DETAILED ACTION
This non-final Office action is responsive to the application filed July 9th, 2024. Claims 1-21 are presented for examination.
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 .
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 non-statutory subject matter;
When considering subject matter eligibility under 35 U.S.C. 101, it must be determined whether the claim is directed to one of the four statutory categories of invention, i.e., process, machine, manufacture, or composition of matter. If the claim does fall within one of the statutory categories, it must then be determined whether the claim is directed to a judicial exception (i.e., law of nature, natural phenomenon, and abstract idea), and if so, it must additionally be determined whether the claim is a patent-eligible application of the exception. If an abstract idea is present in the claim, any element or combination of elements in the claim must be sufficient to ensure that the claim amounts to significantly more than the abstract idea itself.
Step 1: Independent claims 1 (method), 15 (a computer-program product comprising one or more non-transitory machine-readable storage media), and 19 (system) and dependent claims 2-14, 16-18, and 20-21, respectively, fall within at least one of the four statutory categories of 35 U.S.C. 101: (i) process; (ii) machine; (iii) manufacture; or (iv) composition of matter.
Step 2A Prong 1: The independent claims recite storing a plurality of task records, wherein each task record comprises characteristics of a task of a plurality of tasks and a task status; wherein a particular task record for a particular task comprises a particular task status value for the task status that indicates the particular task is not completed; wherein the particular task record identifies, in association with the task, a team of one or more actors of a plurality of actors and a candidate partner of a plurality of candidate partners; storing an action trigger in association with the plurality of task records, wherein the action trigger comprises: one or more conditions that are based at least in part on the task status, and a referenced API that uses a specified path to call a large language model; storing a user-modifiable template for prompts to the large language model, the user-modifiable template comprising a plurality of placeholders for a plurality of characteristics including one or more particular characteristics, the user-modifiable template further comprising modifiable static text to appear in the prompts; for the particular task record, receiving an update to the particular task status value indicating the particular task is completed, wherein the one or more particular characteristics of the particular task record comprise one or more particular values that are unique to the particular task among the plurality of tasks; based at least in part on the update, detecting that the one or more conditions are satisfied for the particular task record; in response to detecting that the one or more conditions are satisfied for the particular task record, generating a task completion narrative at least in part by: identifying the particular task record for the task completion narrative; populating the user-modifiable template to generate a particular prompt at least in part by substituting the one or more particular values of the one or more particular characteristics for one or more placeholders of the plurality of placeholders; triggering a call to the large language model using the specified path; wherein the call includes the particular prompt to the large language model comprising the one or more particular values of the one or more particular characteristics of the particular task record and the modifiable static text; receiving and storing the task completion narrative in a task completion narrative field of the particular task record; accessing the task completion narrative field to cause display of the task completion narrative to at least one actor of the plurality of actors (Certain Method of Organizing Human Activity), which are considered to be abstract ideas (See PEG 2019 and MPEP 2106.05). [Examiner notes the underlined limitations above recite the abstract idea].
The steps/functions disclosed above and in the independent claims recite the abstract idea of Certain Methods of Organizing Human Activity because the claimed limitations are monitoring the status of task records and in response to an update regarding the task status generating a task completion narrative, which is managing personal behavior. The Applicant’s claimed limitations are generating a task completion narrative, which recite the abstract idea of Organizing Human Activity.
The steps/functions disclosed above and in the independent claims recite the abstract idea of Mental Process because the claimed limitations are monitoring the status of task records and in response to an update regarding the task status generating a task completion narrative by identifying the particular task record for the task completion narrative and populating the template to generate the particular prompt by substituting placeholders for particular characteristics, which are observations, judgments, and evaluations of the human mind. Additionally, the population of the template can be performed utilizing pen and paper. The Applicant’s claimed limitations are generating a task completion narrative, which recite the abstract idea of Mental Process.
In addition, dependent claims 2-5, 9-12, 17, and 21 further narrow the abstract idea and recite further defining the particular characteristics of a task; particular values describing interactions between the team; determining that the one or more values of the one or more characteristics of the plurality of characteristics satisfy one or more data exclusion conditions; based at least in part on determining that the one or more values of the one or more characteristics satisfy the one or more data exclusion conditions, excluding the one or more values from the particular prompt even though the user-modifiable template comprises one or more placeholders for the one or more characteristics; determining whether the initial task completion narrative comprises any data characteristics that satisfy one or more data exclusion conditions; based at least in part on determining the initial task completion narrative comprises one or more data characteristics that satisfy the one or more data exclusion conditions, prompting the large language model to provide another task completion narrative that removes the one or more data characteristics from the initial task completion narrative; the particular prompt; detecting that at least one of the plurality of characteristics is in a different language than a target language of the particular prompt; and transforming the at least one of the plurality of characteristics to the target language before including the at least one of the plurality of characteristics in the particular prompt; and adding, to the particular prompt, text requesting that the task completion narrative be provided in the target language. These processes are similar to the abstract idea noted in the independent claims because they further the limitations of the independent claims which recite a certain method of organizing human activity which include managing personal behavior as well as mental processes. Accordingly, these claim elements do not serve to confer subject matter eligibility to the claims since they recite abstract ideas. Dependent claims 6-8, 13-14, 16, 18, and 20 will be discussed in Prong 2 analysis below.
