DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of Claims
Claims 1-20 are pending in this application.
Examiner’s Comments Relating to Prior Art for Claims 3-4, 6-8, 13-14, and 16-18
The examiner notes that there are no prior art rejections for dependent claims 3-4, 6-8, 13-14, and 16-18, because prior art searches have yielded nothing similar to the claimed invention. This is because the claims contain very specific steps and procedures in the business idea of answering user’s question by looking/searching for answer and responding to the user.
Specifically, dependent claims 3 and 13 further discloses (in addition to the elements disclosed by the referenced claim) the very specific steps and elements of:
“generating, by the server system, a prompt embedding based, at least in part, on the prompt;
accessing, by the server system, a set of factual prompt embeddings and a set of reasoning prompt embeddings from the database;
computing, by the server system, a first set of cosine similarity metrics based, at least in part, on comparing the prompt embedding with each factual prompt embedding of the set of factual prompt embeddings, wherein each cosine similarity metric in the first set of cosine similarity metrics indicates an extent of cosine similarity between the prompt embedding and a particular factual prompt embedding in the set of factual prompt embeddings;
computing, by the server system, a second set of cosine similarity metrics based, at least in part, on comparing the prompt embedding with each reasoning prompt embedding of the set of reasoning prompt embeddings, wherein each cosine similarity metric in the second set of cosine similarity metrics indicates an extent of cosine similarity between the prompt embedding and a particular reasoning prompt embedding in the second set of cosine similarity metrics; and
identifying, by the server system, the prompt type, based, at least in part, on the first set of cosine similarity metrics, the second set of cosine similarity metrics, and a set of similarity rules (emphasis examiner’s).”
Similarly, dependent claims 4 and 14 further discloses (in addition to the elements disclosed by the referenced claim) the very specific steps and elements of:
“generating, by the server system, a first set of tokens based, at least in part, on the prompt,
wherein an individual token is a discreet unit of the prompt that provides a portion of a numerical representation of the prompt for the LLM;
determining, by the LLM associated with the server system, a contextual relationship among each token in the first set of tokens; and determining, by the LLM, the one or more prompt attributes based, at least in part, on the determined contextual relationship (emphasis examiner’s).”
Specifically, dependent claims 6 and 16 further discloses (in addition to the elements disclosed by the referenced claim) the very specific steps and elements of:
“generating, by the server system, a second set of tokens based, at least in part, on the prompt response;
generating, by the server system, a third set of tokens based, at least in part, on the relevant information;
computing, by the server system, a contextual similarity metric based, at least in part, on the second set of tokens, and the third set of tokens,
wherein the contextual similarity metric indicates an extent of contextual similarity between the prompt response and the relevant information; and
regenerating, by the LLM, the prompt response when the contextual similarity metric is less than a second predefined threshold (emphasis examiner’s).”
Specifically, dependent claims 7 and 17 further discloses (in addition to the elements disclosed by the referenced claim) the very specific steps and elements of:
“identifying, by the server system, a first set of terms from the prompt response;
identifying, by the server system, a second set of terms from the relevant information;
computing, by the server system, a sequence metric based, at least in part, on comparing order of the first set of terms with the order of the second set of terms,
wherein the sequence metric indicates an extent of similarity between the order of the first set of terms and the order of the second set of terms; and
regenerating, by the LLM, the prompt response when the sequence metric is less than a third predefined threshold (emphasis examiner’s).”
Specifically, dependent claims 8 and 18 further discloses (in addition to the elements disclosed by the referenced claim) the very specific steps and elements of:
“generating, by the server system, a fourth set of tokens from the prompt response, wherein an individual token is a discreet unit of the prompt response that provides a portion of a numerical representation of the prompt response;
generating, by the server system, a profanity metric based, at least in part, on the fourth set of tokens and a second predefined set of rules, wherein the profanity metric indicates an extent of profanity present in the prompt response; and
regenerating, by the LLM, the prompt response when the profanity metric is at least equal to a fourth predefined threshold (emphasis examiner’s).”
Thus, there are no prior art rejections because prior art searches have yielded nothing similar to the claimed invention – in combination with the referenced independent claim elements. Incorporation of these specific elements (positively claimed and in their entirety) into all the dependent claims may help advance the patent prosecution process.
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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Claims 1-20 are directed to a system, method, or product, which are/is one of the statutory categories of invention. (Step 1: YES).
