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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 12/04/2025 has been entered.
Response to Amendment
Claims 1-6, 10-15, and 18-19 are amended. Claims 1-6 and 8-21 are presented for examination.
Response to Arguments
Rejection under 35 U.S.C. 103
Applicant’s arguments have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1, 3, 5, 9-10, 12, 14, 16, and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Konam et al. (US 20230334263 A1; hereinafter referred to as Konam) in view of Annadi et al. (US 20240303431 A1; hereinafter referred to as Annadi), Gangadharaiah et al. (US 10860629 B1; hereinafter referred to as Gangadharaiah), and Higgins et al. (US 20220210033 A1; hereinafter referred to as Higgins).
Regarding claim 1, Konam teaches: an intelligent virtual assistant system, comprising: one or more processors coupled to a memory that stores instructions that, when executed by the one or more processors ([0006] a system including a processor and a memory), cause the one or more processors to: generate a generic entity placeholder for one or more aspects in a set of transcripts of historical interactions ([0066] Each template 315 may define a known category of action item and the data used to complete that action item. For example, categories of action items can include “contact other participant,” “contact non-participant party,” “confirm adherence to plan,” or the like that can be further developed based on standard follow-up actions in the user's environment and role in the environment. Various users can develop and specify what data each template 315 specifies to have filled in, when those data need to be provided, and divisions between the various templates 315. The generic entity placeholders can be the data to be filled in for a template) between one or more customers, one or more customer service agents ([0025] a first party 110a (generally or collectively, party 110) is holding a conversation 120 with a second party 110b. The conversation 120 is spoken aloud and includes several utterances 122a-e (generally or collectively, utterances 122) spoken by the first party 110a and by the second party 110b in relation to a healthcare visit. As shown in the example scenario, the first party 110a is a patient and the second party 110b is a caregiver (e.g., a doctor, nurse, nurse practitioner, physician's assistant, etc.). Although two parties 110 are shown in FIG. 1, in various embodiments, more than two parties 110 may contribute to the conversation), and one or more data stores ([0076] the action-item creator 300 may query a supplemental data source 370 via the network interface 350 to supply missing data, or combinations thereof);
identify a data retrieval action of a customer service agent ([0066-0067] The data to include in an action item, and relevant intents behind an action item, may be defined in various templates 315 included in the template database 310… Some examples of templates 315 can include record updates, referrals, reminders, queries, confirmations, inventory orders, calendar entries, and the like, each of which may be identified via different contexts and intents from the conversation, and may request different data from the conversation) in one or more transcripts in the set of transcripts ([0023] One element extracted from a transcript can be a follow-up action item. Extracting an action item from a transcript can include determining the identification of a party to perform the action and an identity of the action to perform);
add reference information associated with the data retrieval action in the one or more transcripts… ([0053] The analysis system 230 may include an augmenter 236 that operates in conjunction with the extractor 232 to develop supplemental content 235c to provide with the transcript 225. In various embodiments, the supplemental content 235c can include callouts of pseudo-key terms based on inferred or omitted details from a conversation, hyperlinks between key points and semantically relevant segments of the transcript, links to (or provides the content for) supplemental or definitional information to display with the transcript);
wherein the second language model ([0005] various Machine Learning Models (MLM) trained to convert spoken utterances to written transcripts and summaries of those transcripts as part of a Natural Language Processing (NLP) system. Various action items can be identified for different parties to the conversation from the transcript (and non-party entities), which differ based on the role of the party in the conversation. The MLMs supplement the data identified from the conversation with data from supplemental data sources that may be used to contextually fill in missing information from the conversation) is configured to: generate a response template ([0061] identify various action items to follow up on based on a conversation and the information included or omitted therefrom. The action-item creator 300 includes a template database 310 that defines templates 315 for various action items and the data used in fulfilling the action items) with one or more generic entity placeholders and reference information ([0072] the action-item creator 300 can expand the information available from the conversation to fill in the data elements with using various external sources, and may leave some elements blank (or later update the values thereof) as time progresses and new data become available. An element that can be updated later is a placeholder.);
and generate a predicted response ([0064] the action-item creator 300 uses the action-item identifier 330 to analyze the underlying intent of various segments of the conversation. Accordingly, by using the intent of the utterance, the system is able to analyze natural speech patterns to extract action items from a conversation, and identify supplemental data sources to quickly and accurately cure ambiguities and omissions from the conversation used to complete the generation or execution of the action items) using the reference information to populate the one or more generic entity placeholders in the response template… ([0076] the action-item creator 300 attempts to fill in the template 315 with relevant data from the transcript 225. The action-item creator 300 initially uses the action-item identifier 330 to attempt to retrieve the associated data from the transcript 225; however, as the conversation may omit or leave ambiguous various data, the action-item creator 300 may query the user via the UI API 320 to resolve ambiguities or supply missing data, the action-item creator 300 may query a supplemental data source 370 via the network interface 350 to supply missing data, or combinations thereof).
