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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 11 May 2025 has been entered.
Claims 1-5, 7-15, 17-20 are pending.
Response to Arguments
Applicant’s arguments regarding the rejection under 35 U.S.C. 103 of claims 1, 11 have been considered but are moot in view of the new grounds of rejection presented in this Office action. Note applicant argues the claims as amended.
Applicant’s arguments regarding the rejection of all pending claims under 35 U.S.C. 101 have been fully considered but they are not persuasive.
Applicant argues at page 8 of the response filed 11 May 2026:
“Claim 1 is not directed merely to a mental process. Rather, claim 1 recites a particular machine-implemented interaction between "one or more processors coupled to non-transitory memory and intermediary to a plurality of client devices and one or more language models," in which the processors are configured to "receive, from a client device of the plurality of client devices…”
In response the examiner is not persuaded. The claimed system although comprising hardware components merely serve as a tool to implement the abstract idea of a process performed by humans using pen and paper. Note the “use of one or more language models” is recited at a high level of generality and does not require more than one model thus do not seem to recite any “particular machine-implemented interaction” as alleged by the applicant.
Applicant argues at page 9 last 7 lines to page 10 first paragraph:
“Claim 1 then further requires "retrieve, from a data structure comprising a plurality of wager opportunities corresponding to a plurality of live events, a subset of the plurality of wager opportunities corresponding to the classification of the intent" and "responsive to generating the classification of the intent, generate an input context comprising the first prompt, the second prompt, and the classification of the intent, and data of the subset of the plurality of wager opportunities," followed by "provide the input context to the one or more language models to generate the output message." The claim therefore recites a specific technological workflow in which the one or more language models first generate "a plurality of candidate intents determined by the one or more language models based on the first prompt," and that output is then used in a subsequent multi-step pipeline to retrieve a wager-opportunity subset from a live-event data structure and to construct the input context that is supplied to the language model(s) for final output generation. That is not "mere data gathering" or "insignificant extra-solution activity"; it is the operative mechanism by which the claimed system processes ambiguous prompts and generates the final language-model output.”
In response the examiner is not persuaded. Again as written the claim does not show how the “one or more” language models determine candidate intents that is different from a human user guessing intentions of an ambiguous request in order to provide a response.
Furthermore applicant seems to argue limitations not reflected in the claim language. No multi-step pipeline is recited in any claim.
Applicant argues at page 10 of the response: “the claim language also reflects a concrete improvement in computer operation”.
In response the examiner is not persuaded. The recited operations “receiving a first prompt, input to a language model to generate an intent message, receiving a second prompt, generating a classification, retrieving a subset of wager opportunities, generating input context, providing input context to one or more language model to generate output message” are mere routine conventional activities for any computer system, do not apply the judicial exception with or by use of a particular machine, do not include other meaningful limitations beyond linking the use of the judicial exception to a particular technological environment.
Applicant argues at page 11 of the response that the claim recites: “a specific way of constructing the language-model input that is rooted in computer implementation and directed to how the system prepares and supplies data for machine processing”.
In response the examiner is not persuaded. A written, the claimed “one or more language models” does not seem to be defined in any specific manner showing any improvement in computer operations.
For all the reasons discussed above, the rejection of all pending claims under 35 U.S.C. 101 is maintained.
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 1-5, 7-15, 17-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
An analysis of subject matter patentability for method claims 11-15, 17-20 is presented below.
Step 1: claim 11 recites a method thus is one of the statutory categories of invention.
Step 2A Prong 1: Claim 11 recites: determining that an intent of the first prompt for the one or more language models does not satisfy one or more classification criteria. These limitations are processes that, under their broadest reasonable interpretation, covers performance of the limitation by a human user. Note nothing in the claim element precludes the steps from practically being performed by a human user with the aid of pen and paper. If a claim limitation, under its broadest reasonable interpretation cover performance of the limitation in the mind, then it falls within the "Mental Processes' grouping of abstract idea (concept performed in the human mind including an observation, evaluation, judgment and opinion). The mere nominal recitation of one or more processors coupled to non- transitory memory and intermediary to a plurality of client devices and one or more language models does not take the claim limitation out of the mental processes grouping. Thus, the limitations merely represent a mental process.
