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
Claims 1-21 received on 05 June 2024 are currently pending and being considered by Examiner in this Office Action.
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 1-21 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
The claims recite subject matter within a statutory category as a process (claims 18-21) and machine (claims 1-13 & 14-17) (Subject Matter Eligibility (SME) Test Step 1: Yes) which recite steps of:
store a memory list comprising subjects that a user has difficulty to remember, wherein the computer memory is configured to store personal data associated with the user in which the user’s memory needs to be improved; and
one or more computer processors in communication with the computer memory, the one or more computer processors configured to execute a cognitive exercise computation agent and a large language model responsive to the cognitive exercise computation agent;
wherein the cognitive exercise computation agent comprises a cognitive exercise generation controller configured to retrieve the memory list and the personal data associated with the user from the computer memory;
wherein the cognitive exercise computation agent comprises a cognitive exercise generator;
wherein the cognitive exercise generation controller is configured to control the cognitive exercise generator and the large language model to produce the generated cognitive exercises under constraints of the memory list and the personal data associated with the user,
wherein the cognitive exercise generation controller is configured to receive user responses or feedback, wherein the cognitive exercise generation controller is configured to steer the cognitive exercise generator and the large language model to produce improved cognitive exercises in response to user responses or feedback.
These steps of storing personal data of a user and memory list of subjects for cognitive enhancement for the user, generating content for cognitive exercises based on the personal data and the memory list, generating cognitive exercises, and presenting/outputting the cognitive exercises to the user, receiving user responses/feedback, and tailoring the cognitive exercise according to user responses or feedback, as drafted, under the broadest reasonable interpretation (BRI), include performance of the limitation in the mind but for recitation of generic computer components. That is, other than reciting steps as performed by the generic computer components, nothing in the claim element precludes the step from practically being performed in the mind. For example, but for the storing personal data and/or memory list of subjects for cognitive enhancement of a user language, storing personal data and/or a memory list in the context of this claim encompasses a mental process of a doctor maintaining one or more memories or physical records/lists for a patient regarding their patient data and/or memory list. Similarly, the limitation of generating content for cognitive exercises based on the personal data and the memory list and outputting the cognitive exercises for the user, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, such as the same doctor creating exercises for a patient to complete based on information/memory data of the patient, such as by generating the exercises using pen and paper or a generic computer for outputting said exercises to the patient. If a claim limitation, under its BRI, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea (SME Test Step 2A, Prong 1: Yes).
These steps of storing personal data of a user, storing a memory list of subjects for cognitive enhancement for the user, generating content for cognitive exercises based on the personal data and the memory list, generating cognitive exercise, and presenting/outputting the cognitive exercises to the user, as drafted, under the BRI, includes methods of organizing human activity. MPEP 2106.04(a)(2)(II) describes certain methods of organizing human activity (MOHA), including fundamental economic principles or practices (including hedging, insurance, mitigating risk); commercial or legal interactions (including agreements in the form of contracts, legal obligations, advertising, marketing or sales activities or behaviors, and business relations); and managing personal behavior or relationships or interactions between people, (including social activities, teaching, and following rules or instructions). For instance, MPEP 2106.04(a)(2)(II)(C)(i)-(iii) further specifies examples of managing personal behavior or relationships or interactions between people including filtering content, considering historical usage information when inputting data, and/or a mental process that a neurologist should follow when testing a patient for nervous system malfunctions. The steps recited above are substantially similar to a mental process that a neurologist should follow when testing a patient for nervous system malfunctions, at least by the system performing steps of storing personal data of a user, storing a memory list of subjects for cognitive enhancement for the user, generating content for cognitive exercises based on the personal data and the memory list, generating cognitive exercise, and presenting/outputting the cognitive exercises to the user. That is, the system effectively performs the efforts of a mental process that a neurologist should follow when testing a patient for nervous system malfunctions, such as determining a patient’s issues regarding memory or cognitive malfunctions, and generating associated treatments/exercises based on said malfunctions/memory problems. Therefore, since the claims substantially relate to a mental process that a neurologist should follow when testing a patient for nervous system malfunctions and/or managing personal behavior or relationships or interactions between people, by modifying the cognitive tasks a patient/user should perform in view of the varying user data, the claims fall into the MOHA grouping of abstract ideas, under BRI. Accordingly, the claim recites an abstract idea (SME Test Step 2A, Prong 1: Yes).
