METHODS AND SYSTEMS FOR FACILITATING MANAGEMENT OF REAL ESTATE TRANSACTIONS

Application No. 19/425,653

• Filed: Dec 18, 2025
• Priority: Dec 18, 2024 — provisional 63/735,707
• Examiner: PADUA, NICO LAUREN
• Art Unit: 3626
• Tech Center: 3600 — Transportation & Electronic Commerce
• Assignee: Klaviss Technologies Corporation
• OA Round: 1 (Non-Final)

Office Action

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 is a non-final rejection in response to claims filed on 12/18/2025. Claims 1-20 are pending and are examined herein.
Priority
The claims hold the priority of prior filed provisional application filed on 12/18/2024.

Information Disclosure Statement
The information disclosure statement (IDS) submitted on US 20240320745 A1 The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.

Claim Rejections – 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.

Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.

Step 1: Is the claim to a Process, Machine, Manufacture, or Composition of Matter?
Claims 1-10: A method for facilitating management of real estate transactions, the method comprising:
Claims 11-20: A system for facilitating management of real estate transactions, the system comprising:
Claims 1-10 are directed to a method making it a process claim. Claims 11-20 are directed to a computer system and a non-transitory computer readable medium which falls under at least machine or manufacture. Therefore, claims 1-16 are directed to at least one potentially eligible subject matter category and are to be further analyzed under step 2 of the eligibility analysis.

Step 2a Prong 1: Is the claim directed to a Judicial Exception (A Law of Nature, a Natural Phenomenon (Product of Nature), or An Abstract Idea?)
The claims under the broadest reasonable interpretation in light of the specification are analyzed herein. Claims 1, and 11 are marked up, isolating the abstract idea from additional elements, wherein the abstract idea is set in bold and the additional elements have been italicized as follows:

Claim 1: A method for facilitating management of real estate transactions, the method comprising:
receiving, using a communication device, a document data from at least one first entity device associated with at least one first entity, wherein the document data represents at least one real estate document associated with at least one real estate transaction;
receiving, using the communication device, a task data from the at least one first entity device, wherein the task data represents at least one task associated with the at least one real estate document relative to the at least one real estate transaction;
analyzing, using a processing device, each of the document data and the task data using at least one artificial intelligence (AI) model;
determining, using the processing device, a completion status for the at least one real estate transaction using the at least one AI model based on the analyzing of each of the document data and the task data;
generating, using the processing device, a notification data based on the determining of the completion status, wherein the notification data represents at least one notification informing at least one second entity of completion status; and
transmitting, using the communication device, the notification data to at least one second entity device associated with the at least one second entity.

Claim 11: A system for facilitating management of real estate transactions, the system comprising:
a communication device configured for:
receiving a document data from at least one first entity device associated with at least one first entity, wherein the document data represents at least one real estate document associated with at least one real estate transaction;
receiving a task data from the at least one first entity device, wherein the task data represents at least one task associated with the at least one real estate document relative to the at least one real estate transaction; and
transmitting a notification data to at least one second entity device associated with at least one second entity; and
a processing device communicatively coupled with the communication device, wherein the processing device is configured for:
analyzing each of the document data and the task data using at least one artificial intelligence (AI) model;
determining a completion status for the at least one real estate transaction using the at least one AI model based on the analyzing of each of the document data and the task data; and
generating the notification data based on the determining of the completion status, wherein the notification data represents at least one notification informing the at least one second entity of completion status.

When evaluating the bolded limitations of the claims under the broadest reasonable interpretation in light of the specification, it is clear that representative claims 1, and 11 recite an abstract idea under the category of certain methods of organizing human activity. This abstract idea grouping found in MPEP 2106.04(a)(2)(II)(B) includes claims to “commercial or legal interactions (including agreements in the form of contracts, legal obligations, advertising, marketing or sales activities or behaviors, and business relations);” The claim language at hand falls squarely within this subcategory because, as a non-limiting example, receiving document data (which includes real estate contracts and other legal information), in order to determine whether a task at hand is complete, is a recitation of enforcing contractual obligations, and performing sales activities, behaviors, and business relations, which are all examples of “commercial or legal interactions.” Furthermore, even when considering that a “model” performs the analysis, given that the claims merely recite data collection, data analysis, and data output, wherein the output is merely a notification to a user, it is no more than an interaction of a user that falls within “certain methods of organizing human activity.” MPEP 2106.04(a)(2)(II) states, “Finally, the sub-groupings encompass both activity of a single person (for example, a person following a set of instructions or a person signing a contract online) and activity that involves multiple people (such as a commercial interaction), and thus, certain activity between a person and a computer (for example a method of anonymous loan shopping that a person conducts using a mobile phone) may fall within the "certain methods of organizing human activity" grouping. It is noted that the number of people involved in the activity is not dispositive as to whether a claim limitation falls within this grouping. Instead, the determination should be based on whether the activity itself falls within one of the sub-groupings.” Therefore, the activity itself falls within the sub-grouping, regardless of whether a model or a person is performing the analysis. Therefore, the claims recite an abstract idea of “receiving real estate document data,” “receiving task data,” “analyzing the data using a model,” “determining the completion status of a real estate transaction,” and “generating and transmitting a notification of the completion status to a user.”
Therefore, the claims recite “certain methods of organizing human activity,” under at least “commercial or legal interactions.”

Step 2A Prong 2: Does the claim recite additional elements that integrate the judicial exception into a practical application?
The claims include the following additional elements:
- communication device in claims 1 and 11
- processing device in claims 1 and 11
- artificial intelligence in claims 1 and 11

The additional elements are no more than a recitation of the words “apply it” (or an equivalent) or mere instructions to implement an abstract idea or other exception using generic computing components. In this case the abstract idea of “receiving real estate document data,” “receiving task data,” “analyzing the data using a model,” “determining the completion status of a real estate transaction,” and “generating and transmitting a notification of the completion status to a user” is being implemented on communication devices, and processing devices. Please review MPEP 2106.05(f) for more information regarding Mere Instructions To Apply An Exception. It is clear in Fig. 1 that the system architecture is no more than a generic computer, wherein the data processing can be performed on any generic computing device. Furthermore, the additional element of the model being an “artificial intelligence model” is no more than “a general link to a particular technological field,” and it further falls under “apply it.” Other than merely limiting the model to be an artificial intelligence model, there are no steps that meaningfully limit how artificial intelligence is applied to the abstract idea. Furthermore, the use of “artificial intelligence” is equivalent to apply it because it merely recites the intended outcome or use of the artificial intelligence model, without the necessary steps (such as algorithms, or structure) to arrive at the intended solution.
Furthermore, there is no improvement to any computer functionality or technical field, therefore, even when considering the additional elements individually or as an ordered combination, the additional elements fail to integrate the abstract idea into a practical application. Even when considering the specification, particularly [0036-0047], the specification alleges “inherent technical improvements,” however, it is not clear that the claims themselves reflect any of the alleged improvements in the specification, given the breadth of the claims. Furthermore, the search for a technical improvement is based on whether the claim contains an improvement to the functioning of a computer, or an improvement to any other technology or technical field. However, the specification alleges improvements over “traditional systems” in [0038, 0040, 0041, 0046], wherein the analysis is based on whether there is a technical improvement over the prior art at the time of the filing of the invention.
Therefore, even when considering the claims individually or as an ordered combination, the claims are directed to an abstract idea without integration into a practical application.

Step 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception?
The claims include the following additional elements:
- communication device in claims 1 and 11
- processing device in claims 1 and 11
- artificial intelligence in claims 1 and 11

The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because, when considered separately and as an ordered combination, they do not add significantly more (also known as an “inventive concept”) to the exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using communication devices, and processing devices to carry out “receiving real estate document data,” “receiving task data,” “analyzing the data using a model,” “determining the completion status of a real estate transaction,” and “generating and transmitting a notification of the completion status to a user” amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept(See MPEP 2106.05(f)). Furthermore, no improvements to the processing resources have been purported, because generic computing devices are known to be able to handle the software functions claimed. Furthermore, no improvements to the fields of artificial intelligence have been purported, as they are merely used in their ordinary capacity or are generally linked to the abstract idea. Please review MPEP 2106.05(a) for more information regarding improvements to computing devices(Section I), or technological fields(Section II). Therefore in accordance with MPEP 2106.05(a), nothing in the claims, even when viewed as a whole, meaningfully limits the claims such that they provide significantly more than the abstract idea.

The dependent claims 2-10, and 12-20 are also given the full two-part analysis, individually and in combination with the claims they depend on, in the following analysis:
Claims 2, 3, 12 and 13 recite more of the same abstract idea because it adds the steps of determining a regulatory requirement, obtaining regulatory data, and analyzing the regulatory data to determine the completion status (claims 2 and 12), or generating a regulatory query, transmitting the regulatory query to obtain regulatory data (claims 3 and 13). Both of these steps are still no more than “data gathering, data analysis, and data output steps,” which fall within “commercial or legal interactions,” because they all consist of legal interactions and checking for compliance. There are no further additional elements, and even when considering the repeated additional element of the AI model, this is still “apply it” and “a general link” because it is merely instructing the use of AI to perform the analyzing step without any further information on how such analysis is to be carried out. Therefore, the claims do not integrate the abstract idea into a practical application, even when viewed as a whole, and nothing meaningfully limits the claims such that it is significantly more than the abstract idea. Claims 4 and 14 merely further add the additional element of the AI model being an “optical character recognition-enabled large language (OCR-LLM) model.” However, merely naming a type of model, that is not part of the claimed invention, is also a general link to a technical field, in this case, the field of optical character recognition and large language models. The claims merely limit the reach of the claimed abstract idea to a particular technological use, such that it merely confines the use of OCR and LLM to the abstract idea without meaningfully limiting exactly how the use of OCR and LLM carries out the intended outcome or solution. Furthermore, no improvements to OCR, LLMs, or even AI are reflected within the scope of the claims, therefore whether analyzed individually or in combination with the previous additional elements, the claims are still equivalent to “apply it” and therefore do not integrate the abstract idea into a practical application. Even when viewed as a whole, and nothing meaningfully limits the claims such that it is significantly more than the abstract idea.
Claims 5 and 15 further limit the abstract idea by adding steps that still fall within the abstract idea, for example, verifying a document using “zero-knowledge proof,” at the level of generality in which it is claimed is no more than a “commercial or legal interaction,” because it merely recites the intended outcome of verifying without revealing the content of the document. However, there are no further additional elements to consider, because the scope of the claims falls squarely within the abstract idea. Therefore, the claims do not integrate the abstract idea into a practical application, even when viewed as a whole, and nothing meaningfully limits the claims such that it is significantly more than the abstract idea.
Claims 6-8, and 16-18 further limit the abstract idea by instructing the AI model to perform further abstract idea tasks, such as determining a jurisdiction associated with the transaction, identifying the regulatory body, and transmitting a regulatory query (claims 6 and 16), which all fall squarely under “commercial or legal interactions.” Furthermore, claims 7 and 17 merely predict upcoming additional tasks using a third AI model, however, the claims do not recite the steps required to arrive at the outcome, therefore it is merely a further limitation of the abstract idea. Finally, claims 8 and 18 recite determining a valuation for a real estate property based on characteristics derived from document data, which falls within marketing, sales activity or business relations, however, other than using AI, it does not recite exactly how to arrive at the valuation. Therefore, the claims recite more of the same abstract idea, with the additional element of the “database device(claims 6 and 16), and the “second, third, and fourth AI models” still being equivalent to “apply it” because they are merely generic computing used to carry out the abstract idea. Even when considering individually, or in combination with the existing additional elements, the claims still fall within “apply it” or mere instructions to perform the abstract idea. Even when viewed as a whole, nothing meaningfully limits the abstract idea such that it is significantly more.
Claims 9, 10, 19 and 20 recite more of the same abstract idea because it is merely recites further data outputs that fall within “commercial or legal interactions,” such as providing “rectification data based on the incomplete status,” or “generating an assessment report.” These tasks still fall within “certain methods of organizing human activity,” especially when considering the generality in which they are recited. Furthermore, the additional element of the fifth AI model is still equivalent to “apply it” because they are merely used to carry out the abstract idea. Even when considering individually, or in combination with the existing additional elements, the claims still fall within “apply it” or mere instructions to perform the abstract idea. Even when viewed as a whole, nothing meaningfully limits the abstract idea such that it is significantly more.

Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –

(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.

(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.

Claims 1-4, 6, 7, 9, 11-14, 16, 17, and 19 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Malanga et al. (US 20240411982 A1) hereinafter Malanga.

Regarding Claim 1:
Malanga teaches:
A method for facilitating management of real estate transactions, the method comprising: (Malanga [0002] The present application is directed to systems and methods for extracting information from textual and non-textual data sources. Some embodiments are directed to extracting values associated with key-value pairs from non-textual data sources. Some embodiments are directed to validating received data to ensure compliance with completeness and/or correctness rules.)
- receiving, using a communication device, a document data from at least one first entity device associated with at least one first entity, (Malanga [0056] In some embodiments, the compliance review system 100 may receive one or more documents from the TCs 154 or the auditors 152 through one or more user interfaces provided by the TC User Interface module 104 and/or the Auditor User Interface module 102, through APIs, through databases, and/or through cloud storage, in order to satisfy one or more compliance requirements. For example, there may be an upload function for the TCs 154 to send documents from their local hard drive to the compliance review system 100 or an attachment function that allows TCs 154 to associate uploaded documents with specific checklist items. In some embodiments, these documents can be stored in the Transaction Database 130 along with any other relevant information about that transaction. [0054] In some embodiments, the compliance review system 100 may have a TC User Interface module 104 that provides user interfaces for transaction coordinators 154 (“TCs”) or other agents to interact with the compliance review system 100, such as through their user device. The compliance review system 100 may also have an Auditor User Interface module 102 that provides user interfaces for auditors 152 or compliance review teams to interact with the compliance review system 100, such as through their user device. )
- wherein the document data represents at least one real estate document associated with at least one real estate transaction; (Malanga [0007] In some embodiments, a compliance review system may facilitate or at least partially automate a compliance review process for auditing real estate transaction documents. [0048] Currently, most real estate transactions are performed manually, requiring an individual, such as an agent or broker, to identify, collect, and populate documents required to complete a real estate transaction. The agent or broker must also ensure that the documents contain any updates and are correctly populated.)
- receiving, using the communication device, a task data from the at least one first entity device, wherein the task data represents at least one task associated with the at least one real estate document relative to the at least one real estate transaction; (Malanga [0008] In some embodiments, the compliance review system may provide transaction coordinators with a checklist of compliance requirements of one or more applicable jurisdictions and lists of documents needed to satisfy those compliance requirements. [0071] In some embodiments, the compliance review system 100 may include a Checklist Database 134 that stores various checklists, each of which can be associated with a particular jurisdiction and the rules of that jurisdiction. For instance, a checklist may contain checklist items that describe the type(s) of document(s) that need to be validated in order to satisfy requirements for any given transaction for the associated jurisdiction. In some embodiments, the checklist listing the compliance requirements of one or more applicable jurisdictions can be specified or otherwise prepared by managing brokers associated with the compliance review system. [0072] In some embodiments, the compliance review system 100 may include a Dynamic Checklist module 122 for manipulating or modifying these checklists.) Checklist requirements falls within the scope of “task data.”
- analyzing, using a processing device, each of the document data and the task data using at least one artificial intelligence (AI) model; (Malanga [0095] FIG. 5 is a block diagram illustrating an overview of devices on which some implementations of the compliance review system can operate. The devices can comprise hardware components of a device 500 with an operating system (OS) 562. Device 500 can include one or more input devices 520, that provide input to the CPU(s) (processor) 510, notifying it of actions. [0077] As described in more detail herein, in some embodiments, not all documents may undergo review by an auditor. Rather, some documents may be automatically processed and/or analyzed by the system. In some embodiments, the system can be configured to accept or reject documents automatically under certain conditions. [0017] applying the compliance rule, wherein the applying the compliance rule including checking for at least one of: correctness of the document or completeness of the document; [0064] As a non-limiting example, a TC 154 may upload a document and the Document Automation AI 110 may automatically read the document, determine its contents, classify the document, extract the relevant data from the document, determine whether that relevant data is proper based on context, and/or split the document into separate files to be attached to separate checklist items based on page ranges chosen from within the document, and so forth. [0065] Together with the Document Automation AI 110, these two AI components may serve to perform automated document validation and acceptance using various techniques such as OCR, machine learning, rules engines, and so forth.)
- determining, using the processing device, a completion status for the at least one real estate transaction using the at least one AI model based on the analyzing of each of the document data and the task data; (Malanga [0017] determining, based at least in part on applying the compliance rule, that the document complies with the compliance rule; and [0089] In response, the system can provide the checklist and outstanding audit items. At operation 372, the system can receive audit feedback, which can indicate that one or more items in a checklist require revision, are missing, etc. In some embodiments, the audit feedback may indicate that the checklist is complete. [0092] At operation 392, the system can automatically review the coversheet information to determine the completeness, correctness, or both of the coversheet information. At operation 392, the system can receive completed documents. For example, the system can receive completed electronic documents... In some embodiments, received documents can include documents with electronic signatures. In some embodiments, received documents can include documents with wet ink signatures. At operation 396, the system can automatically review the received completed documents, for example, to check for consistency, completeness, compliance with signature requirements, etc., for example, as described herein. )
- generating, using the processing device, a notification data based on the determining of the completion status, wherein the notification data represents at least one notification informing at least one second entity of completion status; and (Malanga [0017] accepting the document, wherein accepting the document includes updated the checklist item to indicate that the checklist item is complete. [0092] At operation 398, the system can notify respective parties (e.g., agents, lenders, etc.) that one or more documents were rejected. The system may reject a document for a variety of reasons, such as inability to parse the document (e.g., due to poor scan quality), missing information, incorrect information, a document being an incorrect document (e.g., the wrong form was submitted), etc. The respective parties can receive notification of a rejected document and take action to correct the issue.)
- transmitting, using the communication device, the notification data to at least one second entity device associated with the at least one second entity. (Malanga [0060] In some embodiments, the Event Driven Workflow module 108 may play a role in alerts and notifications, such as sending system-generated emails to TCs 154 to alert them of upcoming listing expirations and missing checklist requirements. [0107] The document processing AI may also be able to process content within communications (such as email, chat, comments, audit summaries, canned responses), extract any relevant data, and then present that data where/when auditors may need it within the workflow described herein. For example, the system may provide to auditors a dashboard that displays notifications and alerts for missing or incorrect documents or missing/incorrect data within a particular document.)

Regarding Claim 2:
Malanga teaches: The method of claim 1 further comprising:
- determining, using the processing device, at least one regulatory requirement associated with the at least one real estate transaction based on the analyzing of each of the document data and the task data; (Malanga [0071] In some embodiments, the compliance review system 100 may include a Checklist Database 134 that stores various checklists, each of which can be associated with a particular jurisdiction and the rules of that jurisdiction. For instance, a checklist may contain checklist items that describe the type(s) of document(s) that need to be validated in order to satisfy requirements for any given transaction for the associated jurisdiction. In some embodiments, the checklist listing the compliance requirements of one or more applicable jurisdictions can be specified or otherwise prepared by managing brokers associated with the compliance review system. [0071] In some embodiments, the checklist can be automatically populated by the system 100 based on the Rules Database 132 containing various compliance requirements organized by jurisdiction, and the applicable jurisdictions of the property as determined by the TCs 154, the Auditors 152, and/or the system 100. In some embodiments, the checklist lists the types of documents that can satisfy each compliance requirement or otherwise required by the system 100 for validation.)
- obtaining, using the processing device, a regulatory data based on the determining of the at least one regulatory requirement, wherein the regulatory data represents at least one regulatory detail associated with the at least one real estate transaction; and (Malanga [0072] In some embodiments, the compliance review system 100 may include a Dynamic Checklist module 122 for manipulating or modifying these checklists. For instance, the Dynamic Checklist module 122 may automatically or selectively provide checklist template management as an admin function to various users (e.g., non-engineers) of the compliance review system 100 to allow them to make changes to the checklists and their items (e.g., listed types of documents acceptable for a particular compliance requirement) to better suit a particular transaction or set of transactions. TCs 154 may also be able to use the Dynamic Checklist module 122 to filter checklists based on the locality of the transaction property and property type. These dynamic checklists may allow for streamlined document creation and validation and also a unification of experiences for the TCs 154 and partner agents.)
- analyzing, using the processing device, the regulatory data using the at least one AI model, wherein the determining of the completion status is further based on the analyzing of the regulatory data. (Malanga [0067] In some embodiments, large language models (LLM) calibrated to perform particular tasks may be used. An LLM fine-tuned on real estate transactions may be integrated, along with the Document Automation AI 110 and/or the Risk Analysis AI 112 into a conversational AI such as Chatbot AI 114, which can be used to carry out various tasks associated with the compliance review workflow. For instance, an auditor 152 may be able to converse with the Chatbot AI 114 and request that it check to see if a set of documents are properly signed. The system 100 may be able to retrieve the set of documents from the Transaction Database 134 and apply the Document Automation AI 110 and/or the Risk Analysis AI 112 to verify that the documents are properly signed, and then the Chatbot AI 114 may be able to accurately convey that information back to the auditor 152 in the conversation. [0070] In some embodiments, the compliance review system 100 may include a Rules Database 132 that contains sets of rules for various jurisdictions that transactions may take place in.)

Regarding Claim 3:
Malanga teaches The method of claim 2 further comprising:
- generating, using the processing device, at least one regulatory query based on the determining of the at least one regulatory requirement; (Malanga [0070] Thus, the transactions for a particular jurisdiction may be further subject to different checklists and checklist items. In some embodiments, the compliance review system 100 can receive property information and can automatically determine, for example, a specific ruleset to use based on the property location, property type (e.g., condominium, apartment, co-op, single family home, single family home in a planned development, etc.), and/or any other relevant information.)
- transmitting, using the communication device, the at least one regulatory query to at least one regulatory database device associated with at least one regulatory database of at least one regulatory body; and (Malanga [0071] In some embodiments, the compliance review system 100 may include a Checklist Database 134 that stores various checklists, each of which can be associated with a particular jurisdiction and the rules of that jurisdiction. For instance, a checklist may contain checklist items that describe the type(s) of document(s) that need to be validated in order to satisfy requirements for any given transaction for the associated jurisdiction. In some embodiments, the checklist listing the compliance requirements of one or more applicable jurisdictions can be specified or otherwise prepared by managing brokers associated with the compliance review system. [0129] For example, requirements for different documents can be stored in a database, and the system can query the database to determine the requirements based on the document type.)
- receiving, using the communication device, the regulatory data from the at least one regulatory database device, wherein the obtaining of the regulatory data is further based on the receiving of the regulatory data. (Malanga [0071] In some embodiments, the checklist can be automatically populated by the system 100 based on the Rules Database 132 containing various compliance requirements organized by jurisdiction, and the applicable jurisdictions of the property as determined by the TCs 154, the Auditors 152, and/or the system 100. In some embodiments, the checklist lists the types of documents that can satisfy each compliance requirement or otherwise required by the system 100 for validation. [0128] As described herein, different jurisdictions may have different requirements for documents. In some cases, a jurisdiction may require a handwritten (“wet ink”) signature on certain documents, while other jurisdictions may permit typed signatures. In some embodiments, the approaches herein can be used to determine if signatures meet one or more signature requirements.)

