DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of Claims
This action is in reply to the communications filed on 11/08/2025.
Claims 1, 4, 9-10, 12-13, 16-18, and 20 have been amended and are hereby entered.
Claims 2-3, 7, 14-15, and 19 have been canceled.
Claims 1, 4-6, 8-13, 16-18, and 20 are currently pending and have been examined.
This action is made Final.
Examiner Request
The Applicant is requested to indicate where in the specification there is support for future claim amendments to avoid U.S.C 112(a) issues that can arise. The Examiner thanks the Applicant in advance.
Claim Objections
Claims 1, 9, 13, and 16 are objected to because of the following informalities:
Claim 1: line 21, Claim 9: line 23, and Claim 13: line 24 recite the limitation “whererin the virtual assistant.” “Wherein” is misspelled. It appears there is a grammatical mistake. For compact examination purposes, Examiner interpreted the instances recited in Claim 1: line 21, Claim 9: line 23, and Claim 13: line 24 as “wherein the virtual assistant.” Appropriate correction is required.
Claim 16 is dependent on Claim 14. However, dependent claim 14 has been canceled. It appears there is a typographical mistake since dependent claim 16 cannot be dependent on claim 14, which has been canceled. For compact examination purposes, Examiner interpreted that claim 16 is dependent on independent claim 13. Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(d):
(d) REFERENCE IN DEPENDENT FORMS.—Subject to subsection (e), a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
The following is a quotation of pre-AIA 35 U.S.C. 112, fourth paragraph:
Subject to the following paragraph [i.e., the fifth paragraph of pre-AIA 35 U.S.C. 112], a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
Claim 12 is rejected under 35 U.S.C. 112(d) or pre-AIA 35 U.S.C. 112, 4th paragraph, as being of improper dependent form for failing to further limit the subject matter of the claim upon which it depends, or for failing to include all the limitations of the claim upon which it depends. Dependent claim 12 does not further limit independent claim 9. Applicant may cancel the claim(s), amend the claim(s) to place the claim(s) in proper dependent form, rewrite the claim(s) in independent form, or present a sufficient showing that the dependent claim(s) complies with the statutory requirements.
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, 4-6, 8-13, 16-18, and 20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea of receiving and analyzing user data to identify not-satisfied requirements within a set of underwriting requirements, without significantly more.
Claim 1 is directed to a method, which is one of the statutory categories of invention. (Step 1: YES).
Claim 1 is directed to a method for using a context-aware loan origination system, the method comprising: in response to receiving, from a virtual assistant comprising a language model and a knowledge base that comprises a set of pre-loaded mortgage rules, user-related data associated with an interaction session, generating a set of queries for an underwriting database and a product database, the user-related data comprising a set of requirements; in response to receiving a set of query results from the underwriting database and the product database, analyzing the set of query results to identify query items that satisfy at least some requirements in the set of requirements; iteratively performing steps comprising: determining whether any of the requirements in the set of requirements have not been satisfied; in response to identifying at least one not-satisfied requirement within the set of requirements, identifying additional user-related data related to the not-satisfied requirement; instructing the virtual assistant to request the additional user-related data; in response to receiving the additional user-related data, determining one or more items from the query results that match the set of requirements; and using the one or more items to generate a user recommendation; whererin the virtual assistant, in response to receiving from an underwriting engine a user question regarding an underwriting calculation, calculates an alignment between the user question and answers in the knowledge base to identify an answer to the user question to explain the underwriting calculation. These series of steps describe the abstract idea of receiving and analyzing user data to identify not-satisfied requirements within a set of underwriting requirements (with the exception of the italicized and bolded terms above), which is mitigating risk by identifying user data related to the not-satisfied requirements in a set of underwriting requirements and determining which results matches the set of underwriting requirements to generate user recommendations; therefore, corresponding to a fundamental economic principle or practice (including mitigating risk). Hence, a fundamental economic principle or practice (mitigating risk) is a Certain Methods of Organizing Human Activity. The abstract idea is also loan origination based on identifying user data that is not-satisfied requirements in a set of underwriting requirements and determining which results matches the set of underwriting requirements to generate user recommendations, which is a commercial interaction. Therefore, a commercial interaction is also a Certain Methods of Organizing Human Activity. The system limitations, e.g., a context-aware loan origination system, virtual assistant, language model, knowledge base, underwriting database, underwriting engine, and product database, do not necessarily restrict the claim from reciting an abstract idea. Thus, claim 1 recites an abstract idea (Step 2A-Prong 1: YES).
This judicial exception is not integrated into a practical application because the additional elements of a context-aware loan origination system, virtual assistant, language model, knowledge base, underwriting database, underwriting engine, and product database, are no more than simply applying the abstract idea using generic computer elements. The additional elements listed above are all recited at a high level of generality and under their broadest reasonable interpretation comprises a generic computing arrangement. The presence of a generic computer arrangement is nothing more than to implement the claimed invention (MPEP 2106.05(f)). Therefore, the recitations of additional elements do not meaningfully apply the abstract idea and hence do not integrate the abstract idea into a practical application. Thus, claim 1 does not integrate the abstract idea into a practical application (Step 2A-Prong 2: NO).
Claim 1 does not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements of a context-aware loan origination system, virtual assistant, language model, knowledge base, underwriting database, underwriting engine, and product database, are recited at a high level of generality in that it results in no more than simply applying the abstract idea using generic computer elements. The additional elements when considered separately and as an ordered combination do not amount to add significantly more as these limitations provide nothing more than to simply apply the exception in a generic computer environment (Step 2B: NO). Thus, claim 1 is not patent eligible.
Dependent claims 4-6 and 8 are directed to a method, which recites the steps that describe the abstract idea of receiving and analyzing user data to identify not-satisfied requirements within a set of underwriting requirements. Specifically, dependent claim 8 is directed to a method, which recites the step, e.g., wherein the virtual assistant, in response to receiving, at a chat interface, data comprising at least one of a user profile-related question, an issue statement, or context information, analyzes the received data to output a user-specific answer or a product recommendation. These series of steps describe the abstract idea of receiving and analyzing user data to identify not-satisfied requirements within a set of underwriting requirements (with the exception of the italicized and bolded terms above), which is mitigating risk by identifying user data related to the not-satisfied requirements in a set of underwriting requirements and determining which results matches the set of underwriting requirements to generate user recommendations; therefore, corresponding to a fundamental economic principle or practice (including mitigating risk). Hence, a fundamental economic principle or practice (mitigating risk) is a Certain Methods of Organizing Human Activity. The abstract idea is also loan origination based on identifying user data that is not-satisfied requirements in a set of underwriting requirements and determining which results matches the set of underwriting requirements to generate user recommendations, which is a commercial interaction. Therefore, a commercial interaction is also a Certain Methods of Organizing Human Activity. Thus, claims 4-6 and 8 recite an abstract idea. The additional limitations of a context-aware loan origination system, virtual assistant, underwriting database, product database, language model, knowledge base, underwriting engine, and chat interface, are no more than simply applying the abstract idea using generic computer elements. The presence of a generic computer arrangement is nothing more than to implement the claimed invention (MPEP 2106.05(f)). Therefore, the recitations of additional elements do not meaningfully apply the abstract idea and hence do not integrate the abstract idea into a practical application. Furthermore, the additional elements: a context-aware loan origination system, virtual assistant, underwriting database, product database, language model, knowledge base, underwriting engine, and chat interface, do not amount to add significantly more as these limitations provide nothing more than to simply apply the exception in a generic computer environment.
Claim 13 is directed to a system, which is one of the statutory categories of invention. (Step 1: YES).