Dependent claims recite additional subject matter which further narrows or defines the abstract idea embodied in the claims (such as claim 2-13, 15-17, & 19-21, reciting particular aspects of how generating cognitive exercises, determining appropriate content for cognitive exercises, and/or parameterizing patient data may be performed in the mind but for recitation of generic computer components).
This judicial exception is not integrated into a practical application. In particular, the additional elements do not integrate the abstract idea into a practical application, other than the abstract idea per se, because the additional elements amount to no more than limitations which:
amount to mere instructions to apply an exception (such as recitation of a computer system, a computer memory, one or more computer processors, a cognitive exercise computation agent/controller/generator, a large language model/natural language processing tool, amounts to invoking computers as a tool to perform the abstract idea, see Applicant’s specification [0020] for a computer system; [0011] for a computer memory; [0011] for one or more processors; [0012] for a cognitive exercise computation agent/controller/generator; [0020] for a large language model/natural language processing tool; and/or “steering” or “modifying” various parameters of said models, see MPEP 2106.05(f));
add insignificant extra-solution activity to the abstract idea (such as recitation of retrieving the memory list and the personal data from computer memory, presenting said exercises, receiving user responses/feedback, producing additional/subsequent cognitive exercises in response to user responses or feedback amounts to mere data gathering; recitation of storing a memory list comprising subjects that a user has difficulty to remember, storing personal data associated with the user amounts to selecting a particular data source or type of data to be manipulated, recitation of producing generated cognitive exercises using the large language model, , producing additional/subsequent cognitive exercises in response to user responses or feedback, “steering” or “modifying” various parameters of said models amounts to insignificant application, see MPEP 2106.05(g));
generally link the abstract idea to a particular technological environment or field of use (such as recitation of applying the steps to generation of cognitive exercises and/or using a large language model/natural language processing tool and/or various module implementations, see MPEP 2106.05(h)).
Dependent claims recite additional subject matter which amount to limitations consistent with the additional elements in the independent claims (such as claims 2-13, 15-17, & 19-21, additional limitations which amount to invoking computers as a tool to perform the abstract idea by reciting a computer system, a computer memory, a cognitive exercise computation agent/controller/generator, a large language model/natural language processing tool, a voice generation module, and/or a multimodal module which amount to invoking computers as a tool to perform the abstract idea, see Applicant’s specification [0020] for a computer system; [0011] for a computer memory; [0011] for one or more processors; [0012] for a cognitive exercise computation agent/controller/generator; [0020] for a large language model/natural language processing tool; [0012] for a voice generation module; [0039] for a multimodal module, see MPEP 2106.05(f)); claims 6-7, 10-11, & 21, which recite limitations relating to receiving the memory list and personal data associated with the user, receiving user responses, receiving speech/voice data, receiving user responses and feedback in one or more forms of voice, images, video, text, or touch, additional limitations which add insignificant extra-solution activity to the abstract idea which amounts to mere data gathering; claims 3-4, 9-13, 16-17, & 20-21, which recite limitations relating to storing various forms of data, including the personal knowledge graph and attributes associated therewith, exercise styles, and/or specifying certain aspects or forms of the stored/retrieved data, selecting an exercise style/type for the user, additional limitations which add insignificant extra-solution activity to the abstract idea by selecting a particular data source or type of data to be manipulated; claims 2, 7-11, 13, 15, & 19-21, which recite limitations relating to producing cognitive exercises in view of certain data/patient constraints, and/or generating a personal knowledge graph for the user, additional limitations which amount to insignificant application; claims 2-13, 15-17, & 19-21, which recite limitations relating to generation of cognitive exercises, using a large language model/natural language processing tool, and/or use of a chatbot/avatar for speech and/or multimodal generation, additional limitations which generally link the abstract idea to a particular technological environment or field of use). Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely provide conventional computer implementation and do not impose a meaningful limit to integrate the abstract idea into a practical application (SME Test Step 2A, Prong 2: No).
