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 .
This action is responsive to the application filed 01/25/2024. Claims 1-20 are presented for
examination.
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.
Claim 1
Step 1: The claim recites “An automated suspicious activity report (SAR) narrative system configured to automate SAR narrative generations using prompts to a generative artificial intelligence (AI) service, the automated SAR narrative system comprising:”; therefore, it is directed to the statutory category of a machine.
Step 2A Prong 1: The claim recites, inter alia:
extracting, from the plurality of SAR fields of the SAR, the SAR data corresponding to one or more of the prompt input fields for the prompt template: These limitations recite a mentally performable process with the aid of pen and paper of using observation and judgement to extract the SAR data corresponding to one or more of the prompt input fields for the prompt template.
creating an updated prompt based on the extracted SAR data and the prompt template, wherein the creating includes entering the extracted SAR data to the one or more of the prompt input fields: These limitations recite a mentally performable process with the aid of pen and paper of using observation and judgement to create an updated prompt based on the extracted SAR data and the prompt template, wherein the creating includes entering the extracted SAR data to the one or more of the prompt input fields.
calling the generative AI service using the updated prompt: These limitations recite a mentally performable process with the aid of pen and paper of calling the generative AI service using the updated prompt, which is similar to performing a mental process in a computer environment per MPEP 2106.04(a)(2)(III)(C)(2).
Thus, the claim recites a judicial exception.
Step 2A Prong 2: This judicial exception is not integrated into a practical application. The additional elements of the claim are as follows:
An automated suspicious activity report (SAR) narrative system configured to automate SAR narrative generations using prompts to a generative artificial intelligence (AI) service, the automated SAR narrative system comprising: These additional elements are recited at a high level of generality and merely indicate a field of use or technological environment in which to apply a judicial exception, e.g. An automated suspicious activity report (SAR) narrative system, to a particular technological environment or field of use, e.g. configured to automate SAR narrative generations using prompts to a generative artificial intelligence (AI) service. See MPEP 2106.05(h). Elements that use or interact with the judicial exception do not integrate the judicial exception into a practical application.
a processor and a computer readable medium operably coupled thereto, the computer readable medium comprising a plurality of instructions stored in association therewith that are accessible to, and executable by, the processor, to perform narrative generation operations which comprise: These additional elements are recited at a high level of generality and amount to invoking computers or other machinery merely as a tool to apply the underlying judicial exception. See MPEP § 2106.05(f).
receiving a SAR having a plurality of SAR fields and SAR data in one or more of the plurality of SAR fields: These additional elements amount to insignificant extra-solution activity in the form of mere data gathering per MPEP § 2106.05(g).
loading a prompt template into a local memory of the automated SAR narrative system: These additional elements amount to insignificant extra-solution activity in the form of selecting a particular data source or type of data to be manipulated MPEP § 2106.05(g).
wherein the prompt template is associated with generating a SAR narrative by the generative AI service, and wherein the prompt template includes instructions to the generative AI service that cause a generation of the SAR narrative for the SAR, wherein the prompt template further includes prompt input fields for the generation of the SAR narrative, and wherein the instructions are developed so that corresponding text generated using the prompt template meets guidelines for the SAR narrative established by a financial crime regulatory or enforcement body: These additional elements are recited at a high level of generality and merely indicate a field of use or technological environment in which to apply a judicial exception, e.g. the prompt template, to a particular technological environment or field of use, e.g. is associated with generating a SAR narrative by the generative AI service, and wherein the prompt template includes instructions to the generative AI service that cause a generation of the SAR narrative for the SAR, wherein the prompt template further includes prompt input fields for the generation of the SAR narrative, and wherein the instructions are developed so that corresponding text generated using the prompt template meets guidelines for the SAR narrative established by a financial crime regulatory or enforcement body. See MPEP 2106.05(h). Elements that use or interact with the judicial exception do not integrate the judicial exception into a practical application.
wherein the calling comprises prompting, via one or more text commands to the generative AI service, the generative AI service to provide a response to the instructions based on the extracted SAR data in the one or more of the prompt input fields: These additional elements are recited at a high level of generality and merely indicate a field of use or technological environment in which to apply a judicial exception, e.g. the calling, to a particular technological environment or field of use, e.g. comprises prompting the generative AI service to provide a response to the instructions based on the extracted SAR data in the one or more of the prompt input fields, via one or more text commands to the generative AI service. See MPEP 2106.05(h). Elements that use or interact with the judicial exception do not integrate the judicial exception into a practical application.
and generating and storing the SAR narrative in a data container based on the response: These additional elements amount to insignificant extra-solution activity in the form of selecting a particular data source or type of data to be manipulated MPEP § 2106.05(g).
Thus, the way in which the additional elements use or interact with the judicial exception do not integrate the judicial exception into a practical application.