Claim 13 is directed to a context-aware loan origination system, the system comprising: a processor; and a non-transitory computer-readable medium comprising instructions that, when executed by the processor, cause steps to be performed, the steps comprising: in response to receiving, from a virtual assistant comprising a language model and a knowledge base that comprises a set of pre-loaded mortgage rules, user-related data associated with an interaction session, generating a set of queries for an underwriting database and a product database, the user-related data comprising a set of requirements; in response to receiving a set of query results from the underwriting database and the product database, analyzing the set of query results to identify query items that satisfy at least some requirements in the set of requirements; iteratively performing steps comprising: determining whether any of the requirements in the set of requirements have not been satisfied; in response to identifying at least one not-satisfied requirement within the set of requirements, identifying additional user-related data related to the not-satisfied requirement; instructing the virtual assistant to request the additional user-related data; in response to receiving the additional user-related data, determining one or more items from the query results that match the set of requirements; and using the one or more items to generate a user recommendation; whererin the virtual assistant, in response to receiving from an underwriting engine a user question regarding an underwriting calculation, calculates an alignment between the user question and answers in the knowledge base to identify an answer to the user question to explain the underwriting calculation. These series of steps describe the abstract idea of receiving and analyzing user data to identify not-satisfied requirements within a set of underwriting requirements (with the exception of the italicized and bolded terms above), which is mitigating risk by identifying user data related to the not-satisfied requirements in a set of underwriting requirements and determining which results matches the set of underwriting requirements to generate user recommendations; therefore, corresponding to a fundamental economic principle or practice (including mitigating risk). Hence, a fundamental economic principle or practice (mitigating risk) is a Certain Methods of Organizing Human Activity. The abstract idea is also loan origination based on identifying user data that is not-satisfied requirements in a set of underwriting requirements and determining which results matches the set of underwriting requirements to generate user recommendations, which is a commercial interaction. Therefore, a commercial interaction is also a Certain Methods of Organizing Human Activity. The system limitations, e.g., a context-aware loan origination system, processor, non-transitory computer-readable medium, virtual assistant, underwriting database, product database, language model, knowledge base, and underwriting engine, do not necessarily restrict the claim from reciting an abstract idea. Thus, claim 13 recites an abstract idea (Step 2A-Prong 1: YES).
This judicial exception is not integrated into a practical application because the additional elements of a context-aware loan origination system, processor, non-transitory computer-readable medium, virtual assistant, underwriting database, product database, language model, knowledge base, and underwriting engine are no more than simply applying the abstract idea using generic computer elements. The additional elements listed above are all recited at a high level of generality and under their broadest reasonable interpretation comprises a generic computing arrangement. The presence of a generic computer arrangement is nothing more than to implement the claimed invention (MPEP 2106.05(f)). Therefore, the recitations of additional elements do not meaningfully apply the abstract idea and hence do not integrate the abstract idea into a practical application. Thus, claim 13 does not integrate the abstract idea into a practical application (Step 2A-Prong 2: NO).
Claim 13 does not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements of a context-aware loan origination system, processor, non-transitory computer-readable medium, virtual assistant, underwriting database, product database, language model, knowledge base, and underwriting engine, are recited at a high level of generality in that it results in no more than simply applying the abstract idea using generic computer elements. The additional elements when considered separately and as an ordered combination do not amount to add significantly more as these limitations provide nothing more than to simply apply the exception in a generic computer environment (Step 2B: NO). Thus, claim 13 is not patent eligible.
Dependent claims 16-18 and 20 are directed to a system which performs the steps that describe the abstract idea of receiving and analyzing user data to identify not-satisfied requirements within a set of underwriting requirements. Specifically, dependent claim 20 is directed to a system, which perform the step, e.g., wherein the virtual assistant, in response to receiving, at a chat interface, data comprising at least one of a user profile-related question, an issue statement, or context information, analyzes the received data to output a user-specific answer or a product recommendation. These series of steps describe the abstract idea of receiving and analyzing user data to identify not-satisfied requirements within a set of underwriting requirements (with the exception of the italicized and bolded terms above), which is mitigating risk by identifying user data related to the not-satisfied requirements in a set of underwriting requirements and determining which results matches the set of underwriting requirements to generate user recommendations; therefore, corresponding to a fundamental economic principle or practice (including mitigating risk). Hence, a fundamental economic principle or practice (mitigating risk) is a Certain Methods of Organizing Human Activity. The abstract idea is also loan origination based on identifying user data that is not-satisfied requirements in a set of underwriting requirements and determining which results matches the set of underwriting requirements to generate user recommendations, which is a commercial interaction. Therefore, a commercial interaction is also a Certain Methods of Organizing Human Activity. Thus, claims 16-18 and 20 recite an abstract idea. The additional limitations of a context-aware loan origination system, processor, non-transitory computer-readable medium, virtual assistant, underwriting database, product database, language model, knowledge base, underwriting engine and chat interface, are no more than simply applying the abstract idea using generic computer elements. The presence of a generic computer arrangement is nothing more than to implement the claimed invention (MPEP 2106.05(f)). Therefore, the recitations of additional elements do not meaningfully apply the abstract idea and hence do not integrate the abstract idea into a practical application. Furthermore, the additional elements: a context-aware loan origination system, processor, non-transitory computer-readable medium, virtual assistant, underwriting database, product database, language model, knowledge base, underwriting engine and chat interface, do not amount to add significantly more as these limitations provide nothing more than to simply apply the exception in a generic computer environment.
Claims 9-12 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. Claims directed to an apparatus must be distinguished from the prior art in terms of structure rather than function, In re Danly 263 F.2d 844, 847, 120 USPQ 582, 531 (CCPA 1959). A claim containing a “recitation with respect to the manner in which a claimed apparatus is intended to be employed does not differentiate the claimed apparatus from a prior art apparatus” if the prior art apparatus teaches all the structural limitations of the claim. Ex parte Masham, 2 USPQ2d 1657 (bd Pat. App. & Inter. 1987). However, the claim does not positively recite any elements that necessarily constitute a system or apparatus, such as computer hardware. It is not clear what structure is included or excluded by the claim language. The structural limitations of these claims are interpreted as computer code or software per-se and are not statutory. Claims 9-12 recite a context-aware loan origination system, chat user interface (UI), task user interface (UI), virtual assistant, core engine, underwriting database, product database, language model, knowledge base, underwriting engine, data aggregation and storage module, and converter, which are not claimed as embodied in computer-readable media are functional descriptive material per se and are considered to be software per se, which is not statutory (see MPEP 2106.03). Here, Applicant has claimed systems defined merely by software or terms synonymous with software or files, namely “a context-aware loan origination system, chat user interface (UI), task user interface (UI), virtual assistant, core engine, underwriting database, product database, language model, knowledge base, underwriting engine, data aggregation and storage module, and converter,” lacking storage on a medium, which does not enable any underlying functionality to occur. Examiner recommends amending the claim to clearly include hardware in order to overcome this rejection. Additionally, any amendments must be fully supported by the specification.
Examiner respectfully notes that even if Claims 9-12 are directed to statutory subject matter (e.g. a system), Claims 9-12 would be rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea of receiving and analyzing user data to identify not-satisfied requirements within a set of underwriting requirements, without significantly more. Considering Claims 9-12 are directed to statutory subject matter (e.g. a system), which they are not, Examiner provides below a full analysis of the 35 U.S.C. 101 rejection of Claims 9-12.
Claims 9-12 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea of facilitating information sharing for selling and buying of assets, and processing lending and brokering information, without significantly more.
Claim 9 is directed to a system (currently as recited it is not directed to statutory subject matter -system ). (Step 1: YES).
