Detailed Action
This communication is in response to the Application filed on 9/24/2024.
Claims 1-20 are pending and have been examined.
Claims 1-20 are rejected.
Independent Claims 1, 11 and 19 are parallel method, system and non-transitory computer-readable storage medium claims, respectively.
Apparent priority: 9/24/2024.
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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 12/26/2024 have been considered by the examiner.
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.
Regarding Independent Claim 1, Claim 1 recites,
“1. A method comprising:
receiving, by one or more processors, a natural language query; [This relates to a human receiving a query using pen and paper.]
executing, by the one or more processors, a first large language model (LLM) using as input the natural language query to generate a preliminary response to the natural language query; [This relates to a human generating a response using pen and paper.]
executing, by the one or more processors, a machine learning model using as input the preliminary response to generate a preliminary response embedding; [This relates to a human generating a response embedding using pen and paper.]
querying, by the one or more processors, a vector database using the preliminary response embedding to retrieve contextual data for the natural language query; and [This relates to a human retrieving contextual data using pen and paper.]
executing, by the one or more processors, a second LLM using as input the natural language query and the contextual data to generate a response to the natural language query. [This relates to a human generating a response using pen and paper.]
Regarding Independent Claim 11, Claim 11 is a System claim with limitations similar to that of claim 1 and is rejected under the same rationale.
Regarding Independent Claim 19, Claim 19 is a non-transitory computer-readable storage medium claim with limitations similar to that of claim 1 and is rejected under the same rationale.
The Dependent Claim does not include additional limitations that could incorporate the abstract idea into a practical application or cause the Claim as a whole to amount to significantly more than the underlying abstract idea.
This judicial exception is not integrated into a practical application. In particular, claims 1, 11, and 19 recites the additional element of “processor” For example, in [0014] the claim recites the computing device 106 may each contain a processor and a memory. Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are directed to an abstract idea.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to the integration of the abstract idea into a practical application, the additional element of using a processor is noted as a general computer. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. Further, the additional limitation in the claims noted above are directed towards insignificant solution activity. The claims are not patent eligible.
Dependent claim 2 recites,
“2. The method of claim 1, further comprising executing, by the one or more processors, the machine learning model using as input domain data to generate the vector database. [This relates to a human generating a vector database using pen and paper.] A machine learning model is noted as an additional limitation.
Dependent claim 3 recites,
“3. The method of claim 1, further comprising fine-tuning, by the one or more processors, the first LLM using domain data used to generate the vector database. [This relates to a human fine-tuning using logic and reasoning in the human mind.] an LLM is noted as an additional limitation.
Dependent claim 4 recites,
“4. The method of claim 1, further comprising: executing, by the one or more processors, an evaluation model using as input the response to determine an accuracy score for the response; and [This relates to a human determining a accuracy score using pen and paper.]
based on the accuracy score being below a predetermined threshold, performing one or more of: transmitting, by the one or more processors, the response to a user device; [This relates to a human transmitting a response to a user device using human physical processes to press a button.]
executing, by the one or more processors, the first LLM using as input the natural language query and the response; or executing, by the one or more processors, the machine learning model using as input the response to generate a response embedding. [This relates to a human generating a response embedding using pen and paper.] An LLM is noted as an additional limitation.
Dependent claim 5 recites,
“5. The method of claim 1, further comprising: executing, by the one or more processors, the first LLM using as input the natural language query and the response to generate a second preliminary response; [This relates to a human generating a response using pen and paper.]
executing, by the one or more processors, the machine learning model using as input the second preliminary response to generate a second preliminary response embedding; [This relates to a human generating a response using pen and paper.]
querying, by the one or more processors, the vector database using the second preliminary response embedding to retrieve second contextual data; and [This relates to a human retrieving contextual data using pen and paper.]
executing, by the one or more processors, the second LLM using as input the natural language query and the second contextual data. [This relates to a human executing an LLM by physical processes of human touch.] LLMs are noted as additional limitations.
