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 .
DETAILED ACTION
Response to Arguments
Applicant's arguments with respect to claim 1 have been considered but are moot in view of the new ground(s) of rejection. Applicant’s arguments are directed to the updated citations of existing art.
It is believed that applicant intended to amend claims 9 and 16 based on the typographical errors, and thus the same amendments are therefore applied to claim 9 and 16, considering the Remarks as follows:
Regarding Remarks from 07/20/2026:
“Claims 1-20 were previously pending. In this response, claims 1, 9, and 17 are amended. No new matter is added.
Claim Objections
Claims 1-20 were objected to for certain informalities. Claims are amended to overcome the informalities.”
The above changes did not take place and do not correspond to the current claim set. No informalities have been resolved, and only claim 1 was amended, therefore the amendments to claim 1 have been addressed below and applied to independent claims 9 and 16.
Note: The claims are not directed towards patent ineligible subject matter under 35 U.S.C. 101
Step 1: IS THE CLAIM DIRECTED TO A PROCESS, MACHINE, MANUFACTURE OR COMPOSITION OF MATTER?
Yes
Step 2A.1: IS THE CLAIM DIRECTED TO A LAW OF NATURE, A NATURAL PHENOMENON (PRODUCT OF NATURE) OR AN ABSTRACT IDEA?
No
Step 2A.2: DOES THE CLAIM RECITE ADDITIONAL ELEMENTS THAT INTEGRATE THE JUDICIAL EXCEPTION INTO A PRACTICAL APPLICATION?
No.
Supported by the following:
In Finjan Inc. v. Blue Coat Systems, Inc., 879 F.3d 1299, 125 USPQ2d 1282 (Fed. Cir. 2018), the claimed invention was a method of virus scanning that scans an application program, generates a security profile identifying any potentially suspicious code in the program, and links the security profile to the application program. 879 F.3d at 1303-04, 125 USPQ2d at 1285-86. The Federal Circuit noted that the recited virus screening was an abstract idea, and that merely performing virus screening on a computer does not render the claim eligible. 879 F.3d at 1304, 125 USPQ2d at 1286. The court then continued with its analysis under part one of the Alice/Mayo test by reviewing the patent’s specification, which described the claimed security profile as identifying both hostile and potentially hostile operations. The court noted that the security profile thus enables the invention to protect the user against both previously unknown viruses and “obfuscated code,” as compared to traditional virus scanning, which only recognized the presence of previously-identified viruses. The security profile also enables more flexible virus filtering and greater user customization. 879 F.3d at 1304, 125 USPQ2d at 1286. The court identified these benefits as improving computer functionality, and verified that the claims recite additional elements (e.g., specific steps of using the security profile in a particular way) that reflect this improvement. Accordingly, the court held the claims eligible as not being directed to the recited abstract idea. 879 F.3d at 1304-05, 125 USPQ2d at 1286-87. This analysis is equivalent to the Office’s analysis of determining that the additional elements integrate the judicial exception into a practical application at Step 2A Prong Two, and thus that the claims were not directed to the judicial exception (Step 2A: NO).
Examples of claims that improve technology and are not directed to a judicial exception include: Enfish, LLC v. Microsoft Corp., 822 F.3d 1327, 1339, 118 USPQ2d 1684, 1691-92 (Fed. Cir. 2016) (claims to a self-referential table for a computer database were directed to an improvement in computer capabilities and not directed to an abstract idea); McRO, Inc. v. Bandai Namco Games Am. Inc., 837 F.3d 1299, 1315, 120 USPQ2d 1091, 1102-03 (Fed. Cir. 2016) (claims to automatic lip synchronization and facial expression animation were directed to an improvement in computer-related technology and not directed to an abstract idea); Visual Memory LLC v. NVIDIA Corp., 867 F.3d 1253,1259-60, 123 USPQ2d 1712, 1717 (Fed. Cir. 2017) (claims to an enhanced computer memory system were directed to an improvement in computer capabilities and not an abstract idea); Finjan Inc. v. Blue Coat Systems, Inc., 879 F.3d 1299, 125 USPQ2d 1282 (Fed. Cir. 2018) (claims to virus scanning were found to be an improvement in computer technology and not directed to an abstract idea); SRI Int’l, Inc. v. Cisco Systems, Inc., 930 F.3d 1295, 1303 (Fed. Cir. 2019) (claims to detecting suspicious activity by using network monitors and analyzing network packets were found to be an improvement in computer network technology and not directed to an abstract idea). Additional examples are provided in MPEP § 2106.05(a).