Konam does not explicitly, but Annadi teaches: apply self-supervised learning ([0072] the natural language sequence generator 116 represents uses a language model, such as a trained UMLFit or Bidirectional Encoder Representation from Transformers (BERT) model to generate language that is most likely to lead to a positive satisfaction score… BERT model is self-supervised and can be trained offline) based on the one or more transcripts in an offline training phase to produce a second language model from a pre-trained language model… ([0031] in addition or alternative to pre-training on generic documents to understand natural language or sentiment, particular model aspects are fine-tuned on transcript documents between customer service agents and customers, unlike existing language models. In this way, these models understand natural language or sentiment at a deeper level).
Konam and Annadi are considered analogous in the field of dialog processing. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Konam to combine the teachings of Annadi because doing so would allow for the use of pre-trained models, like BERT, for training and fine-tuning an assistant system on past historic dialogs to improve future responses from the assistant system (Annadi [0081] the user call transcripts 130 are used by the natural language utterance attributor 112, the satisfaction score 114, and/or the natural language sequence generator 116 in order to perform their corresponding functionalities. Specifically, for example, such call transcripts 130 can be fed into a model to fine-tune the model to perform such functionalities after it has initially pre-trained on the natural language corpus 132. In some embodiments, such fine-tuning is preceded by labeling each of the call transcripts 130 with corresponding labels in preparation for training).
The combination of Konam and Annadi does not explicitly, but Gangadharaiah teaches: and apply reinforcement learning in an online training phase to produce a third language model from the second language model ([col 3, lines 4-8] Embodiments disclosed herein can utilize aspects of both SL and RL type approaches to implement highly-accurate task-oriented dialog systems. Embodiments can provide additional rewards at every turn of the dialog, that depend on the final goal state) that maximizes a reward ([col 3,lines 6-15] Embodiments can provide additional rewards at every turn of the dialog, that depend on the final goal state. Embodiments can use SL type techniques to learn embeddings (or real valued representations) of dialog history, at each turn of the dialog, offline without the need for additional human annotation. Embodiments can add a reward term to the negative cross entropy at each turn that measures the deviation of the predicted next state learned embedding from the final state embedding for that dialog) based on received customer input and similarity between a response provided by a customer service agent and the predicted response generated by the second language model ([col 4, lines 45-56] the chatbot system 114 may generate one or more candidate responses (e.g., one response, five diverse responses, etc.) given the dialog history. The agent 104 can then select or modify one of these responses, or type a completely different response if the responses are unsatisfactory. In some embodiments, the chatbot system 114 uses nearest neighbor-based techniques to retrieve agent responses corresponding to the most similar dialog state from the training data. To identify similar dialog states, embodiments create and use an embedding (or representation) of dialog history in a space where Euclidean distances can be used. The response provided by a customer service agent is in the training data.).
Konam, Annadi, and Gangadharaiah are considered analogous in the field of dialog processing. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Konam and Annadi to combine the teachings of Gangadharaiah because doing so would improve the performance of a virtual assistant in multi-turn task dialogs by maximizing a reward based on previous dialog history to improve generated responses (Gangadharaiah [col 7, lines 61-67] embodiments can improve chatbot performance in such multi-turn task-oriented dialogs via the learning of embeddings and tracking how these approached final/end goals during the course of a dialog. Moreover, embodiments can use historical dialogs while the representation learning of state and action spaces can beneficially be completely unsupervised).
