DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This non-final office action is in response to the application filed 11 April 2024.
Claims 1-20 are pending. Claims 1, 15, and 18 are independent claims.
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 8 October 2025 and 24 August 2026 are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements are being considered by the examiner.
Drawings
The examiner accepts the drawings filed 11 April 2024.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1:
According to Step 1 of the two Step analysis, claims 1-14 are directed toward a system (machine). Claims 15-17 are directed toward a method (process). Claims 18-20 are directed toward a non-transitory computer-readable medium (manufacture). Therefore, each of these claims falls within one of the four statutory categories.
Claim 1:
Step 2A, Prong 1:
The claim recites:
selecting a set of functions from among a plurality of functions supported by a digital assistant (mental process; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses a judgement to select a set of functions from among a plurality of functions)
invoking… the first function to obtain the first output data… based on inclusion of the at least one function dependency in the prompt data (mental process; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses an evaluation of a first function to obtain first output data based on function dependency in the prompt data)
invoking… the second function to obtain second output data (mental process; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses an evaluation of a second function to obtain first output data based on function dependency in the prompt data)
Step 2A, Prong 2:
The judicial exception is not integrated into a practical application.
The claim recites the additional elements:
at least one memory that stores instructions
one or more processors configured by the instructions to perform operations
The additional elements are recited at a high-level of generality such that it amounts to no more than mere instructions to apply the exception using a generic computer component (See MPEP 2106.05(f)).
The claim recites the additional element:
providing prompt data to a generative machine learning model, the prompt data comprising user input and function data, the user input being received from a user via a user interface of the digital assistant, and the function data identifying the set of functions and comprising dependency data that includes at least one function dependency between a first function and a second function of the set of functions
The additional element amounts to a data gathering step recited at a high level of generality and amounts to extra-solution activity of receiving data i.e. pre-solution activity of gathering data for use in the claimed process. The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
The claim recites the additional elements:
a first response from the generative machine learning model… the first response identifying the first function and being provided by the generative machine learning model
a second response from the generative machine learning model received after updating the prompt data to include the first output data
The generation of responses by a generative machine learning model are recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f))
The claim recite the additional element:
causing presentation of at least one of the first output data or the second output data in the user interface associated with the digital assistant
These limitations amount to extra solution activity because it is a mere nominal or tangential addition to the claim, amounting to mere data output (see MPEP 2106.05(g)). The courts have similarly found limitations directed to displaying a result, recited at a high level of generality, to be well-understood, routine, and conventional. See (MPEP 2106.05(d)(II), "presenting offers and gathering statistics.", “determining an estimated outcome and setting a price”)
Accordingly, at Step 2A, prong two, the additional elements individually or in combination do no integrate the judicial exception into a practical application.
Step 2B:
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception.
The claim recites the additional elements:
at least one memory that stores instructions
one or more processors configured by the instructions to perform operations
The additional elements are recited at a high-level of generality such that it amounts to no more than mere instructions to apply the exception using a generic computer component (See MPEP 2106.05(f)).
The claim recites the additional element:
providing prompt data to a generative machine learning model, the prompt data comprising user input and function data, the user input being received from a user via a user interface of the digital assistant, and the function data identifying the set of functions and comprising dependency data that includes at least one function dependency between a first function and a second function of the set of functions
The additional element amounts to a data gathering step recited at a high level of generality and amounts to extra-solution activity of receiving data i.e. pre-solution activity of gathering data for use in the claimed process. The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
The claim recites the additional elements:
a first response from the generative machine learning model… the first response identifying the first function and being provided by the generative machine learning model
a second response from the generative machine learning model received after updating the prompt data to include the first output data
The generation of responses by a generative machine learning model are recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f))
The claim recite the additional element:
causing presentation of at least one of the first output data or the second output data in the user interface associated with the digital assistant
These limitations amount to extra solution activity because it is a mere nominal or tangential addition to the claim, amounting to mere data output (see MPEP 2106.05(g)). The courts have similarly found limitations directed to displaying a result, recited at a high level of generality, to be well-understood, routine, and conventional. See (MPEP 2106.05(d)(II), "presenting offers and gathering statistics.", “determining an estimated outcome and setting a price”)
Accordingly, at Step 2B the additional elements individually or in combination do not amount to significantly more than the judicial exception.
Claim 2:
With respect to claim 2, the claim depends upon claim 1. The analysis of claim 1 is incorporated herein by reference.
Step 2A, Prong 1:
The claim recites:
wherein the first set of functions is selected from among the plurality of functions supported by the digital assistant based on at least one of the user input, a user profile of the user, previous interactions with the digital assistant, or function dependencies within the set of function (mental process; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses a judgement to select a set of functions from among a plurality of functions supported by the digital assistant based on at least one of the user input, a user profile of the user, previous interactions with the digital assistant, or function dependencies)
Step 2A, Prong 2:
The claim fails to recite additional elements considered under Step 2A, Prong 2.
Step 2B:
The claim fails to recite additional elements considered under Step 2B.
Claim 3:
With respect to claim 3, the claim depends upon claim 1. The analysis of claim 1 is incorporated herein by reference.
Step 2A, Prong 1:
The claim is directed toward abstract idea identified with respect to claim 1.
Step 2A, Prong 2:
The judicial exception is not integrated into a practical application.
The claim recites the additional elements:
wherein the at least one function dependency between the first function and the second function indicates that the first function is a helper function in relation to the second function, and the second response identifies the second function and includes at least a subset of the first output data as one or more parameter values for the second function
The additional element amounts to a data gathering step recited at a high level of generality and amounts to extra-solution activity of receiving data i.e. pre-solution activity of gathering data for use in the claimed process. The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
Accordingly, at Step 2A, prong two, the additional elements individually or in combination do no integrate the judicial exception into a practical application.
Step 2B:
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception.
The claim recites the additional elements:
wherein the at least one function dependency between the first function and the second function indicates that the first function is a helper function in relation to the second function, and the second response identifies the second function and includes at least a subset of the first output data as one or more parameter values for the second function
The additional element amounts to a data gathering step recited at a high level of generality and amounts to extra-solution activity of receiving data i.e. pre-solution activity of gathering data for use in the claimed process. The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
Accordingly, at Step 2B the additional elements individually or in combination do not amount to significantly more than the judicial exception.
Claim 4:
With respect to claim 4, the claim depends upon claim 1. The analysis of claim 1 is incorporated herein by reference.