Step 2B: The additional elements from Step 2A Prong 2 include generally linking the use of the judicial exception to indicate a field of use or technological environment and invoking generic computer components to apply the underlying judicial exception. The additional elements also include insignificant extra-solution activity of data gathering recited by “receiving a SAR having a plurality of SAR fields and SAR data in one or more of the plurality of SAR fields” which are well-understood routine and conventional activities similar to presenting offers and gathering statistics per MPEP 2106.05(d)(II), “loading a prompt template into a local memory of the automated SAR narrative system” which are well-understood routine and conventional activities similar to receiving or transmitting data over a network per MPEP 2106.05(d)(II), and “generating and storing the SAR narrative in a data container based on the response” which are well-understood routine and conventional activities similar to storing and retrieving information in memory per MPEP 2106.05(d)(II). Thus, the additional elements, viewed individually or in combination, do not provide an inventive concept or otherwise amount to significantly more than the abstract idea itself. See MPEP § 2106.05.
Claim 2
Step 1: A machine, as above.
Step 2A Prong 1: The claim recites the abstract ideas as the judicial exception of claim 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application. The additional elements of the claim are as follows:
wherein the calling the generative AI service uses a prompting technique for a single zero-shot prompting call having the instructions with the extracted SAR data in a single interaction call made to the generative AI service: These additional elements are recited at a high level of generality and merely indicate a field of use or technological environment in which to apply a judicial exception, e.g. the calling the generative AI service, to a particular technological environment or field of use, e.g. uses a prompting technique for a single zero-shot prompting call having the instructions with the extracted SAR data in a single interaction call made to the generative AI service. See MPEP 2106.05(h). Elements that use or interact with the judicial exception do not integrate the judicial exception into a practical application.
Thus, the way in which the additional elements use or interact with the judicial exception do not integrate the judicial exception into a practical application.
Step 2B: The additional elements from Step 2A Prong 2 include generally linking the use of the judicial exception to indicate a field of use or technological environment. Thus, the additional elements, viewed individually or in combination, do not provide an inventive concept or otherwise amount to significantly more than the abstract idea itself. See MPEP § 2106.05.
Claim 3
Step 1: A machine, as above.
Step 2A Prong 1: The claim recites the abstract ideas as the judicial exception of claim 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application. The additional elements of the claim are as follows:
wherein the calling the generative AI service uses a prompting technique for a generation-by-parts of the SAR narrative having the instructions with the extracted SAR data in a plurality of parallel calls made to the generative AI service for each section of the SAR narrative, and wherein parts of the response to the plurality of parallel calls are received and combined to form the SAR narrative by the generation-by-parts: These additional elements are recited at a high level of generality and merely indicate a field of use or technological environment in which to apply a judicial exception, e.g. the calling the generative AI service, to a particular technological environment or field of use, e.g. uses a prompting technique for a generation-by-parts of the SAR narrative having the instructions with the extracted SAR data in a plurality of parallel calls made to the generative AI service for each section of the SAR narrative, and wherein parts of the response to the plurality of parallel calls are received and combined to form the SAR narrative by the generation-by-parts. See MPEP 2106.05(h). Elements that use or interact with the judicial exception do not integrate the judicial exception into a practical application.
Thus, the way in which the additional elements use or interact with the judicial exception do not integrate the judicial exception into a practical application.
Step 2B: The additional elements from Step 2A Prong 2 include generally linking the use of the judicial exception to indicate a field of use or technological environment. Thus, the additional elements, viewed individually or in combination, do not provide an inventive concept or otherwise amount to significantly more than the abstract idea itself. See MPEP § 2106.05.
Claim 4
Step 1: A machine, as above.
Step 2A Prong 1: The claim recites the abstract ideas as the judicial exception of claim 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application. The additional elements of the claim are as follows:
wherein the calling the generative AI service uses a prompting technique for few-shot prompting calls having the instructions with the extracted SAR data in a set of calls made to the generative AI service with one or more examples of an input-output pair for another SAR and another SAR narrative: These additional elements are recited at a high level of generality and merely indicate a field of use or technological environment in which to apply a judicial exception, e.g. the calling the generative AI service, to a particular technological environment or field of use, e.g. uses a prompting technique for few-shot prompting calls having the instructions with the extracted SAR data in a set of calls made to the generative AI service with one or more examples of an input-output pair for another SAR and another SAR narrative. See MPEP 2106.05(h). Elements that use or interact with the judicial exception do not integrate the judicial exception into a practical application.
Thus, the way in which the additional elements use or interact with the judicial exception do not integrate the judicial exception into a practical application.
Step 2B: The additional elements from Step 2A Prong 2 include generally linking the use of the judicial exception to indicate a field of use or technological environment. Thus, the additional elements, viewed individually or in combination, do not provide an inventive concept or otherwise amount to significantly more than the abstract idea itself. See MPEP § 2106.05.