Dependent claim 6 recites,
“6. The method of claim 1, further comprising: executing, by the one or more processors, the machine learning model using as input the response to generate a response embedding; [This relates to a human generating a response embedding using pen and paper.]
querying, by the one or more processors, the vector database using the response embedding to retrieve second contextual data; and [This relates to a human retrieving contextual data using pen and paper.]
executing, by the one or more processors, the second LLM using as input the natural language query and the second contextual data. [This relates to a human executing a LLM using physical processes of touch.] LLMs are noted as additional limitations.
Dependent claim 7 recites,
“7. The method of claim 1, wherein the first LLM and the second LLM are the same LLM. [This relates to a human recognizing the LLMs are the same using logic and reasoning.] LLMs are noted as additional limitations.
Dependent claim 8 recites,
“8. The method of claim 1, further comprising: executing, by the one or more processors, the machine learning model using as input the natural language query to generate a natural language query embedding; and [this relates to a human generating a natural language query embedding using pen and paper.]
querying, by the one or more processors, the vector database using the natural language query embedding to retrieve additional contextual data for the natural language query, wherein executing, by the one or more processors, the second LLM includes executing, by the one or more processors, the second LLM using as input the contextual data and the additional contextual data. [This relates to a human retrieving additional contextual data using pen and paper.] LLMs are noted as additional limitations.
Dependent claim 9 recites,
“9. The method of claim 1, wherein the response to the natural language query includes a relevance score for the contextual data, and wherein the method further comprises: determining, by the one or more processors, whether the relevance score is above a predetermined threshold; [this relates to a human determining a relevance score using logic and reasoning in the human mind.] and displaying, by the one or more processors, via a user interface, the response based on the relevance score being above the predetermined threshold. [This relates to a human displaying a response using pen and paper.] No additional limitations present.
Dependent claim 10 recites,
“10. The method of claim 1, further comprising: receiving, by the one or more processors, a plurality of preliminary responses; [This relates to a human receiving a response using pen and paper.]
executing, by the one or more processors, the machine learning model using as input the plurality of preliminary responses to generate a plurality of preliminary response embeddings; [This relates to a human generating a plurality of response embeddings using pen and paper.]
querying, by the one or more processors, the vector database using the plurality of preliminary response embeddings to retrieve additional contextual data for the natural language query; and [This relates to a human retrieving additional contextual data using pen and paper.]
executing, by the one or more processors, a second LLM using as input the natural language query and the additional contextual data to generate a plurality of responses to the natural language query. [This relates to a human executing an LLM using physical processes of touch.] LLMs are noted as additional limitations.
As to Claim 12, Claim 12 is a system claim with limitations similar to that of claim 2 and is rejected under the same rationale.
As to Claim 13, Claim 13 is a system claim with limitations similar to that of claim 3 and is rejected under the same rationale.
As to Claim 14, Claim 14 is a system claim with limitations similar to that of claim 4 and is rejected under the same rationale.
As to Claim 15, Claim 15 is a system claim with limitations similar to that of claim 5 and is rejected under the same rationale.
As to Claim 16, Claim 16 is a system claim with limitations similar to that of claim 6 and is rejected under the same rationale.
As to Claim 17, Claim 17 is a system claim with limitations similar to that of claim 7 and is rejected under the same rationale.
As to Claim 18, Claim 18 is a system claim with limitations similar to that of claim 8 and is rejected under the same rationale.
As to Claim 20, Claim 20 is a non-transitory, computer-readable media claim with limitations similar to that of claim 4 and is rejected under the same rationale.
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.
Claims 1-20 are rejected under 35 U.S.C. 102a2 as being unpatentable over Shekhar (US Patent US 20250232134 A1), in view of Morales (U.S. Patent Number US 12282733 B1).