Regarding Claim 4:
Malanga teaches: The method of claim 1,
- wherein the at least one AI model is an optical character recognition-enabled large language (OCR-LLM) model. (Malanga [0063] These AI components may utilize one or more AI or data processing techniques 116, such as machine learning (ML), large language models (LLMs), optical character recognition (OCR), natural language processing (NLP), and so forth. These AI or data processing techniques may be integrated into one or more particular applications associated with the system. For example, NLP and/or an LLM can be used to summarize a freeform document such as an inspection report. [0067] In some embodiments, large language models (LLM) calibrated to perform particular tasks may be used. An LLM fine-tuned on real estate transactions may be integrated, along with the Document Automation AI 110 and/or the Risk Analysis AI 112 into a conversational AI such as Chatbot AI 114, which can be used to carry out various tasks associated with the compliance review workflow. [0105] In some embodiments, once the TC has uploaded at least one document, the compliance review system may scan the document to determine whether the document can be approved by the system or the document needs to be reviewed by a human Auditor. In some embodiments, the system may utilize optical character recognition (OCR), machine learning (ML), artificial intelligence (AI), large language models (LLMs), and/or natural language processing (NLP) techniques to scan, determine the contents of, and/or identify certain features (e.g., signatures) in the document. )

Regarding Claim 6:
Malanga teaches: The method of claim 3,
- wherein the at least one AI model comprises a second artificial intelligence (AI) model, wherein the method further comprises:(Malanga [0063] For example, in some embodiments, the compliance review system 100 may include various AI components such as a Document Automation AI 110, a Risk Analysis AI 112, and/or a Chatbot AI 114.)
- determining, using the processing device, at least one jurisdiction associated with the at least one real estate transaction using the second AI model based on the analyzing of each of the document data and the task data; and (Malanga [0049] In some embodiments, the system provides a predetermined checklist listing the compliance requirements of one or more applicable jurisdictions. [0070] In some embodiments, the compliance review system 100 may include a Rules Engine 120 that may be used to generate and determine the checklists that are stored in the Checklist Database 134. The Rules Engine 120 may evaluate certain data points about a property or transaction and, if present, automatically change certain checklist items from “optional” to “required.” Thus, the transactions for a particular jurisdiction may be further subject to different checklists and checklist items. In some embodiments, the compliance review system 100 can receive property information and can automatically determine, for example, a specific ruleset to use based on the property location, property type (e.g., condominium, apartment, co-op, single family home, single family home in a planned development, etc.), and/or any other relevant information.)
- identifying, using the processing device, the at least one regulatory body associated with the at least one jurisdiction based on the determining of the at least one jurisdiction, (Malanga [0079] In some embodiments, the system requests preliminary information (“cover sheet information”) about the property to be listed from the TC, such as the year the property was built, if there will be tenants, the type of deal, the commission to be offered (e.g., as a percentage), and any HOA options. In some embodiments, the system gives the TC the option to select one or more applicable jurisdictions. In some embodiments, the system automatically selects one or more applicable jurisdictions based on, for example, the location of the property (e.g., per the address input by the TC) and/or any special features of the property (e.g., includes solar panels). [0115] In some embodiments, the system may allow the Auditor to notify the TC that the TC or the system selected the incorrect jurisdiction for the checklist and/or start a new checklist corresponding to the proper jurisdiction.)
- wherein the transmitting of the at least one regulatory query to the at least one regulatory database device associated with the at least one regulatory database of the at least one regulatory body is further based on the identifying of the at least one regulatory body. (Malanga [0071] In some embodiments, the compliance review system 100 may include a Checklist Database 134 that stores various checklists, each of which can be associated with a particular jurisdiction and the rules of that jurisdiction. For instance, a checklist may contain checklist items that describe the type(s) of document(s) that need to be validated in order to satisfy requirements for any given transaction for the associated jurisdiction. In some embodiments, the checklist listing the compliance requirements of one or more applicable jurisdictions can be specified or otherwise prepared by managing brokers associated with the compliance review system. In some embodiments, the checklist can be automatically populated by the system 100 based on the Rules Database 132 containing various compliance requirements organized by jurisdiction, and the applicable jurisdictions of the property as determined by the TCs 154, the Auditors 152, and/or the system 100. In some embodiments, the checklist lists the types of documents that can satisfy each compliance requirement or otherwise required by the system 100 for validation.)

Regarding Claim 7:
Malanga teaches: The method of claim 1,
- wherein the at least one AI model further comprises a third artificial intelligence (AI) model, wherein the method further comprises: (Malanga [0149] Machine learning models can used for various operations as described herein. A model can refer to a construct that is trained using training data to generate new data items, classify data items, or analyze data items, for example, to make predictions or provide probabilities. For example, training data for supervised learning can include items with various parameters and an assigned classification. A new data item can have parameters that a model can use to assign a classification to the new data item.)
- determining, using the processing device, at least one upcoming additional task associated with the at least one real estate transaction using the third AI model based on the analyzing of each of the document data and the task data; (Malanga [0070] In some embodiments, the compliance review system 100 may include a Rules Engine 120 that may be used to generate and determine the checklists that are stored in the Checklist Database 134. The Rules Engine 120 may evaluate certain data points about a property or transaction and, if present, automatically change certain checklist items from “optional” to “required.” Thus, the transactions for a particular jurisdiction may be further subject to different checklists and checklist items. In some embodiments, the compliance review system 100 can receive property information and can automatically determine, for example, a specific ruleset to use based on the property location, property type (e.g., condominium, apartment, co-op, single family home, single family home in a planned development, etc.), and/or any other relevant information.) Determining further checklist items satisfies “upcoming additional task.”
- generating, using the processing device, an upcoming task data using the third AI model based on the determining of the at least one upcoming additional task; and (Malanga [0110] In some embodiments, the system provides a Productization of Risk Score to facilitate dynamic acceptance criteria based on locale, transaction attributes, TC attributes, etc. In some embodiments, the system includes a rules engine that evaluates certain data points about a property and, if present, automatically changes certain checklist items from “optional” to “required.” In some embodiments, the system includes a rules engine that can automate the marking of checklist items as required based on property attributes. In some embodiments, the system includes filters and restrictions to prevent incomplete data from being synced to downstream systems. In some embodiments, the platform includes a risk function that can include TC evaluations based on historical performance. For example, if a particular TC is marked as “low risk” or has a high reliability score, the system may automatically accept documents attached to certain checklist items by that particular TC, while the same documents may not be automatically accepted when submitted by a TC with a higher risk or lower reliability. In another example, in calculating a TC reliability score, the system may review a 180-day period (or a different period) of the TC's recent history and calculate what percentage of documents uploaded by the TC were approved the first time. In some embodiments, the system includes automated document validation and acceptance using OCR, machine learning, AI, and/or additions to the rules engines.)
- transmitting, using the communication device, the upcoming task data to each of the at least one first entity device and the at least one second entity device. (Malanga [0010] In some embodiments, the compliance review system may transmit and/or display the documents received from the transaction coordinators to the auditors, organized by the compliance requirements on the checklist. [0090] 376, the system can provide a list of action items to the user. In some embodiments, the user may view the rejected checklist items or the action items, but not both. In some embodiments, action items can be provided first, and the checklist items can be shown to the user upon the user selecting an action item. At operation 377, the system can receive one or more new or revised documents for one or more checklist items. For example, the user may upload new or revised documents for checklist items that were rejected. In some embodiments, the user may review comments that indicate why a previously-submitted document was rejected, which can help inform the user of what needs to be done to correct the issue or issues that caused the document to be rejected. At operation 378, the system can update one or more checklist items to indicate a new status. For example, in response to the user uploading a new or modified document for a checklist item, the status of the checklist item can change from rejected to accepted or from rejected to under review, for example, depending upon whether the uploaded document was automatically accepted or will undergo further review before being accepted. )

Regarding Claim 9:
Malanga teaches: The method of claim 1,
- wherein the completion status comprises at least one of a complete status and an incomplete status, wherein the method further comprises (Malanga [0140]Compliance reviews can include, for example, validating an uploaded document, validating that a correct document was uploaded, automated review of system-generated or system-provided documents, [0017] wherein the applying the compliance rule including checking for at least one of: correctness of the document or completeness of the document; determining, based at least in part on applying the compliance rule, that the document complies with the compliance rule; and accepting the document, wherein accepting the document includes updated the checklist item to indicate that the checklist item is complete. [0110] In some embodiments, the system includes filters and restrictions to prevent incomplete data from being synced to downstream systems.)
- generating, using the processing device, a rectification data based on the determining of the completion status comprising the incomplete status, (Malanga [0090] For example, the user may upload new or revised documents for checklist items that were rejected. In some embodiments, the user may review comments that indicate why a previously-submitted document was rejected, which can help inform the user of what needs to be done to correct the issue or issues that caused the document to be rejected. [0122] At operation 1208, the system can verify document correctness. For example, the system can verify that dates are within an acceptable range (e.g., a closing date is not in the past, a build date for an existing property is not in the future, etc.), that dollar amounts are within a predefined range (e.g., greater than a minimum amount or less than a maximum amount), that values are consistent with values previously entered on other forms, and so forth. At operation 1210, if the system determines that the document is not correct, the system can reject the document at operation 1212. In some embodiments, the system can provide an explanation for why the document was rejected, such as a closing date being in the past, a price being inconsistent with the price on another form, and so forth. If, at operation 1210, the system determines that the document is correct, the system can accept the document at operation 1214.)
- wherein the rectification data represents at least one rectification detail relative to the at least one task. (Malanga [0092] At operation 396, the system can automatically review the received completed documents, for example, to check for consistency, completeness, compliance with signature requirements, etc., for example, as described herein. At operation 398, the system can notify respective parties (e.g., agents, lenders, etc.) that one or more documents were rejected. The system may reject a document for a variety of reasons, such as inability to parse the document (e.g., due to poor scan quality), missing information, incorrect information, a document being an incorrect document (e.g., the wrong form was submitted), etc. The respective parties can receive notification of a rejected document and take action to correct the issue.)