The Examiner has identified independent method claim 1 as the claim that represents the claimed invention for analysis and is similar to independent system claim 11 and product claim 20. Claim 1 recites the limitations of answering user’s prompt/question by looking/searching for answer and responding to the user.
These limitations, under their broadest reasonable interpretation, cover performance of the limitation as certain methods of organizing human activity. Determining user’s intent based on user’s prompt; determining prompt type; Identifying prompt attribute describing an entity’s financial event; extracting entity’s information; generating a prompt response; and transmitting prompt response to the user, – specifically, the claim recites
“determining… a prompt intent based, at least in part, on a prompt from a user, the prompt intent indicating an intent of the user; determining… a prompt type of the prompt based, at least in part, on the prompt intent, the prompt type comprising at least one of a factual prompt, a reasoning prompt, or a combination prompt; identifying… one or more prompt attributes associated with the prompt, the one or more prompt attributes indicating information describing one or more financial events associated with an entity; extracting… relevant information associated with the entity from a database based, at least in part, on the prompt intent, the prompt type, and the one or more prompt attributes; generating… a prompt response based, at least in part, on the relevant information and the prompt intent, the prompt response indicating a curated response to the prompt based on the prompt type using the relevant information; and transmitting… the prompt response to the user”, recites a fundamental economic practice, directed to mitigating risk.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation as a fundamental economic practice or commercial or legal interactions, then it falls within the “Certain Methods of Organizing Human Activity” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
The “a server system”, “a communication interface”, “a memory”, “a processor”, “a database”, and “a Large Language Model (LLM)”, in claim 11; and the additional technical element of “a non-transitory computer-readable storage medium” in claim 20, are just applying generic computer components to the recited abstract limitations. The recitation of generic computer components in a claim does not necessarily preclude that claim from reciting an abstract idea. Claims 1 and 20 are also abstract for similar reasons. (Step 2A-Prong 1: YES. The claims recite an abstract idea)
This judicial exception is not integrated into a practical application. In particular, the claims recite the additional elements of: a computer such as a server system and a processor; a communication device such as a communication interface; a storage unit such as a memory, a database, and a non-transitory computer-readable storage medium; and software module and algorithm such as a Large Language Model (LLM).
The computer hardware/software is/are recited at a high-level of generality (i.e., as a generic processor performing a generic computer function) such that it amounts no more than mere instructions to apply the exception using a generic computer component.
The examiner notes that although the claim recites “a Large Language Model (LLM)”, it is recited at a high level. See claims 1, 11 and 20. For example, the claims simply state what the “a Large Language Model (LLM)” will do in the claimed business process – i.e. determining user’s intent based on user’s prompt/question, determining the prompt/question type (e.g., is if factual question), and generating a prompt response based on the prompt/question. These are nominal recitations. The examiner notes that the applicant is not improving “a Large Language Model (LLM). Rather the applicant is using “a Large Language Model (LLM)” in a business process. Accordingly, these additional elements, when considered separately and as an ordered combination, do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea and are at a high level of generality. Therefore, claims 1, 11, and 20 are directed to an abstract idea without a practical application. (Step 2A-Prong 2: NO. The additional claimed elements are not integrated into a practical application)
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because, when considered separately and as an ordered combination, they do not add significantly more (also known as an “inventive concept”) to the exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a computer hardware 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. Accordingly, these additional elements, do not change the outcome of the analysis, when considered separately and as an ordered combination. Thus, claims 1, 11, and 20 are not patent eligible. (Step 2B: NO. The claims do not provide significantly more)
Dependent claims further define the abstract idea that is present in their respective independent claims 1, 11, and 20 and thus correspond to Certain Methods of Organizing Human Activity, and hence are abstract for the reasons presented above.