Claim 9 is directed to a context-aware loan origination system, the system comprising: a chat user interface (UI); a task UI that displays a set of tasks; a virtual assistant coupled to the chat UI and the task UI, the virtual assistant comprises a language model and a knowledge base that comprises a set of pre- loaded mortgage rules, the virtual assistant uses an interaction session to obtain, from the chat UI, user-related data comprising a set of requirements; a core engine coupled to the virtual assistant, the core engine receives the user-related data to generate a set of queries for an underwriting database and a product database and, in response to receiving a set of query results from the underwriting database and the product database, analyzes the set of query results to identify query items that satisfy at least some requirements in the set of requirements, the core engine iteratively performing steps comprising: determining whether any of the requirements in the set of requirements have not been satisfied; in response to identifying at least one not-satisfied requirement within the set of requirements, identifying additional user-related data related to the not-satisfied requirement; instructing the virtual assistant to request the additional user-related data; in response to receiving the additional user-related data, determining one or more items from the query results that match the set of requirements; and using the one or more items to generate a user recommendation; whererin the virtual assistant, in response to receiving from an underwriting engine a user question regarding an underwriting calculation, calculates an alignment between the user question and answers in the knowledge base to identify an answer to the user question to explain the underwriting calculation. These series of steps describe the abstract idea of receiving and analyzing user data to identify not-satisfied requirements within a set of underwriting requirements (with the exception of the italicized and bolded terms above), which is mitigating risk by identifying user data related to the not-satisfied requirements in a set of underwriting requirements and determining which results matches the set of underwriting requirements to generate user recommendations; therefore, corresponding to a fundamental economic principle or practice (including mitigating risk). Hence, a fundamental economic principle or practice (mitigating risk) is a Certain Methods of Organizing Human Activity. The abstract idea is also loan origination based on identifying user data that is not-satisfied requirements in a set of underwriting requirements and determining which results matches the set of underwriting requirements to generate user recommendations, which is a commercial interaction. Therefore, a commercial interaction is also a Certain Methods of Organizing Human Activity. The system limitations, e.g., a context-aware loan origination system, chat user interface (UI), task user interface (UI), virtual assistant, core engine, underwriting database, language model, knowledge base, underwriting engine, and product database, do not necessarily restrict the claim from reciting an abstract idea. Thus, claim 9 recites an abstract idea (Step 2A-Prong 1: YES).
This judicial exception is not integrated into a practical application because the additional elements of a context-aware loan origination system, chat user interface (UI), task user interface (UI), virtual assistant, core engine, underwriting database, language model, knowledge base, underwriting engine, and product database, are no more than simply applying the abstract idea using generic computer elements. The additional elements listed above are all recited at a high level of generality and under their broadest reasonable interpretation comprises a generic computing arrangement. The presence of a generic computer arrangement is nothing more than to implement the claimed invention (MPEP 2106.05(f)). Therefore, the recitations of additional elements do not meaningfully apply the abstract idea and hence do not integrate the abstract idea into a practical application. Thus, claim 9 does not integrate the abstract idea into a practical application (Step 2A-Prong 2: NO).
Claim 9 does not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements of a context-aware loan origination system, chat user interface (UI), task user interface (UI), virtual assistant, core engine, underwriting database, language model, knowledge base, underwriting engine, and product database, are recited at a high level of generality in that it results in no more than simply applying the abstract idea using generic computer elements. The computer network limitations are a field of use limitations (MPEP 2106.05(h)). The additional elements when considered separately and as an ordered combination do not amount to add significantly more as these limitations provide nothing more than to simply apply the exception in a generic computer environment (Step 2B: NO). Thus, claim 9 is not patent eligible.
Dependent claims 10-12 are directed to a system (currently as recited it is not statutory subject matter), which performs a series of steps that describe the abstract idea of receiving and analyzing user data to identify not-satisfied requirements within a set of underwriting requirements. Specifically, dependent claims 10-12 are directed to a system (currently as recited it is not statutory subject matter), which performs a series of steps, e.g., further comprising data aggregation and storage module coupled to the core engine; and further comprising a converter that converts data obtained from the virtual assistant into a format that is compatible with at least one of the underwriting database or the product database; and wherein the virtual assistant comprises at least one of a language model or a knowledge base. These series of steps describe the abstract idea of receiving and analyzing user data to identify not-satisfied requirements within a set of underwriting requirements (with the exception of the italicized and bolded terms above), which is mitigating risk by identifying user data related to the not-satisfied requirements in a set of underwriting requirements and determining which results matches the set of underwriting requirements to generate user recommendations; therefore, corresponding to a fundamental economic principle or practice (including mitigating risk). Hence, a fundamental economic principle or practice (mitigating risk) is a Certain Methods of Organizing Human Activity. The abstract idea is also loan origination based on identifying user data that is not-satisfied requirements in a set of underwriting requirements and determining which results matches the set of underwriting requirements to generate user recommendations, which is a commercial interaction. Therefore, a commercial interaction is also a Certain Methods of Organizing Human Activity. Thus, claims 10-12 recite an abstract idea. The additional limitations of a context-aware loan origination system, chat user interface (UI), task user interface (UI), virtual assistant, core engine, underwriting database, product database, language model, knowledge base, underwriting engine, data aggregation and storage module, and converter, are no more than simply applying the abstract idea using generic computer elements. The presence of a generic computer arrangement is nothing more than to implement the claimed invention (MPEP 2106.05(f)). Therefore, the recitations of additional elements do not meaningfully apply the abstract idea and hence do not integrate the abstract idea into a practical application. Furthermore, the additional elements: a context-aware loan origination system, chat user interface (UI), task user interface (UI), virtual assistant, core engine, underwriting database, product database, language model, knowledge base, underwriting engine, data aggregation and storage module, and converter, do not amount to add significantly more as these limitations provide nothing more than to simply apply the exception in a generic computer environment.
Dependent claims 4-6, 8, 10-12, 16-18, and 20 have further defined the abstract idea that is present in their respective independent claims: Claim 1, 9, and 13; and thus correspond to Certain Methods of Organizing Human Activity and/or Mental Processes, and hence are abstract in nature for the reason presented above. The dependent claims 4-6, 8, 10-12, 16-18, and 20 do not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception when considered both individually and as an ordered combination. Therefore, dependent claims 4-6, 8, 10-12, 16-18, and 20 are directed to an abstract idea without significantly more.
Thus, claims 1, 4-6, 8-13, 16-18, and 20 are not patent-eligible.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, 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.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1, 4-6, 8-13, 16-18, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Agarwal (U.S. Patent Application Publication No. US 2023/0105825 A1; hereinafter “Agarwal”), in view of Masson (U.S. Patent Publication No. US 2023/0186385 A1; hereinafter “Masson”).