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to discussion of integration of the abstract idea into a practical application, the additional elements amount to no more than mere instructions to apply an exception, add insignificant extra-solution activity to the abstract idea, and generally link the abstract idea to a particular technological environment or field of use. Additionally, the additional limitations, other than the abstract idea per se, amount to no more than limitations which:
amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields (such as recitation of retrieving the memory list and the personal data from computer memory, presenting said exercises, receiving user responses/feedback, producing additional/subsequent cognitive exercises in response to user responses or feedback, e.g., receiving or transmitting data over a network or locally, Symantec, MPEP 2106.05(d)(II)(i); generating cognitive exercises using the large language model, “steering” or “modifying” various parameters of said models, producing additional/subsequent cognitive exercises in response to user responses or feedback, e.g., performing repetitive calculations, Flook, MPEP 2106.05(d)(II)(ii); maintaining one or more memory lists and/or personal data records for a patient, e.g., electronic recordkeeping, Alice Corp., MPEP 2106.05(d)(II)(iii); storing a memory list comprising subjects that a user has difficulty to remember, storing personal data associated with the user, e.g., storing and retrieving information in memory, Versata Dev. Group, MPEP 2106.05(d)(II)(iv); i); generating cognitive exercises using the large language model, such as by parsing/scanning the retrieved memory list and personal data associated with the patient, e.g., electronic scanning or extracting data from a physical document, Content Extraction, MPEP 2106.05(d)(II)(v)).
Dependent claims recite additional subject matter which, as discussed above with respect to integration of the abstract idea into a practical application, amount to invoking computers as a tool to perform the abstract idea. Dependent claims recite additional subject matter which amount to limitations consistent with the additional elements in the independent claims (such as claims 2-13, 15-17, & 19-21, additional limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields; claims 6-7, 10-11, & 21, which recite limitations relating to receiving the memory list and personal data associated with the user, receiving user responses, receiving speech/voice data, receiving user responses and feedback in one or more forms of voice, images, video, text, or touch, e.g., receiving or transmitting data over a network, Symantec, MPEP 2106.05(d)(II)(i); claims 2, 7-11, 13, 15, & 19-21, which recite limitations relating to producing cognitive exercises in view of certain data/patient constraints, and/or generating a personal knowledge graph for the user, e.g., performing repetitive calculations, Flook, MPEP 2106.05(d)(II)(ii); claims 3-4, 9-13, 16-17, & 20-21, which recite limitations relating to storing various forms of data, including the personal knowledge graph and attributes associated therewith, exercise styles, and/or specifying certain aspects or forms of the stored/retrieved data, selecting an exercise style/type for the user and under BRI include interpretation of storage of one or more records associated therewith, e.g., electronic recordkeeping, Alice Corp., MPEP 2106.05(d)(II)(iii); storing a memory list comprising subjects that a user has difficulty to remember, storing personal data associated with the user, claims 3-4, 9-13, 16-17, & 20-21, which recite limitations relating to storing various forms of data, including the personal knowledge graph and attributes associated therewith, exercise styles, and/or specifying certain aspects or forms of the stored/retrieved data, selecting an exercise style/type for the user, e.g., storing and retrieving information in memory, Versata Dev. Group, MPEP 2106.05(d)(II)(iv); claims 6-7, 10-11, 13, & 21, which recite limitations relating to receiving, i.e. via parsing/extraction by a large language model, the memory list and personal data associated with the user, receiving user responses, receiving speech/voice data, receiving user responses and feedback in one or more forms of voice, images, video, text, or touch, e.g., electronic scanning or extracting data from a physical document, Content Extraction, MPEP 2106.05(d)(II)(v)). Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely provide conventional computer implementation (SME Test Step 2B: No).
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-21 are rejected under 35 U.S.C. 103 as being unpatentable over Cohen et al. (U.S. Patent Publication No. 2018/0147493), hereinafter “Cohen”, in view of Duffy et al. (U.S. Patent Publication No. 2023/0105053), hereinafter “Duffy”.