Regarding the December 5th 2025 Memo in light of September 26, 2025 Appeals Review Panel Decision in Ex parte Desjardins, Appeal 2024-000567 for Application 16/319,040, in deciding if a recited abstract idea does or does not direct the entire claim to an abstract idea, when a claim is considered as a whole:
Paragraph 21 of the Specification, which the Appellant cites, identifies improvements in training the machine learning model itself. Of course, such an assertion in the Specification alone is insufficient to support a patent eligibility determination, absent a subsequent determination that the claim itself reflects the disclosed improvement. See MPEP § 2106.05(a) (citing Intellectual Ventures I LLC v. Symantec Corp., 838 F.3d 1307, 1316 (Fed. Cir. 2016)). Here, however, we are persuaded that the claims reflect such an improvement. For example, one improvement identified in the 8 Appeal2024-000567 Application 16/319,040 Specification is to "effectively learn new tasks in succession whilst protecting knowledge about previous tasks." Spec. ,r 21. The Specification also recites that the claimed improvement allows artificial intelligence (AI) systems to "us[e] less of their storage capacity" and enables "reduced system complexity." Id. When evaluating the claim as a whole, we discern at least the following limitation of independent claim 1 that reflects the improvement: "adjust the first values of the plurality of parameters to optimize performance of the machine learning model on the second machine learning task while protecting performance of the machine learning model on the first machine learning task." We are persuaded that constitutes an improvement to how the machine learning model itself operates, and not, for example, the identified mathematical calculation. Under a charitable view, the overbroad reasoning of the original panel below is perhaps understandable given the confusing nature of existing § 101 jurisprudence, but troubling, because this case highlights what is at stake. Categorically excluding AI innovations from patent protection in the United States jeopardizes America's leadership in this critical emerging technology. Yet, under the panel's reasoning, many AI innovations are potentially unpatentable-even if they are adequately described and nonobvious-because the panel essentially equated any machine learning with an unpatentable "algorithm" and the remaining additional elements as "generic computer components," without adequate explanation. Dec. 24. Examiners and panels should not evaluate claims at such a high level of generality.
Specifically, Ex Parte Desjardins explained the following:
Enfish ranks among the Federal Circuit's leading cases on the eligibility of technological improvements. In particular, Enfish recognized that “[m]uch of the advancement made in computer technology consists of improvements to software that, by their very nature, may not be defined by particular physical features but rather by logical structures and processes.” 822 F.3d at 1339. Moreover, because “[s]oftware can make non-abstract improvements to computer technology, just as hardware improvements can,” the Federal Circuit held that the eligibility determinations should turn on whether “the claims are directed to an improvement to computer functionality versus being directed to an abstract idea.” Id. at 1336. (Desjardins, page 8).
Further in Ex Parte Desjardins, Appeal No. 2024-000567 (PTAB September 26, 2025, Appeals Review Panel Decision) (precedential), the claimed invention was a method of training a machine learning model on a series of tasks. The Appeals Review Panel (ARP) overall credited benefits including reduced storage, reduced system complexity and streamlining, and preservation of performance attributes associated with earlier tasks during subsequent computational tasks as technological improvements that were disclosed in the patent application specification. Specifically, the ARP upheld the Step 2A Prong One finding that the claims recited an abstract idea (i.e., mathematical concept). In Step 2A Prong Two, the ARP then determined that the specification identified improvements as to how the machine learning model itself operates, including training a machine learning model to learn new tasks while protecting knowledge about previous tasks to overcome the problem of “catastrophic forgetting” encountered in continual learning systems. Importantly, the ARP evaluated the claims as a whole in discerning at least the limitation “adjust the first values of the plurality of parameters to optimize performance of the machine learning model on the second machine learning task while protecting performance of the machine learning model on the first machine learning task” reflected the improvement disclosed in the specification. Accordingly, the claims as a whole integrated what would otherwise be a judicial exception instead into a practical application at Step 2A Prong Two, and therefore the claims were
The claim itself does not need to explicitly recite the improvement described in the specification (e.g., “thereby increasing the bandwidth of the channel”). See, e.g., Ex Parte Desjardins, Appeal No. 2024-000567 (PTAB September 26, 2025, Appeals Review Panel Decision) (precedential), in which the specification identified the improvement to machine learning technology by explaining how the machine learning model is trained to learn new tasks while protecting knowledge about previous tasks to overcome the problem of “catastrophic forgetting,” and that the claims reflected the improvement identified in the specification. Indeed, enumerated improvements identified in the Desjardins specification included disclosures of the effective learning of new tasks in succession in connection with specifically protecting knowledge concerning previously accomplished tasks; allowing the system to reduce use of storage capacity; and the enablement of reduced complexity in the system. Such improvements were tantamount to how the machine learning model itself would function in operation and therefore not subsumed in the identified mathematical calculation.
Step 2B: DOES THE CLAIM RECITE ADDITIONAL ELEMENTS THAT AMOUNT TO SIGNIFICANTLY MORE THAN THE JUDICIAL EXCEPTION?
If Yes at step 2A.1 and step 2A.2 fails, the interpretation in the context of 35 USC 101 amounts to a process by which a device is used to communicate with a user in a significant way using stored nodes and updating thereof based on communication particularly by using vectors, rather than simply using a device to accomplish what two users in a conversation can do. For instance, a user would not mentally update their mind per se based on a conversation and use vectors or nodes as part of the learning of a human per se. A human would not seek such claim limitations as a general or routine step. Such claim language provides significance beyond mere data manipulation or mental decision making and is also analogous to interim amendment examples. Additionally, if one or ordinary skill in the art fails to properly consider any specified hardware or arranged components in the claims, considers such claim limitations non-generic, or simply disregards Enfish, the claims still demonstrate that there exists improvements to the functioning of a computer (or technology), e.g., a modification of conventional Internet hyperlink protocol to dynamically produce a dual-source hybrid webpage, as discussed in DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258-59, 113 USPQ2d 1097, 1106-07 (Fed. Cir. 2014) (see MPEP § 2106.05(a));. Therefore, in light of the above as a whole, it is not warranted to give a rejection under 35 USC 101.
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory obviousness-type double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); and In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on a nonstatutory double patenting ground provided the conflicting application or patent either is shown to be commonly owned with this application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement.