Regarding Claims 1 and 13:
Agarwal teaches:
A method for using a context-aware loan origination system, the method comprising: (Agarwal, a system and method for providing a natural language interface or conversation/chat interface for interacting with an automated software assistant (AA) and/or a human assistant (HA) when completing an electronic form is disclosed. For example, the electronic form may be a mortgage application soliciting input from the user in the form of questions wishing to obtain a mortgage loan. (See, Abstract; Para. 43, 54; Fig. 1));
A context-aware loan origination system, the system comprising: a processor; and a non-transitory computer-readable medium comprising instructions that, when executed by the processor, cause steps to be performed, the steps comprising: (Agarwal, a system and method for providing a natural language interface or conversation/chat interface for interacting with an automated software assistant (AA) and/or a human assistant (HA) when completing an electronic form is disclosed. For example, the electronic form may be a mortgage application soliciting input from the user in the form of questions wishing to obtain a mortgage loan. (See, Abstract; Para. 43, 54-59; Claim 12; Fig. 1));
in response to receiving, from a virtual assistant comprising a language model and a knowledge base that comprises a set of pre-loaded mortgage rules, user-related data associated with an interaction session, generating a set of queries for [an underwriting database] and a product database, the user-related data comprising a set of requirements; (Agarwal, a system and method for providing a natural language interface or conversation/chat interface for interacting with an automated software assistant (AA) and/or a human assistant (HA) when completing an electronic form is disclosed. For example, the electronic form may be a mortgage application soliciting input from the user in the form of questions wishing to obtain a mortgage loan….. The system may also generate quick requests, which may include individual questions or requests that user must provide when completing the form. For example, age, income, property address, and so on. Each quick request element may include a unique icon. User's response to a quick request or any other question may be tagged with an icon thus making it easier for the user to recognize which response is related to which data element. (See, Abstract; Para. 43-50, 54, 65, 85, 97); providing a natural language interface or conversation/chat interface for interacting with an automated software assistant (AA) and/or a human assistant (HA) when completing the electronic form ….. AA may act like an “intelligent concierge” or a go-between the HA and the user. The user may converse with both the AA and the HA within the chat interface; The user satisfaction index may be the result of a mathematical function that includes the results of machine learning applied to data associating subject-related factors and self-reported or imputed levels of satisfaction, and may also combine domain expertise in the form of explicit knowledge or rule (See, Abstract; Para. 37, 40-45, 52, 54, 65, 82-83, 96-97, 100, 107; Fig. 1));
in response to receiving a set of query results from [the underwriting database] and the product database, analyzing the set of query results to identify query items that satisfy at least some requirements in the set of requirements; (Agarwal, a system and method for providing a natural language interface or conversation/chat interface for interacting with an automated software assistant (AA) and/or a human assistant (HA) when completing an electronic form is disclosed. For example, the electronic form may be a mortgage application soliciting input from the user in the form of questions wishing to obtain a mortgage loan….. The system may also generate quick requests, which may include individual questions or requests that user must provide when completing the form. For example, age, income, property address, and so on. Each quick request element may include a unique icon. User's response to a quick request or any other question may be tagged with an icon thus making it easier for the user to recognize which response is related to which data element. (See, Abstract; Para. 43-50, 54, 65, 85, 97));
iteratively performing steps comprising: determining whether any of the requirements in the set of requirements have not been satisfied; (Agarwal, in an effort to change a response buried in a multi-message exchange, the user would have to scroll to find a relevant response and then modify it. As a result, the AA would generate a “new” set of downstream answers or commands corresponding with the updated user input (e.g., as a separate branch). These downstream answers in a new branch may be generated by reusing the information provided by the user in the original branch; the application 126 or computing components 102 operating the AA may utilize machine learning classifier that is trained based at least in part on known bad actor statements expressing interest in utilizing the services provided by the chat interface and statements of similar contextual value extracted from the prior message exchange threads of the present user. (See, Abstract; Para. 42-45, 62, 65, 78, 81-85, 96-97, 116));
in response to identifying at least one not-satisfied requirement within the set of requirements, identifying additional user-related data related to the not-satisfied requirement; (Agarwal, the application 126 or computing components 102 operating the AA may utilize machine learning classifier that is trained based at least in part on known bad actor statements expressing interest in utilizing the services provided by the chat interface and statements of similar contextual value extracted from the prior message exchange threads of the present user. For example, a corpus of prior message exchange threads may be authorized for use in training an artificial intelligence scheme such as a machine learning classifier or neural network. User words, phrases, and/or statements in the message exchange threads from known bad actors and other uses may be used as user inputs. Known identity may be provided as labeled outputs. For example, messages from known scammers., may be identified as such. A machine learning classifier, a neural network, or other artificial intelligence model may be trained using these labeled pairs to identify potential bad actor user input and/or confirm identity of a known user. (See, Abstract; Para. 42-45, 62, 65, 78, 81-85, 96-97, 116));
instructing the virtual assistant to request the additional user-related data; (Agarwal, the user may receive additional instruction from AA or HA which will then be incorporated into the response. The user may continue responding to the remaining questions and finish the multi-step process. By having AA explain to the user the question results in a timelier response and higher customer satisfaction. (See, Abstract; Para. 42-45, 62, 65, 78, 81-85, 96-97, 116));
in response to receiving the additional user-related data, determining one or more items from the query results that match the set of requirements; and (Agarwal, the user may receive additional instruction from AA or HA which will then be incorporated into the response. The user may continue responding to the remaining questions and finish the multi-step process. By having AA explain to the user the question results in a timelier response and higher customer satisfaction. (See, Abstract; Para. 42-45, 62, 65, 78, 81-85, 96-97, 116));
using the one or more items to generate a user recommendation; (Agarwal, Individual workflows are optimized for individual users based on a determination of user satisfaction for existing or standard electronic form completion workflows. As alluded to above, workflows comprise questions configured to elicit user responses to complete a particular category or phase of the process. Prior to the beginning completing a form and following each response of each user, the application 126 and/or component 104 (illustrated in FIG. 1 ) calculates a user satisfaction index which represents the overall satisfaction for each user completing the form. The user satisfaction index may be the result of a mathematical function that includes the results of machine learning applied to data associating subject-related factors and self-reported or imputed levels of satisfaction, and may also combine domain expertise in the form of explicit knowledge or rules…. User satisfaction is also a function of the chat interface guidance provided by AA or HA. User satisfaction can be increased by: (1) eliminating repeat questions, (2) having empathetic and supportive AA or HA, (3) providing user friendly instruction on how to submit and subsequently access documents, (4) the opportunity to adaptively modify answers, and (5) keeping the user informed of the progress and time necessary to complete the form. (See, Abstract; Para. 42-45, 62, 65, 78, 81-85, 96-97, 116));
wherein the virtual assistant, in response to receiving from an underwriting engine a user question regarding [an underwriting calculation, calculates an alignment between the user question and answers] in the knowledge base to identify an answer to the question to explain [the underwriting calculation]. (Agarwal, Individual workflows are optimized for individual users based on a determination of user satisfaction for existing or standard electronic form completion workflows. As alluded to above, workflows comprise questions configured to elicit user responses to complete a particular category or phase of the process. Prior to the beginning completing a form and following each response of each user, the application 126 and/or component 104 (illustrated in FIG. 1 ) calculates a user satisfaction index which represents the overall satisfaction for each user completing the form. The user satisfaction index may be the result of a mathematical function that includes the results of machine learning applied to data associating subject-related factors and self-reported or imputed levels of satisfaction, and may also combine domain expertise in the form of explicit knowledge or rules…. User satisfaction is also a function of the chat interface guidance provided by AA or HA. User satisfaction can be increased by: (1) eliminating repeat questions, (2) having empathetic and supportive AA or HA, (3) providing user friendly instruction on how to submit and subsequently access documents, (4) the opportunity to adaptively modify answers, and (5) keeping the user informed of the progress and time necessary to complete the form. (See, Abstract; Para. 42-45, 62, 65, 78, 81-85, 96-97, 116)).
Agarwal does not specifically teach an underwriting database; and an underwriting calculation, calculates an alignment between the user question and answers.