Dependent claim 2 discloses the limitation of receiving, by the server system, the prompt from a virtual assistant, wherein the user provides the prompt to the virtual assistant, and the virtual assistant is an application configured to receive the prompt from the user; determining, by the server system, a category of the prompt based, at least in part, on a first predefined set of rules, wherein the category indicates whether the prompt is one of a valid prompt or an invalid prompt; in response to determining that the prompt is the valid prompt, providing, by the server system, the prompt to the LLM as input; and in response to determining that the prompt is the invalid prompt, facilitating, by the server system, transmission of an invalid prompt response to the user through the virtual assistant, which further narrows the abstract idea. Note that the technical elements “the server system”, “the LLM”, and “the virtual assistant”, are recited at a high level of generality. They do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
Dependent claim 3 discloses the limitation of generating, by the server system, a prompt embedding based, at least in part, on the prompt; accessing, by the server system, a set of factual prompt embeddings and a set of reasoning prompt embeddings from the database; computing, by the server system, a first set of cosine similarity metrics based, at least in part, on comparing the prompt embedding with each factual prompt embedding of the set of factual prompt embeddings, wherein each cosine similarity metric in the first set of cosine similarity metrics indicates an extent of cosine similarity between the prompt embedding and a particular factual prompt embedding in the set of factual prompt embeddings; computing, by the server system, a second set of cosine similarity metrics based, at least in part, on comparing the prompt embedding with each reasoning prompt embedding of the set of reasoning prompt embeddings, wherein each cosine similarity metric in the second set of cosine similarity metrics indicates an extent of cosine similarity between the prompt embedding and a particular reasoning prompt embedding in the second set of cosine similarity metrics; and identifying, by the server system, the prompt type, based, at least in part, on the first set of cosine similarity metrics, the second set of cosine similarity metrics, and a set of similarity rules, which further narrows the abstract idea. Note that the technical elements “the server system” and “the database”, are recited at a high level of generality. They do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
Dependent claim 4 discloses the limitation of generating, by the server system, a first set of tokens based, at least in part, on the prompt, wherein an individual token is a discreet unit of the prompt that provides a portion of a numerical representation of the prompt for the LLM; determining, by the LLM associated with the server system, a contextual relationship among each token in the first set of tokens; and determining, by the LLM, the one or more prompt attributes based, at least in part, on the determined contextual relationship, which further narrows the abstract idea. Note that the technical elements “the server system” and “the LLM”, are recited at a high level of generality. They do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
Dependent claim 5 discloses the limitation of determining, by the LLM, context of the relevant information; computing, by the server system, an alignment metric indicating an extent of factual correctness of the prompt intent determined based on the context; in response to determining that the alignment metric is lower than a preset threshold, generating, by the LLM, the prompt response based on the context, wherein the prompt response comprises a reasoning indicating that the prompt is factually incorrect; and in response to determining that the alignment metric is at least equal to the preset threshold, generating, by the LLM, the prompt response based on the context, which further narrows the abstract idea. Note that the technical elements “the server system” and “the LLM”, are recited at a high level of generality. They do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
Dependent claim 6 discloses the limitation of generating, by the server system, a second set of tokens based, at least in part, on the prompt response; generating, by the server system, a third set of tokens based, at least in part, on the relevant information; computing, by the server system, a contextual similarity metric based, at least in part, on the second set of tokens, and the third set of tokens, wherein the contextual similarity metric indicates an extent of contextual similarity between the prompt response and the relevant information; and regenerating, by the LLM, the prompt response when the contextual similarity metric is less than a second predefined threshold, which further narrows the abstract idea. Note that the technical elements “the server system” and “the LLM”, are recited at a high level of generality. They do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
Dependent claim 7 discloses the limitation of identifying, by the server system, a first set of terms from the prompt response; identifying, by the server system, a second set of terms from the relevant information; computing, by the server system, a sequence metric based, at least in part, on comparing order of the first set of terms with the order of the second set of terms, wherein the sequence metric indicates an extent of similarity between the order of the first set of terms and the order of the second set of terms; and regenerating, by the LLM, the prompt response when the sequence metric is less than a third predefined threshold, which further narrows the abstract idea. Note that the technical elements “the server system” and “the LLM”, are recited at a high level of generality. They do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
Dependent claim 8 discloses the limitation of generating, by the server system, a fourth set of tokens from the prompt response, wherein an individual token is a discreet unit of the prompt response that provides a portion of a numerical representation of the prompt response; generating, by the server system, a profanity metric based, at least in part, on the fourth set of tokens and a second predefined set of rules, wherein the profanity metric indicates an extent of profanity present in the prompt response; and regenerating, by the LLM, the prompt response when the profanity metric is at least equal to a fourth predefined threshold, which further narrows the abstract idea. Note that the technical elements “the server system” and “the LLM”, are recited at a high level of generality. They do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
Dependent claim 9 discloses the limitation of the relevant information comprises explainable Artificial Intelligence (AI) values indicating a weightage of a plurality of parameters contributing to a risk score associated with the one or more financial events, which further narrows the abstract idea.