Step 2A Prong 2: In this application, the above “storing a plurality of task records, wherein each task record comprises characteristics of a task of a plurality of tasks and a task status; storing an action trigger in association with the plurality of task records, wherein the action trigger comprises: one or more conditions that are based at least in part on the task status, and a referenced API that uses a specified path to call a large language model; storing a user-modifiable template for prompts to the large language model, the user-modifiable template comprising a plurality of placeholders for a plurality of characteristics including one or more particular characteristics, the user-modifiable template further comprising modifiable static text to appear in the prompts; for the particular task record, receiving an update to the particular task status value indicating the particular task is completed, wherein the one or more particular characteristics of the particular task record comprise one or more particular values that are unique to the particular task among the plurality of tasks; triggering a call to the large language model using the specified path; wherein the call includes the particular prompt to the large language model comprising the one or more particular values of the one or more particular characteristics of the particular task record and the modifiable static text; receiving and storing the task completion narrative in a task completion narrative field of the particular task record; accessing the task completion narrative field to cause display of the task completion narrative to at least one actor of the plurality of actors” steps/functions of the independent claims would not account for additional elements that integrate the judicial exception (e.g. abstract idea) into a practical application because receiving/storing data and displaying data merely add insignificant extra-solution activity and merely adds the words to apply it with the judicial exception. Also, the claimed “A computer; a referenced API; A computer-program product comprising one or more non-transitory machine-readable storage media, including stored instructions configured to cause a computing system to perform a set of actions; A system comprising: one or more processors; one or more non-transitory computer-readable media storing instructions, which, when executed by the system, cause the system to perform a set of actions” would not account for additional elements that integrate the judicial exception (e.g. abstract idea) into a practical application because the claimed structure merely adds the words to apply it with the judicial exception and mere instructions to implement an abstract idea on a computer (See PEG 2019 and MPEP 2106.05).
Independent claims 1, 15, and 19 reference “a large language model”. The “large language model” is recited so generically (no details whatsoever are provided other than that they are general purpose computing components) that they represent no more than mere instructions to apply the judicial exception on a computer. These limitations can also be viewed as nothing more than an attempt to generally link the use of the judicial exception to the technological environment of a computer. These limitations would not account for additional elements that integrate the judicial exception (e.g. abstract idea) into a practical application because the claimed structure merely adds the words to apply it with the judicial exception and mere instructions to implement an abstract idea on a computer (See PEG 2019 and MPEP 2106.05).
In addition, dependent claims 2-5, 9-12, 17, and 21 further narrow the abstract idea and dependent claims 2, 4-8, 13-14, 16, 18, and 20 additionally recite “receiving, via a user interface, a request for information relating to tasks having the one or more other particular values; wherein accessing the task completion narrative field to cause display of the task completion narrative is performed in response to the request”; “accessing one or more values of one or more characteristics of the plurality of characteristics”; “receiving an initial task completion narrative from the large language model”; “storing one or more validation rules in association with the task completion narrative field; wherein the one or more validation rules comprise one or more constraints on content that can be stored in the task completion narrative field, and wherein storing the task completion narrative in the task completion narrative field is performed based at least in part on determining that the one or more constraints are satisfied”; “accessing the task completion narrative field to cause display of the task completion narrative to at least one actor comprises triggering an email communication to at least one other team of a plurality of teams, wherein the particular task record is not modifiable by at least one actor of the plurality of actors on the at least one other team”; “accessing the task completion narrative field to cause display of the task completion narrative to at least one actor comprises triggering an email communication to at least one actor on the team”; “accessing the task completion narrative field to cause display of the task completion narrative to at least one actor comprises conditionally rendering the task completion narrative field in a user interface for viewing details about the particular task based at least in part on determining that the task completion narrative field is not blank”; “causing display of the user-modifiable template at least in part by displaying the plurality of placeholders as movable graphical objects within the modifiable static text” which do not account for additional elements that integrate the judicial exception (e.g. abstract idea) into a practical application because receiving/storing data and displaying data merely add insignificant extra-solution activity and the claimed “a computer” & “a user interface” which do not account for additional elements that integrate the judicial exception (e.g. abstract idea) into a practical application because the claimed structure merely adds the words to apply it with the judicial exception and mere instructions to implement an abstract idea on a computer (See PEG 2019 and MPEP 2106.05).
Step 2B: When analyzing the additional element(s) and/or combination of elements in the claim(s) other than the abstract idea per se the claim limitations amount(s) to no more than: a general link of the use of an abstract idea to a particular technological environment and merely amounts to the application or instructions to apply the abstract idea on a computer (See MPEP 2106.05 and PEG 2019). Further, method claims 1-14; computer program product claims 15-18; and system claims 19-21 recite “A computer; a referenced API; A computer-program product comprising one or more non-transitory machine-readable storage media, including stored instructions configured to cause a computing system to perform a set of actions; A system comprising: one or more processors; one or more non-transitory computer-readable media storing instructions, which, when executed by the system, cause the system to perform a set of actions”; however, these elements merely facilitate the claimed functions at a high level of generality and they perform conventional functions and are considered to be general purpose computer components which is supported by Applicant’s specification in Paragraphs 0158-0160 and Figures 2 & 5-7. The Applicant’s claimed additional elements are mere instructions to implement the abstract idea on a general purpose computer and generally link of the use of an abstract idea to a particular technological environment. Also, the above “storing a plurality of task records, wherein each task record comprises characteristics of a task of a plurality of tasks and a task status; storing an action trigger in association with the plurality of task records, wherein the action trigger comprises: one or more conditions that are based at least in part on the task status, and a referenced API that uses a specified path to call a large language model; storing a user-modifiable template for prompts to the large language model, the user-modifiable template comprising a plurality of placeholders for a plurality of characteristics including one or more particular characteristics, the user-modifiable template further comprising modifiable static text to appear in the prompts; for the particular task record, receiving an update to the particular task status value indicating the particular task is completed, wherein the one or more particular characteristics of the particular task record comprise one or more particular values that are unique to the particular task among the plurality of tasks; triggering a call to the large language model using the specified path; wherein the call includes the particular prompt to the large language model comprising the one or more particular values of the one or more particular characteristics of the particular task record and the modifiable static text; receiving and storing the task completion narrative in a task completion narrative field of the particular task record; accessing the task completion narrative field to cause display of the task completion narrative to at least one actor of the plurality of actors” steps/functions of the independent claims would not account for significantly more than the abstract idea because receiving data and displaying/presenting data (See MPEP 2106.05) have been identified as well-known, routine, and conventional steps/functions to one of ordinary skill in the art. When viewed as a whole, these additional claim element(s) do not provide meaningful limitation(s) to transform the abstract idea into a patent eligible application of the abstract idea such that the claim(s) amounts to significantly more than the abstract idea itself.