Step 2A Prong 2: The judicial exception is not integrated into a practical application because although the claim recites the additional element of "receiving a first prompt receiving a second prompt... ", “retrieve from a data structure comprising a plurality of wager opportunities…” these limitations are at best mere data gathering process which is considered to be insignificant extra solution activity (see MPEP 2106.05(g)). The recitation of "receiving a first prompt, receiving a second prompt, retrieving a subset of wager opportunities" does not integrate the mental process into a practical application, does not improve any technology or technical field, does not apply the judicial exception with or by use of a particular machine, does not add unconventional steps that confine the claim to a particular useful application, does not include other meaningful limitations beyond linking the use of the judicial exception to a particular technological environment.
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. The additional elements "responsive to determining, generate an intent message based on the first prompt, the intent message identifying a plurality of candidate intents determined by the one or more language models based on the first prompt”, “generate a classification of the intent for the communication session based on the first prompt and the second prompt", "responsive to generating the classification of the intent, generate an input context, provide the input context to the one or more language models to generate the output message, generate a response to the request, provide the response to the client device" do not seem to impose any meaningful limits on practicing the abstract idea, do not add specific limitation other than what is well-understood, routine, conventional activities in the field when they are claimed in a merely generic manner. (See MPEP 2106.05(d)(II) (iv).
Thus claim 11 is rejected under 35 USC 101 as being an abstract idea without significantly more.
Claim 12 merely further describes the generating the classification using the language model, considered insignificant extra solution activity (see MPEP 2106.05(g)).
Claim 13 merely recites identifying a training dataset and training the model using the training dataset, considered insignificant extra solution activity (see MPEP 2106.05(g)).
Claim 14 merely recites generating the classification of the intent using a machine-learning model different from the language model, considered insignificant extra solution activity (see MPEP 2106.05(g)).
Claim 15 merely further describes the language model as a generative pre-trained transformer model, considered insignificant extra solution activity (see MPEP 2106.05(g)).
Claim 17 merely further describes the classification corresponds to one or more of the requests, considered insignificant extra solution activity (see MPEP 2106.05(g)).
Claim 18 merely adds generating the classification based on player profile associated with client device, considered insignificant extra solution activity (see MPEP 2106.05(g)).
Claim 19 merely adds establishing communication session and generating a second message, considered insignificant extra solution activity (see MPEP 2106.05(g)).
Claim 20 merely adds determining the intent for the communication session based on the second message, considered insignificant extra solution activity (see MPEP 2106.05(g)).
Although the dependent claims seem more detailed than their parent claim, none include additional elements that are sufficient to amount to significantly more than the judicial exception.
Claims 1-5, 7-10 merely recite limitations similar to claims 11-15, 17-20 in form of systems, thus are similarly rejected under 35 U.S.C. 101 as directed to an abstract idea discussed in claims 11-15, 17-20 above.
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.
Claim(s) 1, 2, 4, 5, 7-12, 14, 15, 17-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over BHATHENA et al (US 20240282296 A1) of record, in view of HUKE CASEY et al (WO 2023064563 A1), further in view of Gelfenbeyn et al (US 12118320 B2) of record,
Regarding claim 1, BHATHENA substantially teaches a system, comprising: one or more processors coupled to non-transitory memory (see Fig. 1 items 104, 106), the one or more processors configured to:
receive, from a client device during a communication session, a first prompt for a language model (see [0008] method for using a virtual assistant to respond to a request of a user);
determine that an intent of the first prompt for the language model does not satisfy one or more classification criteria (see [0008].. applying, to the received utterance by the at least one processor, an artificial intelligence (AI) model that is configured to assign the received utterance to at least one domain from among a predetermined plurality of domains; outputting, by the at least one processor based on the at least one domain to which the received utterance is assigned, information that prompts the user to provide additional input that relates to the intent of the user;
receiving, by the at least one processor from the user, the additional input; and secondarily determining, by the at least one processor based on the additional input, the intent of the user);
responsive to determining that the intent does not satisfy the one or more classification criteria, provide the first prompt as input to the one or more language models to generate an intent message based on the first prompt, the intent message identifying a plurality of candidate intents determined by the one or more language models based on the first prompt (see [0078] At step S408, the query domain routing and intent classification module 302 outputs domain-related information that prompts the user to provide additional input that is usable for more reliably determining the intent of the user. In an exemplary embodiment, the outputting may include displaying, to the user, a predetermined list of items that corresponds to possible intentions associated with the domain(s) to which the utterance has been assigned, together with a prompt that acts as an invitation to the user to provide a response by which one or more of the possible intentions is selected by the user. In an exemplary embodiment, the outputting may include providing a question for which a user response would be indicative of the intent of the user. Then, at step S410, the query domain routing and intent classification module 302 receives the additional input from the user and makes a final determination of the user intent based on the additional input.)