Claim 5
Step 1: A machine, as above.
Step 2A Prong 1: The claim recites the abstract ideas as the judicial exception of claim 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application. The additional elements of the claim are as follows:
wherein the instructions include one or more sub-instructions configured to handle hallucinations by the generative AI service that have other data not included in the extracted SAR data in the response from the generative AI service: These additional elements are recited at a high level of generality and merely indicate a field of use or technological environment in which to apply a judicial exception, e.g. the instructions, to a particular technological environment or field of use, e.g. include one or more sub-instructions configured to handle hallucinations by the generative AI service that have other data not included in the extracted SAR data in the response from the generative AI service. See MPEP 2106.05(h). Elements that use or interact with the judicial exception do not integrate the judicial exception into a practical application.
wherein the one or more sub-instructions include a statement to the generative AI to utilize only the extracted SAR data found in the one or more of the prompt input fields in the response: These additional elements are recited at a high level of generality and merely indicate a field of use or technological environment in which to apply a judicial exception, e.g. the one or more sub-instructions, to a particular technological environment or field of use, e.g. include a statement to the generative AI to utilize only the extracted SAR data found in the one or more of the prompt input fields in the response. See MPEP 2106.05(h). Elements that use or interact with the judicial exception do not integrate the judicial exception into a practical application.
Thus, the way in which the additional elements use or interact with the judicial exception do not integrate the judicial exception into a practical application.
Step 2B: The additional elements from Step 2A Prong 2 include generally linking the use of the judicial exception to indicate a field of use or technological environment. Thus, the additional elements, viewed individually or in combination, do not provide an inventive concept or otherwise amount to significantly more than the abstract idea itself. See MPEP § 2106.05.
Claim 6
Step 1: A machine, as above.
Step 2A Prong 1: The claim recites the abstract ideas as the judicial exception of claim 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application. The additional elements of the claim are as follows:
wherein the generative AI service comprises at least one generative AI model including a large language model (LLM), and wherein the generative AI service provides a conversational AI based on the LLM that processes input conversational text corresponding to the updated prompt and provides output conversational text having the SAR narrative: These additional elements are recited at a high level of generality and amount to invoking computers or other machinery merely as a tool to apply the underlying judicial exception. See MPEP § 2106.05(f).
Thus, the way in which the additional elements use or interact with the judicial exception do not integrate the judicial exception into a practical application.
Step 2B: The additional elements from Step 2A Prong 2 include invoking generic computer components to apply the underlying judicial exception. Thus, the additional elements, viewed individually or in combination, do not provide an inventive concept or otherwise amount to significantly more than the abstract idea itself. See MPEP § 2106.05.
Claim 7
Step 1: A machine, as above.
Step 2A Prong 1: The claim recites the abstract ideas as the judicial exception of claim 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application. The additional elements of the claim are as follows:
returning a notification to a SAR reporting application after the generating and the storing the SAR narrative, wherein the notification identifies the data container stored and indicates that the SAR narrative is available for use with the SAR: These additional elements amount to insignificant extra-solution activity in the form of mere data gathering per MPEP § 2106.05(g).
Thus, the way in which the additional elements use or interact with the judicial exception do not integrate the judicial exception into a practical application.
Step 2B: The additional elements from Step 2A Prong 2 include insignificant extra-solution activity of data gathering recited by “returning a notification to a SAR reporting application after the generating and the storing the SAR narrative” which are well-understood routine and conventional activities similar to electronic recordkeeping per MPEP 2106.05(d)(II). Thus, the additional elements, viewed individually or in combination, do not provide an inventive concept or otherwise amount to significantly more than the abstract idea itself. See MPEP § 2106.05.
Claim 8
Step 1: A machine, as above.
Step 2A Prong 1: The claim recites the abstract ideas as the judicial exception of claim 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application. The additional elements of the claim are as follows:
wherein the calling the generative AI service is done in a specified order designated by the prompt template selected for the generation of the SAR narrative: These additional elements are recited at a high level of generality and merely indicate a field of use or technological environment in which to apply a judicial exception, e.g. the calling the generative AI service, to a particular technological environment or field of use, e.g. is done in a specified order designated by the prompt template selected for the generation of the SAR narrative. See MPEP 2106.05(h). Elements that use or interact with the judicial exception do not integrate the judicial exception into a practical application.
Thus, the way in which the additional elements use or interact with the judicial exception do not integrate the judicial exception into a practical application.
Step 2B: The additional elements from Step 2A Prong 2 include generally linking the use of the judicial exception to indicate a field of use or technological environment. Thus, the additional elements, viewed individually or in combination, do not provide an inventive concept or otherwise amount to significantly more than the abstract idea itself. See MPEP § 2106.05.
Claim 9
Step 1: A machine, as above.
