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 .
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.
Claims 1-16 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Claims 1, 7, and 13, Further claim 1 recites A computer implemented method for determining speaker effectiveness in conversations, the method comprising:
determining, at an analytics server, a sentiment transition (ST) score in a consecutive speaker turn pair in a conversation between a first speaker and a second speaker, wherein the ST score measures whether the sentiment transition from the first speaker to the second speaker is negative, neutral, or positive;
determining, at the analytics server, a semantic classification (SC) score in the speaker turn pair, wherein the SC score measures the relevance of utterances of the second speaker to the utterance of the first speaker; and
determining, at the analytics server, an empathy score for the second speaker in the speaker turn pair based on the ST score and the SC score.
Further claim 7 states A computing apparatus comprising:
a processor; and
a memory storing instructions that, when executed by the processor, configure the apparatus to:
The limitation of “determining…”, “determining …”, and “determining …” , as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, a person receiving a transcript where the person analyzes the transcript for a sentiment and sematic score. He does this by seeing how the two people interacted from their word choice as well as if they talked about the same topic. From this the individual would have a score for sematic transition and sematic classification where he would create some sort of logic gate for a final score.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claims recite an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claim only recites additional elements that are computer components “processor” (paragraph 14) and “memory” (paragraphs 14) recited at a high-level of generality such that it amounts no more than mere instructions to apply the exception using a generic computer component. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are directed to an abstract idea.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using the computer components amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The claims are not patent eligible.
Claims 2 and 8 additionally claim 2 recites the computer implemented method of claim 1, wherein the empathy score is determined to be high if the ST score is neutral or high, and the SC score is high. However, this limitation does not prevent a human from performing the steps mentally as described above. Further, the person creating his own logic gate system for the ST and SC score to get the empathy score. Similar to above, no additional limitations are provided that provide a practical application, or amount to significantly more than the abstract idea. Therefore, the claims are not patent eligible.
Claims 3 and 9 additionally claim 3 recites the computer implemented method of claim 2, wherein the empathy score is determined to be neutral if the ST score is neutral or positive and the SC score is neutral, or if the ST score is negative and the SC score is positive. However, this limitation does not prevent a human from performing the steps mentally as described above. Further, the person creating his own logic gate system for the ST and SC score to get the empathy score. Similar to above, no additional limitations are provided that provide a practical application, or amount to significantly more than the abstract idea. Therefore, the claims are not patent eligible.
Claims 4 and 10 additionally claim 4 recites the computer implemented method of claim 3, wherein the empathy score is determined to be negative if the empathy score is neither positive nor neutral. However, this limitation does not prevent a human from performing the steps mentally as described above. Further, the person creating his own logic gate system for the ST and SC score to get the empathy score. Similar to above, no additional limitations are provided that provide a practical application, or amount to significantly more than the abstract idea. Therefore, the claims are not patent eligible.
Claims 5, 11, and 15 additionally claim 5 recites the computer implemented method of claim 1, wherein the sentiment for at least one of the first speaker or the second speaker is determined based on at least one of: a transcript, tonal data, or video data of the utterance of the respective speaker. However, this limitation does not prevent a human from performing the steps mentally as described above. Further, the person analyzing the transcript to determine the empathy score. Similar to above, no additional limitations are provided that provide a practical application, or amount to significantly more than the abstract idea. Therefore, the claims are not patent eligible.
Claims 6, 12, and 16 additionally claim 6 recites the computer implemented method of claim 1, wherein determining at least one of: the sentiment, the ST score, the SC score, or the empathy score using an Artificial Intelligence and/or Machine Learning (AI/ML) model. However, this limitation does not prevent a human from performing the steps mentally as described above. Further, the person analyzing the transcript to determine the empathy score. In particular, the claim only recites additional elements that are computer components “Artificial Intelligence” (paragraph 8) and “Machine Learning” (paragraphs 8) recited at a high-level of generality such that it amounts no more than mere instructions to apply the exception using a generic computer component. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are directed to an abstract idea.
Claim 14 contains limitations similar to those found in claims 2, 3, and 4 and therefore are not patent eligible for the same reasons.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1, 5, 6, 7, 11, 12, 13, 15 and 16 are rejected under 35 U.S.C. 103 as obvious over US Patent US 20150195406 A1, (Dwyer; Michael C.) in view of US 20210366468 A1, (Rajeev; Harikrishnan.) in further view of US Patent US 20120296642 A1, (SHAMMASS; Sherrie.).