receive, from the client device, a second prompt in response to the intent message (see [0008]: outputting, by the at least one processor based on the at least one domain to which the received utterance is assigned, information that prompts the user to provide additional input that relates to the intent of the user; receiving, by the at least one processor from the user, the additional input; and secondarily determining, by the at least one processor based on the additional input, the intent of the user); and
generate a classification of the intent for the communication session based on the first prompt and the second prompt (see [0009] The outputting of the information may include displaying, to the user, a respective predetermined list of items that corresponds to possible intentions associated with the at least one domain to which the received utterance is assigned.);
BHATHENA does not specifically show the now added limitations:
“retrieve from a data structure comprising a plurality of wager opportunities corresponding to a plurality of live events, a subset of the plurality of wager opportunities corresponding to the classification of the intent”;
However it is customary in the art to do so as shown by HUKE CASEY (see at least Fig.41, Fig.155 and related text);
it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include such features while implementing the system of BHATHENA in order to assist users in making gambling decisions on live events as taught by HUKE CASEY (see at least Fig.156 wager proposal module 15322);
BHATHENA/ HUKE CASEY further teaches:
responsive to generating the classification of the intent, generate an input context comprising the first prompt, the second prompt, the classification of the intent and data of the subset of the plurality of wager opportunities (see at least BHATHENA [0078] At step S408, the query domain routing and intent classification module 302 outputs domain-related information that prompts the user to provide additional input that is usable for more reliably determining the intent of the user. In an exemplary embodiment, the outputting may include displaying, to the user, a predetermined list of items that corresponds to possible intentions associated with the domain(s) to which the utterance has been assigned, together with a prompt that acts as an invitation to the user to provide a response by which one or more of the possible intentions is selected by the user. In an exemplary embodiment, the outputting may include providing a question for which a user response would be indicative of the intent of the user. Then, at step S410, the query domain routing and intent classification module 302 receives the additional input from the user and makes a final determination of the user intent based on the additional input;
see also BHATHENA [0088] contextual QA system, [0089] To provide contextual answers, the answers are not directly presented in the retrieved FAQs to the user; instead, a prompt is constructed to instruct the Large Language Model (LLM) to utilize the top-k most relevant FAQ answers, together with the available conversation history, to generate appropriate responses to user questions.);
the difference is BHATHENA/HUKE CASEY does not specifically show:
provide the input context to the one or more language models to generate the output message.
However it is customary in the art as shown by Gelfenbeyn to do so (see col. 15 lines 22-36: Upon generating and providing the input by the processor to the generative language model, the generative language model may receive the input generated based on one or more of the following: the context of the dialog, the message of the user in the dialog, the at least one keyword that expands the message based on the context, parameters associated with the language model, the third party data, and other applicable data related to the context of the dialog. Upon receiving the input, the generative language model may predict, based on the input, the response to the message of the user. Predicting the response may include predicting one or more words to follow the sequence of words provided to the generative language model. The response may be generated based on the one or more words and data received in the input);
it would have been obvious to one of ordinary skill in the art to include such features while implementing the system of BHATHENA/HUKE CASEY in order to train the LLM of BHATHENA with more reliable data regarding the intent of the user;
BHATHENA/HUKE CASEY/Gelfenbeyn further teaches:
receive, from the one or more language models, the output message (Gelfenbeyn col. 15 lines 37-41 In block 1010, the method 1000 may include transmitting, by the processor, the response to the client-side computing device. The client-side computing device may be configured to present the response to the user in the dialog of the user with the Al character model.);
generate a response to the request based on the output message (Gelfenbeyn col. 15 lines 37-41 In block 1010, the method 1000 may include transmitting, by the processor, the response to the client-side computing device. The client-side computing device may be configured to present the response to the user in the dialog of the user with the Al character model.); and
provide the response to the request to the client device (Gelfenbeyn col. 15 lines 37-41 In block 1010, the method 1000 may include transmitting, by the processor, the response to the client-side computing device. The client-side computing device may be configured to present the response to the user in the dialog of the user with the AI character model.).