Step 2A, Prong 1:
The claim is directed toward the abstract idea identified with respect to claim 1.
Step 2A, Prong 2:
The judicial exception is not integrated into a practical application.
The claim recites the additional elements:
maintaining, for a digital conversation between the user and the digital assistant, model-accessible data and non-model accessible data, the model-accessible data comprising the user input and function data, and the non-model-accessible data comprising technical context data
The additional elements of maintaining (storing) data is recited at a high level of generality and amounts to extra-solution activity of storing data for use in the claimed process. The courts have found limitations directed to storing information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
Accordingly, at Step 2A, prong two, the additional elements individually or in combination do no integrate the judicial exception into a practical application.
Step 2B:
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception.
The claim recites the additional elements:
maintaining, for a digital conversation between the user and the digital assistant, model-accessible data and non-model accessible data, the model-accessible data comprising the user input and function data, and the non-model-accessible data comprising technical context data
The additional elements of maintaining (storing) data is recited at a high level of generality and amounts to extra-solution activity of storing data for use in the claimed process. The courts have found limitations directed to storing information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
Accordingly, at Step 2B the additional elements individually or in combination do not amount to significantly more than the judicial exception.
Claim 5:
With respect to claim 5, the claim depends upon claim 4. The analysis of claim 4 is incorporated herein by reference.
Step 2A, Prong 1:
The claim recites:
identifying a context dependency of the parameter and in response to identifying the context dependency, accessing the non-model-accessible data to obtain a parameter value for the parameter from the technical context data (mental process; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses an observation to identify context dependency data and based on this data (evaluation) accessing a non-model-accessible data to obtain a parameter value)
Step 2A, Prong 2:
The claim fails to recite additional elements considered under Step 2A, Prong 2.
Step 2B:
The claim fails to recite additional elements considered under Step 2B.
Claim 6:
With respect to claim 6, the claim depends upon claim 4. The analysis of claim 4 is incorporated herein by reference.
Step 2A, Prong 1:
The claim recites:
detecting that a parameter value for the parameter is not available within the technical context data of the non-model-accessible data (mental process; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses a judgement to detect that the parameter value is not available within the technical context data of the non-model-accessible data)
in response to detecting that the parameter value for the parameter is not available within the technical context data, designating, in the function data, the parameter as a mandatory model-obtainable parameter (mental process; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses a judgement to designate the parameter as a mandatory model-obtainable parameter)
Step 2A, Prong 2:
The claim fails to recite additional elements considered under Step 2A, Prong 2.
Step 2B:
The claim fails to recite additional elements considered under Step 2B.
Claim 7:
With respect to claim 7, the claim depends upon claim 4. The analysis of claim 4 is incorporated herein by reference.
Step 2A, Prong 1:
The claim recites:
detecting that a parameter value for the parameter is available within the technical context data for the non-model-accessible data (mental process; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses a judgement to detect that the parameter value is available within the technical context data of the non-model-accessible data)
in response to detecting that the parameter value for the parameter is available within the technical context data, designating, in the function data, the parameter as an optional model-obtainable parameter (mental process; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses a judgement to designate the parameter as an optional model-obtainable parameter)
Step 2A, Prong 2:
The claim fails to recite additional elements considered under Step 2A, Prong 2.
Step 2B:
The claim fails to recite additional elements considered under Step 2B.
Claim 8:
With respect to claim 8, the claim depends upon claim 1. The analysis of claim 1 is incorporated herein by reference.
Step 2A, Prong 1:
The claim is directed toward the abstract idea identified with respect to claim 1.
Step 2A, Prong 2:
The judicial exception is not integrated into a practical application.
The claim recites the additional elements:
wherein the prompt data further comprises at least one of a role definition for the generative machine learning model, a conversation history, or additional function data comprising a natural language description of one or more characteristics of each function in the set of functions
The additional element amounts to a data gathering step recited at a high level of generality and amounts to extra-solution activity of receiving data i.e. pre-solution activity of gathering data for use in the claimed process. The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
Accordingly, at Step 2A, prong two, the additional elements individually or in combination do no integrate the judicial exception into a practical application.
Step 2B:
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception.
The claim recites the additional elements:
wherein the prompt data further comprises at least one of a role definition for the generative machine learning model, a conversation history, or additional function data comprising a natural language description of one or more characteristics of each function in the set of functions
The additional element amounts to a data gathering step recited at a high level of generality and amounts to extra-solution activity of receiving data i.e. pre-solution activity of gathering data for use in the claimed process. The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
Accordingly, at Step 2B the additional elements individually or in combination do not amount to significantly more than the judicial exception.
Claim 9:
With respect to claim 9, the claim depends upon claim 1. The analysis of claim 1 is incorporated herein by reference.
Step 2A, Prong 1:
The claim is directed toward the abstract idea identified with respect to claim 1.
Step 2A, Prong 2:
The judicial exception is not integrated into a practical application.
The claim recites the additional elements:
wherein the at least one function dependency comprises a first function dependency of a plurality of function dependencies in the function data, and the plurality of function dependencies is represented via a dependency relationship data structure
The additional element amounts to a data gathering step recited at a high level of generality and amounts to extra-solution activity of receiving data i.e. pre-solution activity of gathering data for use in the claimed process. The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
Accordingly, at Step 2A, prong two, the additional elements individually or in combination do no integrate the judicial exception into a practical application.
Step 2B:
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception.
The claim recites the additional elements:
wherein the at least one function dependency comprises a first function dependency of a plurality of function dependencies in the function data, and the plurality of function dependencies is represented via a dependency relationship data structure
The additional element amounts to a data gathering step recited at a high level of generality and amounts to extra-solution activity of receiving data i.e. pre-solution activity of gathering data for use in the claimed process. The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
Accordingly, at Step 2B the additional elements individually or in combination do not amount to significantly more than the judicial exception.
Claim 10:
With respect to claim 10, the claim depends upon claim 9. The analysis of claim 9 is incorporated herein by reference.
Step 2A, Prong 1:
The claim is directed toward the abstract idea identified with respect to claim 9.
Step 2A, Prong 2:
The judicial exception is not integrated into a practical application.
The claim recites the additional elements:
wherein the prompt data comprises an instruction to the generative machine learning model to adhere to one or more relations defined by the dependency relationship data structure
The additional element amounts to a data gathering step recited at a high level of generality and amounts to extra-solution activity of receiving data i.e. pre-solution activity of gathering data for use in the claimed process. The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
Accordingly, at Step 2A, prong two, the additional elements individually or in combination do no integrate the judicial exception into a practical application.