Claim 1 –
Regarding Claim 1, Cohen discloses a computer system for automatically generating cognitive exercises, comprising:
a computer memory configured to store a memory list comprising subjects that a user has difficulty to remember (See Cohen Par [0013]-[0015] which discloses a user profile comprising sub-profiles, and further include microtasks, i.e. a set of goals to be learned or accomplished by the user to provide training and measurement of a set of qualities embodied in one or more sub-profiles, and further specifies that the tasks can include, in Cohen Par [0051], a set, i.e. list, of learning/assessment core activities or capabilities representing any kind of fundamental learning or fundamental activity with which a metric or set of metrics can be associated, including cognitive ability, mathematical ability, scientific ability, and accumulated knowledge that can be acted upon; See Cohen Par [0111] which specifically references microtasks and assessments relating to a working memory profile and a set of micro-tasks directed to test visuo-spatial short term memory of a user; See Cohen Par [0071] which discloses the working memory assessment microtasks, including, for example, mathematics, reading, language learning, science, history, music, etc.), wherein
the computer memory is configured to store personal data associated with the user (See Cohen Par [0052] & [0062] which discloses a user profile including a dataset stored in a non-transitory memory comprising one or more of the following: a working memory profile, a motivation profile, an accuracy assessment, response time assessment, delay lengths in delay tasks (e.g., how long user remembers accurately), reward profile, task complexity increase rates versus performance improvement assessment, modality assessment, strategy assessment, personality assessment, mood assessment, self-confidence assessment, automatization assessment via automaticity measures, activity preferences, learning style assessment); and
one or more computer processors in communication with the computer memory (See Cohen Par [0032]-[0033] & [0068] which discloses one or more processors under control of an operating system performing steps recited throughout the disclosure of Cohen), the one or more computer processors configured to execute a cognitive exercise computation agent responsive to the cognitive exercise computation agent (See Cohen Par [0032]-[0033] & [0068] which discloses one or more processors under control of an operating system performing steps recited throughout the disclosure of Cohen), wherein
the cognitive exercise computation agent is configured to retrieve the memory list and the personal data associated with the user from the computer memory (See Cohen Par [0013]-[0015] which discloses a user profile comprising sub-profiles, and further include microtasks, i.e. a set of goals to be learned or accomplished by the user to provide training and measurement of a set of qualities embodied in one or more sub-profiles, and further specifies that the tasks can include, in Cohen Par [0051], a set, i.e. list, of learning/assessment core activities or capabilities representing any kind of fundamental learning or fundamental activity with which a metric or set of metrics can be associated, including cognitive ability, mathematical ability, scientific ability, and accumulated knowledge that can be acted upon; See Cohen Par [0052] & [0062] which discloses a user profile including a dataset stored in a non-transitory memory comprising the memory list and personal data of the user), wherein
the cognitive exercise computation agent is configured to produce generated cognitive exercises under constraints of the memory list and the personal data associated with the user (See Cohen Par [0118] which discloses the use of a predictive model being trained across users by aggregating data users relating to any combination of task complexity increase rate preferences; problem repetition tolerance; sensory modality preferences; activity and task preferences; personality style; mental model and schema preferences; learning style preferences; working memory capabilities; problem solving strategy preferences; and/or target level of success/challenge to optimize microtasks and/or microtask structures for the current user based on said predictive models training from historical users and the current user’s user profile, albeit not recited for a large language model).
While Cohen discloses the use of a predictive model trained across historical users regarding assigning appropriate microtasks, difficulty of microtasks, and/or microtask structures, such as based on a list of microtasks assigned to the historical users and/or personal data of the historical users, Cohen does not explicitly mention the predictive model being a large language model, in particular, as required by the following limitations:
the one or more computer processors configured to execute a large language model;
the cognitive exercise computation agent is configured to produce generated cognitive exercises using the large language model under constraints of the memory list and the personal data associated with the user.
However, Duffy discloses a system, wherein the one or more computer processors configured to execute a large language model (See Duffy Par [0007] & [0101] which discloses a machine learning algorithm, referred to as a text prediction algorithm, such that an autoregressive language model configured to generate human-like text can be executed, such as Generative Pre-trained Transformer 3 (GPT-3)); and the cognitive exercise computation agent is configured to produce generated cognitive exercises using the large language model under constraints of the memory list and the personal data associated with the user (See Duffy Par [0015]-[0023] which discloses one or more cognitive tasks, i.e. exercises, that need to be completed by a user, based on varying user data, including health data, See Duffy Par [0007], [0097], & [0100]-[0102] which discloses the proposed cognitive task may include the use of the text prediction algorithm, i.e. autoregressive language model configured to generate human-like text can be executed, such as Generative Pre-trained Transformer 3 (GPT-3), as in Duffy Par [0101], to ascertain user cognitive states to determine subsequent writing, i.e. cognitive, tasks/exercises). The disclosure of Duffy is directly applicable to the disclosure of Cohen, because both disclosures share limitations and capabilities, such as being directed towards assigning cognitive tasks for a user to complete to enhance the user’s mental facilities.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the disclosure of Cohen, which already discloses the use of a predictive model to generate cognitive exercises under constraints of the memory list and the personal data associated with the user, to further specifically include a large language model, as disclosed by Duffy, because this allows for automated/predictive generation of text and can thereby be used as an aide in generating text, etc. associated with future cognitive tasks to be performed by the user (See Duffy [0097] & [0100]-[0102]).