Regarding Claim 11:
Malanga teaches: A system for facilitating management of real estate transactions, the system comprising:
- a communication device configured for: (Malanga [0054] In some embodiments, the compliance review system 100 may have a TC User Interface module 104 that provides user interfaces for transaction coordinators 154 (“TCs”) or other agents to interact with the compliance review system 100, such as through their user device. The compliance review system 100 may also have an Auditor User Interface module 102 that provides user interfaces for auditors 152 or compliance review teams to interact with the compliance review system 100, such as through their user device.)
- receiving a document data from at least one first entity device associated with at least one first entity, wherein the document data represents at least one real estate document associated with at least one real estate transaction; (Malanga [0056] In some embodiments, the compliance review system 100 may receive one or more documents from the TCs 154 or the auditors 152 through one or more user interfaces provided by the TC User Interface module 104 and/or the Auditor User Interface module 102, through APIs, through databases, and/or through cloud storage, in order to satisfy one or more compliance requirements. For example, there may be an upload function for the TCs 154 to send documents from their local hard drive to the compliance review system 100 or an attachment function that allows TCs 154 to associate uploaded documents with specific checklist items. In some embodiments, these documents can be stored in the Transaction Database 130 along with any other relevant information about that transaction. [0007] In some embodiments, a compliance review system may facilitate or at least partially automate a compliance review process for auditing real estate transaction documents. [0048] Currently, most real estate transactions are performed manually, requiring an individual, such as an agent or broker, to identify, collect, and populate documents required to complete a real estate transaction. The agent or broker must also ensure that the documents contain any updates and are correctly populated.)
- receiving a task data from the at least one first entity device, wherein the task data represents at least one task associated with the at least one real estate document relative to the at least one real estate transaction; and (Malanga [0008] In some embodiments, the compliance review system may provide transaction coordinators with a checklist of compliance requirements of one or more applicable jurisdictions and lists of documents needed to satisfy those compliance requirements. [0071] In some embodiments, the compliance review system 100 may include a Checklist Database 134 that stores various checklists, each of which can be associated with a particular jurisdiction and the rules of that jurisdiction. For instance, a checklist may contain checklist items that describe the type(s) of document(s) that need to be validated in order to satisfy requirements for any given transaction for the associated jurisdiction. In some embodiments, the checklist listing the compliance requirements of one or more applicable jurisdictions can be specified or otherwise prepared by managing brokers associated with the compliance review system. [0072] In some embodiments, the compliance review system 100 may include a Dynamic Checklist module 122 for manipulating or modifying these checklists.) Checklist requirements falls within the scope of “task data.”
- transmitting a notification data to at least one second entity device associated with at least one second entity; and (Malanga [0060] In some embodiments, the Event Driven Workflow module 108 may play a role in alerts and notifications, such as sending system-generated emails to TCs 154 to alert them of upcoming listing expirations and missing checklist requirements. [0107] The document processing AI may also be able to process content within communications (such as email, chat, comments, audit summaries, canned responses), extract any relevant data, and then present that data where/when auditors may need it within the workflow described herein. For example, the system may provide to auditors a dashboard that displays notifications and alerts for missing or incorrect documents or missing/incorrect data within a particular document.)
- a processing device communicatively coupled with the communication device, wherein the processing device is configured for: (Malanga [0095] FIG. 5 is a block diagram illustrating an overview of devices on which some implementations of the compliance review system can operate. The devices can comprise hardware components of a device 500 with an operating system (OS) 562. Device 500 can include one or more input devices 520, that provide input to the CPU(s) (processor) 510, notifying it of actions.)
- analyzing each of the document data and the task data using at least one artificial intelligence (AI) model; (Malanga [0077] As described in more detail herein, in some embodiments, not all documents may undergo review by an auditor. Rather, some documents may be automatically processed and/or analyzed by the system. In some embodiments, the system can be configured to accept or reject documents automatically under certain conditions. [0017] applying the compliance rule, wherein the applying the compliance rule including checking for at least one of: correctness of the document or completeness of the document; [0064] As a non-limiting example, a TC 154 may upload a document and the Document Automation AI 110 may automatically read the document, determine its contents, classify the document, extract the relevant data from the document, determine whether that relevant data is proper based on context, and/or split the document into separate files to be attached to separate checklist items based on page ranges chosen from within the document, and so forth. [0065] Together with the Document Automation AI 110, these two AI components may serve to perform automated document validation and acceptance using various techniques such as OCR, machine learning, rules engines, and so forth.)
- determining a completion status for the at least one real estate transaction using the at least one AI model based on the analyzing of each of the document data and the task data; and (Malanga [0017] determining, based at least in part on applying the compliance rule, that the document complies with the compliance rule; and [0089] In response, the system can provide the checklist and outstanding audit items. At operation 372, the system can receive audit feedback, which can indicate that one or more items in a checklist require revision, are missing, etc. In some embodiments, the audit feedback may indicate that the checklist is complete. [0092] At operation 392, the system can automatically review the coversheet information to determine the completeness, correctness, or both of the coversheet information. At operation 392, the system can receive completed documents. For example, the system can receive completed electronic documents... In some embodiments, received documents can include documents with electronic signatures. In some embodiments, received documents can include documents with wet ink signatures. At operation 396, the system can automatically review the received completed documents, for example, to check for consistency, completeness, compliance with signature requirements, etc., for example, as described herein. )
- generating the notification data based on the determining of the completion status, wherein the notification data represents at least one notification informing the at least one second entity of completion status. (Malanga [0017] accepting the document, wherein accepting the document includes updated the checklist item to indicate that the checklist item is complete. [0092] At operation 398, the system can notify respective parties (e.g., agents, lenders, etc.) that one or more documents were rejected. The system may reject a document for a variety of reasons, such as inability to parse the document (e.g., due to poor scan quality), missing information, incorrect information, a document being an incorrect document (e.g., the wrong form was submitted), etc. The respective parties can receive notification of a rejected document and take action to correct the issue.)

Regarding Claim 12:
Malanga teaches The system of claim 11,
- wherein the processing device is further configured for: determining at least one regulatory requirement associated with the at least one real estate transaction based on the analyzing of each of the document data and the task data; (Malanga [0071] In some embodiments, the compliance review system 100 may include a Checklist Database 134 that stores various checklists, each of which can be associated with a particular jurisdiction and the rules of that jurisdiction. For instance, a checklist may contain checklist items that describe the type(s) of document(s) that need to be validated in order to satisfy requirements for any given transaction for the associated jurisdiction. In some embodiments, the checklist listing the compliance requirements of one or more applicable jurisdictions can be specified or otherwise prepared by managing brokers associated with the compliance review system. [0071] In some embodiments, the checklist can be automatically populated by the system 100 based on the Rules Database 132 containing various compliance requirements organized by jurisdiction, and the applicable jurisdictions of the property as determined by the TCs 154, the Auditors 152, and/or the system 100. In some embodiments, the checklist lists the types of documents that can satisfy each compliance requirement or otherwise required by the system 100 for validation.)

- obtaining a regulatory data based on the determining of the at least one regulatory requirement, wherein the regulatory data represents at least one regulatory detail associated with the at least one real estate transaction; and (Malanga [0072] In some embodiments, the compliance review system 100 may include a Dynamic Checklist module 122 for manipulating or modifying these checklists. For instance, the Dynamic Checklist module 122 may automatically or selectively provide checklist template management as an admin function to various users (e.g., non-engineers) of the compliance review system 100 to allow them to make changes to the checklists and their items (e.g., listed types of documents acceptable for a particular compliance requirement) to better suit a particular transaction or set of transactions. TCs 154 may also be able to use the Dynamic Checklist module 122 to filter checklists based on the locality of the transaction property and property type. These dynamic checklists may allow for streamlined document creation and validation and also a unification of experiences for the TCs 154 and partner agents.)
- analyzing the regulatory data using the at least one AI model, wherein the determining of the completion status is further based on the analyzing of the regulatory data. (Malanga [0067] In some embodiments, large language models (LLM) calibrated to perform particular tasks may be used. An LLM fine-tuned on real estate transactions may be integrated, along with the Document Automation AI 110 and/or the Risk Analysis AI 112 into a conversational AI such as Chatbot AI 114, which can be used to carry out various tasks associated with the compliance review workflow. For instance, an auditor 152 may be able to converse with the Chatbot AI 114 and request that it check to see if a set of documents are properly signed. The system 100 may be able to retrieve the set of documents from the Transaction Database 134 and apply the Document Automation AI 110 and/or the Risk Analysis AI 112 to verify that the documents are properly signed, and then the Chatbot AI 114 may be able to accurately convey that information back to the auditor 152 in the conversation. [0070] In some embodiments, the compliance review system 100 may include a Rules Database 132 that contains sets of rules for various jurisdictions that transactions may take place in.)

Regarding Claim 13:
Malanga teaches: The system of claim 12,
- wherein the processing device is further configured for generating at least one regulatory query based on the determining of the at least one regulatory requirement, (Malanga [0070] Thus, the transactions for a particular jurisdiction may be further subject to different checklists and checklist items. In some embodiments, the compliance review system 100 can receive property information and can automatically determine, for example, a specific ruleset to use based on the property location, property type (e.g., condominium, apartment, co-op, single family home, single family home in a planned development, etc.), and/or any other relevant information.)
- wherein the communication device is further configured for: transmitting the at least one regulatory query to at least one regulatory database device associated with at least one regulatory database of at least one regulatory body; and (Malanga [0071] In some embodiments, the compliance review system 100 may include a Checklist Database 134 that stores various checklists, each of which can be associated with a particular jurisdiction and the rules of that jurisdiction. For instance, a checklist may contain checklist items that describe the type(s) of document(s) that need to be validated in order to satisfy requirements for any given transaction for the associated jurisdiction. In some embodiments, the checklist listing the compliance requirements of one or more applicable jurisdictions can be specified or otherwise prepared by managing brokers associated with the compliance review system. [0129] For example, requirements for different documents can be stored in a database, and the system can query the database to determine the requirements based on the document type.)
- receiving the regulatory data from the at least one regulatory database device, wherein the obtaining of the regulatory data is further based on the receiving of the regulatory data. (Malanga [0071] In some embodiments, the checklist can be automatically populated by the system 100 based on the Rules Database 132 containing various compliance requirements organized by jurisdiction, and the applicable jurisdictions of the property as determined by the TCs 154, the Auditors 152, and/or the system 100. In some embodiments, the checklist lists the types of documents that can satisfy each compliance requirement or otherwise required by the system 100 for validation. [0128] As described herein, different jurisdictions may have different requirements for documents. In some cases, a jurisdiction may require a handwritten (“wet ink”) signature on certain documents, while other jurisdictions may permit typed signatures. In some embodiments, the approaches herein can be used to determine if signatures meet one or more signature requirements.)

Regarding Claim 14:
Malanga teaches: The system of claim 11,
- wherein the at least one AI model is an optical character recognition-enabled large language (OCR-LLM) model. (Malanga [0063] These AI components may utilize one or more AI or data processing techniques 116, such as machine learning (ML), large language models (LLMs), optical character recognition (OCR), natural language processing (NLP), and so forth. These AI or data processing techniques may be integrated into one or more particular applications associated with the system. For example, NLP and/or an LLM can be used to summarize a freeform document such as an inspection report. [0067] In some embodiments, large language models (LLM) calibrated to perform particular tasks may be used. An LLM fine-tuned on real estate transactions may be integrated, along with the Document Automation AI 110 and/or the Risk Analysis AI 112 into a conversational AI such as Chatbot AI 114, which can be used to carry out various tasks associated with the compliance review workflow. [0105] In some embodiments, once the TC has uploaded at least one document, the compliance review system may scan the document to determine whether the document can be approved by the system or the document needs to be reviewed by a human Auditor. In some embodiments, the system may utilize optical character recognition (OCR), machine learning (ML), artificial intelligence (AI), large language models (LLMs), and/or natural language processing (NLP) techniques to scan, determine the contents of, and/or identify certain features (e.g., signatures) in the document. )