The combination of Konam, Annadi, and Gangadharaiah does not explicitly, but Higgins teaches: deploy the third language model ([0138] input data 1010 (e.g., a user input as part of a two-way communication) is received. In some examples, the user input is text data, but in other examples, the user input can be any such data, including voice data, voice data that is converted to text data, and structured output data from a natural language processing system. A plurality of bots 1020, shown as bot A 1020A, bot B 1020B, bot C 1020C, and bot D 1020D are then queried for confidence scores. The confidence scores provided by the bots are independent (e.g., heterogeneous) representations of each bot's response to the input data. The third language model can be a type of bot.) to respond to a subset of live user input ([0129] The feedback may be reflective of how well the bot identified the intent and/or handled the request expressed by the user on the network device), wherein the subset of live user input is determined based on a particular type of user input ([0116] The intent determination engine 827 may further be configured to, in conjunction with the processor 810, determine an intent for the conversation. The intent may be determined from the request. For example, the request may state, “I want my order status.” The intent may be extracted from the request as “order_status”);
compute a performance score of the third language model ([0134] intelligent routing system 925 may evaluate the content (e.g., text, audio clips, images, emoticons, or other suitable content) included in the received message using a trained machine-learning model to identify an intent. The input data (e.g., communication text and/or intent data) can be sent to available bots to receive confidence scores, and intelligent routing system 925 can then calibrate the received confidence scores) based on one or more feedback signals associated with the subset of live user input ([0129] Feedback module 831 may be configured to, in conjunction with the processor 810, receive feedback on the conversation… at the end of a conversation, the feedback module 831 may transmit, to the network device utilized by a user, a request to provide feedback with regard to its conversation with the bot and/or live agent. This request may be provided in the form of a survey, through which the user may indicate its sentiment with regard to the conversation, as well as provide a performance evaluation of the bot and/or live agent);
and adjust a size of the subset of live user ([0130] machine learning engine 835 may be configured to, in conjunction with the processor 810, feed the conversation, identified intent, and provided feedback into a database and analyze the data to draw inferences about how well a type of bot and/or live agent handled the conversation. This data, along with other historical conversation data and feedback, may be used to build a model that may be used to determine a future intent associated with one or more future requests. For example, if a particular type of bot successfully handled an “order_status” intent to the satisfaction of a user, future “order_status” intents may also be transferred to a bot of the particular type) input based on the performance score of the third language model ([0130] if a particular type of bot unsuccessfully handled an intent to the dissatisfaction of the user, future intents similar to the aforementioned intent may be transferred to a terminal device in order for these future intents to be handled by a live agent or to another type of bot that may be better suited to handle the intent based on a confidence score for the other type of bot and calculated based on the intent).
Konam, Annadi, Gangadharaiah, and Higgins are considered analogous in the field of dialog processing. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Konam, Annadi, and Gangadharaiah to combine the teachings of Higgins because doing so would allow for the input that a chatbot receives to be adjusted based on the performance of the chatbot, leading to improved chatbot responses to user inputs (Higgins [0144] bot mappers can be dynamically updated using real-time feedback data at the same time that the bot mappers are being used to calibrate scores for new user inputs that are received by the system. The new user inputs are then assessed to select bots for the new user inputs, and feedback from those communications is similarly feed back into bot score mapper training (e.g., as modifications to adjustments of standardized scores associated with particular user inputs) to improve system operation by improving selection of bots used to resolve customer issues).
Regarding claim 3, the combination of Konam, Annadi, Gangadharaiah, and Higgins teaches: the intelligent virtual assistant system of claim 1. Konam further teaches: wherein the data retrieval action of the customer service agent comprises one of document retrieval, data access, or application access ([0076] Once the action-item creator 300 has identified the action items to create for a given entity, the action-item creator 300 attempts to fill in the template 315 with relevant data from the transcript 225. The action-item creator 300 initially uses the action-item identifier 330 to attempt to retrieve the associated data from the transcript 225… the action-item creator 300 may query a supplemental data source 370 via the network interface 350 to supply missing data, or combinations thereof), and wherein the reference information comprises one of a document path, file name, or application ([0078] supplemental data refers to data obtained outside of the transcript 225 of the conversation, which may include data provided by a user in response to a query via the UI API 320, data provided by a source under the control of a participant of the conversation (e.g., a database or configuration file with user preferences and user-maintained records) via the network interface 350).