Claim 2 –
Regarding Claim 2, Cohen and Duffy disclose the computer system of claim 1 in its entirety. Cohen and Duffy further disclose a computer system, wherein:
the computer memory is configured to store a personal knowledge graph associated with the user (See Cohen Par [0016] which discloses the use of a neural link profile that comprises a set of nodes and linkages, with associated node strength values and link strength values that are calculated by the engine, node strength represents how well an individual understands, relates to, and/or accomplishes that node (which represents a skill or knowledge item) and/or a link strength represents the strength of an individual's connection between a set of nodes connected by the link), wherein
the cognitive exercise computation agent is configured to produce the generated cognitive exercises based on the personal knowledge graph using the large language model (See Cohen Par [0016] which discloses the use of a neural link profile and/or link/data structure that comprises a set of nodes and linkages, with associated node strength values and link strength values that are calculated by the engine, node strength represents how well an individual understands, relates to, and/or accomplishes that node (which represents a skill or knowledge item) and/or a link strength represents the strength of an individual's connection between a set of nodes connected by the link, thereby understood to comprise a knowledge graph; See Cohen Par [0118] which discloses the use of a predictive model being trained across users by aggregating data users relating to any combination of task complexity increase rate preferences; problem repetition tolerance; sensory modality preferences; activity and task preferences; personality style; mental model and schema preferences; learning style preferences; working memory capabilities; problem solving strategy preferences; and/or target level of success/challenge to optimize microtasks and/or microtask structures for the current user based on said predictive models training from historical users and the current user’s user profile, albeit not recited for a large language model; See Cohen Par [0139] which discloses a user-specific graph (a neural linking structure graph) indicating the strength of the user's skill, knowledge, or usage of a mental model for all those covered in the graph along with links indicating the strength of relationships between nodes for that user, that is used in order to generate microtasks, i.e. cognitive exercises, for the user to accomplish to train said skills, knowledge, or usage of a mental model; See Duffy Par [0015]-[0023] which discloses one or more cognitive tasks, i.e. exercises, that need to be completed by a user, based on varying user data, including health data, See Duffy Par [0007], [0097], & [0100]-[0102] which discloses the proposed cognitive task may include the use of the text prediction algorithm, i.e. autoregressive language model configured to generate human-like text can be executed, such as Generative Pre-trained Transformer 3 (GPT-3), as in Duffy Par [0101], to ascertain user cognitive states to determine subsequent writing, i.e. cognitive, tasks/exercises).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the disclosure of Cohen, which already discloses the use of a predictive model to generate cognitive exercises under constraints of the memory list and the personal data associated with the user, to further specifically include a large language model, as disclosed by Duffy, because this allows for automated/predictive generation of text and can thereby be used as an aide in generating text, etc. associated with future cognitive tasks to be performed by the user (See Duffy [0097] & [0100]-[0102]).
Claim 3 –
Regarding Claim 3, Cohen and Duffy disclose the computer system of claim 2 in its entirety. Cohen further discloses a computer system, wherein:
the personal knowledge graph comprises a user node representing the user, one or more first nodes in connection with the user node, representing relationships that the user has, and one or more second nodes in connection with the user node, representing interests and hobbies of the user (See Cohen Par [0016] which discloses the use of a neural link profile and/or link/data structure that comprises a set of nodes, i.e. a first and second node, and linkages, with associated node strength values and link strength values that are calculated by the engine, node strength represents how well an individual understands, relates to, and/or accomplishes that node (which represents a skill or knowledge item) and/or a link strength represents the strength of an individual's connection between a set of nodes connected by the link, thereby understood to comprise a knowledge graph and the knowledge graph representing relationships the user has with one or more skill or knowledge items; upon; See Cohen Par [0111] which specifically references microtasks and assessments relating to a working memory profile and a set of micro-tasks directed to test visuo-spatial short term memory of a user; See Cohen Par [0071] which discloses the working memory assessment microtasks, including, for example, mathematics, reading, language learning, science, history, music, etc. and therefore the knowledge graph would also relate to those topics).