Regarding claim 2, BHATHENA/ HUKE CASEY/ Gelfenbeyn further teaches the system of claim 1, wherein the one or more processors are further configured to: generate the classification of the intent using the one or more language models (see BHATHENA [0079] In an exemplary embodiment, the AI model is trained by using historical utterance data that is augmented by using any one or more of several techniques. One technique for augmenting the historical utterance data is a keyboard perturbation technique by which a particular utterance is altered by randomly replacing characters with words with neighboring characters on a keyboard. A second technique for augmenting the historical utterance data is a swapping character perturbation technique by which a particular utterance is altered by randomly swapping characters within a word while maintaining word length. A third technique for augmenting the historical utterance data is a back-translation technique by which a particular utterance is translated from English to a second language, such as French or German, and then the once-translated version of the utterance is translated back into English. A fourth technique for augmenting the historical utterance data is a paraphrasing technique by which a particular utterance is used for generating an additional example utterance that is different from the particular utterance but still maintains an original intent that is associated with the particular utterance, i.e., saying the same thing while using a different set of words to do so.).
Regarding claim 4, BHATHENA/ HUKE CASEY/Gelfenbeyn further teaches the system of claim 1, wherein the one or more processors are further configured to: generate the classification of the intent using a machine- learning model different from the one or more language models (see BHATHENA [0083] Additionally, the DIET model also supplements the intent prediction and entity losses with masked language modeling loss, which generally further improves performance, especially on domains that are different from the ones on which the dense featurizer is pre-trained).
Regarding claim 5, BHATHENA/ HUKE CASEY/Gelfenbeyn further teaches the system of claim 4, wherein the one or more language models is a large language model comprising generative pre-trained transformer (GPT) models (see BHATHENA [0088] FAQs Retrieval and Question-Answer with Large Language Models: In an exemplary embodiment, to further reduce the frequency of fallback answers that prompt users to rephrase their queries, an implementation has been made of a proof of concept of contextual question-answering (QA) system that leverages the conversation history, an FAQs knowledge base, and Large Language Models (LLMs). FIG. 6 is a diagram 600 that illustrates a question answering pipeline that is usable in a method for performing hierarchical domain routing and intent classification on user queries in order to improve accuracy in responding to such queries and to create smoother conversations between virtual assistants and users, according to an exemplary embodiment.).
Regarding claim 7, BHATHENA/ HUKE CASEY/ Gelfenbeyn further teaches the system of claim 1, wherein the classification of the intent corresponds to one or more of a request for a wager recommendation, a request to modify a wager, a request for information relating to a live event, a request for information relating to at least one wager opportunity, a request to place a wager, or a request for information maintained by the one or more processors (see BHATHENA [0064] The client devices 208(1)-208(n) may run interface applications, such as standard web browsers or standalone client applications, which may provide an interface to communicate with the QDRIC device 202 via the communication network(s) 210 in order to communicate user requests and information. The client devices 208(1)- 208(n) may further include, among other features, a display device, such as a display screen or touchscreen, and/or an input device, such as a keyboard, for example.).
Regarding claim 8, BHATHENA/ HUKE CASEY/ Gelfenbeyn further teaches the system of claim 1, wherein the client device is associated with a player profile, and wherein the one or more processors are further configured to:
generate the classification of the intent for the communication session further based on data of the player profile associated with the client device (see BHATHENA [0089] Following the classification process by both intent and domain models, utterances that are identified as being out-of-scope are directed to an LLM-powered conversational QA system. A knowledge base of FAQs and their corresponding answers has been curated. All FAQs are initially indexed as dense embedding vectors using an embedding model. At inference time, the incoming query is encoded using the same embeddings model, and then the most similar FAQ questions are retrieved, based on cosine similarity. To provide contextual answers, the answers are not directly presented in the retrieved FAQs to the user; instead, a prompt is constructed to instruct the LLM to utilize the top-k most relevant FAQ answers, together with the available conversation history, to generate appropriate responses to user questions.). note the claimed profile reads on the conversation history of BHATHENA.