Effective January 1, 1994, a registered attorney or agent of record may sign a terminal disclaimer. A terminal disclaimer signed by the assignee must fully comply with 37 CFR 3.73(b).
Claims 1, 9, and 16 with dependent claims thereof, are rejected on the ground of nonstatutory obviousness-type double patenting as being unpatentable over claims 1, 9, and 17 and any dependent claims thereof of U.S. Patent No. 12277155. Although the conflicting claims are not identical, they are not patentably distinct from each other because said claims of the instant application includes all of the features of said claims of U.S. Patent No. 12277155. It would have been obvious to one of ordinary skill in the art to omit the step of determining whether to create an epoch node, as such as a step is equivalent to a broader representation e.g. updating a node, and aligned with select dependent claims, In re Karlson 136 USPQ 184 (1963): "Omission of an element and its function is an obvious expedient if the remaining elements perform the same functions as before"
Present invention U.S. Patent No. 12277155
1. (Currently Amended) A computer-implemented method, comprising: storing in a vector database, vector representations of plurality of natural language questions; receiving request for extracting information from a user; creating a data structure storing a plurality of nodes, each node associated with information obtained from the user; interacting with the user via a client device to obtain information from the user by repeatedly: selecting a node of the data structure for further exploration from the data structure, determining a context based on the selected node; selecting a natural language question from [[a]] the plurality of natural language questions stored in a vector database, the natural language question selected based on a vector distance between a vector representation of the context of the selected node and vector representations of natural language questions stored in the vector database; sending the natural language question to the client device, receiving a natural language answer to the natural language question from the client device, and updating the data structure by adding one or more nodes of the data structure storing information obtained from based on the natural language answer, and storing a representation of the data structure.
2. The computer-implemented method of claim 1, wherein selecting the natural language question comprises: generating a natural language description of the context; and selecting from the vector database, the natural language question based on a vector distance between a vector representation of the natural language description of the context and vector representations of natural language questions stored in the vector database.
3. The computer-implemented method of claim 2, wherein generating a natural language description of the context for a particular node comprises: generating a prompt for a machine learning-based language model, the prompt comprising information stored in the particular node; sending the prompt for execution to the machine learning-based language model, the prompt requesting the machine learning-based language model to generate a natural language description of the context for the particular node; and receiving a response based on the execution of the machine learning-based language model, wherein the response comprises the natural language description of the context.
4. The computer-implemented method of claim 1, wherein each node has a relevance score determined based on the information stored in the node, wherein selecting the node of the data structure for further exploration is based on relevance scores of nodes of the data structure.
5. The computer-implemented method of claim 4, wherein the node selected for further exploration is the node with a highest relevance score of the plurality of nodes of the data structure.
6. The computer-implemented method of claim 1, wherein the data structure comprises a hierarchy of nodes having a root node, wherein the context for a particular node is determined based on one or more nodes encountered in a path from the root node to the particular node.
7. The computer-implemented method of claim 1, further comprising: selecting a subset of nodes from the data structure; generating a prompt for a machine learning-based language model, the prompt comprising information stored in subset of nodes; sending the prompt for execution to the machine learning-based language model, the prompt requesting the machine learning-based language model to generate a statement describing the user; and receiving a response based on the execution of the machine learning-based language model, wherein the response comprises the statement describing the user.
8. The computer-implemented method of claim 1, further comprising: determining a score evaluating the user based on information obtained from the user stored in the data structure.
9. A non-transitory computer readable storage medium, storing instructions that when executed by one or more computer processors cause the one or more computer processors to perform steps comprising: receiving request for extracting information from a user; creating a data structure storing a plurality of nodes, each node associated with information obtained from the user; interacting with the user via a client device to obtain information from the user by repeatedly:selecting a node of the data structure for further exploration from the data structure,determining a context based on the selected node;selecting a natural language question from a plurality of natural language questions stored in a vector database, the natural language question selected based on the context of the selected node;sending the natural language question to the client device,receiving a natural language answer to the natural language question from the client device, andupdating the data structure by adding one or more nodes of the data structure based on the natural language answer, and storing a representation of the data structure.
10. The non-transitory computer readable storage medium of claim 9, wherein selecting the natural language question comprises: generating a natural language description of the context; andselecting from the vector database, the natural language question based on a vector distance between a vector representation of the natural language description of the context and vector representations of natural language questions stored in the vector database.
11. The non-transitory computer readable storage medium of claim 10, wherein generating a natural language description of the context for a particular node comprises: generating a prompt for a machine learning-based language model, the prompt comprising information stored in the particular node; sending the prompt for execution to the machine learning-based language model, the prompt requesting the machine learning-based language model to generate a natural language description of the context for the particular node; and receiving a response based on the execution of the machine learning-based language model, wherein the response comprises the natural language description of the context.
12. The non-transitory computer readable storage medium of claim 9, wherein each node has a relevance score determined based on the information stored in the node, wherein selecting the node of the data structure for further exploration is based on relevance scores of nodes of the data structure.
13. The non-transitory computer readable storage medium of claim 9, wherein the data structure comprises a hierarchy of nodes having a root node, wherein the context for a particular node is determined based on one or more nodes encountered in a path from the root node to the particular node.