Claim 1, 7 , and 13
Regarding Claim 1, 7, and 13, Dwyer teach
1. A computer implemented method for determining speaker effectiveness in conversations, the method comprising:
determining, at an analytics server, a sentiment transition (ST) score in a consecutive speaker turn pair in a conversation between a first speaker and a second speaker, wherein the ST score measures whether the sentiment transition from the first speaker to the second speaker is negative, neutral, or positive;
(Paragraph 107 " In an example, a customer service quality package may provide a standard set of `instant insight` categories and scores to help measure the performance of agents and an associated contact center. The RT conversational analytics facility is relevant to a broad range of industries and includes a plurality of metrics, categories, scores, and the like. For instance, categories may include agent ownership, churn language, compliments, dissatisfaction, empathy, escalation, hold language, payment language, politeness, repeat contact, sales language, transfer language, understandability issues, and the like. Scores may include agent quality, customer satisfaction, emotion, and the like. Other metrics may include contact duration, percent silence, longest silence, tempo, word count, acoustic agitation, and the like."
Paragraph 146 "The RT conversational analytics facility may benefit applications, including increased sales, improved legal compliance, increased customer satisfaction, and the like, thus maximizing performance, such as in industry contact centers. For instance, the RT conversational analytics facility may enable increased contact center agent performance in real-time while calls are still ongoing, such as to ensure positive outcomes. The RT conversational analytics facility may optimize real-time agent performance with state-of-the-art speech technology, monitoring ongoing calls in the call center, sending critical real-time alerts to supervisors, providing timely next best action guidance to agents, and the like. From the supervisor user interface command post, supervisors may be provided a view of key events on calls in progress, such as including customer sentiment, escalation attempts, compliance violations, sales opportunities, and the like, where the command post may automatically prioritize high-value call events, giving supervisors the opportunity to adjust performance in real-time (e.g., by making a crucial adjustment to the progress of the call). Based on conversational flow between agents and customers, the call agent user interface assistant may produce timely, relevant information and pivotal guidance to agents. For example, constant feedback of customer agitation may keep agents mindful of talk-down opportunities. Procedural scripts, qualifying upsell offers, or context driven guidance, may be automatically offered at critical moments, ensuring agents follow correct procedures and stay compliant with complex regulations.")
Dwyer do not explicitly teach all of determining, at the analytics server, a semantic classification (SC) score in the speaker turn pair, wherein the SC score measures the relevance of utterances of the second speaker to the utterance of the first speaker; and
determining, at the analytics server, an empathy score for the second speaker in the speaker turn pair based on the ST score and the SC score.
However, Rajeev teaches determining, at the analytics server, a semantic classification (SC) score in the speaker turn pair, wherein the SC score measures the relevance of utterances of the second speaker to the utterance of the first speaker; and
(Paragraph 59 "As an example, focus score 122 may be determined by analyzing the words of a service representative and may reflect whether a service representative chose the appropriate words to be responsive to a customer's questions. For example, if the service representative selects incorrect words to respond to a question, then the response may be unresponsive, which lowers focus score 122. On the other hand, if the service representative selects words with the correct meanings to respond to the customer's question, then the response is considered responsive and focus score 122 increases. As another example, sentiment score 124 may be determined by evaluating the words of the customer. If the customer uses words with positive connotations, then sentiment score 124 may be higher to reflect that the customer is pleased with the service representative. On the other hand, if the customer uses words with negative connotations, then sentiment score 124 may be lower to reflect that the customer is not pleased with the service representative.")
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Dwyer to incorporate the teachings of Rajeev to provide a “determining, at the analytics server, a semantic classification (SC) score in the speaker turn pair, wherein the SC score measures the relevance of utterances of the second speaker to the utterance of the first speaker; and” Doing so would Measure how pleased the customer is, as recognized by Rajeev. (paragraph 58,59).
Dwyer in view of Rajeev do not explicitly teach all of determining, at the analytics server, an empathy score for the second speaker in the speaker turn pair based on the ST score and the SC score.
However, SHAMMASS teach
determining, at the analytics server, an empathy score for the second speaker in the speaker turn pair based on the ST score and the SC score.