Step 2B:
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception.
The claim recites the additional elements:
wherein the prompt data comprises an instruction to the generative machine learning model to adhere to one or more relations defined by the dependency relationship data structure
The additional element amounts to a data gathering step recited at a high level of generality and amounts to extra-solution activity of receiving data i.e. pre-solution activity of gathering data for use in the claimed process. The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
Accordingly, at Step 2B the additional elements individually or in combination do not amount to significantly more than the judicial exception.
Claim 11:
With respect to claim 11, the claim depends upon claim 1. The analysis of claim 1 is incorporated herein by reference.
Step 2A, Prong 1:
The claim is directed toward the abstract idea identified with respect to claim 1.
Step 2A, Prong 2:
The judicial exception is not integrated into a practical application.
The claim recites the additional elements:
wherein the first response comprises a first function call associated with the first function, the second response comprises a second function call associated with the second function, the first response comprises one or more first parameter values for one or more parameters of the first function, and the second response comprises one or more second parameter values for one or more parameters of the second function
The generation of responses by a generative machine learning model are recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f))
Accordingly, at Step 2A, prong two, the additional elements individually or in combination do no integrate the judicial exception into a practical application.
Step 2B:
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception.
The claim recites the additional elements:
wherein the first response comprises a first function call associated with the first function, the second response comprises a second function call associated with the second function, the first response comprises one or more first parameter values for one or more parameters of the first function, and the second response comprises one or more second parameter values for one or more parameters of the second function
The generation of responses by a generative machine learning model are recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f))
Accordingly, at Step 2B the additional elements individually or in combination do not amount to significantly more than the judicial exception.
Claim 12:
With respect to claim 12, the claim depends upon claim 1. The analysis of claim 1 is incorporated herein by reference.
Step 2A, Prong 1:
The claim recites:
identifying, in a conversation context for a digital conversation between the user and the digital assistant, a function… the selected function being at least one of the first function and the second function (mental process; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses an observation to identify a function between the first and second functions in a conversation context)
identifying, in the conversation context, one or more new or modified parameter values provided by the user for one or more parameters of the selected function (mental process; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses an observation to identify one or more new modified parameter values provided by the user)
invoking a validation function to validate the one or more new modified parameters values against one or more predefined criteria (mental process; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses an evaluation to determine the validity of the new or modified parameters based upon a validation function)
Step 2A, Prong 2:
The judicial exception is not integrated into a practical application.
The claim recites the additional elements:
the generative machine learning model
The generation of responses by a generative machine learning model are recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f))
Accordingly, at Step 2A, prong two, the additional elements individually or in combination do no integrate the judicial exception into a practical application.
Step 2B:
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception.
The claim recites the additional elements:
the generative machine learning model
The generation of responses by a generative machine learning model are recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f))
Accordingly, at Step 2B the additional elements individually or in combination do not amount to significantly more than the judicial exception.
Claim 13:
With respect to claim 13, the claim depends upon claim 12. The analysis of claim 12 is incorporated herein by reference.
Step 2A, Prong 1:
The claim recites:
detecting, after the invoking of the validation function, a failed validation (mental process; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses an observation to detect a failed validation)
in response to detecting the failed validation, generating additional prompt data comprising details of the failed validation (mental process; As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses an evaluation to generate additional prompt data comprising details of the failed validation)
Step 2A, Prong 2:
The judicial exception is not integrated into a practical application.
The claim recites the additional element:
providing the additional prompt data
The additional element amounts to a data gathering step recited at a high level of generality and amounts to extra-solution activity of receiving data i.e. pre-solution activity of gathering data for use in the claimed process. The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
The claim recites the additional element:
the generative machine learning model obtain a third response, the third response comprising a user-directed message related to the failed validation
The generation of responses by a generative machine learning model are recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f))
The claim recite the additional element:
causing presentation of third output data comprising the user-directed message in the user interface associated with the digital assistant
These limitations amount to extra solution activity because it is a mere nominal or tangential addition to the claim, amounting to mere data output (see MPEP 2106.05(g)). The courts have similarly found limitations directed to displaying a result, recited at a high level of generality, to be well-understood, routine, and conventional. See (MPEP 2106.05(d)(II), "presenting offers and gathering statistics.", “determining an estimated outcome and setting a price”)
Accordingly, at Step 2A, prong two, the additional elements individually or in combination do no integrate the judicial exception into a practical application.
Step 2B:
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception.
The claim recites the additional element:
providing the additional prompt data
The additional element amounts to a data gathering step recited at a high level of generality and amounts to extra-solution activity of receiving data i.e. pre-solution activity of gathering data for use in the claimed process. The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
The claim recites the additional element:
the generative machine learning model obtain a third response, the third response comprising a user-directed message related to the failed validation
The generation of responses by a generative machine learning model are recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f))
The claim recite the additional element:
causing presentation of third output data comprising the user-directed message in the user interface associated with the digital assistant
These limitations amount to extra solution activity because it is a mere nominal or tangential addition to the claim, amounting to mere data output (see MPEP 2106.05(g)). The courts have similarly found limitations directed to displaying a result, recited at a high level of generality, to be well-understood, routine, and conventional. See (MPEP 2106.05(d)(II), "presenting offers and gathering statistics.", “determining an estimated outcome and setting a price”)
Accordingly, at Step 2B the additional elements individually or in combination do not amount to significantly more than the judicial exception.
Claim 14:
With respect to claim 14, the claim depends upon claim 1. The analysis of claim 1 is incorporated herein by reference.
Step 2A, Prong 1:
The claim is directed toward abstract idea identified with respect to claim 1.
Step 2A, Prong 2:
The judicial exception is not integrated into a practical application.
The claim recites the additional element:
prior to invoking the second function, causing presentation of a user-selectable approval element in the user interface together with a parameter value for one or more parameters of the second function
These limitations amount to extra solution activity because it is a mere nominal or tangential addition to the claim, amounting to mere data output (see MPEP 2106.05(g)). The courts have similarly found limitations directed to displaying a result, recited at a high level of generality, to be well-understood, routine, and conventional. See (MPEP 2106.05(d)(II), "presenting offers and gathering statistics.", “determining an estimated outcome and setting a price”)
The claim recites the additional element:
receiving a user selection of the user-selectable approval element, wherein the second function is invoked in response to receiving the user selection of the user-selectable approval element
The additional element amounts to a data gathering step recited at a high level of generality and amounts to extra-solution activity of receiving data i.e. pre-solution activity of gathering data for use in the claimed process. The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
Accordingly, at Step 2A, prong two, the additional elements individually or in combination do no integrate the judicial exception into a practical application.