Dependent claim 10 discloses the limitation of the entity is at least one of an issuer, an acquirer, a merchant, or a cardholder, which further narrows the abstract idea.
Dependent claim 12 discloses the limitation of receive the prompt from a virtual assistant, wherein the user provides the prompt to the virtual assistant, and the virtual assistant is an application configured to receive the prompt from the user; determine a category of the prompt based, at least in part, on a first predefined set of rules, wherein the category indicates whether the prompt is one of a valid prompt or an invalid prompt; in response to determining that the prompt is the valid prompt, providing the prompt to the LLM as input; and in response to determining that the prompt is the invalid prompt, facilitating transmission of an invalid prompt response to the user through the virtual assistant, which further narrows the abstract idea. Note that the technical elements “the server system”, “the LLM”, and “the virtual assistant”, are recited at a high level of generality. They do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
Dependent claim 13 discloses the limitation of generate a prompt embedding based, at least in part, on the prompt; access a set of factual prompt embeddings and a set of reasoning prompt embeddings from the database; compute a first set of cosine similarity metrics based, at least in part, on comparing the prompt embedding with each factual prompt embedding of the set of factual prompt embeddings, wherein each cosine similarity metric in the first set of cosine similarity metrics indicates an extent of cosine similarity between the prompt embedding and a particular factual prompt embedding in the set of factual prompt embeddings;
compute a second set of cosine similarity metrics based, at least in part, on comparing the prompt embedding with each reasoning prompt embedding of the set of reasoning prompt embeddings, wherein each cosine similarity metric in the second set of cosine similarity metrics indicates an extent of cosine similarity between the prompt embedding and a particular reasoning prompt embedding in the second set of cosine similarity metrics; and identify the prompt type, based, at least in part, on the first set of cosine similarity metrics, the second set of cosine similarity metrics, and a set of similarity rules, which further narrows the abstract idea. Note that the technical elements “the server system” and “the database”, are recited at a high level of generality. They do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
Dependent claim 14 discloses the limitation of generate a first set of tokens based, at least in part, on the prompt, wherein an individual token is a discreet unit of the prompt that provides a portion of a numerical representation of the prompt for the LLM; determine, by the LLM associated with the server system, a contextual relationship among each token in the first set of tokens; and determine, by the LLM, the one or more prompt attributes based, at least in part, on the determined contextual relationship, which further narrows the abstract idea. Note that the technical elements “the server system” and “the LLM”, are recited at a high level of generality. They do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
Dependent claim 15 discloses the limitation of determine, by the LLM, context of the relevant information;
compute an alignment metric indicating an extent of factual correctness of the prompt intent determined based on the context; in response to determining that the alignment metric is lower than a preset threshold, generate, by the LLM, the prompt response based on the context, wherein the prompt response comprises a reasoning indicating that the prompt is factually incorrect; and in response to determining that the alignment metric is at least equal to the preset threshold, generate, by the LLM, the prompt response based on the context, which further narrows the abstract idea. Note that the technical elements “the server system” and “the LLM”, are recited at a high level of generality. They do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
Dependent claim 16 discloses the limitation of generate a second set of tokens based, at least in part, on the prompt response; generate a third set of tokens based, at least in part, on the relevant information; compute a contextual similarity metric based, at least in part, on the second set of tokens, and the third set of tokens, wherein the contextual similarity metric indicates an extent of contextual similarity between the prompt response and the relevant information; and regenerate, by the LLM, the prompt response when the contextual similarity metric is less than a second predefined threshold, which further narrows the abstract idea. Note that the technical elements “the server system” and “the LLM”, are recited at a high level of generality. They do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
Dependent claim 17 discloses the limitation of identify a first set of terms from the prompt response; identify a second set of terms from the relevant information; compute a sequence metric based, at least in part, on comparing order of the first set of terms with the order of the second set of terms, wherein the sequence metric indicates an extent of similarity between the order of the first set of terms and the order of the second set of terms; and regenerate, by the LLM, the prompt response when the sequence metric is less than a third predefined threshold, which further narrows the abstract idea. Note that the technical elements “the server system” and “the LLM”, are recited at a high level of generality. They do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
Dependent claim 18 discloses the limitation of generate a fourth set of tokens from the prompt response, wherein the fourth set of tokens indicates a collection of individual units in the prompt response; generate a profanity metric based, at least in part, on the fourth set of tokens and a second predefined set of rules, wherein the profanity metric indicates an extent of profanity present in the prompt response; and regenerate, by the LLM, the prompt response when the profanity metric is at least equal to a fourth predefined threshold, which further narrows the abstract idea. Note that the technical elements “the server system” and “the LLM”, are recited at a high level of generality. They do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
Dependent claim 19 discloses the limitation of the relevant information comprises explainable Artificial Intelligence (AI) values indicating a weightage of a plurality of parameters contributing to a risk score associated with the one or more financial events, which further narrows the abstract idea.