Regarding Claim 16:
Malanga teaches: The system of claim 13,
- wherein the at least one AI model comprises a second artificial intelligence (AI) model, wherein the processing device is further configured for: (Malanga [0063] For example, in some embodiments, the compliance review system 100 may include various AI components such as a Document Automation AI 110, a Risk Analysis AI 112, and/or a Chatbot AI 114.)
- determining at least one jurisdiction associated with the at least one real estate transaction using the second AI model based on the analyzing of each of the document data and the task data; and (Malanga [0049] In some embodiments, the system provides a predetermined checklist listing the compliance requirements of one or more applicable jurisdictions. [0070] In some embodiments, the compliance review system 100 may include a Rules Engine 120 that may be used to generate and determine the checklists that are stored in the Checklist Database 134. The Rules Engine 120 may evaluate certain data points about a property or transaction and, if present, automatically change certain checklist items from “optional” to “required.” Thus, the transactions for a particular jurisdiction may be further subject to different checklists and checklist items. In some embodiments, the compliance review system 100 can receive property information and can automatically determine, for example, a specific ruleset to use based on the property location, property type (e.g., condominium, apartment, co-op, single family home, single family home in a planned development, etc.), and/or any other relevant information.)
- identifying the at least one regulatory body associated with the at least one jurisdiction based on the determining of the at least one jurisdiction, (Malanga [0079] In some embodiments, the system requests preliminary information (“cover sheet information”) about the property to be listed from the TC, such as the year the property was built, if there will be tenants, the type of deal, the commission to be offered (e.g., as a percentage), and any HOA options. In some embodiments, the system gives the TC the option to select one or more applicable jurisdictions. In some embodiments, the system automatically selects one or more applicable jurisdictions based on, for example, the location of the property (e.g., per the address input by the TC) and/or any special features of the property (e.g., includes solar panels). [0115] In some embodiments, the system may allow the Auditor to notify the TC that the TC or the system selected the incorrect jurisdiction for the checklist and/or start a new checklist corresponding to the proper jurisdiction.)
- wherein the transmitting of the at least one regulatory query to the at least one regulatory database device associated with the at least one regulatory database of the at least one regulatory body is further based on the identifying of the at least one regulatory body. (Malanga [0071] In some embodiments, the compliance review system 100 may include a Checklist Database 134 that stores various checklists, each of which can be associated with a particular jurisdiction and the rules of that jurisdiction. For instance, a checklist may contain checklist items that describe the type(s) of document(s) that need to be validated in order to satisfy requirements for any given transaction for the associated jurisdiction. In some embodiments, the checklist listing the compliance requirements of one or more applicable jurisdictions can be specified or otherwise prepared by managing brokers associated with the compliance review system. In some embodiments, the checklist can be automatically populated by the system 100 based on the Rules Database 132 containing various compliance requirements organized by jurisdiction, and the applicable jurisdictions of the property as determined by the TCs 154, the Auditors 152, and/or the system 100. In some embodiments, the checklist lists the types of documents that can satisfy each compliance requirement or otherwise required by the system 100 for validation.)

Regarding Claim 17:
Malanga teaches: The system of claim 11,
- wherein the at least one AI model further comprises a third artificial intelligence (AI) model, wherein the processing device is further configured for: (Malanga [0149] Machine learning models can used for various operations as described herein. A model can refer to a construct that is trained using training data to generate new data items, classify data items, or analyze data items, for example, to make predictions or provide probabilities. For example, training data for supervised learning can include items with various parameters and an assigned classification. A new data item can have parameters that a model can use to assign a classification to the new data item.)
- determining at least one upcoming additional task associated with the at least one real estate transaction using the third AI model based on the analyzing of each of the document data and the task data; and (Malanga [0070] In some embodiments, the compliance review system 100 may include a Rules Engine 120 that may be used to generate and determine the checklists that are stored in the Checklist Database 134. The Rules Engine 120 may evaluate certain data points about a property or transaction and, if present, automatically change certain checklist items from “optional” to “required.” Thus, the transactions for a particular jurisdiction may be further subject to different checklists and checklist items. In some embodiments, the compliance review system 100 can receive property information and can automatically determine, for example, a specific ruleset to use based on the property location, property type (e.g., condominium, apartment, co-op, single family home, single family home in a planned development, etc.), and/or any other relevant information.) Determining further checklist items satisfies “upcoming additional task.”
- generating an upcoming task data using the third AI model based on the determining of the at least one upcoming additional task, (Malanga [0110] In some embodiments, the system provides a Productization of Risk Score to facilitate dynamic acceptance criteria based on locale, transaction attributes, TC attributes, etc. In some embodiments, the system includes a rules engine that evaluates certain data points about a property and, if present, automatically changes certain checklist items from “optional” to “required.” In some embodiments, the system includes a rules engine that can automate the marking of checklist items as required based on property attributes. In some embodiments, the system includes filters and restrictions to prevent incomplete data from being synced to downstream systems. In some embodiments, the platform includes a risk function that can include TC evaluations based on historical performance. For example, if a particular TC is marked as “low risk” or has a high reliability score, the system may automatically accept documents attached to certain checklist items by that particular TC, while the same documents may not be automatically accepted when submitted by a TC with a higher risk or lower reliability. In another example, in calculating a TC reliability score, the system may review a 180-day period (or a different period) of the TC's recent history and calculate what percentage of documents uploaded by the TC were approved the first time. In some embodiments, the system includes automated document validation and acceptance using OCR, machine learning, AI, and/or additions to the rules engines.)
- wherein the communication device is further configured for transmitting the upcoming task data to each of the at least one first entity device and the at least one second entity device. (Malanga [0010] In some embodiments, the compliance review system may transmit and/or display the documents received from the transaction coordinators to the auditors, organized by the compliance requirements on the checklist. [0090] 376, the system can provide a list of action items to the user. In some embodiments, the user may view the rejected checklist items or the action items, but not both. In some embodiments, action items can be provided first, and the checklist items can be shown to the user upon the user selecting an action item. At operation 377, the system can receive one or more new or revised documents for one or more checklist items. For example, the user may upload new or revised documents for checklist items that were rejected. In some embodiments, the user may review comments that indicate why a previously-submitted document was rejected, which can help inform the user of what needs to be done to correct the issue or issues that caused the document to be rejected. At operation 378, the system can update one or more checklist items to indicate a new status. For example, in response to the user uploading a new or modified document for a checklist item, the status of the checklist item can change from rejected to accepted or from rejected to under review, for example, depending upon whether the uploaded document was automatically accepted or will undergo further review before being accepted. )

Regarding Claim 19:
Malanga teaches: The system of claim 11,
- wherein the completion status comprises at least one of a complete status and an incomplete status, (Malanga [0140]Compliance reviews can include, for example, validating an uploaded document, validating that a correct document was uploaded, automated review of system-generated or system-provided documents, [0017] wherein the applying the compliance rule including checking for at least one of: correctness of the document or completeness of the document; determining, based at least in part on applying the compliance rule, that the document complies with the compliance rule; and accepting the document, wherein accepting the document includes updated the checklist item to indicate that the checklist item is complete. [0110] In some embodiments, the system includes filters and restrictions to prevent incomplete data from being synced to downstream systems.)
- wherein the processing device is further configured for generating a rectification data based on the determining of the completion status comprising the incomplete status, (Malanga [0090] For example, the user may upload new or revised documents for checklist items that were rejected. In some embodiments, the user may review comments that indicate why a previously-submitted document was rejected, which can help inform the user of what needs to be done to correct the issue or issues that caused the document to be rejected. [0122] At operation 1208, the system can verify document correctness. For example, the system can verify that dates are within an acceptable range (e.g., a closing date is not in the past, a build date for an existing property is not in the future, etc.), that dollar amounts are within a predefined range (e.g., greater than a minimum amount or less than a maximum amount), that values are consistent with values previously entered on other forms, and so forth. At operation 1210, if the system determines that the document is not correct, the system can reject the document at operation 1212. In some embodiments, the system can provide an explanation for why the document was rejected, such as a closing date being in the past, a price being inconsistent with the price on another form, and so forth. If, at operation 1210, the system determines that the document is correct, the system can accept the document at operation 1214.)
- wherein the rectification data represents at least one rectification detail relative to the at least one task. (Malanga [0092] At operation 396, the system can automatically review the received completed documents, for example, to check for consistency, completeness, compliance with signature requirements, etc., for example, as described herein. At operation 398, the system can notify respective parties (e.g., agents, lenders, etc.) that one or more documents were rejected. The system may reject a document for a variety of reasons, such as inability to parse the document (e.g., due to poor scan quality), missing information, incorrect information, a document being an incorrect document (e.g., the wrong form was submitted), etc. The respective parties can receive notification of a rejected document and take action to correct the issue.)

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 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 8, 10, 18 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Malanga et al. (US 20240411982 A1) hereinafter Malanga, in view of Damien Patton (US 20240320745 A1) hereinafter Patton.

Regarding Claim 8:
Malanga teaches The method of claim 1,
Furthermore, Malanga teaches:
- wherein the at least one AI model further comprises a fourth artificial intelligence (AI) model, wherein the method further comprises: (Malanga [0063] In some embodiments, depending on the stages of the workflow, the Event Driven Workflow module 108 may invoke one or more corresponding components of the system 100 as needed by the workflow. For example, in some embodiments, the compliance review system 100 may include various AI components such as a Document Automation AI 110, a Risk Analysis AI 112, and/or a Chatbot AI 114. These AI components may utilize one or more AI or data processing techniques 116, such as machine learning (ML), large language models (LLMs), optical character recognition (OCR), natural language processing (NLP), and so forth.)
- analyzing, using the processing device, the document data using the fourth AI model based on the at least one request; (Malanga [0105] In some embodiments, once the TC has uploaded at least one document, the compliance review system may scan the document to determine whether the document can be approved by the system or the document needs to be reviewed by a human Auditor. In some embodiments, the system may utilize optical character recognition (OCR), machine learning (ML), artificial intelligence (AI), large language models (LLMs), and/or natural language processing (NLP) techniques to scan, determine the contents of, and/or identify certain features (e.g., signatures) in the document. One or more of these techniques may be used together in order to automate the reading and processing of documents.)
- identifying, using the processing device, at least one characteristic of the at least one real estate property using the fourth AI model based on the analyzing of the document data; (Malanga [0064] In some embodiments, the Event Driven Workflow module 108 may invoke a particular AI component based on the stage of the workflow and corresponding need. For instance, as TCs 154 upload documents to the system 100, the Event Driven Workflow module 108 may direct the Document Automation AI 110 to process the documents based on need. As a non-limiting example, a TC 154 may upload a document and the Document Automation AI 110 may automatically read the document, determine its contents, classify the document, extract the relevant data from the document, determine whether that relevant data is proper based on context, and/or split the document into separate files to be attached to separate checklist items based on page ranges chosen from within the document, and so forth. [0092] At operation 384, the system can populate coversheet information, which can include basic information about the listing (e.g., property address, listing price, square footage, number of bedrooms, number of bathrooms, school district, etc.). In some embodiments, the system can populate the coversheet information based on information supplied by an agent of TC. In some embodiments, the system can advantageously automatically populate the coversheet information based on, for example, data retrieved from one or more data sources, such as MLS listings. In some embodiments, information can be automatically populated based on, for example, the property location (which can indicate, for example, school district), previous transactions, or any other source of information.)

However, Malanga fails to teach:
- receiving, using the communication device, a valuation request data from the at least one first entity device, wherein the valuation request data represents at least one request from the at least one first entity for valuating at least one real estate property associated with the at least one real estate transaction;
- determining, using the processing device, a valuation for the at least one real estate property based on the identifying of the at least one characteristic; and
- transmitting, using the communication device, the valuation to the at least one first entity device.