Regarding claim 5, the combination of Konam, Annadi, Gangadharaiah, and Higgins teaches: the intelligent virtual assistant system of claim 1. Annadi further teaches: wherein the instructions further cause the one or more processors to: detect one or more errors that fail to satisfy a predetermined performance threshold… ([0117] and responsive to the customer service agent utterance, a customer may utter “wow finally, I've been on hold for a long time . . . ” which node 606 represents. In some embodiments, and as described herein, in response to the natural language utterance detector 102 detecting this utterance, the natural language utterance attributor 112 attributing this phrase to a customer, the satisfaction scorer 114 may determine a score indicative of the customer satisfaction being low or below a threshold).
Gangadharaiah further teaches: based on historical customer input and comparison of the predicted response with the response provided by the customer service agent ([col 16, lines 3-9] The ML model evaluator 628 can then compare the outputs of the machine learning model to the expected outputs, and determine one or more quality metrics of the machine learning model being trained based on the comparison (e.g., the error rate can be a difference or distance between the machine learning model outputs and the expected outputs));
and initiate additional offline updating ([col 4, lines 62-67] Such training of a ML model can be part of an overall “offline” phase 300 used in some embodiments that is represented in FIG. 3, which is a diagram illustrating exemplary operations of an offline phase for implementing a multi-turn task-based dialog system using a goal-oriented model according to some embodiments) of the pre-trained language model ([col 16, lines 28-41] the user, via the user device 602, can transmit a request to the model training system 620 to modify the machine learning model being trained (e.g., transmit a modification request). The request can include a new or modified container image, a new or modified algorithm, new or modified hyperparameter(s), and/or new or modified information describing the computing machine on which to train a machine learning model. The model training system 620 can modify the machine learning model accordingly. For example, the model training system 620 can cause the virtual machine instance 622 to optionally delete an existing ML training container 630, create and initialize a new ML training container 630 using some or all of the information included in the request).
Konam, Annadi, Gangadharaiah, and Higgins are considered analogous in the field of dialog processing. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Konam, Annadi, Gangadharaiah, and Higgins to further combine the teachings of Gangadharaiah because doing so would allow for a language model to be updated to reduce errors based on response data, improving future response generation from an assistant system (Gangadharaiah [col 16, lines 3-9] The ML model evaluator 628 can then compare the outputs of the machine learning model to the expected outputs, and determine one or more quality metrics of the machine learning model being trained based on the comparison (e.g., the error rate can be a difference or distance between the machine learning model outputs and the expected outputs)).
Regarding claim 9, the combination of Konam, Annadi, Gangadharaiah, and Higgins teaches: the intelligent virtual assistant system of claim 1. Gangadharaiah further teaches: wherein the instructions further cause the one or more processors to update the second language model online based on customer service agent feedback ([col 7, lines 17-23] at block 427, in some embodiments the ultimately selected agent utterance (from a set of candidate utterances) or edited utterance or agent -composed utterance (which may not even be based on any recommended utterance) is provided back to the chatbot system 114 for use in later online phase analysis). Agent utterance can be considered feedback and used as a future suggestion.).
Regarding claim 10, it recites similar limitations as claim 1 and therefore is rejected similarly.
Regarding claim 12, it recites similar limitations as claim 3 and therefore is rejected similarly.
Regarding claim 14, it recites similar limitations as claim 5 and therefore is rejected similarly.
Regarding claim 16, the combination of Konam, Annadi, Gangadharaiah, and Higgins teaches: the computer-implemented method of claim 10. Gangadharaiah further teaches: receiving, by the one or more computing devices, a request to update the third language model when a new product or feature is released ([col 16, lines 28-35] can transmit a request to the model training system 620 to modify the machine learning model being trained (e.g., transmit a modification request). The request can include a new or modified container image, a new or modified algorithm, new or modified hyperparameter(s), and/or new or modified information describing the computing machine on which to train a machine learning model);
and initiating, by the one or more computing devices, further updating of the third language model to enable the third language model to be responsive to inquiries regarding the new product or feature ([col 29, lines 32-40] The data store 1010 is operable, through logic associated therewith, to receive instructions from the application server 1008 and obtain, update, or otherwise process data in response thereto. In one example, a user might submit a search request for a certain type of item. In this case, the data store 1010 might access the user information 1016 to verify the identity of the user and can access a production data 1012 to obtain information about items of that type).