Next, when the “large language model” is evaluated as an additional element, this feature is recited at a high level of generality and encompasses well-understood, routine, and conventional prior art activity. See, e.g., Reza et al., US 2023/0237277 A1, noting in paragraph [0025] that “As discussed herein, most conventional language models follow a general training approach of pre-training and fine-tuning the model.” Further, paragraph [0025] states, “Conventional large language models pre-trained with prompting demonstrate the ability to infer with the help of zero shot and few shot learning and can handle a large set of downstream tasks like Q&A, sentiment analysis, NER, etc.” See also, O’Kelly et al. US Pat. No. 11,861,321 B1, noting in paragraph [0034] that “Large language models, while powerful, have a number of drawbacks when used for technical, domain-specific tasks. When using conventional techniques, large language models often invent “facts” that are actually not true.” Accordingly, the use of large language modeling does not add significantly more to the claim.
In addition, claims 2-5, 9-12, 17, and 21 further narrow the abstract idea identified in the independent claims. The Examiner notes that the dependent claims merely further define the data being analyzed and how the data is being analyzed. Similarly, claims 2, 4-8, 13-14, 16, 18, and 20 additionally recite “receiving, via a user interface, a request for information relating to tasks having the one or more other particular values; wherein accessing the task completion narrative field to cause display of the task completion narrative is performed in response to the request”; “accessing one or more values of one or more characteristics of the plurality of characteristics”; “receiving an initial task completion narrative from the large language model”; “storing one or more validation rules in association with the task completion narrative field; wherein the one or more validation rules comprise one or more constraints on content that can be stored in the task completion narrative field, and wherein storing the task completion narrative in the task completion narrative field is performed based at least in part on determining that the one or more constraints are satisfied”; “accessing the task completion narrative field to cause display of the task completion narrative to at least one actor comprises triggering an email communication to at least one other team of a plurality of teams, wherein the particular task record is not modifiable by at least one actor of the plurality of actors on the at least one other team”; “accessing the task completion narrative field to cause display of the task completion narrative to at least one actor comprises triggering an email communication to at least one actor on the team”; “accessing the task completion narrative field to cause display of the task completion narrative to at least one actor comprises conditionally rendering the task completion narrative field in a user interface for viewing details about the particular task based at least in part on determining that the task completion narrative field is not blank”; “causing display of the user-modifiable template at least in part by displaying the plurality of placeholders as movable graphical objects within the modifiable static text” which do not account for additional elements that amount to significantly more than the abstract idea because receiving data and displaying/presenting data (See MPEP 2106.05) have been identified as well-known, routine, and conventional steps/functions to one of ordinary skill in the art and the claimed “a computer” and “user interface” which do not account for additional elements that amount to significantly more than the abstract idea because the claimed structure merely amounts to the application or instructions to apply the abstract idea on a computer and does not move beyond a general link of the use of an abstract idea to a particular technological environment (See MPEP 2106.05). The additional limitations of the independent and dependent claim(s) when considered individually and as an ordered combination do not amount to significantly more than the abstract idea. The examiner has considered the dependent claims in a full analysis including the additional limitations individually and in combination as analyzed in the independent claim(s). Therefore, the claim(s) are rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
The claimed “A computer; a referenced API; A computer-program product comprising one or more non-transitory machine-readable storage media, including stored instructions configured to cause a computing system to perform a set of actions; A system comprising: one or more processors; one or more non-transitory computer-readable media storing instructions, which, when executed by the system, cause the system to perform a set of actions” are recited so generically (no details whatsoever are provided other than that they are general purpose computing components and regular office supplies) that they represent no more than mere instructions to apply the judicial exception on a computer. These limitations can also be viewed as nothing more than an attempt to generally link the use of the judicial exception to the technological environment of a computer. Even when viewed in combination, the additional elements in the claims do no more than use the computer components as a tool. There is no change to the computers and other technology that is recited in the claim, and thus the claims do not improve computer functionality or other technology (See PEG 2019).
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(s) 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.
Claim(s) 1-3, 6-10, and 13-21 is/are rejected under 35 U.S.C. 103 as being unpatentable over Helvik (U.S 2024/0403829 A1) in view of Bathula (U.S 2025/0245664 A1) .