Alternatively, Patton discloses a data validation and assessment valuation of real estate properties via an automated broker opinion of value (BOV) performed using artificial intelligence. Patton teaches:
- receiving, using the communication device, a valuation request data from the at least one first entity device, wherein the valuation request data represents at least one request from the at least one first entity for valuating at least one real estate property associated with the at least one real estate transaction; (Patton [0041] The pricing oracle 136 may provide a user of the system 100 with an estimate of the current value of an asset. The pricing oracle 136 may facilitate calculations and computations based on the estimate as directed by the user. [0087] A BOV is typically requested by a property owner (e.g., the owner 112) prior to beginning a sale process, and a BOV is a standard requirement for a transaction according to the current industry standards and conventional operating procedures.)
- determining, using the processing device, a valuation for the at least one real estate property based on the identifying of the at least one characteristic; and (Patton [0087] FIG. 9 is a block diagram illustrating an example of a broker opinion of value module 900 (e.g., mechanism or application or module) to calculate the broker opinion of value (“BOV”) for, real estate, independent valuations, independent appraisals, and other appropriate valuations for real and non-real assets. The broker opinion of value module 900 may be a separate module in communication with the pricing oracle 136 or may be included in the pricing oracle 136 (see FIG. 1). The broker opinion of value module 900 is configured to perform data validation and assessment valuation. In particular, the broker opinion of value module 900 is configured to completely automate the calculation of a BOV 902 using models 904 including artificial intelligence (AI), machine learning, and/or other appropriate models. A BOV is an assessment of the value of commercial real estate assets, and therefore is a key component of commercial real estate transactions in the industry today. [0088] For example, a BOV could take into account a range of inputs, including but not limited to: property type, property condition, comparable property condition, market trends for the location, financials (over any timeframe provided), tenant data, and demographic information on the area (construction, employment, traffic, population, etc.), and other appropriate inputs.)See [0088-0098] for all examples of characteristics.
- transmitting, using the communication device, the valuation to the at least one first entity device. (Patton [0041] The seller 114 may transmit information indicating agreement with pricing data provided by the pricing oracle 136, or the seller 114 may transmit information that overrides the pricing data provided by the pricing oracle 136. For example, in the context of commercial real estate assets, the pricing oracle 136 may include a digital broker opinion of value (BOV). [0098] Finally, the broker opinion of value module 900 is configured to combine the components into a calculation model and generate the BOV 902 based on the calculation. The BOV 902 will be presented to the owner and associated with the asset on the Exchange.)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the present disclosure to modify Malanga by adding the teachings of Patton, particularly, the use of the scraped property characteristic data, to perform a “broken opinion of value” or a valuation, and transmit the valuation to a first entity. One of ordinary skill in the art would have been motivated by the benefit of enabling buyers to determine the best choice for their investment with the most up to date information. (Patton [0098] Buyers will be able to look at the inputs and will be able to compare a standardized measurement across different assets. This will enable buyers to determine the best choice for their investment. [0099] The broker opinion of value module 900 may include an internal set of rules that inform the system (e.g., the system 100) when certain aspects of the BOV 902 need to be updated over time. The broker opinion of value module 900 is configured to monitor and track this updating process, and flag when inputs have become stale versus the BOV standard. If that information is “out of date” (outside the standard update range) the BOV calculation will start to discount the value of the property based on a weighted metric of non-compliance.)

Regarding Claim 10:
Malanga teaches: The method of claim 1,
- wherein the at least one AI model further comprises a fifth artificial intelligence (AI) model, wherein the method further comprises: (Malanga [0063] In some embodiments, depending on the stages of the workflow, the Event Driven Workflow module 108 may invoke one or more corresponding components of the system 100 as needed by the workflow. For example, in some embodiments, the compliance review system 100 may include various AI components such as a Document Automation AI 110, a Risk Analysis AI 112, and/or a Chatbot AI 114. These AI components may utilize one or more AI or data processing techniques 116, such as machine learning (ML), large language models (LLMs), optical character recognition (OCR), natural language processing (NLP), and so forth. These AI or data processing techniques may be integrated into one or more particular applications associated with the system. For example, NLP and/or an LLM can be used to summarize a freeform document such as an inspection report. These AI components or models may be trained on, or fine-tuned based on, data specific to real estate transactions. In some embodiments, AI components can utilize retrieval augmented generation (RAG) techniques to improve the performance, accuracy, etc., of AI components. In some embodiments, these AI components may be used together or integrated.)
- analyzing, using the processing device, the document data using the fifth AI model based on the at least one second request; (Malanga [0065] In some embodiments, the Risk Analysis AI 112 may be configured to automatically categorize documents into different risk tiers or quantify/score the risk associated with those documents based on various factors such as contextual information, document type, data extracted from the documents, and so forth. Together with the Document Automation AI 110, these two AI components may serve to perform automated document validation and acceptance using various techniques such as OCR, machine learning, rules engines, and so forth.
[0066] In some embodiments, the Document Automation AI 110 and the Risk Analysis AI 112 may be singularly integrated or operated together (e.g., by the Event Driven Workflow module 108), such that a document's type is immediately determined and the document is sorted into a particular risk tier (e.g., by the Risk Analysis AI 112) after it is ingested and processed (e.g., by the Document Automation AI 110). In other embodiments, the Event Driven Workflow module 108 may direct how and when the Document Automation AI 110 and the Risk Analysis AI 112 are utilized to process and score documents.)

However, Malanga fails to teach:
- receiving, using the communication device, a property assessment request data from the at least one first entity device,
- wherein the property assessment request data represents at least one second request from the at least one first entity for assessing at least one real estate property associated with the at least one real estate transaction;
- generating, using the processing device, an assessment report for the at least one real estate property using the fifth AI model based on the analyzing of the document data; and
- transmitting, using the communication device, the assessment report to the at least one first entity device.

Alternatively, Patton teaches:
- receiving, using the communication device, a property assessment request data from the at least one first entity device, (Patton [0087] A BOV is typically requested by a property owner (e.g., the owner 112) prior to beginning a sale process, and a BOV is a standard requirement for a transaction according to the current industry standards and conventional operating procedures. [0085] The computer system 800 may send messages and receive data, including program code, through the network(s), network link and network interface(s) 818. In the Internet example, a server might transmit a requested code for an application program through the Internet, the ISP, the local network, and the network interface(s) 818.) The broadest reasonable interpretation of “property assessment request data” is any information regarding the assessment of a property. Since valuation and “broker opinion of value” fall within the scope of “assessment,” the limitation is satisfied.
- wherein the property assessment request data represents at least one second request from the at least one first entity for assessing at least one real estate property associated with the at least one real estate transaction; (Patton [0041] The pricing oracle 136 may include a third-party service that connects smart contracts in the transaction platform of the system 100 with third-party entities and third-party systems outside of the system 100. The pricing oracle 136 may provide a user of the system 100 with an estimate of the current value of an asset. The pricing oracle 136 may facilitate calculations and computations based on the estimate as directed by the user. The user may modify inputs to the pricing oracle 136 to utilize the pricing oracle 136 for determining the user's own market pricing estimates. For example, the buyer 116 may modify inputs to the pricing oracle 136 to utilize the pricing oracle 136 for estimating a future value of their investment in an asset and determining an amount of funds the buyer 116 may agree to exchange for the asset on a given day. The seller 114 may transmit information indicating agreement with pricing data provided by the pricing oracle 136, or the seller 114 may transmit information that overrides the pricing data provided by the pricing oracle 136. For example, in the context of commercial real estate assets, the pricing oracle 136 may include a digital broker opinion of value (BOV).) Based on Patton’s updating off the pricing oracle, the property assessment request data can be a second request (an updated request of a pricing). Therefore, Patton satisfies the limitation because the updated pricing data request falls within the scope of the limitation.
- generating, using the processing device, an assessment report for the at least one real estate property using the fifth AI model based on the analyzing of the document data; and (Patton [0088] Although a BOV is a prerequisite for all commercial real estate transactions today, there are many issues with the BOV calculation process. To begin, a BOV is not a standardized (defined) measurement. Although there are some standard inputs that are generally included across all BOV, these reports are generated by commercial real estate brokers such that inputs and methodologies can differ between firms. For example, a BOV could take into account a range of inputs, including but not limited to: property type, property condition, comparable property condition, market trends for the location, financials (over any timeframe provided), tenant data, and demographic information on the area (construction, employment, traffic, population, etc.), and other appropriate inputs. [0089] The broker opinion of value module 900 is configured to employ the models 904, such as AI models, to make decisions on what data should be input into BOV calculation. The broker opinion of value module 900 is configured to validate data 906 that is used to generate the BOV 902 by gathering multiple sources of data for each entry, and then comparing them against each other to determine the most relevant and accurate input. For example, a property condition rating is an element that goes into BOV calculation, and this is usually based on submitted photos or an in-person visit. The broker opinion of value module 900 is configured to evaluate images for the property, determine which are most recent, highlight changes between different images of the same property (to point out changes that might have been made over time, either positive or negative), and then apply a rating score based on the images that most accurately reflect the state of the property today.)
- transmitting, using the communication device, the assessment report to the at least one first entity device.(Patton [0101] FIG. 10 shows an example method 1000 for data validation and assessment valuation performed by the broker opinion of value module 900. The method 1000 includes collecting data associated with an asset (step 1002), validating and selecting the collected data based on relevance and/or accuracy of the data (step 1004), calculating a BOV of the asset based on the selected data (step 1006), and transmitting the BOV for listing the asset with the BOV (step 1008).)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the present disclosure to modify Malanga by adding the teachings of Patton, particularly, the use of the scraped property characteristic data, to perform a “broken opinion of value” or a property assessment, and transmit the assessment report to a first entity. One of ordinary skill in the art would have been motivated by the benefit of enabling buyers to determine the best choice for their investment with the most up to date information. (Patton [0098] Buyers will be able to look at the inputs and will be able to compare a standardized measurement across different assets. This will enable buyers to determine the best choice for their investment. [0099] The broker opinion of value module 900 may include an internal set of rules that inform the system (e.g., the system 100) when certain aspects of the BOV 902 need to be updated over time. The broker opinion of value module 900 is configured to monitor and track this updating process, and flag when inputs have become stale versus the BOV standard. If that information is “out of date” (outside the standard update range) the BOV calculation will start to discount the value of the property based on a weighted metric of non-compliance.)

Regarding Claim 18:
Malanga teaches The system of claim 11,
- wherein the at least one AI model further comprises a fourth artificial intelligence (AI) model, wherein the communication device is further configured for: (Malanga [0063] In some embodiments, depending on the stages of the workflow, the Event Driven Workflow module 108 may invoke one or more corresponding components of the system 100 as needed by the workflow. For example, in some embodiments, the compliance review system 100 may include various AI components such as a Document Automation AI 110, a Risk Analysis AI 112, and/or a Chatbot AI 114. These AI components may utilize one or more AI or data processing techniques 116, such as machine learning (ML), large language models (LLMs), optical character recognition (OCR), natural language processing (NLP), and so forth.)
- wherein the processing device is further configured for: analyzing the document data using the fourth AI model based on the at least one request; (Malanga [0105] In some embodiments, once the TC has uploaded at least one document, the compliance review system may scan the document to determine whether the document can be approved by the system or the document needs to be reviewed by a human Auditor. In some embodiments, the system may utilize optical character recognition (OCR), machine learning (ML), artificial intelligence (AI), large language models (LLMs), and/or natural language processing (NLP) techniques to scan, determine the contents of, and/or identify certain features (e.g., signatures) in the document. One or more of these techniques may be used together in order to automate the reading and processing of documents.)
- identifying at least one characteristic of the at least one real estate property using the fourth AI model based on the analyzing of the document data; and (Malanga [0064] In some embodiments, the Event Driven Workflow module 108 may invoke a particular AI component based on the stage of the workflow and corresponding need. For instance, as TCs 154 upload documents to the system 100, the Event Driven Workflow module 108 may direct the Document Automation AI 110 to process the documents based on need. As a non-limiting example, a TC 154 may upload a document and the Document Automation AI 110 may automatically read the document, determine its contents, classify the document, extract the relevant data from the document, determine whether that relevant data is proper based on context, and/or split the document into separate files to be attached to separate checklist items based on page ranges chosen from within the document, and so forth. [0092] At operation 384, the system can populate coversheet information, which can include basic information about the listing (e.g., property address, listing price, square footage, number of bedrooms, number of bathrooms, school district, etc.). In some embodiments, the system can populate the coversheet information based on information supplied by an agent of TC. In some embodiments, the system can advantageously automatically populate the coversheet information based on, for example, data retrieved from one or more data sources, such as MLS listings. In some embodiments, information can be automatically populated based on, for example, the property location (which can indicate, for example, school district), previous transactions, or any other source of information.)