Regarding claim 18, it recites similar limitations as claim 1 and therefore is rejected similarly.
Claims 2 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over Konam in view of Annadi, Gangadharaiah, and Higgins, as applied to claims 1, 3, 5, 9-10, 12, 14, 16, and 18 above, and further in view of Bhatnagar et al. (US 20230134796 A1; hereinafter referred to as Bhatnagar).
Regarding claim 2, the combination of Konam, Annadi, Gangadharaiah, and Higgins teaches: the intelligent virtual assistant system of claim 1. The combination of Konam, Annadi, Gangadharaiah, and Higgins does not explicitly, but Bhatnagar teaches: wherein the generic entity placeholder for the one or more aspects in the set of transcripts of historical interactions comprises a tag configured to replace one of a customer-specific entity or a conversation-specific entity ([0029] The personal information removing module 320 may replace sensitive information with tags. The personal information to remove may include but is not limited to names, email addresses, addresses, credit card numbers, date of birth, URLs, phone numbers, username and password combinations, social media usernames, Social Security Numbers, Tax numbers, Driver license numbers, or any information that is sensitive or personal. The personal information removing module 320 may replace the personal information with a placeholder. For example, names may be replaced with a tag “[NAME]” or alternatively with fake names).
Konam, Annadi, Gangadharaiah, Higgins, and Bhatnagar are considered analogous in the field of dialog processing. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Konam, Annadi, Gangadharaiah, and Higgins to combine the teachings of Bhatnagar because doing so would allow for the generation of specific training data for an assistant system by using tags to label specific entities in transcripts, leading to improved predicted responses from a trained language model (Bhatnagar [0006] The disclosed named entity recognition system provides multiple advantageous technical features for efficient analysis of textual data… The training dataset also helps to train the machine learning model to make accurate predictions because the training dataset is generated based on a comprehensive guide with a set of well-developed and appropriate labels. Moreover, the named entity recognition system provides a user interface through which a user may view labeled texts and highlighted keywords for a more efficient information extraction and decision making process).
Regarding claim 11, it recites similar limitations as claim 2 and therefore is rejected similarly.
Claims 4, 13, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Konam in view of Annadi, Gangadharaiah, and Higgins, as applied to claims 1, 3, 5, 9-10, 12, 14, 16, and 18 above, and further in view of Da Jornada et al. (US 20230370393 A1; hereinafter referred to as Da Jornada).
Regarding claim 4, the combination of Konam, Annadi, Gangadharaiah, and Higgins teaches: the intelligent virtual assistant system of claim 1. The combination of Konam, Annadi, Gangadharaiah, and Higgins does not explicitly, but Da Jornada teaches: wherein the one or more feedback signals comprises at least one of the response provided by the customer service agent, selection of the predicted response, or a rating of the predicted response ([0042] user feedback 290 from the agent device 280 may be employed in a feedback manner by the supervised machine learning training process 220 to update the trained machine learning model 250. For example, the user feedback 290 may comprise implicit feedback derived from an acceptance by a customer service agent of one or more predicted message responses 270 (e.g., by selecting one or more of the recommended alternative responses when composing a response), or based on how often a customer service agent accepts at least one recommended alternative response).
Konam, Annadi, Gangadharaiah, Higgins, and Da Jornada are considered analogous in the field of dialog processing. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Konam, Annadi, Gangadharaiah, and Higgins to combine the teachings of Da Jornada because doing so would allow for specific feedback for predicted responses to be gathered from customer service agents, leading to improved predicted responses from an assistant system model by retraining the model to incorporate the feedback (Da Jornada [0042] implicit feedback derived from an acceptance by a customer service agent of one or more predicted message responses 270 (e.g., by selecting one or more of the recommended alternative responses when composing a response), or based on how often a customer service agent accepts at least one recommended alternative response. The user feedback 290 may be employed, for example, to determine when and/or how to retrain the trained machine learning model 250).
Regarding claim 13, it recites similar limitations as claim 4 and therefore is rejected similarly.