Claims 1, 15, and 19
Regarding Claim 1, Helvik discloses the following:
A computer-implemented method comprising [see at least Paragraph 0024 for reference to the technology described herein makes use of the project context by building a project-context oriented task description; Paragraph 0079 for reference to the method for providing task insights can be performed by a computer device; Figures 5-7 for reference to the method for facilitating generation of task insights]
storing a plurality of task records, wherein each task record comprises characteristics of a task of a plurality of tasks and a task status [see at least Paragraph 0023 for reference to a digital task record includes, among other features, a task description, to be completed date, a completed date, and an associated user or users; Paragraph 0054 for reference to digital task record may include a task identification, task description, task title, task scheduled date, task completion data, task status (e.g., pending, in progress, or complete); Paragraph 0099 for reference to digital task record may reside in computer storage and be associated with the project record]
wherein a particular task record for a particular task comprises a particular task status value for the task status that indicates the particular task is not completed [see at least Paragraph 0054 for reference to digital task record may include a task identification, task description, task title, task scheduled date, task completion data, task status (e.g., pending, in progress, or complete); Paragraph 0067 for reference to any tasks with a status or state change (within a threshold time or number of tasks) may be identified]
wherein the particular task record identifies, in association with the task, a team of one or more actors of a plurality of actors and a candidate partner of a plurality of candidate partners [see at least Paragraph 0023 for reference to a digital task record includes, among other features, a task description, to be completed date, a completed date, and an associated user or users; Paragraph 0026 for reference to task-insight recommendation system may consider whether a potential collaborator with relevant experience has worked with the user associated with the active task; Examiner notes the associated user as analogous to the ‘plurality of actors’ and the potential collaborator as analogous to the ‘candidate partners’]
storing an action trigger in association with the plurality of task records, wherein the action trigger comprises: one or more conditions that are based at least in part on the task status [see at least Paragraph 0080 for reference to the task insight request being generated in response to various triggers including an explicit user instruction; Paragraph 0080 for reference to the type of task generated by an implicit trigger may depend on the status of the active task, the role of the user associated with the task, and other factors]
for the particular task record, receiving an update to the particular task status value indicating the particular task is completed, wherein the one or more particular characteristics of the particular task record comprise one or more particular values that are unique to the particular task among the plurality of tasks [see at least Paragraph 0067 for reference to any tasks with a status or state change (within a threshold time or number of tasks) may be identified; Paragraph 0067 for reference to a task with any modification may be identified (e.g., a modification within a threshold time, such as the past week; a number of modifications, such as more than one modification; modifications by more than one individual or entity; etc.); Paragraph 0067 for reference to a status change, state change, and/or modification may be used herein to refer to any alterations associated with a task, such as, for example, an edit to the task, a comment associated with the task, a response associated with the task, a view associated with the task, etc.; Paragraph 0067 for reference to any state, status, or modification change may be identified in any number of ways, such as by accessing a data source containing such information]
based at least in part on the update, detecting that the one or more conditions are satisfied for the particular task record [see at least Paragraph 0067 for reference to any tasks with a status or state change (within a threshold time or number of tasks) may be identified; Paragraph 0067 for reference to a task with any modification may be identified (e.g., a modification within a threshold time, such as the past week; a number of modifications, such as more than one modification; modifications by more than one individual or entity; etc.); Examiner notes that ‘within a threshold time’ is analogous to the ‘satisfying of conditions’]
in response to detecting that the one or more conditions are satisfied for the particular task record, generating a task completion narrative at least in part by: identifying the particular task record for the task completion narrative [see at least Paragraph 0068 for reference to the task similarity generator identifying similar tasks in response to a detected state change; Paragraph 0068 for reference to the task similarity generator including a project-oriented task description generator, a language model, and similarity logic wherein the project-oriented task description generator builds a project-context oriented task description; Paragraph 0068 for reference to project-oriented task description includes the task description of the active task along with additional descriptions for other elements in the project]
triggering the large language model wherein the large language model comprising the one or more particular values of the one or more particular characteristics of the particular task record and the modifiable static text [see at least Paragraph 0070 for reference to the language model uses the project-oriented task description to generate an embedding that represents a meaning of the project-oriented task description in a data structure, such as a vector; Figure 5 and related text regarding item 540; Figure 7 and related text regarding item 740]
receiving and storing the task completion narrative in a task completion narrative field of the particular task record [see at least Paragraph 0024 for reference to all task descriptions in the direct hierarchy above an active task are included within the project-oriented task description; Paragraph 0074 for reference to the task insight, which may identify one or more potential collaborators for an active task, is then provided to a user associated with the task insight request]
accessing the task completion narrative field to cause display of the task completion narrative to at least one actor of the plurality of actors [see at least Paragraph 0074 for reference to the task insight, which may identify one or more potential collaborators for an active task, is then provided to a user associated with the task insight request; Paragraph 0074 for reference to the task insight may include an interface element that allows the user to assign or initiate assignment of the active task to a potential collaborator or working group identified in the task insight; Paragraph 0075 for reference to task insight may also display information used to select a potential collaborator]
While Helvik discloses the limitations above, it does not disclose a referenced API that uses a specified path to call a large language model; storing a user-modifiable template for prompts to the large language model, the user-modifiable template comprising a plurality of placeholders for a plurality of characteristics including one or more particular characteristics, the user-modifiable template further comprising modifiable static text to appear in the prompts; populating the user-modifiable template to generate a particular prompt at least in part by substituting the one or more particular values of the one or more particular characteristics for one or more placeholders of the plurality of placeholders; and triggering a call to the large language model using the specified path; wherein the call includes the particular prompt to the large language model comprising the one or more particular values of the one or more particular characteristics of the particular task record and the modifiable static text.