Regarding claim 9, BHATHENA/ HUKE CASEY/ Gelfenbeyn further teaches the system of claim 1, wherein the one or more processors are further configured to:
establish the communication session in response to a request from an application executing on the client device (see BHATHENA Fig.2 communication network 210,); and
generate a second message for the communication session in response to the request (see BHATHENA [0017] According to another exemplary embodiment, a computing apparatus for using a virtual assistant to respond to a request of a user is provided. The computing apparatus includes a processor; a memory; and a communication interface coupled to each of the processor and the memory. The processor is configured to: receive, via the communication interface, an utterance from the user; analyze the received utterance in order to make an initial determination of an intent of the user and a confidence level that relates to the initial determination of the intent; when the confidence level is less than a predetermined threshold, apply, to the received utterance, an artificial intelligence (AI) model that is configured to assign the received utterance to at least one domain from among a predetermined plurality of domains; output, based on the at least one domain to which the received utterance is assigned, first information that prompts the user to provide additional input that relates to the intent of the user; receive, from the user via the communication interface, the additional input; and secondarily determine, based on the additional input, the intent of the user.).
Regarding claim 10, BHATHENA/ HUKE CASEY/ Gelfenbeyn further teaches the system of claim 9, wherein the one or more processors are further configured to: determine the intent for the communication session further based on the second message (see BHATHENA [0017] According to another exemplary embodiment, a computing apparatus for using a virtual assistant to respond to a request of a user is provided. The computing apparatus includes a processor; a memory; and a communication interface coupled to each of the processor and the memory. The processor is configured to: receive, via the communication interface, an utterance from the user; analyze the received utterance in order to make an initial determination of an intent of the user and a confidence level that relates to the initial determination of the intent; when the confidence level is less than a predetermined threshold, apply, to the received utterance, an artificial intelligence (AI) model that is configured to assign the received utterance to at least one domain from among a predetermined plurality of domains; output, based on the at least one domain to which the received utterance is assigned, first information that prompts the user to provide additional input that relates to the intent of the user; receive, from the user via the communication interface, the additional input; and secondarily determine, based on the additional input, the intent of the user.).
Claims 11, 12, 14, 15, 17-20 essentially recite limitations similar to claims 1, 2, 4, 5, 7-10 in form of methods, thus are rejected for the same reasons discussed in claims 1, 2, 4, 5, 7-10 above.
Claim(s) 3, 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over BHATHENA et al (US 20240282296 A1) of record, in view of HUKE CASEY et al (WO 2023064563 A1), in view of Gelfenbeyn et al (US 12118320 B2) of record, further in view of Han et al (US 20240086648 A1) of record.
Regarding claim 3, BHATHENA/ HUKE CASEY/ Gelfenbeyn further teaches the system of claim 2, wherein the one or more processors are further configured to: identify a training dataset comprising a plurality of training examples (see BHATHENA paragraphs
[0017] The processor is configured to: receive, via the communication interface, an utterance from the user; analyze the received utterance in order to make an initial determination of an intent of the user and a confidence level that relates to the initial determination of the intent; when the confidence level is less than a predetermined threshold, apply, to the received utterance, an artificial intelligence (AI) model that is configured to assign the received utterance to at least one domain from among a predetermined plurality of domains; output, based on the at least one domain to which the received utterance is assigned, first information that prompts the user to provide additional input that relates to the intent of the user; receive, from the user via the communication interface, the additional input; and secondarily determine, based on the additional input, the intent of the user.
[0018] The processor may be further configured to perform the outputting of the information by displaying, to the user, a respective predetermined list of items that corresponds to possible intentions associated with the at least one domain to which the received utterance is assigned); and
train the language model using the training dataset (see BHATHENA [0091] To achieve these goals, advantageous use is made of a hybrid solution with two components-a rule-based component and a machine learning-based component. For the rule-based component, a next action is determined by a combination of a current state and the previous N states, where state is defined as a combination of intent, action, and values of different state variables. Key value pairs of all state-to-action mappings are extracted from dialogue training data, i.e., conversation stories, and stored in a hash table, which is then used to retrieve an action at inference time. Conversation stories that lead to key collisions are excluded in construction of the hash table.).