Claim 4 –
Regarding Claim 4, Cohen and Duffy disclose the computer system of claim 1 in its entirety. Cohen and Duffy further disclose a computer system, wherein:
the computer memory is configured to store exercise styles comprising concrete, focused, broad, stimulative, imaginative, exploratory, personalized, conversational, real-life situation, multimedia, multi-sensory, kinesthetic that involves physical movement or gestures, collaborative with other users, adaptive, progressive, or thematic around specific themes, or narratives (See Cohen Par [0109] which discloses a variety of learning styles that can be implemented for the cognitive exercises, including modalities for presenting concepts (e.g., graphic vs. diagrammatic vs. textual vs. verbal/auditory, etc.)), wherein
the cognitive exercise computation agent is configured to control the large language model to produce generated cognitive exercises further under constraint of the exercise styles stored in the computer memory (See Cohen Par [0118] which discloses the use of a predictive model being trained across users by aggregating data users relating to any combination of task complexity increase rate preferences; problem repetition tolerance; sensory modality preferences; activity and task preferences; personality style; mental model and schema preferences; learning style preferences; working memory capabilities; problem solving strategy preferences; and/or target level of success/challenge to optimize microtasks and/or microtask structures for the current user based on said predictive models training from historical users and the current user’s user profile, albeit not recited for a large language model; See Cohen Par [0139] which discloses a user-specific graph (a neural linking structure graph) indicating the strength of the user's skill, knowledge, or usage of a mental model for all those covered in the graph along with links indicating the strength of relationships between nodes for that user, that is used in order to generate microtasks, i.e. cognitive exercises, for the user to accomplish to train said skills, knowledge, or usage of a mental model and further includes parameterization of user-preferred learning style of the cognitive exercises as described in Cohen Par [0109]; See Duffy Par [0015]-[0023] which discloses one or more cognitive tasks, i.e. exercises, that need to be completed by a user, based on varying user data, including health data, See Duffy Par [0007], [0097], & [0100]-[0102] which discloses the proposed cognitive task may include the use of the text prediction algorithm, i.e. autoregressive language model configured to generate human-like text can be executed, such as Generative Pre-trained Transformer 3 (GPT-3), as in Duffy Par [0101], to ascertain user cognitive states to determine subsequent writing, i.e. cognitive, tasks/exercises).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the disclosure of Cohen, which already discloses the use of a predictive model to generate cognitive exercises under constraints of the memory list and the personal data associated with the user, to further specifically include a large language model, as disclosed by Duffy, because this allows for automated/predictive generation of text and can thereby be used as an aide in generating text, etc. associated with future cognitive tasks to be performed by the user (See Duffy [0097] & [0100]-[0102]).
Claim 5 –
Regarding Claim 5, Cohen and Duffy disclose the computer system of claim 1 in its entirety. Cohen and Duffy further disclose a computer system, wherein:
the cognitive exercise computation agent comprises a cognitive exercise generator configured to produce the generated cognitive exercises using the large language model under constraints of the memory list and the personal data associated with the user (See Cohen Par [0118] which discloses the use of a predictive model being trained across users by aggregating data users relating to any combination of task complexity increase rate preferences; problem repetition tolerance; sensory modality preferences; activity and task preferences; personality style; mental model and schema preferences; learning style preferences; working memory capabilities; problem solving strategy preferences; and/or target level of success/challenge to optimize microtasks and/or microtask structures for the current user based on said predictive models training from historical users and the current user’s user profile, albeit not recited for a large language model; See Cohen Par [0139] which discloses a user-specific graph (a neural linking structure graph) indicating the strength of the user's skill, knowledge, or usage of a mental model for all those covered in the graph along with links indicating the strength of relationships between nodes for that user, that is used in order to generate microtasks, i.e. cognitive exercises, for the user to accomplish to train said skills, knowledge, or usage of a mental model; See Duffy Par [0015]-[0023] which discloses one or more cognitive tasks, i.e. exercises, that need to be completed by a user, based on varying user data, including health data, See Duffy Par [0007], [0097], & [0100]-[0102] which discloses the proposed cognitive task may include the use of the text prediction algorithm, i.e. autoregressive language model configured to generate human-like text can be executed, such as Generative Pre-trained Transformer 3 (GPT-3), as in Duffy Par [0101], to ascertain user cognitive states to determine subsequent writing, i.e. cognitive, tasks/exercises).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the disclosure of Cohen, which already discloses the use of a predictive model to generate cognitive exercises under constraints of the memory list and the personal data associated with the user, to further specifically include a large language model, as disclosed by Duffy, because this allows for automated/predictive generation of text and can thereby be used as an aide in generating text, etc. associated with future cognitive tasks to be performed by the user (See Duffy [0097] & [0100]-[0102]).