Regarding independent Claim 1, Shekhar teaches 1. A method comprising: receiving, by one or more processors, a natural language query; (see Shekhar [0015] “In some examples, a first LM-based natural language processing system may initially be used to process an input user request.”) executing, by the one or more processors, a first large language model (LLM) using as input the natural language query to generate a preliminary response to the natural language query; (see Shekhar [0010-0011] “Some natural language processing flows may employ one or more language models (LMs) in order to process natural language requests. Colloquially, some LMs may be referred to as “large” language models (LLMs) based on a number of parameters learned by the models during training. An LM is an artificial intelligence (AI) model that may be capable of processing and generating human-like text based on the latent information it has learned from vast amounts of training data. The term “large” refers to the size of these models in terms of the number of parameters or weights, which are the values that the model learns during training to make predictions and/or generate output such as text, synthesized speech, control instructions for control of other devices, etc. LMs may have millions, billions (or even more) parameters, which enable such models to capture complex patterns and nuances in language that, in turn, allow the models to understand and generate more natural-sounding text (relative to previous approaches). LMs are typically trained on massive datasets that include a wide variety of text from various sources, enabling the LMs to understand grammar, context, and the relationships between words, sentences, paragraphs, etc. Examples of LMs include the generative pre-trained transformer models (e.g., GPT-3, GPT-4), Pathways Language Model (PaLM), Large Language Model Meta Artificial Intelligence (LLaMA), as well as non-generative examples such as BERT (bidirectional encoder representations from Transformers), etc. [0011] In a generative context, an LM may generate text that is responsive to the input prompt provided to the LM. LMs excel at generating natural sounding text that appears as though it has been generated by a native speaker in the relevant language. In addition to fluency, generative LMs are able to generate detailed, relevant, and largely accurate responses to input prompts in many cases due to the large amount of latent information the generative LM has learned during training.”) executing, by the one or more processors, a machine learning model using as input the preliminary response to generate a preliminary response embedding; (see Shekhar [0030] “Concretely, for each attention unit the transformer model learns three weight matrices; the query weights Wo, the key weights W.sub.K, and the value weights W.sub.V. For each token i, the input embedding x.sub.i is multiplied with each of the three weight matrices to produce a query vector q.sub.i=x.sub.i W.sub.Q, a key vector k.sub.i=x.sub.i W.sub.K, and a value vector v.sub.i=x.sub.i W.sub.V. Attention weights are calculated using the query and key vectors: the attention weight a.sub.ij from token i to token j is the dot product between q.sub.i and k.sub.j. The attention weights are divided by the square root of the dimension of the key vectors, √{square root over (d.sub.k)}, which stabilizes gradients during training. The attention weights are then passed through a softmax layer that normalizes the weights to sum to 1. The fact that W.sub.Q and W.sub.K are different matrices allows attention to be non-symmetric: if token i attends to token j, this does not necessarily mean that token j will attend to token i. The output of the attention unit for token i is the weighted sum of the value vectors of all tokens, weighted by a.sub.ij, the attention from i to each token.”)
Shekhar does not specifically teach querying, by the one or more processors, a vector database using the preliminary response embedding to retrieve contextual data for the natural language query; and However, Morales does teach this limitation (see Morales 3:6-14) “(9)…the associated user supplied information (USI) extraction processes comprise a grant application information extraction process for retrieving data of question and answer pairs as USI information from prior grant applications, converting the USI information to USI vector data, and storing the USI vector data in a USI information and vector database that is accessible to the LLM and backend server.”)(see Morales (3:1-5) “(8) In some embodiments, the associated autofill grant application response generation processes comprise an automated context-specific code artifacts collection process. In particular, the automated context-specific code artifacts collection process carries out several automatic steps for identification, retrieval, and collection of relevant code artifacts associated with each field as a sub-process of the fully automated AI autofill grant application response generation process.”) executing, by the one or more processors, a second LLM using as input the natural language query and the contextual data to generate a response to the natural language query. (see Morales (1:48-55) “(10)…at least one large language model (LLM) that is trained on user supplied information (USI) from prior grant applications and other training data that provides a context for an AI system, with natural language processing (NPL), to understand requested information in fields of a grant application and to generate answers-custom to a particular user or entity...”)
Shekhar and Morales are in the same field of endeavor of signal processing, therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Shekhar to incorporate querying, by the one or more processors, a vector database using the preliminary response embedding to retrieve contextual data for the natural language query; and executing, by the one or more processors, a second LLM using as input the natural language query and the contextual data to generate a response to the natural language query of Morales. This allows the system to understand requested information as recognized by Morales (1:52).