However, Masson further teaches the following limitations:
an underwriting database; (Masson, The cloud-based platform 730 may output the results of the lending strategies and business revenue management system 102 in different formats. One example of output may be directly to the Financial Institution Operating Systems (e.g., Loan Origination System or Automated Underwriting Systems) through API 742 and following a strategy validation protocol from the system user on the interfaces 230. This may require an initial technology setup but may enhance the Financial Institution Quality Control strategy implementation results and speed to market to instantly deploy any strategies built and validated in the system 102 by the user. (See, Para. 34-36; Abstract));
[an underwriting calculation, calculates an alignment between the user question and answers] in the knowledge base to identify an answer to the question to explain [the underwriting calculation]. (Masson, The cloud-based platform 730 may output the results of the lending strategies and business revenue management system 102 in different formats. One example of output may be directly to the Financial Institution Operating Systems (e.g., Loan Origination System or Automated Underwriting Systems) through API 742 and following a strategy validation protocol from the system user on the interfaces 230. This may require an initial technology setup but may enhance the Financial Institution Quality Control strategy implementation results and speed to market to instantly deploy any strategies built and validated in the system 102 by the user; For example, this “non-compliant Reg. B data” type of information may not be used for any consumer lending underwriting strategy developed by the automated strategy builder module 212. At a high level, the Customer Data Input 202 may be flagged as regulatory non-compliant 606 or as regulatory compliant 608. At step 610, the regulatory compliant data 608 may be tested based on historical performance across users. This step may leverage the artificial intelligence / machine learning module 326 and stored performance rating in memory 226 for each data field based on previous Customer Data Input 202 and the Vendor Model Evaluation module 320. (See, Para. 34-36; Abstract)).
It would have been obvious to one of ordinary skill in the art before the effective filing of the claimed invention to have modified Agarwal with the features of Masson’s system because “while conventional systems may be capable of providing optimization models and reporting, these systems, however, are unable to capture industry knowledge and, instead, require a team of lending industry experts and statisticians to review manually or in separate systems the lending product characteristics (e.g. credit card debt to income, mortgage loan to value), and lending function and program characteristics (e.g. marketing prescreen, underwriting eligibility criteria, account line management). Such limitation either reduces the performance of lending strategies if implemented solely based on the system output or requires the work and interaction of several teams to produce a higher quality strategy that may answer the business needs and revenue targets.” (Masson, Para. 16).
Regarding Claims 2 and 14:
(Canceled).
Regarding Claims 3 and 15:
(Canceled).
Regarding Claims 4 and 16:
Agarwal teaches:
wherein the virtual assistant, in response to receiving a user question regarding income, identifies a characteristic answer associated with the user question regarding income. (Agarwal, AA may act like an “intelligent concierge” or a go-between the HA and the user. The user may converse with both the AA and the HA within the chat interface. By having the ability to interact with both the AA and HA, the user will be in the “company” of two helpful guides, never left alone to complete the arduous task of filling out an online form….The system may also generate quick requests, which may include individual questions or requests that user must provide when completing the form. For example, age, income, property address, and so on. Each quick request element may include a unique icon….. the user may “fill-out” a plurality of electronic forms using distinct conversations within the chat interface. In other words, the system may recognize that one conversation may be associated with an identifier, e.g., a loan number. In the event the system cannot recognize the identifier, the user may drag an icon of a previously submitted document related to that loan number to the conversation to form the association; The system may also generate quick requests, which may include individual questions or requests that user must provide when completing the form. For example, age, income, property address (See, Abstract; Para. 37-38, 40-48, 52, 54, 65, 82-85, 96-97, 100, 107, 116; Fig. 1)).
Regarding Claims 5 and 17:
Agarwal teaches:
wherein the virtual assistant uses at least one of the language model or the knowledge base to generate a set of unique instructions associated with the characteristic answer. (Agarwal, systems and methods for improving electronic form submissions by providing a natural language interface or conversation/chat interface for interacting with an automated software assistant (AA) and/or a human assistant (HA) when completing the electronic form; Further, the AA is configured to “invite” HA based on user's needs, the HA's level of skill, the HA's availability, and/or other such factors. In essence, AA may act like an “intelligent concierge” or a go-between the HA and the user. The user may converse with both the AA and the HA within the chat interface….. the user may “fill-out” a plurality of electronic forms using distinct conversations within the chat interface. In other words, the system may recognize that one conversation may be associated with an identifier, e.g., a loan number. In the event the system cannot recognize the identifier, the user may drag an icon of a previously submitted document related to that loan number to the conversation to form the association. Alternatively, the user may enter a text or voice command to make the association. Additionally, the conversation may include folders or sub-folders within the conversation which may contain information related to one particular identifier. For example, a loan number may be a parent folder and a bank account may be a folder or a sub-folder. The system may identify the folder using the identifier. (See, Abstract; Para. 37, 40-48, 52, 54, 65, 82-83, 96-97, 100; Fig. 1)).
Regarding Claims 6 and 18:
Agarwal teaches:
wherein the virtual assistant, in response to receiving a subsequent related user question, identifies a subsequent characteristic answer from a set of characteristic answers that more closely matches the related user question to generate a set of unique instructions associated with the subsequent characteristic answer. (Agarwal, AA may act like an “intelligent concierge” or a go-between the HA and the user. The user may converse with both the AA and the HA within the chat interface. By having the ability to interact with both the AA and HA, the user will be in the “company” of two helpful guides, never left alone to complete the arduous task of filling out an online form….The system may also generate quick requests, which may include individual questions or requests that user must provide when completing the form. For example, age, income, property address, and so on. Each quick request element may include a unique icon….. the user may “fill-out” a plurality of electronic forms using distinct conversations within the chat interface. In other words, the system may recognize that one conversation may be associated with an identifier, e.g., a loan number. In the event the system cannot recognize the identifier, the user may drag an icon of a previously submitted document related to that loan number to the conversation to form the association. (See, Abstract; Para. 37-38, 40-48, 52, 54, 65, 82-83, 100, 107; Fig. 1); a system and method for providing a natural language interface or conversation/chat interface for interacting with an automated software assistant (AA) and/or a human assistant (HA) when completing an electronic form is disclosed. For example, the electronic form may be a mortgage application soliciting input from the user in the form of questions wishing to obtain a mortgage loan….. The system may also generate quick requests, which may include individual questions or requests that user must provide when completing the form. For example, age, income, property address, and so on. Each quick request element may include a unique icon. User's response to a quick request or any other question may be tagged with an icon thus making it easier for the user to recognize which response is related to which data element. (See, Abstract; Para. 43-50, 54, 65, 85, 96, 97));
Regarding Claims 7 and 19:
(Canceled).
Regarding Claims 8 and 20:
Agarwal teaches:
wherein the virtual assistant, in response to receiving, at a chat interface, data comprising at least one of a user profile-related question, an issue statement, or context information, analyzes the received data to output a user-specific answer or a product recommendation. (Agarwal, a system and method for providing a natural language interface or conversation/chat interface for interacting with an automated software assistant (AA) and/or a human assistant (HA) when completing an electronic form is disclosed. For example, the electronic form may be a mortgage application soliciting input from the user in the form of questions wishing to obtain a mortgage loan….. The system may also generate quick requests, which may include individual questions or requests that user must provide when completing the form. For example, age, income, property address, and so on. Each quick request element may include a unique icon. User's response to a quick request or any other question may be tagged with an icon thus making it easier for the user to recognize which response is related to which data element. (See, Abstract; Para. 43-50, 54, 65, 85, 97)).