Claim 6 –
Regarding Claim 6, Cohen and Duffy disclose the computer system of claim 5 in its entirety. Cohen and Duffy further disclose a computer system, wherein:
the cognitive exercise computation agent comprises a cognitive exercise generation controller configured to receive the memory list and the personal data associated with the user (See Cohen Par [0013]-[0015] which discloses a user profile comprising sub-profiles, and further include microtasks, i.e. a set of goals to be learned or accomplished by the user to provide training and measurement of a set of qualities embodied in one or more sub-profiles, and further specifies that the tasks can include, in Cohen Par [0051], a set, i.e. list, of learning/assessment core activities or capabilities representing any kind of fundamental learning or fundamental activity with which a metric or set of metrics can be associated, including cognitive ability, mathematical ability, scientific ability, and accumulated knowledge that can be acted upon; See Cohen Par [0052] & [0062] which discloses a user profile including a dataset stored in a non-transitory memory comprising the memory list and personal data of the user), wherein
the cognitive exercise generation controller is configured to control the cognitive exercise generator and the large language model to produce the generated cognitive exercises under constraints of the memory list and the personal data associated with the user (See Cohen Par [0118] which discloses the use of a predictive model being trained across users by aggregating data users relating to any combination of task complexity increase rate preferences; problem repetition tolerance; sensory modality preferences; activity and task preferences; personality style; mental model and schema preferences; learning style preferences; working memory capabilities; problem solving strategy preferences; and/or target level of success/challenge to optimize microtasks and/or microtask structures for the current user based on said predictive models training from historical users and the current user’s user profile, albeit not recited for a large language model; See Cohen Par [0139] which discloses a user-specific graph (a neural linking structure graph) indicating the strength of the user's skill, knowledge, or usage of a mental model for all those covered in the graph along with links indicating the strength of relationships between nodes for that user, that is used in order to generate microtasks, i.e. cognitive exercises, for the user to accomplish to train said skills, knowledge, or usage of a mental model; See Duffy Par [0015]-[0023] which discloses one or more cognitive tasks, i.e. exercises, that need to be completed by a user, based on varying user data, including health data, See Duffy Par [0007], [0097], & [0100]-[0102] which discloses the proposed cognitive task may include the use of the text prediction algorithm, i.e. autoregressive language model configured to generate human-like text can be executed, such as Generative Pre-trained Transformer 3 (GPT-3), as in Duffy Par [0101], to ascertain user cognitive states to determine subsequent writing, i.e. cognitive, tasks/exercises).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the disclosure of Cohen, which already discloses the use of a predictive model to generate cognitive exercises under constraints of the memory list and the personal data associated with the user, to further specifically include a large language model, as disclosed by Duffy, because this allows for automated/predictive generation of text and can thereby be used as an aide in generating text, etc. associated with future cognitive tasks to be performed by the user (See Duffy [0097] & [0100]-[0102]).