As to Claim 2, Shekhar in view of Morales teaches 2. The method of claim 1,
Furthermore, Shekhar teaches further comprising executing, by the one or more processors, the machine learning model using as input domain data to generate the vector database. (see Shekhar [0027-0028] “Transformer models are machine learning models that include an encoder network and a decoder network. LMs are often implemented using transformer models. The encoder takes an input (e.g., a “prompt”) and generates feature representations (e.g., feature vectors, feature maps, etc.) of the input. The feature representation is then fed into a decoder that may generate an output based on the encodings. In natural language processing, transformer models take sequences of words as input. A transformer may receive a sentence and/or a paragraph (or any other quantum of text) comprising a sequence of words as an input. [0028] The encoder network of a transformer comprises a set of encoding layers that processes the input data one layer after another. Each encoder layer generates encodings (referred to herein as “tokens”). These tokens include feature representations (e.g., feature vectors and/or maps) that include information about which parts of the input data are relevant to each other. Each encoder layer passes its token output to the next encoder layer. The decoder network takes the tokens output by the encoder network and processes them using the encoded contextual information to generate an output (e.g., the aforementioned one-dimensional vector of tokens). The output data may be used to perform task-specific functions (e.g., action plan generation for an LM-based natural language processing flow, etc.). To encode contextual information from other inputs (e.g., combined feature representation), each encoder and decoder layer of a transformer uses an attention mechanism, which for each input, weighs the relevance of every other input and draws information from the other inputs to generate the output. Each decoder layer also has an additional attention mechanism which draws information from the outputs of previous decoders, prior to the decoder layer determining information from the encodings. Both the encoder and decoder layers have a feed-forward neural network for additional processing of the outputs, and contain residual connections and layer normalization steps.”)
As to Claim 3, Shekhar in view of Morales teaches 3. The method of claim 1,
Furthermore, Shekhar teaches further comprising fine-tuning, by the one or more processors, the first LLM using domain data used to generate the vector database. (see Shekhar [0026-0027] “Generally, in machine learning models, such as neural networks, after initialization, annotated training data may be used to generate a cost or “loss” function that describes the difference between expected output of the machine learning model and actual output. The parameters (e.g., weights and/or biases) of the machine learning model may be updated to minimize (or maximize) the cost. For example, the machine learning model may use a gradient descent (or ascent) algorithm to incrementally adjust the weights to cause the most rapid decrease (or increase) to the output of the loss function. The method of updating the parameters of the machine learning model is often referred to as back propagation. [0027] Transformer models are machine learning models that include an encoder network and a decoder network. LMs are often implemented using transformer models. The encoder takes an input (e.g., a “prompt”) and generates feature representations (e.g., feature vectors, feature maps, etc.) of the input. The feature representation is then fed into a decoder that may generate an output based on the encodings. In natural language processing, transformer models take sequences of words as input. A transformer may receive a sentence and/or a paragraph (or any other quantum of text) comprising a sequence of words as an input.”)
As to Claim 4, Shekhar in view of Morales teaches 4. The method of claim 1,
Furthermore, Shekhar teaches further comprising: executing, by the one or more processors, an evaluation model using as input the response to determine an accuracy score for the response; and (see Shekhar [0059] The LM orchestrator 230 may be configured for generating the prompt to be used by the LM 260 to determine an action responsive to user input. As shown in FIG. 2, the LM orchestrator 230 receives (at step 1) input query 106. In some instances, the input query 106 may correspond to a text or tokenized representation of a user input. For example, prior to the LM orchestrator 230 receiving the input query 106, another component (e.g., an ASR component) may receive audio data representing the user input. The ASR component may perform ASR processing on the audio data to determine ASR output data corresponding to the user input. As previously described, an ASR component may determine ASR data that includes an ASR N-best list including multiple ASR hypotheses and corresponding confidence scores representing what the user may have said. The ASR hypotheses may include text data, token data, etc. as representing the input utterance. The confidence score of each ASR hypothesis may indicate the ASR component's level of confidence that the corresponding hypothesis represents what the user said. The ASR component may also determine token scores corresponding to each token/word of the ASR hypothesis, where the token score indicates the ASR component's level of confidence that the respective token/word was spoken by the user. The token scores may be identified as an entity score when the corresponding token relates to an entity. In some instances, the input query 106 may include a top scoring ASR hypothesis of the ASR data.”)