Step 2B:
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception.
The claim recites the additional element:
prior to invoking the second function, causing presentation of a user-selectable approval element in the user interface together with a parameter value for one or more parameters of the second function
These limitations amount to extra solution activity because it is a mere nominal or tangential addition to the claim, amounting to mere data output (see MPEP 2106.05(g)). The courts have similarly found limitations directed to displaying a result, recited at a high level of generality, to be well-understood, routine, and conventional. See (MPEP 2106.05(d)(II), "presenting offers and gathering statistics.", “determining an estimated outcome and setting a price”)
The claim recites the additional element:
receiving a user selection of the user-selectable approval element, wherein the second function is invoked in response to receiving the user selection of the user-selectable approval element
The additional element amounts to a data gathering step recited at a high level of generality and amounts to extra-solution activity of receiving data i.e. pre-solution activity of gathering data for use in the claimed process. The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
Accordingly, at Step 2B the additional elements individually or in combination do not amount to significantly more than the judicial exception.
Claim 15:
With respect to claim 15, the claim recites the limitations substantially similar to those in claim 1. The analysis of claim 1 is incorporated herein by reference.
Claim 16:
With respect to claim 16, the claim recites the limitations substantially similar to those in claim 4. The analysis of claim 4 is incorporated herein by reference.
Claim 17:
With respect to claim 17, the claim recites the limitations substantially similar to those in claim 5. The analysis of claim 5 is incorporated herein by reference.
Claim 18:
With respect to claim 18, the claim recites the limitations substantially similar to those in claim 1. The analysis of claim 1 is incorporated herein by reference.
Claim 19:
With respect to claim 19, the claim recites the limitations substantially similar to those in claim 4. The analysis of claim 4 is incorporated herein by reference.
Claim 20:
With respect to claim 20, the claim recites the limitations substantially similar to those in claim 5. The analysis of claim 5 is incorporated herein by reference.
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-2, 4-5, and 8-20 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Baldua et al. (US 2025/0110957, filed 31 January 2024, hereafter Baldua).
As per independent claim 1, Baldua discloses a system comprising:
at least one memory that stores instructions (paragraph 0157: Here, a system includes memory)
one or more processors configured by the instructions to perform operations (paragraph 0206: Here, a processing device includes a processor for performing operations) comprising:
selecting a set of functions from among a plurality of functions supported by a digital assistant (paragraph 0022: Here, based upon a user input to a prompt, the large language model automatically selects functions for determining filters and facets to be included in executing the query)
providing prompt data to a generative machine learning model, the prompt data comprising user input and function data (paragraphs 0022-0024: Here, a user provides an natural language input to a prompt, such as “fortune 500 companies on the west coast.” This input is provided to the large language model)
the user input being received from a user via a user interface of the digital assistant (Figures 1A-1B, item 102: Here a user enters a query through an application running on a client device. This application may include a front end user interface (paragraph 0045))
and the function data identifying the set of functions and comprising dependency data that includes at least one function dependency between a first function and a second function of the set of functions (paragraph 0101: Here, a function dependency component formulates a function dependency query including functions as parameters. This query is executed against a function dependency graph to determine relevant functions based on the graph)
invoking, based on a first response from the generative machine learning model, the first function to obtain first output data, the first response identifying the first function and being provided by the generative machine learning model based on inclusion of the at least one function dependency in the prompt data (paragraphs 0101-0104: Here, based upon the determination that function dependencies exist for a first function, the large language model reads and processes the plan generation prompt wherein the large language model is constrained to the relevant possible functions, possible resources, and function dependency data (paragraph 0103))
invoking, based on a second response from the generative machine learning model received after updating the prompt data to include the first output data, the second function to obtain second output data (paragraph 0103: Here, based upon the determination that function dependencies exist for a first function, the large language model reads and processes the plan generation prompt wherein the large language model is constrained to the relevant possible functions, possible resources, and function dependency data)
causing presentation of at least one of the first output data or the second output data in the user interface associated with the digital assistant (Figures 1A-1B and Figure 7B; paragraphs 0101-0107 and 0187: Here, based upon the determination of function dependencies (second response), the prompt is updated to include the initial function and any dependent functions for generating an output using the LLM. Additionally, output may be presented to the user indicating results, a restatement of the original input, facets used in generating the output, and a feedback mechanism (Figure 1, items 184 and 186))
As per dependent claim 2, Baldua discloses wherein the set of functions is selected from among the plurality of functions supported by the digital assistant based on at least one of the user input, a user profile of the user, previous interactions with the digital assistant, or function dependencies within the set of functions (paragraphs 0101-0104: Here, based upon the determination that function dependencies exist for a first function, the large language model reads and processes the plan generation prompt wherein the large language model is constrained to the relevant possible functions, possible resources, and function dependency data (paragraph 0103)).
As per dependent claim 4, Baldua discloses maintaining, for a digital conversation between the user and the digital assistant, model-accessible data and non-model accessible data, the model accessible data comprising the user input and the function data (paragraphs 0101-0104: Here, user inputs and function dependencies for the LLM are maintained for generating a conversation between the user and digital assistant (Figure 1B)), and the non-model-accessible data comprising technical context data (paragraph 0052: Here, context data and a set of heuristics may be applied to the user input instead of formulating a prompt using the LLM to respond to user input).
As per dependent claim 5, Baldua discloses wherein the first function and the second function each has one or more parameters, the operations further comprising, for a parameter of the one or more parameters of the first function or the second function:
identify a context dependency of the parameter (paragraph 0170: Here, contextual data associated with the first query. This contextual data can include information about the user’s previous interactions with the user interface and information about search results to refine the search query by selecting/deselecting facets/filters)
in response to identifying the context dependency, accessing the non-model-accessible data to obtain a parameter value for the parameter from the technical context data (paragraphs 0101-0104: Here, user inputs and function dependencies for the LLM are maintained for generating a conversation between the user and digital assistant (Figure 1B)), and the non-model-accessible data comprising technical context data (paragraph 0052: Here, context data and a set of heuristics may be applied to the user input instead of formulating a prompt using the LLM to respond to user input)
As per dependent claim 8, Baldua discloses wherein the prompt data further comprises at least one of a role definition for the generative machine learning model, a conversation history (paragraph 0170: Here, contextual data associated with the first query. This contextual data can include information about the user’s previous interactions with the user interface and information about search results to refine the search query by selecting/deselecting facets/filters), or additional function data comprising a natural language description of one or more characteristics of each function in the set of functions.
