hawes, and Mahindru teach the method of claim 1. Sotiriou further teaches receiving, during the support encounter, a customer input; determining, based on the customer input, a sentiment of the customer, wherein the intent is determined by applying a sentiment model to the customer input (Sotiriou: ¶24-25, ¶28, ¶70, ¶120); determining, using on the sentiment, an action to be performed by the support agent; and providing, to the support agent, one or more instructions to perform the action (Sotiriou: ¶69-71, ¶83-85, ¶107-117).
In regards to claim 14, the claim recites the same or similar limitations as those addressed above in claim 1 and therefore is rejected for the same reasons set forth above for claim 1. Additionally, Sotiriou further teaches the system comprising: a processor; and a non-volatile computer-readable storage medium having instructions recorded thereon (Sotiriou: ¶131-132). Furthermore, the rationale to combine the prior art set forth above for claim 1 applies to the rejection of claim 14.
In regards to claim 15, Sotiriou, Hawes, and Mahindru teach the system of claim 14. Additionally, the claim recites the same or similar limitations as those addressed above in claim 2 and therefore is rejected for the same reasons set forth above for claim 2.
In regards to claim 17, Sotiriou, Hawes, and Mahindru teach the system of claim 14. Additionally, the claim recites the same or similar limitations as those addressed above in claim 7 and therefore is rejected for the same reasons set forth above for claim 7.
In regards to claim 18, the claim recites the same or similar limitations as those addressed above in claim 1 and therefore is rejected for the same reasons set forth above for claim 1. Additionally, Sotiriou further teaches A non-transitory, computer-readable storage medium comprising instructions recorded thereon (Sotiriou: ¶131-132). Furthermore, the rationale to combine the prior art set forth above for claim 1 applies to the rejection of claim 18.
In regards to claim 19, Sotiriou, Hawes, and Mahindru teach the non-transitory computer-readable storage medium of claim 18. Additionally, the claim recites the same or similar limitations as those addressed above in claim 2 and therefore is rejected for the same reasons set forth above for claim 2.
In regards to claim 20, Sotiriou, Hawes, and Mahindru teach the non-transitory computer-readable storage medium of claim 18. Additionally, the claim recites the same or similar limitations as those addressed above in claim 7 and therefore is rejected for the same reasons set forth above for claim 7.
Claim(s) 3 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sotiriou (U.S. Patent App. Pub. No. 20250069086), in view of Hawes (U.S. Patent App. Pub. No. 20140052645), in further view of Mahindru (U.S. Patent App. Pub. No. 20220405315) and Ge (U.S. Patent App. Pub. No. 20250061465).
In regards to claim 3, Sotiriou, Hawes, and Mahindru teach the method of claim 1. Although Sotiriou teaches summarizing previous support interactions, the reference does not explicitly state wherein the previous support interactions occurred within a specified timeframe.
However, Ge teaches wherein the one or more previous support encounters occurred within a threshold period of time of the requested support encounter (Ge: ¶39-41).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the time period, as taught by Ge, into the system and method of Sotiriou, Hawes, and Mahindru. One of ordinary skill in the art would have been motivated to make this modification in order to “enable review and analysis of customer inquiries” (Ge: ¶3).
Claim(s) 9, 10, and 11 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sotiriou (U.S. Patent App. Pub. No. 20250069086), in view of Hawes (U.S. Patent App. Pub. No. 20140052645), in further view of Mahindru (U.S. Patent App. Pub. No. 20220405315) and Brown (U.S. Patent App. Pub. No. 20210258424).
In regards to claim 9, Sotiriou, Hawes, and Mahindru teach the method of claim 8. Although Sotiriou teaches determining a user sentiment based on user speech audio and generating a transcript, the reference does not explicitly state isolating the audio of the speakers.
However, Sotiriou and Brown together teach wherein the customer input comprises audio input (Sotiriou: ¶24-25, ¶28, ¶60-61, ¶70, ¶120), and wherein determining the sentiment comprises: isolating a speech of the customer from a speech of the support agent; generating a text representation of the isolated speech; and inputting the generated text representation to a text-based sentiment analysis model to determine the sentiment (Brown: ¶26-29, ¶41-42, ¶50-53, ¶131; Sotiriou: ¶24-25, ¶28, ¶60-61, ¶70, ¶120).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the speech recognition and analysis, as taught by Brown, into the system and method of Sotiriou, Hawes, and Mahindru. One of ordinary skill in the art would have been motivated to make this modification in order to “improve the likelihood and/or probability of producing the desired outcome or disposition based on the computed probabilities and/or comparison with other patterns from completed conversations” (Brown: ¶22).
In regards to claim 10, Sotiriou, Hawes, and Mahindru teach the method of claim 8. Although Sotiriou teaches determining a user sentiment based on user speech audio and generating a transcript, the reference does not explicitly state isolating the audio of the speakers and extracting speech features.