Furthermore Morales teaches based on the accuracy score being below a predetermined threshold, performing one or more of: (See Morales (14:53-15:27) “(43)…This results in returning either an invalid response (e.g., “<<UNABLE>>”) or a valid response…”) transmitting, by the one or more processors, the response to a user device; (14:53-15:27) “(43)… Next, the semi-automated AI autofill grant application process 400 proceeds to a step at which the server utilizes the API for post-processing of the generated response for return to the browser extension and, ultimately, display for the end user to view (at 455).”) executing, by the one or more processors, the first LLM using as input the natural language query and the response; or (14:53-15:27) “(43)… again and prompts the LLM to answer the question (which was generated by the LLM at 435 based on the current fields HTML code artifacts),”) executing, by the one or more processors, the machine learning model using as input the response to generate a response embedding. (see Morales (14:53-15:27) “(43)… The semi-automated AI autofill grant application process 400 proceeds to the next step at which the server transforms the question-generated by the LLM-into a vector representation using an embedding model (at 440).”)
Shekhar in view of Morales are in the same field of endeavor of signal processing, therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of combination of Shekhar and Morales to incorporate teaches based on the accuracy score being below a predetermined threshold, performing one or more of: transmitting, by the one or more processors, the response to a user device; executing, by the one or more processors, the first LLM using as input the natural language query and the response; or executing, by the one or more processors, the machine learning model using as input the response to generate a response embedding of Morales. This allows the system to understand requested information as recognized by Morales (1:52).
As to Claim 5, Shekhar in view of Morales teaches 5. The method of claim 1,
Furthermore, Morales teaches further comprising: executing, by the one or more processors, the first LLM using as input the natural language query and the response to generate a second preliminary response; (See Morales (16:50-54) “(47… the user can always repeat the process for the application or can also repeat the process with other applications as well.”) executing, by the one or more processors, the machine learning model using as input the second preliminary response to generate a second preliminary response embedding; (See Morales (14:65-15:3) “(43)… The semi-automated AI autofill grant application process 400 proceeds to the next step at which the server transforms the question-generated by the LLM-into a vector representation using an embedding model (at 440)”) querying, by the one or more processors, the vector database using the second preliminary response embedding to retrieve second contextual data; and (see Morales (15:2-10) “(43)… Next, the semi-automated AI autofill grant application process 400 moves forward to a step at which the server uses the vector representation of the LLM's generated question to identify pieces of semantically relevant USI records in the selected program profile (at 445), followed by the server assessing the similarity of this vector to the vectors of all stored USI information with selection of only the top few records.”) executing, by the one or more processors, the second LLM using as input the natural language query and the second contextual data. (see Moarales (15:9-18) “(43) … The semi-automated AI autofill grant application process 400 continues to the next step at which the server invokes the LLM again and prompts the LLM to answer the question (which was generated by the LLM at 435 based on the current fields HTML code artifacts), followed by providing the top few most relevant USI records to the LLM and steering the LLM to answer the question using only the retrieved USI information (at 450).”)
Shekhar in view of Morales are in the same field of endeavor of signal processing, therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of combination of Shekhar and Morales to incorporate teaches further comprising: executing, by the one or more processors, the first LLM using as input the natural language query and the response to generate a second preliminary response; executing, by the one or more processors, the machine learning model using as input the second preliminary response to generate a second preliminary response embedding; querying, by the one or more processors, the vector database using the second preliminary response embedding to retrieve second contextual data; and executing, by the one or more processors, the second LLM using as input the natural language query and the second contextual data of Morales. This allows the system to understand requested information as recognized by Morales (1:52).