(FIG 2 Shows the combining of the scores emotion analysis (202), dialog analysis (204 ), accent analysis (206) into a scoring engine to generate scores, further generating a singular score (210) based on multiple scores. Where the final score is the empathy score )
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Dwyer in view of Rajeev to incorporate the teachings of SHAMMASS to provide a “determining, at the analytics server, an empathy score for the second speaker in the speaker turn pair based on the ST score and the SC score.” Doing so would depict certain characteristics in the interaction, as recognized by SHAMMASS. (Paragraph 100).
Regarding Claim 7, Dwyer further teaches
7. A computing apparatus comprising:
a processor; and
(Paragraph 6 "In an aspect, a non-transitory computer readable medium with an executable program may provide a dynamic graphical representation of at least one of a category, a score, a sentiment, and an alert. The program may instruct a computer processor to perform at least the following steps: receiving a voice communication, analyzing the voice communication in at least near real-time relative to the receipt of the communication using a computer-based communications analytics facility for at least one of a language characteristic and an acoustic characteristic, determining at least one of the category, the score, the sentiment, and the alert associated with at least one participant in the voice communication using the at least one language and/or acoustic characteristic, and providing a dynamic graphical representation of the at least one category, score, sentiment, or alert through a graphical user interface. The dynamic graphical representation may be provided to a user other than the participant in the voice communication as the received voice communication is on-going. The user may be a non-participant in the voice communication and the dynamic graphical representation is provided to assist the non-participant in at least one of supervising and evaluating a participant in the voice communication. The dynamic graphical representation may be provided as feedback to a participant in the voice communication as the received voice communication is on-going. The acoustic characteristic may be at least one of a stress of words, an aggregated stress of a plurality of words, an agitation, a tempo, a change in tempo, an amount of silence, a silence between words, a gain in volume or energy of the words, a tone, an overtalk, a time lag between words, a time dependency between key words and phrases, an inter-word timing, an inflexion of words, and a temporal pattern. The language characteristic may be at least one of a category, a sentiment, a regulation compliance, a score, a text, an alternative text, a presence or absence of specific language, and a confidence in word match. The steps may further include repeating the steps for a plurality of in-progress voice communications, and displaying a dynamic graphical representation of each in-progress voice communication on the graphical user interface. The steps may further include assigning metadata representative of the voice communication based on the analysis, and displaying the metadata for the voice communication on the graphical user interface. Metadata representative of the voice communication may include at least one of a speaker, an agent data, an agent grouping, a call handling location, a time and date of call, a department, a skill or queue, a pertinent IVR path data, and a call length. The steps may further include before analyzing the voice communication for the at least one language characteristic, converting the voice communication to text using computer-based speech recognition. The analysis for the presence or absence of specific language may include identifying whether a required statement has been spoken within a specific time period. The required statement may be a disclosure to a participant that satisfies a legal requirement, identifying the use of profanity, or identifying the absence of compliance scripts.")
a memory storing instructions that, when executed by the processor, configure the apparatus to:
(Paragraph 6 "In an aspect, a non-transitory computer readable medium with an executable program may provide a dynamic graphical representation of at least one of a category, a score, a sentiment, and an alert. The program may instruct a computer processor to perform at least the following steps: receiving a voice communication, analyzing the voice communication in at least near real-time relative to the receipt of the communication using a computer-based communications analytics facility for at least one of a language characteristic and an acoustic characteristic, determining at least one of the category, the score, the sentiment, and the alert associated with at least one participant in the voice communication using the at least one language and/or acoustic characteristic, and providing a dynamic graphical representation of the at least one category, score, sentiment, or alert through a graphical user interface. The dynamic graphical representation may be provided to a user other than the participant in the voice communication as the received voice communication is on-going. The user may be a non-participant in the voice communication and the dynamic graphical representation is provided to assist the non-participant in at least one of supervising and evaluating a participant in the voice communication. The dynamic graphical representation may be provided as feedback to a participant in the voice communication as the received voice communication is on-going. The acoustic characteristic may be at least one of a stress of words, an aggregated stress of a plurality of words, an agitation, a tempo, a change in tempo, an amount of silence, a silence between words, a gain in volume or energy of the words, a tone, an overtalk, a time lag between words, a time dependency between key words and phrases, an inter-word timing, an inflexion of words, and a temporal pattern. The language characteristic may be at least one of a category, a sentiment, a regulation compliance, a score, a text, an alternative text, a presence or absence of specific language, and a confidence in word match. The steps may further include repeating the steps for a plurality of in-progress voice communications, and displaying a dynamic graphical representation of each in-progress voice communication on the graphical user interface. The steps may further include assigning metadata representative of the voice communication based on the analysis, and displaying the metadata for the voice communication on the graphical user interface. Metadata representative of the voice communication may include at least one of a speaker, an agent data, an agent grouping, a call handling location, a time and date of call, a department, a skill or queue, a pertinent IVR path data, and a call length. The steps may further include before analyzing the voice communication for the at least one language characteristic, converting the voice communication to text using computer-based speech recognition. The analysis for the presence or absence of specific language may include identifying whether a required statement has been spoken within a specific time period. The required statement may be a disclosure to a participant that satisfies a legal requirement, identifying the use of profanity, or identifying the absence of compliance scripts.")