14. The non-transitory computer readable storage medium of claim 9, wherein the instructions further cause the one or more computer processors to perform steps comprising: selecting a subset of nodes from the data structure; generating a prompt for a machine learning-based language model, the prompt comprising information stored in subset of nodes; sending the prompt for execution to the machine learning-based language model, the prompt requesting the machine learning-based language model to generate a statement describing the user; and receiving a response based on the execution of the machine learning-based language model, wherein the response comprises the statement describing the user.
15. The non-transitory computer readable storage medium of claim 9, wherein the instructions further cause the one or more computer processors to perform steps comprising: determining a score evaluating the user based on information obtained from the user stored in the data structure.
16. A computer system comprising: one or more computer processors; and a non-transitory computer readable storage medium, storing instructions that when executed by the one or more computer processors cause the one or more computer processors to perform steps comprising:receiving request for extracting information from a user;creating a data structure storing a plurality of nodes, each node associated with information obtained from the user;interacting with the user via a client device to obtain information from the user by repeatedly:selecting a node of the data structure for further exploration from the data structure,determining a context based on the selected node;selecting a natural language question from a plurality of natural language questions stored in a vector database, the natural language question selected based on the context of the selected node;sending the natural language question to the client device, receiving a natural language answer to the natural language question from the client device, andupdating the data structure by adding one or more nodes of the data structure based on the natural language answer, and storing a representation of the data structure.
17. The computer system of claim 16, wherein selecting the natural language question comprises: generating a natural language description of the context; and selecting from the vector database, the natural language question based on a vector distance between a vector representation of the natural language description of the context and vector representations of natural language questions stored in the vector database.
18. The computer system of claim 17, wherein generating a natural language description of the context for a particular node comprises: generating a prompt for a machine learning-based language model, the prompt comprising information stored in the particular node; sending the prompt for execution to the machine learning-based language model, the prompt requesting the machine learning-based language model to generate a natural language description of the context for the particular node; and receiving a response based on the execution of the machine learning-based language model, wherein the response comprises the natural language description of the context.
19. The computer system of claim 16, wherein the data structure comprises a hierarchy of nodes having a root node, wherein the context for a particular node is determined based on one or more nodes encountered in a path from the root node to the particular node.
20. The computer system of claim 16, wherein the instructions further cause the one or more computer processors to perform steps comprising: selecting a subset of nodes from the data structure; generating a prompt for a machine learning-based language model, the prompt comprising information stored in subset of nodes; sending the prompt for execution to the machine learning-based language model, the prompt requesting the machine learning-based language model to generate a statement describing the user; andreceiving a response based on the execution of the machine learning-based language model, wherein the response comprises the statement describing the user.
1. A computer-implemented method, comprising: determining a total time interval associated with a user for exploration of information describing the user; creating a root epoch node for building a weighted epoch tree comprising epoch nodes, each epoch node associated with a time interval associated with the user, wherein an epoch node has a relevance score determined based on a set of events associated with the user that occurred during the time interval of the epoch node; building the weighted epoch tree based on information describing the user, comprising: selecting an epoch node of the weighted epoch tree for further exploration based on relevance scores of epoch nodes of the weighted epoch tree, determining a natural language question relevant to a context represented by the selected epoch node, determining a natural language answer to the natural language question, determining whether to create child epoch nodes for the selected epoch node based on the natural language answer using a machine learning-based language model, and responsive to determining to create child epoch nodes, dividing the time interval of the epoch node into sub-intervals based on the natural language answer and creating a child epoch node for each sub-interval; and traversing the weighted epoch tree for generating a synthetic statement for the user.
2. The computer-implemented method of claim 1, wherein determining a natural language question relevant to the context represented by the selected epoch node comprises: storing, in a vector database, a set of natural language questions; generating a natural language description of the context represented by the selected epoch node; and selecting from the vector database, one or more natural language questions based on a vector distance between a vector representation of the natural language description of the context and vector representations of natural language questions stored in the vector database.
3. The computer-implemented method of claim 1, wherein determining whether to create child epoch nodes for the selected epoch node based on the natural language answer comprises: generating a prompt for a machine learning-based language model, the prompt specifying the natural language answer and requesting the machine learning-based language model to determine whether the natural language answer comprises a plurality of epochs; sending the prompt for execution to the machine learning-based language model; receiving a response based on the execution of the machine learning-based language model; and responsive to the response indicating that there are multiple epochs within the time interval represented by the selected epoch node, determining to create child epoch nodes for the selected epoch node.
4. The computer-implemented method of claim 1, wherein selecting an epoch node of the weighted epoch tree for further exploration based on relevance scores of epoch nodes of the weighted epoch tree comprises: traversing the weighted epoch tree to identify a leaf epoch node having a highest relevance score compared to other leaf epoch nodes of the weighted epoch tree; and providing the identified epoch node as the selected epoch node.
5. The computer-implemented method of claim 1, wherein determining the natural language answer to the natural language question comprises: sending the natural language question for display via a client device; and receiving, via the client device, the natural language answer to the natural language question.
6. The computer-implemented method of claim 1, wherein building the weighted epoch tree further comprises: responsive to determining not to create child epoch nodes, generating one or more natural language questions for extracting events associated with the user within the time interval of the epoch node; and adding information to the epoch node based on natural language answers corresponding to the one or more natural language questions.
7. The computer-implemented method of claim 1, further comprising, for a particular epoch node of the weighted epoch tree: storing an attribute representing user provided information as received from the user; and generating a summary of the user provided information, comprising: generating a prompt for the machine learning-based language model, the prompt specifying the user provided information and requesting the machine learning-based language model to generate a summary having less than a threshold size; sending the prompt for execution to the machine learning-based language model; and extracting the summary for the epoch node from a response received by executing the machine learning-based language model.