Thus, the dependent claims do not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception when considered both individually and as an ordered combination. Therefore, the dependent claims are directed to an abstract idea. Thus, the claims 1-20 are not patent-eligible.
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 of this title, 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 1-2, 5, 10-12, 15, and 19-20 are rejected under AIA 35 U.S.C. 103 as being unpatentable over Wikipedia (Information retrieval https://web.archive.org/web/20211213133139/https://en.wikipedia.org/wiki/Information_retrieval; 12/13/2021) in view of Kurani (20250209933).
Regarding claim 1, Wikipedia discloses
a computer-implemented method, comprising:
determining, by [a Large Language Model (LLM)] associated with a server system, a prompt intent based, at least in part, on a prompt from a user, the prompt intent indicating an intent of the user
((Page 1, para 3: “An information retrieval process begins when a user enters a query into the system. Queries are formal statements of information needs, for example search strings in web search engines. In information retrieval a query does not uniquely identify a single object in the collection. Instead, several objects may match the query, perhaps with different degrees of relevancy”).
determining, by the server system, a prompt type of the prompt based, at least in part, on the prompt intent, the prompt type comprising at least one of a factual prompt, a reasoning prompt, or a combination prompt
(“Algebraic models represent documents and queries usually as vectors, matrices, or tuples. The similarity of the query vector and document vector is represented as a scalar value.
■ Vector space model
■ Generalized vector space model
■ Enhanced Topic-based Vector Space Model
■ Extended Boolean model
■ Latent semantic indexing a.k.a. latent semantic analysis”).
extracting, by the server system, relevant information associated with the entity from a database based, at least in part, on the prompt intent, the prompt type, and the one or more prompt attributes
(Page 1, para 1: “Information retrieval (IR) in computing and information science is the process of obtaining information system resources that are relevant to an information need from a collection of those resources. Searches can be based on full-text or other content-based indexing. Information retrieval is the science of searching for information in a document, searching for documents themselves, and also searching for the metadata that describes data, and for databases of texts, images or sounds”).
generating, by the LLM, a prompt response based, at least in part, on the relevant information and the prompt intent, the prompt response indicating a curated response to the prompt based on the prompt type using the relevant information; and transmitting, by the server system, the prompt response to the user
((Page 2, para 1: “An object is an entity that is represented by information in a content collection or database. User queries are matched against the database information. However, as opposed to classical SQL queries of a database, in information retrieval the results returned may or may not match the query, so results are typically ranked. This ranking of results is a key difference of information retrieval searching compared to database searching”).
((Page 2, para 3: “Most IR systems compute a numeric score on how well each object in the database matches the query, and rank the objects according to this value. The top ranking objects are then shown to the user. The process may then be iterated if the user wishes to refine the query”).