Step 2A Prong 1: The claim recites the abstract ideas of claim 1 as well as, inter alia:
performing a set of data pre-processing and data cleaning steps on the SAR data in the SAR: These limitations recite a mentally performable process with the aid of pen and paper of using observation and judgement to perform data pre-processing and data cleaning steps on the SAR data in the SAR.
Thus, the claim recites a judicial exception.
Step 2A Prong 2 & Step 2B: There are no additional elements recited so the claim does not provide a
practical application and is not considered to be significantly more. As such, the claim is patent
ineligible.
Claims 10-18
Step 1: These claims are directed to “A method to automate suspicious activity report (SAR) narrative generations using prompts to a generative artificial intelligence (AI) service for an automated SAR narrative system, the method comprising:”; therefore, it is directed the statutory category of a process.
Step 2A Prong 1: Claims 10-18 recite the same judicial exception as Claims 1-9, respectively.
Step 2A Prong 2: The judicial exception recited in these claims are not integrated into a practical application. The analysis at this step for 10-18 mirrors that of Claims 1-9, respectively.
Step 2B: The additional elements from Step 2A Prong 2 do not contain significantly more than the judicial exception for these claims. The analysis at this step for Claims 10-18 mirrors that of Claims 1-9, respectively.
Claims 19-20
Step 1: This claim recites "A non-transitory computer-readable medium having stored thereon computer-readable instructions executable to automate suspicious activity report (SAR) narrative generations using prompts to a generative artificial intelligence (AI) service for an automated SAR narrative system, the computer-readable instructions executable to perform narrative generation operations which comprise:"; therefore, it is directed to the statutory category of an article of manufacture.
Step 2A Prong 1: Claims 19-20 recite the same judicial exception as Claims 1-2, respectively.
Step 2A Prong 2: The judicial exception recited in these claims are not integrated into a practical application. The only difference between Claims 19-20 and Claims 1-2, is that Claims 19-20 are directed to "A non-transitory computer-readable medium having stored thereon computer-readable instructions executable to automate suspicious activity report (SAR) narrative generations using prompts to a generative artificial intelligence (AI) service for an automated SAR narrative system, the computer-readable instructions executable to perform narrative generation operations which comprise”. However, mere recitation that a judicial exception is to be performed using generic computer equipment in their ordinary capacity, i.e. a non-transitory computer-readable medium having stored thereon computer-readable instructions executable to automate suspicious activity report (SAR) narrative generations using prompts to a generative artificial intelligence (AI) service for an automated SAR narrative system, the computer-readable instructions executable to perform narrative generation operations which comprise, cannot meaningfully integrate the judicial exception into a practical application. See MPEP 2106.05(f). With that exception, the analysis at this step for Claims 19-20 mirrors that of Claims 1-2, respectively.
Step 2B: The additional elements from Step 2A Prong 2 do not contain significantly more than the judicial exception for these claims. The only difference between Claims 19-20 and Claims 1-2, is that Claims 19-20 are directed to "A non-transitory computer-readable medium having stored thereon computer-readable instructions executable to automate suspicious activity report (SAR) narrative generations using prompts to a generative artificial intelligence (AI) service for an automated SAR narrative system, the computer-readable instructions executable to perform narrative generation operations which comprise”. However, mere recitation that a judicial exception is to be performed using generic computer equipment in their ordinary capacity, i.e. a non-transitory computer-readable medium having stored thereon computer-readable instructions executable to automate suspicious activity report (SAR) narrative generations using prompts to a generative artificial intelligence (AI) service for an automated SAR narrative system, the computer-readable instructions executable to perform narrative generation operations which comprise, cannot amount to significantly more than the judicial exception. See MPEP 2106.05(f). With that exception, the analysis at this step for Claims 19-20 mirrors that of Claims 1-2, respectively.
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 1-4, 6, 8-13, 15, & 17-20 are rejected under 35 U.S.C. 103 as being unpatentable over Pati et al. (US 2022/0044199 A1, published 02/10/2022), hereafter Pati, in view of Saxena (US 2024/0330579 A1, filed 05/23/2023), hereafter Saxena, and in view of Guang et al. (US 12073186 B1, filed 09/30/2021), hereafter Guang.