However, Bathula discloses the following:
a referenced API that uses a specified path to call a large language model [see at least Paragraph 0050 for reference to external LLM service may function similarly to follow instructions to generate and/or validate the narrative, and may be accessible via APIs and called through API calls]
storing a user-modifiable template for prompts to the large language model, the user-modifiable template comprising a plurality of placeholders for a plurality of characteristics including one or more particular characteristics, the user-modifiable template further comprising modifiable static text to appear in the prompts [see at least Paragraph 0055 for reference to prompts may correspond to text or other input that contains information and instructions to a generative AI model or LLM of internal LLM service or external LLM service wherein the prompts may be configured to obtain a desired output in the form of a response (e.g., text or other output data) to the information and instructions; Paragraph 0055 for reference to prompt templates being stored to prompt database; Figure 2 and related text regarding item 214 ‘prompt database’]
populating the user-modifiable template to generate a particular prompt at least in part by substituting the one or more particular values of the one or more particular characteristics for one or more placeholders of the plurality of placeholders [see at least Paragraph 0054 for reference to narrative generation service may then identify and load the appropriate generative AI and/or LLM prompt templates into local memory from prompt database, as well as create updated prompts for the generative AI and/or LLM of internal LLM service or external LLM service; Paragraph 0057 for reference to prompts from the templates may be used to extract details corresponding to different sections of the narrative, such as subject information, filings and impacted financial institutions, summary and details of the suspicious or fraudulent activity, and other narrative information]
triggering a call to the large language model using the specified path; wherein the call includes the particular prompt to the large language model comprising the one or more particular values of the one or more particular characteristics of the particular task record and the modifiable static text [see at least Paragraph 0050 for reference to external LLM service may function similarly to follow instructions to generate and/or validate the narrative, and may be accessible via APIs and called through API calls; Paragraph 0059 for reference to the latest prompt templates are queried from a database, such as an Amazon Web Services (AWS) Dynamo® database in a cloud environment, for the form type for the SAR (e.g., the corresponding templates for the SAR) and the customer tenant for the customer ID; Paragraph 0059 for reference to if the prompting strategy “few-shot examples” is used, for each prompt template the examples may be read from an online or cloud storage through running a fetch from the storage based on the prompt template identifiers or other information]
Before the effective filing date, it would have been obvious to one of ordinary skill in the art to modify the language model method of Helvik to include the calling of API and prompt template modification of Bathula. Doing so would provide faster, more efficient, and more precise ML model evaluation and processing of SARs and SAR narratives, as stated by Bathula (Paragraph 0027).
Regarding claims 15 and 19, the claims recite limitations already addressed by the rejection of claim 1. Regarding claim 15, Helvik teaches a computer-program product comprising one or more non-transitory machine-readable storage media, including stored instructions configured to cause a computing system to perform a set of actions [Paragraphs 0114-115]. Regarding claim 19, Helvik teaches a system comprising: one or more processors; one or more non-transitory computer-readable media storing instructions, which, when executed by the system, cause the system to perform a set of actions [Paragraph 00112-116 & Figure 8]. Therefore, claims 15 and 19 are rejected as being unpatentable over the combination of Helvik and Bathula.
Claim 2
While the combination of Helvik and Bathula disclose the limitations above, regarding Claim 2, Helvik discloses the following:
wherein the one or more particular characteristics of the particular task record comprise one or more other particular values that are shared by one or more other tasks of the plurality of tasks [see at least Paragraph 0023 for reference to a digital task record includes, among other features, a task description, to be completed date, a completed date, and an associated user or users; Paragraph 0054 for reference to digital task record may include a task identification, task description, task title, task scheduled date, task completion data, task status (e.g., pending, in progress, or complete); Paragraph 0099 for reference to digital task record may reside in computer storage and be associated with the project record]
the computer-implemented method further comprising receiving, via a user interface, a request for information relating to tasks having the one or more other particular values [see at least Paragraph 0042 for reference to a user may request a task insight(s) related to a task(s); Paragraph 0047 for reference to the task insight service may receive insight requests for determining task insights via the user device (or other device) wherein insight requests generally refer to any request or indication to determine and/or provide task insights, such as the identification of potential collaborators with experience relevant to completing an active task; Paragraph 0047 for reference to an insight request may include a task identifier indicating a particular task for which a task insight is desired]
wherein accessing the task completion narrative field to cause display of the task completion narrative is performed in response to the request [see at least the task insight, which may identify one or more potential collaborators for an active task, is then provided to a user associated with the task insight request; Paragraph 0074 for reference to the task insight may include an interface element that allows the user to assign or initiate assignment of the active task to a potential collaborator or working group identified in the task insight; Paragraph 0075 for reference to task insight may also display information used to select a potential collaborator]
Claim 3
While the combination of Helvik and Bathula disclose the limitations above, regarding Claim 3, Helvik discloses the following:
wherein the one or more particular values describe one or more interactions between the team and the candidate partner in natural language text, wherein the modifiable static text comprises one or more section headers of one or more blank sections to be completed by the large language model [see at least Paragraph 0028 for reference to each time a user issues a query, for example, the contents or payload of the query is typically supplemented with header information or other metadata within a packet in TCP/IP and other protocol networks; Paragraph 0033 for reference to task embedding is a numerical representation of the project-oriented task description generated by a language model; Paragraph 0070 for reference to the language model taking the form of a machine learning model]
the computer-implemented method further comprising: generating, by the large language model, one or more summaries of the one or more interactions to address the one or more section headers, and including the one or more summaries in the task completion narrative to fill in the one or more blank sections [see at least Paragraph 0070 for reference to the language model uses the project-oriented task description to generate an embedding that represents a meaning of the project-oriented task description in a data structure, such as a vector; Figure 5 and related text regarding item 540; Figure 7 and related text regarding item 740]
Claim 6
While the combination of Helvik and Bathula disclose the limitations above, regarding Claim 6, Helvik discloses the following:
further comprising storing one or more validation rules in association with the task completion narrative field [see at least Paragraph 0058 for reference to insight logic may comprise a series of rules that return a desired insight]