As to Claim 6, Shekhar in view of Morales teaches 6. The method of claim 1,
Furthermore, Morales teaches further comprising: executing, by the one or more processors, the machine learning model using as input the response to generate a response embedding; (see Morales (14:66-15:2) “(43) …The semi-automated AI autofill grant application process 400 proceeds to the next step at which the server transforms the question-generated by the LLM-into a vector representation using an embedding model (at 440)”) querying, by the one or more processors, the vector database using the response embedding to retrieve second contextual data; and (see Morales (15:2-10) “(43)… Next, the semi-automated AI autofill grant application process 400 moves forward to a step at which the server uses the vector representation of the LLM's generated question to identify pieces of semantically relevant USI records in the selected program profile (at 445), followed by the server assessing the similarity of this vector to the vectors of all stored USI information with selection of only the top few records.”) executing, by the one or more processors, the second LLM using as input the natural language query and the second contextual data. (see Morales (15:9-18) “(43) … The semi-automated AI autofill grant application process 400 continues to the next step at which the server invokes the LLM again and prompts the LLM to answer the question (which was generated by the LLM at 435 based on the current fields HTML code artifacts), followed by providing the top few most relevant USI records to the LLM and steering the LLM to answer the question using only the retrieved USI information (at 450).”)(examiner notes the applicant defines in claim 7 and in the specification [0082] …the first LLM and the second LLM are the same LLM.)
Shekhar in view of Morales are in the same field of endeavor of signal processing, therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of combination of Shekhar and Morales to incorporate teaches further comprising: executing, by the one or more processors, the machine learning model using as input the response to generate a response embedding querying, by the one or more processors, the vector database using the response embedding to retrieve second contextual data; and executing, by the one or more processors, the second LLM using as input the natural language query and the second contextual data of Morales. This allows the system to understand requested information as recognized by Morales (1:52).
As to Claim 7, Shekhar in view of Morales teaches 7. The method of claim 1,
Furthermore, Shekhar teaches wherein the first LLM and the second LLM are the same LLM. (see Shekhar [0064] “In other embodiments, the preliminary action plan generation component 240 may be an LM, similar to the LM 260. In such embodiments, the architecture (e.g., LM 80) may include a further component configured to generate a prompt to be provided to the LM (e.g., similar to the LM prompt generation component 250) or the prompt may be generated by the LM prompt generation component 250. The component may generate a prompt (e.g., according to a template) including the input query 106 and instructions to determine the one or more portions of data (or types of data) relevant to the processing of the user input. The LM may process the prompt and generate model output data representing the one or more portions of data (or types of data). The preliminary action plan generation component 240 may process the model output data to determine the prompt generation action plan data 245.”)
As to Claim 8, Shekhar in view of Morales teaches 8. The method of claim 1,
Furthermore, Morales teaches further comprising: executing, by the one or more processors, the machine learning model using as input the natural language query to generate a natural language query embedding; and (see Morales (14:66-15:2) “(43) …The semi-automated AI autofill grant application process 400 proceeds to the next step at which the server transforms the question-generated by the LLM-into a vector representation using an embedding model (at 440)”) querying, by the one or more processors, the vector database using the natural language query embedding to retrieve additional contextual data for the natural language query, (see Morales (15:2-10) “(43)… Next, the semi-automated AI autofill grant application process 400 moves forward to a step at which the server uses the vector representation of the LLM's generated question to identify pieces of semantically relevant USI records in the selected program profile (at 445), followed by the server assessing the similarity of this vector to the vectors of all stored USI information with selection of only the top few records.”) wherein executing, by the one or more processors, the second LLM includes executing, by the one or more processors, the second LLM using as input the contextual data and the additional contextual data. (see Morales (15:9-18) “(43) … The semi-automated AI autofill grant application process 400 continues to the next step at which the server invokes the LLM again and prompts the LLM to answer the question (which was generated by the LLM at 435 based on the current fields HTML code artifacts), followed by providing the top few most relevant USI records to the LLM and steering the LLM to answer the question using only the retrieved USI information (at 450).”)(examiner notes the applicant defines in claim 7 and in the specification [0082] …the first LLM and the second LLM are the same LLM.)