However, Malanga fails to teach:
- receiving a valuation request data from the at least one first entity device, wherein the valuation request data represents at least one request from the at least one first entity for valuating at least one real estate property associated with the at least one real estate transaction; and
- transmitting a valuation to the at least one first entity device,
- determining the valuation for the at least one real estate property based on the identifying of the at least one characteristic.
Alternatively, Patton teaches:
- receiving a valuation request data from the at least one first entity device, wherein the valuation request data represents at least one request from the at least one first entity for valuating at least one real estate property associated with the at least one real estate transaction; and(Patton [0041] The pricing oracle 136 may provide a user of the system 100 with an estimate of the current value of an asset. The pricing oracle 136 may facilitate calculations and computations based on the estimate as directed by the user. [0087] A BOV is typically requested by a property owner (e.g., the owner 112) prior to beginning a sale process, and a BOV is a standard requirement for a transaction according to the current industry standards and conventional operating procedures.)
- transmitting a valuation to the at least one first entity device, (Patton [0041] The seller 114 may transmit information indicating agreement with pricing data provided by the pricing oracle 136, or the seller 114 may transmit information that overrides the pricing data provided by the pricing oracle 136. For example, in the context of commercial real estate assets, the pricing oracle 136 may include a digital broker opinion of value (BOV). [0098] Finally, the broker opinion of value module 900 is configured to combine the components into a calculation model and generate the BOV 902 based on the calculation. The BOV 902 will be presented to the owner and associated with the asset on the Exchange.)
- determining the valuation for the at least one real estate property based on the identifying of the at least one characteristic. (Patton [0087] FIG. 9 is a block diagram illustrating an example of a broker opinion of value module 900 (e.g., mechanism or application or module) to calculate the broker opinion of value (“BOV”) for, real estate, independent valuations, independent appraisals, and other appropriate valuations for real and non-real assets. The broker opinion of value module 900 may be a separate module in communication with the pricing oracle 136 or may be included in the pricing oracle 136 (see FIG. 1). The broker opinion of value module 900 is configured to perform data validation and assessment valuation. In particular, the broker opinion of value module 900 is configured to completely automate the calculation of a BOV 902 using models 904 including artificial intelligence (AI), machine learning, and/or other appropriate models. A BOV is an assessment of the value of commercial real estate assets, and therefore is a key component of commercial real estate transactions in the industry today. [0088] For example, a BOV could take into account a range of inputs, including but not limited to: property type, property condition, comparable property condition, market trends for the location, financials (over any timeframe provided), tenant data, and demographic information on the area (construction, employment, traffic, population, etc.), and other appropriate inputs.)See [0088-0098] for all examples of characteristics.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the present disclosure to modify Malanga by adding the teachings of Patton, particularly, the use of the scraped property characteristic data, to perform a “broken opinion of value” or a valuation, and transmit the valuation to a first entity. One of ordinary skill in the art would have been motivated by the benefit of enabling buyers to determine the best choice for their investment with the most up to date information. (Patton [0098] Buyers will be able to look at the inputs and will be able to compare a standardized measurement across different assets. This will enable buyers to determine the best choice for their investment. [0099] The broker opinion of value module 900 may include an internal set of rules that inform the system (e.g., the system 100) when certain aspects of the BOV 902 need to be updated over time. The broker opinion of value module 900 is configured to monitor and track this updating process, and flag when inputs have become stale versus the BOV standard. If that information is “out of date” (outside the standard update range) the BOV calculation will start to discount the value of the property based on a weighted metric of non-compliance.)

Regarding Claim 20:
Malanga teaches The system of claim 11,
- wherein the at least one AI model further comprises a fifth artificial intelligence (AI) model, wherein the communication device is further configured for: (Malanga [0063] In some embodiments, depending on the stages of the workflow, the Event Driven Workflow module 108 may invoke one or more corresponding components of the system 100 as needed by the workflow. For example, in some embodiments, the compliance review system 100 may include various AI components such as a Document Automation AI 110, a Risk Analysis AI 112, and/or a Chatbot AI 114. These AI components may utilize one or more AI or data processing techniques 116, such as machine learning (ML), large language models (LLMs), optical character recognition (OCR), natural language processing (NLP), and so forth. These AI or data processing techniques may be integrated into one or more particular applications associated with the system. For example, NLP and/or an LLM can be used to summarize a freeform document such as an inspection report. These AI components or models may be trained on, or fine-tuned based on, data specific to real estate transactions. In some embodiments, AI components can utilize retrieval augmented generation (RAG) techniques to improve the performance, accuracy, etc., of AI components. In some embodiments, these AI components may be used together or integrated.)
- wherein the processing device is further configured for: analyzing the document data using the fifth AI model based on the at least one second request; and (Malanga [0065] In some embodiments, the Risk Analysis AI 112 may be configured to automatically categorize documents into different risk tiers or quantify/score the risk associated with those documents based on various factors such as contextual information, document type, data extracted from the documents, and so forth. Together with the Document Automation AI 110, these two AI components may serve to perform automated document validation and acceptance using various techniques such as OCR, machine learning, rules engines, and so forth.
[0066] In some embodiments, the Document Automation AI 110 and the Risk Analysis AI 112 may be singularly integrated or operated together (e.g., by the Event Driven Workflow module 108), such that a document's type is immediately determined and the document is sorted into a particular risk tier (e.g., by the Risk Analysis AI 112) after it is ingested and processed (e.g., by the Document Automation AI 110). In other embodiments, the Event Driven Workflow module 108 may direct how and when the Document Automation AI 110 and the Risk Analysis AI 112 are utilized to process and score documents.)

However, Malanga fails to teach:
- receiving a property assessment request data from the at least one first entity device, wherein the property assessment request data represents at least one second request from the at least one first entity for assessing at least one real estate property associated with the at least one real estate transaction; and
- transmitting an assessment report to the at least one first entity device,
- generating the assessment report for the at least one real estate property using the fifth AI model based on the analyzing of the document data.

Alternatively, Patton teaches:
- receiving a property assessment request data from the at least one first entity device, (Patton [0087] A BOV is typically requested by a property owner (e.g., the owner 112) prior to beginning a sale process, and a BOV is a standard requirement for a transaction according to the current industry standards and conventional operating procedures. [0085] The computer system 800 may send messages and receive data, including program code, through the network(s), network link and network interface(s) 818. In the Internet example, a server might transmit a requested code for an application program through the Internet, the ISP, the local network, and the network interface(s) 818.) The broadest reasonable interpretation of “property assessment request data” is any information regarding the assessment of a property. Since valuation and “broker opinion of value” fall within the scope of “assessment,” the limitation is satisfied.
- wherein the property assessment request data represents at least one second request from the at least one first entity for assessing at least one real estate property associated with the at least one real estate transaction; and (Patton [0041] The pricing oracle 136 may include a third-party service that connects smart contracts in the transaction platform of the system 100 with third-party entities and third-party systems outside of the system 100. The pricing oracle 136 may provide a user of the system 100 with an estimate of the current value of an asset. The pricing oracle 136 may facilitate calculations and computations based on the estimate as directed by the user. The user may modify inputs to the pricing oracle 136 to utilize the pricing oracle 136 for determining the user's own market pricing estimates. For example, the buyer 116 may modify inputs to the pricing oracle 136 to utilize the pricing oracle 136 for estimating a future value of their investment in an asset and determining an amount of funds the buyer 116 may agree to exchange for the asset on a given day. The seller 114 may transmit information indicating agreement with pricing data provided by the pricing oracle 136, or the seller 114 may transmit information that overrides the pricing data provided by the pricing oracle 136. For example, in the context of commercial real estate assets, the pricing oracle 136 may include a digital broker opinion of value (BOV).) Based on Patton’s updating off the pricing oracle, the property assessment request data can be a second request (an updated request of a pricing). Therefore, Patton satisfies the limitation because the updated pricing data request falls within the scope of the limitation.
- transmitting an assessment report to the at least one first entity device, (Patton [0101] FIG. 10 shows an example method 1000 for data validation and assessment valuation performed by the broker opinion of value module 900. The method 1000 includes collecting data associated with an asset (step 1002), validating and selecting the collected data based on relevance and/or accuracy of the data (step 1004), calculating a BOV of the asset based on the selected data (step 1006), and transmitting the BOV for listing the asset with the BOV (step 1008).)
- generating the assessment report for the at least one real estate property using the fifth AI model based on the analyzing of the document data. (Patton [0088] Although a BOV is a prerequisite for all commercial real estate transactions today, there are many issues with the BOV calculation process. To begin, a BOV is not a standardized (defined) measurement. Although there are some standard inputs that are generally included across all BOV, these reports are generated by commercial real estate brokers such that inputs and methodologies can differ between firms. For example, a BOV could take into account a range of inputs, including but not limited to: property type, property condition, comparable property condition, market trends for the location, financials (over any timeframe provided), tenant data, and demographic information on the area (construction, employment, traffic, population, etc.), and other appropriate inputs. [0089] The broker opinion of value module 900 is configured to employ the models 904, such as AI models, to make decisions on what data should be input into BOV calculation. The broker opinion of value module 900 is configured to validate data 906 that is used to generate the BOV 902 by gathering multiple sources of data for each entry, and then comparing them against each other to determine the most relevant and accurate input. For example, a property condition rating is an element that goes into BOV calculation, and this is usually based on submitted photos or an in-person visit. The broker opinion of value module 900 is configured to evaluate images for the property, determine which are most recent, highlight changes between different images of the same property (to point out changes that might have been made over time, either positive or negative), and then apply a rating score based on the images that most accurately reflect the state of the property today.)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the present disclosure to modify Malanga by adding the teachings of Patton, particularly, the use of the scraped property characteristic data, to perform a “broken opinion of value” or a property assessment, and transmit the assessment report to a first entity. One of ordinary skill in the art would have been motivated by the benefit of enabling buyers to determine the best choice for their investment with the most up to date information. (Patton [0098] Buyers will be able to look at the inputs and will be able to compare a standardized measurement across different assets. This will enable buyers to determine the best choice for their investment. [0099] The broker opinion of value module 900 may include an internal set of rules that inform the system (e.g., the system 100) when certain aspects of the BOV 902 need to be updated over time. The broker opinion of value module 900 is configured to monitor and track this updating process, and flag when inputs have become stale versus the BOV standard. If that information is “out of date” (outside the standard update range) the BOV calculation will start to discount the value of the property based on a weighted metric of non-compliance.)