8. The computer-implemented method of claim 1, further comprising, for a particular epoch node of the weighted epoch tree having a plurality of child epoch nodes, generating a summary of a user provided description, comprising: generating a prompt for the machine learning-based language model, the prompt specifying the summary of each of the child epoch nodes and requesting the machine learning-based language model to generate a summary having less than a threshold size; sending the prompt for execution to the machine learning-based language model; and extracting the summary for the epoch node from a response received by executing the machine learning-based language model.
9. A non-transitory computer readable storage medium, storing instructions that when executed by one or more computer processors cause the one or more computer processors to perform steps comprising: determining a total time interval associated with a user for exploration of information describing the user; creating a root epoch node for building a weighted epoch tree comprising epoch nodes, each epoch node associated with a time interval associated with the user, wherein an epoch node has a relevance score determined based on a set of events associated with the user that occurred during the time interval of the epoch node; building the weighted epoch tree based on information describing the user, comprising: selecting an epoch node of the weighted epoch tree for further exploration based on relevance scores of epoch nodes of the weighted epoch tree, determining a natural language question relevant to a context represented by the selected epoch node, determining a natural language answer to the natural language question, determining whether to create child epoch nodes for the selected epoch node based on the natural language answer using a machine learning-based language model, and responsive to determining to create child epoch nodes, dividing the time interval of the epoch node into sub-intervals based on the natural language answer and creating a child epoch node for each sub-interval; and traversing the weighted epoch tree for generating a synthetic statement for the user.
10. The non-transitory computer readable storage medium of claim 9, wherein determining a natural language question relevant to the context represented by the selected epoch node comprises: storing, in a vector database, a set of natural language questions; generating a natural language description of the context represented by the selected epoch node; and selecting from the vector database, one or more natural language questions based on a vector distance between a vector representation of the natural language description of the context and vector representations of natural language questions stored in the vector database.
11. The non-transitory computer readable storage medium of claim 9, wherein determining whether to create child epoch nodes for the selected epoch node based on the natural language answer comprises: generating a prompt for a machine learning-based language model, the prompt specifying the natural language answer and requesting the machine learning-based language model to determine whether the natural language answer comprises a plurality of epochs; sending the prompt for execution to the machine learning-based language model; receiving a response based on the execution of the machine learning-based language model; and responsive to the response indicating that there are multiple epochs within the time interval represented by the selected epoch node, determining to create child epoch nodes for the selected epoch node.
12. The non-transitory computer readable storage medium of claim 9, wherein selecting an epoch node of the weighted epoch tree for further exploration based on relevance scores of epoch nodes of the weighted epoch tree comprises: traversing the weighted epoch tree to identify a leaf epoch node having a highest relevance score compared to other leaf epoch nodes of the weighted epoch tree; and providing the identified epoch node as the selected epoch node.
13. The non-transitory computer readable storage medium of claim 9, wherein determining the natural language answer to the natural language question comprises: sending the natural language question for display via a client device; and receiving, via the client device, the natural language answer to the natural language question.
14. The non-transitory computer readable storage medium of claim 9, wherein building the weighted epoch tree further comprises: responsive to determining not to create child epoch nodes, generating one or more natural language questions for extracting events associated with the user within the time interval of the epoch node; and adding information to the epoch node based on natural language answers corresponding to the one or more natural language questions.
15. The non-transitory computer readable storage medium of claim 9, wherein the instructions further cause the one or more computer processors to perform steps comprising, for a particular epoch node of the weighted epoch tree: storing an attribute representing user provided information as received from the user; and generating a summary of the user provided information, comprising: generating a prompt for the machine learning-based language model, the prompt specifying the user provided information and requesting the machine learning-based language model to generate a summary having less than a threshold size; sending the prompt for execution to the machine learning-based language model; and extracting the summary for the epoch node from a response received by executing the machine learning-based language model.
16. The non-transitory computer readable storage medium of claim 9, wherein the instructions further cause the one or more computer processors to perform steps comprising, for a particular epoch node of the weighted epoch tree having a plurality of child epoch nodes, generating a summary of a user provided description, comprising: generating a prompt for the machine learning-based language model, the prompt specifying the summary of each of the child epoch nodes and requesting the machine learning-based language model to generate a summary having less than a threshold size; sending the prompt for execution to the machine learning-based language model; and extracting the summary for the epoch node from a response received by executing the machine learning-based language model.
17. A computer system comprising: one or more computer processors; and a non-transitory computer readable storage medium, storing instructions that when executed by the one or more computer processors cause the one or more computer processors to perform steps comprising: determining a total time interval associated with a user for exploration of information describing the user; creating a root epoch node for building a weighted epoch tree comprising epoch nodes, each epoch node associated with a time interval associated with the user, wherein an epoch node has a relevance score determined based on a set of events associated with the user that occurred during the time interval of the epoch node; building the weighted epoch tree based on information describing the user, comprising: selecting an epoch node of the weighted epoch tree for further exploration based on relevance scores of epoch nodes of the weighted epoch tree, determining a natural language question relevant to a context represented by the selected epoch node, determining a natural language answer to the natural language question, determining whether to create child epoch nodes for the selected epoch node based on the natural language answer using a machine learning-based language model, and responsive to determining to create child epoch nodes, dividing the time interval of the epoch node into sub-intervals based on the natural language answer and creating a child epoch node for each sub-interval; and traversing the weighted epoch tree for generating a synthetic statement for the user.