As per dependent claim 9, Baldua discloses wherein the at least one function dependency comprises a first function dependency of a plurality of function dependencies in the function data, and the plurality of function dependencies is represented via a dependency relationship data structure functions (paragraphs 0101-0104: Here, based upon the determination that function dependencies exist for a first function, the large language model reads and processes the plan generation prompt wherein the large language model is constrained to the relevant possible functions, possible resources, and function dependency data (paragraph 0103). These dependencies are stored in a function dependency graph (paragraph 0101)).
As per dependent claim 10, Baldua discloses wherein the prompt data comprises an instruction to the generative machine learning model to adhere to one or more relations defined by the dependency relationship data structure (paragraphs 0101-0104: Here, based upon the determination that function dependencies exist for a first function, the large language model reads and processes the plan generation prompt wherein the large language model is constrained to the relevant possible functions, possible resources, and function dependency data (paragraph 0103). These dependencies are stored in a function dependency graph (paragraph 0101)).
As per dependent claim 11, Baldua discloses wherein the first response comprises a first function call associated with the first function, the second response comprises a second function call associated with the second function, the first response comprises one or more first parameter values for one or more parameters of the first function, and the second response comprises one or more second parameters for one or more parameters of the second function (Figure 3; paragraphs 0096-0097: Here, a function library contains a plurality of functions, including Function1, Function 2, to FunctionN. Each of these functions includes parameters and are invoked based upon the query. These parameters are passed to the function and values are returned from the function to configure the Plan Generation Prompt (item 304)).
As per dependent claim 12, Baldua discloses:
identifying, in a conversation context for a digital conversation between the user and the digital assistant, a function selected by the generative machine learning mode, the selected function being at least one of the first function or the second function (paragraph 0170: Here, contextual data associated with the first query. This contextual data can include information about the user’s previous interactions with the user interface and information about search results to refine the search query by selecting/deselecting facets/filters)
identifying, in the conversation context, one or more new or modified parameter values provided by the user for one or more parameters of the selected function (Figures 1A-1B: Here, the query has been updated to more clearly define the search parameters. In the Dynamic Query Planning System (item 110) the Input Classification (item 168) and Plan Generation Prompt (172) are changed to reflect the change in parameters)
invoking a validation function to validate the one or more new or modified parameter values against one or more predefined criteria (Figure 1B; paragraph 0082: Here, a user is provided with a feedback mechanism (item 190) to provide validation of the results for inclusion in context data for subsequent interactions)
As per dependent claim 13, Baldua discloses:
detecting, after the invoking of the validation function, a failed validation (paragraph 0082: Here, a click on the thumbs-down feedback mechanism is received)
in response to detecting the failed validation, generating additional prompt data comprising details of the failed validation (paragraph 0082: Here, a subsequent query iteration is performed by modifying the query to unselect applied facets)
providing the additional prompt data to the generative machine learning model to obtain a third response, the third response comprising a user-directed message related to the failed validation (paragraph 0082: Here, a subsequent query iteration is performed by modifying the query to unselect applied facets)
causing the presentation of third output data comprising the user-directed message in the user interface with the digital assistant (paragraph 0082: Here, a subsequent query iteration is performed by modifying the query to unselect applied facets for display via the user interface)
As per dependent claim 14, Baldua discloses:
prior to invoking the second function, causing presentation of a user-selectable approval element in the user interface together with a parameter value for one or more parameters of the second function (paragraph 0082: Here, a subsequent query iteration is performed by modifying the query to selected applied facets)
receiving a user selection of the user-selectable approval element, wherein the second function is invoked in response to receiving the user selection of the user-selectable approval element (paragraph 0082: Here, a subsequent query iteration is performed by modifying the query to unselect applied facets for display via the user interface)
With respect to claims 15-17, the claims recite the limitations substantially similar to those in claims 1 and 4-5, respectively. Claims 15-17 are similarly rejected.
With respect to claims 18-20, the claims recite the limitations substantially similar to those in claims 1 and 4-5, respectively. Claims 18-20 are similarly rejected.
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.
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 3 is rejected under 35 U.S.C. 103 as being unpatentable over Baldua and further in view of Patry et al. (US 2023/0297877, published 21 September 2023, hereafter Patry).
As per dependent claim 3, Baldua discloses the limitations similar to those in claim 1, and the same rejection is incorporated herein. Baldua fails to specifically disclose:
wherein the at least one function dependency between the first function and the second function indicates that the first function is a helper function in relation to the second function, and the second response identifies the second function and includes at least a subset of the first output data as one or more parameter values of the second function
However, Patry, which is analogous to the claimed invention because it is directed toward machine learning, discloses:
wherein the at least one function dependency between the first function and the second function indicates that the first function is a helper function in relation to the second function, and the second response identifies the second function and includes at least a subset of the first output data as one or more parameter values of the second function (Figure 3; paragraphs 0065-0067: Here, an activation function is a helper function that provides outputs to another function)
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Patry with Baldua, with a reasonable expectation of success, as it would have allowed for sharing interactions between multiple functions for improved processing (Patry: paragraph 0065).
Claims 6-7 are rejected under 35 U.S.C. 103 as being unpatentable over Baldua and further in view of Morgan et al. (US 2021/0158456, published 27 May 2021, hereafter Morgan).
As per dependent claim 6, Baldua discloses the limitations similar to those in claim 4, and the same rejection is incorporated herein. Baldua discloses wherein the first function and the second function each has one or more parameters (Figure 1B). But, Baldua fails to specifically disclose:
detecting that a parameter value for the parameter is not available within the technical context data of the non-model-accessible data
in response to detecting that the parameter value for the parameter is not available within the technical context data, designating, in the function data, the parameter as a mandatory model-obtainable parameter
However, Morgan, which is analogous to the claimed invention because it is directed toward a user interface for prompting users, discloses:
detecting that a parameter value for the parameter is not available within the technical context data of the non-model-accessible data (paragraph 0002: Here, it is determined that ta parameter is not available (missing) and indicating the parameter as required)
in response to detecting that the parameter value for the parameter is not available within the technical context data, designating, in the function data, the parameter as a mandatory model-obtainable parameter (paragraph 0002: Here, it is determined that a parameter is not available (missing) and indicating the parameter as required. Based upon this requirement, the user is queried for the parameter value)
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Morgan with Baldua, with a reasonable expectation of success, as it would have allowed for identifying a required parameter and obtaining the parameter information to facilitate completing the process (Morgan: paragraph 0002).