Regarding independent claim 1, Pati teaches an automated suspicious activity report (SAR) narrative system configured to automate SAR narrative generations using prompts to a generative artificial intelligence (AI) service ([Abstract] a system for automatically generating a two-part readable SAR from data regarding financial transactions using a generative artificial intelligence service), the automated SAR narrative system comprising:
a processor and a computer readable medium operably coupled thereto, the computer readable medium comprising a plurality of instructions stored in association therewith that are accessible to, and executable by, the processor, to perform narrative generation operations which comprise ([0013] discusses the use of a processor and a memory; [0036] discusses the non-transitory storage medium may store instructions to perform operations and processes associated with narrative generation);
receiving a SAR having a plurality of SAR fields and SAR data in one or more of the plurality of SAR fields ([0095] discusses receiving a SAR template having a predefined construction and thus, contains SAR fields and prepopulated SAR data);
wherein the instructions are developed so that corresponding text generated using the prompt template meets guidelines for the SAR narrative established by a financial crime regulatory or enforcement body ([0005 & 0010] discusses the goal of their specific system is to automate the SAR narrative process while conforming to the guidelines established by a financial crime regulatory or enforcement body and thus, the text generated using the prompt template meets guidelines established);
the generative AI service to provide a response ([0112] discusses generating a SAR report using an NLG translation model);
and generating and storing the SAR narrative ([0017] discusses combining a plurality of SAR reports into one collective SAR, implying each SAR narrative is stored after generation).
Pati does not expressly disclose loading a prompt template into a local memory of the automated SAR narrative system, wherein the prompt template is associated with generating a SAR narrative by the generative AI service and wherein the prompt template includes instructions to the generative AI service that cause a generation of the SAR narrative for the SAR, wherein the prompt template further includes prompt input fields for the generation of the SAR narrative; extracting, from the plurality of SAR fields of the SAR, the SAR data corresponding to one or more of the prompt input fields for the prompt template; creating an updated prompt based on the extracted SAR data and the prompt template, wherein the creating includes entering the extracted SAR data to the one or more of the prompt input fields; calling the generative AI service using the updated prompt, wherein the calling comprises prompting, via one or more text commands to the generative AI service, the generative AI service to provide a response to the instructions based on the extracted SAR data in the one or more of the prompt input fields; receiving the response to the updated prompt from the generative AI service responsive to the calling; and generating and storing the SAR narrative in a data container based on the response.
However, Saxena teaches a system for prompt template loading for LLM, including loading a prompt template into a local memory, wherein the prompt template includes instructions to the generative AI service that cause a generation of the narrative, and wherein the prompt template further includes prompt input fields for the generation of the narrative ([0018] discusses obtaining and loading a prompt template that includes parameters for generating text; [0028-0029] further discusses the prompt template includes parameters and instructions for generating specific text as well as prompt input fields for generating text); extracting data corresponding to one or more of the prompt input fields for the prompt template ([0033] discusses retrieving the data corresponding to the prompt input fields and parameters of the selected prompt template); creating an updated prompt based on the extracted data and the prompt template, wherein the creating includes entering the extracted data to the one or more of the prompt input fields ([0040 & 0048] discusses the prompt generator creates an updated prompt based on the extracted data and user input from the analysis module 225); calling the generative AI service using the updated prompt, wherein the calling comprises prompting, via one or more text commands to the generative AI service, the generative AI service to provide a response to the instructions based on the extracted data in the one or more of the prompt input fields ([0047-0048] discusses the user inputting a value of a parameter and upon the input, the AI service generates a prompt using the instructions based on the extracted data to the LLM to provide a response in text form and thus, represents a text command to prompt the service to call the LLM to respond); and receiving the response to the updated prompt from the generative AI service responsive to the calling ([0048] discusses that the text generated by the LLM can be output to the user for approval or regeneration and thus, the response to the updated prompt is received).
Because Pati teaches a processor and computer readable medium operably coupled to perform narrative generation for SAR, receiving a SAR having SAR fields and data, instructions meant to conform to financial crime regulatory or enforcement bodies, generating a SAR report, and storing SAR narratives; and Saxena teaches loading a prompt template into a local memory, wherein the prompt template includes instructions to the generative AI service that cause a generation of the narrative, and wherein the prompt template further includes prompt input fields for the generation of the narrative, extracting data corresponding to one or more of the prompt input fields for the prompt template, creating an updated prompt based on the extracted data and the prompt template, wherein the creating includes entering the extracted data to the one or more of the prompt input fields, calling the generative AI service using the updated prompt, wherein the calling comprises prompting the generative AI service to provide a response to the instructions based on the extracted data in the one or more of the prompt input fields, and receiving the response to the updated prompt from the generative AI service responsive to the calling, accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to substitute loading a prompt template into a local memory, wherein the prompt template includes instructions to the generative AI service that cause a generation of the narrative, and wherein the prompt template further includes prompt input fields for the generation of the narrative, extracting data corresponding to one or more of the prompt input fields