wherein the one or more validation rules comprise one or more constraints on content that can be stored in the task completion narrative field, and wherein storing the task completion narrative in the task completion narrative field is performed based at least in part on determining that the one or more constraints are satisfied [see at least Paragraph 0058 for reference to the insight logic may receive the ask insight request and generate insights about the user associated with the insight request; Paragraph 0058 for reference to a relational distance between a user assigned to an active task and a potential collaborator to be identified in a task insight as having experience working a task that is similar to the active task]
Claim 7
While the combination of Helvik and Bathula disclose the limitations above, regarding Claim 7, Helvik discloses the following:
wherein accessing the task completion narrative field to cause display of the task completion narrative to at least one actor comprises triggering an email communication to at least one other team of a plurality of teams, wherein the particular task record is not modifiable by at least one actor of the plurality of actors on the at least one other team [see at least Paragraph 0056 for reference to potential collaborator may then receive a request to accept responsibility for the task wherein the request may be an email, text, instant message, system notification, application (e.g., project management application) notification, or the like; Paragraph 0074 for reference to the task insight, which may identify one or more potential collaborators for an active task, is then provided to a user associated with the task insight request; Paragraph 0074 for reference to the task insight may include an interface element that allows the user to assign or initiate assignment of the active task to a potential collaborator or working group identified in the task insight; Paragraph 0075 for reference to task insight may also display information used to select a potential collaborator]
Claims 8, 16, and 20
While the combination of Helvik and Bathula disclose the limitations above, regarding Claim 8, Helvik discloses the following:
wherein accessing the task completion narrative field to cause display of the task completion narrative to at least one actor comprises triggering an email communication to at least one actor on the team, wherein the email communication comprises an interactive option which, when selected, triggers one or more email communications to at least one other team of a plurality of teams, wherein the particular task record is modifiable by the at least one actor on the team but is not modifiable by at least one other actor of the plurality of actors on the at least one other team [see at least Paragraph 0056 for reference to potential collaborator may then receive a request to accept responsibility for the task wherein the request may be an email, text, instant message, system notification, application (e.g., project management application) notification, or the like; Paragraph 0056 for reference to if the potential collaborator agrees to accept responsibility for the active task through the interface that provided the request (or by navigating to an interface associated with the task management application) then a task record for the task may be updated to show the active task is assigned to the potential collaborator; Paragraph 0074 for reference to the task insight, which may identify one or more potential collaborators for an active task, is then provided to a user associated with the task insight request; Paragraph 0074 for reference to the task insight may include an interface element that allows the user to assign or initiate assignment of the active task to a potential collaborator or working group identified in the task insight; Paragraph 0075 for reference to task insight may also display information used to select a potential collaborator]
Regarding claims 16 and 20, the claims recite limitations already addressed by the rejection of claim 8.
Claim 9
While the combination of Helvik and Bathula disclose the limitations above, Helvik does not disclose wherein the particular prompt includes an example of another task completion narrative that is based on other information that does not have the one or more particular values for the one or more particular characteristics but has one or more other values for the one or more particular characteristics.
Regarding Claim 9, Bathula discloses the following:
wherein the particular prompt includes an example of another task completion narrative that is based on other information that does not have the one or more particular values for the one or more particular characteristics but has one or more other values for the one or more particular characteristics [see at least Paragraph 0057 for reference to the computing service and framework for narrative generation service 212 may the identify and load the appropriate validation prompt templates into local memory from prompt database 214, which may be used for prompts to the generative AI and/or other LLM of internal LLM service 216 a or external LLM service 216 b to validate the narrative; Paragraph 0057 for reference to prompts may then be provided as input to the generative AI and/or LLM of internal LLM service 216 a or external LLM service 216 b, which may perform a comparison of the extracted details (e.g., in JSON format with the input for the prompts also in the JSON format)]
Before the effective filing date, it would have been obvious to one of ordinary skill in the art to modify the method of Helvik to include the prompt template modification of Bathula. Doing so would provide faster, more efficient, and more precise ML model evaluation and processing of SARs and SAR narratives, as stated by Bathula (Paragraph 0027).
Claims 10, 17, and 21
While the combination of Helvik and Bathula disclose the limitations above, regarding Claim 10, Helvik discloses the following:
wherein the one or more particular characteristics of the particular task record comprise one or more other particular values that are shared by one or more other tasks of the plurality of tasks [see at least Paragraph 0023 for reference to a digital task record includes, among other features, a task description, to be completed date, a completed date, and an associated user or users; Paragraph 0054 for reference to digital task record may include a task identification, task description, task title, task scheduled date, task completion data, task status (e.g., pending, in progress, or complete); Paragraph 0099 for reference to digital task record may reside in computer storage and be associated with the project record]
the computer-implemented method further comprising summarizing a plurality of task completion narrative fields for a plurality of tasks sharing a particular value of the one or more other particular values at least in part by prompting the large language model with the plurality of task completion narrative fields and other modifiable static text [see at least Paragraph 0070 for reference to the language model uses the project-oriented task description to generate an embedding that represents a meaning of the project-oriented task description in a data structure, such as a vector; Figure 5 and related text regarding item 540; Figure 7 and related text regarding item 740]
Regarding claims 17 and 21, the claims recite limitations already addressed by the rejection of claim 10.
Claim 13
While the combination of Helvik and Bathula disclose the limitations above, regarding Claim 13, Helvik discloses the following:
wherein accessing the task completion narrative field to cause display of the task completion narrative to at least one actor comprises conditionally rendering the task completion narrative field in a user interface for viewing details about the particular task based at least in part on determining that the task completion narrative field is not blank [see at least Paragraph 0074 for reference to the task insight, which may identify one or more potential collaborators for an active task, is then provided to a user associated with the task insight request; Paragraph 0074 for reference to the task insight request may be generated without user input or in response to a request provided through a user interface, such as may be provided by a project management application; Paragraph 0074 for reference to the task insight may include an interface element that allows the user to assign or initiate assignment of the active task to a potential collaborator or working group identified in the task insight; Paragraph 0075 for reference to task insight may also display information used to select a potential collaborator]
Claims 14 and 18
While the combination of Helvik and Bathula disclose the limitations above, Helvik does not disclose causing display of the user-modifiable template at least in part by displaying the plurality of placeholders as movable graphical objects within the modifiable static text.