18. The computer system of claim 17, wherein determining a natural language question relevant to the context represented by the selected epoch node comprises: storing, in a vector database, a set of natural language questions; generating a natural language description of the context represented by the selected epoch node; and selecting from the vector database, one or more natural language questions based on a vector distance between a vector representation of the natural language description of the context and vector representations of natural language questions stored in the vector database.
19. The computer system of claim 17, wherein determining whether to create child epoch nodes for the selected epoch node based on the natural language answer comprises: generating a prompt for a machine learning-based language model, the prompt specifying the natural language answer and requesting the machine learning-based language model to determine whether the natural language answer comprises a plurality of epochs; sending the prompt for execution to the machine learning-based language model; receiving a response based on the execution of the machine learning-based language model; and responsive to the response indicating that there are multiple epochs within the time interval represented by the selected epoch node, determining to create child epoch nodes for the selected epoch node.
20. The computer system of claim 17, wherein the instructions further cause the one or more computer processors to perform steps comprising, for a particular epoch node of the weighted epoch tree having a plurality of child epoch nodes, generating a summary of a user provided description, comprising: generating a prompt for the machine learning-based language model, the prompt specifying the summary of each of the child epoch nodes and requesting the machine learning-based language model to generate a summary having less than a threshold size; sending the prompt for execution to the machine learning-based language model; and extracting the summary for the epoch node from a response received by executing the machine learning-based language model.
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 –
(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.
Claims 1-20 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by US 20240194178 A1 Austraat; Bjorn (hereinafter Austraat).
1. A computer-implemented method, comprising: (fig. 1 hardware)
storing in a vector database, vector representations of a plurality of natural language questions; (a natural language question produces a natural language description i.e. resolution or answer per se, resolutions stored in a database containing response and requests 0073 based on helpdesk requests 0116-0120)
receiving request for extracting information from a user; (user sends a request such a question 0055 and 0206-0207)
creating a data structure storing a plurality of nodes, each node associated with information obtained from the user; (using the input query from the user as in 0206-0207 input into a nodal structure as in fig. 3 and fig. 4 with sub-nodes as in fig. 2b)
interacting with the user via a client device to obtain information from the user by repeatedly: (in a repeat situation such as a chat or instant message back and forth 0072, user sends a request such a question 0055 and 0206-0207)
selecting a node of the data structure for further exploration from the data structure, (moving through the node to find the highest scoring node 0206-0207 referencing fig. 2b for instance)
determining a context based on the selected node; (goal is to determine intent or context 0175, using the input query from the user as in 0206-0207 input into a nodal structure as in fig. 3 and fig. 4 with sub-nodes as in fig. 2b)
selecting a natural language question from a a vector database, based on a vector distance between a vector representation of the context and vector representations of natural language questions stored in the vector database; (relating to a context or subject per se 0115, using intent similarity thereof with a known certainty for a group, vector, or cluster 0099 0101 where differences in probability are calculated, once in vector form using cosine similarity to utilize such a metric to match a request with a resolution as vector 0139, where a natural language question produces a natural language description i.e. resolution or answer per se, resolutions stored in a database containing response and requests 0073 based on helpdesk requests 0116-0120, and discerning meaning using questions stored as viable candidate to match input 0128-0135, using nodes to help customers e.g. 0101 with vectors with distances 0116 and 0147)
sending the natural language question to the client device, (0186-0190 in communication with the user to send questions while interpreting inquiry and engaging until resolution is met)
receiving a natural language answer to the natural language question from the client device, and (user provides questions and replies as the agent provides answers to questions and also asks questions such as if the customer needs assistance 0186-0190 in communication with the user to send questions while interpreting inquiry and engaging until resolution is met and as in an agent 0178, using a device for instance 0053-0055)
updating the data structure by adding one or more nodes storing information obtained from the natural language answer, and (updating a model e.g. machine learning model 0092, with a neural network 0161-0162 and nodes using the input query from the user as in 0206-0207 input into a nodal structure as in fig. 3 and fig. 4 with sub-nodes as in fig. 2b, in which the nodes help customers e.g. 0101 with vectors with distances 0116 and 0147… where user provides questions and replies as the agent provides answers to questions and also asks questions such as if the customer needs assistance 0186-0190 in communication with the user to send questions while interpreting inquiry and engaging until resolution is met and as in an agent 0178, using a device for instance 0053-0055… relating to a context or subject per se 0115, using intent similarity thereof with a known certainty for a group, vector, or cluster 0099 0101 where differences in probability are calculated, once in vector form using cosine similarity to utilize such a metric to match a request with a resolution as vector 0139, where a natural language question produces a natural language description i.e. resolution or answer per se, resolutions stored in a database containing response and requests 0073 based on helpdesk requests 0116-0120, and discerning meaning using questions stored as viable candidate to match input 0128-0135, using nodes to help customers e.g. 0101 with vectors with distances 0116 and 0147)
storing a representation of the data structure. (nodes… from updating a model e.g. machine learning model 0092, with a neural network 0161-0162 and nodes using the input query from thez user as in 0206-0207 input into a nodal structure as in fig. 3 and fig. 4 with sub-nodes as in fig. 2b, in which the nodes help customers e.g. 0101 with vectors with distances 0116 and 0147)
Re claim 9, this claim has been rejected for teaching a broader claim, in the instance of intent to claim elements such as vector database and distances thereof, and primarily based on general inclusion of hardware alone (e.g. processor, memory, instructions), representation of claim 1 omitting/including hardware for instance, otherwise amounting to a virtually identical scope
For instance, see fig. 1 which contains hardware.