The difference is BHATHENA / HUKE CASEY/ Gelfenbeyn does not specifically show: each example of the plurality of training examples comprising a respective input prompt having ambiguous intent and a corresponding ground truth output message identifying one or more candidate intents;
However it is customary in the art to do so as shown by Han (see Han [0136] One or more, including potentially all, of the intent classification models may be trained using supervised learning. For example, a training dataset may be generated from historical email messages (e.g., from customers). The training dataset may comprise, for each of a plurality of historical email messages, a record comprising one or more features extracted from the historical email message, labeled with an intent classification, from the plurality of possible intent classifications, representing the ground-truth intent classification. The records may be labeled with the ground-truth intent classifications manually (e.g., by a panel of experts) or in any other suitable manner. An intent classification model may be trained by, for each of record in the training dataset, minimizing a loss function that calculates an error between the intent classification output by intent classification model being trained, given the feature(s) in the record, and the ground-truth intent classification for that record. The same training dataset may be used for each of the plurality of intent classification models, or one or more of the plurality of intent classification models may be trained using a different training dataset than one or more other ones of the plurality of intent classification models).
it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include such features while implementing the system of BHATHENA / HUKE CASEY/ Gelfenbeyn, the motivation being to document the conversation history of generated responses to user questions (see BHATHENA [0089] a prompt is constructed to instruct the LLM to utilize the top-k most relevant FAQ answers, together with the available conversation history, to generate appropriate responses to user questions.).
Claim 13 essentially recites limitations similar to claim 3 in form of method, thus is rejected for the same reasons discussed in claim 3 above.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Ma et al (US 20250232126 A1) teach natural language communications may be automated using language models and session contexts. A first session context may be created for communications between a language model and a first entity. Prompts may be generated using this session context, and responses from the language model may be used to communicate with the first entity. A second session context may also be created for communications between a language model and a second entity. Context transfer information may be generated by processing the first session context with a language model. The context transfer information may be added to the second session context. The second session context with the context transfer information may then be used to generate a communication to the second entity using a language model.
Dakss et al (US 11785280 B1) teaches a system and method for ingesting, normalizing and analyzing multiple disparate datasets surrounding live sports events combined with real-time viewing content recognition and understanding on a user device to enable digital services to recommend real-time, personalized interactive offers such as sports bet offers to the device that are synchronized to live events being visual or audibly projected proximate the user device despite inherent latency between the user device and the projected live event.
Kassis et al (WO 2025019764 A1) teach methods and systems for predictive classification of a sample's raw mass spectra, said spectra produced by mass spectrometry. Said predictive classification is performed by a trained large spectral model comprising, a self-supervised large foundational spectral model trained with unlabeled sample spectra from a plurality of sources, and fine-tuned with a task-specific model trained using labelled spectra.
Lin et al (WO 2025042386 A1) teach systems and methods for generating recommendations for a first user regarding at least one of an industrial process or an industrial product including receiving information from one or more input sources associated with at least one of the industrial process or the industrial product, processing the received information using one or more MT models associated with a model management system, generating, for the first user, a first natural language query regarding at least one of the received information or the processed information using one or more MT NLP models, generating, for the first user, a first natural language recommendation based on the first natural language query and at least one of the received information or the processed information, and outputting, for the first user, a first indication of at least the first natural language recommendation via the user interface.
Mohsenimofidi S, Prasad AS, Zahid A, Rafiq U, Wang X, Attal MI. Classifying user intent for effective prompt engineering: A case of a chatbot for startup teams. InGenerative AI for Effective Software Development 2024 Jun 1 (pp. 317-329). Cham: Springer Nature Switzerland.
Abstract
Prompt engineering plays a pivotal role in effective interaction with large language models (LLMs), including ChatGPT. Understanding user intent behind interactions with LLMs is an important part of prompt construction to elicit relevant and meaningful responses from them. Existing literature sheds little light on this aspect of prompt engineering. Our study seeks to address this knowledge gap. Using the example of building a chatbot for startup teams to obtain better responses from ChatGPT, we demonstrate a feasible way of classifying user intent automatically using ChatGPT itself. Our study contributes to a rapidly increasing body of knowledge of prompt engineering for LLMs. Even though the application domain of our approach is startups, it can be adapted to support effective prompt engineering in various other application domains as well.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to UYEN T LE whose telephone number is (571)272-4021. The examiner can normally be reached M-F 9-5.
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, Ajay M Bhatia can be reached at 5712723906. 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.
/UYEN T LE/Primary Examiner, Art Unit 2156 11 July 2026
Prosecution Insights