for the prompt template, creating an updated prompt based on the extracted data and the prompt template, wherein the creating includes entering the extracted data to the one or more of the prompt input fields, calling the generative AI service using the updated prompt, wherein the calling comprises prompting, via one or more text commands to the generative AI service, the generative AI service to provide a response to the instructions based on the extracted data in the one or more of the prompt input fields, and receiving the response to the updated prompt from the generative AI service responsive to the calling as taught by Saxena into Pati’s SAR narrative generation system, with a reasonable expectation of success, to teach an automated suspicious activity report (SAR) narrative system configured to automate SAR narrative generations using prompts to a generative artificial intelligence (AI) service, the automated SAR narrative system comprising: a processor and a computer readable medium operably coupled thereto, the computer readable medium comprising a plurality of instructions stored in association therewith that are accessible to, and executable by, the processor, to perform narrative generation operations which comprise: receiving a SAR having a plurality of SAR fields and SAR data in one or more of the plurality of SAR fields; loading a prompt template into a local memory of the automated SAR narrative system, wherein the prompt template is associated with generating a SAR narrative by the generative AI service, and wherein the prompt template includes instructions to the generative AI service that cause a generation of the SAR narrative for the SAR, wherein the prompt template further includes prompt input fields for the generation of the SAR narrative, and wherein the instructions are developed so that corresponding text generated using the prompt template meets guidelines for the SAR narrative established by a financial crime regulatory or enforcement body; extracting, from the plurality of SAR fields of the SAR, the SAR data corresponding to one or more of the prompt input fields for the prompt template; creating an updated prompt based on the extracted SAR data and the prompt template, wherein the creating includes entering the extracted SAR data to the one or more of the prompt input fields; calling the generative AI service using the updated prompt, wherein the calling comprises prompting, via one or more text commands to the generative AI service, the generative AI service to provide a response to the instructions based on the extracted SAR data in the one or more of the prompt input fields; receiving the response to the updated prompt from the generative AI service responsive to the calling; and generating and storing the SAR narrative. This substitution would have been motivated by the desire to enable an LLM to generate text for a call or request using data that is retrieved, inputted, or derived (Saxena [0017-0018]) within the architecture of generating SAR narratives as described by Pati.
The combination of Pati and Saxena does not expressly teach storing the SAR narrative in a data container based on the response.
However, in a similar field of endeavor, Guang teaches a machine learning report generation system designed to automate SAR writing, wherein SAR narratives are stored in a data container ([Col. 8, Lines 4-6] discusses the data storage 214 may store one or more reports and further; [Col. 16, Lines 64-67] discusses that a template-based narrative may be retrieved from data storage 214; thus, representing a data container storing SAR narratives).
Because the combination of Pati and Saxena teaches generating and storing SAR narratives, and Guang teaches storing the SAR narrative in a data container based on the response, accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate storing the SAR narrative in a data container based on the response as taught by Guang into the combination of Pati and Saxena’s SAR narrative generation system, with a reasonable expectation of success, to teach an automated suspicious activity report (SAR) narrative system configured to automate SAR narrative generations using prompts to a generative artificial intelligence (AI) service, the automated SAR narrative system comprising: a processor and a computer readable medium operably coupled thereto, the computer readable medium comprising a plurality of instructions stored in association therewith that are accessible to, and executable by, the processor, to perform narrative generation operations which comprise: receiving a SAR having a plurality of SAR fields and SAR data in one or more of the plurality of SAR fields; loading a prompt template into a local memory of the automated SAR narrative system, wherein the prompt template is associated with generating a SAR narrative by the generative AI service, and wherein the prompt template includes instructions to the generative AI service that cause a generation of the SAR narrative for the SAR, wherein the prompt template further includes prompt input fields for the generation of the SAR narrative, and wherein the instructions are developed so that corresponding text generated using the prompt template meets guidelines for the SAR narrative established by a financial crime regulatory or enforcement body; extracting, from the plurality of SAR fields of the SAR, the SAR data corresponding to one or more of the prompt input fields for the prompt template; creating an updated prompt based on the extracted SAR data and the prompt template, wherein the creating includes entering the extracted SAR data to the one or more of the prompt input fields; calling the generative AI service using the updated prompt, wherein the calling comprises prompting, via one or more text commands to the generative AI service, the generative AI service to provide a response to the instructions based on the extracted SAR data in the one or more of the prompt input fields; receiving the response to the updated prompt from the generative AI service responsive to the calling; and generating and storing the SAR narrative in a data container based on the response. This combination would have been motivated by the desire for future SAR generation to retrieve the template or labeled case data of a stored SAR narrative (Guang [Col. 10, Lines 15-17]).
Regarding dependent claim 2, the combination of Pati, Saxena, and Guang teaches the claimed invention as claimed in claim 1 including wherein the calling the generative AI service uses a prompting technique for a single zero-shot prompting call having the instructions with the extracted SAR data in a single interaction call made to the generative AI service (Saxena [0075] discusses the system is capable of handling a prompt with no example inputs, otherwise known as a zero-shot prompting call; Saxena [0021] discusses that the single interaction call can be made to a LLM 130).