Regarding Claim 13, Dwyer further teaches
A non-transitory computer-readable storage medium, the computer-readable storage medium including instructions that when executed by a computer, cause the computer to:
(Paragraph 6 "In an aspect, a non-transitory computer readable medium with an executable program may provide a dynamic graphical representation of at least one of a category, a score, a sentiment, and an alert. The program may instruct a computer processor to perform at least the following steps: receiving a voice communication, analyzing the voice communication in at least near real-time relative to the receipt of the communication using a computer-based communications analytics facility for at least one of a language characteristic and an acoustic characteristic, determining at least one of the category, the score, the sentiment, and the alert associated with at least one participant in the voice communication using the at least one language and/or acoustic characteristic, and providing a dynamic graphical representation of the at least one category, score, sentiment, or alert through a graphical user interface. The dynamic graphical representation may be provided to a user other than the participant in the voice communication as the received voice communication is on-going. The user may be a non-participant in the voice communication and the dynamic graphical representation is provided to assist the non-participant in at least one of supervising and evaluating a participant in the voice communication. The dynamic graphical representation may be provided as feedback to a participant in the voice communication as the received voice communication is on-going. The acoustic characteristic may be at least one of a stress of words, an aggregated stress of a plurality of words, an agitation, a tempo, a change in tempo, an amount of silence, a silence between words, a gain in volume or energy of the words, a tone, an overtalk, a time lag between words, a time dependency between key words and phrases, an inter-word timing, an inflexion of words, and a temporal pattern. The language characteristic may be at least one of a category, a sentiment, a regulation compliance, a score, a text, an alternative text, a presence or absence of specific language, and a confidence in word match. The steps may further include repeating the steps for a plurality of in-progress voice communications, and displaying a dynamic graphical representation of each in-progress voice communication on the graphical user interface. The steps may further include assigning metadata representative of the voice communication based on the analysis, and displaying the metadata for the voice communication on the graphical user interface. Metadata representative of the voice communication may include at least one of a speaker, an agent data, an agent grouping, a call handling location, a time and date of call, a department, a skill or queue, a pertinent IVR path data, and a call length. The steps may further include before analyzing the voice communication for the at least one language characteristic, converting the voice communication to text using computer-based speech recognition. The analysis for the presence or absence of specific language may include identifying whether a required statement has been spoken within a specific time period. The required statement may be a disclosure to a participant that satisfies a legal requirement, identifying the use of profanity, or identifying the absence of compliance scripts.")
Claim 5, 11 , and 15
Regarding Claim 5, 11, and 15, Dwyer further teaches
5. The computer implemented method of claim 1, wherein the sentiment for at least one of the first speaker or the second speaker is determined based on at least one of: a transcript, tonal data, or video data of the utterance of the respective speaker.