Shekhar in view of Morales are in the same field of endeavor of signal processing, therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of combination of Shekhar and Morales to incorporate teaches further comprising: executing, by the one or more processors, the machine learning model using as input the natural language query to generate a natural language query embedding; and querying, by the one or more processors, the vector database using the natural language query embedding to retrieve additional contextual data for the natural language query, wherein executing, by the one or more processors, the second LLM includes executing, by the one or more processors, the second LLM using as input the contextual data and the additional contextual data of Morales. This allows the system to understand requested information as recognized by Morales (1:52).
As to Claim 9, Shekhar in view of Morales teaches 9. The method of claim 1,
Furthermore, Shekhar teaches wherein the response to the natural language query includes a relevance score for the contextual data, and wherein the method further comprises: (see Shekhar [0059] The LM orchestrator 230 may be configured for generating the prompt to be used by the LM 260 to determine an action responsive to user input. As shown in FIG. 2, the LM orchestrator 230 receives (at step 1) input query 106. In some instances, the input query 106 may correspond to a text or tokenized representation of a user input. For example, prior to the LM orchestrator 230 receiving the input query 106, another component (e.g., an ASR component) may receive audio data representing the user input. The ASR component may perform ASR processing on the audio data to determine ASR output data corresponding to the user input. As previously described, an ASR component may determine ASR data that includes an ASR N-best list including multiple ASR hypotheses and corresponding confidence scores representing what the user may have said. The ASR hypotheses may include text data, token data, etc. as representing the input utterance. The confidence score of each ASR hypothesis may indicate the ASR component's level of confidence that the corresponding hypothesis represents what the user said. The ASR component may also determine token scores corresponding to each token/word of the ASR hypothesis, where the token score indicates the ASR component's level of confidence that the respective token/word was spoken by the user. The token scores may be identified as an entity score when the corresponding token relates to an entity. In some instances, the input query 106 may include a top scoring ASR hypothesis of the ASR data.”)
Furthermore Morales teaches determining, by the one or more processors, whether the relevance score is above a predetermined threshold; and (see Morales (15:2-10) “(43)… Next, the semi-automated AI autofill grant application process 400 moves forward to a step at which the server uses the vector representation of the LLM's generated question to identify pieces of semantically relevant USI records in the selected program profile (at 445), followed by the server assessing the similarity of this vector to the vectors of all stored USI information with selection of only the top few records.”) displaying, by the one or more processors, via a user interface, the response based on the relevance score being above the predetermined threshold. (See Morales (14:53-15:27) “(43)…This results in returning either an invalid response (e.g., “<<UNABLE>>”) or a valid response…”)
Shekhar in view of Morales are in the same field of endeavor of signal processing, therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of combination of Shekhar and Morales to incorporate teaches determining, by the one or more processors, whether the relevance score is above a predetermined threshold; and displaying, by the one or more processors, via a user interface, the response based on the relevance score being above the predetermined threshold of Morales. This allows the system to understand requested information as recognized by Morales (1:52).