Regarding Claim 9:
Agarwal teaches:
A context-aware loan origination system, the system comprising: a chat user interface (UI);a task UI coupled that displays a set of tasks: (Agarwal, (See, Abstract; Para. 43, 54-59; Claim 12; Fig. 1));
a virtual assistant coupled to the chat UI and the task UI, the virtual assistant uses an interaction session to obtain, from the chat UI, user-related data comprising a set of requirements; (Agarwal, systems and methods for improving electronic form submissions by providing a natural language interface or conversation/chat interface for interacting with an automated software assistant (AA) and/or a human assistant (HA) when completing the electronic form; Further, the AA is configured to “invite” HA based on user's needs, the HA's level of skill, the HA's availability, and/or other such factors. In essence, AA may act like an “intelligent concierge” or a go-between the HA and the user. The user may converse with both the AA and the HA within the chat interface. The user satisfaction index may be the result of a mathematical function that includes the results of machine learning applied to data associating subject-related factors and self-reported or imputed levels of satisfaction, and may also combine domain expertise in the form of explicit knowledge or rules. (See, Abstract; Para. 37, 40-45, 52, 54-59, 65, 82-83, 96-97, 100, 107; Claim 12; Fig. 1));
a core engine coupled to the virtual assistant, the core engine receives the user-related data to generate a set of queries for [an underwriting database] and a product database and, in response to receiving a set of query results from [the underwriting database] and the product database, analyzes the set of query results to identify query items that satisfy at least some requirements in the set of requirements, (Agarwal, systems and methods for improving electronic form submissions by providing a natural language interface or conversation/chat interface for interacting with an automated software assistant (AA) and/or a human assistant (HA) when completing the electronic form; Further, the AA is configured to “invite” HA based on user's needs, the HA's level of skill, the HA's availability, and/or other such factors. In essence, AA may act like an “intelligent concierge” or a go-between the HA and the user. The user may converse with both the AA and the HA within the chat interface….. the user may “fill-out” a plurality of electronic forms using distinct conversations within the chat interface. In other words, the system may recognize that one conversation may be associated with an identifier, e.g., a loan number. In the event the system cannot recognize the identifier, the user may drag an icon of a previously submitted document related to that loan number to the conversation to form the association. Alternatively, the user may enter a text or voice command to make the association. Additionally, the conversation may include folders or sub-folders within the conversation which may contain information related to one particular identifier. For example, a loan number may be a parent folder and a bank account may be a folder or a sub-folder. The system may identify the folder using the identifier. (See, Abstract; Para. 37, 40-48, 52, 54, 65, 82-83, 96-97, 100; Fig. 1));
the core engine iteratively performing steps comprising: determining whether any of the requirements in the set of requirements have not been satisfied; (Agarwal, in an effort to change a response buried in a multi-message exchange, the user would have to scroll to find a relevant response and then modify it. As a result, the AA would generate a “new” set of downstream answers or commands corresponding with the updated user input (e.g., as a separate branch). These downstream answers in a new branch may be generated by reusing the information provided by the user in the original branch; the application 126 or computing components 102 operating the AA may utilize machine learning classifier that is trained based at least in part on known bad actor statements expressing interest in utilizing the services provided by the chat interface and statements of similar contextual value extracted from the prior message exchange threads of the present user. (See, Abstract; Para. 42-45, 62, 65, 78, 81-85, 96-97, 116));
in response to identifying at least one not-satisfied requirement within the set of requirements, identifying additional user-related data related to the not-satisfied requirement; (Agarwal, the application 126 or computing components 102 operating the AA may utilize machine learning classifier that is trained based at least in part on known bad actor statements expressing interest in utilizing the services provided by the chat interface and statements of similar contextual value extracted from the prior message exchange threads of the present user. For example, a corpus of prior message exchange threads may be authorized for use in training an artificial intelligence scheme such as a machine learning classifier or neural network. User words, phrases, and/or statements in the message exchange threads from known bad actors and other uses may be used as user inputs. Known identity may be provided as labeled outputs. For example, messages from known scammers., may be identified as such. A machine learning classifier, a neural network, or other artificial intelligence model may be trained using these labeled pairs to identify potential bad actor user input and/or confirm identity of a known user. (See, Abstract; Para. 42-45, 62, 65, 78, 81-85, 96-97, 116));
instructing the virtual assistant to request the additional user-related data; (Agarwal, the user may receive additional instruction from AA or HA which will then be incorporated into the response. The user may continue responding to the remaining questions and finish the multi-step process. By having AA explain to the user the question results in a timelier response and higher customer satisfaction. (See, Abstract; Para. 42-45, 62, 65, 78, 81-85, 96-97, 116));
in response to receiving the additional user-related data, determining one or more items from the query results that match the set of requirements; and (Agarwal, the user may receive additional instruction from AA or HA which will then be incorporated into the response. The user may continue responding to the remaining questions and finish the multi-step process. By having AA explain to the user the question results in a timelier response and higher customer satisfaction. (See, Abstract; Para. 42-45, 62, 65, 78, 81-85, 96-97, 116));
using the one or more items to generate a user recommendation. (Agarwal, Individual workflows are optimized for individual users based on a determination of user satisfaction for existing or standard electronic form completion workflows. As alluded to above, workflows comprise questions configured to elicit user responses to complete a particular category or phase of the process. Prior to the beginning completing a form and following each response of each user, the application 126 and/or component 104 (illustrated in FIG. 1 ) calculates a user satisfaction index which represents the overall satisfaction for each user completing the form. The user satisfaction index may be the result of a mathematical function that includes the results of machine learning applied to data associating subject-related factors and self-reported or imputed levels of satisfaction, and may also combine domain expertise in the form of explicit knowledge or rules…. User satisfaction is also a function of the chat interface guidance provided by AA or HA. User satisfaction can be increased by: (1) eliminating repeat questions, (2) having empathetic and supportive AA or HA, (3) providing user friendly instruction on how to submit and subsequently access documents, (4) the opportunity to adaptively modify answers, and (5) keeping the user informed of the progress and time necessary to complete the form. (See, Abstract; Para. 42-45, 62, 65, 78, 81-85, 96-97, 116)).
Agarwal does not specifically teach an underwriting database; and an underwriting calculation, calculates an alignment between the user question and answers.
However, Masson further teaches the following limitations:
an underwriting database; (Masson, The cloud-based platform 730 may output the results of the lending strategies and business revenue management system 102 in different formats. One example of output may be directly to the Financial Institution Operating Systems (e.g., Loan Origination System or Automated Underwriting Systems) through API 742 and following a strategy validation protocol from the system user on the interfaces 230. This may require an initial technology setup but may enhance the Financial Institution Quality Control strategy implementation results and speed to market to instantly deploy any strategies built and validated in the system 102 by the user. (See, Para. 34-36; Abstract));
[an underwriting calculation, calculates an alignment between the user question and answers] in the knowledge base to identify an answer to the question to explain [the underwriting calculation]. (Masson, The cloud-based platform 730 may output the results of the lending strategies and business revenue management system 102 in different formats. One example of output may be directly to the Financial Institution Operating Systems (e.g., Loan Origination System or Automated Underwriting Systems) through API 742 and following a strategy validation protocol from the system user on the interfaces 230. This may require an initial technology setup but may enhance the Financial Institution Quality Control strategy implementation results and speed to market to instantly deploy any strategies built and validated in the system 102 by the user; For example, this “non-compliant Reg. B data” type of information may not be used for any consumer lending underwriting strategy developed by the automated strategy builder module 212. At a high level, the Customer Data Input 202 may be flagged as regulatory non-compliant 606 or as regulatory compliant 608. At step 610, the regulatory compliant data 608 may be tested based on historical performance across users. This step may leverage the artificial intelligence / machine learning module 326 and stored performance rating in memory 226 for each data field based on previous Customer Data Input 202 and the Vendor Model Evaluation module 320. (See, Para. 34-36; Abstract)).