Claims 5 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Malanga et al. (US 20240411982 A1) hereinafter Malanga, in view of Akporefe Agbamu (US 20230316261 A1) hereinafter Agbamu

Regarding Claim 5:
Malanga teaches: The method of claim 1 further comprising
- verifying, using the processing device, the at least one real estate document (Malanga [0110] In some embodiments, the system includes automated document validation and acceptance using OCR, machine learning, AI, and/or additions to the rules engines. [0140] In some embodiments, the approaches described herein can reduce human involvement in compliance processes while improving the overall effectiveness of compliance reviews. Compliance reviews can include, for example, validating an uploaded document, validating that a correct document was uploaded, automated review of system-generated or system-provided documents, automated review of external documents, complete human review of system-generated or system-provided documents, and/or complete human review of external documents. )
- wherein the analyzing of each of the document data and the task data is further based on the verifying of the at least one real estate document.(Malanga [0065] In some embodiments, the Risk Analysis AI 112 may be configured to automatically categorize documents into different risk tiers or quantify/score the risk associated with those documents based on various factors such as contextual information, document type, data extracted from the documents, and so forth. Together with the Document Automation AI 110, these two AI components may serve to perform automated document validation and acceptance using various techniques such as OCR, machine learning, rules engines, and so forth. [0067] In some embodiments, large language models (LLM) calibrated to perform particular tasks may be used. An LLM fine-tuned on real estate transactions may be integrated, along with the Document Automation AI 110 and/or the Risk Analysis AI 112 into a conversational AI such as Chatbot AI 114, which can be used to carry out various tasks associated with the compliance review workflow. For instance, an auditor 152 may be able to converse with the Chatbot AI 114 and request that it check to see if a set of documents are properly signed. The system 100 may be able to retrieve the set of documents from the Transaction Database 134 and apply the Document Automation AI 110 and/or the Risk Analysis AI 112 to verify that the documents are properly signed, and then the Chatbot AI 114 may be able to accurately convey that information back to the auditor 152 in the conversation.)

However, Malanga fails to teach:
- that the “verifying, using the processing device, the at least one real estate document” is using a zero-knowledge proof,
- wherein the zero-knowledge proof enables a validation of at least one of an authenticity and an integrity of the at least one real estate document without revealing at least one content of the at least one real estate document,

Alternatively, Agbamu discloses a document, transaction system for analyzing documents, and managing document data. Agbamu teaches:
- that the “verifying, using the processing device, the at least one real estate document” is using a zero-knowledge proof, (Agbamu [0066] For entities comprising banks, brokerages, financial advisors, or insurance companies, documents exchanged 410 may be an account opening document or terms of service for the account or loan; for a residential or commercial real estate landlord, this document may be the lease agreement for the property being rented or purchased; [0094] A benefit of the system is a blockchain 110 where smart contracts 130 may be utilized for storing identity, document, and transaction information or a hash of said information on the blockchain 110. To ensure anonymity and privacy for transactors of the system, on-chain 110 cryptographic mechanisms comprising private smart contracts 130, ring signatures, stealth addresses, and mixing, may be utilized. To protect on-chain 110 and/or off-chain 108 identity, document, and transaction data, cryptographic tools comprising zero-knowledge proofs...)
- wherein the zero-knowledge proof enables a validation of at least one of an authenticity and an integrity of the at least one real estate document without revealing at least one content of the at least one real estate document, (Agbamu [0031] Certain exemplary embodiments of the system 300 that may utilize optical character recognition (OCR) 308, enhanced via intelligence of supervised and/or unsupervised methods 106, to aid in detecting and identifying regions of interest on documents 306. Enabling the extracting and synthesizing of uploaded documents for authentication, validation, verification, attestation, and classification purposes of the system 300... [0095] In certain exemplary embodiments of the system, personal information may be hashed in order to protect the anonymity of the underlying. As a result, a user may be asked to decrypt certain information linked to the portable ID 130a that may prove identification in a zero-knowledge manner—without exposing the underlying data associated with the ID. In these exemplary embodiments, a hash of the encrypted information may be recreated by the user providing attestation to the underlying variables by verifying the hash. The underlying information need not be viewable by any 3rd party to provide validity, as 3rd parties may take the hash and compare it to hashed information stored centrally, tied to the portable ID 130a, in decentralized storage 128 tied to a portable ID 130a, or in the decentralized data oracle 916, as an attestation to the validity of the underlying information without viewing it directly.)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the present disclosure to modify Malanga by adding the teachings of Agbamu, particularly, securing the document data using zero-knowledge proofs, in order to verify and authenticate the data without revealing the contents of the document. One of ordinary skill in the art would have been motivated by the benefit of being able to autonomously verify onboarded users in a defined and repeatable manner. (Agbamu [0142] In certain exemplary embodiments of the system, zero-knowledge proofs may be present, leveraging priori and posteriori verification of facts to allow trustless attestation of datasets. The trust source may be a decentralized autonomous organization and/or governing body, reaching consensus once the system identity management system 100 completes an onboarding process. Certain embodiments of the system may utilize the Proof of Process consensus algorithm, which allows the system to validate a user's identity—biometric, identity card, and geolocation, among other requirements, as the user is onboarded by the system, in a fully (semi) automated, defined and repeatable manner.)

Regarding Claim 15:
Malanga teaches The system of claim 11,
- wherein the processing device is further configured for verifying the at least one real estate document (Malanga [0110] In some embodiments, the system includes automated document validation and acceptance using OCR, machine learning, AI, and/or additions to the rules engines. [0140] In some embodiments, the approaches described herein can reduce human involvement in compliance processes while improving the overall effectiveness of compliance reviews. Compliance reviews can include, for example, validating an uploaded document, validating that a correct document was uploaded, automated review of system-generated or system-provided documents, automated review of external documents, complete human review of system-generated or system-provided documents, and/or complete human review of external documents. )
- wherein the analyzing of each of the document data and the task data is further based on the verifying of the at least one real estate document. (Malanga [0065] In some embodiments, the Risk Analysis AI 112 may be configured to automatically categorize documents into different risk tiers or quantify/score the risk associated with those documents based on various factors such as contextual information, document type, data extracted from the documents, and so forth. Together with the Document Automation AI 110, these two AI components may serve to perform automated document validation and acceptance using various techniques such as OCR, machine learning, rules engines, and so forth. [0067] In some embodiments, large language models (LLM) calibrated to perform particular tasks may be used. An LLM fine-tuned on real estate transactions may be integrated, along with the Document Automation AI 110 and/or the Risk Analysis AI 112 into a conversational AI such as Chatbot AI 114, which can be used to carry out various tasks associated with the compliance review workflow. For instance, an auditor 152 may be able to converse with the Chatbot AI 114 and request that it check to see if a set of documents are properly signed. The system 100 may be able to retrieve the set of documents from the Transaction Database 134 and apply the Document Automation AI 110 and/or the Risk Analysis AI 112 to verify that the documents are properly signed, and then the Chatbot AI 114 may be able to accurately convey that information back to the auditor 152 in the conversation.)

However, Malanga fails to teach:
-that the the processing device is further configured for verifying the at least one real estate document using a zero-knowledge proof,
- wherein the zero-knowledge proof enables a validation of at least one of an authenticity and an integrity of the at least one real estate document without revealing at least one content of the at least one real estate document,

Alternatively, Agbamu teaches:
- wherein the processing device is further configured for verifying the at least one real estate document using a zero-knowledge proof, (Agbamu [0066] For entities comprising banks, brokerages, financial advisors, or insurance companies, documents exchanged 410 may be an account opening document or terms of service for the account or loan; for a residential or commercial real estate landlord, this document may be the lease agreement for the property being rented or purchased; [0094] A benefit of the system is a blockchain 110 where smart contracts 130 may be utilized for storing identity, document, and transaction information or a hash of said information on the blockchain 110. To ensure anonymity and privacy for transactors of the system, on-chain 110 cryptographic mechanisms comprising private smart contracts 130, ring signatures, stealth addresses, and mixing, may be utilized. To protect on-chain 110 and/or off-chain 108 identity, document, and transaction data, cryptographic tools comprising zero-knowledge proofs...)
- wherein the zero-knowledge proof enables a validation of at least one of an authenticity and an integrity of the at least one real estate document without revealing at least one content of the at least one real estate document, (Agbamu [0031] Certain exemplary embodiments of the system 300 that may utilize optical character recognition (OCR) 308, enhanced via intelligence of supervised and/or unsupervised methods 106, to aid in detecting and identifying regions of interest on documents 306. Enabling the extracting and synthesizing of uploaded documents for authentication, validation, verification, attestation, and classification purposes of the system 300... [0095] In certain exemplary embodiments of the system, personal information may be hashed in order to protect the anonymity of the underlying. As a result, a user may be asked to decrypt certain information linked to the portable ID 130a that may prove identification in a zero-knowledge manner—without exposing the underlying data associated with the ID. In these exemplary embodiments, a hash of the encrypted information may be recreated by the user providing attestation to the underlying variables by verifying the hash. The underlying information need not be viewable by any 3rd party to provide validity, as 3rd parties may take the hash and compare it to hashed information stored centrally, tied to the portable ID 130a, in decentralized storage 128 tied to a portable ID 130a, or in the decentralized data oracle 916, as an attestation to the validity of the underlying information without viewing it directly.)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the present disclosure to modify Malanga by adding the teachings of Agbamu, particularly, securing the document data using zero-knowledge proofs, in order to verify and authenticate the data without revealing the contents of the document. One of ordinary skill in the art would have been motivated by the benefit of being able to autonomously verify onboarded users in a defined and repeatable manner. (Agbamu [0142] In certain exemplary embodiments of the system, zero-knowledge proofs may be present, leveraging priori and posteriori verification of facts to allow trustless attestation of datasets. The trust source may be a decentralized autonomous organization and/or governing body, reaching consensus once the system identity management system 100 completes an onboarding process. Certain embodiments of the system may utilize the Proof of Process consensus algorithm, which allows the system to validate a user's identity—biometric, identity card, and geolocation, among other requirements, as the user is onboarded by the system, in a fully (semi) automated, defined and repeatable manner.)

Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
- Sheila Nanamala Reddy (US 20240386512 A1) discloses a computer-implemented platform for real estate personnel with document management tools and compliance management. (Reddy [0056] Transaction Management: this module may form, or be part of, a transaction management module. Individual transactions within the platform may be designed to be collaborative—e.g., where agents can invite clients and third parties (e.g., lenders, title companies, lawyers, insurers, appraisers, etc.) into the platform to ensure one source of truth and increase visibility for all parties. This module may allow for timeline management, task management, document management, integrated forms (e.g., having e-signature capabilities), and/or built-in compliance logs. This module may also or instead include offers and showings management for listings, and similar. This module may also or instead include powerful templating and automations to minimize redundant work for agents and their clients, and to mitigate risks of non-compliance.)

-Bryan Brewer et al. (US 20260010964 A1) discloses a negotiation platform for real estate agreements, with built in compliance features. ([0057] Furthermore, the system's built-in compliance features, including automated adverse action notifications, ensure adherence to regulatory requirements without imposing additional administrative burden on property owners.)

-Bex et al. (US 20240403563 A1) discloses a platform for ingesting a text document and parsing the document for semantic similarity to other documents. The inter-institutional text analysis tool is applicable for regulatory compliance for real estate applications. (Bex [0077] The inter-institutional text analysis and comparison tool is able to be used for real estate applications by providing robust mechanisms for analyzing and comparing a wide array of property documentation and legal documents across various real estate functions. With capabilities to perform detailed similarity evaluations at various levels of text granularity, from entire documents to specific sections, the present invention provides for precise evaluations, crucial for improving property documentation management, legal compliance, and market analysis.)

Any inquiry concerning this communication or earlier communications from the examiner should be directed to NICO LAUREN PADUA whose telephone number is [phone]. The examiner can normally be reached Mon to Fri: 8:30 to 5:00pm.
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, Jessica Lemieux can be reached at [phone]. 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.

/NICO L PADUA/Junior Patent Examiner, Art Unit 3626
/SANGEETA BAHL/Primary Examiner, Art Unit 3626

Prosecution Timeline

• Dec 18, 2025: Application Filed
• Aug 20, 2026: Non-Final Rejection mailed — §101, §102, §103 (current)