Re claim 16, this claim has been rejected for teaching a broader claim, in the instance of intent to claim elements such as vector database and distances thereof, and primarily based on general inclusion of hardware alone (e.g. processor, memory, instructions), representation of claim 1 omitting/including hardware for instance, otherwise amounting to a virtually identical scope
For instance, see fig. 1 which contains hardware.
Re claims 2, 10, and 17, Austraat teaches
2. The computer-implemented method of claim 1, wherein selecting the natural language question comprises:
generating a natural language description of the context; and (determine intent or context 0175… updating a model e.g. machine learning model 0092, with a neural network 0161-0162 and nodes using the input query from the user as in 0206-0207 input into a nodal structure as in fig. 3 and fig. 4 with sub-nodes as in fig. 2b, in which the nodes help customers e.g. 0101 with vectors with distances 0116 and 0147… where user provides questions and replies as the agent provides answers to questions and also asks questions such as if the customer needs assistance 0186-0190 in communication with the user to send questions while interpreting inquiry and engaging until resolution is met and as in an agent 0178, using a device for instance 0053-0055)
selecting from the vector database, the natural language question based on a vector distance between a vector representation of the natural language description of the context and vector representations of natural language questions stored in the vector database. (vectors with distances 0116 and 0147…updating a model e.g. machine learning model 0092, with a neural network 0161-0162 and nodes using the input query from the user as in 0206-0207 input into a nodal structure as in fig. 3 and fig. 4 with sub-nodes as in fig. 2b, in which the nodes help customers e.g. 0101 with vectors with distances 0116 and 0147… where user provides questions and replies as the agent provides answers to questions and also asks questions such as if the customer needs assistance 0186-0190 in communication with the user to send questions while interpreting inquiry and engaging until resolution is met and as in an agent 0178, using a device for instance 0053-0055)
Re claims 3, 11, and 18, Austraat teaches
3. The computer-implemented method of claim 2, wherein generating a natural language description of the context for a particular node comprises:
generating a prompt for a machine learning-based language model, the prompt comprising information stored in the particular node; (prompting using a device for instance 0053-0055, updating a model e.g. machine learning model 0092, with a neural network 0161-0162 and nodes using the input query from the user as in 0206-0207 input into a nodal structure as in fig. 3 and fig. 4 with sub-nodes as in fig. 2b, in which the nodes help customers e.g. 0101 with vectors with distances 0116 and 0147… where user provides questions and replies as the agent provides answers to questions and also asks questions such as if the customer needs assistance 0186-0190 in communication with the user to send questions while interpreting inquiry and engaging until resolution is met and as in an agent 0178)
sending the prompt for execution to the machine learning-based language model, the prompt requesting the machine learning-based language model to generate a natural language description of the context for the particular node; and (prompting using a device for instance 0053-0055, updating a model e.g. machine learning model 0092, with a neural network 0161-0162 and nodes using the input query from the user as in 0206-0207 input into a nodal structure as in fig. 3 and fig. 4 with sub-nodes as in fig. 2b, in which the nodes help customers e.g. 0101 with vectors with distances 0116 and 0147… where user provides questions and replies as the agent provides answers to questions and also asks questions such as if the customer needs assistance 0186-0190 in communication with the user to send questions while interpreting inquiry and engaging until resolution is met and as in an agent 0178)
receiving a response based on the execution of the machine learning-based language model, wherein the response comprises the natural language description of the context. (in the premise of a chat session for instance with a customer and agent back and forth 0072, where user provides questions and replies as the agent provides answers to questions and also asks questions such as if the customer needs assistance 0186-0190 in communication with the user to send questions while interpreting inquiry and engaging until resolution is met and as in an agent 0178, prompting using a device for instance 0053-0055, updating a model e.g. machine learning model 0092, with a neural network 0161-0162 and nodes using the input query from the user as in 0206-0207 input into a nodal structure as in fig. 3 and fig. 4 with sub-nodes as in fig. 2b, in which the nodes help customers e.g. 0101 with vectors with distances 0116 and 0147)
Re claims 4 and 12, Austraat teaches
4. The computer-implemented method of claim 1, wherein each node has a relevance score determined based on the information stored in the node, wherein selecting the node of the data structure for further exploration is based on relevance scores of nodes of the data structure. (relevance score can be weights 0143-0144 or confidence scores 0206-0207…in the premise of a chat session for instance with a customer and agent back and forth 0072, where user provides questions and replies as the agent provides answers to questions and also asks questions such as if the customer needs assistance 0186-0190 in communication with the user to send questions while interpreting inquiry and engaging until resolution is met and as in an agent 0178, prompting using a device for instance 0053-0055, updating a model e.g. machine learning model 0092, with a neural network 0161-0162 and nodes using the input query from the user as in 0206-0207 input into a nodal structure as in fig. 3 and fig. 4 with sub-nodes as in fig. 2b, in which the nodes help customers e.g. 0101 with vectors with distances 0116 and 0147)
Re claim 5, Austraat teaches