Wikipedia does not disclose, however, Kurani teaches
[a Large Language Model (LLM)] and
identifying, by the LLM, one or more prompt attributes associated with the prompt, the one or more prompt attributes indicating information describing one or more financial events associated with an entity
(“[0021] The AI system 120 may include one or more servers, databases, or cloud computing environments that may execute one or more generative AI models. The generative AI models may include, but are not limited to, large language models (LLMs), which can be trained to generate human-like text, speech, images, and/or components of graphical user interfaces. The generative AI models may be structured using a deep learning architecture that includes a multitude of interconnected layers, including attention mechanisms, self-attention layers, and transformer blocks. The generative AI models are trained on large datasets to assimilate patterns, structures, and relationships within the data. The trained generative AI models can be trained to generate outputs that resemble or closely resemble the characteristics of the input data. The generative AI models may be fine-tuned to generate specific output data, including data that is compatible with various database architectures or provider computing systems. The generative AI models can be trained via optimization of a large number of parameters, in which the generative AI models learn to minimize the error between its predictions and the actual data points, resulting in highly accurate and coherent generative capabilities”). and
(“[0016] the generative AI model receives general inputs from a user and, in response, provides user specific content, and particularly training material or information. The generative AI model can obtain a general request (e.g., “help me with my finances”) from a user, obtain information associated with the user (e.g., contextual information, such as a current location of the user, and user information such as account information), and then generate a response that is specific to the user's individual circumstances despite the general query relating to the search query (in this instance, financial help). As described herein, the use of the generative AI model in a reverse operation may teach the user “how to learn something,” rather than simply provide formulaic responses. For example, the generative AI model described herein can teach a user “how to create a financial plan” rather simply generating the financial plan for the user. The generative AI model can generate training material based on a user's prior knowledge surrounding the topic, any goals specified by the user, and general knowledge thresholds relating to the topic in order to teach the user about the topic”).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Wikipedia to include [a Large Language Model (LLM)] and identifying, by the LLM, one or more prompt attributes associated with the prompt, the one or more prompt attributes indicating information describing one or more financial events associated with an entity as taught by Kurani to use algorithm to provide information to a user, including information related to finance. See “[0002] Artificial intelligence (AI) may be used to provide information to a user. More specifically, generative AI models may be used to provide a relatively robust set of information to the user, as the generative AI models may improve over time via continuous interactions with the generative AI model” And “([0016] the generative AI model receives general inputs from a user and, in response, provides user specific content, and particularly training material or information. The generative AI model can obtain a general request (e.g., “help me with my finances”) from a user, obtain information associated with the user (e.g., contextual information, such as a current location of the user, and user information such as account information), and then generate a response that is specific to the user's individual circumstances despite the general query relating to the search query (in this instance, financial help). As described herein, the use of the generative AI model in a reverse operation may teach the user “how to learn something,” rather than simply provide formulaic responses”.
Regarding claim 2, the combination of Wikipedia and Kurani, as shown in the rejection above, discloses the limitations of claim 1.
Wikipedia does not disclose, however, Kurani further discloses
receiving, by the server system, the prompt from a virtual assistant, wherein the user provides the prompt to the virtual assistant, and the virtual assistant is an application configured to receive the prompt from the user
(“[0019] The network 101 can include an overlay network which is virtual and sits on top of one or more layers of other networks. The network 101 can be of any such network topology as known to those ordinarily skilled in the art capable of supporting the operations described herein”).
(“[0025] the third-party system can include an operating system to execute a virtual environment. The operating system can include hardware control instructions and program execution instructions. The operating system can include a high-level operating system, a server operating system, an embedded operating system, or a boot loader”).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Wikipedia to include receiving, by the server system, the prompt from a virtual assistant, wherein the user provides the prompt to the virtual assistant, and the virtual assistant is an application configured to receive the prompt from the user as taught by Kurani to use algorithm to provide information to a user, including information related to finance operable from different types system (including virtual network). See “[0002] Artificial intelligence (AI) may be used to provide information to a user. More specifically, generative AI models may be used to provide a relatively robust set of information to the user, as the generative AI models may improve over time via continuous interactions with the generative AI model” And (“[0025] the third-party system can include an operating system to execute a virtual environment. The operating system can include hardware control instructions and program execution instructions. The operating system can include a high-level operating system, a server operating system, an embedded operating system, or a boot loader”).
Wikipedia further discloses
determining, by the server system, a category of the prompt based, at least in part, on a first predefined set of rules, wherein the category indicates whether the prompt is one of a valid prompt or an invalid prompt
(Page 1, para 1: “Information retrieval (IR) in computing and information science is the process of obtaining information system resources that are relevant to an information need from a collection of those resources. Searches can be based on full-text or other content-based indexing. Information retrieval is the science of searching for information in a document, searching for documents themselves, and also searching for the metadata that describes data, and for databases of texts, images or sounds”).
(“Algebraic models represent documents and queries usually as vectors, matrices, or tuples. The similarity of the query vector and document vector is represented as a scalar value.