Claim 7 –
Regarding Claim 7, Cohen and Duffy disclose the computer system of claim 6 in its entirety. Cohen and Duffy further disclose a computer system, wherein:
the cognitive exercise generation controller is configured to receive user responses or feedback (See Cohen Par [0068] & [0187] which discloses an input/output interface that allows the system to receive audio input, key input, touch input, pointer input, etc., and interfacing certain devices such as brain or behavior monitoring systems, eye trackers, movement trackers, speech recognizers, microphones, physical game elements, brain stimulation systems, body chemistry monitoring systems, drug delivery systems, electronic medical records, etc.; See Cohen Claim 2 which discloses receiving responses from the user through the user interface in response to the microtasks and adapting the user profile to a learning level of the user in response to user execution of the microtasks), wherein
the cognitive exercise generation controller is configured to steer the cognitive exercise generator and the large language model to produce improved cognitive exercises in response to user responses or feedback (See Cohen Claim 2 which discloses receiving responses from the user through the user interface in response to the microtasks and adapting the user profile to a learning level of the user in response to user execution of the microtasks; See Cohen Par [0118] which discloses the use of a predictive model being trained across users by aggregating data users relating to any combination of task complexity increase rate preferences; problem repetition tolerance; sensory modality preferences; activity and task preferences; personality style; mental model and schema preferences; learning style preferences; working memory capabilities; problem solving strategy preferences; and/or target level of success/challenge to optimize microtasks and/or microtask structures for the current user based on said predictive models training from historical users and the current user’s user profile, which as disclosed in Cohen Claim 2, is adapted according to responses of the user during execution of the microtasks, albeit not recited for a large language model; See Cohen Par [0139] which discloses a user-specific graph (a neural linking structure graph) indicating the strength of the user's skill, knowledge, or usage of a mental model for all those covered in the graph along with links indicating the strength of relationships between nodes for that user, that is used in order to generate microtasks, i.e. cognitive exercises, for the user to accomplish to train said skills, knowledge, or usage of a mental model; See Duffy Par [0015]-[0023] which discloses one or more cognitive tasks, i.e. exercises, that need to be completed by a user, based on varying user data, including health data, See Duffy Par [0007], [0097], & [0100]-[0102] which discloses the proposed cognitive task may include the use of the text prediction algorithm, i.e. autoregressive language model configured to generate human-like text can be executed, such as Generative Pre-trained Transformer 3 (GPT-3), as in Duffy Par [0101], to ascertain user cognitive states to determine subsequent writing, i.e. cognitive, tasks/exercises).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the disclosure of Cohen, which already discloses the use of a predictive model to generate cognitive exercises under constraints of the memory list and the personal data associated with the user, to further specifically include a large language model, as disclosed by Duffy, because this allows for automated/predictive generation of text and can thereby be used as an aide in generating text, etc. associated with future cognitive tasks to be performed by the user (See Duffy [0097] & [0100]-[0102]).
Claim 8 –
Regarding Claim 8, Cohen and Duffy disclose the computer system of claim 6 in its entirety. Cohen further discloses a computer system, wherein:
the cognitive exercise generation controller is configured to receive an example cognitive exercise (See Cohen Par [0068] & [0187] which discloses an input/output interface that allows the system to receive audio input, key input, touch input, pointer input, etc., and interfacing certain devices such as brain or behavior monitoring systems, eye trackers, movement trackers, speech recognizers, microphones, physical game elements, brain stimulation systems, body chemistry monitoring systems, drug delivery systems, electronic medical records, etc.; See Cohen Claim 2 which discloses receiving responses from the user through the user interface in response to the microtasks and adapting the user profile to a learning level of the user in response to user execution of the microtasks; See Cohen Par [0160] & [0180] which discloses the use of one or more problem templates, i.e. example cognitive exercise, and parameterizing said cognitive microtasks starting from the problem template and editing that template to produce individualized cognitive microtasks), wherein
the cognitive exercise generation controller is configured to produce the generated cognitive exercises that mimic the example cognitive exercise (See Cohen Par [0068] & [0187] which discloses an input/output interface that allows the system to receive audio input, key input, touch input, pointer input, etc., and interfacing certain devices such as brain or behavior monitoring systems, eye trackers, movement trackers, speech recognizers, microphones, physical game elements, brain stimulation systems, body chemistry monitoring systems, drug delivery systems, electronic medical records, etc.; See Cohen Claim 2 which discloses receiving responses from the user through the user interface in response to the microtasks and adapting the user profile to a learning level of the user in response to user execution of the microtasks; See Cohen Par [0160] & [0180] which discloses the use of one or more problem templates, i.e. example cognitive microtask, and parameterizing said cognitive microtask starting from the problem template; See Cohen Par [0118] which discloses the use of a predictive model being trained across users by aggregating data users relating to any combination of task complexity increase rate preferences; problem repetition tolerance; sensory modality preferences; activity and task preferences; personality style; mental model and schema preferences; learning style preferences; working memory capabilities; problem solving strategy preferences; and/or target level of success/challenge to optimize microtasks and/or microtask structures for the current user based on said predictive models training from historical users and the current user’s user profile; See Cohen Par [0139] which discloses a user-specific graph (a neural linking structure graph) indicating the strength of the user's skill, knowledge, or usage of a mental model for all those covered in the graph along with links indi