As per dependent claim 7, Baldua discloses the limitations similar to those in claim 4, and the same rejection is incorporated herein. Baldua discloses wherein the first function and the second function each has one or more parameters (Figure 1B). But, Baldua fails to specifically disclose:
detecting that a parameter value for the parameter is available within the technical context data of the non-model-accessible data
in response to detecting that the parameter value for the parameter is available within the technical context data, designating, in the function data, the parameter as an optional model-obtainable parameter
However, Morgan, which is analogous to the claimed invention because it is directed toward a user interface for prompting users, discloses:
detecting that a parameter value for the parameter is available within the technical context data of the non-model-accessible data (paragraph 0002: Here, it is determined that ta parameter is not available (missing) and indicating the parameter as required. Conversely, other parameters are identified as available)
in response to detecting that the parameter value for the parameter is available within the technical context data, designating, in the function data, the parameter as an optional model-obtainable parameter (paragraph 0002: Here, it is determined that a parameter is available. Based upon this determination, the user is not queried for the parameter value. The examiner interprets the absence of a user query to indicate that obtaining the parameter value is optional)
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Morgan with Baldua, with a reasonable expectation of success, as it would have allowed for identifying a required and optional parameter and obtaining the parameter information to facilitate completing the process (Morgan: paragraph 0002).
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1-2, 4-5, and 8-20 are provisionally rejected on the ground of nonstatutory double patenting as being unpatentable over claim 1 of co-pending Application No. No. 18/538956 (US 2025/0199757 (provided by application on IDS filed 8 October 2025), hereafter “the co-pending application”) in view of Baldua.
Present Application (NOTE: limitations in bold italics are not taught by the co-pending application):
Co-pending Application:
1. A system comprising:
1. A system comprising:
at least one memory that stores instructions
at least one memory that stores instructions
one or more processors configured by the instructions to perform operations comprising:
One or more processors configured by the instructions to perform operations comprising
selecting a set of functions from among a plurality of functions supported by a digital assistant
providing prompt data to a generative machine learning model, the prompt data comprising user input and function data, the user input being received from a user via a user interface of the digital assistant, and the function data identifying the set of functions and comprising dependency data that includes at least one function dependency between a first function and a second function of the set of functions
providing prompt data to a generative machine learning model to obtain a response, the prompt data comprising user input and function data, the user input received via a user interface associated with a digital assistant, and function data identifying a plurality of functions
invoking, based on a first response from the generative machine learning model, the first function to obtain first output data, the first response identifying the first function and being provided by the generative machine learning model based on inclusion of the at least one function dependency in the prompt data
detecting that the response includes a function identifier associated with a function from among the plurality of functions;
in response to detecting that the response includes the function identifier, invoking the function to obtain output data
invoking, based on a second response from the generative machine learning model received after updating the prompt data to include the first output data, the second function to obtain second output data
causing presentation of at least one of the first output data or the second output data in the user interface associated with the digital assistant
causing presentation of the output data in the user interface associated with the digital assistant
With respect to claim 1, the co-pending application discloses the limitations above (see table). However, the co-pending application fails to specifically disclose:
dependency data that includes at least one function dependency between a first function and a second function of the set of functions
invoking, based on a second response from the generative machine learning model received after updating the prompt data to include the first output data, the second function to obtain second output data
However, Baldua, which is analogous to the claimed invention because it is directed toward generating prompts for large language models, discloses:
dependency data that includes at least one function dependency between a first function and a second function of the set of functions (paragraph 0101: Here, a function dependency component formulates a function dependency query including functions as parameters. This query is executed against a function dependency graph to determine relevant functions based on the graph)
invoking, based on a second response from the generative machine learning model received after updating the prompt data to include the first output data, the second function to obtain second output data (Figure 7B; paragraphs 0101-0107 and 0187: Here, based upon the determination of function dependencies (second response), the prompt is updated to include the initial function and any dependent functions for generating an output using the LLM)
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Baldua with the co-pending application, with a reasonable expectation of success, as it would have allowed for identifying and using dependent functions within a large language model (Baldua: paragraphs 0101-0102).
As per dependent claim 2, the co-pending application and Baldua disclose the limitations similar to those in claim 1, and the same rejection is incorporated herein. Baldua discloses wherein the set of functions is selected from among the plurality of functions supported by the digital assistant based on at least one of the user input, a user profile of the user, previous interactions with the digital assistant, or function dependencies within the set of functions (paragraphs 0101-0104: Here, based upon the determination that function dependencies exist for a first function, the large language model reads and processes the plan generation prompt wherein the large language model is constrained to the relevant possible functions, possible resources, and function dependency data (paragraph 0103)).
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Baldua with the co-pending application, with a reasonable expectation of success, as it would have allowed for identifying and using dependent functions within a large language model (Baldua: paragraphs 0101-0102).
As per dependent claim 4, the co-pending application and Baldua disclose the limitations similar to those in claim 1, and the same rejection is incorporated herein. Baldua discloses maintaining, for a digital conversation between the user and the digital assistant, model-accessible data and non-model accessible data, the model accessible data comprising the user input and the function data (paragraphs 0101-0104: Here, user inputs and function dependencies for the LLM are maintained for generating a conversation between the user and digital assistant (Figure 1B)), and the non-model-accessible data comprising technical context data (paragraph 0052: Here, context data and a set of heuristics may be applied to the user input instead of formulating a prompt using the LLM to respond to user input).
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Baldua with the co-pending application, with a reasonable expectation of success, as it would have allowed for identifying and using dependent functions within a large language model (Baldua: paragraphs 0101-0102).