Regarding claim 19, it recites similar limitations as claim 4 and therefore is rejected similarly.
Claims 6, 15, and 21 are rejected under 35 U.S.C. 103 as being unpatentable over Konam in view of Annadi, Gangadharaiah, and Higgins, as applied to claims 1, 3, 5, 9-10, 12, 14, 16, and 18 above, and further in view of Kannan et al. (US 20120130771 A1; hereinafter referred to as Kannan).
Regarding claim 6, the combination of Konam, Annadi, Gangadharaiah, and Higgins teaches: the intelligent virtual assistant system of claim 1. The combination of Konam, Annadi, Gangadharaiah, and Higgins does not explicitly, but Kannan discloses: wherein the set of transcripts is selected from a subset of customer service agents ([0127] The agent performance model can also be used to identify chats that scored best in each of the attributes important to the customer. This, in turn, can be used to build "Best-in-class" knowledge bases) that qualify as high-performing customer service agents based on at least one of experience, recommendation, or evaluation ([0118] The model for each of the attributes identified in the chat transcript (see above) is built based, not on subjective measures, but actually based on customer votes. For example, a text mining model to understand what are features of a conversation that best represent an issue being resolved for a customer is learned by the model from historical chat transcripts, where the customer actually voted that they felt that the quality of resolution was high).
Konam, Annadi, Gangadharaiah, Higgins, and Kannan are considered analogous in the field of dialog processing. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Konam, Annadi, Gangadharaiah, and Higgins to combine the teachings of Kannan because doing so would allow for the language model to identify agent transcripts that represent high quality interactions and use those as part of the training process, leading to improved predicted responses from an assistant system (Kannan [0118] a text mining model to understand what are features of a conversation that best represent an issue being resolved for a customer is learned by the model from historical chat transcripts, where the customer actually voted that they felt that the quality of resolution was high).
Regarding claim 15, it recites similar limitations as claim 6 and therefore is rejected similarly.
Regarding claim 21, it recites similar limitations as claim 6 and therefore is rejected similarly.
Claims 8, 17, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Konam in view of Annadi, Gangadharaiah, and Higgins, as applied to claims 1, 3, 5, 9-10, 12, 14, 16, and 18 above, and further in view of Menon et al. (US 20230188480 A1; hereinafter referred to as Menon).
Regarding claim 8, the combination of Konam, Annadi, Gangadharaiah, and Higgins teaches: the intelligent virtual assistant system of claim 1. The combination of Konam, Annadi, Gangadharaiah, and Higgins does not explicitly, but Menon teaches: determine that the performance score fails to satisfy a predetermined minimum threshold; and initiate further updating of the third language model ([0064] If a negative reward score is received, RL engine 406 can lower down the weight of the corresponding recommendation/option. When a particular recommendation/option is repeatedly assigned negative rewards, its weight will be repeatedly decreased. Eventually, when the weight turns to zero or is lower than a threshold number, RL engine 406 can notify recommendation module 408 to stop or remove this recommendation).
Konam, Annadi, Gangadharaiah, Higgins, and Menon are considered analogous in the field of dialog processing. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Konam, Annadi, Gangadharaiah, and Higgins to combine the teachings of Menon because doing so would allow the virtual assistant to incorporate feedback from the user and improve response performance by updating the language model based on a performance score (Menon [0028] the present disclosure provides an RL-based chatbot solution that is continuously retrained and enhanced with user feedback to improve the efficiency of communication or information search and discovery using chatbot conversations. The technical solution described herein captures the change or variations of user behaviors (e.g., user choices, user preferences) over time and retrains the chatbot models with the captured changes).
Regarding claim 17, it recites similar limitations as claim 8 and therefore is rejected similarly.
Regarding claim 20, it recites similar limitations as claim 8 and therefore is rejected similarly.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Nathan Tengbumroong whose telephone number is (703)756-1725. The examiner can normally be reached Monday - Friday, 11:30 am - 8:00 pm EST.
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, Hai Phan can be reached at 571-272-6338. 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.
/NATHAN TENGBUMROONG/Examiner, Art Unit 2654
/HAI PHAN/Supervisory Patent Examiner, Art Unit 2654
Prosecution Insights