5. The computer-implemented method of claim 4, wherein the node selected for further exploration is the node with a highest relevance score of the plurality of nodes of the data structure. (relevance score can be weights 0143-0144 or confidence scores 0206-0207… input into a nodal structure as in fig. 3 and fig. 4 with sub-nodes as in fig. 2b, in which the nodes help customers e.g. 0101 with vectors with distances 0116 and 0147… in the premise of a chat session for instance with a customer and agent back and forth 0072, where user provides questions and replies as the agent provides answers to questions and also asks questions such as if the customer needs assistance 0186-0190 in communication with the user to send questions while interpreting inquiry and engaging until resolution is met and as in an agent 0178, prompting using a device for instance 0053-0055, updating a model e.g. machine learning model 0092, with a neural network 0161-0162 and nodes using the input query from the user as in 0206-0207)
Re claims 6, 13, and 19, Austraat teaches
6. The computer-implemented method of claim 1, wherein the data structure comprises a hierarchy of nodes having a root node, wherein the context for a particular node is determined based on one or more nodes encountered in a path from the root node to the particular node. (node paths as is well known 0182. updating a model e.g. machine learning model 0092, with a neural network 0161-0162 and nodes using the input query from the user as in 0206-0207 input into a nodal structure as in fig. 3 and fig. 4 with sub-nodes as in fig. 2b, in which the nodes help customers e.g. 0101 with vectors with distances 0116 and 0147… where user provides questions and replies as the agent provides answers to questions and also asks questions such as if the customer needs assistance 0186-0190 in communication with the user to send questions while interpreting inquiry and engaging until resolution is met and as in an agent 0178, using a device for instance 0053-0055)
Re claims 7, 14, and 20, Austraat teaches
7. The computer-implemented method of claim 1, further comprising:
selecting a subset of nodes from the data structure; (nodes using the input query from the user as in 0206-0207 input into a nodal structure as in fig. 3 and fig. 4 with sub-nodes as in fig. 2b, in which the nodes help customers e.g. 0101 with vectors with distances 0116 and 0147…)
generating a prompt for a machine learning-based language model, the prompt comprising information stored in subset of nodes; (prompting using a device for instance 0053-0055, updating a model e.g. machine learning model 0092, with a neural network 0161-0162 and nodes using the input query from the user as in 0206-0207 input into a nodal structure as in fig. 3 and fig. 4 with sub-nodes as in fig. 2b, in which the nodes help customers e.g. 0101 with vectors with distances 0116 and 0147… where user provides questions and replies as the agent provides answers to questions and also asks questions such as if the customer needs assistance 0186-0190 in communication with the user to send questions while interpreting inquiry and engaging until resolution is met and as in an agent 0178)
sending the prompt for execution to the machine learning-based language model, the prompt requesting the machine learning-based language model to generate a statement describing the user; and (intent/context describes the user per se or his/her request as the intent per iteration of inquiry-answer 0175, prompting using a device for instance 0053-0055, updating a model e.g. machine learning model 0092, with a neural network 0161-0162 and nodes using the input query from the user as in 0206-0207 input into a nodal structure as in fig. 3 and fig. 4 with sub-nodes as in fig. 2b, in which the nodes help customers e.g. 0101 with vectors with distances 0116 and 0147… where user provides questions and replies as the agent provides answers to questions and also asks questions such as if the customer needs assistance 0186-0190 in communication with the user to send questions while interpreting inquiry and engaging until resolution is met and as in an agent 0178)
receiving a response based on the execution of the machine learning-based language model, wherein the response comprises the statement describing the user. (intent/context describes the user per se or his/her request as the intent per iteration of inquiry-answer 0175, prompting using a device for instance 0053-0055, updating a model e.g. machine learning model 0092, with a neural network 0161-0162 and nodes using the input query from the user as in 0206-0207 input into a nodal structure as in fig. 3 and fig. 4 with sub-nodes as in fig. 2b, in which the nodes help customers e.g. 0101 with vectors with distances 0116 and 0147… where user provides questions and replies as the agent provides answers to questions and also asks questions such as if the customer needs assistance 0186-0190 in communication with the user to send questions while interpreting inquiry and engaging until resolution is met and as in an agent 0178)
Re claims 8 and 15, Austraat teaches
8. The computer-implemented method of claim 1, further comprising: determining a score evaluating the user based on information obtained from the user stored in the data structure. (relevance score can be weights 0143-0144 or confidence scores 0206-0207…in the premise of a chat session for instance with a customer and agent back and forth 0072, where user provides questions and replies as the agent provides answers to questions and also asks questions such as if the customer needs assistance 0186-0190 in communication with the user to send questions while interpreting inquiry and engaging until resolution is met and as in an agent 0178, prompting using a device for instance 0053-0055, updating a model e.g. machine learning model 0092, with a neural network 0161-0162 and nodes using the input query from the user as in 0206-0207 input into a nodal structure as in fig. 3 and fig. 4 with sub-nodes as in fig. 2b, in which the nodes help customers e.g. 0101 with vectors with distances 0116 and 0147)
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 20240249113 A1 LIU; Ye et al.
Question and answer node maps
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MICHAEL COLUCCI whose telephone number is (571)270-1847. The examiner can normally be reached on M-F 9 AM - 7 PM.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Andrew Flanders can be reached at (571)272-7516. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/MICHAEL COLUCCI/Primary Examiner, Art Unit 2655 (571)-270-1847
Examiner FAX: (571)-270-2847
Michael.Colucci@uspto.gov