As per dependent claim 5, the co-pending application and Baldua disclose the limitations similar to those in claim 4, and the same rejection is incorporated herein. Baldua discloses wherein the first function and the second function each has one or more parameters, the operations further comprising, for a parameter of the one or more parameters of the first function or the second function:
identify a context dependency of the parameter (paragraph 0170: Here, contextual data associated with the first query. This contextual data can include information about the user’s previous interactions with the user interface and information about search results to refine the search query by selecting/deselecting facets/filters)
in response to identifying the context dependency, accessing the non-model-accessible data to obtain a parameter value for the parameter from the technical context data (paragraphs 0101-0104: Here, user inputs and function dependencies for the LLM are maintained for generating a conversation between the user and digital assistant (Figure 1B)), and the non-model-accessible data comprising technical context data (paragraph 0052: Here, context data and a set of heuristics may be applied to the user input instead of formulating a prompt using the LLM to respond to user input)
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Baldua with the co-pending application, with a reasonable expectation of success, as it would have allowed for identifying and using dependent functions within a large language model (Baldua: paragraphs 0101-0102).
As per dependent claim 8, the co-pending application and Baldua disclose the limitations similar to those in claim 1, and the same rejection is incorporated herein. Baldua discloses wherein the prompt data further comprises at least one of a role definition for the generative machine learning model, a conversation history (paragraph 0170: Here, contextual data associated with the first query. This contextual data can include information about the user’s previous interactions with the user interface and information about search results to refine the search query by selecting/deselecting facets/filters), or additional function data comprising a natural language description of one or more characteristics of each function in the set of functions.
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Baldua with the co-pending application, with a reasonable expectation of success, as it would have allowed for identifying and using dependent functions within a large language model (Baldua: paragraphs 0101-0102).
As per dependent claim 9, the co-pending application and Baldua disclose the limitations similar to those in claim 1, and the same rejection is incorporated herein. Baldua discloses wherein the at least one function dependency comprises a first function dependency of a plurality of function dependencies in the function data, and the plurality of function dependencies is represented via a dependency relationship data structure functions (paragraphs 0101-0104: Here, based upon the determination that function dependencies exist for a first function, the large language model reads and processes the plan generation prompt wherein the large language model is constrained to the relevant possible functions, possible resources, and function dependency data (paragraph 0103). These dependencies are stored in a function dependency graph (paragraph 0101)).
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Baldua with the co-pending application, with a reasonable expectation of success, as it would have allowed for identifying and using dependent functions within a large language model (Baldua: paragraphs 0101-0102).
As per dependent claim 10, the co-pending application and Baldua disclose the limitations similar to those in claim 9, and the same rejection is incorporated herein. Baldua discloses wherein the prompt data comprises an instruction to the generative machine learning model to adhere to one or more relations defined by the dependency relationship data structure (paragraphs 0101-0104: Here, based upon the determination that function dependencies exist for a first function, the large language model reads and processes the plan generation prompt wherein the large language model is constrained to the relevant possible functions, possible resources, and function dependency data (paragraph 0103). These dependencies are stored in a function dependency graph (paragraph 0101)).
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Baldua with the co-pending application, with a reasonable expectation of success, as it would have allowed for identifying and using dependent functions within a large language model (Baldua: paragraphs 0101-0102).
As per dependent claim 11, the co-pending application and Baldua disclose the limitations similar to those in claim 1, and the same rejection is incorporated herein. Baldua discloses wherein the first response comprises a first function call associated with the first function, the second response comprises a second function call associated with the second function, the first response comprises one or more first parameter values for one or more parameters of the first function, and the second response comprises one or more second parameters for one or more parameters of the second function (Figure 3; paragraphs 0096-0097: Here, a function library contains a plurality of functions, including Function1, Function 2, to FunctionN. Each of these functions includes parameters and are invoked based upon the query. These parameters are passed to the function and values are returned from the function to configure the Plan Generation Prompt (item 304)).
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Baldua with the co-pending application, with a reasonable expectation of success, as it would have allowed for identifying and using dependent functions within a large language model (Baldua: paragraphs 0101-0102).
As per dependent claim 12, the co-pending application and Baldua disclose the limitations similar to those in claim 1, and the same rejection is incorporated herein. Baldua discloses:
identifying, in a conversation context for a digital conversation between the user and the digital assistant, a function selected by the generative machine learning mode, the selected function being at least one of the first function or the second function (paragraph 0170: Here, contextual data associated with the first query. This contextual data can include information about the user’s previous interactions with the user interface and information about search results to refine the search query by selecting/deselecting facets/filters)
identifying, in the conversation context, one or more new or modified parameter values provided by the user for one or more parameters of the selected function (Figures 1A-1B: Here, the query has been updated to more clearly define the search parameters. In the Dynamic Query Planning System (item 110) the Input Classification (item 168) and Plan Generation Prompt (172) are changed to reflect the change in parameters)
invoking a validation function to validate the one or more new or modified parameter values against one or more predefined criteria (Figure 1B; paragraph 0082: Here, a user is provided with a feedback mechanism (item 190) to provide validation of the results for inclusion in context data for subsequent interactions)
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Baldua with the co-pending application, with a reasonable expectation of success, as it would have allowed for identifying and using dependent functions within a large language model (Baldua: paragraphs 0101-0102).
As per dependent claim 13, the co-pending application and Baldua disclose the limitations similar to those in claim 12, and the same rejection is incorporated herein. Baldua discloses:
detecting, after the invoking of the validation function, a failed validation (paragraph 0082: Here, a click on the thumbs-down feedback mechanism is received)
in response to detecting the failed validation, generating additional prompt data comprising details of the failed validation (paragraph 0082: Here, a subsequent query iteration is performed by modifying the query to unselect applied facets)
providing the additional prompt data to the generative machine learning model to obtain a third response, the third response comprising a user-directed message related to the failed validation (paragraph 0082: Here, a subsequent query iteration is performed by modifying the query to unselect applied facets)
causing the presentation of third output data comprising the user-directed message in the user interface with the digital assistant (paragraph 0082: Here, a subsequent query iteration is performed by modifying the query to unselect applied facets for display via the user interface)
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Baldua with the co-pending application, with a reasonable expectation of success, as it would have allowed for identifying and using dependent functions within a large language model (Baldua: paragraphs 0101-0102).