As to Claim 10, Shekhar in view of Morales teaches 10. The method of claim 1,
Furthermore, Morales teaches further comprising: receiving, by the one or more processors, a plurality of preliminary responses; (6:57-65) “(17) In some embodiments, the associated user supplied information (USI) extraction processes comprise a grant application information extraction process for retrieving data of question and answer pairs as USI information from prior grant applications, converting the USI information to USI vector data, and storing the USI vector data in a USI information and vector database that is accessible to the LLM and backend server”) executing, by the one or more processors, the machine learning model using as input the plurality of preliminary responses to generate a plurality of preliminary response embeddings; (see Morales (14:65-15:2) “(43) …The semi-automated AI autofill grant application process 400 proceeds to the next step at which the server transforms the question-generated by the LLM-into a vector representation using an embedding model (at 440)”) querying, by the one or more processors, the vector database using the plurality of preliminary response embeddings to retrieve additional contextual data for the natural language query; and (see Morales (15:2-18) (43… Next, the semi-automated AI autofill grant application process 400 moves forward to a step at which the server uses the vector representation of the LLM's generated question to identify pieces of semantically relevant USI records in the selected program profile (at 445), followed by the server assessing the similarity of this vector to the vectors of all stored USI information with selection of only the top few records. The semi-automated AI autofill grant application process 400 continues to the next step at which the server invokes the LLM again and prompts the LLM to answer the question (which was generated by the LLM at 435 based on the current fields HTML code artifacts), followed by providing the top few most relevant USI records to the LLM and steering the LLM to answer the question using only the retrieved USI information (at 450).”) executing, by the one or more processors, a second LLM using as input the natural language query and the additional contextual data to generate a plurality of responses to the natural language query. (see Morales (15:10-18) “(43)… the server invokes the LLM again and prompts the LLM to answer the question (which was generated by the LLM at 435 based on the current fields HTML code artifacts), followed by providing the top few most relevant USI records to the LLM and steering the LLM to answer the question using only the retrieved USI information (at 450).”)
Shekhar in view of Morales are in the same field of endeavor of signal processing, therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of combination of Shekhar and Morales to incorporate teaches further comprising: receiving, by the one or more processors, a plurality of preliminary responses; executing, by the one or more processors, the machine learning model using as input the plurality of preliminary responses to generate a plurality of preliminary response embeddings; querying, by the one or more processors, the vector database using the plurality of preliminary response embeddings to retrieve additional contextual data for the natural language query; and executing, by the one or more processors, a second LLM using as input the natural language query and the additional contextual data to generate a plurality of responses to the natural language query of Morales. This allows the system to understand requested information as recognized by Morales (1:52).
As to independent Claim 11, Claim 11 is a system claim with limitations similar to that of claim 1 and is rejected under the same rationale. Furthermore, Shekhar teaches 11. A system comprising: one or more processors; and one or more non-transitory, computer-readable media including instructions which, when executed by the one or more processors, cause the one or more processors to: (see Shekhar [0093] “…In operation, each of these devices (or groups of devices) may include non-transitory computer-readable and computer-executable instructions that reside on the respective device,…”)
As to independent Claim 19, Claim 19 is a non-transitory, computer-readable media claim with limitations similar to that of claim 1 and is rejected under the same rationale. Furthermore, Shekhar teaches 19. One or more non-transitory, computer-readable media including instructions which, when executed by one or more processors, cause the one or more processors to: (see Shekhar [0093] “…In operation, each of these devices (or groups of devices) may include non-transitory computer-readable and computer-executable instructions that reside on the respective device,…”)
As to Claim 12, Claim 12 is a system claim with limitations similar to that of claim 2 and is rejected under the same rationale.
As to Claim 13, Claim 13 is a system claim with limitations similar to that of claim 3 and is rejected under the same rationale.
As to Claim 14, Claim 14 is a system claim with limitations similar to that of claim 4 and is rejected under the same rationale.
As to Claim 15, Claim 15 is a system claim with limitations similar to that of claim 5 and is rejected under the same rationale.
As to Claim 16, Claim 16 is a system claim with limitations similar to that of claim 6 and is rejected under the same rationale.
As to Claim 17, Claim 17 is a system claim with limitations similar to that of claim 7 and is rejected under the same rationale.
As to Claim 18, Claim 18 is a system claim with limitations similar to that of claim 8 and is rejected under the same rationale.
As to Claim 20, Claim 20 is a non-transitory, computer-readable media claim with limitations similar to that of claim 4 and is rejected under the same rationale.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KRISTEN MICHELLE MASTERS whose telephone number is (703)756-1274. The examiner can normally be reached M-F 8:30 AM - 5:00 PM.
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, Pierre Louis Desir can be reached at 571-272-7799. 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.
/KRISTEN MICHELLE MASTERS/Examiner, Art Unit 2659
/PIERRE LOUIS DESIR/Supervisory Patent Examiner, Art Unit 2659
Prosecution Insights