It would have been obvious to one of ordinary skill in the art before the effective filing of the claimed invention to have modified Agarwal with the features of Masson’s system because “while conventional systems may be capable of providing optimization models and reporting, these systems, however, are unable to capture industry knowledge and, instead, require a team of lending industry experts and statisticians to review manually or in separate systems the lending product characteristics (e.g. credit card debt to income, mortgage loan to value), and lending function and program characteristics (e.g. marketing prescreen, underwriting eligibility criteria, account line management). Such limitation either reduces the performance of lending strategies if implemented solely based on the system output or requires the work and interaction of several teams to produce a higher quality strategy that may answer the business needs and revenue targets.” (Masson, Para. 16).
Regarding Claim 10:
Agarwal teaches:
further comprising data aggregation and storage module coupled to the core engine. (Agarwal, The present embodiments provide a solution by associating the information extracted from the original branch of the conversation with a particular transaction identifier (e.g., a loan application number). Each time a new branch is generated, including a modified user response and new AA questions, that branch is associated with a previous branch by utilizing the same identifier. For example, the information extracted from each branch may be stored as a single “conversation log” in a database utilizing the online transactional processing or OLTP processing. (See, Abstract; Para. 36, 97)).
Regarding Claim 11:
Agarwal teaches:
further comprising a converter that converts data obtained from the virtual assistant into a format that is compatible with at least one of [the underwriting database]or the product database. (Agarwal, systems and methods for improving electronic form submissions by providing a natural language interface or conversation/chat interface for interacting with an automated software assistant (AA) and/or a human assistant (HA) when completing the electronic form; Further, the AA is configured to “invite” HA based on user's needs, the HA's level of skill, the HA's availability, and/or other such factors. In essence, AA may act like an “intelligent concierge” or a go-between the HA and the user. The user may converse with both the AA and the HA within the chat interface….. the user may “fill-out” a plurality of electronic forms using distinct conversations within the chat interface. In other words, the system may recognize that one conversation may be associated with an identifier, e.g., a loan number. In the event the system cannot recognize the identifier, the user may drag an icon of a previously submitted document related to that loan number to the conversation to form the association. Alternatively, the user may enter a text or voice command to make the association. Additionally, the conversation may include folders or sub-folders within the conversation which may contain information related to one particular identifier. For example, a loan number may be a parent folder and a bank account may be a folder or a sub-folder. The system may identify the folder using the identifier. (See, Abstract; Para. 37, 40-48, 52, 54, 65, 82-83, 96-97, 100; Fig. 1)).
Agarwal does not specifically teach the underwriting database.
However, Masson further teaches the following limitation:
the underwriting database; (Masson, The cloud-based platform 730 may output the results of the lending strategies and business revenue management system 102 in different formats. One example of output may be directly to the Financial Institution Operating Systems (e.g., Loan Origination System or Automated Underwriting Systems) through API 742 and following a strategy validation protocol from the system user on the interfaces 230. This may require an initial technology setup but may enhance the Financial Institution Quality Control strategy implementation results and speed to market to instantly deploy any strategies built and validated in the system 102 by the user. (See, Para.34-36; Abstract)).
It would have been obvious to one of ordinary skill in the art before the effective filing of the claimed invention to have modified Agarwal with the features of Masson’s system because “while conventional systems may be capable of providing optimization models and reporting, these systems, however, are unable to capture industry knowledge and, instead, require a team of lending industry experts and statisticians to review manually or in separate systems the lending product characteristics (e.g. credit card debt to income, mortgage loan to value), and lending function and program characteristics (e.g. marketing prescreen, underwriting eligibility criteria, account line management). Such limitation either reduces the performance of lending strategies if implemented solely based on the system output or requires the work and interaction of several teams to produce a higher quality strategy that may answer the business needs and revenue targets.” (Masson, Para. 16).
Regarding Claim 12:
Agarwal teaches:
wherein the virtual assistant comprises at least one of a language model or a knowledge base. (Agarwal, systems and methods for improving electronic form submissions by providing a natural language interface or conversation/chat interface for interacting with an automated software assistant (AA) and/or a human assistant (HA) when completing the electronic form; Further, the AA is configured to “invite” HA based on user's needs, the HA's level of skill, the HA's availability, and/or other such factors. In essence, AA may act like an “intelligent concierge” or a go-between the HA and the user. The user may converse with both the AA and the HA within the chat interface. (See, Abstract; Para. 37, 40-45, 52, 54, 65, 82-83, 96-97, 100; Fig. 1)).
Response to Arguments
With respect to the claim objections of claim 9, 10, 12, and 14-20, the objections are withdrawn in view of Applicant’s arguments/remarks made in an amendment filed on 11/08/2025. However, amended claims 1, 9, 12, 13, and 16 are objected to for the reasons presented above in this office action (See, Claim Objections section of this office action).
Applicant's arguments filed on 11/08/2025 have been fully considered, but are not persuasive due to the following reasons:
With respect to the rejection of claims 1-20 under 35 U.S.C. 101, Applicant arguments are moot in view of the grounds of rejections presented above in this office action. The arguments are addressed to the extent they apply to the amended claims.
Applicant argues that “Claims 1, 9, and 13 are clearly related to a practical application of using a context-aware loan origination system. Implementation of the claims may increase efficiency and transparency to the borrower, while simultaneously reducing costs to lenders, as explicitly disclosed in the specification, e.g., the abstract. Specifically, Claims 1, 9, and 13 are amended to explicitly comprise limitations of...a virtual assistant comprising a language model and a knowledge base that comprises a set of pre-loaded mortgage rules...whererin the virtual assistant, in response to receiving from an underwriting engine a user question regarding an underwriting calculation, calculates an alignment between the user question and answers in the knowledge base to identify an answer to the user question to explain the underwriting calculation. Applicant respectfully asserts that such limitations, together with other limitations make claim 1, as a whole, related to a practical application of a context-aware loan origination system or a method of using such a system to increase efficiency and transparency to the borrower, while simultaneously reducing costs to lenders.”
Examiner respectfully disagrees.
Under Step 2A: Prong II, Examiner respectfully notes that there is no improved technology in simply receiving, generating, analyzing (processing), determining, identifying, requesting, using, and outputting data (i.e., user-related data, underwriting data, query results, user recommendations, user questions and answers, and etc.). As noted in the 2019 Guidance on Patent Subject Matter Eligibility, the disclosed invention simply cannot be equated to improvement to technological practices or computers. There is no technical improvement at all. Instead, Applicant recites “using a context-aware loan origination system, the method comprising: in response to receiving, from a virtual assistant comprising a language model and a knowledge base that comprises a set of pre-loaded mortgage rules, user-related data associated with an interaction session, generating a set of queries for an underwriting database and a product database, the user-related data comprising a set of requirements; in response to receiving a set of query results from the underwriting database and the product database, analyzing the set of query results to identify query items that satisfy at least some requirements in the set of requirements; iteratively performing steps comprising: determining whether any of the requirements in the set of requirements have not been satisfied; in response to identifying at least one not-satisfied requirement within the set of requirements, identifying additional user-related data related to the not-satisfied requirement; instructing the virtual assistant to request the additional user-related data; in response to receiving the additional user-related data, determining one or more items from the query results that match the set of requirements; and using the one or more items to generate a user recommendation; whererin the virtual assistant, in response to receiving from an underwriting engine a user question regarding an underwriting calculation, calculates an alignment between the user question and answers in the knowledge base to identify an answer to the user question to explain the underwriting calculation.” The recited features in the limitations of amended claims 1, 9, and 13 do not result in computer functionality or technical improvement. Examiner respectfully notes that Applicant is simply using a computer/processor to input, process, and output data. The recited features in the limitations does not disclose a technical solution to technical problem, but simply a business solution. Specifically, the recited steps, as amended, are merely managing/processing data (MPEP 2106.05(d)(II)) and does not result in computer functionality or technical improvement. Thus, Applicant has simply provided a business method practice of processing data (i.e., user-related data, underwriting data, query results, user recommendations, user questions and answers, and etc.), and no technical solution or improvement has been disclosed.