However, Sotiriou and Brown together teach wherein the customer input comprises audio input (Sotiriou: ¶24-25, ¶28, ¶60-61, ¶70, ¶120), and wherein determining the sentiment comprises: isolating a speech of the customer from a speech of the support agent; extracting one or more features from the isolated speech of the customer, the one or more features related to at least one of: a pitch, an amplitude, a tone of voice, a speed, or a Mel Frequency Cepstral Coefficient (MFCC) of the speech of the customer; and inputting the one or more extracted features to an audio-based sentiment analysis model to determine the sentiment (Brown: ¶26-29, ¶41-42, ¶50-53, ¶131; Sotiriou: ¶24-25, ¶28, ¶60-61, ¶70, ¶120).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the speech recognition and analysis, as taught by Brown, into the system and method of Sotiriou, Hawes, and Mahindru. One of ordinary skill in the art would have been motivated to make this modification in order to “improve the likelihood and/or probability of producing the desired outcome or disposition based on the computed probabilities and/or comparison with other patterns from completed conversations” (Brown: ¶22).
In regards to claim 11, Sotiriou, Hawes, and Mahindru teach the method of claim 8. Although Sotiriou teaches determining a user sentiment based on user speech audio and generating a transcript, the reference does not explicitly state isolating the audio of the speakers and extracting numerical speech features.
However, Sotiriou and Brown together teach wherein the customer input comprises audio input (Sotiriou: ¶24-25, ¶28, ¶60-61, ¶70, ¶120), and wherein determining the sentiment comprises: isolating a speech of the customer from a speech of the support agent; generating a text representation of the isolated speech; providing the generated text representation to a first sentiment analysis model to produce a first output; generating a numerical representation of the isolated speech, the numerical representation corresponding to at least one of a tone, a speed, an amplitude, a pitch, or a Mel Frequency Cepstral Coefficient (MFCC); providing the numerical representation to a second sentiment analysis model to produce a second output; and determining, based on the first output and the second output, the sentiment (Brown: ¶26-29, ¶41-42, ¶50-53, ¶131; Sotiriou: ¶24-25, ¶28, ¶60-61, ¶70, ¶120).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the speech recognition and analysis, as taught by Brown, into the system and method of Sotiriou, Hawes, and Mahindru. One of ordinary skill in the art would have been motivated to make this modification in order to “improve the likelihood and/or probability of producing the desired outcome or disposition based on the computed probabilities and/or comparison with other patterns from completed conversations” (Brown: ¶22).
Claim(s) 12, 13, and 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sotiriou (U.S. Patent App. Pub. No. 20250069086), in view of Hawes (U.S. Patent App. Pub. No. 20140052645), in further view of Mahindru (U.S. Patent App. Pub. No. 20220405315) and Lin (U.S. Patent App. Pub. No. 20240340477).
In regards to claim 12, Sotiriou, Hawes, and Mahindru teach the method of claim 1. Although Sotiriou teaches utilizing a large language model to summarize previous support interactions, the reference does not explicitly state receiving survey data and training the large language model.
However, Lin teaches providing, to the support agent, a post-support survey, the post-support survey configured to obtain information about an effectiveness of the generated one or more summaries of the one or more previous support encounters; receiving, from the support agent, a response to the post-support survey; and updating the first large language model based on the post-support survey, wherein the updating comprises adjusting one or more weights of the first large language model (Lin: ¶44, ¶63, ¶67-69, ¶79-82, ¶88).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the feedback data and LLM training, as taught by Lin, into the system and method of Sotiriou, Hawes, and Mahindru. One of ordinary skill in the art would have been motivated to make this modification in order to “improve its accuracy and performance” (Lin: ¶69).
In regards to claim 13, Sotiriou, Hawes, and Mahindru teach the method of claim 1. Although Sotiriou teaches utilizing a large language model to summarize previous support interactions, the reference does not explicitly state receiving survey data and training the large language model.
However, Lin teaches providing, to the customer, a post-support survey, the post-support survey configured to obtain information about an effectiveness of the generated one or more summaries of the one or more previous support encounters; receiving, from the customer, a response to the post-support survey; and updating the first large language model based on the post-support survey, wherein the updating comprises adjusting one or more weights of the first large language model (Lin: ¶44, ¶63, ¶67-69, ¶79-82, ¶88).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the feedback data and LLM training, as taught by Lin, into the system and method of Sotiriou, Hawes, and Mahindru. One of ordinary skill in the art would have been motivated to make this modification in order to “improve its accuracy and performance” (Lin: ¶69).
In regards to claim 16, Sotiriou, Hawes, and Mahindru teach the system of claim 14. Additionally, the claim recites the same or similar limitations as those addressed above in claim 12 and therefore is rejected for the same reasons set forth above for claim 12. Furthermore, the rationale to combine the prior art set forth above for claim 12 applies to the rejection of claim 16.
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.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to WAYNE S MURRAY whose telephone number is (571)272-4306. The examiner can normally be reached M-F 8am-5pm.
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, Shannon Campbell can be reached at (571) 272-5587. 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.
/Wayne S. Murray/Examiner, Art Unit 3628
/SHANNON S CAMPBELL/Supervisory Patent Examiner, Art Unit 3628
Prosecution Insights