Regarding dependent claim 3, the combination of Pati, Saxena, and Guang teaches the claimed invention as claimed in claim 1 including wherein the calling the generative AI service uses a prompting technique for a generation-by-parts of the SAR narrative having the instructions with the extracted SAR data in a plurality of parallel calls made to the generative AI service for each section of the SAR narrative, and wherein parts of the response to the plurality of parallel calls are received and combined to form the SAR narrative by the generation-by-parts (Pati [0015-0016] discusses each NLG translation model is trained for a different preconfigured transaction type and generates a specific type of SAR for the respective transaction type; Saxena [0040-0048] discusses the process of calling the generative AI service using a prompting technique and instructions with extracted input data; Pati [0088 & 0091] discusses that the SAR generation may operate in parallel in batch a large amount of records, such that a latent vector size is built and is reconstructed one part at a time, resulting in sequential assembly of the SAR; Pati [0017] discusses the SAR narratives may be combined resulting in a final SAR narrative, and thus, a prompting technique for generation by parts of the SAR narrative having the instructions with the extracted SAR data in a plurality of parallel calls made to the generative AI service, and those parts are combined to form the SAR narrative).
Regarding dependent claim 4, the combination of Pati, Saxena, and Guang teaches the claimed invention as claimed in claim 1 including wherein the calling the generative AI service uses a prompting technique for few-shot prompting calls having the instructions with the extracted SAR data in a set of calls made to the generative AI service with one or more examples of an input-output pair for another SAR and another SAR narrative (Saxena [0075] discusses the ability to call the generative AI service using few-shot prompting calls with multiple example input/output pairs; thus, the system can use a prompting technique for few-shot prompting calls).
Regarding dependent claim 6, the combination of Pati, Saxena, and Guang teaches the claimed invention as claimed in claim 1 including wherein the generative AI service comprises at least one generative AI model including a large language model (LLM), and wherein the generative AI service provides a conversational AI based on the LLM that processes input conversational text corresponding to the updated prompt and provides output conversational text having the SAR narrative (Saxena [0075] discusses that any commercially available or custom LLM can be used; Saxena [0073-0074] further discusses that GPT-type language models can also be used as the LLM, which is conversational-based and takes chat-like input and generates chat-like output).
Regarding dependent claim 8, the combination of Pati, Saxena, and Guang teaches the claimed invention as claimed in claim 1 including wherein the calling the generative AI service is done in a specified order designated by the prompt template selected for the generation of the SAR narrative (Pati [0009] discusses there is a logical order necessary to provide a complete SAR narrative and thus, there exists some specified order calling the generative AI service; Patti [0141] discusses the data in the preconfigured template may be mapped in order to preserve contingency and logic for the process of correct identification of transaction type, thus the calling is done in a specified order designated by the template).
Regarding dependent claim 9, the combination of Pati, Saxena, and Guang teaches the claimed invention as claimed in claim 1 including wherein, before the extracting the SAR data for the one or more of the prompt input fields, the narrative generation operations further comprise: performing a set of data pre-processing and data cleaning steps on the SAR data in the SAR (Pati [0143] discusses pre-processing the data by replacing high-changing field values with adequate labels before extraction; thus, the narrative generation performs a set of data pre-processing and data cleaning steps on the SAR data).
Regarding claims 10-18, claims 10-18 are method claims that are substantially the same as the system of claims 1-9, respectively. Therefore, claims 10-18 are rejected for the same reasons as claims 1-9.
Regarding dependent claims 19-20, claims 19-20 are non-transitory computer-readable storage medium claims that are substantially the same as the system of Claims 1-2. Therefore, claims 19-20 are rejected for the same reasons as Claims 1-2.
Claims 5 & 14 are rejected under 35 U.S.C. 103 as being unpatentable over Pati, in view of Saxena and Guang, as applied in claim 1, and further in view of Maschmeyer et al. (US 12468878 B2, filed 03/08/2023), hereafter Maschmeyer.
Regarding dependent claim 5, the combination of Pati, Saxena, and Guang teaches the claimed invention as claimed in claim 1 including extracting the SAR data corresponding to one or more of the prompt input fields for the prompt template (Saxena [0033] discusses retrieving the data corresponding to the prompt input fields and parameters of the selected prompt template).
The combination of Pati, Saxena, and Guang does not expressly teach wherein the instructions include one or more sub-instructions configured to handle hallucinations by the generative AI service that have other data not included in the extracted SAR data in the response from the generative AI service, and wherein the one or more sub-instructions include a statement to the generative AI to utilize only the extracted SAR data found in the one or more of the prompt input fields in the response.
However, Maschmeyer teaches a system for handling unsubstantiated information and utilizing only the intended data ([Col. 16, Lines 35-43] discusses including instructions to handle hallucinations and unsubstantiated information by annotating it within the response from the generative AI service, [Col. 21, Lines 28-46] discusses the text-editor 550 will clean up the unsubstantiated information to remove the hallucination; [Col. 1-2, Lines 67-3] discusses the LLM is prompted with instructions to begin the process of annotating the unsubstantiated information, and thus there exists a statement of instructions to utilize only the extracted data found in the prompt input fields).