Regarding Claim 14, Bathula discloses the following:
causing display of the user-modifiable template at least in part by displaying the plurality of placeholders as movable graphical objects within the modifiable static text [see at least Paragraph 0051 for reference to client portal 222 may initiate the process of narrative generation and validation and display the generated narrative and validation messages wherein this may include one or more interactable, clickable, or selectable buttons or other interface elements]
Before the effective filing date, it would have been obvious to one of ordinary skill in the art to modify the method of Helvik to include the prompt template display of Bathula. Doing so would provide faster, more efficient, and more precise ML model evaluation and processing of SARs and SAR narratives, as stated by Bathula (Paragraph 0027).
Claim(s) 4-5 and 11-12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Helvik (U.S 2024/0403829 A1) in view of Bathula (U.S 2025/0245664 A1), as applied in claim 1, in view of Chandrasekaran (U.S 2024/0320476 A1).
Claim 4
While the combination of Helvik and Bathula disclose the limitations above, regarding Claim 4, Helvik discloses the following:
accessing one or more values of one or more characteristics of the plurality of characteristics [see at least Paragraph 0023 for reference to a digital task record includes, among other features, a task description, to be completed date, a completed date, and an associated user or users; Paragraph 0054 for reference to digital task record may include a task identification, task description, task title, task scheduled date, task completion data, task status (e.g., pending, in progress, or complete); Paragraph 0099 for reference to digital task record may reside in computer storage and be associated with the project record]
While Helvik discloses the limitations above, it does not disclose the following determining that the one or more values of the one or more characteristics of the plurality of characteristics satisfy one or more data exclusion conditions; and based at least in part on determining that the one or more values of the one or more characteristics satisfy the one or more data exclusion conditions, excluding the one or more values from the particular prompt even though the user-modifiable template comprises one or more placeholders for the one or more characteristics.
However, Chandrasekaran discloses the following:
determining that the one or more values of the one or more characteristics of the plurality of characteristics satisfy one or more data exclusion conditions [see at least Paragraph 0064 for reference to a toxicity detection unit for detecting the presence of toxicity in the enriched prompt wherein the term “toxicity” is intended mean language present within a prompt that is determined to be harmful, offensive, or hurtful to others, and can include insults, threats, and derogatory remarks; Paragraph 0064 for reference to toxicity detection classifier unit can be configured to discern and classify varying degrees and types of toxic content, such as offensive language, hate speech, personal attacks, stereotyping, and bullying]
based at least in part on determining that the one or more values of the one or more characteristics satisfy the one or more data exclusion conditions, excluding the one or more values from the particular prompt even though the user-modifiable template comprises one or more placeholders for the one or more characteristics [see at least Paragraph 0046 for reference to prompt enrichment unit enriches the prompts by manipulating, such as ingesting, integrating, adding or modifying, one or more attributes associated with the prompts so as to modify, enrich and curate the prompts; Paragraph 0061 for reference to a prompt language filtering unit for filtering the language of the enriched prompt to remove or modify rhetorical or unwanted language that is present within the enriched prompt]
Before the effective filing date, it would have been obvious to one of ordinary skill in the art to modify the method of Helvik to include the determination of exclusion characteristics of Chandrasekaran. Doing so can increase the ease in which a subsequent user can determine that the prompt is a relevant and/or effective prompt for that subsequent user's intended purpose, as stated by Chandrasekaran (Paragraph 0008).
Claim 5
While the combination of Helvik and Bathula disclose the limitations above, regarding Claim 5, Helvik discloses the following:
wherein generating the task completion narrative further comprises: receiving an initial task completion narrative from the large language model [see at least Paragraph 0068 for reference to the task similarity generator identifying similar tasks in response to a detected state change; Paragraph 0068 for reference to the task similarity generator including a project-oriented task description generator, a language model, and similarity logic wherein the project-oriented task description generator builds a project-context oriented task description; Paragraph 0068 for reference to project-oriented task description includes the task description of the active task along with additional descriptions for other elements in the project]
While Helvik discloses the limitations above, it does not disclose determining whether the initial task completion narrative comprises any data characteristics that satisfy one or more data exclusion conditions; and based at least in part on determining the initial task completion narrative comprises one or more data characteristics that satisfy the one or more data exclusion conditions, prompting the large language model to provide another task completion narrative that removes the one or more data characteristics from the initial task completion narrative.
However, Chandrasekaran discloses the following:
determining whether the initial task completion narrative comprises any data characteristics that satisfy one or more data exclusion conditions [see at least Paragraph 0064 for reference to a toxicity detection unit for detecting the presence of toxicity in the enriched prompt wherein the term “toxicity” is intended mean language present within a prompt that is determined to be harmful, offensive, or hurtful to others, and can include insults, threats, and derogatory remarks; Paragraph 0064 for reference to toxicity detection classifier unit can be configured to discern and classify varying degrees and types of toxic content, such as offensive language, hate speech, personal attacks, stereotyping, and bullying]
based at least in part on determining the initial task completion narrative comprises one or more data characteristics that satisfy the one or more data exclusion conditions, prompting the large language model to provide another task completion narrative that removes the one or more data characteristics from the initial task completion narrative [see at least Paragraph 0046 for reference to prompt enrichment unit enriches the prompts by manipulating, such as ingesting, integrating, adding or modifying, one or more attributes associated with the prompts so as to modify, enrich and curate the prompts; Paragraph 0061 for reference to a prompt language filtering unit for filtering the language of the enriched prompt to remove or modify rhetorical or unwanted language that is present within the enriched prompt]
Before the effective filing date, it would have been obvious to one of ordinary skill in the art to modify the method of Helvik to include the determination of exclusion characteristics of Chandrasekaran. Doing so can increase the ease in which a subsequent user can determine that the prompt is a relevant and/or effective prompt for that subsequent user's intended purpose, as stated by Chandrasekaran (Paragraph 0008).