■ Vector space model
■ Generalized vector space model
■ Enhanced Topic-based Vector Space Model
■ Extended Boolean model
■ Latent semantic indexing a.k.a. latent semantic analysis”).
in response to determining that the prompt is the valid prompt, providing, by the server system, the prompt to the LLM as input; and in response to determining that the prompt is the invalid prompt, facilitating, by the server system, transmission of an invalid prompt response to the user through the virtual assistant
(Page 5, para 1: “The evaluation of an information retrieval system' is the process of assessing how well a system meets the information needs of its users. In general, measurement considers a collection of documents to be searched and a search query. Traditional evaluation metrics, designed for Boolean retrieval or top-k retrieval, include precision and recall. All measures assume a ground truth notion of relevancy: every document is known to be either relevant or non-relevant to a particular query. In practice, queries may be ill-posed and there may be different shades of relevancy”).
(Page 2, para 1: “An object is an entity that is represented by information in a content collection or database. User queries are matched against the database information. However, as opposed to classical SQL queries of a database, in information retrieval the results returned may or may not match the query, so results are typically ranked. This ranking of results is a key difference of information retrieval searching compared to database searching”).
(Page 2, para 3: “Most IR systems compute a numeric score on how well each object in the database matches the query, and rank the objects according to this value. The top ranking objects are then shown to the user. The process may then be iterated if the user wishes to refine the query”).
Regarding claim 5, the combination of Wikipedia and Kurani, as shown in the rejection above, discloses the limitations of claim 1.
Wikipedia further discloses
determining, by the LLM, context of the relevant information; computing, by the server system, an alignment metric indicating an extent of factual correctness of the prompt intent determined based on the context
(Page 5, para 1: “The evaluation of an information retrieval system' is the process of assessing how well a system meets the information needs of its users. In general, measurement considers a collection of documents to be searched and a search query. Traditional evaluation metrics, designed for Boolean retrieval or top-k retrieval, include precision and recall. All measures assume a ground truth notion of relevancy: every document is known to be either relevant or non-relevant to a particular query. In practice, queries may be ill-posed and there may be different shades of relevancy ”).
Wikipedia does not disclose, however, Kurani further discloses
in response to determining that the alignment metric is lower than a preset threshold, generating, by the LLM, the prompt response based on the context, wherein the prompt response comprises a reasoning indicating that the prompt is factually incorrect; and in response to determining that the alignment metric is at least equal to the preset threshold, generating, by the LLM, the prompt response based on the context
(“[0068] At process 414, one or more nodes of the plurality of nodes are identified. In some embodiments, the one or more nodes are identified by the AI system 120. The one or more nodes may be identified according to a predefined threshold applied to the value generated for each of the plurality of nodes at process 412. The predefined threshold represents a value of sufficient knowledge on the topic. In some embodiments, the value of sufficient knowledge may be determined based on a general knowledge (e.g., the general knowledge stored in the knowledge dataset 166) of the topic. In some embodiments, the value of sufficient knowledge may be determined based on a user-entered goal (e.g., “I want to learn how to calculate derivatives”). For each of the plurality of nodes with a value less than the predefined threshold, the AI system 120 may indicate an insufficient knowledge of the secondary topic represented by that node”).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Wikipedia to include in response to determining that the alignment metric is lower than a preset threshold, generating, by the LLM, the prompt response based on the context, wherein the prompt response comprises a reasoning indicating that the prompt is factually incorrect; and in response to determining that the alignment metric is at least equal to the preset threshold, generating, by the LLM, the prompt response based on the context as taught by Kurani to use algorithm to provide information to a user, including information related to finance, with relevancy determined by a predefined threshold. See “[0002] Artificial intelligence (AI) may be used to provide information to a user. More specifically, generative AI models may be used to provide a relatively robust set of information to the user, as the generative AI models may improve over time via continuous interactions with the generative AI model” And (“[0068] At process 414, one or more nodes of the plurality of nodes are identified. In some embodiments, the one or more nodes are identified by the AI system 120. The one or more nodes may be identified according to a predefined threshold applied to the value generated for each of the plurality of nodes at process 412. The predefined threshold represents a value of sufficient knowledge on the topic. In some embodiments, the value of sufficient knowledge may be determined based on a general knowledge (e.g., the general knowledge stored in the knowledge dataset 166) of the topic. In some embodiments, the value of sufficient knowledge may be determined based on a user-entered goal (e.g., “I want to learn how to calculate derivatives”). For each of the plurality of nodes with a value less than the predefined threshold, the AI system 120 may indicate an insufficient knowledge of the secondary topic represented by that node”).