As per dependent claim 14, the co-pending application and Baldua disclose the limitations similar to those in claim 12, and the same rejection is incorporated herein. Baldua discloses:
prior to invoking the second function, causing presentation of a user-selectable approval element in the user interface together with a parameter value for one or more parameters of the second function (paragraph 0082: Here, a subsequent query iteration is performed by modifying the query to selected applied facets)
receiving a user selection of the user-selectable approval element, wherein the second function is invoked in response to receiving the user selection of the user-selectable approval element (paragraph 0082: Here, a subsequent query iteration is performed by modifying the query to unselect applied facets for display via the user interface)
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Baldua with the co-pending application, with a reasonable expectation of success, as it would have allowed for identifying and using dependent functions within a large language model (Baldua: paragraphs 0101-0102).
With respect to claims 15-17, the claims recite the limitations substantially similar to those in claims 1 and 4-5, respectively. Claims 15-17 are similarly rejected.
With respect to claims 18-20, the claims recite the limitations substantially similar to those in claims 1 and 4-5, respectively. Claims 18-20 are similarly rejected.
Claim 3 is provisionally rejected on the ground of nonstatutory double patenting as being unpatentable over claim 1 of co-pending application and Baldua in view of Patry.
As per dependent claim 3, the co-pending application and Baldua discloses the limitations similar to those in claim 1, and the same rejection is incorporated herein. The co-pending application fails to specifically disclose:
wherein the at least one function dependency between the first function and the second function indicates that the first function is a helper function in relation to the second function, and the second response identifies the second function and includes at least a subset of the first output data as one or more parameter values of the second function
However, Patry, which is analogous to the claimed invention because it is directed toward machine learning, discloses:
wherein the at least one function dependency between the first function and the second function indicates that the first function is a helper function in relation to the second function, and the second response identifies the second function and includes at least a subset of the first output data as one or more parameter values of the second function (Figure 3; paragraphs 0065-0067: Here, an activation function is a helper function that provides outputs to another function)
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Patry with the co-pending application-Baldua, with a reasonable expectation of success, as it would have allowed for sharing interactions between multiple functions for improved processing (Patry: paragraph 0065).
Claims 6-7 are provisionally rejected on the ground of nonstatutory double patenting as being unpatentable over claim 1 of co-pending application and Baldua in view of Morgan.
As per dependent claim 6, the co-pending application and Baldua disclose the limitations similar to those in claim 4, and the same rejection is incorporated herein. The co-pending application fails to specifically disclose:
the first function and the second function each has one or more parameters
detecting that a parameter value for the parameter is not available within the technical context data of the non-model-accessible data
in response to detecting that the parameter value for the parameter is not available within the technical context data, designating, in the function data, the parameter as a mandatory model-obtainable parameter
Baldua discloses the first function and the second function each has one or more parameters (Figure 3; paragraphs 0096-0097: Here, a function library contains a plurality of functions, including Function1, Function 2, to FunctionN. Each of these functions includes parameters and are invoked based upon the query. These parameters are passed to the function and values are returned from the function to configure the Plan Generation Prompt (item 304)).
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Baldua with the co-pending application, with a reasonable expectation of success, as it would have allowed for identifying and using dependent functions within a large language model (Baldua: paragraphs 0101-0102).
Additionally, Morgan, which is analogous to the claimed invention because it is directed toward a user interface for prompting users, discloses:
detecting that a parameter value for the parameter is not available within the technical context data of the non-model-accessible data (paragraph 0002: Here, it is determined that ta parameter is not available (missing) and indicating the parameter as required)
in response to detecting that the parameter value for the parameter is not available within the technical context data, designating, in the function data, the parameter as a mandatory model-obtainable parameter (paragraph 0002: Here, it is determined that a parameter is not available (missing) and indicating the parameter as required. Based upon this requirement, the user is queried for the parameter value)
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Morgan with the co-pending application-Baldua, with a reasonable expectation of success, as it would have allowed for identifying a required parameter and obtaining the parameter information to facilitate completing the process (Morgan: paragraph 0002).
As per dependent claim 7, the co-pending application and Baldua disclose the limitations similar to those in claim 4, and the same rejection is incorporated herein. The co-pending application fails to specifically disclose:
the first function and the second function each has one or more parameters
detecting that a parameter value for the parameter is available within the technical context data of the non-model-accessible data
in response to detecting that the parameter value for the parameter is available within the technical context data, designating, in the function data, the parameter as an optional model-obtainable parameter
Baldua discloses the first function and the second function each has one or more parameters (Figure 3; paragraphs 0096-0097: Here, a function library contains a plurality of functions, including Function1, Function 2, to FunctionN. Each of these functions includes parameters and are invoked based upon the query. These parameters are passed to the function and values are returned from the function to configure the Plan Generation Prompt (item 304)).
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Baldua with the co-pending application, with a reasonable expectation of success, as it would have allowed for identifying and using dependent functions within a large language model (Baldua: paragraphs 0101-0102).
Additionally, Morgan, which is analogous to the claimed invention because it is directed toward a user interface for prompting users, discloses:
detecting that a parameter value for the parameter is available within the technical context data of the non-model-accessible data (paragraph 0002: Here, it is determined that ta parameter is not available (missing) and indicating the parameter as required. Conversely, other parameters are identified as available)
in response to detecting that the parameter value for the parameter is available within the technical context data, designating, in the function data, the parameter as an optional model-obtainable parameter (paragraph 0002: Here, it is determined that a parameter is available. Based upon this determination, the user is not queried for the parameter value. The examiner interprets the absence of a user query to indicate that obtaining the parameter value is optional)
It would have been obvious to one of ordinary skill in the art at the time of the applicant’s effective filing date to have combined Morgan with the co-pending application-Baldua, with a reasonable expectation of success, as it would have allowed for identifying a required and optional parameter and obtaining the parameter information to facilitate completing the process (Morgan: paragraph 0002).
This is a provisional nonstatutory double patenting rejection.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Qiu et al. (US 12670899): Discloses a digital assistant (column 52, line 52- column 53, line 16) receiving inputs from a user and a LLM generating prompts (Figure 5)
Rongali et al. (US 12632660): Discloses a LLM action resolution component that utilizes various techniques to generate a parameter includes in an actional API call in an LLM (column 37, lines 11-33) on a digital assistant (column 42, lines 28-32)
Boue et al. (US 2025/0315617): Discloses a digital assistant (paragraph 0032) making an API call to an LLM function (paragraph 0048)
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KYLE R STORK whose telephone number is (571)272-4130. The examiner can normally be reached 8am - 2pm; 4pm - 6pm.
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, Omar Fernandez Rivas can be reached at 571/272-2589. 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.
/KYLE R STORK/Primary Examiner, Art Unit 2128
Prosecution Insights