Claim 11
While the combination of Helvik and Bathula disclose the limitations above, they do not disclose detecting that at least one of the plurality of characteristics is in a different language than a target language of the particular prompt; and transforming the at least one of the plurality of characteristics to the target language before including the at least one of the plurality of characteristics in the particular prompt.
Regarding Claim 11, Chandrasekaran discloses the following:
detecting that at least one of the plurality of characteristics is in a different language than a target language of the particular prompt [see at least Paragraph 0021 for reference to the present invention can be configured to identify an author of the ontology prompt by analyzing multiple different language related prompt attributes of the ontology prompt and then determining the author thereof; Paragraph 0025 for reference to present invention can include detecting the presence of propaganda within the language of the enriched prompt, and generating a propaganda score that is indicative of a degree of likelihood that the enriched prompt includes propaganda; and/or detecting the presence of polarity in the enriched prompt; Paragraph 0061 for reference to prompt filtering unit can filter and detect for the presence of certain language within the enriched prompt and determine if the language in the enriched prompt previously existed]
transforming the at least one of the plurality of characteristics to the target language before including the at least one of the plurality of characteristics in the particular prompt [see at least Paragraph 0044 for reference to transformer model is able to generate new text by attending to different parts of the input text prompt and learning the relationships between the parts; Paragraph 0061 for reference to the propaganda detection unit 70 can employ a propaganda transformer 70A having a transformer architecture that employs a neural network to process the enriched prompt 50 and to generate an output; Paragraph 0061 for reference to output of the propaganda transformer within the context of the system 10 is a processed version of the classified, enriched, and catalogued prompts that have been analyzed for elements indicative of propaganda; Paragraph 0061 for reference to processed data is aimed at highlighting the aspects of the prompt that potentially align with propaganda (e.g., information aimed at influencing or manipulating opinions or promoting a particular agenda or ideology). Furthermore, the output may also include categorization or tagging of the identified propaganda elements, providing a detailed breakdown of the types of propaganda detected (e.g., emotional manipulation, biased language, oversimplification, etc.)]
Before the effective filing date, it would have been obvious to one of ordinary skill in the art to modify the method of Helvik to include the detection and transformation of language characteristics of Chandrasekaran. Doing so can increase the ease in which a subsequent user can determine that the prompt is a relevant and/or effective prompt for that subsequent user's intended purpose, as stated by Chandrasekaran (Paragraph 0008).
Claim 12
While the combination of Helvik and Bathula disclose the limitations above, they do not disclose detecting that at least one of the plurality of characteristics may be in a different language than a target language of the particular prompt; and adding, to the particular prompt, text requesting that the task completion narrative be provided in the target language.
Regarding Claim 12, Chandrasekaran discloses the following:
detecting that at least one of the plurality of characteristics may be in a different language than a target language of the particular prompt [see at least Paragraph 0021 for reference to the present invention can be configured to identify an author of the ontology prompt by analyzing multiple different language related prompt attributes of the ontology prompt and then determining the author thereof; Paragraph 0025 for reference to present invention can include detecting the presence of propaganda within the language of the enriched prompt, and generating a propaganda score that is indicative of a degree of likelihood that the enriched prompt includes propaganda; and/or detecting the presence of polarity in the enriched prompt; Paragraph 0061 for reference to prompt filtering unit can filter and detect for the presence of certain language within the enriched prompt and determine if the language in the enriched prompt previously existed]
adding, to the particular prompt, text requesting that the task completion narrative be provided in the target language [see at least Paragraph 0046 for reference to the prompt enrichment unit enriches the prompts by manipulating, such as ingesting, integrating, adding or modifying, one or more attributes associated with the prompts so as to modify, enrich and curate the prompts; Paragraph 0055 for reference to this process can include dynamically adding contextual information that enhances the prompt's relevance and utility for generating specific and accurate outputs]
Before the effective filing date, it would have been obvious to one of ordinary skill in the art to modify the method of Helvik to include the detection and addition of language characteristics of Chandrasekaran. Doing so can increase the ease in which a subsequent user can determine that the prompt is a relevant and/or effective prompt for that subsequent user's intended purpose, as stated by Chandrasekaran (Paragraph 0008).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Reynolds, Laria, and Kyle McDonell. "Prompt programming for large language models: Beyond the few-shot paradigm." Extended abstracts of the 2021 CHI conference on human factors in computing systems. 2021.
DOCUMENT ID
INVENTOR(S)
TITLE
U.S 2025/0045308 A1
Rogynskyy et al.
Systems and methods for automatic generation of electronic activity content for record objects using machine learning architectures
US 2025/0078969 A1
Low et al.
SYSTEMS AND METHODS FOR AUTOMATED EVIDENCE GENERATION
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KRISTIN ELIZABETH GAVIN whose telephone number is (571)270-7019. The examiner can normally be reached M-F 7:30-4:30 PM EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Jerry O'Connor can be reached at 571-272-6787. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/KRISTIN E GAVIN/Primary Examiner, Art Unit 3624