Moreover, there is no technology/technical improvement as a result of implementing the abstract idea. The recited limitations in the pending claims simply amount to the abstract idea of receiving and analyzing user data to identify not-satisfied requirements within a set of underwriting requirements, without significantly more. There is no computer functionality improvement or technology improvement. The claim does not provide a technical solution to a technical problem. If there is an improvement, it is to the abstract idea and not to technology. Furthermore, Examiner notes that it is important to keep in mind that an improvement in the judicial exception itself (e.g., recited fundamental economic principle or practice and/or commercial interaction) is not an improvement in technology (See, MPEP 2106.05(a)(II)). Additionally, Examiner respectfully notes that claims 1, 9, and 13, as amended, recite steps at a high level of generality. In addition, all uses of the recited judicial exceptions require such data gathering and outputting, and, as such, these limitations do not impose any meaningful limits on the claim. These limitations amount to necessary data gathering and output. See MPEP 2106.05. The claim simply makes use of a computer as a tool to apply the abstract idea without transforming the abstract idea into a patent eligible subject matter. Thus, these arguments are not persuasive.
Additionally, these steps, as amended, are recited as being performed by a context-aware loan origination system, virtual assistant, language model, knowledge base, underwriting database, underwriting engine, and product database. The additional elements of a context-aware loan origination system, virtual assistant, language model, knowledge base, underwriting database, underwriting engine, and product database are recited at a high level of generality, and are used as a tool to perform the generic computer function of receiving, processing, and outputting data. See MPEP 2106.05(f). Amended claims 1, 9, and 13 recite a context-aware loan origination system, virtual assistant, language model, knowledge base, underwriting database, underwriting engine, and product database, which are simply used to perform an abstract idea, as discussed above in Step 2A, Prong I, such that it amounts to no more than mere instructions to apply the exception using a generic computer. See MPEP 2106.05(f). Specifically, the recitation of “a context-aware loan origination system, virtual assistant, language model, knowledge base, underwriting database, underwriting engine, and product database” in the limitations merely indicates a field of use or technological environment in which the judicial exception is performed. The claims, as amended, merely confines the use of the abstract idea to a particular technological environment; and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h). Even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application, and the claim is directed to the judicial exception. Hence, Claims 1, 9, and 13 do not integrate the abstract idea into a practical application. Thus, these arguments are not persuasive.
Applicant argues that “the claim elements amount to "significantly more" than merely a judicial exception….. Applicant respectfully asserts that the claims 1, 9, and 13, as amended, comprises at least the following elements:...a virtual assistant comprising a language model and a knowledge base that comprises a set of pre-loaded mortgage rules... whererin the virtual assistant, in response to receiving from an underwriting engine a user question regarding an underwriting calculation, calculates an alignment between the user question and answers in the knowledge base to identify an answer to the user question to explain the underwriting calculation. Such a combination of elements, a virtual assistant, comprising a language model and a knowledge base, calculates an alignment between the user question and answers in the knowledge base to identify an answer to the user question to explain the underwriting calculation is NOT well- understood routine, or conventional, evidenced by distinction from prior art with details presented in the following argument with respect to the claim rejection under 35 U.S.C. § 103.”
Examiner respectfully disagrees.
Under Step 2B, Examiner respectfully notes that all of Applicant's arguments have been reviewed, and the inventive concept cannot be furnished by a judicial exception. The improvements argued are to the abstract idea and not to technology. The technical limitations are simply utilized as a tool to implement the abstract idea without adding significantly more. Thus, the claim is directed to an abstract idea, and hence these arguments are not persuasive. The presence of a computer does not make the claimed solution necessarily rooted in computer technology. As noted above, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements of context-aware loan origination system, virtual assistant, language model, knowledge base, underwriting database, underwriting engine, and product database (Claim 1) are recited at a high level of generality in that it results in no more than simply applying the abstract idea using generic computer elements. The additional elements when considered separately and as an ordered combination do not amount to add significantly more as these limitations provide nothing more than to simply apply the exception in a generic computer environment. Furthermore, as explained above with respect to Step 2A, Prong II, the additional elements: context-aware loan origination system, virtual assistant, language model, knowledge base, underwriting database, underwriting engine, and product database (Claim 1), are at best mere instructions to “apply” the abstract idea, which cannot provide an inventive concept. See MPEP 2106.05(f). As discussed in Step 2A, Prong II above, the claims’ limitations are recited at a high level of generality. These elements simply amount to receiving and outputting data and are well-understood, routine, conventional activity. See MPEP 2106.05(d)(II). As discussed in Step 2A, Prong II above, the recitation of a computer/processor to perform recited limitations amounts to no more than mere instructions to apply the exception using a generic computer component. Even when considered in combination, these additional elements represent mere instructions to implement an abstract idea or other exception on a computer, which do not provide an inventive concept.
Hence, Examiner respectfully declines Applicant’s request to withdraw the 35 U.S.C. 101 rejection of claims 1, 4-6, 8-13, 16-18, and 20.
With respect to the rejection of claims 1-20 under 35 U.S.C. 103, Applicant arguments are moot in view of cited language in previously used prior art, as presented above in this office action. The arguments are addressed to the extent they apply to the amended claims
Applicant argues that “Applicant has amended claims 1, 9 and 13, and respectfully asserts that the claims, as amended, are patentable over Agarwal in view of Masson…..Based on at least the above remarks, the Applicant respectfully asserts that claims 1, 9, and 14, as amended, are patentable over Agarwal in view of Masson and requests withdrawn of the rejections under 35 USC 103.” Examiner respectfully disagrees and notes that Applicant's arguments are moot in view of new grounds of rejection presented above based on newly cited portions of paragraphs 37, 40-46, 52, 54-59, 65, 82-85, 96-97, 100, 107, 116; Fig. 1; and abstract of the disclosed prior art: Agarwal; and paragraphs 34-36 and abstract of the disclosed prior art: Masson, which reads on the amended language. Hence, Examiner respectfully declines Applicant’s request to withdraw the 35 U.S.C. 103 rejection of claims 1, 4-6, 8-13, 16-18, and 20.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure are the following:
Hsieh (U.S. Patent Application Publication No. US 2019/0295107 A1) - “Lead management system and methods thereof”
Wood (U.S. Patent Application Publication No. US 2022/0129890 A1) “Compliance controller for the integration of legacy systems in smart contract asset control”
Gueye (U.S. Patent Application Publication No. US 2019/0303807 A1) “Method and system for facilitating provisioning of social networking data to a mobile device”
McDonald (U.S. Patent Application Publication No. US 2017/0221142 A1) “Mortgage loan data processing system and method for a loan broker”
Arnall (U.S. Patent Application Publication No. US 2017/0337628 A1) “Automated consumer-facing mortgage processing system”
Hansen (U.S. Patent No. US 11,238,075 B1) “Systems and methods for providing inquiry responses using linguistics and machine learning”
Goel (U.S. Patent No. US 11,568,482 B1) “Systems and methods for detecting and linking data objects across distributed platforms”
Hepp (U.S. Patent Application Publication No. US 2024/0257236 A1) “Real estate finance exchange”
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MOHAMMED H MUSTAFA whose telephone number is (571)270-7978. The examiner can normally be reached M-F 8:00 - 5:00.
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, Michael W Anderson can be reached on 571-270-0508. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/MOHAMMED H MUSTAFA/Examiner, Art Unit 3693
/ELIZABETH H ROSEN/Primary Examiner, Art Unit 3693