Because the combination of Pati, Saxena, and Guang teaches extracting SAR data corresponding to prompt input fields for the prompt template, and Maschmeyer teaches handling hallucinations to utilize only the extracted data found in prompt input fields, accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate instructions to handle hallucinations that have data not included in extracted data and instructions that detail utilizing only the extracted data found in prompt input fields as taught by Maschmeyer into the combination of Pati, Saxena, and Guang’s SAR narrative generation system, with a reasonable expectation of success, to teach wherein the instructions include one or more sub-instructions configured to handle hallucinations by the generative AI service that have other data not included in the extracted SAR data in the response from the generative AI service, and wherein the one or more sub-instructions include a statement to the generative AI to utilize only the extracted SAR data found in the one or more of the prompt input fields in the response. This combination would have been motivated by the desire to reduce the quantity of text that requires close review by a human and reduces the risk of an error being inadvertently missed (Maschmeyer [Col. 2, Lines 4-6]).
Regarding claim 14, claim 14 is a method claim that is substantially the same as the system of claim 5. Therefore, claim 14 is rejected for the same reasons as claim 5.
Claims 7 & 16 are rejected under 35 U.S.C. 103 as being unpatentable over Pati, in view of Saxena and Guang, as applied in claim 1, and further in view of Lubbers et al. (US 20090259681 A1, published 10/15/2009), hereafter Lubbers.
Regarding dependent claim 7, the combination of Pati, Saxena, and Guang teaches the claimed invention as claimed in claim 1 including returning a notification to a SAR reporting application after the generating and the storing the SAR narrative (Saxena [0103] discusses the system may post a description of the action or event that occurs with an update, which would include notification after the generating and storing).
The combination of Pati, Saxena, and Guang does not expressly teach wherein the notification identifies the data container stored and indicates that the SAR narrative is available for use with the SAR.
However, Lubbers teaches a system for generating a report, publishing the report on a server and notifying a user of the location ([0027] discusses publishing a report and sending email notification of where the report is stored and that it is available for use).
Because the combination of Pati, Saxena, and Guang teaches returning a notification to a reporting application after generating and storing a SAR narrative, and Lubbers teaches notification of the data container a report is stored in, and indicating it is available for use, accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate sending a notification of where the report is stored and that is available for use as taught by Lubbers into the combination of Pati, Saxena, and Guang’s SAR narrative generation system, with a reasonable expectation of success, to teach wherein the narrative generation operations further comprise: returning a notification to a SAR reporting application after the generating and the storing the SAR narrative, wherein the notification identifies the data container stored and indicates that the SAR narrative is available for use with the SAR. This combination would have been motivated by the desire to directly provide the SAR narrative to the user as well as automate the publication process (Lubbers [0027]).
Regarding claim 16, claim 16 is a method claim that is substantially the same as the system of claim 7. Therefore, claim 16 is rejected for the same reasons as claim 7.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Guang (US 12131281 B1, filed 09/29/2021) ([Col. 2, Lines 53-64] After the SAR is filed, there is no way of knowing the outcome, i.e., no known result. For example, it is unknown whether the suspicious activity was malfeasance and resulted in a conviction, or did not. Therefore, there is no explicit ground-truth or result. Additionally, the number of SAR reports is multiple orders of magnitude smaller than the number of activities (e.g., transactions) monitored, which means that relying solely on those transactions associated with a SAR report may result in overfitting and, perhaps, many false-negatives. The systems and methods described herein may address, at least in part, the issues of having no or sparse results).
Kreth et al. (US 2021/0295338 A1, published 09/23/2021) ([Abstract] Aspects of the disclosure relate to using machine learning techniques for generating automated suspicious activity reports (SAR). A computing platform may generate a labelled transaction history dataset by combining historical transaction data with historical report information. The computing platform may train a convolutional neural network using the labelled transaction history dataset. The computing platform may receive new transaction data and compress the new transaction data using lossy compression. The computing platform may input the compressed transaction data into the convolutional neural network, which may cause the convolutional neural network to output a suspicious event probability score based on the compressed transaction data. The computing platform may determine whether the suspicious event probability score exceeds a predetermined threshold and, if so, the computing platform may send one or more commands directing a report processing system to generate a SAR, which may cause the report processing system to generate the SAR).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to RILEY S ACOSTA whose telephone number is (571)272-8714. The examiner can normally be reached Monday-Thursday 6am-4pm.
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, Jennifer N Welch can be reached at (571)272-7212. 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.
/RILEY S ACOSTA/Examiner, Art Unit 2143
/JENNIFER N WELCH/Supervisory Patent Examiner, Art Unit 2143
Prosecution Insights