(paragraph 82 "The present disclosure describes a real-time (RT) conversational analytics facility that provides conversational analytics and real-time, or near real-time monitoring of communications from multiple channels, such as phone calls, chats, text messaging, blog posts, social media posts, surveys, IVR, e-mails, and the like, and may provide for facilities that enable increased performance for individuals involved in live conversational support functions (e.g. enterprise customer support call center employees). Real-time or near real-time may indicate that the system processes the conversations as they are received in order to provide an output, such as immediate feedback, during the conversation as it is proceeding. Processing may be on the order of seconds, milliseconds, and the like. The real-time (RT) conversational analytics facility enables automatically evaluating in real-time or near real-time every communication (of heterogeneous types (e.g., voice, phone call [either to the call center or direct dialed to an agent], voicemail, chat, e-mail, blog, survey, Facebook, Twitter, Google+, other social channels, IVR, etc.) related to an activity, such as an activity of an enterprise, including in-progress calls, for sentiment/acoustics, categorization, and performance scoring, including the presence or absence of specific language or acoustic characteristics, utilizing acoustic and conversational analysis to convert communications to a text format for inclusion in a single database repository that includes fields for data relating to, at least, speech analysis/audio mining of spoken communications. The communications may be routed to a centralized host or handled by distributed computing systems in various embodiments disclosed herein or via a cloud-based system. The raw, unstructured data of recorded or real-time conversations is converted into consumable, structured data. Audio conversations are ingested by the system along with call metadata and speech-to-text transcription is performed to generate a transcript that is analyzed using a set of linguistic and acoustic rules to look for certain key words, phrases, topics, and acoustic characteristics. Along with the call metadata, these conversational and acoustic events allow the system to categorize and annotate the calls. In turn, the categories and events are incorporated into scores for each call, which can be used for automatically monitoring customer satisfaction, compliance, agent performance, and any number of customizable performance indicators.")
Claim 6, 12 , and 16
Regarding Claim 6, 12, and 16, Rajeev further teaches
The computer implemented method of claim 1, wherein determining at least one of: the sentiment, the ST score, the SC score, or the empathy score using an Artificial Intelligence and/or Machine Learning (AI/ML) model.
(Paragraph 58 "The output of bi-directional attention layer 310 may be sent to multi-task model 312. Multi-task model 312 analyzes the predicted meaning of words and/or phrases in text file 120 to produce focus score 122 and sentiment score 124. Multi-task model 312 is trained to predict focus score 122 and sentiment score 124 in a singular model rather than with separate models. In this way, commonalities and different across these two tasks can be exploited to improve the efficiency of predicting focus score 122 and sentiment score 124. As discussed previously, focus score 122 indicates how attentive a person was to another person during a conversation. The more attentive the person is, the higher the score. Using the example of FIG. 1, the more attention the service representative is to the customer, the higher the focus score 122 for the service representative. Additionally, sentiment score 124 indicates how pleased one person is with the other during the conversation. The more pleased a person is with the other person in a conversation, the higher sentiment score 124 will be. Using the example of FIG. 1, sentiment score 124 may measure how pleased a customer is with the service representative."
Paragraph 36 "Language proficiency analyzer 108 combines focus score 122, sentiment score 124, and fluency score 126 to produce a performance score 128. Performance score 128 may be any suitable combination of focus score 122, sentiment score 124, and/or fluency score 126. For example, performance score 128 may be a weighted average of focus score 122, sentiment score 124, and/or fluency score 126. Generally, the higher performance score 128 is, the more proficient user 102A or 102B is in a particular language. In certain embodiments, performance score 128 may be used to evaluate the language proficiency of a user 102A or 102B and to further improve the language proficiency of the user 102A or 102B.")
See claim one for rationale.
Claims 2, 3, 4, 8, 9, 10, 14 are rejected under 35 U.S.C. 103 as obvious over US Patent US 20150195406 A1, (Dwyer; Michael C.) in view of US 20210366468 A1, (Rajeev; Harikrishnan.) in view of US Patent US 20120296642 A1, (SHAMMASS; Sherrie.) in view of US Patent US 20220319535 A1, (CHAWLA; Mohit) in further view of Yang, Zhou, et al. "Exploiting emotion-semantic correlations for empathetic response generation." Findings of the Association for Computational Linguistics: EMNLP 2023. 2023.
Claim 2 and 8
Regarding Claim 2 and 8, Dwyer in view of Rajeev in further view of SHAMMASS do not explicitly teach all of 2. The computer implemented method of claim 1, wherein the empathy score is determined to be high if the ST score is neutral or high, and the SC score is high.