Regarding claim 10, the combination of Wikipedia and Kurani, as shown in the rejection above, discloses the limitations of claim 1.
Wikipedia does not disclose, however, Kurani further discloses
the entity is at least one of an issuer, an acquirer, a merchant, or a cardholder
(“[0020] The provider computing system 110 is owned by, associated with, or otherwise operated by a provider institution (e.g., a bank or other financial institution) that maintains one or more accounts held by various customers (e.g., the customer/user associated with the client computing device 140), such as demand deposit accounts, credit card accounts, receivables accounts, and so on”).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Wikipedia to include the entity is at least one of an issuer, an acquirer, a merchant, or a cardholder as taught by Kurani to use algorithm to provide information to a financial customer, including information related to finance. See “[0002] Artificial intelligence (AI) may be used to provide information to a user. More specifically, generative AI models may be used to provide a relatively robust set of information to the user, as the generative AI models may improve over time via continuous interactions with the generative AI model” And
(“[0020] The provider computing system 110 is owned by, associated with, or otherwise operated by a provider institution (e.g., a bank or other financial institution) that maintains one or more accounts held by various customers (e.g., the customer/user associated with the client computing device 140), such as demand deposit accounts, credit card accounts, receivables accounts, and so on”).
Claim 11 is rejected using the same rationale that was used for the rejection of claim 1.
Claim 12 is rejected using the same rationale that was used for the rejection of claim 2.
Claim 15 is rejected using the same rationale that was used for the rejection of claim 5.
Claim 20 is rejected using the same rationale that was used for the rejection of claim 1.
Claim 9 and 19 are rejected under AIA 35 U.S.C. 103 as being unpatentable over Wikipedia in view of Kurani, further in view of and Butvinik (20250200578).
Regarding claim 9, the combination of Wikipedia and Kurani, as shown in the rejection above, discloses the limitations of claim 1.
The combination of Wikipedia and Kurani do not disclose but Butvinik does teaches
the relevant information comprises explainable Artificial Intelligence (AI) values indicating a weightage of a plurality of parameters contributing to a risk score associated with the one or more financial events
(“[0061] As such, the rule-based logic and ML models may be used to process the inputs shown in diagram 300b for DMM 224 (e.g., investigation stage 314 and task 316) and provide corresponding outputs, such as selected agent 322, sequence 324, and/or recommendations 326 for fraud investigation 312. DMM 224 may also be deployed with algorithmic logic for processing. For example, in order to evaluate fraud investigation 312 during investigation stage 314 and for task 316 in that stage, DMM 224 may utilize a weighted evaluation function with LLM 318. The weighted evaluation function may be computed using the following Equation 1: [0062] Given an alert A, DMM 224 evaluates”). and
(“[0063] Where: [0064] R is a risk score. [0065] D is a date. [0066] H is a historical context. H represents a quantified measure of the alert's historical context, derived from similar past alerts and their outcomes [0067] w.sub.1, w.sub.2, and w.sub.3 are weights that determine the importance of risk score, date, and historical context, respectively”).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the combination Wikipedia and Kurani to include the relevant information comprises explainable Artificial Intelligence (AI) values indicating a weightage of a plurality of parameters contributing to a risk score associated with the one or more financial events as taught by Butvinik to use artificial intelligence model (such as LLM) to process information based on the importance of the parameter by assigned weights – see “[0061] DMM 224 may utilize a weighted evaluation function with LLM 318. The weighted evaluation function may be computed using the following Equation 1: [0062] Given an alert A, DMM 224 evaluates”). And (“[0063] Where: [0064] R is a risk score. [0065] D is a date. [0066] H is a historical context. H represents a quantified measure of the alert's historical context, derived from similar past alerts and their outcomes [0067] w.sub.1, w.sub.2, and w.sub.3 are weights that determine the importance of risk score, date, and historical context, respectively”).
Claim 19 is rejected using the same rationale that was used for the rejection of claim 9.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure.
Alexander (20120066216) teaches system and method for quantifying visibility within search engines.
Jou (20250126144) teaches definition and extension of stories of core entities and calculation of risk scores.
Paiz (8977621) teaches search engine optimizer.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MARK H GAW whose telephone number is (571)270-0268. The examiner can normally be reached Mon-Fri: 9am -5pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Mike Anderson can be reached on 571 270-0508. 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.
/MARK H GAW/Examiner, Art Unit 3693
Prosecution Insights