However, CHAWLA teach 2. The computer implemented method of claim 1, wherein the empathy score is
(Paragraph 48 "The customer system may calculate the empathy score based on the emotion score, the intent score, and the sentiment score. The empathy score may provide an indication of whether one of the plurality of speakers, associated with the empathy score, is empathetic, neutral, or non-empathetic. The customer system may determine an empathy score for each speaker segment, of the plurality of speaker segments, in a manner similar to that described above.")
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Dwyer in view of Rajeev in further view of SHAMMASS to incorporate the teachings of CHAWLA to provide a “2. The computer implemented method of claim 1, wherein the empathy score is.” Doing so would Cause a reward to be implemented, as recognized by CHAWLA. (paragraph 49).
Dwyer in view of Rajeev in view of SHAMMASS in further view of CHAWLA do not explicitly teach all determined to be high if the ST score is neutral or high, and the SC score is high.
However, Yang teaches determined to be high if the ST score is neutral or high, and the SC score is high.
(page 4830 right col section 3.5 Emotion and Response Predicting "Similarly, we use the same structure to construct an aggregation attention network about the correlations and obtain emotion probabilities Pecor ∈ Rd e. Weadd the two types of emotion probabilities together as the overall emotion probability Pe ∈ Rd e. Pe =Pe ctx +Pe cor (15)" equation 15 shows the relationship between ST and SC where if there both high than the final score will be high)
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Dwyer in view of Rajeev in view of SHAMMASS in further view of CHAWLA to incorporate the teachings of Yang to provide a “determined to be high if the ST score is neutral or high, and the SC score is high.” Doing so would Have better empathetic responses, as recognized by Yang. (section 3.5 Emotion and Response Predicting).
Claim 3 and 9
Regarding Claim 3 and 9, CHAWLA further teaches teach
The computer implemented method of claim 2, wherein the empathy score
(Paragraph 48 "The customer system may calculate the empathy score based on the emotion score, the intent score, and the sentiment score. The empathy score may provide an indication of whether one of the plurality of speakers, associated with the empathy score, is empathetic, neutral, or non-empathetic. The customer system may determine an empathy score for each speaker segment, of the plurality of speaker segments, in a manner similar to that described above.")
See claim two for rationale.
YANG further teaches teach
determined to be neutral if the ST score is neutral or positive and the SC score is neutral, or if the ST score is negative and the SC score is positive.
(page 4830 right col section 3.5 Emotion and Response Predicting "Similarly, we use the same structure to construct an aggregation attention network about the correlations and obtain emotion probabilities Pecor ∈ Rd e. Weadd the two types of emotion probabilities together as the overall emotion probability Pe ∈ Rd e. Pe =Pe ctx +Pe cor (15)" equation 15 shows the relationship between ST and SC where if either is high and low then it would be neutral as they offset)
See claim two for rationale.
Claim 4 and 10
Regarding Claim 4 and 10, CHAWLA further teaches teach
The computer implemented method of claim 3, wherein the empathy score is
(Paragraph 48 "The customer system may calculate the empathy score based on the emotion score, the intent score, and the sentiment score. The empathy score may provide an indication of whether one of the plurality of speakers, associated with the empathy score, is empathetic, neutral, or non-empathetic. The customer system may determine an empathy score for each speaker segment, of the plurality of speaker segments, in a manner similar to that described above.")
See claim two for rationale.
YANG further teaches teach
determined to be negative if the empathy score is neither positive nor neutral.
(page 4830 right col section 3.5 Emotion and Response Predicting "Similarly, we use the same structure to construct an aggregation attention network about the correlations and obtain emotion probabilities Pecor ∈ Rd e. Weadd the two types of emotion probabilities together as the overall emotion probability Pe ∈ Rd e. Pe =Pe ctx +Pe cor (15)" equation 15 shows the relationship between ST and SC where if the both scores are low then overall score will also be low)
See claim two for rationale.
Claim 14 contains limitations similar to those found in claims 2, 3, and 4 and therefore are not patent eligible for the same reasons.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ALI M HASSAN whose telephone number is (571)272-5331. The examiner can normally be reached Monday - Friday 8:00am - 4:00pm.
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, Paras Shah can be reached at (571)270-1650. 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.
/ALI M HASSAN/Examiner, Art Unit 2653
/Paras D Shah/Supervisory Patent Examiner, Art Unit 2653
11/28/2025